Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/21/88)
Vision-List Digest Wed Apr 20 16:06:24 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
*** Change in VISION LIST moderator
Character recognition
Digitizer boards for Q-bus
contrast and size
Recording Visual Images
------------------------------
Date: Wed, 20 Apr 88 14:42:16 PST
From: Vision-List-Request@ads.com <Vision List moderator>
Subject: *** Change in VISION LIST moderator
To the Readership:
Just to let you know, there has been a change of guard. Tod
Levitt, the moderator, protector, and champion of this Vision List for
the past several years has decided to buy a sailboat and travel around
the world. (Actually, Tod's not REALLY doing that; he just thought a
change in moderatorship was due.) His efforts in expanding the
readership (now into the thousands) have made this List the primary
conversant forum for Vision and Image Processing researchers and
practicians. Tod's presence and valuable input will continue in his
submissions to this List.
The list will continue to operate as before. That is, mail
Vision List submissions to VISION-LIST@ADS.COM. Administrative
mail (e.g., adding/deleting you from the list, problems in receiving
the List) should continue to be directed to VISION-LIST-REQUEST@ADS.COM.
Please notify me of any problems you have; this changeover is likely
to cause at least a few glitches.
Since Tod assumed the moderatorship in 1985, I have been
encouraged at the solidity and diversity of the readership. Readers
vary from newcomers to the field to well-established researchers in
vision and/or image processing. The bulk of the submissions to the
List is made up of seminar announcements, requests for literature, and
specific system questions. This role is important in helping us keep
abreast of the field and it provides us with a rapid way to answer
questions by asking a large group.
Yet, this List is not being utilized to our full advantage.
When I founded this List in 1984, I had hoped there would be more
technical dialogue on vision and IP-related issues. In part, the
historically more limited role of this List is due to the great
diversity in the technical background of the readership and the
chronic time pressues most of us must endure. Even within these
constraints, I believe that submissions to this List can be expanded
in order to substantively address other important issues. I encourage
all of you to consider how you can more effectively use this List and
other readers to solve and discuss common problems and issues.
Comments to me or submitted to the List could get this going.
Phil Kahn
----------------------------------------------------------------------
From: oltz@tcgould.tn.cornell.edu (Michael Oltz)
Date: 23 Mar 88 19:27:08 GMT
Organization: Theory Center, Cornell U., Ithaca NY
Frequently-asked question #487 :-)
What are some good references re character recognition, particularly
re arbitrary typeset fonts? Algorithms requiring training for each
font would be fine, but forgiving algorithms would be helpful too.
Please respond by email and I will summarize.
Mike Oltz oltz@tcgould.tn.cornell.UUCP (607)255-8312
Cornell Computer Services
215 Computing and Communications Center
Ithaca NY 14853
------------------------------
Date: Mon, 11 Apr 88 14:38:18 CDT
From: dyer@cs.wisc.edu (Chuck Dyer)
Subject: Digitizer boards for Q-bus
What vendors sell digitizer boards for the Q-bus (for Vaxstations)?
-- Chuck Dyer
dyer@cs.wisc.edu
[ All I know about is the MicroVAX II/Q-bus board(s) by Data Translation
(617) 481-3700; I've no experience with them. Let us know what you find.
-pk- ]
------------------------------
From: munnari!latcs1.oz.au!suter@uunet.uu.net (David Suter)
Subject: contrast and size
Keywords: classical size illusion
Date: 12 Apr 88 11:30:46 GMT
Organization: Comp Sci, La Trobe Uni, Australia
I am seeking pointers or comments on variations upon what I believe is
called the classical size illusion: A dark square on a light
background - or the reverse - seems to be larger than it really is and
that this apparent size increases with increasing contrast.
Specifically I am interested in whether one can deduce that a 1-D
version of this (stripe instead of square) induces the same effect.
Furthermore, I am interested in explanations of this illusion. I am
aware of the explanations mentioned in van Erning et al. (Vision
Research Vol. 28 No. 3) and wonder if any radically different
explanations have been proposed.
I have tried using this newsgroup for commentary and pointers before -
without success - Is anybody out there? - or is it just that my
queries are not in the interests of subscribers. Any comments etc.
would be welcome.
[ I believe this question is well within the bounds of this List. You
may also want to post these type of questions to the Psychology
bboards/digests. -pk- ]
d.s.
David Suter ISD: +61 3 479-1311
Department of Computer Science, STD: (03) 479-1311
La Trobe University, ACSnet: suter@latcs1.oz
Bundoora, CSnet: suter@latcs1.oz
Victoria, 3083, ARPA: suter%latcs1.oz@uunet.uu.net
Australia UUCP: ...!uunet!munnari!latcs1.oz!suter
TELEX: AA33143
FAX: 03 4785814
------------------------------
Date: Thu, 14 Apr 88 11:45:54 MDT
From: Wahner Brooks <wbrooks@yuma.arpa>
Subject: Recording Visual Images
Greetings,
Can anyone provide me recommendations for film/lens/filters and
exposure durations that would record an image as the "average" human
eye would see it under both photopic and scotopic conditions? Data
is required for still and motion cameras (and, if anyone has worked
with it, video). Leads to individuals or organizations working this
problem would be useful.
Thank you. Wahner Brooks <wbrooks@yuma.arpa>
602-328-2135
[ Contrast sensing after dark adaptation is scotopic (has reduced ability
to perceive color); light adapted sensing is photopic. P46 in
"Digital Picture Processing," by Rosenfeld and Kak describes the
phenomena. The index for the Optical Society of America or the
Science Citation Index might help...
-pk- ]
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/22/88)
Vision-List Digest Tue Jun 21 11:54:52 PDT 1988 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Matrox Comments Vicom, Datacube comments Medical Image Processing? ---------------------------------------------------------------------- Date: Fri 17 Jun 88 10:59:19-PDT From: Gerard Medioni <MEDIONI%DWORKIN.usc.edu@oberon.USC.EDU> Subject: MATROX Comments Regarding the digitizers for the PC, here at USC we have bought a few MATROX boards and are very happy with them. They cost about $1200, give you 512*512*8 (actually 512*480), and come with 1Meg of on-board memory, organized into 4 512*512 panes. There is a decent library of low level routines which are C and Fortran callable. ------------------------------ Date: Mon, 20 Jun 88 16:25:24 EDT From: Matthew Turk <turk@media-lab.media.mit.edu> Subject: Vicom, Datacube comments marc@acf8.nyu.edu writes: >We are considering the purchase of some of the Datacube Max Video >VME-bus image processing boards for use in a Sun environment. We >currently have a VICOM-1, and would like the new facility to support >VICOM-like commands, support vision studies, and support real-time >robotic applications. > .... I used a Vicom for almost three years and have been working with a Datacube system for the past six months, so I'll chip in my $0.02 worth. First the Vicom.... The Vicom I used was their Versados-based version (is that VICOM-1, I forget?), not the newer VMEbus/Sun version. It was used as the vision system for an autonomous vehicle, processing video and range images to do things like find and describe the road and obstacles. (In fact, two Vicoms are now being used in this system.) The machine was equipped with digitizers and framestores, a bunch of image memory, a 3x3 convolution box, a point processor, mouse and graphics interface, and a fast histogram board. Things generally happen at frame rate. My impression is that the hardware was good, but rather inflexible. What could be done with the machine was sorta limited unless you wanted to hack very low-level driver stuff. The software that comes with the Vicom was reasonably good -- once we got the thing up and running, we could do all kinds of image processing from their canned routines, and write Pascal programs to do others. Programming the thing wasn't too hard -- again, unless you wanted to do something different than what was provided. The development environment is another story -- it was atrocious! Although I complained at the time, I must admit that Vicom's service was pretty good. The Datacube system that I'm currently working with is sort of the opposite of the Vicom. Its hardware seems to be pretty hot, and can be configured to do just about anything you are clever enough to think of. However, it may take you months to figure out the thing well enough to digitize an image, store it, convolve it, and display the output! It is clearly a hardware product, and the software is up to you. The good thing is that you never have to worry about coding obscure low-level driver stuff -- Datacube provides thorough interfacing software -- but you certainly have to worry about what to do with the medium-low-level routines you have available, how to configure data paths in software and via bus cables, how to deal with interrups and pipeline delays, etc. For example, I have been spending a great deal of time and effort trying to avoid crashing my Sun every time I initialize the ``Roistore'' board! With this and other problems I have had little help from Datacube. They seem to be much more concerned with selling than supporting -- I hope this will improve as more of us complain. There's a group across the street at the AI Lab using a Datacube/Sun to track a bouncing ball in real-time for such things as juggling and ping-pong playing robots. Their current simple vision system (using five Datacube boards for two cameras) runs at frame rate. Another group at Harvard is using Datacube for tracking objects in real-time. (Important to both of these projects is the Featuremax board....) Our group at the Media Lab is starting to get almost real-time pyramids running. The arithmetic depends on the board, but most of it is 8- or 16-bit. (I think the 8x8 convolution kernel elements are 8-bit, output is 16-bit.) I don't know of any commercially available software packages for the Datacube -- someone please speak up if you do! There is a group at Boeing who have done quite a bit with their Datacube equipment, so it is possible to develop a VICOM-like command set -- but at this point it's a *big* job. I'd love to hear other opinions on this..... Matthew Turk MIT Media Lab ------------------------------ Date: 21 Jun 88 03:34:51 GMT From: sher@sunybcs.uucp.arpa (David Sher) Subject: Medical Image Processing? Keywords: Medical Instrumentation Organization: SUNY/Buffalo Computer Science I am involved in a small project (that I hope will grow into a large project) on medical image processing (in particular on echocardiographic data). I am also interested in other topics on medical instrumentation. However my expertise lies in computer perception rather than medicine. Anyway is there a mailing list or discussion group that is particularly relevant to this topic? Of particular interest to me are the issues of: 1. Funding sources for such work. 2. Places where work on this topic is published. (There is some but not a lot of such work documented in the typical computer vision literature such as CGVIP, and PAMI.) 3. Ways to learn more about the topic. (Would it be a good idea to take a course on radiology or would it be just a waste of time?) 4. What other people out there are doing about medical imaging. 5. Successes and failures in collaborations between computer scientists and MD's. -David Sher Ph.D. Computer Science -David Sher ARPA: sher@cs.buffalo.edu BITNET: sher@sunybcs UUCP: {rutgers,ames,boulder,decvax}!sunybcs!sher ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/16/88)
Vision-List Digest Fri Jul 15 11:58:02 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Motion vision hardware
Updated call for Papers, Israeli AI Conference
----------------------------------------------------------------------
Date: Thu, 14 Jul 88 08:57:55 PDT
From: John B. Nagle <jbn@glacier.stanford.edu>
Subject: Motion vision hardware
Special-purpose hardware seems to be a necessity for real-time
motion vision. (Yes, one might be able to do it on a supercomputer,
a Connection Machine, or a GigaLogician, but that route is too
expensive for more than brief experiments.) But, as yet, not much
suitable hardware is available. On the other hand, the PRISM work
at MIT and Nishihara's later work at Schlumberger indicate that such
hardware can be built at relatively modest cost. Is there sufficient
demand for such hardware to justify manufacturing it? Are there
applications in sight?
John Nagle
------------------------------
From: Shmuel Peleg <peleg%humus.Huji.AC.IL@CUNYVM.CUNY.EDU>
Date: Thu, 14 Jul 88 22:34:57 JDT
Subject: Please Post: Call for Papers, Israeli AI Conference
Call For Papers
Fifth Israeli Conference on Artificial Intelligence
Tel-Aviv, Ganei-Hata`arucha,
December 27-28, 1988
The Israeli Conference on Artificial Intelligence is the annual meeting
of the Israeli Association for Artificial Intelligence, which is a SIG
of the Israeli Information Processing Association. Papers addressing
all aspects of AI, including, but not limited to, the following
topics, are solicited:
- AI and education
- AI languages, logic programming
- Automated reasoning
- Cognitive modeling
- Expert systems
- Image processing and pattern recognition
- Inductive inference, learning and knowledge acquisition
- Knowledge theory, logics of knowledge
- Natural language processing
- Computer vision and visual perception
- Planning and search
- Robotics
This year, the conference is held in cooperation with the SIG on
Computer Vision and Pattern Recognition, and in conjunction with the
Tenth Israeli Conference on CAD and Robotics. There will be a special
track devoted to Computer Vision and Pattern Recognition. Joint
activities with the Confernece on CAD and Robotics include the
openning session, a session on Robotics and AI, and the exhibition.
Submitted papers will be refereed by the program committee, listed
below. Authors should submit 4 camera-ready copies of a full paper or
an extended abstract of at most 15 A4 pages. Accepted papers will
appear without revision in the proceedings. Submissions prepared on a
laser printed are preferred. The first page should contain the title,
the author(s), affiliation, postal address, e-mail address, and
abstract, followed immediately by the body of the paper. Page numbers
should appear in the bottom center of each page. Use 1 inch margin
and single column format.
Submitted papers should be received at the following address by
October 1st, 1988:
Ehud Shapiro
5th ICAI
The Weizmann Institute of Science
Rehovot 76100, Israel
The conference program will be advertized at the end of October. It
is expected that 30 minutes will be allocated for the presentation of
each paper, including question time.
Program Committee
Moshe Ben-Bassat, Tel-Aviv University (B25@taunivm.bitnet)
Martin Golumbic, IBM Haifa Scientific Center
Ehud Gudes, Ben-Gurion University (ehud@bengus.bitnet)
Tamar Flash, Weizmann Institute of Science
Yoram Moses, Weizmann Institute of Science
Uzzi Ornan, Technion
Shmuel Peleg, Hebrew University (peleg@humus.bitnet)
Gerry Sapir, ITIM
Ehud Shapiro (chair), Weizmann Institute of Science (udi@wisdom.bitnet)
Jeff Rosenschein, Hebrew University (jeff@humus.bitnet)
Shimon Ullman, Weizmann Institute of Science (shimon@wisdom.bitnet)
Hezy Yeshurun, Tel-Aviv University (hezy@taurus.bitnet)
Secreteriate
Israeli Association for Information Processing
Kfar Hamacabia
Ramat-Gan 52109, Israel
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/02/88)
Vision-List Digest Mon Aug 1 12:31:07 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
-- Thesis defense: Bayesian Modeling of Uncertainty in Low-Level Vision
-- Automated supernova search people need advice
-- Workstation Questions
-- NETWORK COMPUTING FORUM - CALL FOR PAPERS
-- FIRST ANNUAL MEETING OF THE INTERNATIONAL NEURAL NETWORK SOCIETY
-- Public Domain Sun Image Processing Software
-- multidisciplinary conference on VISION, PROCESSING, and DISPLAY
----------------------------------------------------------------------
Date: Mon, 18 Jul 1988 09:34-EDT
From: Richard.Szeliski@IUS2.CS.CMU.EDU
Subject: Thesis defense: Bayesian Modeling of Uncertainty in Low-Level Vision
Bayesian Modeling of Uncertainty in Low-Level Vision
[ Thesis defense ]
Richard Szeliski
Computer Science Department
Carnegie Mellon University
July 28, 1:00pm, WeH 5409
ABSTRACT
Over the last decade, many low-level vision algorithms have been devised for
extracting depth from one or more intensity images. The output of such
algorithms usually contains no indication of the uncertainty associated with
the scene reconstruction. In other areas of computer vision and robotics,
the need for such error modeling is becoming recognized, both because of the
uncertainty inherent in sensing, and because of the desire to integrate
information from different sensors or viewpoints.
In this thesis, we develop a new Bayesian model for the dense fields such as
depth maps or optic flow maps that are commonly used in low-level vision.
The Bayesian model consists of three components: a prior model, a sensor
model, and a posterior model. The prior model captures any a priori
information about the structure of the dense field. We construct this model
by using the smoothness constraints from regularization to define a Markov
Random Field. By applying Fourier analysis to this prior model, we show
that the class of functions being modeled is fractal. The sensor model
describes the behaviour and noise characteristics of our measurement system.
We develop a number of sensor models for both sparse depth measurements and
dense flow or intensity measurements. The posterior model combines the
information from the prior and sensor models using Bayes' Rule, and can be
used as the input to later stages of processing. We show how to compute
optimal estimates from the posterior model, and also how to compute the
uncertainty (variance) in these estimates.
This thesis applies Bayesian modeling to a number of low-level vision
problems. The main application is the on-line extraction of depth from
motion. For this application, we use a two-dimensional generalization of
the Kalman filter to convert the current posterior model into a prior model
for the next estimate. The resulting incremental algorithm provides a dense
on-line estimate of depth whose uncertainty and error are reduced over time.
In other applications of Bayesian modeling, we use the Bayesian
interpretation of regularization to choose the optimal smoothing parameter
for interpolation; we use a Bayesian model to determine observer motion from
sparse depth measurements without correspondence; and we use the fractal
nature of the prior model to construct multiresolution relative surface
representations. The approach to uncertainty modeling which we develop, and
the utility of this approach in various applications, support our thesis
that Bayesian modeling is a useful and practical framework for low-level
vision.
------------------------------
Date: Fri, 29 Jul 88 07:46:22 PDT
From: John B. Nagle <jbn@glacier.stanford.edu>
Subject: Automated supernova search people need advice
This is forwarded from USENET; please reply to "beard@uxl.lbl.gov", not me.
>From: beard@ux1.lbl.gov (Patrick C Beard)
Subject: Workstation Questions
Date: 28 Jul 88 23:41:21 GMT
Distribution: comp.sys.workstations,comp.edu,comp.graphics,comp.os.vms
Organization: Lawrence Berkeley Laboratory, Berkeley
Summary: Questions about available workstations, accelerating mVax
Hello everybody.
My group is conducting an automated search for supernovae and is
in the market for upgrading the computer that is the heart of the
system. We require a system that outperforms our current computer,
a Microvax, by at least a factor of 4, and hopefully a factor of 10.
I am submitting this message to the network community to ask three
questions:
1) What machines are there in the workstation type class that can
outperform a Microvax by a factor of 4 to 10 times? (Please describe
briefly, cost, speed, manufacturer.)
2) Alternatively, what options exist for speeding up a Microvax?
Are there accelerator boards, processor upgrades, anything you can
think of?
3) What image processing systems are available? Commercial or public
domain, source code included, optimized for what hardware, and how easy
are they to modify or extend for special purpose use (such as astronomical
work)?
You may answer me directly, or via the net. I'm sure there are a lot
of people who could benefit from this information.
Thanks in advance,
+=============================================================+
| Patrick C. Beard |
| Lawrence Berkeley Laboratory |
| Automated Supernova Search |
+-------------------------------------------------------------+
| PCBeard@LBL.gov (arpa only) |
+=============================================================+
------------------------------
Date: 29 Jul 88 12:31 PDT
From: William Daul / McAir / McDonnell-Douglas Corp <WBD.MDC@OFFICE-8.ARPA>
Author: Beverly Pieper <BKP.MDC@office-8.arpa>
Subject: NETWORK COMPUTING FORUM - CALL FOR PAPERS
NETWORK COMPUTING FORUM
CALL FOR PAPERS
OCTOBER 5-8, 1988
HOLIDAY INN WESTPORT, ST. LOUIS, MISSOURI
The next meeting of the Network Computing Forum will be held on October 5-7 in
St. Louis, Missouri. This will be the fourth meeting of the Forum, and will
focus on the role of the Forum as a catalyst for change in the industry. The
Forum is an industry group chartered to lead the way for rapid adoption of
multi-vendor network computing concepts and technologies. Forum meetings allow
representatives from users and vendors to work together on common issues in an
open, informal atmosphere. The Forum has over 100 member organizations, and
more than 220 representatives attended the May 1988 meeting.
Forum meetings are organized into three sessions: a conference featuring
invited papers and panel sessions, meetings of interest groups and working
groups, and a policy making executive committee meeting. Some areas of
interest to the Forum member organizations are listed, to suggest possible
topics for papers:
Definition of user requirements for network computing
Practical experiences using network computing concepts & technologies
Partitioning and/or integration of applications across networks
Remote procedure calls and other core services for network computing
System and network administration for networks of heterogeneous computers
User interfaces and user environments for network computing
Software licensing in a network environment
Data representation and command scripting across heterogeneous networks
Use of network computing with IBM mainframes (MVS and VM)
Invited Papers
As part of each Forum meeting, papers are invited from the community at
large for presentation and discussion. These papers should address the use
or development of network based applications and services. Emphasis should
be placed on creating and using tightly coupled links between multiple,
heterogeneous computer systems. Technical descriptions of research
projects, user experiences, as well as commerically available products are
welcome. Invitations are also extended for more informal talks on practical
experience in administering heterogeneous computer networks. All
presentations should be 35 minutes in length, with 15 minutes of discussion
following each presentation.
Abstracts must be received by August 10, 1988. Abstracts should summarize
the paper in two or three paragraphs and include the mailing address,
affiliation, and phone number of the author(s). Notification of abstracts
selected will be sent on August 19, 1988 and papers must be submitted no
later than September 20, 1988. Papers can be copyrighted, but must include
authorization for unrestricted reproduction by the Network Computing Forum.
Papers can be marked as working papers to allow future publication.
SEND ABSTRACTS BY AUGUST 10, 1988 TO the Program Chairman for the October 1988
meeting:
T.D. Carter
c/o Jan McPherson
McDonnell Douglas Travel Company
944 Anglum Drive, Suite A
Hazelwood, MO 63042
(314) 233-2951
Internet Address: TDC.MDC@OFFICE-8.ARPA
------------------------------
Date: Mon, 1 Aug 88 12:08:42 EDT
From: mike%bucasb.bu.edu@bu-it.BU.EDU (Michael Cohen)
Subject: FIRST ANNUAL MEETING OF THE INTERNATIONAL NEURAL NETWORK SOCIETY
MEETING UPDATE:
September 6--10, 1988
Park Plaza Hotel
Boston, Massachusetts
The first annual INNS meeting promises to be a historic event. Its program
includes the largest selection of investigators ever assembled to present
the full range of neural network research and applications.
The meeting will bring together over 2000 scientists, engineers, students,
government administrators, industrial commercializers, and financiers. It
is rapidly selling out. Reserve now to avoid disappointment.
Call J.R. Shuman Associates, (617) 237-7931 for information about registration
For information about hotel reservations, call the Park Plaza Hotel at
(800) 225-2008 and reference "Neural Networks." If you call
from Massachusetts, call (800) 462-2022.
There will be 600 scientific presentations, including tutorials, plenary
lectures, symposia, and contributed oral and poster presentations. Over 50
exhibits are already reserved for industrial firms, publishing houses, and
government agencies.
The full day of tutorials presented on September 6 will be given by Gail
Carpenter, John Daugman, Stephen Grossberg, Morris Hirsch, Teuvo Kohonen,
David Rumelhart, Demetri Psaltis, and Allen Selverston. The plenary lecturers
are Stephen Grossberg, Carver Mead, Terrence Sejnowski, Nobuo Suga, and Bernard
Widrow. Approximately 30 symposium lectures will be given, 125 contributed oral
presentations, and 400 poster presentations.
Fourteen professional societies are cooperating with the INNS meeting. They
are:
American Association of Artificial Intelligence
American Mathematical Society
Association for Behavior Analysis
Cognitive Science Society
IEEE Boston Section
IEEE Computer Society
IEEE Control Systems Society
IEEE Engineering in Medicine and Biology Society
IEEE Systems, Man and Cybernetics Society
Optical Society of America
Society for Industrial and Applied Mathematics
Society for Mathematical Biology
Society of Photo-Optical Instrumentation Engineers
Society for the Experimental Analysis of Behavior
DO NOT MISS THE FIRST BIRTHDAY CELEBRATION OF THIS IMPORTANT NEW
RESEARCH COALITION!
------------------------------
From: Phill Everson <everson%COMPSCI.BRISTOL.AC.UK@CUNYVM.CUNY.EDU>
Subject: Public Domain Sun Image Processing Software
Date: Tue, 19 Jul 88 13:26:39 +0100
Version 1.1.1: of ALV Public Domain (see file "COPYRIGHT") Image
Processing Toolkit for the Sun Workstation
released Sun 17 Jul, 1988
This is to introduce family of image processing programs written by
Phill Everson <everson@uk.ac.bristol.cs> with help from Gareth Waddell
(notably for the dynamic array library) at Bristol University in the UK
for SUN workstations, both colour and black/white. (The imed image
editor is largely based on sunpaint, written a year or two ago by Ian
Batten at Birmingham University. Thanks very much!) It includes tools
to display images, to convolve a filter over an image, to create a
histogram of the greylevels in an image, to perform histogram
equalisation of an image, to threshold an image, to convert an image to
Postscript and ... (read the manual page alv(1) for other features).
AlV stands for Autonomous Land Vehicle, the research project that these
were originally developed for. The toolkit was written to fullfil a
need rather than to be especially pretty, so in places there are some
rough edges. Some of the tools have been used MUCH more than
others and so can be regarded as being pretty much correct (dsp,
convolve, pixval, imagelw, subarea, subsample, winwidth, hist &
invert). If any of the others seem to be playing up it is possible
that there is a bug in there somewhere -- some tools were added at the
request of others who promised to test them and have never been heard
of since! Please send me any bug reports (and fixes please :-) ) to me.
Note that imed does *not* work with colour workstations as yet!
*************************************************************************
To get this system up and on the road:
1. Edit the Makefile, changing the directory paths for
BINDIR, LIBDIR, INCDIR, MANDIR & FILDIR to suit your system.
2. You might want to alter the command to send Postscript to
your Laserprinter in imagelw.c - at present it is "lpr -Plw -v"
on line 58.
3. Type 'make' and everything will be compiled and installed. This
takes about 15 minutes.
4. Read the manual page alv(1). It can be formatted from this
directory by typing 'nroff -man alv.1 | more'.
*************************************************************************
This family of programs has 3 manual pages; alv(1), alv(3) & alv(5).
alv(1) has a general description of each of the programs and what each
of them should do. alv(3) is a description of the library created and
alv(5) is a description of the file format used for an image. (I've
also included the manual page dynamem(3) for a dynamic memory
allocation library which is used by the alv library and which someone
may find useful.)
The method that we have found works best is that everyone working
on vision programs uses the same file format (see alv(5)) and
most people will use the core tools to display images etc and the
library functions for their own programs.
These are and will be used a lot here, so if anybody adds or modifies
them, please send me details and I'll collect, collate and send updates
out on the mailing list. It is likely that new tools will be added here
also as I'm now sure to be here until at least 1990.
If you want to be put on a mailing list for additions and bugfix
reports, mail "alv-users-request@uk.ac.bristol.cs". The actual mailing
list can be accessed by mailing to "alv-users@uk.ac.bristol.cs".
I hope they're of some use.
Phill Everson
SNAIL: Phill Everson, Comp. Sci. Dept., U of Bristol, Bristol, UK
JANET: everson@uk.ac.bristol.cs UUCP: ...mcvax!ukc!csisles!everson
ARPANET: everson%cs.bristol.ac.uk@nss.cs.ucl.ac.uk
------------------------------
Date: 28 Jul 88 12:41:17 EDT
From: Bernice Rogowitz <ROGOWTZ@ibm.com>
Subject: multidisciplinary conference on VISION, PROCESSING, and DISPLAY
********** MEETING ANNOUNCEMENT AND CALL FOR PAPERS ********
a multidisciplinary conference on:
HUMAN VISION, VISUAL PROCESSING, AND DIGITAL DISPLAY
Bernice E. Rogowitz, chairman
January 19-20, 1989
This meeting is a subset of the
SPSE/SPIE Symposium on Electronic Imaging, January 15-20, 1989
Los Angeles Hilton Hotel, Los Angeles, California
TOPICS:
o Models for Human and Machine Vision
o Color Vision and Color Coding
o Digitization, Spatial Sampling, and Anti-Aliasing
o Vision-Based Algorithms for Image Processing
o Psychophysics of Image Quality
o Spatial/Color/Temporal Interactions in Perception and Coding
CONFERENCE GOAL:
The goal of this two-day conference is to explore interactions between
human visual processing and the diverse technologies for displaying,
coding, processing, and interpreting visual information.
PARTICIPANTS:
Paper are solicited from scientists working in visual psychophysics,
computer vision, computer graphics, digital display, printing,
photography, image processing, visualization, medical imaging, etc.
IMPORTANT DATES:
150-word Abstracts Due: August 31, 1988
Camera-ready Manuscript due: December 19, 1988
FOR MORE INFORMATION, PLEASE CONTACT:
Dr. Bernice E. Rogowitz, chair SPIE Technical Program
IBM T. J. Watson Research Center 1022 19th Street
Box 218 Yorktown Heights, NY 10598 Bellingham, WA 98225
(914) 945-1687 Net: ROGOWTZ@IBM.COM (206) 676-3290
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/03/88)
Vision-List Digest Fri Sep 2 15:33:46 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
IEEE CVPR 1989 Call for Papers
----------------------------------------------------------------------
Date: 31 Aug 88 23:02:18 GMT
From: wnm@uvacs.CS.VIRGINIA.EDU (Worthy N. Martin)
Subject: IEEE CVPR 1989 Call for Papers
Keywords: CVPR 1989
Organization: U.Va. CS Department, Charlottesville, VA
CALL FOR PAPERS
IEEE Computer Society Conference
on
COMPUTER VISION AND PATTERN RECOGNITION
Sheraton Grand Hotel
San Diego, California
June 4-8, 1989.
General Chair
Professor Rama Chellappa
Department of EE-Systems
University of Southern California
Los Angeles, California 90089-0272
Program Co-Chairs
Professor Worthy Martin Professor John Kender
Dept. of Computer Science Dept. of Computer Science
Thornton Hall Columbia University
University of Virginia New York, New York 10027
Charlottesville, Virginia 22901
Program Committee
Charles Brown John Jarvis Gerard Medioni
Larry Davis Avi Kak Theo Pavlidis
Arthur Hansen Rangaswamy Kashyap Alex Pentland
Robert Haralick Joseph Kearney Roger Tsai
Ellen Hildreth Daryl Lawton John Tsotsos
Anil Jain Martin Levine John Webb
Ramesh Jain David Lowe
Submission of Papers
Four copies of complete drafts, not exceeding 25 double
spaced typed pages should be sent to Worthy Martin at the
address given above by November 16, 1988 (THIS IS A HARD
DEADLINE). All reviewers and authors will be anonymous for
the review process. The cover page will be removed for the
review process. The cover page must contain the title,
authors' names, primary author's address and telephone
number, and index terms containing at least one of the below
topics. The second page of the draft should contain the
title and an abstract of about 250 words. Authors will be
notified of notified of acceptance by February 1, 1989 and
final camera-ready papers, typed on special forms, will be
required by March 8, 1989. Submission of Video Tapes As a
new feature there will be one or two sessions where the
authors can present their work using video tapes only. For
information regarding the submission of video tapes for
review purposes, please contact John Kender at the address
above.
Conference Topics Include:
-- Image Processing
-- Pattern Recognition
-- 3-D Representation and Recognition
-- Motion
-- Stereo
-- Visual Navigation
-- Shape from _____ (Shading, Contour, ...)
-- Vision Systems and Architectures
-- Applications of Computer Vision
-- AI in Computer Vision
-- Robust Statistical Methods in Computer Vision
Dates
November 16, 1988 -- Papers submitted
February 1, 1989 -- Authors informed
March 8, 1989 -- Camera-ready manuscripts to IEEE
June 4-8, 1989 -- Conference
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/13/88)
Vision-List Digest Mon Sep 12 14:44:52 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Postdoc. Fellowships at National Research Council, Canada
Del-squared G
problems with multiple mailings, etc.
book on basics of optical scanning
Congress on Cybernetics and Systems
Where to go for image processing software?
----------------------------------------------------------------------
Date: 7 Sep 88 15:50:53 GMT
From: Stephen MacKay <samackay@watcgl.waterloo.edu>
Subject: Postdoc. Fellowships at National Research Council, Canada
Keywords: postdoctorate fellowships, intelligent robotics
Organization: National Research Council, Canada
Postdoctorate Fellowships at NRC
Applications for postdoctorate fellowships are being accepted
from citizens of U.S.A., U.K., Japan, W. Germany, France, and
Italy, in the area of Intelligent robotics. These are 1 yr.,
non-renewable fellowships valued at approximately $CAN 29K plus
travel expenses. Interested parties can contact:
Nestor Burtnyk or Colin Archibald
Laboratory for Intelligent Systems
National Research Council of Canada
Ottawa, Ont. Canada K1A 0R8
(613) 993-6580
email: archibald@dee.nrc.ca
------------------------------
Date: 8 Sep 88 06:59:09 GMT
From: srini@mist.cs.orst.edu (Srinivas Raghvendra)
Subject: Del-squared G
Keywords: edge detectors, zero crossings, Gaussian filter, David Marr
In the literature I hae been looking up, there are frequent references
to the Del-squared G operator ( the Laplacian of the convolution of the image
with a Gaussian filter ). I would like to try and apply this operator to a
set of images that I have and study the results. I have the following questions
for you net folks :
(1) Can you point me to an article/book that discusses the actual
implementation of this operator. I have read a couple of David Marr's articles
that tell me why the operator is good and stuff of the sort. I need to know
how I can actually implement such an operator in code ( as a program ).
(2) Related to this is the issue of detecting zero-crossings in the
output of the above operator. Can this step be combined in some way with the
convolution step ?
I apologise if this is not the appropriate newsgroup for this request.
I am unable to think of a better group for posting this request.
I will be grateful to those of you who will take some time off to
respond to my request.
Thank you all.
Srinivas Raghvendra ( srini@mist.cs.orst.edu )
[ (1) The convolution is usually implemented using a discrete mask.
The formulas used to compute this mask is in many books (e.g.,
Computer Vision by Ballard & Brown, Rosenfield & Kak,
and other newer vision books. Symmetric (isotropic) masks are
linearly decomposable, and can be implemented as two passes using
one dimensional masks (see PAMI articles in the past year or two).
Zero crossings can be detected by thresholding and detecting transition
points.
(2) I don't know of any.
phil... ]
------------------------------
Date: Fri, 9 Sep 88 20:57:07 PDT
From: Vision-List-Request <vision@deimos.ads.com>
Subject: problems with multiple mailings, etc.
As many of you might have noticed, there have been some rather
annoying multiple mailings of the List. In part, this occured because
our SENDMAIL program has a problem with large distribution lists
(there are 367 sites on my master list). In addition, there have
been some problems with multiple mailings from buggy UUCP node
programs.
The SENDMAIL problems are easy to fix (simply break the list down into
chunks), but I am attempting to streamline the list by having more
sites with multiple recipients set up local redistribution systems.
The List is also distributed as a USENET digest with the title
comp.ai.vision. If you have access or currently access the List
through this facility, and you currently receive the List directly
through your mail facility, please let me know so that I can delete
you from the master list. Please let me know of other mailer
anomalies or problems you are having.
I find my time with the List dominated by fielding problems in the
mailing of the List itself. I am cleaning this up now to free up my
time to spend more time moderating the List. Perhaps throw in a bit
of wood to stimulate some heated discussions.
phil...
------------------------------
Date: 10 Sep 88 14:31:23 GMT
From: dscatl!mgresham@gatech.edu (Mark Gresham)
Subject: book on basics of optical scanning
Organization: Digital Systems Co. , Atlanta
Could anyone out there recommend a book on the basics of how optical
character recognition is handled? And I do mean the *basic*,
fundamental principles of how the decisionmaking is done by the
software.
Please e-mail response. Thanks!
--Mark Gresham
++++++++++++++++++++++++++++++++
INTERNET: mgresham@dscatl.UUCP
UUCP: ...!gatech!dscatl!mgresham
++++++++++++++++++++++++++++++++
------------------------------
Date: Mon, 12 Sep 88 14:07:58 PDT
From: Vision-List-Request <vision>
Subject: Congress on Cybernetics and Systems
[Reposted from Neuron digest. phil... ]
Date: 9 Sep 88 20:13:56 GMT
From: SPNHC@CUNYVM.CUNY.EDU
Subject: Congress on Cybernetics and Systems
Organization: The City University of New York - New York, NY
DISCLAIMER: Author bears full responsibility for contents
of this article
WORLD ORGANIZATION OF SYSTEMS AND CYBERNETICS
8 T H I N T E R N A T I O N A L C O N G R E S S
O F C Y B E R N E T I C S A N D S Y S T E M S
to be held
June 11-15, 1990
at
Hunter College
City University of New York
New York, U.S.A.
This triennial conference is supported by many international
groups concerned with management, the sciences, computers, and
technology systems.
The 1990 Congress is the eighth in a series, previous events
having been held in London (1969), Oxford (1972), Bucharest (1975),
Amsterdam (1978), Mexico City (1981), Paris (1984) and London (1987).
The Congress will provide a forum for the presentation
and discussion of current research. Several specialized sections
will focus on computer science, artificial intelligence, cognitive
science, psychocybernetics and sociocybernetics. Suggestions for
other relevant topics are welcome.
Participants who wish to organize a symposium or a section,
are requested to submit a proposal ( sponsor, subject, potencial
participants, very short abstracts ) as soon as possible, but not
later than September 1989. All submissions and correspondence
regarding this conference should be addressd to:
Prof. Constantin V. Negoita
Congress Chairman
Department of Computer Science
Hunter College
City University of New York
695 Park Avenue, New York, N.Y. 10021 U.S.A.
------------------------------
Date: Mon, 12 Sep 88 14:28:55 PDT
From: gungner@CS.UCLA.EDU (David Gungner)
Subject: Where to go for image processing software?
I'd like to know how to order GYPSY, VICAR, and XVISION image
processing software.
Thanks ... David Gungner, UCLA Machine Perception Lab
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/27/88)
Vision-List Digest Mon Sep 26 09:55:18 PDT 1988 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Motion, correspondence, and aperture problem Re: temporal domain in vision Re: temporal domain in vision Image Processing User's Group - Twin Cities Re: How to connect SUN 3-160M and Imaging technology's series 151 Re: Real-time data acquisition Info. request on computerised colorimetry/microscopy. Faculty position at Stanford Information needed on Intl. Wkshp. on Dynamic Image Analysis... Workshop on VLSI implementation of Neural Nets The 6th Scandinavian Conference on Image Analysis Stanford Robotics Seminars ---------------------------------------------------------------------- Date: Wed, 21 Sep 88 16:13:49 PDT From: stiber@CS.UCLA.EDU (Michael D Stiber) Subject: Motion, correspondence, and aperture problem I am currently working on a thesis involving shape from motion, and would appreciate pointers to the literature that specifically address my topic, as detailed in the "abstract" below. If the following rings any bells, please send me the results of the bell-ringing. I appreciate any efforts that you make with regards to this, even if it is just to send me flames. SHAPE FROM MOTION: ELIMINATING THE CORRESPONDENCE AND APERTURE PROBLEMS The traditional approach to the task of shape from motion has been to first apply spatial processing techniques to individual images in a sequence (to localize features of interest), and then to apply other algorithms to the images to determine how features moved. The oft-mentioned "correspondence" and "aperture" problems arise here, since one cannot be sure, from the information in the processed frames, which features in one frame match which features in the following frames. The methods designed to process visual motion are actually confounded by that motion. Alternative approaches to shape from motion perform temporal (rather than spatial) processing first. These include work on optic flow. When the causes of temporal variation are considered in this manner, it becomes clear that different classes of variation are caused by quite different types of changes in the "real world", and are best accounted for at different levels of processing within a visual system. Thus, overall brightness changes (such as when a cloud moves in front of the sun) are "eliminated from the motion equation" at the lowest levels, with lightness constancy processing. Changes due to eye or camera motion, self motion, and object motion are likewise identified at the appropriate stage of visual processing. This strategy for processing motion uses temporal changes as a source of much additional information, in contrast to the "spatial first" approaches, which throw away that information. The "correspondence" and "aperture" problems are eliminated by using this additional information. This thesis details an algorithm and connectionist architecture for the processing of visual motion due to camera motion. It performs this by converting images from a sensor-based coordinate system (in which camera motion causes temporal variation of images) to a body-centered coordinate system (in which the percept remains constant, independent of camera movement). The "correspondence" and "aperture" problems (as a result of camera motion) are eliminated by this approach. ------------------------------ Date: 21 Sep 88 20:50:53 GMT From: lag@cseg.uucp (L. Adrian Griffis) Subject: Re: temporal domain in vision Keywords: multiplex filter model Organization: College of Engineering, University of Arkansas, Fayetteville In article <233@uceng.UC.EDU>, dmocsny@uceng.UC.EDU (daniel mocsny) writes: > In Science News, vol. 134, July 23, 1988, C. Vaughan reports on the > work of B. Richmond of NIMH and L. Optican of the National Eye > Institute on their multiplex filter model for encoding data on > neural spike trains. The article implies that real neurons multiplex > lots of data onto their spike trains, much more than the simple > analog voltage in most neurocomputer models. I have not seen > Richmond and Optican's papers and the Science News article was > sufficiently watered down to be somewhat baffling. Has anyone > seen the details of this work, and might it lead to a method to > significantly increase the processing power of an artificial neural > network? My understanding is that neurons in the eye depart from a number of general rules that neurons seem to follow elsewhere in the nervous system. One such departure is that sections of a neuron can fire independent of other sections. This allows the eye to behave as though is has a great many logical neuron without having to use the the space that the same number of discrete cellular metabolic systems would require. I'm not an expert in this field, but this suggests to me that many of the special tricks that neurons of the eye employ may be attempts to overcome space limitations rather than to make other processing schemes possible. Whether or not this affects the applicability of such tricks to artificial neural networks is another matter. After all, artificial neural networks have space limitations of their own. UseNet: lag@cseg L. Adrian Griffis BITNET: AG27107@UAFSYSB ------------------------------ Date: 22 Sep 88 01:42:30 GMT From: jwl@ernie.Berkeley.EDU (James Wilbur Lewis) Subject: Re: temporal domain in vision Keywords: multiplex filter model Organization: University of California, Berkeley In article <724@cseg.uucp> lag@cseg.uucp (L. Adrian Griffis) writes: >In article <233@uceng.UC.EDU>, dmocsny@uceng.UC.EDU (daniel mocsny) writes: >> In Science News, vol. 134, July 23, 1988, C. Vaughan reports on the >> work of B. Richmond of NIMH and L. Optican of the National Eye >> Institute on their multiplex filter model for encoding data on >> neural spike trains. The article implies that real neurons multiplex >> lots of data onto their spike trains, much more than the simple >> analog voltage in most neurocomputer models. > >My understanding is that neurons in the eye depart from a number of >general rules that neurons seem to follow elsewhere in the nervous system. I think Richmond and Optican were studying cortical neurons. Retinal neurons encode information mainly by graded potentials, not spike trains....another significant difference between retinal architecture and most of the rest of the CNS. I was somewhat baffled by the Science News article, too. For example, it was noted that the information in the spike trains might be a result of the cable properties of the axons involved, not necessarily encoding any "real" information, but this possibility was dismissed with a few handwaves. Another disturbing loose end was the lack of discussion about how this information might be propogated across synapses. Considering that it generally takes input from several other neurons to trigger a neural firing, and that the integration time necessary would tend to smear out any such fine-tuned temporal information, I don't see how it could be. It's an interesting result, but I think they may have jumped the gun with the conclusion they drew from it. -- Jim Lewis U.C. Berkeley ------------------------------ Date: 22 Sep 88 04:51:39 GMT From: manning@mmm.serc.3m.com (Arthur T. Manning) Subject: Image Processing User's Group - Twin Cities Summary: Announcement of Group's Formation Keywords: vision, image, datacube Organization: 3M Company - Software and Electronics Resource Center (SERC); St. Paul, MN Datacube Inc. (a high-speed image processing hardware manufacturer) is initiating an image processing user's group in the twin cities through their local sales rep Barb Baker Micro Resources Corporation phone: (612) 830-1454 4640 W. 77th St, Sui 109 ITT Telex 499-6349 Edina, Minnesota 55435 FAX (612) 830-1380 Hopefully this group will be the basis of valuable cooperation between various commercial vision groups (as well as others) in the Twin Cities. The first meeting to formulate the purpose, governing body, etc of this image processing user's group was held September 22, 1988. It looks like this newsgroup would be the best place to post further developments. Arthur T. Manning Phone: 612-733-4401 3M Center 518-1 FAX: 612-736-3122 St. Paul MN 55144-1000 U.S.A. Email: manning@mmm.uucp ------------------------------ Date: Thu, 22 Sep 88 00:01:33 CDT From: schultz@mmm.3m.com (John C Schultz) Subject: Re:How to connect SUN 3-160M and Imaging technology's series 151 While we do not have the exact same hardware we are using Bit 3 VME-VME bus repeaters (not extenders) with our SUN 3/160 and Datacube hardware. We had to add a small patch the the Datacube driver to get it to work with the Bit 3 because of the strange Bit 3 handling of interrrupt vectors but now it is fine. The Bit 3 might work for you application, as opposed to a bus "extender", because this repeater keeps the VME backplanes logically and electricially separate although memory mapping is possible. Hope this helps. We don't have IT boards to try it out with. ------------------------------ Date: Thu, 22 Sep 88 00:10:49 CDT From: schultz@mmm.3m.com (John C Schultz) Subject: re:real-time data acquisition >I was wondering if anybody out there knows of a system that will record >rgb digital data in real-time plus some ancillary position information. An >inexpensive medium is of course preferred since it would be useful to >be able to share this data with other folks. Two ways to go (as the moderator mentioned) are low quality VHS style machines which only record maybe 200 lines/image or broadcast quality 3/4 inch tape machines which cost big bucks (and still will probably lose some data from a 512 x 485 image). Digital storage is limited to maybe 30 seconds. In addition to Gould I know of one vendor (Datacube) who supplies 1.2 GB of mag disk for real-time image recording ($25-40K depending on size I think). If the speed requirements are bursty, thse real-time disk systems could be backed up to a Exabyte style cartridge holding a couple GB - or a write-once optical media for faster recall I suppose. As to location info, how about encoding during either vertical blanking or on the audio channel if you use video tape. ------------------------------ Date: 23-SEP-1988 17:02:02 GMT From: ALLEN%BIOMED.ABDN.AC.UK@CUNYVM.CUNY.EDU Subject: Info. request on computerised colorimetry/microscopy. I wonder if anyone can help me with some background information. We have a potential application which involves the measurement of the colour of a surface in an industrial inspection task. It is possible that this will be computerised (eg. camera + framestore). I am trying to find background information on the use of computers in colorimetry. Any books, review articles, etc. which you can recommend, or experience with actual systems, etc. - any info. would be gratefully received. The second part of the project involves the measurement of the thickness of a film (< 20/1000 inch), possibly by optical inspection. We don't want to reinvent the wheel: anyone been here before? Alastair Allen Dept of Physics University of Aberdeen UK. ALLEN@UK.AC.ABDN ------------------------------ Date: 23 Sep 88 19:58:04 GMT From: rit@coyote.stanford.edu (Jean-Francois Rit) Subject: Faculty position at Stanford Organization: Stanford University STANFORD UNIVERSITY Department of Computer Science Faculty Position in Robotics Qualified people are invited to submit applications for a tenure-track faculty position in Robotics. The appointment may be made at either the junior or senior level depending on the qualifications of the applicants. Applicants for a tenured position must have strong records of achievements both in research and in teaching and have demonstrated potential for research leadership and future accomplishments. Applicants for a junior, tenure-track position must have a PhD in Computer Science and have demonstrated competence in one or several areas of Robotics research and must have demonstrated potential for excellent teaching. Outstanding candidates in all areas of Robotics will be considered, with preference to those in Advanced Control or Computer Vision. Depending on specific background and interests, there is a strong possibility of joint appointments with the Mechanical Engineering or Electrical Engineering Departments. Please send applications with curriculum vitae and names of at least four references to: Professor Jean-Claude Latombe, Chairman of Robotics Search Committee, Computer Science Department, Stanford University, Stanford, CA 94305. Stanford University is an Equal Opportunity/Affirmative Action employer and actively solicits applications from qualified women and targeted minorities. Jean-Francois Rit Tel: (415) 723 3796 CS Dept Robotics Laboratory e-mail: rit@coyote.stanford.edu Cedar Hall B7 Stanford, CA 94305-4110 ------------------------------ Date: Sat, 24 Sep 88 14:52 EDT From: From the Land of the Himalayas <SAWHNEY@cs.umass.EDU> Subject: Information needed on Intl. Wkshp. on Dynamic Image Analysis... Hullo Folks, Does anyone out there have information about THE 3RD INTERNATIONAL WORKSHOP on TIME-VARYING ANALYSIS and MOVING OBJECT RECOGNITION to be held in Florence, Italy in May,1989 ? I need information on deadlines, the program committee and the rest. Harpreet Univ. of Mass. at Amherst, COINS Dept. sawhney@umass ------------------------------ Date: 22 Sep 88 00:43:58 GMT From: munnari!extro.ucc.su.oz.au!marwan@uunet.UU.NET From: marwan@extro.ucc.su.oz (Marwan Jabri) Subject: Workshop on VLSI implementation of Neural Nets Organization: University of Sydney Computing Service, Australia Neural Networks - Their Implementation in VLSI A Two Day Workshop 5-6 November 1988 Sydney University Electrical Engineering Sponsored by Electrical Engineering Foundation, University of Sydney Introduction ------------- Research in artificial neural systems or, more commonly, artificial neural networks (NNs) has gained new momentum following a decline in the late 1960s as a result of unsuccessful problem solving areas where conventional digital computers, with processing elements switching in nanoseconds, do not perform as well as ``biological'' neural systems that have electrochemical devices responding in milliseconds. These problem solving areas share important attributes in that they may be performed on noisy and distorted data. Vision, speech recognition and combinatorial optimisation are examples of such problems. VLSI implementations of NN systems have begun to appear as a natural solution to building large and fast computational systems. AT&T Bell Labs and California Institute of Technology (Caltech) are two of the leading research institutions where VLSI NN systems have been developed recently. Successful development of VLSI NNs requires a robust design methodology. Objectives of the Workshop -------------------------- The workshop is organised by the Systems Engineering and Design Automation Laboratory (SEDAL), Sydney University Electrical Engineering (SUEE) and is sponsored by the Electrical Engineering Foundation. The workshop will present to academics, researchers and engineers state-of-the-art methodologies for the implementation of VLSI NN systems. It will also ll cover 6 important lectures of the program. Dr. Larry Jackel ---------------- Head Device Structures Research Department, AT\&T Bells Labs. Dr. Larry Jackel is a world expert on VLSI implementation of artificial NNs. He is leader of a group working on the implementation of VLSI chips with several hundreds of neurons for image classification, pattern recognition and associative memories. Dr Jackel has over 80 technical publications in professional journals and seven US patents. He is recipient of the 1985 IEEE Electron Device Society Paul Rappaport Award for best paper. Dr. Jackel is author and/or co-author of several invited papers on NN design, in particular, recently in the special issue on NNs of the IEEE Computer magazine (March 88). Ms. Mary Ann Maher ------------------ Member of the technical staff, Computer Science Department, Caltech. Ms Mary Ann Maher is member of the research group headed by professor Carver in the simulation of VLSI implementations of NNs. She has participated as an invited speaker at several conferences and workshops on VLSI implementation of NNs including the IEEE International Symposium on Circuits and Systems, 1988 at Helsinki. Invited Speakers ---------------- The seminar will also feature speakers from several Australian research institutions with a diverse background who will give the participants a broad overview of the subject. Prof. Max Benne Wales Prof. Rigby will present an introduction to important MOS building blocks used in the VLSI implementation of NNs. Other lectures and tutorials will be presented by the following speakers from Sydney University Electrical Engineering: Peter Henderson, SEDAL Marwan Jabri, SEDAL Dr. Peter Nickolls, Laboratory for Imaging Science and Engineering Clive Summerfield, Speech Technology Research Venue ----- The course will be held in Lecture Theatre 450, Sydney University Electrical Engineering on November 5 and 6, 1988. Registration ------------ The workshop registration cost is $400 for a private institutioFor more information please contact: Marwan Jabri, SEDAL, Sydney University Electrical Engineering, NSW 2006 or by: Tel: 02 692 2240 Fax: 02 692 2012 ACSnet marwan@extro.ucc.su.oz ------------------------------ Date: Thu, 22 Sep 88 13:43:59 +0300 From: scia@stek5.oulu.fi (SCIA confrence in OULU) The 6th Scandinavian Conference on Image Analysis ================================================= June 19 - 22, 1989 Oulu, Finland Second Call for Papers INVITATION TO 6TH SCIA The 6th Scandinavian Conference on Image Analysis (6SCIA) will be arranged by the Pattern Recognition Society of Fin- land from June 19 to June 22, 1989. The conference is spon- sored by the International Association for Pattern Recogni- tion. The conference will be held at the University of Oulu. Oulu is the major industrial city in North Finland, situated not far from the Arctic Circle. The conference site is at the Linnanmaa campus of the University, near downtown Oulu. CONFERENCE COMMITTEE Erkki Oja, Conference Chairman Matti Pietik{inen, Program Chairman Juha R|ning, Local organization Chairman Hannu Hakalahti, Exhibition Chairman Jan-Olof Eklundh, Sweden Stein Grinaker, Norway Teuvo Kohonen, Finland L. F. Pau, Denmark SCIENTIFIC PROGRAM The program will consist of contributed papers, invited talks and special panels. The contributed papers will cov- er: * computer vision * image processing * pattern recognition * perception * parallel algorithms and architectures as well as application areas including * industry * medicine and biology * office automation * remote sensing There will be invited speakers on the following topics: Industrial Machine Vision (Dr. J. Sanz, IBM Almaden Research Center) Vision and Robotics (Prof. Y. Shirai, Osaka University) Knowledge-Based Vision (Prof. L. Davis, University of Maryland) Parallel Architectures (Prof. P. E. Danielsson, Link|ping University) Neural Networks in Vision (to be announced) Image Processing for HDTV (Dr. G. Tonge, Independent Broadcasting Authority). Panels will be organized on the following topics: Visual Inspection in the Electronics Industry (moderator: prof. L. F. Pau); Medical Imaging (moderator: prof. N. Saranummi); Neural Networks and Conventional Architectures (moderator: prof. E. Oja); Image Processing Workstations (moderator: Dr. A. Kortekan- gas). SUBMISSION OF PAPERS Authors are invited to submit four copies of an extended summary of at least 1000 words of each of their papers to: Professor Matti Pietik{inen 6SCIA Program Chairman Dept. of Electrical Engineering University of Oulu SF-90570 OULU, Finland tel +358-81-352765 fax +358-81-561278 telex 32 375 oylin sf net scia@steks.oulu.fi The summary should contain sufficient detail, including a clear description of the salient concepts and novel features of the work. The deadline for submission of summaries is December 1, 1988. Authors will be notified of acceptance by January 31st, 1989 and final camera-ready papers will be re- quired by March 31st, 1989. The length of the final paper must not exceed 8 pages. In- structions for writing the final paper will be sent to the authors. EXHIBITION An exhibition is planned. Companies and institutions in- volved in image analysis and related fields are invited to exhibit their products at demonstration stands, on posters or video. Please indicate your interest to take part by con- tacting the Exhibition Committee: Matti Oikarinen P.O. Box 181 SF-90101 OULU Finland tel. +358-81-346488 telex 32354 vttou sf fax. +358-81-346211 SOCIAL PROGRAM A social program will be arranged, including possibilities to enjoy the location of the conference, the sea and the midnight sun. There are excellent possibilities to make post-conference tours e.g. to Lapland or to the lake dis- trict of Finland. The social program will consist of a get-together party on Monday June 19th, a city reception on Tuesday June 20th, and the conference Banquet on Wednesday June 21st. These are all included in the registration fee. There is an extra fee for accompanying persons. REGISTRATION INFORMATION The registration fee will be 1300 FIM before April 15th, 1989 and 1500 FIM afterwards. The fee for participants cov- ers: entrance to all sessions, panels and exhibition; proceedings; get-together party, city reception, banquet and coffee breaks. The fee is payable by - check made out to 6th SCIA and mailed to the Conference Secretariat; or by - bank transfer draft account or - all major credit cards Registration forms, hotel information and practical travel information are available from the Conference Secretariat. An information package will be sent to authors of accepted papers by January 31st, 1989. Secretariat: Congress Team P.O. Box 227 SF-00131 HELSINKI Finland tel. +358-0-176866 telex 122783 arcon sf fax +358-0-1855245 There will be hotel rooms available for participants, with prices ranging from 135 FIM (90 FIM) to 430 FIM (270 FIM) per night for a single room (double room/person). ------------------------------ From: binford@Boa-Constrictor.Stanford.EDU.stanford.edu (Tom Binford) Subject: ROBOTICS SEMINARS Monday, Sept. 26, 4:15 Self-Calibrated Collinearity Detector. Yael Neumann Weizmann inst. Israel. Abstract: The visual system can make highly precise spatial judgments. It has been sugested that the high accuracy is maintained by an error correction mechanism. According to this view, adaptation and aftereffect phenomena can be explained as a by product of an error correction mecahnism. This work describes an adaptive system for collinearity and straightness detection. The system incorporates an error correction mechanism and it is, therefore, highly accurate. The error correction mechanism is performed by a simple self calibration process names proportional multi-gain asjustment. The calibration process adjusts the gain values of the system input units. It compensate for errors due to noise in the input units receptive fields location and response functions by ensuring that the average collinearity offset (or curvature) detected by the system is zero (straight). Wednesday, September 28, 1988 Greg Hager Computer and Information Science University of Pennsylvania ACTIVE REDUCTION OF UNCERTAINTY IN MULTI-SENSOR SYSTEMS 4:15 p.m. Oct 3, 1988 Dr. Doug Smith Kestrel Institute KIDS - A Knowledge-Based Software Development System Abstract: KIDS (Kestrel Interactive Development System) is an experimental knowledge-based software development system that integrates a number of sources of programming knowledge. It is used to interactively develop formal specifications into correct and efficient programs. Tools for performing algorithm design, a generalized form of deductive inference, program simplification, finite differencing optimizations, and partial evaluation are available to the program developer. We describe these tools and discuss the derivation of several programs drawn from scheduling and pattern-recognition applications. All of the KIDS tools are automatic except the algorithm design tactics which require some interaction at present. Dozens of derivations have been performed using the KIDS environment and we believe that it is close to the point where it can be used for some routine programming. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/04/88)
Vision-List Digest Mon Oct 3 14:01:56 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Circle Detection Literature
RE: TEMPORAL DOMAIN IN VISION
----------------------------------------
Date: Fri, 30 Sep 88 15:31:06-0000
From: "x.cao" <eecao%PYR.SWAN.AC.UK@cunyvm.cuny.edu>
Subject: Circle Detection Literature
I am looking for information on image processing algorithms
and architectures especially suited to detection of circles
in 2D digital images. In particular I am interested in parallel
systems and real-time operation.
I would be most grateful if you could send me details of any references
you have found useful in this area.
- - - - - - - - - - - - - - - - - - - -
Cao Xing, | UUCP : ...!ukc!pyr.swan.ac.uk!eecao |
Image Processing Laboratory, | JANET : eecao@uk.ac.swan.pyr |
Electrical Engineering Dept., | voice : +44 792 205678 Ext. 4698 |
University of Wales, | Fax : +44 792 295532 |
Swansea, SA2 8PP, U.K. | Telex : 48358 |
- - - - - - - - - - - - - - - - - - - -
[ Related to this is the detection and grouping of general
curves in imagery. Please post references directly to this List.
phil... ]
----------------------------------------
Date: Fri, 30 Sep 88 10:22 EDT
From: Richard A. Young (YOUNG@GMR.COM)
Subject: RE: TEMPORAL DOMAIN IN VISION
Re: temporal domain in vision
I take issue with two replies recently made to dmocsny@uceng.UC.EDU (daniel
mocsny) regarding the Science News article on the work of B. Richmond of NIMH
and L. Optican of the National Eye Institute on their multiplex filter model
for encoding data on neural spike trains:
L. Adrian Griffis (lag@cseg.uucp):
> I'm not an expert in this field, but this suggests to me that many of the
> special tricks that neurons of the eye employ may be attempts to overcome
> space limitations rather than to make other processing schemes possible.
James Wilbur Lewis ( jwl@ernie.Berkeley.EDU):
> Another disturbing loose end was the lack of discussion about how this
> information might be propagated across synapses...It's an interesting result,
> but I think they may have jumped the gun with the conclusion they drew.
Instead, I have a more positive view of Richmond and Optican's work after
reviewing their publications (see references at end), and talking with them
at the recent Neural Net meetings in Boston. I am impressed with their
approach and research. I think that the issue of temporal coding deserves
much more careful attention by vision and neural net researchers than it has
received over the years. Richmond and Optican have produced the first hard
published evidence I am aware of in the primate visual system that temporal
codes can carry meaningful information about visual form.
Their first set of papers dealt with the inferotemporal cortex, a high level
vision area (Richmond et al., 1987; Richmond and Optican, 1987; Optican and
Richmond, 1987). They developed a new technique using principal component
analysis of the neural spike density waveform that allowed them to analyze
the information content in the temporal patterns in a quantifiable manner.
Each waveform is expressed in terms of a few coefficients -- the weights on
the principal components. By looking at these weights or "scores", it is
much easier to see what aspects of the stimulus might be associated with
the temporal properties of the waveform than has been previously possible.
They used a set of 64 orthogonal stimulus patterns (Walsh functions), that were
each presented in a 400 msec flash to awake fixating monkeys. Each stimulus was
shown in two contrast-reversed forms, for a total of 128 stimuli. They devised
an information theoretic measure which showed that "the amount of information
transmitted in the temporal modulation of the response was at least twice that
transmitted by the spike count" alone, which they say is a conservative
estimate. In other words, they could predict which stimuli were present to
a much better extent when the full temporal form of the response was
considered rather than just the total spike count recorded during a trial.
Their laboratory has since extended these experiments to the visual cortex
(Gawne et al., 1987) and the lateral geniculate nucleus (McClurkin et al.)
and found similar evidence for temporal coding of form.
The concept of temporal coding in vision has been around a long time (Troland,
1921), but primarily in the area of color vision. Unfortunately the prevailing
bias in biological vision has been against temporal coding in general for
many years. It has been difficult to obtain funding or even get articles
published on the subject. Richmond and Optican deserve much credit for
pursuing their research and publishing their data in the face of such strong
bias (as does Science News for reporting it). The conventional view is that
all neural information is spatially coded. Such models are variants of the
"doctrine of specific nerve energies" first postulated by Mueller in the
nineteenth century. This "labelled-line" hypothesis assumes that the
particular line activated carries the information. From an engineering
viewpoint, temporal coding allows for more information to be carried along any
single line. Such coding allows more efficient use of the limited space
available in the brain for axons compared to cell bodies (most of the brain
volume is white matter, not grey!). In terms of biological plausibility, it
seems to me that the burden of proof should be on those who maintain that such
codes would NOT be used by the brain.
Anyone who has recorded post-stimulus time histograms from neurons observes
the large variations in the temporal pattern of the responses that occur
with different stimuli. The "accepted view" is that such variations do
not encode stimulus characteristics but represent epi-phenomena or noise. Hence
such patterns are typically ignored by researchers. Perhaps one difficulty
has been that there has not been a good technique to quantify the many
waveshape patterns that have been observed. It is indeed horrendously difficult
to try to sort the patterns out by eye -- particularly without knowing what the
significant features might be, if any. With the application of the principal
component technique to the pattern analysis question, Richmond and Optican
have made a significant advance, I believe -- it is now possible to quantify
such waveforms and relate their properties to the stimulus in a simple manner.
The question raised by Lewis of whether the nervous system can actually make
use of such codes is a potentially rich area for research. Chung, Raymond, and
Lettvin (1970) have shown that branching at axonal nodes is an effective
mechanism for decoding temporal messages. Young (1977) was the first to show
that bypassing the receptors and inserting temporal codes directly into
a human nervous system could led to visual perceptions that were the same for
a given code across different observers.
Work on temporal coding has potentially revolutionary implications for
both physiological and neural net research. As was noted at the INNS
neural net meeting in Boston, temporal coding has not yet been applied or
even studied by neural net researchers. Neural nets today can obviously
change their connection strengths -- but the temporal pattern of the signal on
the connecting lines is not used to represent or transmit information. If it
were, temporal coding methods would seem to offer potentially rich rewards for
increasing information processing capabilities in neural nets without having to
increase the number of neurons or their interconnections.
References
-----------
Chung, S. H., Raymond, S. & Lettvin, J. Y. (1970) Multiple meaning in single
visual units. Brain Behav. Evol. 3, 72-101.
Gawne, T. J. , Richmond, B. J., & Optican, L. M. (1987) Striate cortex neurons
do not confound pattern, duration, and luminance, Abstr., Soc. for Neuroscience
McClurkin, J.W., Gawne, Richmond, B.J., Optican, L. M., & Robinson, D. L.(1988)
Lateral geniculate nucleus neurons in awake behaving primates: I. Response to
B&W 2-D patterns, Abstract, Society for Neuroscience.
Optican, L. M., & Richmond, B. J. (1987) Temporal encoding of two-dimensional
patterns by single units in primate inferior temporal cortex. III. Information
theoretic analysis. J. Neurophysiol., 57, 147-161.
Richmond, B. J., Optican, L. M., Podell, M., & Spitzer, H. (1987) Temporal
encoding of two-dimensional patterns by single units in primate inferior
temporal cortex. I. Response characteristics. J. Neurophysiol., 57, 132-146.
Richmond, B.J., & Optican, L. M. (1987) Temporal encoding of two-dimensional
patterns by single units in primate inferior temporal cortex. II.
Quantification of response waveform. J. Neurophysiol., 57, 147-161.
Richmond, B. J., Optican, L. M., & Gawne, T. J. (accepted) Neurons use multiple
messages encoded in temporally modulated spike trains to represent pictures.
Seeing, Contour, and Colour, ed. J. Kulikowski, Pergamon Press.
Richmond, B. J., Optican, L. M., & Gawne, T. J. (1987) Evidence of an intrinsic
code for pictures in striate cortex neurons, Abstr., Soc. for Neuroscience.
Troland, L. T. (1921) The enigma of color vision. Am. J. Physiol. Op. 2, 23-48.
Young, R. A. (1977) Some observations on temporal coding of color vision:
Psychophysical results. Vision Research, 17, 957-965.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/20/88)
Vision-List Digest Wed Oct 19 12:34:49 PDT 1988
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
ever hear of FULCRUM? Help...
Re: Looking for info on Complex Cepstrums
Request for sensor information
----------------------------------------------------------------------
Date: Fri, 14 Oct 88 19:30:08 PDT
From: palmer%hbvb.span@VLSI.JPL.NASA.GOV (Gary Palmer)
Subject: ever hear of FULCRUM? Help...
Hello everyone, I need some help.
I am looking for some (any) information on a
system/package/who-knows-what that does automated mapping. What I
have heard is that one called FULCRUM exists but I have been unable to
gather any other information. That's all I know, any other help would
be greatly appreciated... Any leads about other automated mapping
(from you cartographers out there) products would also be appreciated.
If there are any requests to do so, I will post my findings.
Please respond to me directly as I do not subscribe to these BB's
that I am posting to.
Many Thanks,
Gary Palmer
Science Applications International Corp.
(213) 781-8644
SPAN: hbva::palmer
INTERNET: palmer%hbva.span@vlsi.jpl.nasa.gov
[ I am posting this because many of the problems in automated mapping are
experienced in spatial vision. If you think your answers are relevant
to vision-types, please post to this List.
phil... ]
------------------------------
Date: Mon, 17 Oct 88 12:18:56 EDT
From: efrethei@BLACKBIRD.AFIT.AF.MIL (Erik J. Fretheim)
Subject: Re: Looking for info on Complex Cepstrums
Cepstrums come in two varieties. The first of these is
called the power cepstrum and is defined as the
Fourier transform of the log magnitude of a Fourier
transform.
FFT{log(|FFT{f(x)}|}
This gives a non-invertable result which shows the relative
magnitude of occurrences of frequency intervals in the base
function. A this is used in voice analysis where it will give
a relatively constant spike for gluttal pitches, and at another
point on the quefrency scale give a series of peaks which represent
the formants for any particular utterance. In image analysis the
power cepstrum can be used to discover any regularity of structure.
The complex cepstrum differs from the power cepstrum in that it is
invertable. The complex cepstrum is computed by calculating an FFT
using the magnitude of an FFT as the real term and the phase of an
FFT as the imaginary term. The complication in computing the complex
cepstrum is that the phase must be unwrapped to be continuous, rather
than being limited to values between PI and -PI or 0 and 2*PI. The
complex cepstrum is used in canceling echos in seismographic testing
and for similar functions in voice processing. In image processing it
can be used to cancel multiple copies of an object. For example, if
an image has three vertical bars, one of brightness level 80, one 50, and
one 30, a change to one term in the complex cepstrum will result in an
image with only the 80 bar and slight (2-3 gray levels) disturbances
where the other bars had been. Another tweek to the complex
cepstrum will introduce multiple copies of a bar into a scene where there
previously was only one.
I have been unable to find any references which do more than describe the
complex cepstrum and report it's uses. I am interested in finding
information about the theory behind the complex cepstrum, guidelines on
how to consistently decide just where to apply changes to the complex
cepstrum to obtain consistent results in the image (so far a guessing
game) and information about two-dimensional applications of the complex
cepstrum. I have an image processing problem where if I could get a
consistent theory for the complex cepstrum, I feel I could make some
progress.
------------------------------
Date: Tue, 18 Oct 88 15:42:47 EDT
From: Mark Noworolski <noworol@eecg.toronto.edu>
Subject: Reqest for sensor information
Organization: EECG, University of Toronto
A project that I'm currently on requires that I be able to locate
the area around an individuals open mouth- with his face being well
lit (similar to a dentists light).
My preferred method would be to use some kind of DSP techiniques on
the visual signal received by sensor 'X'.
My current problem is finding said sensor 'X' at a reasonable price.
(nb 2 dimensions are essential- the vision element can not scan left
to right or up and down).
A 2D CCD array would be nice but $ come into play there (or am I mistaken?)
I recall reading in byte about an 'optical ram' sometime around Sept 83.
In fact I even used that part once and it only cost me about $50.
Unfortunately it was very contrast sensitive and quite difficult to get;
and so now I'm considering it as my last resort.
Does anyone know where I can get parts of comparable value for a reasonable
price? Even a general guideline where to look would be appreciated.
Hoping for some help,
mark (noworol@godzilla.eecg or noworol@ecf.toronto.edu)
[ The price of 2d CCD cameras has come down quite a bit, so you might
be able to get one for around $500. If it's 2D CCD imaging chips you're
after (without the camera), you might take a look at Fairchild Weston/
Schlumberger. Looking art their catalog, they have a 488x380 CCD
chip (CCD222) and DSP chips which may solve your problem (phone
number is 408-720-7600 USA). There are many others.
phil... ]
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/22/88)
Vision-List Digest Fri Oct 21 14:55:25 PDT 1988 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: FULCRUM gathering dense image sequences ---------------------------------------------------------------------- Date: Friday, 21 October 1988 10:22:36 EDT From: Dave.McKeown@maps.cs.cmu.edu Subject: FULCRUM Status: RO FULCRUM is an interactive map display system that uses a video disk to store digitized maps at various resolutions. There is a graphic man-machine interface that allows a user to query the display for lat/lon/elevation, a gazetteer, and the ability to generate and place icons. It is not so much automated mapping (ie., cultural or terrain feature extraction from imagery, or automated map name placement, or automated map digitization) as it is a way to interface the display of precompiled cartographic information with a spatial database of geographic facts. It is (was) developed by a company called Interactive Television Company in Virgina, but I don't know any other particulars. Cheers, Dave ------------------------------ Date: Fri, 21 Oct 88 14:22:07 PDT From: pkahn@meridian.ads.com (Phil Kahn) Subject: gathering dense image sequences Status: RO I thought this might be of interest to those of you trying to acquire controlled motion image sequences for testing or developing algorithms. I am particularly interested in acquiring dense image sequences; that is, imagery in which objects don't move more than about a single pixel between frames (as described in Bolles, Baker, & Marimont IJCV, V1, 1987; Kahn, PAMI 7/85 and CVPR88 for a better description). Smooth and controlled motion can be simply obtained by using a special dolly and track available from most Motion Picture Equipment and Supplies rental services (check the phone book). The movie industry uses this to obtain smooth translation of the camera while changing camera position. Your tripod mounts on top of the dolly (about 2' x 3') and fixed positions may be marked along the track position in order to precisely control the position of the camera on the ground plane. Tracks come in 4' and 8' sections. It only cost $25 p/day for the dolly and $8 p/day for each 8' track section. For $50 p/day, we were able to acquire very smooth and precise motion. Because of drift in robots, it is even more precise and controllable than using a mobile robot vehicle to acquire test imagery. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/29/88)
Vision-List Digest Fri Oct 28 17:23:21 PDT 88 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: MACHINE VISION AND APPLICATIONS JOURNAL ---------------------------------------------------------------------- From: Gerhard Rossbach <rossbach@hub.ucsb.edu> Subject: MACHINE VISION AND APPLICATIONS JOURNAL Date: Mon, 24 Oct 88 12:29:33 PDT There is now a journal in the field of machine vision, integrating theory and applications. It is published four times a year and has a personal subscription rate of $44.00. The contents of Volume 1, Issue 4 are: "Dynamic Monocular Machine Vision", by Ernst Dieter Dickmanns and Volker Graefe. "Applications of Dynamic Monocular Machine Vision", by Ernst Dieter Dickmanns and Volker Graefe. "The P300: A System for Automatic Patterned Wafer Inspection", by Byron E. Dom. The three previous issues have contained articles on: "Background Substration Algorithms for Videodensitometric Quantification of Coronary Stenosis", by O. Nalcioglu, et. al. "Automatic Optical Inspection of Plated Through-holes for Ultrahigh Density Printed Wiring Boards", by Moritoshi Ando and Takefumi Inagaki. "Projection-based High Accuracy Measurement of Straight Line Edges", by Dragutin Petkovic, Wayne Niblack, and Myron Flickner. "An Image-Recognition System Using Algorithmically Dedicated Integrated Circuits", by Peter A. Ruetz and Robert W. Brodersen. "Pipelined Architectures for Morphologic Image Analysis", by Lynn Abbott, Robert M. Haralick, and Xinhua Zhuang. "3-D Imaging Systems and High-Speed Processing for Robot Control", by Robert M. Lougheed and Robert E. Sampson. "Interactive and Automatic Image Recognition System", by Fumiaki Tomita. "Multidimensional Biomedical Image Display and Analysis in the Biotechnology Computer Resource at the Mayo Clinic", by Richard A. Robb. "A Class of Adaptive Model- and Object-Driven Nonuniform Sampling Methods for 3-D Inspection", by Charles B. Malloch, William I. Kwak and Lester A. Gerhardt. "Model-Based Estimation Techniques for 3-D Reconstruction from Projections", by Yoram Bresler, Jeffrey A. Fessler, and Albert Macovski. "Active, Optical Range Imageing Sensors", by Paul J. Besl. "Ash Line Control", by Ola Dahl and Lars Nielsen. If you would like more information on submitting a paper or subscribing to the Journal, please send email to: rossbach@hub.ucsb.edu ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/08/88)
Vision-List Digest Mon Nov 07 11:05:22 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
convexity bibliography update
PIX IPS vision bulletin board 508-441-2118
standford seminar
----------------------------------------------------------------------
Date: Mon, 31 Oct 88 13:14:21 PST
From: binford@Boa-Constrictor.Stanford.EDU.stanford.edu (Tom Binford)
Monday, Nov 7, 1988
4:15pm Cedar Hall Conference Room
Exploiting Temporal Coherence in
Scene Analysis for an Autonomous Land Vehicle
Aaron F. Bobick
Artificial Intelligence Center
SRI International
A technique to build reliable scene descriptions by evaluating the
temporal stability of detected objects is presented. Although current
scene analysis techniques usually analyze individual images correctly,
they occasionally make serious mistakes that could endanger an
autonomous vehicle that is depending upon them for navigational
information. Our approach is designed to avoid these ugly mistakes and
to increase the competence of the sensing system by tracking objects
from image to image and evaluating the stability of their descriptions
over time. Since the information available about an object can change
significantly over time, we introduce the idea of a representation
space, which is a lattice of representations progressing from crude
blob descriptions to complete semantic models, such as bush, rock, and
tree. One of these representations is associated with an object only
after the object has been described multiple times in the representation
and the parameters of the representation are stable. We define
stability in a statistical sense enhanced by a set of explanations
describing valid reasons for deviations from expected measurements.
These explanations may draw upon many types of knowledge, including the
physics of the sensor, the performance of the segmentation procedure,
and the reliability of the matching technique. To illustrate the power
of these ideas we have implemented a system, which we call TraX, that
constructs and refines models of outdoor objects detected in sequences
of range data. This work is a joint project with Bob Bolles.
------------------------------
Date: 4 Nov 88 12:31:25 GMT
From: prlb2!ronse@uunet.UU.NET (Christian Ronse)
Subject: convexity bibliography update
Organization: Philips Research Laboratory, Brussels
Keywords: 370 entries!
In February 1987 I publicised on the net a convexity bibliography with over
250 entries. Many people asked me a copy of it. It has since been updated and
contains now 370 entries. It will appear in IEEE Trans. PAMI in early 1989,
probably in March. You can again ask me a copy of it, provided that you can't
wait until March or you don't have PAMI in your library.
Christian Ronse maldoror@prlb2.UUCP
{uunet|philabs|mcvax|cernvax|...}!prlb2!{maldoror|ronse}
------------------------------
Date: 6 Nov 88 03:55:33 GMT
From: manning@mmm.serc.3m.com (Arthur T. Manning)
Subject: PIX IPS vision bulletin board 508-441-2118
Keywords: software
Organization: 3M Company - Software and Electronics Resource Center (SERC); St. Paul, MN
Paragon Imaging has set up a bulletin board for vision topics and also
to promote their IPS (Image Processing Software) package. All the stuff
I've seen so far has been in FORTRAN, but other source code may appear
soon. It is a fairly unsophisticated system, but it may prove useful.
Paragon advertized this at Electronic Imaging in Boston last month.
Arthur T. Manning Phone: 612-733-4401
3M Center 518-1 FAX: 612-736-3122
St. Paul MN 55144-1000 U.S.A. Email: manning@mmm.uucp
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/08/88)
Vision-List Digest Mon Nov 07 11:21:58 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
CONFERENCE ANNOUNCEMENTS:
=========================
CVPR Call for Papers reminder
AI Symposium in Israel: Program
CFP - 6TH SCANDINAVIAN CONFERENCE ON IMAGE ANALYSIS
IEEE 1989 Int Conf on Image Processing
Symposium on Chinese Text Processing
----------------------------------------------------------------------
Date: Sun, 06 Nov 88 20:46:25 EST
From: "Worthy N. Martin" <wnm@uvacs.cs.virginia.edu>
Subject: CVPR Call for Papers reminder
The following call for papers has appeared before,
however, it is being reissued to remind interested
parties of the first deadline, namely:
---->
----> November 16, 1988 -- Papers submitted
---->
This deadline will be held to firmly with the submission
date determined by postmark.
Thank you for your interest in CVPR89
Worthy Martin
CALL FOR PAPERS
IEEE Computer Society Conference
on
COMPUTER VISION AND PATTERN RECOGNITION
Sheraton Grand Hotel
San Diego, California
June 4-8, 1989.
General Chair
Professor Rama Chellappa
Department of EE-Systems
University of Southern California
Los Angeles, California 90089-0272
Program Co-Chairs
Professor Worthy Martin Professor John Kender
Dept. of Computer Science Dept. of Computer Science
Thornton Hall Columbia University
University of Virginia New York, New York 10027
Charlottesville, Virginia 22901
Program Committee
Charles Brown John Jarvis Gerard Medioni
Larry Davis Avi Kak Theo Pavlidis
Arthur Hansen Rangaswamy Kashyap Alex Pentland
Robert Haralick Joseph Kearney Roger Tsai
Ellen Hildreth Daryl Lawton John Tsotsos
Anil Jain Martin Levine John Webb
Ramesh Jain David Lowe
Submission of Papers
Four copies of complete drafts, not exceeding 25 double
spaced typed pages should be sent to Worthy Martin at the
address given above by November 16, 1988 (THIS IS A HARD
DEADLINE). All reviewers and authors will be anonymous for
the review process. The cover page will be removed for the
review process. The cover page must contain the title,
authors' names, primary author's address and telephone
number, and index terms containing at least one of the below
topics. The second page of the draft should contain the
title and an abstract of about 250 words. Authors will be
notified of notified of acceptance by February 1, 1989 and
final camera-ready papers, typed on special forms, will be
required by March 8, 1989. Submission of Video Tapes As a
new feature there will be one or two sessions where the
authors can present their work using video tapes only. For
information regarding the submission of video tapes for
review purposes, please contact John Kender at the address
above.
Conference Topics Include:
-- Image Processing
-- Pattern Recognition
-- 3-D Representation and Recognition
-- Motion
-- Stereo
-- Visual Navigation
-- Shape from _____ (Shading, Contour, ...)
-- Vision Systems and Architectures
-- Applications of Computer Vision
-- AI in Computer Vision
-- Robust Statistical Methods in Computer Vision
Dates
November 16, 1988 -- Papers submitted
February 1, 1989 -- Authors informed
March 8, 1989 -- Camera-ready manuscripts to IEEE
June 4-8, 1989 -- Conference
------------------------------
Date: Tue, 1 Nov 88 19:15:01 JST
From: Shmuel Peleg <peleg%humus.Huji.AC.IL@CUNYVM.CUNY.EDU>
Subject: AI Symposium in Israel: Program
Fifth Israeli Symposium on Artificial Intelligence
Tel-Aviv, Ganei-Hata`arucha
December 27-28, 1988
Preliminary Program
Tuesday, December 27.
08:00-09:00 Registration
09:00-12:00 Openning Session, Joint with ITIM/CASA
Openning addresses.
Invited Talk: Three dimensional vision for robot applications
David Nitzan, SRI International
12:00-13:30 Lunch Break
13:30-15:15 Session 2.4 Constraints
Invited Talk: An Overview of the Constraint Language CLP(R)
Joxan Jaffar, IBM TJW Research Center
Belief maintenance in dynamic constraint networks
Rina Dechter, UCLA, and Avi Dechter, California State University
13:30-15:15 Session 2.5 Vision
Multiresolution shape from shading
Gad Ron and Shmuel Peleg, Hebrew University
Describing geometric objects symbolically
Gerald M. Radack and Leon S. Sterling, Case Western Reserve University
A vision system for localization of textile pieces on a light table
(short talk)
H. Garten and M. Raviv, Rafael
15:15-15:45 Coffee Break
15:45-17:45 Session 3.4 Reasoning Systems
A classification approach for reasoning systems - a case study in
graph theory
Rong Lin, Old Dominion University
Descriptively powerful terminological representation
Mira Balaban and Hana Karpas, Ben-Gurion University
Bread, Frappe, and Cake: The Gourmet's Guide to Automated Deduction
Yishai A. Feldman and Charles Rich, MIT
15:45-17:45 Session 3.5 Vision
Invited Talk: Cells, skeletons and snakes
Martin D. Levine, McGill University
The Radial Mean of the Power Spectrum (RMPS) and adaptive image restoration
Gavriel Feigin and Nissim Ben-Yosef, Hebrew University
Geometric and probabilistic criteria with an admissible cost structure
for 3-d object recognition by search
Hezekiel Ben-Arie, Technion
17:45-18:15 IAAI Bussiness meeting
Wednesday, December 28.
09:00-10:30 Session 4.4 Computer Aided Instruction
The implementation of artificial intelligence in computer based training
Avshalom Aderet and Sachi Gerlitz, ELRON Electronic Industries
A logical programming approach to research and development of a
student modeling component in a computer tutor for characteristics of
functions
Baruch Schwarz and Nurit Zehavi, Weizmann Institute
Meimad --- A database integrated with instructional system for retrieval
(in Hebrew)
Avigail Oren and David Chen, Tel-Aviv University
09:00-10:30 Session 4.5 Robotics/Search
Invited Talk: Principles for Movement Planning and Control
Tamar Flash, Weizmann Institute
Strategies for efficient incremental nearest neighbor search
Alan J. Broder, The MITRE Corporation
10:30-11:00 Coffee Break
11:00-13:00 Session 5.4 Legal Applications/Language
Towards a computational model of concept acquisition and
modification using cases and precedents from contract law
Seth R. Goldman, UCLA
Expert Systems in the Legal Domain
Uri J. Schild, Bar-Ilan University
Machinary for Hebrew Word Formation
Uzzi Ornan, Technion
What's in a joke?
Michal Ephratt, Haifa University
11:00-13:00 Session 5.5 Expert Systems
Explanatory Meta-rules to provide explanations in expert systems
C. Millet, EUROSOFT, and M. Gilloux, CNET
Declarative vs. procedural representation in an expert system: A perspective
Lev Zeidenberg, IET, and Ami Shapiro IDF
Automatic models generation for troubleshooting
Arie Ben-David, Hebrew University
A general expert system for resource allocation (in Hebrew)
Zvi Kupelik, Ehud Gudes, Amnon Mizels, and Perets Shoval, Ben-Gurion University
13:00-14:30 Lunch Break
14:30-16:00 Session 6.4 Logic Programming
Invited Talk: The CHIP constraint programming system
Mehmet Dincbas, ECRC
Time constrained logic programming
Andreas Zell, Stuttgart University
Automatic generation of control information in five steps
Kristof Verschaetse, Danny De Schreye and Maurice Bruynooghe,
Katoliche Universitet Leuven
14:30-16:00 Session 6.5 Data Structures for Vision
Invited Talk: An Overview of Hierarchical Spatial Data Structures
Hanan Samet, University of Maryland
Optimal Parallel Algorithms for Quadtree Problems
Simon Kasif, Johns Hopkins University
16:00-16:30 Coffee Break
16:30-18:00 Session 7.4 Reasoning and Nonmonotonic Logic
Preferential Models and Cumulative Logics
Daniel Lehmann, Hebrew University
Invited Talk: Baysian and belief-functions formalisms for evidential
reasoning: A conceptual analysis
Judea Pearl, UCLA
16:30-18:00 Session 7.5 Pattern Matching
Scaled pattern matching
Amihood Amir, University of Maryland
Term Matching on a Mesh-Connected Parallel Computer
Arthur L. Delcher and Simon Kasif, The Johns Hopkins University
18:00-18:15 Closing remarks
For registration information please contact:
5th ISAI Secretariat
IPA, Kfar Maccabiah,
Ramat Gan 52109
Israel
(972) 3-715772
Or by e-mail:
udi@wisdom.bitnet
hezy@taurus.bitnet
------------------------------
Date: Thu, 3 Nov 88 08:26:40 +0200
From: jjr@tolsun.oulu.fi (Juha R|ning)
Subject: CFP - 6TH SCANDINAVIAN CONFERENCE ON IMAGE ANALYSIS
The 6th Scandinavian Conference on Image Analysis
=================================================
June 19 - 22, 1989
Oulu, Finland
Second Call for Papers
INVITATION TO 6TH SCIA
The 6th Scandinavian Conference on Image Analysis (6SCIA)
will be arranged by the Pattern Recognition Society of Fin-
land from June 19 to June 22, 1989. The conference is spon-
sored by the International Association for Pattern Recogni-
tion. The conference will be held at the University of Oulu.
Oulu is the major industrial city in North Finland, situated
not far from the Arctic Circle. The conference site is at
the Linnanmaa campus of the University, near downtown Oulu.
CONFERENCE COMMITTEE
Erkki Oja, Conference Chairman
Matti Pietik{inen, Program Chairman
Juha R|ning, Local organization Chairman
Hannu Hakalahti, Exhibition Chairman
Jan-Olof Eklundh, Sweden
Stein Grinaker, Norway
Teuvo Kohonen, Finland
L. F. Pau, Denmark
SCIENTIFIC PROGRAM
The program will consist of contributed papers, invited
talks and special panels. The contributed papers will cov-
er:
* computer vision
* image processing
* pattern recognition
* perception
* parallel algorithms and architectures
as well as application areas including
* industry
* medicine and biology
* office automation
* remote sensing
There will be invited speakers on the following topics:
Industrial Machine Vision
(Dr. J. Sanz, IBM Almaden Research Center)
Vision and Robotics
(Prof. Y. Shirai, Osaka University)
Knowledge-Based Vision
(Prof. L. Davis, University of Maryland)
Parallel Architectures
(Prof. P. E. Danielsson, Link|ping University)
Neural Networks in Vision
(to be announced)
Image Processing for HDTV
(Dr. G. Tonge, Independent Broadcasting Authority).
Panels will be organized on the following topics:
Visual Inspection in the Electronics Industry (moderator:
prof. L. F. Pau);
Medical Imaging (moderator: prof. N. Saranummi);
Neural Networks and Conventional Architectures (moderator:
prof. E. Oja);
Image Processing Workstations (moderator: Dr. A. Kortekan-
gas).
SUBMISSION OF PAPERS
Authors are invited to submit four copies of an extended
summary of at least 1000 words of each of their papers to:
Professor Matti Pietik{inen
6SCIA Program Chairman
Dept. of Electrical Engineering
University of Oulu
SF-90570 OULU, Finland
tel +358-81-352765
fax +358-81-561278
telex 32 375 oylin sf
net scia@steks.oulu.fi
The summary should contain sufficient detail, including a
clear description of the salient concepts and novel features
of the work. The deadline for submission of summaries is
December 1, 1988. Authors will be notified of acceptance by
January 31st, 1989 and final camera-ready papers will be re-
quired by March 31st, 1989.
The length of the final paper must not exceed 8 pages. In-
structions for writing the final paper will be sent to the
authors.
EXHIBITION
An exhibition is planned. Companies and institutions in-
volved in image analysis and related fields are invited to
exhibit their products at demonstration stands, on posters
or video. Please indicate your interest to take part by con-
tacting the Exhibition Committee:
Matti Oikarinen
P.O. Box 181
SF-90101 OULU
Finland
tel. +358-81-346488
telex 32354 vttou sf
fax. +358-81-346211
SOCIAL PROGRAM
A social program will be arranged, including possibilities
to enjoy the location of the conference, the sea and the
midnight sun. There are excellent possibilities to make
post-conference tours e.g. to Lapland or to the lake dis-
trict of Finland.
The social program will consist of a get-together party on
Monday June 19th, a city reception on Tuesday June 20th, and
the conference Banquet on Wednesday June 21st. These are all
included in the registration fee. There is an extra fee for
accompanying persons.
REGISTRATION INFORMATION
The registration fee will be 1300 FIM before April 15th,
1989 and 1500 FIM afterwards. The fee for participants cov-
ers: entrance to all sessions, panels and exhibition;
proceedings; get-together party, city reception, banquet and
coffee breaks.
The fee is payable by
- check made out to 6th SCIA and mailed to the
Conference Secretariat; or by
- bank transfer draft account or
- all major credit cards
Registration forms, hotel information and practical travel
information are available from the Conference Secretariat.
An information package will be sent to authors of accepted
papers by January 31st, 1989.
Secretariat:
Congress Team
P.O. Box 227
SF-00131 HELSINKI
Finland
tel. +358-0-176866
telex 122783 arcon sf
fax +358-0-1855245
There will be hotel rooms available for participants, with
prices ranging from 135 FIM (90 FIM) to 430 FIM (270 FIM)
per night for a single room (double room/person).
------------------------------
Date: Fri, 4 Nov 88 12:26 H
From: <CHTEH%NUSEEV.BITNET@CUNYVM.CUNY.EDU>
Subject: ICIP'89 : IEEE 1989 Int Conf on Image Processing
IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
(ICIP'89)
5-8 September, 1989, Singapore
CALL FOR PAPERS (Updated)
The 1989 IEEE International Conference on Image
Processing (ICIP'89) will be held in Singapore on 5-8
September, 1989. The conference is jointly organized by the
Computer Chapter, IEEE Singapore Section and the Department
of Electrical Engineering, National University of Singapore.
The conference will include regular sessions on all aspects
of the theory and applications of image processing. In
addition, tutorials by eminent speakers presenting the
state-of-the-art in selected areas of image processing will
be offered. An exhibition will be held in conjunction with
the conference.
Papers describing original work in all aspects of image
processing are invited. Topics for regular sessions
include, but are not limited to, the following :
Image analysis/modeling Office image processing
Image restoration/enhancement Machine vision
Video communications AI vision techniques
Image pattern recognition VLSI implementation
Remote sensing System architecture
Biomedical imaging Color image processing
Authors are invited to submit four copies of an
extended summary of at least 1000 words to :
Technical Program Chairman, ICIP'89
c/o Meeting Planners Pte Ltd
100 Beach Road, #33-01
Shaw Towers, Singapore 0718
Republic of Singapore
Telex : RS40125 MEPLAN
Fax : (65) 2962670
E-mail : OSH@NUSEEV.BITNET
The summary should contain sufficient detail, including
a clear description of the salient concepts and novel
features of the work. The summary should include the
authors' names, addresses, affiliations, and telephone,
telex and fax numbers. The authors should also indicate one
or more of the above topics that best describe the contents
of the paper.
Proposals for tutorials and special sessions are also
welcome and should be addressed to the Technical Program
Chairman before 16 January 1989.
AUTHORS' SCHEDULE
Submission of summary 1 February 1989
Notification of acceptance 31 March 1989
Submission of final manuscripts 1 June 1989
------------------------------------------------------------
Date: 2 Nov 88 17:58:33 GMT
From: uflorida!proxftl!francis@gatech.edu (Francis H. Yu)
Subject: 1989 Symposium on Chinese Text Processing
Organization: Proximity Technology, Ft. Lauderdale
*************************************
* CALL FOR PAPER *
*************************************
1989 Symposium on Chinese Text Processing
Boca Raton, FL, March 16-17, 1988
Sponsored by
The Chinese Language Computer Society of Florida
The Symposium's objective is to serve as an international
forum for the presentation of research conducted in the area
of ideographics.
Papers describing original work in all aspects of
ideographics are invited.
A non-exclusive sample of the included topics follows:
* Charactor Input and Display
* Charactor Encoding
* Disign of Ternimals and Keyboards
* Chinese Language Lexicon
* Chinese Language Parsing
* Machine Translation
* Optical Charactor Recognition
* Computer Ideographics in 90's
* Speech Recognition
* Application
Word Processors
Electronic Typewriters
Desk Top Publishing
Typesetting
Authors please submit 3 copies of proposed paper to
Paper Review Committee
1989 Symposium on Chinese Text Processing
Florida Atlantic University
Department of Computer Engineering
500 NW 20 Street
Boca Raton, FL 33486
Symposium Chairman
Dr George Kostopoulos
(407) 393-3463
Paper Submission Deadline: December 1, 1988
Notification of Acceptance: January 1, 1989
Final Manuscript Due: February 1, 1989
FRANCIS H. YU (305)-566-3511
Proximity Technology, Inc., Ft. Lauderdale, FL, USA
Domain: francis@proxftl.uucp
Uucp: ...!{ uunet, uflorida!novavax }!proxftl!francis
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/12/88)
Vision-List Digest Fri Nov 11 14:13:22 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Vision systems question/advice
Translator
----------------------------------------------------------------------
Date: 11 Nov 88 03:36:37 GMT
From: rr21@isl1.ri.cmu.edu (Rajan Ramaswamy)
Subject: Vision systems question/advice
Keywords: vision system, steel plants, sensing
Organization: Carnegie-Mellon University, CS/RI
APPLYING COMPUTER-VISION TO STEEL PLANT PROCESS CONTROL
We are investigating the feasibility of installing vision systems to
replace existing sensing systems in steel plants. These are electric
arc furnaces that produce couple of hundred tons of molten steel (3000
F) every few hours and the people concerned want to move their sensors
as far away as they possibly can.
I would appreciate any views/advice/warnings/EXPERIENCE that anyone on
the net has to offer. Pointers to relevant references or equipment
will also be welcome.
The following is a summary of the application and problems we foresee,
o We want to sense the position of large (10 ft), slow moving objects
(~ 1 ft/sec) with reasonable accuracy (~1 inch). These items are, the roof
of a furnace, the tilt angle of the furnace etc.
o Light conditions are extremely variable. There is an order of magnitude
change (at least) when the furnace lid is opened. Lots of shadows etc.
o Lots of dust, vibration and sparks flying about are to be expected.
o The temperatures may be rather high (100+ F). This requires that cameras
be decently far off.
o Processing should be completed in less than 5 seconds.
Thanks a lot,
Rajan
p.s.: If you need further details to answer anything PLEASE contact me.
--
"Until the philosophy of one race superior, and another, inferior,
is finally and permanently discredited and abandoned, it's WAR.
Haile Selassie,Emperor of Abyssinia,
O.A.U. Conference 197?
------------------------------
Date: Thu, 10 Nov 88 14:36:46 GMT
From: Guanghua Zhang <mcvax!cs.hw.ac.uk!guanghua@uunet.UU.NET>
Subject: Translator
For the moment, I am working on a knowledge-based vision system
which includes a commercial Solid Modelling package. The Solid Modeller
represents curve surface as a set of facets which can be displayed on the
screen or printed. What I am trying to do is to write a translator to
transform the output data into the real from, e.g. cyclinder.
Could anybody give me some pointers about the existing work or any
publications ?
Thanks in advance.
guanghua
[ I believe the work on Acronym and Successor by Binford and his students
at Stanford has addressed this?
phil... ]
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/20/88)
Vision-List Digest Sat Nov 19 12:16:19 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Translator
bibliography requests
Assistant Professor position at MIT
----------------------------------------------------------------------
Date: Sat, 12 Nov 88 13:22:20 GMT
From: Guanghua Zhang <mcvax!cs.hw.ac.uk!guanghua@uunet.UU.NET>
Subject: Translator
Following the previous mail, I describe more about our system on request.
The Solid Modelling package we use is RoboSolid Modeller from Robocom
Limited, UK (or Robosystems in some places).
Models can be built interactively on the screen using mouse. One of the output
files is in the format of SXF, which includes coordinate data of vertex,
facets formed from those vertices and the adjacence of those facets.
The work I am intending to do starts from the SXF file. I woulde like to
translate the SXF fromat into the internal representation of models in
the model base of our vision system.
I'd like to hear anything about using comercial modelling packages
as the modeller of vision systems.
Thanks a lot.
guanghua
[ I requested this author post more info about this package. If you know of
any other solid modelling packages which you feel could be useful for
vision, please post a summary and pointers to the source.
phil... ]
------------------------------
Date: Mon, 14 Nov 88 10:20:55 +0100
From: prlb2!ronse@uunet.UU.NET (Christian Ronse)
Subject: bibliography requests
Summary: s-mail address needed if you want a copy
Note to all those who requested me a copy of that bibliography:
1) As this bibliography will be copyrighted, I cannot make it available in
electronic form (FTP or anything else). I can only give preprints.
2) My electronic mailer does not transmit paper.
So: no postal address means request not honoured.
Christian Ronse maldoror@prlb2.UUCP
{uunet|philabs|mcvax|cernvax|...}!prlb2!{maldoror|ronse}
Time is Mona Lisa
------------------------------
Date: Mon, 14 Nov 88 14:48:13 est
From: Steve Pinker <steve@psyche.mit.edu>
Site: MIT Center for Cognitive Science
vision-list@ads.com
Subject: Assistant Professor position at MIT
November 8, 1988
JOB ANNOUNCEMENT
The Department of Brain and Cognitive Sciences (formerly the
Department of Psychology) of the Massachusetts Institute of
Technology is seeking applicants for a nontenured, tenure-track
position in Cognitive Science, with a preferred specialization in
psycholinguistics, reasoning, or knowledge representation. The
candidate must show promise of developing a distinguished
research program, preferably one that combines human
experimentation with computational modeling or formal analysis,
and must be a skilled teacher. He or she will be expected to
participate in department's educational programs in cognitive
science at the undergraduate and graduate levels, including
supervising students' experimental research and offering courses
in Cognitive Science or Psycholinguistics.
Applications must include a brief cover letter stating the
candidate's research and teaching interests, a resume, and at
least three letters of recommendation, which must arrive by
January 1, 1989. Address applications to:
Cognitive Science Search Committee
Attn: Steven Pinker, Chair
E10-018
Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology
Cambridge, MA 02139
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/03/88)
Vision-List Digest Fri Dec 02 16:16:37 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
DeScreening
dissemination of sharware for Image Processing and Computer Vision
Robotics Seminar
----------------------------------------------------------------------
Date: Thu, 24 Nov 88 15:47:37 IST
From: Shelly Glaser 011 972 3 5450119 <GLAS%TAUNIVM.BITNET@CUNYVM.CUNY.EDU>
Subject: DeScreening
Please publish the following question in the Vision Newsletter:
I am looking for information on practical solutions to the
"de-screening" problem: taking a half-toned image (like the one
in printed book or magazine) and removing the half-tone screen
so we get a true continuous-gray-scale image (as opposed to the
binary pulse area modulated half-tone image). The obvious
solution, low-pass filtering, often kills too much of the fine
details in the image, so I am looking for something more
sophisticated.
Many thanks,
Sincerely Yours,
Shelly Glaser
Department of Electronic, Communication, Control
and Computer Systems
Faculty of Engineering
Tel-Aviv University
Tel-Aviv, Israel
FAX: 972 3 419513
Computer network: GLAS@TAUNIVM.BITNET
------------------------------
Date: 26 Nov 88 18:58:00 GMT
From: annala%neuro.usc.edu@oberon.usc.edu (A J Annala)
Subject: possible use of comp.ai.vision
Organization: University of Southern California, Los Angeles, CA
There has been some discussion in comp.graphics about using comp.ai.vision
as the home for discussions about andf distribution of image processing
software. I personally suspect that this would not be an appropriate use
of the comp.ai.vision group; however, I would appreciate email to my user
account (which I will summarize) on this issue.
Thanks, AJ Annala ( annala%neuro.usc.edu@oberon.usc.edu )
[ Discussions on IP sofware are most definitely appropriate for the Vision
List and comp.ai.vision. Yet, as with other SIG networks, it is not
appropriate to submit the code in this forum. Rather, if there is
shareware IP and CV software which should be disseminated, then a
new network newsgroup entitled something like COMP.BINARIES.VISION
should be established. This requires a site and moderator for this new
net which can establish and manage this new facility. Any volunteers?
phil... ]
------------------------------
Date: Tue, 29 Nov 88 19:30:46 PST
From: binford@Boa-Constrictor.Stanford.EDU.stanford.edu (Tom Binford)
Subject: Robotics Seminar
Robotics Seminar
Monday, Dec 7, 1988
4:15pm Cedar Hall Conference Room
SOLVING THE STEREO CONSTRAINT EQUATION
Stephen Barnard
Artificial Intelligence Center
SRI International
The essential problem of stereo vision is to find a disparity map
between two images in epipolar correspondence. The stereo constraint
equation, in any of its several forms, specifies a function of disparity
that is a linear combination of photometric error and the first order
variation of the map. This equation can also be interpreted as the
potential energy of a nonlinear, high dimensional dynamic system. By
simulating either the deterministic newtonian dynamics or the
statistical thermodynamics of this system one can find approximate
ground states (i.e., states of minimum potential energy), thereby
solving the stereo constraint equation while constructing a dense
disparity map.
The focus of this talk will be a stochastic method that uses a
microcanonical version of simulated annealing. That is, it explicitly
represents the heat in the system with a lattice of demons, and it cools
the system by removing energy from this lattice. Unlike the
``standard'' Metropolis version of simulated annealing, which simulates
the canonical ensemble, temperature emerges as a statistical property of
the system in this approach. A scale-space image representation is
coupled to the thermodynamics in such a way that the higher frequency
components come into play as the temperature decreases. This method has
recently been implemented on a Connection Machine.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/08/88)
Vision-List Digest Wed Dec 07 20:05:04 PDT 88 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: If you have difficulties posting... ---------------------------------------------------------------------- Date: Wed, 7 Dec 88 20:04:42 PST From: Vision-List-Request <vision@deimos.ads.com> Subject: If you have difficulties posting... Please let me know if you have posted and not seen the posting. There have been some reported problems. phil... ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/17/88)
Vision-List Digest Fri Dec 16 12:44:29 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
announcement: Image Understanding & Machine Vision, Human & Machine Vision
repost Geometer and request for info
Call for Papers for ACM INTERFACES meeting
----------------------------------------------------------------------
Date: Fri, 16 Dec 88 10:58 EST
From: Sandy Pentland <sandy@MEDIA-LAB.MEDIA.MIT.EDU>
Subject: announcement
CALL FOR PAPERS:
Optical Society Topical Meeting on
IMAGE UNDERSTANDING AND MACHINE VISION
June 12-14, 1989, Cape Cod, Massachusetts
chair: Alex Pentland, M.I.T.
FIFTH WORKSHOP ON HUMAN AND MACHINE VISION
June 15, 1989, Cape Cod, Massachusetts
chairs: Jacob Beck, U. Oregon,
Azriel Rosenfeld, U. Maryland
SCOPE OF TOPICAL MEETING: In the last few years the availability of
inexpensive image processing equipment has caused an upsurge of interest
in real-time vision, and now groups all across the country are engaged
in such projects. This meeting will focus on the results of these
projects.
We especially encourage research reports on new algorithms and
techniques that are (1) already demonstrated on real imagery, and (2)
have a computational complexity that makes real-time applications
economically feasible within the next few years. Papers concerning
implemented models of human visual processing are appropriate for this
conference. Papers which are purely theoretical or purely application
oriented are not appropriate for this meeting.
Technical Committee: Ted Adelson (M.I.T.), Ruzena Bajcsy (U.
Pennsylvania) Dana Ballard (U. Rochester), Peter Burt (SRI Sarnoff
Research Center) Steve Case (Cyberoptics), Ramesh Jain (U. Michigan).
WORKSHOP ON HUMAN AND MACHINE VISION: June 15, the day following the
Topical Meeting, will be devoted to the Fifth Workshop on Human and
Machine Vision. The workshop will consist of invited papers on models
for human visual processes. There will be a separate, nominal
registration fee for this workshop.
SUBMISSION OF PAPERS: Each author is requested to submit a SUMMARY
PAPER of no more than FOUR pages, including all figures and equations.
Original figures or glossy photographs must be submitted, pasted into
position on the summary pages. If accepted this summary will be
reproduced directly by photo offset and be published in the meeting
proceedings. The first page of the summary must begin with title,
author, affiliation, and address.
Authors must also submit a 25 word abstract on a separate sheet of
paper, with the title at the top of the page in 12-point upper- and
lower-case letters, followed by the authors name, affiliation, complete
return address, and the body of the abstract. In the case of multiple
authors each author's name and address should be listed separately after
the title. If the paper is accepted this abstract will appear in the
advance program.
All abstracts and summaries must reach the Optical Society office by
February 21, 1989. Send your paper to:
Image Understanding
Optical Society of America
1816 Jefferson Place NW
Washington, DC 20036
(202) 223-0920
Authors will be notified of acceptance by mid April.
REGISTRATION at the meeting is $220 for Optical Society members, $260
for non-members, $90 for students. Preregistration materials are
available from the Optical Society, at the above address, before May 12,
1989.
HOUSING will be at the Sea Crest Resort, North Falmouth, Cape Cod, MA.,
(508)540-9400. Convention rates will be $122.50/night single occupancy,
$74.50 per person double occupancy. BOTH RATES INCLUDE ROOM, BREAKFAST,
LUNCH, AND TAX, and include use of recreational facilities. All
reservations, plus a $75 deposit check payable to the Sea Crest, must
reach the hotel by MAY 10, 1989, and must note affliation with the
Optical Society. Check-in time is 3:00 pm; rates apply June 10-17,
1989.
------------------------------
Date: Fri, 16 Dec 88 12:43:51 PST
From: Vision-List-Request <vision@deimos.ads.com>
Subject: repost Geometer and request for info
A subscriber posted a message which specified the location of Geometer
(a modeling package) on the UMASS FTP system. Please repost. Mailer
problems trashed the posting.
thanks,
phil...
------------------------------
Subject: Call for Papers
Date: Mon, 12 Dec 88 17:54:24 -0500
From: mitchell%community-chest.mitre.org@gateway.mitre.org
***** CALL FOR PAPERS AND PARTICIPATION *****
28th Annual Technical Symposium of the Washington, D.C. Chapter of the ACM
INTERFACES: Systems and People Working Together
National Institute of Standards and Technology
Gaithersburg, Maryland - August 24, 1989
No computer is an island. Increasingly, systems are being tied together
to improve their value to the organizations they serve. This symposium will
explore the theoretical and practical issues in interfacing systems and in
enabling people to use them effectively.
*** SOME TOPICS OF INTEREST FOR SUBMITTED PAPERS ***
* HUMAN FACTORS *
User interfaces Meeting the needs of handicapped users
Conquering complexity Designing systems for people
Intelligent assistants The human dimension of information interchange
* SYSTEMS INTEGRATION *
Communications networks Distributed databases
Data standardization System fault tolerance
Communications standards (e.g. GOSIP)
* STRATEGIC SYSTEMS *
Decision support systems Embedding expert systems in information systems
Strategic info systems Computer Aided Logistics Support (CALS)
* SYSTEM DEVELOPMENT AND OPERATION *
Quality control and testing Designing a system of systems
System management Conversion and implementation strategies
Software tools and CASE Identifying requirements thru prototyping
* ENABLING TECHNOLOGIES FOR APPLICATIONS PORTABILITY *
Ada Database management
Open software Open protocol technology
Operating systems (e.g., POSIX)
==> DON'T BE LIMITED BY OUR SUGGESTIONS - MAKE YOUR OWN!
Both experienced and first-time authors are encouraged to present their
work. Papers will be refereed. A length of 10 to 20 double-spaced pages is
suggested.
Those presenting a paper are entitled to register for the symposium at
the early advance registration rate.
To propose special sessions or noncommercial demonstrations, please send
three copies of an extended abstract to the Program Chairman at the address
below.
Note: A paper must include the name, mailing address, and telephone
number of each author or other presenter. Authors of accepted papers must
transfer copyright to ACM for material published in the Proceedings (excepting
papers that cannot be copyrighted under Government regulations).
The ACM policy on prior publication was revised in 1987. A complete
statement of the policy appears in the November 1987 issue of Communications
of the ACM. In part it states that "republication of a paper, possibly
revised, that has been disseminated via a proceedings or newsletter is
permitted if the editor of the journal to which it has been submitted judges
that there is significant additional benefit to be gained from republication."
*** SCHEDULE ***
March 2, 1989 Please send five copies of your paper to the Program Chairman:
Dr. Milton S. Hess
American Management Systems, Inc.
1525 Wilson Boulevard
Arlington, VA 22209
April 13, 1989 Acceptance notification
June 22, 1989 Final camera ready papers are due
August 24, 1989 Presentation at the symposium
If you have any questions or suggestions, please contact:
Symposium General Chairman: Charles E. Youman, The MITRE Corporation,
(703) 883-6349 (voice), (703) 883-6308 (FAX), or youman@mitre.org (internet).
Program Chairman: Dr. Milton Hess, American Management Systems, Inc.,
(703) 841-5942 (voice) or (703) 841-7045 (FAX).
NIST Liaison: Ms. Elizabeth Lennon, National Institute of Standards and
Technology (formerly the National Bureau of Standards), (301) 975-2832 (voice)
or (301) 948-1784 (FAX).
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/22/88)
Vision-List Digest Wed Dec 21 15:38:00 PDT 88
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Geometer
----------------------------------------------------------------------
Date: Mon, 19 Dec 88 17:36 EST
From: "C. Connolly" <GEOMETER@cs.umass.EDU>
Subject: Geometer
The GE R&D center and (more recently) the vision group at UMass have
been developing and using a solid modeler with some algebraic
manipulation capabilities for various vision & automated reasoning
experiments. The system is called "Geometer", and some of its salient
features are:
- Written in Common Lisp (runs on Symbolics, TI, Lucid, DEC)
- Reliable at planar modeling
- Capable of curved surface modeling
- contains machinery for polynomial & transcendental function
arithmetic, algebraic numbers, Grobner basis computation.
- contains machinery for various projections & transformations
It is available via anonymous FTP from COINS.CS.UMASS.EDU, although some
people have reported trouble with the connection. The files are in the
directories:
VIS$DISK:[GEOMETER]*.LISP
VIS$DISK:[GEOMETER.DOC]*.TEX
If you do get a copy this way, please send a message to
GEOMETER@COINS.CS.UMASS.EDU, just for verification purposes. More
information will probably be available at the next DARPA IU workshop.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/31/88)
Vision-List Digest Fri Dec 30 09:55:05 PDT 88 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: backissues of Vision List DIgest available via anonymous FTP ---------------------------------------- Date: Fri, 30 Dec 88 09:54:42 PST From: Vision-List-Request <vision@deimos.ads.com> Subject: backissues of Vision List DIgest available via anonymous FTP Backissues of the Vision List Digest are now available via anonymous FTP. For those of you without FTP connection, limited backissues may still be obtained by mailing your request to Vision-List-Request@ADS.COM . To access the Digest backissues from anonymous FTP: 1) FTP to ADS.COM 2) Login name is ANONYMOUS 3) Once you're logged on, change directory (cd) to pub/VISION-LIST-ARCHIVE 4) Each file contains an archived issue, and the file name is the date and time the issue was created. I hope that the availability of these backissues will provide a better dissemination of information and add to the usefulness of the Vision List. Please let me know if you have any problems. I'd like to see more discussion of vision issues on the List. Some potential topics are: assessment of recent advances and approaches, pointers to interesting literature or equipment, state of funding and the economic environment for vision research, impact of technologies on vision work, short summaries of work going on in vision labs, relationships between biological and machine vision, current and emerging paradigms, deeply personal vignettes about key workers in the field (only kidding), etc. The continued posting of conferences and talks, dissertation topics/ defenses, call for papers, etc. continues to be a valuable contribution to the List. Also, please let me know if you've had trouble posting, receiving the List, multiple copies, etc. We continue to restructure the mechanics of the List, and your feedback is always valued. phil... ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (01/06/89)
Vision-List Digest Thu Jan 05 18:34:07 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Comments on Vision List
Re: AICPA
----------------------------------------------------------------------
Date: Tue, 3 Jan 89 10:46:04 PST
From: oyster@tcville.hac.com (Michael Oyster)
Subject: Comments on Vision List
I have been subscribing to Vision List through UCLA and now directly
through work for more than three years. Vision list has been useful to
me primarily in providing advance notice for conferences. While
I have found vision list to be useful, I would like to make some
hopefully productive comments.
Vision List needs more technical depth. I'm not particularly interested
in reading notes by beginning graduate students about what's a good
frame grabber or what's a good master's topic. We need contributions
from serious researchers concerning CURRENT research topics that
can not be found in the open literature because of their late breaking
nature.
I know this is easier said than done because the hard part is getting
serious people interested and involved. If I can lend a hand, I would
be glad to help.
Best wishes,
Mike Oyster
Hughes Aircraft
[ I agree we need more technical depth. How can we make it happen?
phil...]
------------------------------
Date: Sat, 31 Dec 88 15:16:47 GMT
From: Steven Zenith <mcvax!inmos!zenith@uunet.UU.NET>
Subject: Re: AICPA
occam user group
* artificial intelligence *
special interest group
CALL FOR PAPERS
1st technical meeting of the OUG AISIG
ARTIFICIAL INTELLIGENCE
AND
COMMUNICATING PROCESS ARCHITECTURE
17th and 18th of July 1989, at Imperial College, London UK.
Keynote speakers will include
* Prof. Iann Barron *
"Inventor of the transputer"
The conference organising committee includes:
Dr. Atsuhiro Goto Institute for New Generation Computer
Technology (ICOT), Japan.
Dr.med.Ulrich Jobst Ostertal - Klinik fur Neurologie und
klinische Neurophysiologie
Dr. Heather Liddell, Queen Mary College, London.
Prof. Dr. Y. Paker, Polytechnic of Central London
Prof. Dr. L. F. Pau, Technical University of Denmark.
Prof. Dr. Bernd Radig, Institut Fur Informatik, Munchen.
Prof. Dr. Alan Robinson Syracuse University, U.S.A.
Prof. Dr. David Warren Bristol University, U.K.
Conference chairmen:
Dr. Mike Reeve Imperial College, London
Steven Ericsson Zenith INMOS Limited, Bristol (Chairman OUG AISIG)
Topics include:
The transputer and a.i. Real time a.i
Applications for a.i. Implementation languages
Underlying kernel support Underlying infrastructure
Toolkits/environments Neural networks
Papers must be original and of high quality. Submitted papers
should be about 20 to 30 pages in length, double spaced and single
column, with an abstract of 200-300 words. All papers will be
refereed and will be assessed with regard to their quality and
relevance.
A volume is being planned to coincide with this conference to be
published by John Wiley and Sons as a part of their book series on
Communicating Process Architecture.
Papers must be submitted by the 1st of February 1989. Notification
of acceptance or rejection will be given by March 1st 1989.
Final papers (as camera ready copy) must be provided by April 1st
1989.
Submissions to be made to either:
Steven Ericsson Zenith Mike Reeve
INMOS Limited, Dept. of Computing,
1000 Aztec West, Imperial College,
Almondsbury, 180 Queens Gate,
Bristol BS12 4SQ, London SW7 2BZ,
UNITED KINGDOM. UNITED KINGDOM.
Tel. 0454 616616 x513 Tel. 01 589 5111 x5033
email: zenith@inmos.co.uk email: mjr@doc.ic.ac.uk
Regional Organisers:
J.T Amenyo Ctr. Telecoms Research, Columbia University,
Rm 1220 S.W. Mudd, New York, NY 10027-6699.
Jean-Jacques Codani INRIA, Domaine de Voluceau - Rocquencourt,
B.P.105-78153 Le Chesnay Cedex, France.
Pasi Koikkalainen Lappeenranta University of Technology,
Information Technology Laboratory,
P.O.BOX 20, 53851 Lappeenrantra, Finland.
Kai Ming Shea Dept. of Computer Science,
University of Hong Kong, Hong Kong.
Dr. Peter Kacsuk Multilogic Computing, 11-1015 Budapest,
Csalogaiy u. 30-32. Hungary.
* Steven Ericsson Zenith Snail mail: INMOS Limited, 1000 Aztec West,
| zenith@inmos.uucp Almondsbury, Bristol BS12 4SQ. UK.
zenith@inmos.co.uk Voice: (UK)0454 616616x513
** All can know beauty as beauty only because there is ugliness **
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (01/15/89)
Vision-List Digest Sat Jan 14 12:40:07 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Request for Industrial Research Topics
How to evaluate computer vision techniques?
Course announcement: Computational Neuroscience
Role of Vision List (posted to comp.graphics)
IEEE 1989 Int Conf on Image Processing (Last Call for Paper)
----------------------------------------------------------------------
Date: Mon, 09 Jan 89 08:42:03 -0500
Subject: Request for Industrial Research Topics
<8901060238.AA28121@ads.com>
From: "Kenneth I. Laws" <klaws@note.nsf.gov>
Most engineers start with real problems and do research
to find appropriate tools and solutions. Most academics
start with tools and do research to find appropriate
problems and funding agencies. Perhaps Vision-List
could help bring the two together by generating a list
of real-world problems that need to be solved. This would
help the master's students and the companies with the
problems. I've been told that it would also be a big
help to the funding agencies, particularly the NSF
Small Business program. (It seems that publishing a
specific problem description usually draws good proposals,
whereas vague RFPs may draw nothing.)
I'm not thinking about generic research topics such as
shape from shading or stereo vision -- everyone knows about
those. I'm thinking about applications such as inspecting
solder joints or nose cone windings. Are there specific
problems which seem solvable but for which no off-the-shelf
technology is available? Could some startup or small business
profit by helping your production line with a particular
inspection task? What specific capabilities should the funding
agencies be trying to develop in the next five years?
Academics usually don't wish to reveal their ideas until
they can put together at least a conference paper -- at which
time there is little motivation for publishing in Vision-List.
The field also suffers from lack of definitive solutions for
any problem, making it impossible for any researcher to
declare victory and close out a line of research. I hope that
the engineers will be less reticent in sharing the problems
they are working on (or have insufficient time or interest
to work on). Making a problem widely known may be the
quickest way of uncovering an easy solution or a worthwhile
research priority.
-- Ken
------------------------------
Date: Fri, 6 Jan 89 14:26:14 pst
From: ramin@scotty.stanford.edu (Ramin Samadani)
Subject: How to evaluate computer vision techniques?
I am looking for published results in "quality of results" of computer vision
techniques.
In reading some of the computer vision literature, I get the feeling that
many techniques are proposed, but are not fully tested. Is this true or have
I missed some body of work out there? Are there any standard or published
methods for testing new techniques? Could someone point me to any
literature on evaluation of the "quality" of computer vision techniques? Are
there studies where the techniques have been tried on a large number of
images?
Ramin Samadani
202 Durand Bldg.
Electrical Engineering
Stanford, CA 94305
ramin@scotty.stanford.edu
------------------------------
Date: Thu, 12 Jan 89 09:19:51 EST
From: tony@cortex.psych.nyu.edu (Tony Movshon)
Subject: Course announcement: Computational Neuroscience
Cold Spring Harbor Laboratory Course Announcement, Summer 1989
COMPUTATIONAL NEUROSCIENCE: VISION
Instructors:
Ellen C. Hildreth, Massachusetts Institute of Technology
J. Anthony Movshon, New York University
July 2 - 15
Computational approaches to neuroscience have produced important advances
in our understanding of neural processing. Prominent successes have come in
areas where strong inputs from neurobiological, behavioral and computational
approaches can interact. Through a combination of lectures and hands-on
experience with a computer laboratory, this intensive course will examine
several areas, including feature extraction, motion analysis, binocular
stereopsis, color vision, higher level visual processing, visual neural net-
works, and oculomotor function. The theme is that an understanding of the com-
putational problems, the constraints on solutions to these problems, and the
range of possible solutions can help guide research in neuroscience. Students
should have experience in neurobiological or computational approaches to
visual processing. A strong background in mathematics will be beneficial.
Past lecturers have included: Richard Andersen, Peter Lennie, John Maun-
sell, Gerard Medioni, Michael Morgan, Ken Nakayama, Tomaso Poggio, Terrence
Sejnowski, William Thompson, Shimon Ullman, and Brian Wandell.
The deadline for application is March 15, 1989. Applications and addi-
tional information may be obtained from:
REGISTRAR
Cold Spring Harbor Laboratory
Box 100
Cold Spring Harbor, New York 11724
Telephone: (516) 367-8343
------------------------------
Date: Sat, 14 Jan 89 12:37:03 PST
From: Vision-List-Request <vision@deimos.ads.com>
Subject: Role of Vision List (posted to comp.graphics)
[ Apparently, the role of comp.ai.vision and the Vision List has been
discussed on comp.graphics. E.g., they wanted to know if image processing
was appropriate for this List. The following is a copy of the message I
posted to that group.
phil... ]
The role of comp.ai.vision has been discussed in this group, and as
moderator, I thought it would be appropriate to outline the role of
the vision newsgroup.
The Vision List is a moderated newsgroup for which messages may be
posted by mailing to Vision-List@ADS.COM. Administrative questions
(e.g., to get added/deleted, editorial comments, etc) should be sent
to Vision-List-Request@ADS.COM. The Vision List is distributed
through comp.ai.vision and via direct mail accounts for users which do
not have access to USENET.
The Vision List is intended to embrace discussion on a wide range of
vision topics, including physiological theory, computer vision,
machine vision and image processing algorithms, artificial
intelligence and neural network techniques applied to vision,
industrial applications, robotic eyes, implemented systems, ideas,
profound thoughts -- anything related to vision and its automation is
fair game.
Since this is a graphics newsgroup, let me carefully distinguish what
I believe the primary difference between the graphics and vision
newsgroups. Quite simply, in graphics one goes from the computer to a
screen; in vision, one goes from the sensor to the computer. I.e., the
difference is one of generation versus interpretation. So, for example, an
image processing algorithm which is of use only in image generation would
best appear in comp.graphics or a similar netgroup. Conversely,
image filtering techniques can quite useful in the initial stages of imagery
interpretation. The bottom line: If when you ask yourself "Would this be
of use in understanding imagery?" you get a "Yes!", then it should be
posted to Vision-List@ADS.COM.
Hope this has helped to clarify things a bit.
Philip Kahn
moderator, Vision List
(administrative) Vision-List-Request@ADS.COM
(submissions) Vision-List@ADS.COM
------------------------------
Date: Mon, 9 Jan 89 08:56 H
From: <CHTEH%NUSEEV.BITNET@CUNYVM.CUNY.EDU>
Subject: IEEE 1989 Int Conf on Image Processing (Last Call for Paper)
IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
(ICIP'89)
5-8 September, 1989, Singapore
CALL FOR PAPERS (Updated)
The 1989 IEEE International Conference on Image
Processing (ICIP'89) will be held in Singapore on 5-8
September, 1989. The conference is jointly organized by the
Computer Chapter, IEEE Singapore Section and the Department
of Electrical Engineering, National University of Singapore.
The conference will include regular sessions on all aspects
of the theory and applications of image processing. In
addition, tutorials by eminent speakers presenting the
state-of-the-art in selected areas of image processing will
be offered. An exhibition will be held in conjunction with
the conference.
Papers describing original work in all aspects of image
processing are invited. Topics for regular sessions
include, but are not limited to, the following :
Image analysis/modeling Office image processing
Image restoration/enhancement Machine vision
Video communications AI vision techniques
Image pattern recognition VLSI implementation
Remote sensing System architecture
Biomedical imaging Color image processing
Authors are invited to submit four copies of an
extended summary of at least 1000 words to :
Technical Program Chairman, ICIP'89
c/o Meeting Planners Pte Ltd
100 Beach Road, #33-01
Shaw Towers, Singapore 0718
Republic of Singapore
Telex : RS40125 MEPLAN
Fax : (65) 2962670
E-mail : OSH@NUSEEV.BITNET
The summary should contain sufficient detail, including
a clear description of the salient concepts and novel
features of the work. The summary should include the
authors' names, addresses, affiliations, and telephone,
telex and fax numbers. The authors should also indicate one
or more of the above topics that best describe the contents
of the paper.
Proposals for tutorials and special sessions are also
welcome and should be addressed to the Technical Program
Chairman before 16 January 1989.
AUTHORS' SCHEDULE
Submission of summary 1 February 1989
Notification of acceptance 31 March 1989
Submission of final manuscripts 1 June 1989
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/04/89)
Vision-List Digest Fri Feb 03 09:49:06 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
IEEE Workshop on Motion
Call For Papers : Neural Nets & Optimization.
NIPS CALL FOR PAPERS
Datacube local user's group
----------------------------------------------------------------------
Date: Thu, 2 Feb 89 09:25:37 EST
From: schunck@caen.engin.umich.edu (Brian Schunck)
Subject: IEEE Workshop on Motion
IEEE WORKSHOP ON MOTION
With a selection of papers intended to reflect the state of the art in
computational theories of motion perception, provide recent results
from psychophysical experiments, and discuss attempts to incorporate
motion algorithms in pratical applications, the IEEE Workshop on
Motion will bring together researchers from computer vision,
artificial intelligence, and psychophysics to discuss current work on
the representation and analysis of motion in image sequences. The
workshop will be held in Irvine, California March 20-22, 1989. Papers
will be presented on all aspects of the analysis of motion in human
and machine vision. The number of presentations will be limited to
increase time for discussion in the spirit of a workshop. The
proceedings will be published and will be available at the workshop.
Papers presented at the workshop will cover the topics of object
tracking, estimation of the parameters of object motion, motion
constraint equations, estimation of the image flow velocity field,
motion correspondence, psychophysical experiments on motion
perceptions, structure from motion, visual navigation, and object
discrimination in dynamic scenes.
The program has been completed, so no additional papers or
presentations can be scheduled. The deadline for early registration
is February 17, 1989. Attendees can Register at the workshop site
which is the Newport Beach Marriott. For further information contact:
Brian G. Schunck, Artificial Intelligence Laboratory, University of
Michigan, Ann Arbor, MI 48109-2122, (313) 747-1803,
schunck@caen.engin.umich.edu
------------------------------
Date: 1 Feb 89 17:09:23 GMT
From: harish@ece-csc.UUCP (Harish Hiriyannaiah)
Subject: Call For Papers : Neural Nets & Optimization.
Keywords: TENCON '89.
Organization: North Carolina State University, Raleigh, NC
CALL FOR PAPERS
TENCON '89 (IEEE Region 10 Conference)
SESSION
ON
OPTIMIZATION AND NEURAL NETWORKS
November 22 -- 24, 1989
Bombay, India
Under the auspices of the IEEE, the session organizers invite
submission of papers for a session on "Optimization and Neural
Networks". This session will focus on the interrelationship of
neural networks and optimization problems. Neural networks can
be seen to be related to optimization in two distinct ways:
+ As an adaptive neural network learns from examples,
the convergence of its weights solves an optimiza-
tion problem.
+ A large class of networks , even with constant we-
ights , solves optimization problems as they settle
from initial to final state.
The areas of interest include but are not limited to:
+ Combinatorial optimization
+ Continuous optimization
+ Sensor integration ( when posed as an optimization
problem)
+ Mean Field Annealing
+ Stochastic Relaxation
Depending on the number and quality of the responses,this ses-
sion may be split into multiple sessions, with one part focus-
ing on optimizing the weight-determination process in adaptive
nets,and the second one on using those nets to solve other pro
blems.
Prospective authors should submit two copies of an extended ab
stract (not exceeding 5 pages , double spaced) of their papers
to either of the organizers by March 31, 1989. Authors will be
notified of acceptance or rejection by May 15,1989.Photo-ready
copy of the complete paper (not exceeding 25 pages double-spa-
ced) must be received by Jul 15,1989 for inclusion in the pro-
ceedings which will be published by the IEEE and distributed
at the symposium.
Session Organizers
Dr. Wesley E. Snyder / Mr. Harish P. Hiriyannaiah
Dept of Electrical and Computer Engineering
North Carolina State University
Raleigh, NC 27695-7911, USA
Telephone: (919)-737-2336
FAX: (919)-737-7382
email: {wes,harish}@ecelet.ncsu.edu -- (Internet)
mcnc!ece-csc!{wes,harish} -- (UUCP)
--
harish pu. hi. harish@ece-csc.ncsu.edu
{decvax,possibly other backbone sites}!mcnc!ece-csc!harish
I am not, therefore I think not ?
------------------------------
Date: Thu, 2 Feb 89 13:52:25 EST
From: jose@tractatus.bellcore.com (Stephen J Hanson)
Subject: NIPS CALL FOR PAPERS
CALL FOR PAPERS
IEEE Conference on
Neural Information Processing Systems
- Natural and Synthetic -
Monday, November 27 -- Thursday November 30, 1989
Denver, Colorado
This is the third meeting of a high quality, relatively small,
inter-disciplinary conference which brings together
neuroscientists, engineers, computer scientists, cognitive
scientists, physicists, and mathematicians interested in all
aspects of neural processing and computation. Several days of
focussed workshops will follow at a nearby ski area. Major
categories and examples of subcategories for papers are the
following:
1. Neuroscience: Neurobiological models of development, cellular
information processing, synaptic function, learning, and memory.
Studies and analyses of neurobiological systems and development
of neurophysiological recording tools.
2. Architecture Design: Design and evaluation of net
architectures to perform cognitive or behavioral functions and to
implement conventional algorithms. Data representation; static
networks and dynamic networks that can process or generate
pattern sequences.
3. Learning Theory Models of learning; training paradigms for
static and dynamic networks; analysis of capability,
generalization, complexity, and scaling.
4. Applications: Applications to signal processing, vision,
speech, motor control, robotics, knowledge representation,
cognitive modelling and adaptive systems.
5. Implementation and Simulation: VLSI or optical implementations
of hardware neural nets. Practical issues for simulations and
simulation tools.
Technical Program: Plenary, contributed, and poster sessions will
be held. There will be no parallel sessions. The full text of
presented papers will be published.
Submission Procedures: Original research contributions are
solicited, and will be refereed by experts in the respective
disciplines. Authors should submit four copies of a 1000-word
(or less) summary and four copies of a single-page 50-100 word
abstract clearly stating their results by May 30, 1989. Indicate
preference for oral or poster presentation and specify which of
the above five broad categories and, if appropriate, sub-
categories (for example, Learning Theory: Complexity, or
Applications: Speech) best applies to your paper. Indicate
presentation preference and category information at the bottom of
each abstract page and after each summary. Failure to do so will
delay processing of your submission. Mail submissions to Kathy
Hibbard, NIPS89 Local Committee, Engineering Center, Campus Box
425, Boulder, CO, 80309-0425.
DEADLINE FOR SUMMARIES ABSTRACTS IS MAY 30, 1989
------------------------------
Date: 2 Feb 89 23:02:38 GMT
From: manning@mmm.serc.mmm.com (Arthur T. Manning)
Subject: Datacube local user's group
Summary: Be there!
Organization: 3M Company - Software and Electronics Resource Center (SERC); St. Paul, MN
The Twin Cities Datacube Local User's Group is meeting
Thursday February 16, 4:30 pm
Micro-resources
4640 W 77th St Suite 109
Call Barb Baker for more info 612-830-1454
Speakers are welcome. Please send info to me if you're interested.
--
Arthur T. Manning Phone: 612-733-4401
3M Center 518-1 FAX: 612-736-3122
St. Paul MN 55144-1000 U.S.A. Email: manning@mmm.uucp
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/11/89)
Vision-List Digest Fri Feb 10 16:54:57 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
- Machine Vision and Applications, Volume 2, Issue 1
- Research Fellow in Computer Vision
- RE: NSF Request for Industrial Research Topics
----------------------------------------------------------------------
Date: Thu, 09 Feb 89 11:32:58 PST
From: Gerhard Rossbach <rossbach@hub.ucsb.edu>
Subject: Machine Vision and Applications, Volume 2, Issue 1
There is now a journal in the field of machine vision, integrating theory and
applications. "Machine Vision and Applications", the international journal
from Springer-Verlag is now in its second year. It is published four times a
year and has a personal subscription rate of $45.00 (including postage and
handling). The institutional rate is $105.00 (including postage and handling).
Volume 2, Issue 1 will be published the beginning of March, 1989. The contents
for this new issue are:
"Performance Assessment of Near Perfect Machines," Robert M. Haralick.
"Combined Decision Theoretic and Syntactic Approach to Image Segmentation," by
W. E. Blanz and B. J. Straub.
"Real-Time Model-Based Geometric Reasoning for Vision Guided Navigation," by
Uma Kant Sharma and Darwin Kuan.
"Report on Range Image Understanding Workshop, East Lansing, MI, March 21-23,
1988," by Ramesh Jain and Anil K. Jain.
For further information on submitting a paper or subscribing to the journal,
please send email to:
rossbach@hub.ucsb.edu or write to Springer-Verlag, 815 De La Vina Street, Santa
Barbara, CA 93101
------------------------------
Date: 10 Feb 89 09:47:00 WET
From: JOHN ILLINGWORTH <illing%ee.surrey.ac.uk@NSS.Cs.Ucl.AC.UK>
Subject: Research Fellow in Computer Vision
University of Surrey, Department of Electronic and Electrical Engineering,
United Kindom.
**********************************
RESEARCH FELLOWS : COMPUTER VISION
**********************************
Two Research Fellows are required in the Department of Electronic and
Electrical Engineering for projects in Computer Vision. The project is
called Vision As Process, VAP, and is funded under the ESPRIT BASIC
RESEARCH ACTION, BRA, program. It is an international collaboration
involving institutes at Linkoeping and Stockholm (Sweden), Aalborg
(Denmark) and Grenoble (France). Surrey Universities major
contribution will be the development of a high-level scene
interpretation module.
The project will be carried out within an active research group in
Vision, Speech and Signal Processing. The group comprises about 20
members and has extensive computing resources including SUN, VAX and
Masscomp computers as well as specialised image processing facilities.
The sucessful candidates will be required to develop, implement in
software and experimentally evaluate computer vision algorithms.
Applicants for these post should have a degree in mathematics,
electronics, computer science or physics. Previous experience in
computer vision, image analysis, knowledge based methods or pattern
recognition will be an advantage.
The appointments will be initially for two years with a salary in the
range 9,865 to 14,500 UK pounds per annum depending upon age,
qualifications and experience (superannuation under USS conditions).
Applications in the form of a curriculum vitae (3 copies)
including the names and addresses of two referees should be sent to the
Personnel Office (JLG), University of Surrey, Guildford, Surrey GU2 5XH.
Further information may be obtained from:
Dr J. Kittler (0483 509294) or
Dr J. Illingworth (0483 571281 ext 2299) at
Department of Electronic and Electrical Engineering, Surrey University, UK.
------------------------------
Date: Tue, 07 Feb 89 11:29:23 -0500
Subject: RE: Request for Industrial Research Topics
From: "Kenneth I. Laws" <klaws@nsf.GOV>
> From: skrzypek@CS.UCLA.EDU (Dr Josef Skrzypek)
>>> MOST ACADEMICS START WITH TOOLS AND DO RESEARCH TO FIND APPROPRIATE
>>> PROBLEMS AND FUNDING AGENCIES....
> This is a rather naive view of academics approach to problem solving.
> Ken, you have mixed it up. Normally it's the other way around. One
> thing is certain, having tools and poking around, with the hope of
> finding a problem is a prescription for very poor science and probably
> bad engineering. Is there a fundamental change in NSF philosophy?
No, NSF hasn't changed -- except for the constant turnover in
program directors and their viewpoints. And I'll admit to
overstating the case. I don't know the proportion of academics
who start with tools, and I have certainly seen engineers (or at
least members of technical staff) who have wanted to start at the
tool end. Witness the recent burst of activity in neural
networks, or previous interest in orthogonal transforms, Hough
transforms, iterative relaxation, pyramid relaxation, etc.
I share your concern that this leads to bad science (and
especially to bad engineering). In a few cases, the emphasis on
tools is wholly justified. Someone has to study them, and to
provide expertise to those who need the tools to solve real
problems. Mathematics and other core sciences have always
nurtured such people.
NSF is now charged with supporting engineering research and tech
transfer, as well as with traditional support of science and
of engineering education. This broad mandate motivates us to ask
about relevance in funded research. We would like to see
progress toward long-range goals of national importance. Unfortunately,
few such goals have been identified.
The value of research in computer vision is fairly obvious.
After all, how many industries could expect to remain competitive
in world markets if they hired only unsighted workers? The value
of research in mobile robotics or dexterous hands is less clear,
and I therefore expect stronger justification in such proposals.
For academics working on real-world problems, this should not
be difficult. Very often, however, a professor whose expertise
is at the tool end depends on his graduate students to prove
theorems. The students are thus trained mainly for academic
careers, and may even fail there if they cannot locate customers
willing to support such research. Thus the desperate search for
applications, as well as for grants. Unfortunately, many of
these people drop out of the science/engineering pipeline before
finding the support they need.
Engineers rarely fall into such a trap. There are cases where
someone's expertise becomes outdated and the problems he knows
how to solve are no longer problems. This can happen in pattern
recognition, for instance, when a system functions well enough
that there is no point in further improvements. Still, an
engineer who has solved one problem can usually find work solving
another. There is less of a tendency to stick with just the
tools that one has used in the past, more of a tendency to search
for tools appropriate to the application.
At NSF, we commonly deal with proposals about applying a
particular tool to a particular problem. The need for the
research is often justified in terms of the problem, but the
scientific merit is usually judged by what it will teach us about
the tool. We try to balance the two to best serve the nation,
but our review process and funding policies typically favor
the tool builders.
The particular problem that I was bringing up, and for which
there have been no responses, is the need for a list of research
goals for our Small Business program. Or for any program, for
that matter. The engineering directorate is generally able to
point to specific problems of national importance that they are
trying to solve. The computer science directorate has more
difficulty with this. We talk about bigger, smaller, faster,
cheaper, more robust -- but what are these computers and algorithms
really need for? The COSERS report was one attempt to answer
this. Our small-business people need more-specific projects,
however. As do the nation's graduate students.
One way to get a handle on the problems is to ask about in-house
research efforts that have failed. Perhaps someone else could
solve these problems, avoiding whatever technical or personnel
difficulties arose at your site. Or perhaps someone in
management has been poking around saying "We need X. Can we
do it in-house? Is there a supplier? Who do we call?" Have
you ever had a blue-sky proposal that never got off the ground
because the vision technology just wasn't there? Have customers
called, asking for something that just wasn't your product line?
Or, if you'd rather brainstorm, I'm open for blue-sky
suggestions. Over the next decade, my program may be pumping
something like $50M into machine perception. How would you
like to see that money spent? What should our national goals
be? Which research community should be supported? Where should
we be one or two decades from now? What would we do with
ultimate vision systems if we had them? What's keeping us from
doing it now? Any inputs?
-- Ken Laws
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/11/89)
Vision-List Digest Fri Feb 10 17:04:04 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
6th International Workshop on Machine Learning
Workshop on Models of Complex Human Learning
NIPS latex version PLEASE FORMAT, PRINT and POST
----------------------------------------------------------------------
Date: Sat, 4 Feb 89 21:52:51 -0500
From: segre@gvax.cs.cornell.edu (Alberto M. Segre)
Subject: 6th International Workshop on Machine Learning
Expires:
References:
Followup-To:
Distribution: comp
Organization: Cornell Univ. CS Dept, Ithaca NY
Keywords:
Status: RO
Call for Papers:
Sixth International Workshop on Machine Learning
Cornell University
Ithaca, New York; U.S.A.
June 29 - July 1, 1989
The Sixth International Workshop on Machine Learning will be
held at Cornell University from June 29 through July 1, 1989.
The workshop will be divided into six parallel sessions, each
focusing on a different theme:
Combining Empirical and Explanation-Based Learning (M. Pazzani,
chair). Both empirical evaluation and theoretical analysis have
been used to identify the strengths and weaknesses of
individual learning methods. Integrated approaches to learning
have the potential of overcoming the limitations of individual
methods. Papers are solicited exploring hybrid techniques
involving, for example, explanation-based learning, case-based
reasoning, constructive induction, or neural networks.
Empirical Learning; Theory and Application (C. Sammut, chair).
This session will be devoted to discussions on inductive (also
called empirical) learning with particular emphasis on results
that can be justified by theory or experimental evaluation.
Papers should characterize methodologies (either formally or
experimentally), their performance and/or problems for which
they are well/ill suited. Comparative studies applying
different methodologies to the same problem are also invited.
Learning Plan Knowledge (S. Chien and G. DeJong, co-chairs).
This session will explore machine learning of plan-related
knowledge; specifically, learning to construct, index, and
recognize plans by using explanation-based, empirical, case-
based, analogical, and connectionist approaches.
Knowledge-Base Refinement and Theory Revision (A. Ginsberg,
chair). Knowledge-base refinement involves the discovery of
plausible refinements to a knowledge base in order to improve
the breadth and accuracy of the associated expert system. More
generally, theory revision is concerned with systems that start
out having some domain theory, but one that is incomplete and
fallible. Two basic problems are how to use an imperfect
theory to guide one in learning more about the domain as more
experience accumulates, and how to use the knowledge so gained
to revise the theory in appropriate ways.
Incremental Learning (D. Fisher, chair, with J. Grefenstette, J.
Schlimmer, R. Sutton, and P. Utgoff). Incremental learning
requires continuous adaptation to the environment subject to
performance constraints of timely response, environmental
assumptions such as noise or concept drift, and knowledge base
limitations. Papers that cross traditionally disparate
paradigms are highly encouraged, notably rule-based,
connectionist, and genetic learning; explanation-based and
inductive learning; procedure and concept learning;
psychological and computational theories of learning; and
belief revision, bounded rationality, and learning.
Representational Issues in Machine Learning (D. Subramanian,
chair). This session will study representational practice in
machine learning in order to understand the relationship
between inference (inductive and deductive) and choice of
representation. Present-day learners depend on careful
vocabulary engineering for their success. What is the nature
of the contribution representation makes to learning, and how
can we make learners design/redesign hypotheses languages
automatically? Papers are solicited in areas including, but not
limited to, bias, representation change and reformulation, and
knowledge-level analysis of learning algorithms.
PARTICIPATION
Each workshop session is limited to between 30 and 50
participants. In order to meet this size constraint, attendance
at the workshop is by invitation only. If you are active in
machine learning and you are interested in receiving an
invitation, we encourage you to submit a short vita (including
relevant publications) and a one-page research summary describing
your recent work.
Researchers interested in presenting their work at one of
the sessions should submit an extended abstract (4 pages maximum)
or a draft paper (12 pages maximum) describing their recent work
in the area. Final papers will be included in the workshop
proceedings, which will be distributed to all participants.
SUBMISSION REQUIREMENTS
Each submission (research summary, extended abstract, or
draft paper) must be clearly marked with the author's name,
affiliation, telephone number and Internet address. In addition,
you should clearly indicate for which workshop session your
submission is intended.
Deadline for submission is March 1, 1989. Submissions should be
mailed directly to:
6th International Workshop on Machine Learning
Alberto Segre, Workshop Chair
Department of Computer Science
Upson Hall
Cornell University
Ithaca, NY 14853-7501
USA
Telephone: (607) 255-9196
Internet: ml89@cs.cornell.edu
While hardcopy submissions are preferred, electronic
submissions will be accepted in TROFF (me or ms macros), LaTeX or
plain TeX. Electronic submissions must consist of a single file.
Be sure to include all necessary macros; it is the responsibility
of the submitter to ensure his/her paper is printable without
special handling. Foreign contributors may make special
arrangements on an individual basis for sending their submissions
via FAX.
Submissions will be reviewed by the individual session
chair(s). Determinations will be made by April 1, 1989.
Attendance at the workshop is by invitation only; you must submit
a paper, abstract or research summary in order to be considered.
While you may make submissions to more than one workshop session,
each participant will be invited to only one session.
IMPORTANT DATES
March 1, 1989
Submission deadline for research summaries, extended
abstracts and draft papers.
April 1, 1989
Invitations issued; presenters notified of acceptance.
April 20, 1989
Final camera-ready copy of accepted papers due for inclusion
in proceedings.
------------------------------
Date: Sat, 4 Feb 89 21:57:40 -0500
From: segre@gvax.cs.cornell.edu (Alberto M. Segre)
Subject: Workshop on Models of Complex Human Learning
Expires:
References:
Followup-To:
Distribution: comp
Organization: Cornell Univ. CS Dept, Ithaca NY
Keywords:
Status: RO
9
9 CALL FOR PARTICIPATION
9 WORKSHOP ON
MODELS OF COMPLEX HUMAN LEARNING
Cornell University
Ithaca, New York U.S.A.
June 27-28, 1989
Sponsored by ONR Cognitive Science Branch
This two-day workshop will bring together researchers whose
learning research gives attention to human data and has
implications for understanding human cognition. Of particular
interest is learning research that relates to complex problem-
solving tasks. There is an emphasis on symbol-level learning.
The workshop will be limited to 30-50 attendees. Workshop
presentations will be one hour in length, so as to allow in-depth
presentation and discussion of recent research. Areas of interest
include:
Acquisition of Programming Skills
Apprenticeship Learning
Case Based Reasoning
Explanation Based Learning
Knowledge Acquisition
Learning of Natural Concepts and Categories
Learning of Problem Solving Skills
Natural Language Acquisition
Reasoning and Learning by Analogy
9
The initial list of presenters is based on past proposals
accepted by ONR. This call for papers solicits additional
submissions. The current list of ONR-sponsored presenters
includes:
John Anderson (Carnegie Mellon)
Tom Bever (Univ. of Rochester)
Ken Forbus (Univ. of Illinois)
Dedre Gentner (Univ. of Illinois)
Chris Hammond (Univ. Chicago)
Ryszard Michalski (George Mason Univ.)
Stellan Ohlsson (Univ. of Pittsburgh)
Kurt VanLehn (Carnegie Mellon)
David Wilkins (Univ. of Illinois)
SUBMISSIONS
Presenters: Send four copies of (i) a previously published
paper with a four page abstract that describes recent work or
(ii) a draft paper. These materials will be used to select
presenters; no workshop proceedings will appear. Please indicate
whether you would consider being involved just as a participant.
Participants: Send four copies of a short vitae that
includes relevant publications, and a one-page description of
relevant experience and projects.
Submission Format: Hardcopy submissions are preferred, but
electronic submissions will also be accepted in TROFF (ME or MS
macros), LaTeX or plain TeX. Electronic submissions must consist
of a single file that includes all the necessary macros and can
be printed without special handling.
Deadlines: All submissions should be received by the program
chair by Tuesday, March 28, 1989; they will be acknowledged upon
receipt. Notices of acceptance will be mailed by May 1, 1989.
PROGRAM CHAIR
David C. Wilkins
Dept. of Computer Science
University of Illinois
1304 West Springfield Ave
Urbana, IL 61801
Telephone: (217) 333-2822
Internet: wilkins@m.cs.uiuc.edu
------------------------------
Date: Thu, 9 Feb 89 13:16:17 EST
From: jose@tractatus.bellcore.com (Stephen J Hanson)
ailist@kl.sri.com, arpanet-bboards@mc.lcs.mit.edu,
biotech%umdc.BITNET@psuvax1.cs.psu.edu, chipman@NPRDC.NAVY.MIL,
rna!rocky2!cumc2!wch@cmcl2.ads.com, conferences@hplabs.hp.com,
connectionists@C.CS.CMU.EDU, dynsys-l%unc.BITNET@psuvax1.cs.psu.edu,
epsynet%uhupvm1.BITNET@psuvax1.cs.psu.edu, info-futures@bu-cs.bu.edu,
kaiser%yorkvm1.BITNET@psuvax1.cs.psu.edu, keeler@mcc.com,
mike%bucasb.bu.edu@bu-it.bu.edu, msgs@tractatus.bellcore.com,
msgs@confidence.princeton.edu, neuron@ti-csl.csc.ti.com,
parsym@sumex-aim.stanford.edu, physics@mc.lcs.mit.edu,
self-org@mc.lcs.mit.edu, soft-eng@xx.lcs.mit.edu,
taylor@hplabsz.hpl.hp.com, vision-list@ads.com
Subject: NIPS latex version PLEASE FORMAT, PRINT and POST
Status: RO
\documentstyle[11pt]{article}
%% set sizes to fill page with small margins
\setlength{\headheight}{0in}
\setlength{\headsep}{0in}
\setlength{\topmargin}{-0.25in}
\setlength{\textwidth}{6.5in}
\setlength{\textheight}{9.5in}
\setlength{\oddsidemargin}{0.0in}
\setlength{\evensidemargin}{0.0in}
\setlength{\footheight}{0.0in}
\setlength{\footskip}{0.25in}
\begin{document}
\pagestyle{empty}
\Huge
\begin{center}
{\bf CALL FOR PAPERS\\}
\Large
IEEE Conference on\\
\LARGE
{\bf Neural Information Processing Systems\\
- Natural and Synthetic -\\}
\bigskip
\Large
Monday, November 27 -- Thursday November 30, 1989\\
Denver, Colorado\\
\end{center}
\medskip
\large
\noindent
This is the third meeting of a high quality, relatively small,
inter-disciplinary conference
which brings together neuroscientists,
engineers, computer scientists, cognitive scientists, physicists,
and mathematicians interested in all aspects of neural processing
and computation.
Several days of focussed workshops will follow at a nearby ski area.
Major categories and examples of subcategories
for papers are the following:
\begin{quote}
\small
\begin{description}
\item[{\bf 1. Neuroscience:}] Neurobiological models of development,
cellular information processing, synaptic function,
learning, and memory. Studies and analyses
of neurobiological systems and development of
neurophysiological recording tools.
\item[{\bf 2. Architecture Design:}] Design and evaluation of
net architectures to perform cognitive or behavioral functions and to
implement
conventional algorithms. Data representation;
static networks and dynamic networks
that can process or generate pattern sequences.
\item[{\bf 3. Learning Theory:}] Models of learning; training paradigms
for static and dynamic networks; analysis of capability,
generalization, complexity, and scaling.
\item[{\bf 4. Applications:}] Applications to signal processing, vision,
speech, motor control, robotics, knowledge representation, cognitive
modelling and adaptive systems.
\item[{\bf 5. Implementation and Simulation:}]
VLSI or optical implementations of hardware neural nets.
Practical issues for simulations and simulation tools.
\end{description}
\end{quote}
\large
\smallskip
\noindent
{\bf Technical Program:} Plenary, contributed, and poster sessions will be
held. There will be no parallel sessions. The full text of presented papers
will be published.
\medskip
\noindent
{\bf Submission Procedures:} Original research contributions are
solicited, and will be refereed by experts in the respective disciplines.
Authors should submit four copies of a 1000-word (or less) summary and
four copies of a single-page 50-100 word abstract clearly stating their
results by May 30, 1989. Indicate preference for oral or
poster presentation and specify which of the above five broad
categories and, if appropriate, sub-categories
(for example, {\em Learning Theory: Complexity}, or {\em Applications: Speech})
best applies to your paper. Indicate presentation preference
and category information at the bottom of each abstract page and after
each summary. Failure to do so will delay processing
of your submission. Mail submissions to Kathie Hibbard, NIPS89 Local Committee,
Engineering Center, Campus Box 425, Boulder, CO, 80309-0425.
\medskip
\noindent
{\bf Organizing Committee}\\
\small
\noindent
{Scott Kirkpatrick, IBM Research, General Chairman;
Richard Lippmann, MIT Lincoln Labs, Program Chairman;
Kristina Johnson, University of Colorado, Treasurer;
Stephen J. Hanson, Bellcore, Publicity Chairman;
David S. Touretzky, Carnegie-Mellon, Publications Chairman;
Kathie Hibbard, University of Colorado, Local Arrangements;
Alex Waibel, Carnegie-Mellon, Workshop Chairman;
Howard Wachtel, University of Colorado, Workshop Local Arrangements;
Edward C. Posner, Caltech, IEEE Liaison;
James Bower, Caltech, Neurosciences Liaison;
Larry Jackel, AT\&T Bell Labs, APS Liaison}
\begin{center}
\large
{\bf DEADLINE FOR SUMMARIES \& ABSTRACTS IS MAY 30, 1989}\\
\end{center}
\begin{flushright}
Please Post
\end{flushright}
\end{document}
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/11/89)
Vision-List Digest Fri Feb 10 17:04:04 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
What conferences and workshops should Vision List report?
NIPS Call for Papers
6th International Workshop on Machine Learning
Workshop on Models of Complex Human Learning
----------------------------------------------------------------------
Date: Fri, 10 Feb 89 17:07:12 EST
From: Vision-List moderator Phil Kahn <Vision-List-Request@ADS.COM>
Subject: What conferences and workshops should Vision List report?
If you've noticed, when there are several conference and workshop
proceedings, I bundle them into a single List so regular postings aren't
swamped. Hope this helps.
Of the following three conferences and workshops, I only consider the
NIPS conference to be of interest to the Vision List. The others I
believe are more mainstream AI, and hence are not appropriate for the
Vision List.
Though I tend not to like editorially restricting submitted material, I
favor eliminating conference, seminar, and workshop postings which do
not bear a strong relationship to vision. This is just to let you know
of this policy, since as the readership, this is your list. If you do
not agree, please post your reasons to the List.
I am trying to tighten the content to decrease clutter. In particular,
I want to continue seeing more vision discussions and less peripheral
postings.
phil...
----------------------------------------------------------------------
Date: Thu, 9 Feb 89 13:16:17 EST
From: jose@tractatus.bellcore.com (Stephen J Hanson)
Subject: NIPS CALL FOR PAPERS
IEEE Conference on Neural Information Processing Systems
- Natural and Synthetic -
Monday, November 27 -- Thursday November 30, 1989
Denver, Colorado
This is the third meeting of a high quality, relatively small,
inter-disciplinary conference which brings together neuroscientists,
engineers, computer scientists, cognitive scientists, physicists, and
mathematicians interested in all aspects of neural processing and
computation. Several days of focussed workshops will follow at a
nearby ski area. Major categories and examples of subcategories for
papers are the following:
[ 1. Neuroscience: ] Neurobiological models of development, cellular
information processing, synaptic function, learning, and memory.
Studies and analyses of neurobiological systems and development of
neurophysiological recording tools.
[ 2. Architecture Design: ] Design and evaluation of net
architectures to perform cognitive or behavioral functions and to
implement conventional algorithms. Data representation; static
networks and dynamic networks that can process or generate pattern
sequences.
[ 3. Learning Theory: ] Models of learning; training paradigms for
static and dynamic networks; analysis of capability, generalization,
complexity, and scaling.
[ 4. Applications: ] Applications to signal processing, vision,
speech, motor control, robotics, knowledge representation, cognitive
modelling and adaptive systems.
[ 5. Implementation and Simulation: ] VLSI or optical implementations
of hardware neural nets. Practical issues for simulations and
simulation tools.
Technical Program: Plenary, contributed, and poster sessions will be
held. There will be no parallel sessions. The full text of presented papers
will be published.
Submission Procedures: Original research contributions are
solicited, and will be refereed by experts in the respective
disciplines. Authors should submit four copies of a 1000-word (or
less) summary and four copies of a single-page 50-100 word abstract
clearly stating their results by May 30, 1989. Indicate preference for
oral or poster presentation and specify which of the above five broad
categories and, if appropriate, sub-categories (for example, Learning
Theory: Complexity , or Applications: Speech ) best applies to your
paper. Indicate presentation preference and category information at
the bottom of each abstract page and after each summary. Failure to do
so will delay processing of your submission. Mail submissions to
Kathie Hibbard, NIPS89 Local Committee, Engineering Center, Campus Box
425, Boulder, CO, 80309-0425.
Organizing Committee
Scott Kirkpatrick, IBM Research, General Chairman;
Richard Lippmann, MIT Lincoln Labs, Program Chairman;
Kristina Johnson, University of Colorado, Treasurer;
Stephen J. Hanson, Bellcore, Publicity Chairman;
David S. Touretzky, Carnegie-Mellon, Publications Chairman;
Kathie Hibbard, University of Colorado, Local Arrangements;
Alex Waibel, Carnegie-Mellon, Workshop Chairman;
Howard Wachtel, University of Colorado, Workshop Local Arrangements;
Edward C. Posner, Caltech, IEEE Liaison;
James Bower, Caltech, Neurosciences Liaison;
Larry Jackel, AT T Bell Labs, APS Liaison
DEADLINE FOR SUMMARIES ABSTRACTS IS MAY 30, 1989
----------------------------------------------------------------------
Date: Sat, 4 Feb 89 21:52:51 -0500
From: segre@gvax.cs.cornell.edu (Alberto M. Segre)
Subject: 6th International Workshop on Machine Learning
Organization: Cornell Univ. CS Dept, Ithaca NY
Call for Papers:
Sixth International Workshop on Machine Learning
Cornell University
Ithaca, New York; U.S.A.
June 29 - July 1, 1989
The Sixth International Workshop on Machine Learning will be
held at Cornell University from June 29 through July 1, 1989.
The workshop will be divided into six parallel sessions, each
focusing on a different theme:
Combining Empirical and Explanation-Based Learning (M. Pazzani,
chair). Both empirical evaluation and theoretical analysis have
been used to identify the strengths and weaknesses of
individual learning methods. Integrated approaches to learning
have the potential of overcoming the limitations of individual
methods. Papers are solicited exploring hybrid techniques
involving, for example, explanation-based learning, case-based
reasoning, constructive induction, or neural networks.
Empirical Learning; Theory and Application (C. Sammut, chair).
This session will be devoted to discussions on inductive (also
called empirical) learning with particular emphasis on results
that can be justified by theory or experimental evaluation.
Papers should characterize methodologies (either formally or
experimentally), their performance and/or problems for which
they are well/ill suited. Comparative studies applying
different methodologies to the same problem are also invited.
Learning Plan Knowledge (S. Chien and G. DeJong, co-chairs).
This session will explore machine learning of plan-related
knowledge; specifically, learning to construct, index, and
recognize plans by using explanation-based, empirical, case-
based, analogical, and connectionist approaches.
Knowledge-Base Refinement and Theory Revision (A. Ginsberg,
chair). Knowledge-base refinement involves the discovery of
plausible refinements to a knowledge base in order to improve
the breadth and accuracy of the associated expert system. More
generally, theory revision is concerned with systems that start
out having some domain theory, but one that is incomplete and
fallible. Two basic problems are how to use an imperfect
theory to guide one in learning more about the domain as more
experience accumulates, and how to use the knowledge so gained
to revise the theory in appropriate ways.
Incremental Learning (D. Fisher, chair, with J. Grefenstette, J.
Schlimmer, R. Sutton, and P. Utgoff). Incremental learning
requires continuous adaptation to the environment subject to
performance constraints of timely response, environmental
assumptions such as noise or concept drift, and knowledge base
limitations. Papers that cross traditionally disparate
paradigms are highly encouraged, notably rule-based,
connectionist, and genetic learning; explanation-based and
inductive learning; procedure and concept learning;
psychological and computational theories of learning; and
belief revision, bounded rationality, and learning.
Representational Issues in Machine Learning (D. Subramanian,
chair). This session will study representational practice in
machine learning in order to understand the relationship
between inference (inductive and deductive) and choice of
representation. Present-day learners depend on careful
vocabulary engineering for their success. What is the nature
of the contribution representation makes to learning, and how
can we make learners design/redesign hypotheses languages
automatically? Papers are solicited in areas including, but not
limited to, bias, representation change and reformulation, and
knowledge-level analysis of learning algorithms.
PARTICIPATION
Each workshop session is limited to between 30 and 50
participants. In order to meet this size constraint, attendance
at the workshop is by invitation only. If you are active in
machine learning and you are interested in receiving an
invitation, we encourage you to submit a short vita (including
relevant publications) and a one-page research summary describing
your recent work.
Researchers interested in presenting their work at one of
the sessions should submit an extended abstract (4 pages maximum)
or a draft paper (12 pages maximum) describing their recent work
in the area. Final papers will be included in the workshop
proceedings, which will be distributed to all participants.
SUBMISSION REQUIREMENTS
Each submission (research summary, extended abstract, or
draft paper) must be clearly marked with the author's name,
affiliation, telephone number and Internet address. In addition,
you should clearly indicate for which workshop session your
submission is intended.
Deadline for submission is March 1, 1989. Submissions should be
mailed directly to:
6th International Workshop on Machine Learning
Alberto Segre, Workshop Chair
Department of Computer Science
Upson Hall
Cornell University
Ithaca, NY 14853-7501
USA
Telephone: (607) 255-9196
Internet: ml89@cs.cornell.edu
While hardcopy submissions are preferred, electronic
submissions will be accepted in TROFF (me or ms macros), LaTeX or
plain TeX. Electronic submissions must consist of a single file.
Be sure to include all necessary macros; it is the responsibility
of the submitter to ensure his/her paper is printable without
special handling. Foreign contributors may make special
arrangements on an individual basis for sending their submissions
via FAX.
Submissions will be reviewed by the individual session
chair(s). Determinations will be made by April 1, 1989.
Attendance at the workshop is by invitation only; you must submit
a paper, abstract or research summary in order to be considered.
While you may make submissions to more than one workshop session,
each participant will be invited to only one session.
IMPORTANT DATES
March 1, 1989
Submission deadline for research summaries, extended
abstracts and draft papers.
April 1, 1989
Invitations issued; presenters notified of acceptance.
April 20, 1989
Final camera-ready copy of accepted papers due for inclusion
in proceedings.
------------------------------
Date: Sat, 4 Feb 89 21:57:40 -0500
From: segre@gvax.cs.cornell.edu (Alberto M. Segre)
Subject: Workshop on Models of Complex Human Learning
Organization: Cornell Univ. CS Dept, Ithaca NY
CALL FOR PARTICIPATION
WORKSHOP ON
MODELS OF COMPLEX HUMAN LEARNING
Cornell University
Ithaca, New York U.S.A.
June 27-28, 1989
Sponsored by ONR Cognitive Science Branch
This two-day workshop will bring together researchers whose
learning research gives attention to human data and has
implications for understanding human cognition. Of particular
interest is learning research that relates to complex problem-
solving tasks. There is an emphasis on symbol-level learning.
The workshop will be limited to 30-50 attendees. Workshop
presentations will be one hour in length, so as to allow in-depth
presentation and discussion of recent research. Areas of interest
include:
Acquisition of Programming Skills
Apprenticeship Learning
Case Based Reasoning
Explanation Based Learning
Knowledge Acquisition
Learning of Natural Concepts and Categories
Learning of Problem Solving Skills
Natural Language Acquisition
Reasoning and Learning by Analogy
The initial list of presenters is based on past proposals
accepted by ONR. This call for papers solicits additional
submissions. The current list of ONR-sponsored presenters
includes:
John Anderson (Carnegie Mellon)
Tom Bever (Univ. of Rochester)
Ken Forbus (Univ. of Illinois)
Dedre Gentner (Univ. of Illinois)
Chris Hammond (Univ. Chicago)
Ryszard Michalski (George Mason Univ.)
Stellan Ohlsson (Univ. of Pittsburgh)
Kurt VanLehn (Carnegie Mellon)
David Wilkins (Univ. of Illinois)
SUBMISSIONS
Presenters: Send four copies of (i) a previously published
paper with a four page abstract that describes recent work or
(ii) a draft paper. These materials will be used to select
presenters; no workshop proceedings will appear. Please indicate
whether you would consider being involved just as a participant.
Participants: Send four copies of a short vitae that
includes relevant publications, and a one-page description of
relevant experience and projects.
Submission Format: Hardcopy submissions are preferred, but
electronic submissions will also be accepted in TROFF (ME or MS
macros), LaTeX or plain TeX. Electronic submissions must consist
of a single file that includes all the necessary macros and can
be printed without special handling.
Deadlines: All submissions should be received by the program
chair by Tuesday, March 28, 1989; they will be acknowledged upon
receipt. Notices of acceptance will be mailed by May 1, 1989.
PROGRAM CHAIR
David C. Wilkins
Dept. of Computer Science
University of Illinois
1304 West Springfield Ave
Urbana, IL 61801
Telephone: (217) 333-2822
Internet: wilkins@m.cs.uiuc.edu
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/17/89)
Vision-List Digest Thu Feb 16 12:43:35 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Image Display package on X-windows wanted
SPIE Conference on Robotics and Computer Vision
Re: Vision research information
An inexpensive 16level grey scale sensor
Suggestions for pattern recognition algorithms
ITI150 & ITI151 Image Processing Mailing List
Call for papers: IEEE Workshop on 3D Scene Interpretation
----------------------------------------------------------------------
Date: Mon, 13 Feb 89 17:33:16 JST
From: Shmuel Peleg <peleg%humus.Huji.AC.IL@CUNYVM.CUNY.EDU>
Subject: Image Display package on X-windows wanted
Please let me know if you have available image display and manipulation
system for X windows. We are using Sun 3/60's with grey level and color
screens, and X11 R3.
Thanks,
Shmuel Peleg <peleg@humus.bitnet>
------------------------------
Date: 15 Feb 89 00:11:12 GMT
From: mit-amt!turk@mit-amt.MEDIA.MIT.EDU (Matthew Turk)
Subject: SPIE Conference on Robotics and Computer Vision
Keywords: Philadelphia, 11/89
Organization: MIT Media Lab, Cambridge, MA
** Announcement and Call for Papers **
Intelligent Robots and Computer Vision VIII
Part of SPIE's Advances in Intelligent Robotics Systems
November 5-10, 1989
Adams Mark Hotel
Philadelphia, Pennsylvania USA
Chairman: David Casasent
Carnegie-Mellon University
Co-Chairman: Ernie Hall
University of Cincinnati
This year's conference will focus on new algorithms and techniques for
intelligent robots and computer vision. Papers are solicited
specifically for the following session topics:
- pattern recognition and image processing
- image understanding and scene analysis
- color vision, multi-sensor processing
- 3-D vision: modeling and representation
- neural networks, artificial intelligence, model-based processors
- fuzzy logic in intelligent systems and computer vision
- biological basis for the design of sensors in computer vision
Abstract Due Date: April 3, 1989
Manuscript Due Date: October 9, 1989
Information:
SPIE Technical Program Committee/Philadelphia '89
P.O. Box 10
Bellingham, WA 98227-0010
USA
Or e-mail to:
turk@media-lab.media.mit.edu
------------------------------
Date: Mon, 13 Feb 89 09:04:49 EST
From: steinmetz!pyramid!malek@mcnc.org (aiman a abdel-malek)
Subject: Re: Vision research information
I am doing research in exploiting human visual systems characteristics for
better image generation and compression. If you are doing research on related
topic or one of the following topics :
_ Image segmentation using human visual properties and applications in image
compression.
-The use of visual models for better image generation.
-The use of spatial and temporal characteristics of the visual system to
enhance image quality and update rates.
Contact me, regarding your most recent publications in any of the above
topics. Thank you
malek@pyramid.steinmetz.Ge.Com
------------------------------
Date: Tue, 14 Feb 89 23:35:37 EST
From: Mark Noworolski <noworol@eecg.toronto.edu>
Subject: An inexpensive 16level grey scale sensor
Organization: EECG, University of Toronto
About two months ago I asked about cheap image sensors. The best bet then
was the Fisher Price Kiddie Camcorder (US $99, Canada $169 or so). This is
true, and it's one hell of a deal- it actually works, has a fully funcitonal
B&W TV - and it's lots o'fun.
Well I went out and bought one of these, Fisher-Price didn't want to help
me, so I figured it out myself.
I dug around and found the data stream and all necessary synch pulses- all
at TTL levels.
I'm quite willing to share what I've learned- however I figure probably the
best way would be to first figure out how many people want this info (and
hence whether I should use the SASE method or actually type all that info in-
graphic road maps included).
So if this interests you in a reasonably serious way mail me with a
subject header to that effect and I'll decide which approach to take within
the week (maybe I'll even post here if enough demand develops).
I also wrote really ugly Turbo C code and managed to interface it to my PC
bus (with 3 chips) so that I can see what it sees.
Standard Disclaimer: I have no connection to Fischer-Price except that of a
frustrated hacker.
cheers
mark
noworol@godzilla.eecg or noworol@ecf.toronto.edu
[ If demand develops, I can place it in the VisionList anonymous FTP
directory. I wouldn't want to clutter the list with code...
pk... ]
------------------------------
Date: Tue, 14 Feb 89 23:43:01 EST
From: Mark Noworolski <noworol@eecg.toronto.edu>
Subject: Suggestions for pattern recognition algorithms
Organization: EECG, University of Toronto
Well- now that I've broken the (seeming) tradition of only Conference
calls for Papers on the vision-list. Here's a question.
I need to use the aforementioned sensor to sense a mouth. Yes that's
right. Picture yourself at the dentist and the Dentists light shining
in your mouth and an image sensor on top of the dentists light. That's
almost exactly what it is.
Last time I tried doing pattern recognition I failed miserably (maybe
because I tried to do it MY way). So this time I'm going to be smart
about it.
Are there any algorithms out there particularly well suited for this type
of process? What would be the best places to look? How about using some
kind of neural net to do this (I know very little if nothing about how to
program these- but a friend assures me that they're ideal for pattern
recognition)?
Any help would be appreciated.
mark
------------------------------
Date: Thu, 16 Feb 89 02:05:55 PST
From: pvo1478@oce.orst.edu (Paul V. O'Neill)
Subject: ITI150 & ITI151 Image Processing Mailing List
A new mailing list has been created for users of Imaging Technology's
series 150 and 151 image processing systems and ITEX151 software.
The goal is to share algorithms, code, tricks, pitfalls, advice, etc. in an
effort to decrease development time and increase functionality for the users
of these systems. (Also, despite their good support, we customers may want
to gang up on ITI someday!!)
I envision a simple, unmoderated mail exploder until such time as misuse or
inconsideration forces the list to be moderated.
Subscription requests to:
INTERNET: iti151-request@oce.orst.edu
UUCP: ...!hplabs!hp-pcd!orstcs!oce.orst.edu!iti151-request
UUCP: ...!tektronix!orstcs!oce.orst.edu!iti151-request
Traffic to:
iti151@oce.orst.edu
...!hplabs!hp-pcd!orstcs!oce.orst.edu!iti151
...!tektronix!orstcs!oce.orst.edu!iti151
Paul O'Neill pvo@oce.orst.edu
Coastal Imaging Lab
OSU--Oceanography
Corvallis, OR 97331 503-754-3251
------------------------------
Date: Tue, 14 Feb 89 09:23:17 EST
From: flynn@pixel.cps.msu.edu (Patrick J. Flynn)
Subject: Call for papers: IEEE Workshop on 3D Scene Interpretation
Status: RO
CALL FOR PAPERS
IEEE Workshop on Interpretation of 3D Scenes
Austin Mariott at the Capital
Austin, TX
November 27-29, 1989
The interpretation of 3D scenes remains a difficult problem for many
application areas and has attracted the attention of researchers in
many disciplines. The intent of this workshop is to bring together
vision researchers to discuss current work in scene interpretation,
representation, matching and sensing. A variety of sessions will be
devoted to different aspects of scene interpretation research. The
number of presentations will be limited, so there will be ample
opportunity for discussion. Papers are invited on all aspects of
scene interpretation by human and machine, including:
* General 3D interpretation * Applications in navigation, industry,
problems enabling technology, etc.
* Internal 3D representation and * Matching sensed scene structure
modeling to internal representations.
* Sensing 3D scene structure
Authors are encouraged to present new representations or
computational methods with experimental results, present new
theoretical insights, or relate new observations of relationships
between human and machine processing of 3D scenes.
Submission of Papers:
Submit three copies of your paper to Eric Grimson to be received on or
before June 15, 1989. Papers should not exceed a total of 25 double
spaced pages. Authors will be notified of reviewing decisions by
August 15 and final papers in camera-ready form will be required by
the IEEE Computer Society by September 30,1989.
General Chairman: Anil Jain, Michigan State University
(517) 353-5150
Internet: jain@cps.msu.edu
Program Committee:
Jake Aggarwal, University of Texas, Austin
Dan Huttenlocher, Cornell University
Katsushi Ikeuchi, Carnegie Mellon University
Avi Kak, Purdue University
David Lowe, University of British Columbia
Linda Shapiro, University of Washington
Program Chairpersons:
Eric Grimson
Artificial Intelligence Laboratory
M. I. T.
545 Technology Square
Cambridge, MA 02139
George Stockman
Computer Science Deptartment
Michigan State University
East Lansing, MI 48824
Local Arrangements: Alan Bovik, University of Texas, Austin
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/24/89)
Vision-List Digest Thu Feb 23 12:46:10 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Decision on Fisher Price Camcorder
Paint algorithm needed
report alert: mathematical morphology, pt. 2
Conf. on VISION & 3-D REPRESENTATION
SPIE Conference on Robotics and Computer Vision
Faculty Positions Available
X11R3 on Mac
------------------------------
Date: Thu, 23 Feb 89 12:41:03 EST
From: Mark Noworolski <noworol@eecg.toronto.edu>
Subject: Decision on Fisher Price Camcorder
Organization: EECG, University of Toronto
So far I've gotten about 10-13 requests for what I've
found out about the Kiddie Camcorder. So I'll type it in
(it's going to be part of my thesis) and send it to vision
list. Expected date of arrival: March 6. This week and next
week are way too busy. Iron ring capers, ceremonies, et al.
cheers
"How much more black could it be. The answer is none. None more black."
Nigel - Lead Guitar, Spinal Tap
noworol@eecg.toronto.edu or noworol@ecf.toronto.edu
------------------------------
Date: 15 Feb 89 17:29:06 GMT
From: fuhrman@b.coe.wvu.wvnet.edu (Cris Fuhrman)
Subject: Paint algorithm needed
A friend of mine is working on an object recognition project for
his senior project. He was using some terribly inefficient algorithm to
find the area, centroid, corners, etc., of an object. This algorithm was
taking 11 seconds (a uVAX using C)! I suggested a quick paint/fill
algorithm with some modifications as a better way to obtain these
statistics.
I'm looking for an efficient algorithm that will fill a solid object or
an outlined object (similar to how graphics editors do the "paint-can"
effect). Can anyone give me some pseudo-code or point me to an appropriate
reference guide?
-Cris
[ How about Foley and van Dam? pk ]
------------------------------
Date: Tue, 21 Feb 89 14:15:34 +0100
From: prlb2!ronse@uunet.UU.NET (Christian Ronse)
Subject: report alert: mathematical morphology, pt. 2
The following report is available. Simply send an e-mail message to one of the
two authors, with your postal mail address. NB: Part I was distributed last
summer.
The Algebraic Basis of Mathematical Morphology; Part II: Openings and Closings
C. Ronse (ronse@prlb2.uucp), Philips Research Laboratory Brussels
H. Heijmans (henkh@mcvax.uucp), Centre for Mathematics and Computer Science
ABSTRACT: This paper is the sequel to a previous paper (Part I) where we have
introduced and investigated an abstract algebraic framework for mathematical
morphology. The main assumption is that the object space is a complete
lattice. Of interest are all (increasing) operators which are invariant under
a given abelian group of automorphisms on the lattice. In Part I we have been
mainly concerned with the basic operations dilation and erosion. In this paper
we will concentrate on openings and closings, which are very special classes
of idempotent operators. Much attention is given to specific methods for
building openings and closings. Some examples illustrate the abstract theory.
AMS 1980 Mathematics Subject Classification: 68U10, 68T10, 06A15, 06A23.
Christian Ronse maldoror@prlb2.UUCP
{uunet|philabs|mcvax|cernvax|...}!prlb2!{maldoror|ronse}
``Stars were born of the sky.
Not the stars of glass,
but those of chrome steel.''
------------------------------
Date: Tue, 21 Feb 89 15:40:02 CST
From: mv10801@uc.msc.umn.edu
Subject: Conf. on VISION & 3-D REPRESENTATION
Conference on
VISION AND THREE-DIMENSIONAL REPRESENTATION
May 24-26, 1989
University of Minnesota
Minneapolis, Minnesota
The appearance of the three dimensional world from images pro-
jected on our two dimensional retinas is immediate, effortless,
and compelling. Despite the vigor of research in vision over the
past two decades, questions remain about the nature of three di-
mensional representations and the use of those representations
for recognition and action. What information is gathered? How is
it integrated and structured? How is the information used in
higher level perceptual tasks? This conference will bring togeth-
er nineteen prominent scientists to address these questions from
neurophysiological, psychological, and computational perspec-
tives.
The conference is sponsored by the Air Force Office of Scientific
Research and the University of Minnesota College of Liberal Arts
in cooperation with the Departments of Psychology, Computer
Science, Electrical Engineering, Child Development, and the
Center for Research in Learning, Perception, and Cognition.
Registration:
-------------
The conference fee is $30 ($15 for current students). This fee
includes program materials, refreshments, and Wednesday's recep-
tion. Conference enrollment is limited, so early registration is
recommended.
Accommodations:
---------------
A block of rooms has been reserved at the Radisson University
Hotel. Rates are $68 (plus tax) for double or single occupancy.
To make reservations, contact the hotel at (612) 379-8888 and
refer to the program title to obtain these special rates. Reser-
vations must be made by April 9.
For Further Information, Contact:
Program: Jo Nichols, Center for Research in Learning Perception
and Cognition, (612) 625-9367
Registration: Char Greenwald, Professional Development and
Conference Services, (612) 625-1520
Organizing Chairpersons:
Gordon Legge, Department of Psychology, (612) 625-0846,
legge@eye.psych.umn.edu
Lee Zimmerman, Department of Electrical Engineering,
(612) 625-8544,
lzimmerm@umn-ai.umn-cs.cs.umn.edu
Registrants should include their Name, Address, Day and Evening Telephone,
Job Position, and $30 general registration or $15 current student
registration (give Student I.D. number) or University of Minnesota
Department budget number. Please make check or money order payable to the
University of Minnesota.
Mail to: Registrar
Professional Development and Conference Services
University of Minnesota
338 Nolte Center
315 Pillsbury Drive S.E.
Minneapolis, MN 55455-0139
Registration should be received by May 15.
------------------------------
Date: 15 Feb 89 00:11:12 GMT
From: mit-amt!turk@mit-amt.MEDIA.MIT.EDU (Matthew Turk)
Subject: SPIE Conference on Robotics and Computer Vision
Keywords: Philadelphia, 11/89
Organization: MIT Media Lab, Cambridge, MA
** Announcement and Call for Papers **
Intelligent Robots and Computer Vision VIII
Part of SPIE's Advances in Intelligent Robotics Systems
November 5-10, 1989
Adams Mark Hotel
Philadelphia, Pennsylvania USA
Chairman: David Casasent
Carnegie-Mellon University
Co-Chairman: Ernie Hall
University of Cincinnati
This year's conference will focus on new algorithms and techniques for
intelligent robots and computer vision. Papers are solicited
specifically for the following session topics:
- pattern recognition and image processing
- image understanding and scene analysis
- color vision, multi-sensor processing
- 3-D vision: modeling and representation
- neural networks, artificial intelligence, model-based processors
- fuzzy logic in intelligent systems and computer vision
- biological basis for the design of sensors in computer vision
Abstract Due Date: April 3, 1989
Manuscript Due Date: October 9, 1989
Information:
SPIE Technical Program Committee/Philadelphia '89
P.O. Box 10
Bellingham, WA 98227-0010
USA
Or e-mail to:
turk@media-lab.media.mit.edu
------------------------------
Date: Wed, 22 Feb 89 10:59 H
From: <CHTEH%NUSEEV.BITNET@CUNYVM.CUNY.EDU>
Subject: Faculty Positions Available
National University of Singapore : Faculty positions are available in the
areas of computer communication, computer systems, neural networks, and
computer vision, in the Department of Electrical Engineering. Interested
applicants may send resumes to the Head, Department of Electrical
Engineering, National University of Singapore, Singapore 0511, Singapore.
Enquires on current research activities in specific areas may be sent through
BITNET to : PERSDEPT@NUSVM.
------------------------------
Date: 22 Feb 89 20:20:59 GMT
From: peters@Apple.COM (Steve Peters)
Subject: Re: X11R3 on Mac?
Summary: X11R3 for A/UX is Apple product
Organization: Apple Computer Inc, Cupertino, CA
Apple will ship its X11R3 product for A/UX in March (1989). The
server will support 1-bit and 8-bit deep frame buffers, multiple
screens, backing store and save unders. The graphics code has
undergone substantial optimization. X11R3 will run on both A/UX 1.0
and A/UX 1.1, however A/UX 1.0 allows just a single monochrome screen.
Apple has contributed sources for a single screen, monochrome server
to the MIT X Consortium. These appear on the X11R3 distribution which
has been publicly available since October. comp.windows.x regularly announces
ftp (and other) sites where this distribution may be obtained.
Steve Peters
A/UX X Project Leader
Apple Computer, Inc.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/02/89)
Vision-List Digest Wed Mar 01 13:06:39 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
PD Image Processing Software for Suns
Faculty Positions in Robotics
----------------------------------------------------------------------
Date: Mon, 27 Feb 89 11:15:48 GMT
Subject: PD Image Processing Software for Suns
From: phill%MED-IMAGE.COMPSCI.BRISTOL.AC.UK@CUNYVM.CUNY.EDU
This is to introduce a toolkit of image processing pro-
grams, collectively called the ALV toolkit for historical
reasons, written by Phill Everson <everson@uk.ac.bris.cs> in
the Computer Science Dept. of Bristol University, United
Kingdom.
The toolkit is designed to aid image processing work on
Sun workstations. It is intended to be easy to use, though
not restrictive to experienced users, user-configurable,
extensible and flexible. For example the toolkit will work
on both black and white and colour workstations and in
either case will transparently, to the user, display an
image to the best of its ability on the screen.
The toolkit has recently been rewritten to use the
standard Sun rasterfile format to store its images allowing
multiple depth images to be processed by the same toolkit
and easy migration of data between packages.
*** All people currently on the alv-users mailing list will
receive a copy of the new toolkit in the next couple of days.
The toolkit is made up of a number of tools. These
include programs to display an image on the screen, to
display a histogram, to perform histogram equalisation, to
threshold, to print an image on an Apple Laserwriter, to
invert an image and to convolve an image with a user-
supplied linear filter. Currently, there are 27 such pro-
grams.
The toolkit was initially written to fulfill a need at
Bristol University for a single coherent set of tools to
support basic image processing research on a variety of pro-
jects. We had found that each user or group of users was
writing their own copy of programs to do similar things,
like displaying an image on the screen, and more impor-
tantly, in an enviroment were disk space is always at a
premium, was each keeping separate copies of these often
large programs.
Using a coherent set of tools with a consistent file
format has substantially increased cross-project communica-
tion and in addition has provided a higher starting point on
the learning curve for novice Sun-Users/Imagers. We have
found that users generally use the core tools as a basis and
are then able to concentrate their work in their own area of
interest.
The ALV toolkit comes complete with a 40-50 page manual
online which can easily be dumped to a laserwriter to prov-
ide and impressive reference for a Public Domain Program.
The toolkit is currently distributed via email.
Contact <alv-users-request@uk.ac.bris.cs> to request a copy.
The following are the commands currently in the toolkit:
array2ras - convert array to raster
blend - blend two rasters together
box - box a raster
convert - convert textual raster to raster
convolve - convolve a raster with a linear filter
dither - convert 8 bit raster to 1 bit using dither matrix
dsp - display a raster on screen
equalise - equalise a raster
ffill - flood fill a raster
halftone - convert an 8 bit raster to 1 bit using bitmap
font
hist - display histogram of raster
im2ras - convert old ALV format to raster
invert - invert the pixels in a raster
ras2array - convert raster to array
ras2im - convert raster to old ALV format
ras2lw - output a raster on a Laserwriter
rasinfo - print raster udimensions and depth
rasrange - range a raster's greylevels
rasregion - clip a raster to a region
rasscale - scale a raster's size by a scaling-factor
rasthresh - threshold raster
rasval - print pixel values of raster
scr2ras - interactive screendump to raster
transform - shear or rotate a raster
winlev - convert N bit deep raster to 8 bits deep
winlev8 - interactively change window and level of a
displayed raster
Phill Everson
-------------------------------------------------------------------------
SNAIL: Phill Everson, Dept Comp Sci, University of Bristol, England
JANET: everson@uk.ac.bris.cs
UUCP: ...mcvax!ukc!csisles!everson
ARPANET: everson@cs.bris.ac.uk OR everson%uk.ac.bris.cs@nss.cs.ucl.ac.uk
BITNET: everson%uk.ac.bris.cs@ukacrl.bitnet
------------------------------
Date: Mon, 27 Feb 1989 16:59-EST
From: Takeo.Kanade@IUS3.IUS.CS.CMU.EDU
Subject: Faculty Positions in Robotics
Faculty Positions in Robotics
Carnegie Mellon University
Robotics Ph.D. Program
Applications are invited for tenure-track faculty positions in the Robotics
Ph.D. Program at Carnegie Mellon University. The program is
interdisciplinary with participation from the Robotics Institute, School of
Computer Science, Carnegie Institute of Technology (the engineering
college), and Graduate School of Industrial Administration. Appointees are
expected to play major roles in education and research in the program. The
appointments may be made at either assistant, associate, or full professor
levels, and in general will be joint positions between the Robotics
Institute and an academic department or school, depending on the
qualifications and backgrounds of the applicants. If so desired, a non-
tenure-track research faculty position at the Robotics Institute can also be
considered.
Applicants for tenured positions must have strong records of achievements in
research and education in robotics and have demonstrated leadership in
formulating and performing advanced research projects. Applicants for
junior tenure-track positions must have a Ph.D. in a related discipline and
have demonstrated competence in one or several areas of Robotics research
together with potential for excellent teaching.
Outstanding candidates in all areas of Robotics are invited, including, but
not limited to, mechanism, manipulation, control, locomotion, vision,
design, planning, knowledge-based systems, simulation, graphics,
micro-electronics, parallel computing, manufacturing, and management.
Applicants should send their applications with curriculum vitae and names of
at least four references to: Professor Takeo Kanade, Director of the
Robotics Ph.D. Program, The Robotics Institute, Carnegie Mellon University,
Pittsburgh, PA 15213.
Carnegie Mellon is an Equal Opportunity/Affirmative Action employer.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/07/89)
Vision-List Digest Mon Mar 06 12:31:33 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Images recording
Re: Yet Another Image Proc. Toolkit
Perception data wanted
Re: Vision research information
----------------------------------------------------------------------
Date: Thu, 02 Mar 89 09:51:08 HNE
From: Jean Fortin <3606JFOR%LAVALVM1.BITNET@CORNELLC.CIT.CORNELL.EDU>
Subject: Images recording
Hi everybody,
I'm working with a b/w video camera and I would like
to record my images on magnetic tape. Normal VCR are
equipped with automatic gain control (AGC) and other proces-
sing features which are disturbing in my case. I would like
to know if anybody knows the name of a company offering VCRs
not equipped with these features and specially suited for
scientific recording of images.
Thank you!
Jean Fortin <3606JFOR@LAVALVM1>
Electrical Engineering Dept.
Universite Laval
Local 1114-J
Ste-Foy, Quebec, Canada
G1K 7P4
------------------------------
Date: Sat, 4 Mar 89 18:16:35 PST
From: Lew Hitchner <hitchner@saturn.ucsc.edu>
Subject: Re: Yet ANother Image Proc. Toolkit
The info in a recent Vision-List about Bristol's image Toolkit was
interesting and worthwhile to announce on Vision-List. However, there
seem to be quite a few of these beasts floating around (esp. in
academia), some of which are public domain (i.e., free, no maintenance,
maybe some documentation), some of which have been pseudo-
commercialized, some of which have been commercialized, etc. Perhaps
Vision-List would be a good conduit for compiling a list of the known
image toolkits and their availbility status. If you can find a willing
compiler (i.e., a human) who would edit the responses sent in by
Vision-List readers, it would probably be a very good service to the
Vision community (as you might guess, this implies I am not
volunteering, but perhaps a call for a volunteer in a Vision-List
announcement might succeed).
Lew Hitchner
UC Santa Cruz
[ I agree that this would be worthwhile. Those with information, please
post the information, and I will repost. In particular, specify: the
language, target system and portability, scope of routines, copyrights,
support and maintenance, responsible person(s) to contact, extent of
constructs (e.g., image processing, region-based, abstractions for
object description, etc.), and (if appropriate) the cost of the system.
phil... ]
------------------------------
Date: 2 Mar 89 22:31:11 GMT
From: munnari!rhea.trl.oz.au!dconway@uunet.UU.NET ( Switched Networks)
Subject: Perception data wanted
Keywords: sensory input references
Organization: Telecom Research Labs,IPF,Melbourne, Australia
Is the following sentence meaningful?
"Unimpaired humans receive XX% of all sensory input visually."
If it is:
a) what is the value of XX?
b) how is this determined?
c) what is the standard reference on this?
If not:
a) what _can_ be meaningfully said in this context?
b) what are the issues which complicate such estimates?
b) what is the standard reference on the relative
importance of the different senses?
Please reply by email.
I will summarize responses.
Thankyou,
who: Damian Conway email: dconway@rhea.trl.oz
where: Network Analysis Section phone: (03) 541 6270
SNRB, Telecom Research Labs quote: "He was a dyslextheist;
Clayton South building (CS) he worshipped dogs."
22 Winterton Road
Clayton 3168
AUSTRALIA
------------------------------
Date: Mon, 13 Feb 89 09:04:49 EST
From: steinmetz!pyramid!malek@mcnc.org (aiman a abdel-malek)
Subject: Re: Vision research information
I am doing research in exploiting human visual systems characteristics for
better image generation and compression. If you are doing research on related
topic or one of the following topics :
_ Image segmentation using human visual properties and applications in image
compression.
-The use of visual models for better image generation.
-The use of spatial and temporal characteristics of the visual system to
enhance image quality and update rates.
Contact me, regarding your most recent publications in any of the above
topics. Thank you
malek@pyramid.steinmetz.Ge.Com
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/09/89)
Vision-List Digest Wed Mar 08 11:00:09 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Percent visual input? OBVIUS (vision software) VIEWS: Image Processing Toolkit for Suns? ---------------------------------------------------------------------- Date: Tue, 7 Mar 89 11:26 EDT From: "RCSDY::YOUNG"@gmr.com Subject: Percent visual input? Since I am unsure how to reach him via e-mail, I am replying directly to VisionNet to Damian Conway's prior question: > Is the following sentence meaningful? > "Unimpaired humans receive XX% of all sensory input visually." Consider there are an estimated 10^9 neurons in the primary visual area (V1) in cortex, another 10^9 (or possibly much more) in the secondary visual cortical areas (V2-V4, peristriate, parastriate). Subcortical areas such as LGN we can disregard, since there are only 10^6 neurons in each optic tract, and only 10^8 in each eye. In addition we have motion and eye movement processing over in the superior colliculus and its associated pathways (perhaps about another 10^9). There are altogether at least 20 different known retinotopic maps in the cortex, not all of which have complete number estimates. Total cortex is generally thought to contain about 10^10 neurons, although this figure is a likely underestimate. The usual estimate of vision-related neurons is made by considering just the occipital area of the brain, where the visual sensory paths terminate, which is known to contain about 70 percent of all the neurons in the human central nervous system (M. D. Levine, Vision in Man and Machine, 1985, p. 84). So 70% would be the most widely quoted figure. However if you also include association cortex which associates visual information with auditory and tactile information the total figure would be higher. Also what about the motor pathways controlling eye movements, with visual re-afference which is necessary to maintain visual stability with eye movements? So my own estimate is that final figure would be that about 80% of the neurons in the brain are involved with vision processing -- we are indeed visual creatures! Dick Young Machine Perception Laboratory General Motors Research Labs ------------------------------ Date: Tue, 7 Mar 89 17:30:29 EST From: David Heeger <heeger@paddington.media.mit.edu> Subject: OBVIUS (vision software) OBVIUS (Object-Based Vision and Image Understanding System) is an extension to Common Lisp and CLOS (Common Lisp Object System) for manipulating pictorially displayable objects. The system provides a flexible interactive user interface for working with images. In addition, by using Lisp as its primary language, the system is able to take advantage of the interpretive lisp environment (the ``listener''), object-oriented programming, and the extensibility provided by incremental compilation. OBVIUS runs on Sun 3 (using Lucid Lisp) and Symbolics machines. The basic functionality of OBVIUS is to present certain lisp objects to the user pictorially. These objects are refered to as {\bf viewables}. Some examples of viewables are monochrome images, color images, one bit images, complex images, image pyramids, image sequences, filters and discrete functions. A {\bf picture} is a pictorial representation of a viewable. Note that a given viewable may be compatible with several different picture types. For example, a floating point image may be displayed as an eight bit grayscale picture, as a one bit dithered picture, or as a graphical surface plot. OBVIUS also provides postscript hardcopy output of pictures. In the typical mode of interaction, the user types an expression to the lisp listener and it returns a viewable as a result. The top-level lisp print function then automatically displays a picture of the viewable in a window. Each window contains a circular stack of pictures. Standard stack manipulation operations are provided via mouse clicks (e.g., cycle, pop, and push). Commonly used operations such as histogram and zoom are also provided via mouse clicks. OBVIUS provides a library of image processing routines (e.g., point operations, image statistics, convolutions, fourier transforms). All of the operations are defined on all of the viewable types. The low-level floating point operations on the Suns are implemented in C for speed. OBVIUS also provides a library of functions for synthesizing images. In addition, it is straightforward to add new operations and new viewable and picture types. OBVIUS is now ready for beta-test distribution (available via anonymous ftp from whitechapel.media.mit.edu). Since it is currently an in-house product it comes without warrantee or support. For more information contact David Heeger (heeger@media-lab.media.mit.edu) of the MIT Media Lab Vision Science Group, at (617) 253-0611. ------------------------------ Date: Tue, 7 Mar 89 21:26:48 EST From: achhabra@ucesp1.ece.uc.edu (Atul Chhabra) Subject: VIEWS: Image Processing Toolkit for Suns? At a recent conference, I saw a brochure about VIEWS, an image processing toolkit for SUNs. This is a public domain software developed at Lawrence Livermore Labs. The brochure contained the name and phone number of the contact person at Lawrence Livermore. I have misplaced the brochure. Could someone on the net email me the name, phone number, and the email address of the distributor of VIEWS. Thanks Atul Chhabra, Dept. of Electrical & Computer Engineering, ML 030, University of Cincinnati, Cincinnati, OH 45221-0030. voice: (513)556-4766 INTERNET: achhabra@ucesp1.ece.uc.edu OR achhabra@uceng.uc.edu ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/15/89)
Vision-List Digest Tue Mar 14 10:40:36 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Intrinsic image routines?
Research posts - parallel processing and vision
Imaging software.
Camcorder computer interface modification description
----------------------------------------------------------------------
Date: Mon, 13 Mar 89 19:47:07 EST
From: Sean Philip Engelson <engelson-sean@YALE.ARPA>
Subject: Intrinsic image routines?
I'm doing some work in cognitive mapping and robotics, and, naturally,
I need some vision. I'm just getting to the thinking about hacking
stage, so I figured I'd ask if you had programs to compute any sort of
intrinsic images from input data, that I could get ahold of. Things
like local shape-from-shading, or stereo depth maps, or motion fields,
etc, is what I'm looking for; not model or feature based stuff. I
need source, of course, since I want to interface all this stuff
together, and thus commercial quality is not necessary, but
well-written code would be nice.
Thanks very much in advance,
------------------------------
Date: 13 Mar 89 17:30:55 GMT
From: Andrew Wallace <mcvax!cs.hw.ac.uk!andy@uunet.UU.NET>
Subject: Research posts - parallel processing and vision
Organization: Computer Science, Heriot-Watt U., Scotland
Heriot-Watt University
Department of Computer Science
Research Associates in Parallel Processing and Vision
Applications are invited for two SERC-funded Research
Associateships to work on aspects of rapid prototyping and
implementation of algorithms for high level image interpretation
on multiple instruction multiple data (MIMD) architectures.
Although working closely together, each RA will assume
responsibility for a specific programme. The first will
concentrate primarily on the software methodology, including
functional specification of algorithms and their transformation
into a parallel imperative language, OCCAM 2. The other will
undertake the development, optimisation and implementation of
algorithms for visual recognition and location on a suitable
machine. The persons appointed will join a lively research group
working on several aspects of computer vision and software
development.
Applicants should have an honours degree in Computer Science or a
related discipline, together with relevant postgraduate
experience. The posts are tenable for three years, commencing as
soon as possible after the 1st June. The starting salary will be
in the range L=8,675 to L=13,365 depending on age and
experience.
Enquiries should be directed initially to the Staff Officer,
Heriot-Watt University, Riccarton, Edinburgh EH14 4AS, from whom
further information and application forms may be obtained. The
closing date for applications is 7th April 1989.
Informal enquiries may be directed to Dr. Andrew Wallace at the
Department of Computer Science, tel. 031-225-6465 x542
(andy@uk.ac.hw.cs)
Andrew Wallace JANET : andy@cs.hw.ac.uk
ARPA : andy@uk.ac.hw.cs
UUCP : ..ukc!cs.hw.ac.uk!andy
------------------------------
Date: Wed, 8 Mar 89 14:59 N
From: THIERRY PUN <PUN%CGEUGE51.BITNET@CUNYVM.CUNY.EDU>
Subject: Imaging software.
(Following vision-list digest of Monday March 6, 89).
LABO IMAGE:
Computer Science Center, University of Geneva, Switzerland
GENERAL DESCRIPTION:
Labo Image is a window based software for image processing and analysis. It
contains a comprehensive set of operators as well as general utilities. It
is designed to be open-ended; new modules can easily be added. The software
is mostly written in C, and currently runs on Sun 3/xxx, Sun 4/xxx (OS3.5 and
4.0) under SunView. It has been extensively used by students as well as
researchers from various domains: computer science (image analysis), medicine,
biology, physics. It is freely distributed.
CAPABILITIES:
Labo Image is an interactive software, whose interface is menu, mouse and
windows based. It can work on monochrome (binary) or color workstations. Its
main features are:
- input-output: file, screen, postscript;
- display: mono, RGB, dithering;
- color table manipulations;
- elementary interactive operations: region outlining, statistics and
histogram computation, etc;
- elementary operations: histogramming, conversions, arithmetic, images
and noise generation;
- interpolation, rotation/scaling/translation;
- preprocessing: background substraction, filters, etc;
- convolution/correlation with masks, image; padding;
- edge extractions: various operators, peak-following;
- region segmentation: various methods (being implemented);
- transforms: Fourier, Haar, etc;
- binary mathematical morphology, plus some grey-level morphology;
- expert-system for novice users;
- macros definitions, save and replay;
- etc.
IMAGE FORMATS:
Own format: descriptor file + data file (binary, byte, int, float, complex;
mono or RGB). Conversions to various other formats.
Constructs:
- iconic (pixel-based), which each image having its own parameter list;
- vectors (histograms, look-up tables);
- graphs (for regions; being implemented);
- strings (for macros).
STATUS:
Version 0 has been released in January 1988, version 1 in November 1988,
version 2 will be released before end of March 1989:
- hosts: Sun 3/xxx, Sun 4/xxx;
- OS: Sun OS 3.5, 4.0;
- window system: SunView, View2 as soon as possible; X11 in preparation;
- language: mostly C, plus some Fortran (SPIDER modules) and some
Common-Lisp (expert-system);
- approx. code size: source 1MB (25'000 lines), executable 1.5MB under
SunView/OS3.5;
- documentation: manuals (french), leaflets (english); english manual is
being prepared.
DISTRIBUTION POLICY:
Most of the software has been developped by us, and source code is available.
A few modules are licensed (SPIDER), and of course cannot be distributed;
these are however routines that all imaging groups have, such as median or
Fourier transform.
Interested persons can be sent the software by providing us with a 1/4"
cartridge. Under special request, it can be e-mailed. A typical disclaimer
notice will also be sent. In essence:
- the software is our property, and the copyright notice must appear;
- results obtained with Labo Image should reference it;
- no responsability is assumed;
- no money can be made out of it;
- no redistribution without our consent;
- bugs will usually be corrected since we use intensively the software;
- modifications should be communicated to us, with (normally) allowance
for redistribution.
CONTACTS:
Thierry Pun (general design) or Alain Jacot-Descombes (general design and
principal writer of the software): Computer Science Center, Univ. of Geneva,
12 rue du Lac, CH-1207 Geneva SWITZERLAND.
Tel. +(4122) 87 65 82 (T. Pun), 87 65 84 (A. Jacot-Descombes).
E-mail: pun@cgeuge51.bitnet, pun@cui.unige.ch, or jacot@cuisun.unige.ch.
------------------------------
Date: Mon, 13 Mar 89 10:33:47 PST
From: Mark Noworolski <noworol@eecg.toronto.edu>
Subject: Camcorder computer interface modification description
[ I have omitted the compressed binary files. If anyone has a need for
them, please let me know, and I will mail the uuencoded, compressed,
tar'ed (and feathered) file to you.
phil... ]
Here, as promised are the details of how to interface the
Fischer-Price Kiddie Camcorder to a computer- in my case an
IBM PC. The camera has 120 horiz, 90 vertical, and 16 grey scales.
Several notes are in order:
1. It may sound like part of a thesis. Well it is.
2. Figures are not enclosed, I figure that it's reasonably easy
to figure things out without them anyway (provided you have a unit
near you). Figure that, figure, figure. figure.
3. The interface is built with the premise that if it's possible to do
it in software, it'll be done that way. Improvements are most
DEFINITELY possible (and probably welcome). Some of the parts of it
are probably redundant, but make me much happier about the likelihood
of frying something in my PC.
The actual interface is enclosed in 3 formats:
ORCAD schematic file v3.11
HPGL file spit out by orcad
Postscript file (untested) after running through an hpgl to ps converter.
epson format file.
4. The program is written for Turbo C 2.0. It uses the BGI routines and
is REALLY ugly. I mean that. It's one of those programs that you write in
2 minutes 'just to see if it works' and then never clean it up.
5. The following should only be attempted by people who have a vague idea
of what they're doing. Since you're interfacing to the IBM bus directly you
should be VERY careful.
6. The executable of the display program will be provided on request.
7. A question... Why does the damned program generate a parity error when
starting up? It goes away after that.
Well, here's the goods.
Reverse Engineering
The Fisher Price Kiddie Camcorder was found to be a very useful
image sensor priced reasonably (at the time of writing $180
Canadian). What follows is a description of how to use the unit
as an image sensor giving 16 levels of grey scale and requiring
only a minimum of interface circuitry. Please note that all
direction references (unless specified otherwise) are related to
those observed when actually using the unit as a camera.
Disassembly of the unit is fairly simple, screws are located
underneath the rubber pegs located on the right hand of the unit
(see figure 1). These must be pried off with a pointed object
such as a screwdriver, revealing the screws underneath. These
four screws must then be removed along with the two in the
handle. The unit can then be easily separated into two halves,
revealing the electronics and the cassette mechanism.
Next the cassette mechanism must be separated from the
electronics. This can be accomplished by separating the two while
using the pushbutton side as a pivot point (most wires are to be
found on that side). In order to simplify interfacing the two
wires leading to the motor should be disconnected.
The switch labelled SW1 should next be pushed in permanently (it
is found directly behind the vision sensing element near the
shield), this can be accomplished by pulling the spring out from
within it and then manually pushing it into position. The unit
can at this point be used as a vision sensor which plugs into
your TV. In other words what it now does is work like normal in
the record mode; except that no recording actually takes place
since the motor doesn't turn.
Towards the back of the board there are two SMD's. They are 24
pin devices mounted side by side. Both of them have similar part
numbers- FP519550. To the left of these there are 7 resistors,
the top one is labelled R155. The bottom four are the 4 bit data
stream (see figure 2), thus giving 16 levels of grey scale (a TTL
high level indicates a corresponding high light intensity). The
bottom resistor is the most significant bit and the fourth one up
is the least significant; the right side of each being the data
line itself. These lines are shown in figure 3 together with the
associated control signals. The data lines and associated control
signals are at standard TTL levels of 5 volts.
The synchronising signals can be found on the left FP519550 SMD.
Each is named as follows:
Current Frame- pin 5
This signal is a square wave of period 130 msec. It can be
used as a synchronising signal to indicate start of frame.
Data valid- pin 17
This signal is active low for approximately 250nsec and
occurs 600 nsec before the end of a data valid period. In
addition it goes low for a short period at the beginning and
end of each frame.
Horizontal Sync- pin 23
This signal is active low for approximately 50usec every
0.7msec. This can be used as the horizontal sync signal.
Numerous additional control-related signals can be found on these
two SMD's. However the three described above are sufficient to
enable interfacing to a computer with minimal circuitry.
Interfacing to the IBM PC bus
Emphasis in the interface planning and design was placed on
simplicity as opposed to elegance. The reasoning behind this
being that this was still the initial prototype development phase
of the project. In the final design a microcontroller such as the
8051 might be a good choice for image aquisition processing.
The final circuit designed with this premise in mind is shown in
figure 1. Although simple in function and design, a lack of
reasonable care can damage the PC bus and some I/O cards (the
author himself has manged to destroy his hard disk controller in
a puff of smoke).
The simple precaution of removing all PC cards possible will lead
to a safer environment in which to debug this circuit. Note that
the DMA3 channel is used to do the interfacing. Once again
caution should be stressed as some PC cards use the same channel
for their functions and it is important that this circuit does
not conflict with them.
Circuit Description
The '74 latch is used to generate DMA requests by using the Data
Valid line as a clock. The DMA acknowledge line clears the flip-
flop thereby setting it up for the next data word. The DMA
acknowledge time is significantly less than the 6usec period
during which data is valid.
The Data Valid line is also used as the clock for the '374 latch,
with the data lines, Current Frame bit, and Hsync bit used as its
inputs. The output enable line is controlled by both the IOR and
the DMAK3 lines, thereby assuring that no bus conflicts occur
when another I/O device is accessed (unless it uses the DMA3
channel).
Finally the '06 open collector buffer is used to minimize the
risk of blocking other devices from using the DMA3 channel. This,
however, is probably unnecessary since DMA3 service attempts
would cause bus conflicts anyway. Nevertheless it made the author
feel much more comfortable about the likelihood of other
components in his computer vanishing in puffs of smoke.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/18/89)
Vision-List Digest Fri Mar 17 10:04:20 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Re: VIEW (not VIEWS): Image Processing Toolkit for Suns? Visual System Characteristics Lectureship or Assistant Lectureship Re: Call for image processing software ---------------------------------------------------------------------- Date: Wed, 15 Mar 89 03:32:37 EST From: achhabra@ucesp1.ece.uc.edu (Atul K. Chhabra) Subject: Re: VIEW (not VIEWS): Image Processing Toolkit for Suns? (Following vision-list digest of Wed March 8, 89). > I have misplaced the brochure. Could someone on the net email > me the name, phone number, and the email address of the > distributor of VIEWS. On getting no responses with the info that I had asked for, I searched harder on my desk and located the brochure. It only contains the snail mail address of the contact person: R.M. Rodrigues, L-153 Lawrence Livermore National Laboratory P.O. Box 5504 Livermore, CA 94550 Highlights of the VIEW (not VIEWS) software (quoted from the brochure): o Available at no charge o User friendly interface - Window-based - Menu or command driven o On-line HELP and user manual o Multidimensional processing operations include: - Image display and enhancement - Pseudocolor operations - Point and neighborhood operations - Digital filtering - Fourier transform domain operations - Simulation operations - Database management - Seqeunce and macro processing o Easily transportable o Written in C (sources included) o Handles multiple dimensions and data types o Available on - VAX (VMS, Ultrix) - Sun (UNIX) Atul Atul Chhabra, Dept. of Electrical & Computer Engineering, ML 030, University of Cincinnati, Cincinnati, OH 45221-0030. Phone: (513)556-4766 INTERNET: achhabra@ucesp1.ece.uc.edu [129.137.33.114] OR achhabra@uceng.uc.edu [129.137.33.1] ------------------------------ From: "John K. Tsotsos" <tsotsos@ai.toronto.edu> Subject: Visual System Characteristics Date: Wed, 15 Mar 89 15:45:45 EST I am interested in collecting visual system characteristics from as many different species (both vertebrates and invertebrates) as possible. In particular, I would like to know for each type of animal: - the approximate number of cortical (and/or sub-cortical) neurons devoted primarily to vision - whether or not `visual maps' have been discovered, and if so, how many, what is their size (in neurons), how are they organized, and any other known characteristics. Positive statements about the absence of maps are also important. - average cortical fan-in and fan-out for visual neurons in terms of other neurons rather than total synapses Please cite references as well. Both physical and electronic mail addresses are given below. I will gladly summarize and post the results on the net if there is enough interest. John K. Tsotsos Department of Computer Science 10 King's College Road University of Toronto Toronto, Ontario, Canada M5S 1A4 416-978-3619 tsotsos@ai.toronto.edu ------------------------------ Date: Thu, 16 Mar 89 21:13:39 GMT From: JM123%phoenix.cambridge.ac.uk@NSS.Cs.Ucl.AC.UK Subject: Lectureship or Assistant Lectureship University of Cambridge, UK Department of Experimental Psychology LECTURESHIP or ASSISTANT LECTURESHIP in Psychology An appointment of a Lecturer or Assistant Lecturer in Experimental Psychology will be made shortly under the New Academic Appointments Scheme, subject to funding from the University Grants Committee. The starting date will be October 1, 1989, or as soon afterwards as possible. The appointment will be made in the general area of cognitive psychology, cognitive neuroscience or developmental psychology; preference may be given to candidates working on computational modelling of cognitive processes or on associative or neural networks. The salary for a University Assistant Lecturer is UKL 10,460 p.a. rising by four annual increments to UKL 12,760, and for a University Lecturer, UKL 13,365 p.a., rising by eleven annual increments to UKL 20,615. All Assistant Lecturers are consider for upgrading to Lecturer during their appointment. Further formal particulars may be obtained from Dr. D. Franks, Secretary to the Appointments Committee for the Faculty of Biology B, 19 Trumpington St., Cambridge CB2 1QA, to whom applications should be sent by 17 April, 1989. Informal enquiries may be directed to Professor N. J. Mackintosh (223-333551) Department of Experimental Psychology, Downing St., Cambridge, CB2 3EB, United Kingdom; or, if urgent, to jm123@uk.ac.cam.phx. ------------------------------ Date: Thu, 16 Mar 89 17:08:39 EST From: msl@vml3.psych.nyu.edu (Michael Landy) Subject: Re: Call for image processing software The following is in response to your request for infor- mation on image processing software. HIPS is a software package for image processing that runs under the UNIX operating system. HIPS is modular and flexible, it provides automatic documentation of its actions, and is almost entirely independent of special equipment. It handles sequences of images (movies) in pre- cisely the same manner as single frames. Programs have been developed for simple image transformations, filtering, con- volution, Fourier and other transform processing, edge detection and line drawing manipulation, digital image compression and transmission methods, noise generation, image pyramids, and image statistics computation. Over 150 such image transformation programs have been developed. As a result, almost any image processing task can be performed quickly and conveniently. Additionally, HIPS allows users to easily integrate their own custom routines. HIPS features images that are self-documenting. Each image stored in the system contains a history of the transformations that have been applied to that image. HIPS includes a small set of subroutines which primarily deals with a standardized image sequence header, and a large library of image transformation tools in the form of UNIX ``filters'' written in `C'. As a result it runs on any Unix workstation (users run it on equipment from Sun, Vax/Microvax, Masscomp, NCR, Silicon Graphics/Iris, Apollo, etc. etc.). HIPS has proven itself a highly flexible sys- tem, both as an interactive research tool, and for more production-oriented tasks. It is both easy to use, and quickly adapted and extended to new uses. HIPS is distributed by SharpImage Software, P.O. Box 373, Prince Street Station, New York, NY 10012-0007. To obtain more information, write us or call Michael Landy, (212) 998-7857 (landy@nyu.nyu.edu). HIPS consists of a basic system and a number of additional modules (for fancier Sun display, additional image tools, etc.). The basic sys- tem costs $3,000, and is available at a considerable discount to qualified educational, non-profit, and US government users. The base price is for all computing equipment within a particular academic department of commer- cial laboratory. The software comes complete with source, libraries, a library of convolution masks, documentation, and manual pages. It also includes drivers for the Grinnell and Adage image processors, display drivers for the Sun Microsystems consoles under SunView, gfx, and straight to the console. Users have contributed drivers for the Matrox VIP-1024, ITI IP-512, Macintosh II, X windowing system, Iris, and Lexidata. It is a simple matter to interface HIPS with other framestores, and we can put interested users in touch with users who have interfaced HIPS with the Arlunya, and Datacube Max-Video. Our Hipsaddon product includes an interface to the CRS-4000. HIPS can be easily adapted for other image display devices because 98% of HIPS is machine independent. It has been described in Computer Vision, Graphics, and Image Processing (Vol. 25, 1984, pp. 331- 347), and in Behavior Research Methods, Instrumentation, and Computers (Vol. 16, 1984, pp. 199-216). ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/28/89)
Vision-List Digest Mon Mar 27 16:00:35 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Mobile Robot Information Request
image processing machine learning
ARTIFICIAL INTELLIGENCE AND COMMUNICATING PROCESS ARCHITECTURE
----------------------------------------------------------------------
Date: 22 Mar 89 18:01:36 GMT
From: yamauchi@cs.rochester.edu (Brian Yamauchi)
Subject: Mobile Robot Information Request
Keywords: mobile robot vision robotics
Organization: U of Rochester, CS Dept, Rochester, NY
Our Robotics / Computer Vision research group is looking into
the possibility of getting a mobile robot for our lab. We are looking
for recommendations from mobile robot researchers regarding what types
of robots have worked well for them.
In particular, we are considering the Denning robots and (less
likely) the Heath Hero robots. We limited access to mechanical /
electrical engineering facilities, so we are thinking in terms of a
commercially available robot as opposed to one that would have to be
built from scratch.
We envision mounting CCD video cameras on the robot and having
it communicate through a MaxVideo image processor to a Sun 3/260 that
would be controlling the robot. Both cables and radio/TV links are
being considered for communication, though (depending on the amount of
hardware required) the radio/TV links would be more desireable.
My particular research interests are in the area of
behavior-based robotics, so I would be particularly interesting in
hearing from people who are doing mobile robot work in this area.
Also, does anyone have the address / phone number of Denning
Mobile Robots? Are they on the net?
Thanks in advance,
[ I have seen some literature on the Vectrobot by Real World Interface,
(603)654-6334. Brooks has used it in some of his work. Retails for
$3400 for the base unit (warning: this was the price on 1/88). Has
synchronous drive.
Any others anyone knows of which are applicable for vision
work?
phil... ]
Brian Yamauchi University of Rochester
yamauchi@cs.rochester.edu Computer Science Department
------------------------------
Date: 25 Mar 89 22:35:49 GMT
From: nealiphc@blake.acs.washington.edu (Phillip Neal)
Subject: image processing machine learning
Keywords: image processing machine learning classification
Organization: Univ of Washington, Seattle
I have been trying to do image processing on fish otoliths.
Essentially, counting the rings on otoliths to determine the age of
the fish. The age is then used for management purposes.
However, when I look through the literature, most of the articles seem
to be on triangles, or f-15's/Mig-23's or wrenches or other images
without a lot of noise in them. Furthermore, a lot of the articles seem
to be about theoretical or algorithmic type subjects with very little
discussion of classification results whenapplied to real world data.
Does anybody else sense this ? Or do I have the wrong paradigm
/weltschmertz (sp) .
Is anybody else doing image/learning work on biological images that
aren't kidneys or acres of corn ?
My name is Phil Neal. I am new on the net. I am at
nealiphc@blake.washington.edu in the USA. .
------------------------------
Date: Thu, 23 Mar 89 20:56:37 GMT
From: Steven Zenith <zenith%inmos.co.uk@NSS.Cs.Ucl.AC.UK>
Subject: ARTIFICIAL INTELLIGENCE AND COMMUNICATING PROCESS ARCHITECTURE
International conference
ARTIFICIAL INTELLIGENCE AND COMMUNICATING PROCESS ARCHITECTURE
17th/18th of July 1989, at Imperial College, London UK.
Keynote speaker
Prof. Iann Barron
Invited speakers
Prof. Igor Aleksander Neural Computing Architectures.
Prof. Colin Besant Programming of Robots.
Prof. David Gelernter Information Management in Linda.
Dr. Atsuhiro Goto The Parallel Inference Machine.
Prof. Tosiyasu Kunii Primitive Image Understanding.
Dr. Rajiv Trehan Parallel AI Systems.
Prof. Alan Robinson Functional and Relational reasoning.
Prof. Les Valiant] Bulk-synchronous Parallel Computing.
* Parallel Processing and AI *
Parallel Processing and Artificial Intelligence are two key themes
which have risen to the fore of technology in the past decade. This
international conference brings together the two communities.
Communicating Process Architecture is one of the most successful
models for exploiting the potential power of parallel processing machines.
Artificial Intelligence is perhaps the most challenging applications for
such machines. This conference explores the interaction between these two
technologies.
The carefully selected programme of invited talks and submitted papers
brings together the very best researchers currently working in the field.
* Topics include *
Robotics Neural Networks Image Understanding
Speech Recognition Implementation of Logic Programming Languages
Information management The Japanese Fifth Generation Project
Transputers and Occam
[ Detailed conference program omitted. Please contact the conference
organizers for more information.
phil... ]
* Proceedings *
The edited proceedings includes invited and submitted papers and is
intended for publication in a new book series on Communicating Process
Architecture published by John Wiley and Sons.
* The conference organising committee *
Organising committee, programme editors and conference chairmen:
Dr. Mike Reeve Imperial College, London, UK.
Steven Ericsson Zenith INMOS Limited, Bristol, UK.
The programme and organising committee:
J.T Amenyo Ctr. Telecoms Research, Columbia University.
Jean-Jacques Codani INRIA, France.
Dr. Atsuhiro Goto Institute for New Generation Computer Technology
(ICOT), Japan.
Dr.med.Ulrich Jobst Ostertal - Klinik fur Neurologie und Klinische
Neurophysiologie
Dr. Peter Kacsuk Multilogic Computing, Budapest, Hungary.
Pasi Koikkalainen Lappeenranta University of Technology, Finland.
Prof. T. L. Kunii The University of Tokyo, Japan.
Dr. Heather Liddell Queen Mary College, London.
Prof. Y. Paker Polytechnic of Central London
Prof. L. F. Pau Technical University of Denmark.
Prof. Bernd Radig Institut Fur Informatik, Munchen.
Prof. Alan Robinson Syracuse University, USA.
Kai Ming Shea University of Hong Kong.
Prof. David Warren Bristol University, UK.
Chung Zhang Brighton Polytechnic. UK.
* Registration *
Registration should be received by June 16th. Late registration will
incur a 20 pound surcharge. All enquiries should be addressed to the
conference secretary:
The Conference Secretary,
OUG AI Conferences,
INMOS Limited,
1000 Aztec West,
Almondsbury,
Bristol BS12 4SQ,
UNITED KINGDOM.
Tel. 0454 616616 x503
email: zenith@inmos.co.uk
This conference is underwritten by INMOS Limited, to whom the organising
committee wish to extend their thanks.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/01/89)
Vision-List Digest Fri Mar 31 08:49:55 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Vision List site network reconfiguration warning...
texture data: synthetic and real.
AISB89 Conference and Tutorials, Sussex University, April 18-21
----------------------------------------------------------------------
Date: Fri, 31 Mar 89 08:59:59 PST
From: Vision-List-Request <vision-list-request@ads.com>
To: vision-list@ads.com
Subject: Vision List site network reconfiguration warning...
Next week, the Vision List host site (Advanced Decision Systems) will
be shifting from the ARPANET (officially dead on April 1st) to BARNET
([San Francisco] Bay Area Research NETwork). All addresses remain the
same, though there may be a short interruption of service. If you have
any problems, please let me know ASAP at Vision-List-Request@ADS.COM .
Theretically, the changeover will not disturb service. (Sure, and
Bears use outhouses...)
phil...
----------------------------------------------------------------------
Date: 29 Mar 89 15:59:00 WET
From: JOHN ILLINGWORTH <illing%ee.surrey.ac.uk@NSS.Cs.Ucl.AC.UK>
Subject: texture data: synthetic and real.
greetings all,
I am interested in texture segmentation and would like to
test out some algorithms. For these purposes I would like to know
if anyone has any source programs for generating different types
of textured regions. Ideally I would like a paint-like program so
that I could construct arbitary shaped regions whose internal
texture parameters (local density, orientation etc) are well
defined.
I know of the Brodatz album of textures but does a standard
digitised database version of this exist or does everyone have
their own version taken by pointing their own camera at the
pictures in the album??
I would appreciate any advice on these matters, many thanks
John Illingworth
Dept of Electronics
University of Surrey
Guildford. U.K.
------------------------------
Date: 27 Mar 89 14:46:36 GMT
From: aarons@uk.ac.sussex.syma (Aaron Sloman)
Subject: AISB89 Conference and Tutorials, Sussex University, April 18-21
Keywords: Artificial Intelligence, Cognitive Science, conference, tutorials
Organization: School of Cognitive & Computing Sciences, Sussex Univ. UK
AISB89 CONFERENCE ON ARTIFICIAL INTELLIGENCE
University of Sussex,
BRIGHTON
Tuesday 18th of April - Friday 21st April 1989
INVITED SPEAKERS
J.F. Allen (University of Rochester) H. Barrow (University of Sussex)
V. Lifschitz (Stanford University) Y. Wilks (New Mexico State Uni.)
SESSIONS
Papers will be presented on:
LOGIC PROGRAMMING COGNITIVE MODELLING
CONSTRAINT REASONING NONSTANDARD INFERENCE
ROBOTICS, NEURAL NETWORKS & VISION PLANNING
TUTORIALS
Tutorials will be held on Tuesday 18th April 1989:
Neural Networks Prof. H. Barrow, University of Sussex
Prolog Dr. C. Mellish, University of Edinburgh
Computer Vision Dr. D. Hogg, University of Sussex
Knowledge Elicitation Dr. N. Shadbolt, University of Nottingham
Object-Oriented Programming Mr. T. Simons, University of Sheffield
FEES
TUTORIALS
AISB Members 120.00 pounds sterling
Ordinary Delegates 180.00
Students (Full-time) 60.00
TECHNICAL PROGRAMME
AISB Member 115.00 pounds sterling
Ordinary Delegates 150.00
Students (Full-time) 90.00
NB Fees are not inclusive of lunches or accommodation.
For further details, Programme and Registration forms, contact:
Judith Dennison
AISB 89 Conference Office
School of Cognitive Sciences
University of Sussex
Falmer, Brighton BN1 9QN UK
Tel: (+44) (0) 273 678379
Email: JANET judithd@uk.ac.sussex.cogs
INTERNET judithd%uk.ac.sussex.cogs@nss.cs.ucl.ac.uk
UUCP ...mcvax!ukc!cogs!judithd
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/08/89)
Vision-List Digest Fri Apr 07 10:09:27 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
OPTICOMP computer-mail list on Optical Computing and Holography
resampling filter references wanted
----------------------------------------------------------------------
Date: Sun, 02 Apr 89 14:22:41 IST
From: Shelly Glaser 011 972 3 545 0060 <GLAS%TAUNIVM.BITNET@CUNYVM.CUNY.EDU>
Subject: OPTICOMP computer-mail list on Optical Computing and Holography
'OPTICOMP' COMPUTER-MAIL LIST ON OPTICAL COMPUTING AND HOLOGRAPHY
*---------------------------------------------------------------*
I would like to announce the opening of a new computer mailbox, or list,
named OPTICOMP. This list will be dedicated to Optical Computing and
Holography. Specifically, subjects such as
(*) Holographic displays, including true holographic 3-D display of
computer generated images,
(*) Optical (both analog and digital) information processing, including
pattern recognition, algorithms for rotation/scale/perspective
invariant recognition through correlation, realization of digital
processing machines with optics, communication-intensive computing
architectures etc.
(*) Optical realizations of neural networks and associative memory
systems.
Those of you who are interested in getting this newsletter are invited to
write to me to one of the E-mail addresses below.
Yours,
Shelly Glaser
Snail-mail:
Department of Electronic, Communication, Control and Computer Systems
Faculty of Engineering
Tel-Aviv University
Tel-Aviv, Israel
TELEPHONE: 972 3 545-0060
FAX: 972 3 419513
Computer network: GLAS@TAUNIVM.BITNET
or: glas@vm1.tau.ac.il
or: glas%taunivm.bitnet@cunyvm.cuny.edu
Acknowledge-To: <GLAS@TAUNIVM>
------------------------------
Date: Thu, 6 Apr 89 17:35:30 PDT
From: ph%miro.Berkeley.EDU@berkeley.edu (Paul Heckbert)
Subject: resampling filter references wanted
I'm doing some research on filters for ideal resampling of one discrete
image into another according to an arbitrary 2-D distortion.
I map from a source image with domain (u,v) to a destination image with
domain (x,y) according to user-supplied functions x=x(u,v), y=y(u,v).
The mapping is arbitrary in general, but affine is an important (easy) case.
I want to minimize aliasing due to resampling. Quality filtering for highly
distorted mappings is vital (my application is texture mapping for computer
graphics).
This topic is also called "interpolation" and "multirate DSP" by some.
Any recommendations of books/journal articles would be most appreciated!
Please email them to me, as I don't normally read this list.
thanks,
Paul Heckbert, CS grad student
508-7 Evans Hall, UC Berkeley ARPA: ph@miro.berkeley.edu
Berkeley, CA 94720 UUCP: ucbvax!miro.berkeley.edu!ph
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/28/89)
Vision-List Digest Thu Apr 27 18:04:48 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Volume rendering references
Conference on Visualization in Biomedical Computing
----------------------------------------------------------------------
Date: Thu, 27 Apr 89 11:14 MET
From: "Victor Roos, TFDL-ECIT Wageningen" <"AGRT06::ROOS"%HWALHW50.BITNET@CUNYVM.CUNY.EDU>
Subject: Volume rendering references
We see possibilities for Volume Rendering after reading Karen Frenkels
article in Communications of the ACM, volume 32, #4, april 1989, for
visualization of CT-images from soil samples. Unfortunately Karens
article has no references. We are interested in any leads and references
to articles, algoritms etc. that explain this technique.
Victor Roos
min. of Agriculture and Fisheries
TFDL/ECIT
POB 256
Wageningen
the Netherlands
------------------------------
Date: 27 Apr 89 12:51:52 GMT
From: arkin@gatech.edu (Ron C. Arkin)
Subject: Conference on Visualization in Biomedical Computing
Organization: School of Information and Computer Science, Georgia Tech, Atlanta
First Announcement and Call for Papers
THE FIRST CONFERENCE ON
VISUALIZATION IN BIOMEDICAL COMPUTING
Ritz-Carlton Buckhead Hotel
Atlanta, Georgia
May 22-25, 1990
Sponsored by/in cooperation with:
National Science Foundation
IEEE Computer Society
American Association of Physicists in Medicine
Georgia Institute of Technology
Emory University School of Medicine
Emory-Georgia Tech Biomedical Technology Research Center
Theme:
Visualization in scientific and engineering research is a rapidly emerging
discipline aimed at developing tools and approaches to facilitate the
interpretation of, and interaction with, large amounts of data, thereby
allowing researchers to "see" and comprehend, in a new and deeper manner,
the systems they are studying. This conference, the first of its kind, is
aimed at bringing together researchers working in various aspects of
visualization in order to present and discuss approaches, tools, and
techniques associated with visualization science in general, and visualization
in biomedical computing in particular.
Topics:
o Theories and approaches
Models of visualization
Representation of multidimensional parameters
Psychological aspects of visualization
Perception
Cognition
Human/machine interface
Artificial intelligence in visualization
Computer vision and image processing
Graphics and display
Visual communications and televisualization
Courses and training in visualization
o Applications, techniques, tools
Visualization in
Modeling and simulation of biomedical processes
Diagnostic radiology
Molecular biology and genetics
Neurophysiology
Prosthetics development
Radiation treatment planning
Education
o Other related topics
Technical Committee Co-chairs:
Dr. Edward Catmull, PIXAR Corp.
Dr. Gabor Herman, University of Pennsylvania.
Organizing Committee:
Dr. Norberto Ezquerra, Office of Interdisciplinary Programs,
Georgia Institute of Technology (Chair).
Dr. Ernest Garcia, Department of Radiology, Emory University.
Dr. Ronald C. Arkin, School of Information and Computer Science,
Georgia Institute of Technology.
Call for papers, panels and tutorials (Deadlines):
Paper Abstracts due: August 31, 1989 (Submit 6 copies of 800 word abstract)
Panel and tutorial proposals due: July 31, 1989
Acceptance notification to authors: November 1, 1989
Full papers due: February 1, 1990
Conference: May 22-25, 1990
Abstract Submission/further information:
Dr. Norberto Ezquerra
Office of Interdisciplinary Programs
Georgia Tech, Atlanta, GA 30332
Phone: (404)-894-3964.
Ronald C. Arkin
School of Information & Computer Science, Georgia Tech, Atlanta GA 30332
CSNet: arkin @ GATech ARPA: arkin%GATech.CSNet @ CSNet-Relay.ARPA
uucp: ...!{akgua,allegra,hplabs,ihnp4,linus,seismo,ulysses}!gatech!arkin
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/05/89)
Vision-List Digest Thu May 04 18:00:05 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Discontinuity detection in stereo images/References?
Workshop on MRF models in Computer Vision
Update on CVPR
------------------------------
Date: 1 May 89 17:42:40 GMT
From: doorn@ai.etl.army.mil (Bradley Doorn)
Subject: Discontinuity detection in stereo images/References?
Keywords: stereo,automatic correlation,discontinuities,artificial intelligence
Organization: USAETL, Fort Belvoir, Virginia
I am interested in references and people who are working on the problem of
automatically detecting terrain discontinuities from aerial stereo imagery
prior to obtaining a complete elevation model. The question is 'Can
information obtained from correlation 'attempts' be used to enhance automatic
stereo matching and image interpretation?' One of the baseline problems is the
distinction between textural edges and geometric edges.
Please send the references by e-mail and I will compile and post my findings.
Bradley D. Doorn doorn@ai.etl.army.mil
RI, Engineer Topographic Laboratories
Fort Belvoir, VA 22060
----------------------------------------------------------------------
Date: 1 May 89 16:51:53 GMT
From: anand%brand.usc.edu@usc.edu (Anand Rangarajan)
Subject: Workshop on MRF models in Computer Vision
Organization: University of Southern California, Los Angeles, CA
Workshop on Theory and Applications of
Markov Random Fields
for
Image Processing, Analysis and Computer Vision
June 9, 1989
Sheraton Grand Hotel on Harbor Island
San Diego, California
This one day workshop sponsored by the Information Robotics and Intelligent
Systems Program of NSF will explore the strengths and limitations of the
Theory and Applications of Markov Random Fields for Image Processing, Analysis
and Computer Vision. The preliminary program given below consists of several
invited lectures and a panel session.
Workshop Co-Chairs
Professor Rama Chellappa Professor Anil K. Jain
Department of Electrical Engineering Department of Computer Science
University of Southern California Michigan State University
Los Angeles, CA 90089 East Lansing, MI 44824
(213) 743-8559 (517) 353-5150
rama@brand.usc.edu jain@cps.msu.edu
Preliminary Program
8:00 a.m. Registration
8:30 a.m. Opening Remarks
8:45-10:15 a.m.
J. Besag Introduction to MRF and It's Applications
R.L. Kashyap Robust Image Models for Restoration and Edge Detection
J.W. Woods Simulated Annealing for Compound GMRF Models
10:15-10:45 a.m. Coffee Break
10:45-12:15 p.m.
D.B. Cooper On the Use of MRF in 3-D Surface Estimation
H. Derin MRF Based Segmentation and It's Limitations
S. Geman An Application of MRF to Medical Imaging
12:15-1:30 p.m. Lunch
1:30-3:00 p.m.
C. Koch Analog Networks for Early Vision
T. Poggio and Representation of Discontinuities and Integration of
Vision Modules
D. Weinshall
3:00-3:30 p.m. Coffee Break
3:30-5:00 p.m. Panel Session
Strengths and Limitations of MRF Models
Panelists: J. Besag, R.M. Haralick, A.K. Jain (Moderator)
L.N. Kanal, R.L. Kashyap.
Registration Information
A modest fee of $25.00 will be charged to cover incidental expenses. Please
make check payable to MRF '89 and send to:
Miss Gloria Bullock
University of Southern California
Signal and Image Processing Institute
Powell Hall 306, Mail Code 0272
University Park
Los Angeles, CA 90089
Anand Rangarajan
anand@hotspur.usc.edu
anand@brand.usc.edu
``A spirit with a vision
------------------------------
Date: 1 May 89 17:57:04 GMT
From: anand%brand.usc.edu@usc.edu (Anand Rangarajan)
Subject: Update on CVPR
Organization: University of Southern California, Los Angeles, CA
IEEE Computer Society Conference
on
COMPUTER VISION AND PATTERN RECOGNITION
Sheraton Grand Hotel
San Diego, California
June 4-8, 1989
General Chair
Professor Rama Chellappa
Department of EE-Systems
University of Southern California
Los Angeles, California 90089-0272
Program Co-Chairs
Professor Worthy Martin Professor John Kender
Dept. of Computer Science Dept. of Computer Science
Thornton Hall Columbia University
University of Virginia New York, New York 10027
Charlottesville, Virginia 22903
Tutorials Chair
Professor Keith Price
Department of EE-Systems
University of Southern California
Los Angeles, CA 90089-0272
Local Arrangements Chair
Professor Shankar Chatterjee
Department of Electrical and Computer Engg.
University of California at San Diego
La Jolla, CA 92093
Program Committee
Chris Brown Avi Kak Theo Pavlidis
Allen Hansen Rangaswamy Kashyap Alex Pentland
Robert Haralick Joseph Kearney Azriel Rosenfeld
Ellen Hildreth Daryl Lawton Roger Tsai
Anil Jain Martin Levine John Tsotsos
Ramesh Jain David Lowe John Webb
John Jarvis Gerard Medioni
General Conference Sessions will be held
June 6-8, 1989
Conference Registration
(for CVPR and Tutorials)
Conference Department
CVPR
IEEE Computer Society
1730 Massachusetts Ave
Washington, D.C. 20036-1903
(202) 371 1013
Fax Number:(202) 728 9614
Fees, before May 15
CVPR - $200 (IEEE Members, includes proceedings and banquet)
- $250 (Nonmembers)
- $100 (Students, includes proceedings and banquet)
Tutorials - $100 per session (IEEE Members and Students)
- $125 per session (Nonmembers)
Fees, after May 15
CVPR - $240 (IEEE Members, includes proceedings and banquet)
- $300 (Nonmembers)
- $105 (Students, including proceedings and banquet)
Tutorials - $125 per session (IEEE Members and students)
- $150 per session (Nonmembers)
Hotel Reservations
RESERVATIONS CUT-OFF DATE
-------------------------
All reservations must be received by the hotel before May 15, 1989.
Reservations received after this date are not guaranteed and will be accepted
on a space-available basis only.
A deposit of one night's room fee, a major credit card guarantee or a personal
or company check, is required to confirm a reservation. All rates are subject
to a 9% occupancy tax.
Check-in time: 3:00 p.m. Check out time: 12:00 noon
The Sheraton Grand Hotel on Harbor Island
Sheraton Reservation Center
1590 Harbor Island Drive
San Diego, CA 92101
(619)692-2265
Rooms - $102 per night (single or double)
The Advance Program with registration forms, etc. has been
mailed out of the IEEE offices.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/16/89)
Vision-List Digest Mon May 15 11:17:30 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: CALL TO VOTE: sci.med.physics ---------------------------------------------------------------------- Date: 11 May 89 21:47:22 GMT From: james@rover.bsd.uchicago.edu Subject: CALL TO VOTE: sci.med.physics Organization: University of Chicago - Dept. Rad. Onc. and Med. Physics I would like to call for a vote on the formation of a Medical Physics newsgroup (Sci.Med.Physics), which would deal with most applications of Physics in Medicine. Based on my own experiences in medical imaging and in the Graduate Program in Medical Physics that I am currently in, I would like to see features generally related to imaging and radiation therapy, but I can easily see the applicability to biophysics and related fields. Topics include (but are not limited to): Biomechanics Biophysics Basic interactions of radiation with matter " " living systems Methods of Generating diagnostic information: NMR (MRI) imaging systems CT (computed tomography) Projection Radiography (including angiography and the new MEGAVOLTAGE imaging systems in Radiation therapy, as well as computed Radiography) Ultrasound Nuclear medicine imaging systems (eg. Gamma Camera, PET, SPECT,...) Thermography MEG EEG EKG Electric Impedence Tomography Image Communication Computer aided diagnosis All fields of analysis applied to medical images So on Methods used in Radiation therapy, including: Simulation and verification methods 2D and 3D treatment planning Electrons, protons and assorted heavy ions Neutron therapy Quality assurance Brachytherapy Monoclonal Antibody imaging/treatment methods The call for votes is cross listed in the groups sci.physics and comp.graphics All votes (YES and NO) will be taken by james@rover.uchicago.edu Thank you for your attention. Sincerely, James Balter James@rover.Uchicago.edu "If the hat fits, slice it!" ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/20/89)
Vision-List Digest Fri May 19 15:59:28 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Registration of multiple views of a beating heart
Fifth workshop on human and machine vision
SEMINAR: Prediction of the Illuminant's Effect on Surface Color Appearance
Seminar in Machine Vision at Rutgers University
------------------------------
Date: Fri, 19 May 89 12:00:18 EDT
From: agr@ares.cs.wayne.edu
Subject: Registration of multiple views of a beating heart
REQUEST FOR REFERENCES FOR REGISTRATION OF MULTIPLE VIEW OF A
BEATING HEART.
We are trying to reconstruct the coronary arteries in three
dimension for a live heart. In order to that several views of the
beating heart should be registered correctly.
Any recommendations of books/journal articles would be very much
appreciated.
Please email to the following address:
agr@jupiter.cs.wayne.edu
Thanks
Arindam Guptaray
Cardiac Laser Lab
Harper Hospital
3990 John R,
Detroit, MI 48201.
------------------------------
Date: Fri, 19 May 89 14:25 EDT
From: Sandy Pentland <sandy@media-lab.media.mit.edu>
Subject: Workshop announcement
FIFTH WORKSHOP ON HUMAN AND MACHINE VISION
Sea Crest Resort,350 Quaker Road, North Falmouth, MA 02556-2903
On June 15, the day following the Optical Society of
America's Image Understanding and Machine Vision Topical
Meeting, the Fifth Workshop on Human and Machine Vision will
be held. Organized by Jacob Beck of the University of Ore-
gon and Azriel Rosenfeld of the University of Maryland, the
Workshop will consist of invited papers on models for human
visual processes. It will be held in the Nauset IV Room,
Sea Crest Resort, North Falmouth, MA from 8:30 to 4 PM.
The Workshop registration fee is $30.
The following papers will be presented:
``Line Segregation'', Jacob Beck, Azriel Rosenfeld, and
Richard Ivry, University of Oregon and University of
Maryland.
``Motion and Texture Analysis'', John Daugman, Harvard
University.
``The Medium is Not the Message in Preattentive Vision'',
James Enns, University of British Columbia.
``A Neural Network Architecture for Form and Motion Percep-
tion'', Stephen Grossberg, Boston University.
``Conservation Laws and the Evolution of Shape'', Benjamin
B. Kimia, Allen Tannenbaum, and Steven W. Zucker,
McGill University.
``A Biological Mechanism for Shape from Shading and
Motion'', Alexander Pentland, Massachusetts Institute
of Technology.
For more information about transportation, lodging, etc., contact:
Barbara Hope, Center for Automation Research,
University of Maryland, College Park, MD 20742-3411
Telephone: 301-454-4526
----------------------------------------------------------------------
Date: Wed, 17 May 89 15:24:42 PDT
From: binford@anaconda.stanford.edu (Tom Binford)
Subject: SEMINAR: Prediction of the Illuminant's Effect on Surface Color Appearance
Monday, 2/22, 4:15, Cedar Hall Conference
Prediction of the illuminant's effect on surface color appearance
David H. Brainard
Department of Psychology
Stanford University
Changes in the spectral power distribution of the ambient
illumination change the spectral properties of the light reflected
from a surface to the eye. It is commonly believed that the human
visual system adapts to reduce the change in perceived surface color
appearance under changes of illumination. I use a matching paradigm
to quantify the effects of adaptation to the illuminant on color
appearance. My results show that this adaptation serves to reduce
but not eliminate changes in surface color appearance.
Because there are many possible surfaces and illuminant changes, it
is not possible to measure directly the effects of adaptation for
all of them. I propose using a finite dimensional bi-linear system
to model the process of adaptation. This class of model has two
advantages. First, it is possible to test whether the model
describes the data. Second, to the extent that the model holds, it
allows prediction of the effects of adaptation on the appearance of
any surface for any illuminant change. I present data that test how
well the bi-linear model describes human performance.
------------------------------
Date: 18 May 89 04:16:46 GMT
From: scarter@caip.rutgers.edu (Stephen M. Carter)
Subject: Seminar in Machine Vision at Rutgers University
Organization: Rutgers Univ., New Brunswick, N.J.
[ Though this appears to be a for-profit enterprise, it bears sufficient
relevance to this List to justify posting.
phil... ]
The Center for Computer Aids for Industrial Productivity (CAIP)
at RUTGERS, The State University of N.J.
Presents
MACHINE VISION -An intensive five-day course for engineers and scientists
concerned with the theory and application of machine vision.
July 10-14, 1989 - New Brunswick, New Jersey
Lectures given by Dr. H. Freeman, and a staff of leading experts noted for
their work in the field of machine vision will provide a detailed presentation
of the concepts and techniques used in applying machine vision to industrial
problems. Emphasis will be placed on sensors,illumination techniques, computer
algorithms,hardware requirements, and system considerations. The material
presented will range from basic techniques to the latest,state-of-the-art
methods. Case studies of actual applications in industry, health care,
surveillance, and the military will be presented.
Registration fee: $895. Includes all materials, texts, etc. (Discount of
10% for 3 or more registrants from same organization.)
Course Location: Hyatt Regency, New Brunswick, N.J.
For further information contact:
Sandra Epstein
Telephone: (201) 932-4208
FAX: (201) 932-4775
Email: sepstein@caip.rutgers.edu
..!rutgers!caip!sepstein
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/27/89)
Vision-List Digest Fri May 26 14:43:10 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: learning to play Go and Neural Networks: info request ---------------------------------------------------------------------- Date: 23 May 89 08:32:41 GMT From: munnari!latcs1.oz.au!mahler@uunet.UU.NET (Daniel Mahler) Subject: learning to play Go and Neural Networks: info request Organization: Comp Sci, La Trobe Uni, Australia [ Not a mainline vision question, but perhaps of interest to some. phil... ] i am an honours student working on implementing a neural network that learns to play Go. this seems appropriate as Go has a much higher (~50x) branching factor, forcing a pattern oriented rather than a lookahead orinted approach, and most instruction (heuristics advocated by books & players) are of an intuitive nature hard to formalise into the classical ai symbolic/logical paradigm. My current idea is to preprocess the board position using image/signal processing techniques (eg transforms, filters, convolution, multi dimensional grammars) to enhance the strategic structure of the position over superficial similarities; in other words i will treat the board as a 2d signal/image. I will concentrate mainly on the opening to early middle game phase, as these are quiescent; later stages become more dependent on tactical lookahead. All responses, be they bibliographic, theoretical, practical, or philosophical, will be apprecited. i leave to your discretion to judge the appropriatness of replying by news or email. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/04/89)
Vision-List Digest Sat Jun 03 17:05:23 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Request for range images
Rule based decisions vs functional decisions
Post Doctoral Faculty Positions in Computer Science at CMU
Invitation to Join the SUN Medical Users Group
------------------------------
Date: 02 Jun 89 10:19:06+0200
From: Martin Peter <mpeter@bernina.zir.ethz.ch>
Subject: Request for range images
I'm working as a phd student on a 3-d object recognition system, based
on a constraint search algorithm. Typical application of the system
may be a robot for sorting parcels in a postoffice. Objects in the
scene are modeled with planar, cylindrical and general curved surface
patches.Occlusion is allowed. Inputdatas should come from a structured
light sensor, which the low level part will convert into surface patch
information. Unfortunately the structured light sensor is not yet
working, so I'm playing around with some simple synthetically
generated images.
Question: Are there in the Computer Vision Community some standart
range images avaible, maybe some standart benchmark scenes ? Can some
one mail me some range images ?
Thanks for any help.
[ This is a great idea. It is often difficult for all of us to get
interesting and useful data. Anyone willing to share data with others,
please post a description of its type, size, properties, etc. Anyone
who knows of a public repository for this type of data, please post
what you know. One would think that the U.S. Gov't, with all the
image based work they fund, has at least several public repositories
which could be used to obtain data. Any info anyone?
phil... ]
Martin Peter > EAN: mpeter@zir.ethz.ch
Computer Vison Lab > UUCP: mpeter@ethz.uucp
Swiss Fed. Inst. Of Tech. > BITNET: mpeter@czheth5a.bitnet
IKT/BIWI
ETH Zurich/Swizterland
------------------------------
Date: 3 Jun 89 01:47:52 GMT
From: nealiphc@blake.acs.washington.edu (Phillip Neal)
Subject: rule based decisions vs functional decisions
Keywords: image understanding, machine learning , image processing
Organization: Univ of Washington, Seattle
Does anybody have any performance numbers for a rule based decision
making image segmentation method vs a regular functional decision
making method.
In other words, which is better -- theoretically or empirically in
terms of classification rate:
1. Developing rules like:
If the edge is more than 20 grey levels and the major direction is north
east, then the confidence factor for this rule is 20
else
confidence factor for this rule is 0
vs
2. y = f(delta(grey),direction)
if(y.gt..5) then this is a true edge.
and the coefficients are 'learned' through some inductive process
like discriminant analysis or some bayesian update routine.
That's all for now,
Phil Neal ---- nealiphc@blake.acs.washington.edu
------------------------------
Date: Wednesday, 31 May 1989 23:12:50 EDT
From: Dave.McKeown@maps.cs.cmu.edu
Subject: Post Doctoral Faculty Positions in Computer Science at CMU
Post Doctoral Faculty Positions in Computer Science
Digital Mapping Laboratory
School of Computer Science
Carnegie Mellon University
Applications are invited for a post-doctoral research faculty position in the
School of Computer Science at Carnegie Mellon University. This position is
tenable for two years with possibilities for appointment to the regular
Research or Systems Faculty track within the School.
The successful applicant will be expected to play a major role in the current
and future research efforts within the Digital Mapping Laboratory. Our
research is broadly focused on the automated interpretation of remotely
sensed data including high-resolution aerial imagery and multi-spectral
imagery such as SPOT and Landsat TM. Current areas of investigation include
knowledge-based scene analysis, automated acquisition of spatial and
structural constraints, cultural feature extraction (road network, and
building detection and delineation), automated scene registration and stereo
matching, parallel architectures for production systems, and large-scale
spatial databases.
A strong background in one or more of these or related areas is required.
Excellent written and verbal communication skills are also expected.
Applicants should send a curriculum vitae and names of at least three
references to:
David M. McKeown
Digital Mapping Laboratory
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213.
Carnegie Mellon is an Equal Opportunity/Affirmative Action employer.
----------------------------------------------------------------------
Date: Wed, 31 May 89 10:26:32 PDT
From: clairee%sunwhere@Sun.COM (Claire Eurglunes)
Subject: Invitation to Join the SUN Medical Users Group
Greetings:
My name is Claire Eurglunes and I have recently been hired by SUN
Microsystems in Mountain View to form the SUN Medical Users Group. I
work under Ken Macrae in the Scientific Products area.
I am currently looking for all SUN and TAAC users that may be
interested in joining this users group. We are planning a first
meeting towards the end of June.
Please contact me if you are interested...we hope to establish users
lists, a bibliography of papers, abstracts and presentations, a
software consortium, etc.
Claire Eurglunes
sunwhere.Sun.COM!clairee@sun.com
(415)336-5131
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/17/89)
Vision-List Digest Fri Jun 16 09:19:51 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
rule based decisions vs functional decisions
Image Repository
Range Images
RE: Vision-List delayed redistribution
Range imagery
Re: Request for range images
Neural nets for vision
Where is Alv software ?
Vision/Image Processing Languages
video recording equipment
----------------------------------------------------------------------
Date: 3 Jun 89 01:47:52 GMT
From: Phillip Neal <nealiphc@BLAKE.ACS.WASHINGTON.EDU>
Subject: rule based decisions vs functional decisions
Keywords: image understanding, machine learning , image processing
Organization: Univ of Washington, Seattle
Does anybody have any performance numbers for a rule based decision
making image segmentation method vs a regular functional decision
making method.
In other words, which is better -- theoretically or empirically in terms
of classification rate:
1. Developing rules like:
If the edge is more than 20 grey levels and the major direction is north
east, then the confidence factor for this rule is 20
else
confidence factor for this rule is 0
vs
2. y = f(delta(grey),direction)
if(y.gt..5) then this is a true edge.
and the coefficients are 'learned' through some inductive process
like discriminant analysis or some bayesian update routine.
That's all for now,
Phil Neal ---- nealiphc@blake.acs.washington.edu
------------------------------
Date: Mon, 5 Jun 89 09:08:43 BST
From: alien%VULCAN.ESE.ESSEX.AC.UK@CUNYVM.CUNY.EDU (Adrian F. Clark)
Subject: Image Repository
I'm interested in collecting together a set of `standard' images of
all types--TV, remote sensing, tomography, range, etc to test out a
package I'm developing. I'm also looking at ways of making imagery
available over a network (ie, lossless coding into that ASCII subset
which will pass through most gateways unscathed). The sort of imagery
I'm looking for should be both good (standard algorithms work) and bad
(standard algorithms fail). If anyone else is interested in such an
idea, please contact the author...especially if you've some suitable
imagery!
Adrian F. Clark
JANET: alien@uk.ac.essex.ese
ARPA: alien%uk.ac.essex.ese@nss.cs.ucl.ac.uk
BITNET: alien%uk.ac.essex.ese@ac.uk
Smail: Dept. of Electronic Systems Engineering, Essex University,
Wivenhoe Park, Colchester, Essex C04 3SQ, U. K.
Phone: (+44) 206-872432 (direct)
"The great tragedy of Science--the slaying of a beautiful
hypothesis by an ugly fact." -- T H Huxley (1825-95)
------------------------------
Subject: Range Images
Date: Mon, 05 Jun 89 10:06:58 -0400
From: "Kenneth I. Laws" <klaws@nsf.GOV>
One source of range images is the NRCC Three-Dimensional
Image Data Files. The collection includes: simple objects
with planar, spherical, and cylindrical surfaces, sometimes
overlapping; multiple views of isolated objects; human faces;
and various complex objects. For information about tapes
and diskettes (about $350 for each section of 40-66 images
on tape, $750 on 5.25" diskettes) contact
M. Rioux or L. Cournoyer
Photonics and Sensors Section
Laboratory for Intelligent Systems
Division of Electrical Engineering
National Research Council of Canada
Ottawa, Ontario, Canada K1A 0R8
(613) 993-7902
-- Ken Laws
National Science Foundation
------------------------------
Date: Mon, 5 Jun 89 10:46 CDT
From: "H. Ogmen, OGMEN@UHVAX1.UH.EDU, OGMEN@UHVAX1.BITNET"
Subject: RE: Vision-List delayed redistribution
Re: Three-dimensional image data files.
The National Research Council of Canada (NRC) has a large number of
three-dimensional image data files.
For information about these images (and prices) contact:
M. Rioux, L. Cournoyer
Photonics and Sensors Section
Laboratory for Intelligent Systems
Division of Electrical Engineering
National Research Council of Canada
Ottawa, Ontario, Canada
K1A 0R8
Tel. (613) 993 7902
Telex: 053-4134
Telefax: 613- 952-7998
H. Ogmen
Dept. of EE
University of Houston
------------------------------
Date: Mon 5 Jun 89 10:50:53-PDT
From: Gerard Medioni <MEDIONI%DWORKIN.usc.edu@oberon.usc.edu>
Subject: Range imagery
I am aware of at least two sets of "standard" range image databases,
one from university of Utah (Prof Thom Henderson), and one from the
National Research Council of Canada (M. Rioux and L. Cournoyer). The
first is available at a nominal fee, the second for a few hundred $$.
------------------------------
Date: Tue, 6 Jun 89 09:31:20 PDT
From: Bruce Bon <bon@saavik.Jpl.Nasa.Gov>
Subject: Re: Request for range images
There is an extensive set (214 images) of range images published by the
National Research Council Canada. The range data was taken with a
synchronized laser scanner. A book, "The NRCC Three-dimensional Image
Data Files," CNRC 29077, contains all of these images and is available
at no charge from:
Editorial Office, Room 301
Division of Electrical Engineering
National Research Council of Canada
Ottawa, Ontario, Canada
K1A 0R8
Machine-readable versions are available in several formats (ASCII/binary,
raw/interpolated) on 1600 bpi magtape and 5 1/4" DSDD diskettes. For
information, contact:
M. Rioux and L. Cournoyer
Photonics and Sensors Section
Laboratory for Intelligent Systems
Division of Electrical Engineering
National Research Council of Canada
Ottawa, Ontario, Canada
K1A 0R8
Telephone: (613) 993-7902
Telex: 053-4134
Telefax: (613) 952-7998
I hope this helps.
Bruce Bon
bon@robotics.jpl.nasa.gov (ARPAnet)
------------------------------
Date: 6 Jun 89 23:06:13 GMT
From: kroger@cs.utexas.edu (Jim Kroger)
Subject: Neural nets for vision
Keywords: neural nets, paten recognition, computer vision
Organization: U. Texas CS Dept., Austin, Texas
Are there any existing applications of neural net technology to object
recognition problems? I know that much theoretical work with neural
nets has involved vision, the work of David Marr being an example.
However, I am interested in creatng a system which can actually
recognize a sizeable number of objects. I am not sure whether this is
somehing that can now be accomplished in hardware, or must be
implemented in software. Can anybody advise me as to existing systems
or techniques, either hardware or software, which might accomplish
this task? Also, what kind of hardware is optimal for software
implementations? Basically, I want to know if neural net technology
offers any practical, workable solution to object recognition.
Any information or references will be greatly appreciated, and a
summary will be posted.
Jim Kroger
kroger@cs.utexas.edu
------------------------------
Date: Wed, 7 Jun 89 21:24:00 edt
From: parzen%jimmy@bess.HARVARD.EDU (Michael Parzen)
Subject: Where is Alv software ?
Back in November of 1988, I ftp'd some software written by Phill Everson
called Alv (autonomous land vehicle). It was some good vision software.
Does anyone know where I ftp'd this software from, i.e. where it can be
located on the net ? I forgot where it was and need to get it again.
Thanks in advance.
Mike Parzen
parzen@csc.brown.edu
------------------------------
Date: 10 Jun 89 00:13:20 GMT
From: mdavcr!rdr@uunet.UU.NET (Randolph Roesler)
Subject: Vision/Image Processing Languages
Summary: Wanted - Image Processing Language References
Keywords: Image Language
Organization: /etc/organization
I am looking for references to Image
processing languages. What I want is
a language which has builtin support
for high and low level image/vision
operations.
I.e. image -> image operations
image -> object operations
object -> object operations
Please, don't inform me of great general
purpose languages such as lisp, prolog, ....
Research and commercial languages OK.
We summarize to the Net.
Randy Roesler
MacDonald Dettwiler
Vancouver, BC, Canada
604-278-3411
uunet!van-bc!mdavcr!rdr
------------------------------
Date: 16 Jun 89 01:37:02 GMT
From: munnari!latcs1.oz.au!suter@uunet.UU.NET (David Suter)
Subject: video recording equipment
Organization: Comp Sci, La Trobe Uni, Australia
I have a query about the availabilty of video recording equipment
(manufacturers names if such exists) for a medical monitoring application.
Essentially the video signal has other information (other than the picture)
encoded during the blanking periods. The applications require to different
recording systems:
1. After a period of monitoring (say about 10 secs) the recording equipment
dumps 1 picture frame to tape or disc and also the average of some quantity
that has been encoded on the blanking periods.
2. After an event trigger a recording is made of THE 30 SECS TO 1 MIN
that occurred PRIOR to the Event - as well as 1 MIN or so after the event.
The general idea is that in both cases the encoded data as well as the
video data corresponding to this, can be analysed later to see what
was happening when interestin events occurred - in the later case it
is important to see what lead up to the event. The applications
concerned are not mine - so the details relayed may be a little hazy.
However, the general charcteristics required are as above. My contact
believes that there are commercial systems that do the type of thing
above (DATA VIDEO ENCODER?) but doesn't know sources of such
equipment. For 2. he wants any suggestions of ways of acheiving these
ends (somehow having the previous 1 min available to store if an
interesting event occurs). The system must be capable of running on a
video tape that is changed say every 3 hrs. Thus suggestion of
solutions he can get engineeered himself - or companies that deal in
equipment that provide this sort of functionality.
thanks.
d.s.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/21/89)
Vision-List Digest Tue Jun 20 09:52:12 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
CONFERENCE ANNOUNCEMENTS:
AI and communicating process architecturess conference
CFP Eurographics'90 Conference
----------------------------------------------------------------------
Date: Tue, 13 Jun 89 11:16:22 BST
From: Steven Zenith <zenith@inmos-c.ads.com>
Subject: AI and communicating process architecturess conference
International conference
ARTIFICIAL INTELLIGENCE AND COMMUNICATING PROCESS ARCHITECTURE
17th/18th of July 1989, at Imperial College, London UK.
Keynote speaker
Prof. Iann Barron
Invited speakers
Prof. Igor Aleksander Neural Computing Architectures.
Prof. Colin Besant Programming of Robots.
Prof. David Gelernter Information Management in Linda.
Dr. Atsuhiro Goto The Parallel Inference Machine.
Prof. Tosiyasu Kunii Primitive Image Understanding.
Dr. Rajiv Trehan Parallel AI Systems.
Prof. Alan Robinson Functional and Relational reasoning.
Prof. Les Valiant] Bulk-synchronous Parallel Computing.
* Parallel Processing and AI *
Parallel Processing and Artificial Intelligence are two key themes
which have risen to the fore of technology in the past decade. This
international conference brings together the two communities.
Communicating Process Architecture is one of the most successful
models for exploiting the potential power of parallel processing machines.
Artificial Intelligence is perhaps the most challenging applications for
such machines. This conference explores the interaction between these two
technologies.
The carefully selected programme of invited talks and submitted papers
brings together the very best researchers currently working in the field.
* Topics include *
Robotics Neural Networks Image Understanding
Speech Recognition Implementation of Logic Programming Languages
Information management The Japanese Fifth Generation Project
Transputers and Occam
* Submitted papers *
Fault Tolerant Transputer Network for Image Processing
-- S Pfleger etal.
Multi-Transputer Implementation of CS-Prolog
-- Peter Kacsuk and I Futo
Transputer Common-Lisp: A Parallel Symbolic Language on Transputers
-- Bruno Pages
Fast Robot Kinematic Modelling via Transputer Networks
-- A.Y.Zomaya and A.S.Morris
Transputer-based Behavioral Module for Multi-Sensory Robot Control
-- Zhang Ying
PUSSYCAT: A Parallel Simulation System for Cellular Automata on Transputers
-- Eddy Pauwels
Self-organising Systems and their Transputer Implementation
-- D.A.Linkens and S.B.Hasnain
The Suitability of Transputer Networks for Various Classes of Algorithms
-- M.Korsloot etal.
* Proceedings *
The edited proceedings includes invited and submitted papers and is
published in a new book series on Communicating Process Architecture
published by John Wiley and Sons.
Organising committee, programme editors and conference chairmen:
Dr. Mike Reeve Imperial College, London, UK.
Steven Ericsson Zenith INMOS Limited, Bristol, UK.
* Conference dinner *
The conference dinner will be held at London Zoo, with before dinner
sherry in the Aquarium. Coaches will transport delegates.
* Accommodation *
Accommodation is available on the Campus of Imperial College. Campus
accommodation is available for Sunday and/or Monday night. Hotel
accommodation can be arranged separately by writing to the conference
secretary.
* Car parking *
Available at a number of local NCP sites.
* Payment *
Cheques or bankers drafts in pounds sterling should be made payable
to: OUG AI Conferences
Full name___________________________________________
Institute/Company___________________________________
Address_____________________________________________
____________________________________________________
____________________________________________________
____________________________________________________
Country_____________________________________________
email :_____________________________________________
Non-residential 200 pounds sterling []
Residential (1 night) 225 pounds sterling []
Residential (2 nights) 250 pounds sterling []
Conference dinner 42 pounds sterling []
Total Payable________________________
Some student subsidy is available. 50% subsidy for UK students, 25% subsidy
for overseas students. Accomodation for students is at 15 pounds, but the
conference dinner is full fee.
Special dietary requirements:
Vegan [] Vegetarian [] Other (Please specify)
Date____________
Signed_______________________________ Dated_____________________
* Registration *
Registration should be received by June 16th. Late registration will
incur a 20 pound surcharge. All enquiries should be addressed to the
conference secretary:
The Conference Secretary,
OUG AI Conferences,
INMOS Limited,
1000 Aztec West,
Almondsbury,
Bristol BS12 4SQ,
UNITED KINGDOM.
Tel. 0454 616616 x503
email: zenith@inmos.co.uk
occam user group
* artificial intelligence *
special interest group
1st technical meeting of the OUG AISIG
This conference is underwritten by INMOS Limited, to whom the organising
committee wish to extend their thanks.
------------------------------
Date: 7 Jun 89 07:28:39 GMT
From: ivan@cwi.nl (Ivan Herman)
Subject: CFP Eurographics'90 Conference
Organization: CWI, Amsterdam
Call for Papers, Call for Tutorials and Call for State of the
Art Reports
EUROGRAPHICS '90
September 3-7, 1990
Montreux, Switzerland
Images: Synthesis, Analysis and Interaction
Call for Participation
(first announcement)
The EUROGRAPHICS Association is 10 years old in September 1990.
For the last 10 years, EUROGRAPHICS has served the European and
worldwide research community in computer graphics and its applications,
through the annual event, journal, workshop programme and other
activities.
In the past, EUROGRAPHICS conferences have concentrated in the main on
topics traditionally associated with computer graphics and human
computer interaction. EUROGRAPHICS '90 will continue to address such
topics.
For EUROGRAPHICS '90, a new theme of the conference will be the
relationship between image synthesis (traditionally the domain of
computer graphics) and image processing and computer vision.
It is now clear that there is overlap between image synthesis and image
analysis in both techniques and applications. For example, as computer
graphics is used more and more in the visualization of scientific and
engineering computations, so it looks likely that image processing
techniques will be used to help develop an understanding of the results.
Tutorials, state of the art reports and invited papers will address the
relationship between graphics and image processing, at both introductory
and advanced levels, and submitted papers are invited in this area.
CONFERENCE
September 5-7, 1990
Papers selected by the International Programme Committee will present
the most relevant and recent developments in Computer Graphics.
The Conference Proceedings will be published by North-Holland.
List of Topics
Graphics Hardware
Superworkstations
Hypersystems
Graphics and Parallelism
Distributed Graphics
Visualization Techniques
Animation and Simulation
Image Processing
Sampling Theory
Unwarping
Image Filtering
Image Representation
Computational Geometry
Graphics Algorithms and Techniques
Modelling
Standards
Exchange of Product Data
Graphics for CAD, CAM, CAE, ...
Human-Computer Interaction
Human Factors
Tool Kits for UIMS and WMs
Presentation Graphics
Graphics in the Office
Graphics in Publication and Documentation
Page Description Languages
Novel Graphics Applications
Graphics as an Experimental Tool
Graphics in Education
Integration of Graphics and Data Bases
Colour
Multi Media Graphics
INSTRUCTIONS TO AUTHORS
Authors are invited to submit unpublished original papers related to
recent developments in computer graphics and image processing. Full
papers (maximum 5000 words) including illustrations, should be sent to
the Conference Secretariat by Nov. 15,1989. Authors should indicate
the topic area(s) they consider appropriate for the paper. The first
page should include the title, name of the author(s), affiliation,
address, telephone, telex, and telefax numbers, and electronic mail
address, together with an abstract (maximum 200 words). Papers with
multiple authors should clearly indicate to which author correspondence
should be addressed.
The author of the Best Paper, selected by an international jury, will
receive the Gunter Enderle Award, which includes a cash prize. The best
three papers will be also published in an international journal.
Lectures will be given in English and all papers should be submitted
in English.
TUTORIALS
September 3-4, 1990
The first two days of the event will be devoted to the tutorial
programme. Tutorials will be given by leading international experts
and will cover a wide range of topics offering an excellent opportunity
for professional development in computer graphics and related areas.
The programme includes both introductory and advanced tutorials.
Each tutorial will occupy one full day. Lecture notes will be provided
for attendees.
Preliminary List of Topics
Introduction to Image Processing
Introduction to Ray Tracing and Radiosity
Image Reconstruction
Superworkstations for Graphics
Human Visual Perception
Intelligent CAD Systems
Free-form Surfaces and CSG
Graphics and Distributed Environments
Scientific Data Visualization
Computer Vision
Traditional Animation: A Fresh Look
Computer Graphics for Software Engineering
The list of topics is still preliminary; the organisers would welcome
any new proposal for tutorials.
STATE OF THE ART REPORTS
September 5-7, 1990
In parallel with the conference proper, a series of 1 1/2 hour reports
on topics of wide current interest will be given by leading experts in
the fields. These will serve to keep attendees abreast of the state
of the art in these fields and recent significant advances.
Preliminary List of Topics
Standardization in Graphics and Image Processing: Present and Future
Advanced Rendering
Object Oriented Design in Action
Digital Typography
Simulation of Natural Phenomena
Advanced Mathematics and Computer Graphics
Interactive Graphics and Video Discs
Graphics - Education
Human Prototyping
The list of topics is still preliminary; the organisers would welcome
any new proposal for tutorials.
VIDEO AND FILM COMPETITION
There will be a competition of computer-generated videos and films,
with prizes awarded for the best entries based on creativity and
technical excellence. Submissions are invited for scientific and
technical applications, art and real-time generated sequences. Entries
will be shown during the conference.
SLIDE COMPETITION
A competition will also be held for artistic images and scientific and
technical images submitted on 35mm slides. Prizes will be awarded for
the best entries and slides will be shown during the conference.
The closing date for submission to both competitions will be June 15,
1990. Entries should be sent to the Conference Secretariat. Rules for
the competition will be sent to people returning the slip and
indicating their intention to submit.
IMPORTANT DATES
Today:
Fill in and mail the attached reply card
July 15, 1989
Deadline for proposals for tutorials and state of the art reports
November 15, 1989:
Full paper should be received by Conference Secretariat
January 12, 1990:
International Programme Committee meeting
January 31, 1990:
Notification of acceptance or refusal of papers
March 31, 1990:
Final version of the accepted contributions should be
received by Conference Secretariat
April 1990:
Distribution of Preliminary Programme for EUROGRAPHICS '90
June 15, 1990:
Deadline for receiving Video, Film and Slide Competition entries
September 3-7, 1990:
EUROGRAPHICS '90
in Montreux
Official Conference Language is English
ORGANISING COMMITTEE
Conference Chairmen: Michel Roch (CH)
Michel Grave (F)
International programme committee (Chairs): David Duce (UK),
Carlo Vandoni (CH)
International programme committee (Members):
C. Binot (F)
W. Boehm (FRG)
P. Bono (USA)
K. Brodlie (UK)
P. Brunet (ESP)
S. Coquillart (F)
L. Dreschler-Fisher (FRG)
A. Ducrot (F)
P. Egloff (FRG)
J. Encarnacao (FRG)
B. Falcidieno (I)
A. Gagalowicz (F)
R. Gnatz (FRG)
M. Gomes (P)
P. ten Hagen (NL)
W. Hansmann (FRG)
R. Hersch (CH)
F. Hopgood (UK)
R. Hubbold (UK)
E. Jansen (NL)
M. Jern (DK)
K. Kansy (FRG)
M. Kocher (CH)
C. Pellegrini (CH)
F. Post (NL)
J. Prior (UK)
W. Purgathofer (AU)
W. Strasser (FRG)
P. Stucki (CH)
Tutorial chairmen: Ivan Herman (NL)
Gerald Garcia (CH)
State of the art reports chairmen: Bertrand Ibrahim (CH)
Thierry Pun (CH)
Exhibition chairman: Jean-Francois L'Haire (CH)
Video, film, slide competitions: Jean-Marie Moser (CH)
Daniel Bernard (CH)
Congress Organization: Georges Peneveyre
Paleo Arts et Spectacles
Case postale 177
CH - 1260 Nyon
Switzerland
Tel.: +41-22-62-13-33
Telex: 419 834
Telefax: +41-22-62-13-34
REPLY FORM
I intend to submit a full paper with the following title:
I enclose a full paper (to be submitted before November 15, 1989)
I intend to submit a video film slides
(to be submitted before June 15, 1990)
I would like to receive an information package for exhibitors
I would be interested in giving a tutorial or state of the art report
(include detailed abstract; submit before June 30, 1989)
I intend to participate at the congress
1 Tutorial
2 Tutorials
Date: Signature:
For Further Information Please Contact:
EUROGRAPHICS '90
CONFERENCE SECRETARIAT
PALEO ARTS ET SPECTACLES
Case postale 177
CH - 1260 Nyon
Switzerland
Tel.: +41-22-62-13-33
Telex: 419 834
Telefax: +41-22-62-13-34
MAILING ADDRESSES:
Main address:
EUROGRAPHICS '90
CONFERENCE SECRETARIAT
PALEO ARTS ET SPECTACLES
Case postale 177
CH - 1260 Nyon
Switzerland
Tel.: +41-22-62-13-33
Telex: 419 834
Telefax: +41-22-62-13-34
In case of submission of a state if the art report proposal (AND ONLY IN
THIS CASE) you may also address:
Thierry Pun
EG'90 State of the Art Report Co-chairman
Computing Center, University of Geneva
12, rue du Lac
CH - 1207 Geneve
Switzerland
Tel.: +41-22-787-65-82
Fax.: +41-22-735-39-05
Email: pun@cui.unige.ch, pun@cgeuge51.bitnet
Telex: CH 423 801 UNI
In case of submission of a tutorial proposal (AND ONLY IN THIS CASE)
you may also address:
Ivan Herman
EG'90 Tutorial Co-chairman
Centre for Mathematics and Computer Sciences (CWI)
Dept. of Interactive Systems
Kruislaan 413
NL - 1098 SJ Amsterdam
The Netherlands
Tel. (31)20-592-41-64
Telex: 12571 MACTR NL
Telefax: +31-20-592-4199
Email: ivan@cwi.nl (UUCP), ivan@tuintje.cwi.nl (from BITNET)
All other questions regarding the conference organisation, as well as
submission of papers, have to be addressed to the Conference secretariat
address given above.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/30/89)
Vision-List Digest Thu Jun 29 13:30:10 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
NSF announcement for PRC researchers
Testing 3-D Vision Nets: Call for help
Transputer based frame grabbers
Travel fellowships for graduates students in vision research
Post-doctoral position in human and machine vision
----------------------------------------------------------------------
From: Ken Laws <klaws@note.nsf.gov>
Subject: NSF announcement for PRC researchers
Recently, in response to events in the People's Republic of
China (PRC), President Bush offered a one-year delayed departure
to all PRC students, scholars and other visitors now in the
United States.
Many visitors from the PRC currently receive support through NSF
awards, particularly as graduate students and postdoctoral
researchers. Effective immediately, NSF will entertain requests
for supplements if the duration of the stay of a PRC student or
other researcher supported on an existing award is altered as the
result of the President's initiative.
For the remainder of FY 1989, reserve funds will be made
available to cover these supplements. Program reference code
9284, "PRC Scientist Supplements," should be cited.
Information regarding the opportunity for these supplements will
be provided to the university community by the Division of Grants
and Contracts [(202) 357-9496].
-- Ken Laws
(202) 357-9586
------------------------------
Date: Thu, 22 Jun 89 19:31:16 gmt
From: Ziqung Li <zql%aipna.edinburgh.ac.uk@NSFnet-Relay.AC.UK>
Subject: Testing 3-D Vision Nets: Call for help
The VisionNets is for 3-D object recognition and location
from range image. There is no limit for the types of surface
in an image, i.e. it is expected to deal with free-form objects
(but not those like tree leaves). It consists of 3 levels of
neural nets based on the Hopfield models:
1. Low level net: from a range image to surface
curvature images (work finished, tested using
real range data, well)
2. Intermediate level net: from the suface curvature
images to invariant surface descriptions in
attributed grapghs (work finished, tested using
real range data, well)
3. High level net: from the invariant surface
descriptions to object classification and
location (programs go through, tested in the
recognition phase, work; but not the location
phase owing to lack of a 3-D object model)
I am looking for geometric models to test the VisionNets as well
as the 3rd level net. Any information about available existing 3-D object
models, such as CAD models of free-form objects or any other explicit
models, would be greatly appreciated. I am also interested in a
working environmant in which this work can be carried on.
Thanks in advance.
Ziqing Li
Graduate Student
A.I. Department
Edinburgh University
U.K.
zql@aipna.ed.ac.uk
zql%uk.ac.edinburgh.aipna@ucl.cs.nss
------------------------------
Date: 23 Jun 89 07:55:06 GMT
From: munnari!latcs1.oz.au!suter@uunet.UU.NET (David Suter)
Subject: transputer based frame grabbers
Organization: Comp Sci, La Trobe Uni, Australia
I am interested in details of frame grabber cards that are transputer based.
Any info. - particularly regarding throughput data to transputers
would be appreciated.
d.s.
David Suter ISD: +61 3 479-2393
Department of Computer Science, STD: (03) 479-2393
La Trobe University, ACSnet: suter@latcs1.oz
Bundoora, CSnet: suter@latcs1.oz
Victoria, 3083, ARPA: suter%latcs1.oz@uunet.uu.net
Australia UUCP: ...!uunet!munnari!latcs1.oz!suter
TELEX: AA33143
FAX: 03 4785814
------------------------------
Date: Mon, 26 Jun 89 17:06:48 EDT
From: Color and Vision Network <CVNET%YORKVM1.BITNET@psuvax1.psu.edu>
From: suzanne@skivs.ski.org
Subject: Travel fellowships for graduates students in vision research
Westheimer Symposium Travel Fellowships
August 10 - 12, l989
Thanks to additional support from an NSF grant, we are able to
offer five travel fellowships to graduate students in vision research.
To apply for support send a CV with a letter describing your present
research, and a supporting letter from your graduate advisor.
Fellowships will cover airfare (up to $500.00) and accommodations at
the Clark Kerr Campus. Both those students who are presently
registered for the symposium and those who will be registering are
eligible for these travel fellowships. Unregistered students who are
applying for the fellowships should submit a registration form (but no
money) with their application. Registered students selected for the
fellowships will receive a refund.
You can receive additional registration forms by calling (415)
561-1637 or (415) 561-1620.
We have the pleasure to announce that three additional scientists
have agreed to speak at the symposium: Dr. Russell DeValois, Dr.
Barrie Frost, and Dr. Ralph Freeman.
Anyone who will be submitting a paper to the Westheimer
Festschrift edition of Vision Research is reminded that the deadline
for submission is August 10, l989. Papers may be sent to either Ken
Nakayama or to Suzanne McKee at Smith-Kettlewell Eye Research
Institute, 2232 Webster St., San Francisco, CA, 94115, USA.
------------------------------
Date: Wed, 28 Jun 89 08:52:09 EDT
From: Color and Vision Network <CVNET%YORKVM1.BITNET@psuvax1.psu.edu>
Subject: Post-doctoral position in human and machine vision
POST-DOCTORAL POSITION
Applications are invited for a 2.5 year post-doctoral
position to work on a European Community funded ESPRIT
project on human and machine vision. The project is
interdisciplinary (psychophysics, computation and
electrophysiology) and involves collaboration between some
fifteen major laboratories in Europe. The successful
applicant for this post will take part in experimental and
theoretical studies of binocular disparity, texture and optic
flow as sources of information about 3-D structure and
layout. Salary will be in the range 10,500 - 16,700 U.K.
pounds.
Please contact Dr B.J.Rogers, Department of Experimental
Psychology, University of Oxford, South Parks Road, Oxford.
Phone: (44) 865 271368 or email BJR@vax.oxford.ac.uk
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/08/89)
Vision-List Digest Fri Jul 07 14:15:02 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Vision-based solutions for the game of GO
Summary of Image Processing Languages
Re: Vision/Image Processing Languages
E-mail addresses for range data
----------------------------------------------------------------------
Date: Thu, 29 Jun 89 17:43:25 -0500
From: uhr@cs.wisc.edu (Leonard Uhr)
Subject: Re: Vision-based solutions for the game of GO
Status: RO
Al Zobrist used a vision-correlational approach to [the game of] GO in
his Ph.D. thesis here (see diss abstracts). He published this in one
of the Joint Computer Conferences (Eastern or Spring, around 1968-72).
------------------------------
Date: 29 Jun 89 19:14:47 GMT
From: mdavcr!rdr@uunet.UU.NET (Randolph Roesler)
Subject: Summary of Image Processing Languages
Keywords: image vision language
Organization: MacDonald Dettwiler, Richmond, B.C., Canada
A couple of weeks ago I asked the net for pointers to image processing
lanaguages (not libraries). I was looking for a computer programming
language that would allow me to inter-image operations. That is,
operations such as feature identifcation.
It seems that such things don't really exist. All commercial packages
that claimed "language" were really function libraries (choose your
favorite language) with a little bit of control structure thrown in (a
bonus ?). These libraries perform image to image transformations.
They give you like access to the internals an image.
Some systems were all control structure (KBVision as an example).
These systems provided good end user environments, but not good for
programmers or analyst tring to develop new image processing systems.
(KBVision is great!, get it if you need an image processing system for
"image" engineers, but its not really for programmers.)
Further, most products were tied to specialized hardware. I work in
the research department and have to live with stock SUN 3/60s. So even
as libraries, most of these products are useless to us.
I did receive three informed responces to my query. One person
suggested a set of unix filters (that he wrote) as a useful image
processing language. Another suggested IDL (image description
langauge ?). The third forwarded seven good references on the
subject. I am researching them now. Maybe, I'll write that image
processing language myself.
=====included================
I am not familiar with any image languages, per se, although in the
past I've seen some references to them in the literature. I have
written a general image processing software package (your image->image
transformations, mostly) which consists of a large number of UNIX
`filters' which can be connected up in relatively arbitrary ways using
the UNIX `pipe' facility. If that sounds useful, let me know, and
I'll mail you some blurbs.
Mike Landy
SharpImage Software
P.O. Box 373, Prince St. Sta.
New York, NY 10012-0007
(212) 998-7857
landy@nyu.nyu.edu
=====included================
have you heard of idl on a sun/vax - pretty good, but very few
high-level function in either space. call
david stern research systems inc. (IDL) 303-399-1326
john j. bloomer <jbloomer@crd.ge.com, bloomer@mozart.crd.ge.com>
=====included================
Take a look to Picasso and Pal:
1. Z. Kulpa. Picasso,, picasso-show and pal. a development of a high-level
software system for image processing. pages 13-24 in (3).
2. T. Radhakrishnan, R. Barrera, et al. Design of a high level language (L)
for image processing. pages 25-40 in (3).
3. Languages and Architectures for Image Processing. Academic Press, 1981.
Editors: M. J. B. Duff, S. Levialdi.
4. MAC. Chapter four of (3).
5. A Language for parallel processing of arrays. Chapter five of (3).
6. PIXAL. Chapter sic of (3).
7. A high-level language for constructing image processing commands. Chapter 7
of (3).
Also: Chapters Nine, ten, eleven, twelve, of (3).
Adolfo Guzman. International Software Systems, Inc.
9420 Research Blvd., Suite 200. Austin, TX. 78759
Tel. (512) 338 1895 Telex: 499 1223 ISSIC Fax: (512) 338 9713
issi!guzman@cs.utexas.edu or guzman@issi.uucp or cs.utexas.edu!issi!guzman
==========================
PS - my orginal posting never made it to Canada (or maybe, just not BC).
So the responce may have been smaller than need be.
==========================
Randy Roesler ...!uunet!van-bc!mdavcr!rdr
MacDonald Dettwiler Up here in Canada.
Image Processing Specialists. 604-278-3411
------------------------------
Date: Fri, 30 Jun 89 12:16:29 GMT
From: H Wang <hw%dcs.leeds.ac.uk@NSFnet-Relay.AC.UK>
[Reply to Randy's original request for vision language information. pk...]
Subject: Re: Vision/Image Processing Languages We developed an
image-to-image language at Leeds on the transputer array, called
APPLY, which was originally from CMU fro the Warp machine. APPLY
performs localised window operations, eg. edge detection, 2D
convolution. The APPLY compiler generates OCCAM (for transputer
arrays), C (for UNIX machine) and W2 (for Warp) at the moment,
although it is aimed at machine independent. This language has two
major advantages: (1) ease the programming efforts, (2) efficiency.
For instance, it does better on the Canny edge detector than the
hand-crafted code reported in the literature.
If you are interesting, pls contact me. I could not reach you by e-mail.
My address is:
Mr. H Wang,
School of Comuter Studies, The university of Leeds, Leeds, LS2 9JT,
phone: (0532) 335477 (in UK)
+44532,335477 (international)
e-mail: (ArpaNet)hw%uk.ac.leeds.dcs@uk.ac.ucl.cs.nss
------------------------------
Date: 3 Jul 89 11:54:00 WET
From: John Illingworth <illing%ee.surrey.ac.uk@NSFnet-Relay.AC.UK>
Subject: e-mail addresses for range data
hi, in recent vision lists there has been correspondence about range
image data bases. I wish to obtain further information about these
databases by email. However no email addresses have been given in the
vision list. Anyone know the email address for
M Rioux or L Cournoyer
National Research Centre of Canada
Ottawa, Ontario. Canada
or
Tom Henderson
University of Utah
many thanks John Illingworth
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/15/89)
Vision-List Digest Fri Jul 14 14:08:05 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Call for Papers: INNS/IEEE Conference on Neural Networks, Jan. 1990
Intensive summer school on statistical pattern recognition
----------------------------------------------------------------------
Date: 10 Jul 89 04:39:00 GMT
From: lehr@isl.stanford.edu (Michael Lehr)
Subject: Call for Papers: INNS/IEEE Conference on Neural Networks, Jan. 1990
Summary: Papers requested for joint neural net conference in Washington DC
Keywords: conference, neural networks
Organization: Stanford University EE Dept.
CALL FOR PAPERS
International Joint Conference on Neural Networks
IJCNN-90-WASH DC
January 15-19, 1990,
Washington, DC
The Winter 1990 session of the International Joint Conference on
Neural Networks (IJCNN-90-WASH DC) will be held on January 15-19, 1990
at the Omni Shoreham Hotel in Washington, DC, USA. The International
Neural Network Society (INNS) and the Institute of Electrical and
Electronics Engineers (IEEE) invite all those interested in the field
of neural networks to submit papers for possible publication at this
meeting. Brief papers of no more than 4 pages may be submitted for
consideration for oral or poster presentation in any of the following
sessions:
APPLICATIONS TRACK:
* Expert System Applications
* Robotics and Machine Vision
* Signal Processing Applications (including speech)
* Neural Network Implementations: VLSI and Optical
* Applications Systems (including Neurocomputers & Network
Definition Languages)
NEUROBIOLOGY TRACK:
* Cognitive and Neural Sciences
* Biological Neurons and Networks
* Sensorimotor Transformations
* Speech, Audition, Vestibular Functions
* Systems Neuroscience
* Neurobiology of Vision
THEORY TRACK:
* Analysis of Network Dynamics
* Brain Theory
* Computational Vision
* Learning: Backpropagation
* Learning: Non-backpropagation
* Pattern Recognition
**Papers must be postmarked by August 1, 1989 and received by August
10, 1989 to be considered for presentation. Submissions received
after August 10, 1989 will be returned unopened.**
International authors should be particularly careful to submit their
work via Air Mail or Express Mail to ensure timely arrival. Papers
will be reviewed by senior researchers in the field, and author
notifications of the review decisions will be mailed approximately
October 15, 1989. A limited number of papers will be accepted for
oral and poster presentation. All accepted papers will be published
in full in the meeting proceedings, which is expected to be available
at the conference. Authors must submit five (5) copies of the paper,
including at least one in camera-ready format (specified below), as
well as four review copies. Do not fold your paper for mailing.
Submit papers to:
IJCNN-90-WASH DC
Adaptics
16776 Bernardo Center Drive, Suite 110 B
San Diego, CA 92128 UNITED STATES
(619) 451-3752
SUBMISSION FORMAT:
Papers should be written in English and submitted on 8-1/2 x 11 inch
or International A4 size paper. The print area on the page should be
6-1/2 x 9 inches (16.5 x 23 cm on A4 paper). All text and figures
must fit into no more than 4 pages. The title should be centered at
the top of the first page, and it should be followed by the names of
the authors and their affiliations and mailing addresses (also
centered on the page). Skip one line, and then begin the text of the
paper. We request that the paper be printed by typewriter or
letter-quality printer with clear black ribbon, toner, or ink on plain
bond paper. We cannot guarantee the reproduction quality of color
photographs, so we recommend black and white only. The type font
should be Times Roman or similar type font, in 12 point type
(typewriter pica). You may use as small a type as 10 point type
(typewriter elite) if necessary. The paper should be single-spaced,
one column, and on one side of the paper only. Fax submissions are
not acceptable.
**Be sure to specify which track and session you are submitting your
paper to and whether you prefer an Oral or Poster presentation. Also
include the name, complete mailing address and phone number (or fax
number) of the author we should communicate with regarding your
paper.**
If you would like to receive an acknowledgment that your paper has
been received, include a self-addressed, stamped post-card or envelope
for reply, and write the title and authors of the paper on the back.
We will mark it with the received date and mail it back to you within
48 hours of receipt of the paper. Submission of the paper to the
meeting implies copyright approval to publish it as part of the
conference proceedings. Authors are responsible for obtaining any
clearances or permissions necessary prior to submission of the paper.
------------------------------
Date: 14 Jul 89 14:05:00 WET
From: Josef Kittler <kittler%ee.surrey.ac.uk@NSFnet-Relay.AC.UK>
Subject: Intensive summer school on statistical pattern recognition
INTENSIVE SUMMER SCHOOL
ON
STATISTICAL PATTERN RECOGNITION
11-15 September 1989
University of Surrey
PROGRAMME
The course is divided into two parts:
Course A The Fundamentals of Statistical
Pattern Recognition
Course B Contextual Statistical Pattern
Recognition
Course A will cover the basic methodology of
statistical pattern recognition. Course B will feature a number of
advanced topics concerned
with the use of contextual information in pattern recognition, with a
particular emphasis on Markov models in speech and images.
Several example classes will be aimed at familiarizing the participants
with the material presented. The course will include a seminar on
application of pattern recognition methods to specific problems in which a
step by step description of the design of practical pattern recognition
systems will be outlined. Ample time will be devoted to discussion of
algorithmic and practical aspects of pattern recognition techniques.
COURSE A: THE FUNDAMENTALS OF STATISTICAL PATTERN RECOGNITION
11-13 September 1989
ELEMENTS OF STATISTICAL DECISION THEORY
Model of pattern recognition system. Decision theoretic approach to pattern
classification. Bayes decision rule for minimum loss and minimum error rate.
Sequential and sequential compound decision theory. Optimum error
acceptance tradeoff. Learning algorithms.
NONPARAMETRIC PATTERN CLASSIFICATION
The Nearest Neighbour (NN) technique: 1-NN, k-NN, (k,k')-NN pattern
classifiers. Error acceptance tradeoff for nearest neighbour classifiers.
Error bounds. Editing techniques.
DISCRIMINANT FUNCTIONS
Discriminant functions and learning algorithms. Deterministic learning. The
least square criterion and learning scheme, relationship with the 1-NN
classifier. Stochastic approximation. Optimization of the functional form of
discriminant functions.
ESTIMATION THEORY
Probability density function estimation: Parzen estimator, k-NN estimator,
orthogonal function estimator. Classification error rate estimation:
resubstitution method, leave-one-out method, error estimation based on
unclassified test samples.
FEATURE SELECTION
Concepts and criteria of feature selection, interclass distance measures,
nonlinear distance metric criterion, probabilistic distance and dependence
measures and their properties, probabilistic distance measures for
parametric distributions, entropy measures (logarithmic entropy, square
entropy, Bayesian distance), algorithms for selecting optimal and
suboptimal sets of features, recursive calculation of parametric
separability measures. Nonparametric estimation of feature selection
criterion functions.
FEATURE EXTRACTION
Probabilistic distance measures in feature extraction, Chernoff
parametric measure, divergence, Patrick and Fisher method.
Properties of
the Karhunen-Lo\`eve expansion, feature extraction techniques based on the
Karhunen-Lo\`eve expansion. Nonorthogonal mapping methods, nonlinear
mapping methods, discriminant analysis.
CLUSTER ANALYSIS
Concepts of a cluster, dissemblance and resemblance measures, globally
sensitive methods, global representation of clusters by pivot points and
kernels, locally sensitive methods (methods for seeking valleys in
probability density functions), hierarchical methods, minimum spanning tree
methods, clustering algorithms.
***************************************************************************
COURSE B: CONTEXTUAL STATISTICAL PATTERN RECOGNITION
14-15 September 1989
INTRODUCTION
The role of context in pattern recognition. Heuristic approaches to contextual
pattern recognition. Labelling of objects arranged in networks (chains,
regular and irregular lattices). Neighbourhood systems. Elements of
compound decision theory.
MODELS
Markov chains. Causal and noncausal Markov
random fields (MRF). Gibbs distributions. Hidden Markov chain and
random field models for speech and images.
Simulation of causal Markov processes. Simulation of noncausal MRF:
The Metropolis algorithm.
DISCRETE RELAXATION
Compatibility coefficients. Concept of consistent labelling. Waltz discrete
relaxation algorithm. Maximum aposteriori probability (MAP) of joint
labelling. Viterbi algorithm for Markov chains, dynamic programming.
Iterative algorithm for local MAP optimization in MRF. Geman and Geman
Bayesian estimation by stochastic relaxation, simulated annealing.
RECURSIVE COMPOUND DECISION RULES
MAP of labelling individual objects. Filtering and fixed-lag smoothing in
hidden Markov chains. Baum's algorithm. Labelling in hidden Markov meshes
and in Pickard random fields. Unsupervised learning of underlying model
parameters.
PROBABILISTIC RELAXATION
Problem specification. Combining evidence. Support functions for specific
neighbourhood systems. Relationship with conventional compatibility and
support functions (arithmetic average and product rule). Global criterion
of ambiguity and consistency. Optimization approaches to label probability
updating (Rosenfeld, Hummel and Zucker algorithm, projected gradient
method).
APPLICATIONS
Speech recognition. Image segmentation. Scene labelling. Texture
generation.
************************************************************************
GENERAL INFORMATION
COURSE VENUE
University of Surrey, Guildford, United Kingdom
LECTURERS
Dr Pierre DEVIJVER & Philips Research Laboratory, Avenue
& Em Van Becelaere 2, B-1170 Brussels, Belgium
Dr Josef KITTLER & Department of Electronic and Electri-
& cal Engineering, University of Surrey,
& Guildford GU2 5XH, England
PROGRAMME SCHEDULE
COURSE A will commence on Monday, September 11 at 10.00 a.m. (registration
9.00 - 10.00 a.m.) and finish on Wednesday, September 13 at 4 p.m.
COURSE B will commence on Thursday, September 14 at 10.00 a.m. (registration
9.00 - 10.00 a.m.) and finish on Friday, September 15 at 4 p.m.
ACCOMMODATION
Accommodation for the participants will be available on the campus of the
University for the nights of 10-14 September at the cost of 27.80
per night covering dinner, bed and breakfast.
REGISTRATION AND FURTHER INFORMATION
Address registration forms and any enquiries to Mrs Marion Harris,
Department of Electronic and Electrical Engineering, University of Surrey,
Guildford GU2 5XH, England,
telephone 0483 571281 ext 2271. Rights reserved to cancel the course or
change the programme if minimum numbers are not obtained or to limit
participation according to capacity. All reservations handled on first-come
first-served basis.
WHO SHOULD ATTEND
The course is intended for graduate students, engineers, mathematicians,
computer scientists, applied scientists, medical physicists and social
scientists engaged in work on pattern recognition problems of practical
significance. In addition programmers and engineers concerned with the
effective design of pattern recognition systems would also benefit.
Applicants for COURSE A should have some familiarity with basic engineering
mathematics and some previous exposure to probability and statistics.
Applicants for COURSE B only should have working knowledge of basic
statistical pattern recognition techniques.
The material covered is directly relevant to applications in
character recognition, speech recognition, automatic medical diagnosis,
seismic data classification, target detection and identification,
remote sensing, computer vision for robotics, and many other
application areas.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/22/89)
Vision-List Digest Fri Jul 21 09:07:53 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Image Processing. Mathematical morphology. ---------------------------------------------------------------------- Date: 18 Jul 89 23:40:02 GMT From: maurinco@iris.ucdavis.edu (Eric Maurincomme) Subject: Image Processing. Mathematical morphology. Organization: U.C. Davis - Department of Electrical Engineering and Computer Science Has anyone heard of any public domain software tools for mathematical morphology ? I am particularly interested in grayscale morphology operations. Also, what would be a good newsgroup to send this message to ? Thanks in advance, | Eric Maurincomme | Dept. of Electrical Engineering and Computer Science | University of California | Davis, CA 95616. | e-mail address : maurinco@iris.ucdavis.edu | Phone : (916) 752-9706 ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/01/89)
Vision-List Digest Mon Jul 31 10:25:00 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Resolution issues
Satellite Image Data
IJCAI 89 Update
color processing
defocussing & Fourier domain.
Need time sequences sampled in various ways
----------------------------------------------------------------------
Date: 21 Jul 89 22:13:53 GMT
From: muttiah@cs.purdue.edu (Ranjan Samuel Muttiah)
Subject: Resolution
Organization: Department of Computer Science, Purdue University
I am looking for reference material on that may have been written
on issues pertaining to the relationship of machine vision resolution,
accuracy, and execution time.
Please email.
Thanks
------------------------------
Date: Wed, 26 Jul 89 14:30:09-0000
From: Farzin Deravi <eederavi%pyramid.swansea.ac.uk@NSFnet-Relay.AC.UK>
Subject: Satellite Image Data
I need some satellite image data in a form portable to an IBM PC environment
for a student who is doing a project on region classification by texture. Could
you suggest where I can easily obtain such data. By "easily" I mean not
having to write letters/applications and preferably through email!
Many thanks for your help and advice.
- - - - - - - - - - - - - - - - - - - -
Farzin Deravi, | UUCP : ...!ukc!pyr.swan.ac.uk!eederavi|
Image Processing Laboratory, | JANET : eederavi@uk.ac.swan.pyr |
Electrical Engineering Dept., | voice : +44 792 295583 |
University of Wales, | Fax : +44 792 295532 |
Swansea, SA2 8PP, U.K. | Telex : 48149 |
- - - - - - - - - - - - - - - - - - - -
------------------------------
Date: Wed, 26 Jul 89 15:39:06 EDT
From: dewitt@caen.engin.umich.edu (Kathryn Dewitt)
Subject: IJCAI 89 Update
CONFERENCE HIGHLIGHTS
Invited Speakers:
Koichi Furukawa, ICOT will speak Monday, August 21, at 11:10am. The title
of his talk is "Fifth Generation Computer Project: Toward a Coherent
Framework for Knowledge Information Processing and Parallel Processing".
Gerald Edelman, Rockefeller University, will speak Monday August 21,
at 2:00pm. The title of his talk is"Neural Darwinism and Selective
Recognition Automata".
E.D. Dickmanns, Universitat de Bundeswehr Munchen, will speak Wednesday,
August 23, at 11:10am. The title of his talk is "Real-Time Machine Vision
Exploiting Integrak Spatio-Temporal World Models".
Enn Tyugu, Institute of Cybernetics, USSR, will speak Thursday, August 24,
at 9:00am. The title of his talk is "Knowledge-Based Programming
Environments"
Fernado Pereira, AT&T Bell Laboratories, will speak Thursday, August 24,
at 11:10am. The title of his talk is "Interpreting Natural Language".
Geoffrey Hinton, University of Toronto, will speak Friday, August 25,
at 11:10 am. The title of his talk is "Connectionist Learning
Procedures".
Invited Panels:
THE CHALLENGE OF NEURAL DARWINISM - Monday, August 21, 4:15pm.
members: Stephen W. Smoliar(chair), Linda Smith, David Zisper,
John Hollandand George Reeke
ROBOT NAVIGATION - Tuesday, August 22, 9:00am
members: David Miller(chair), Rod Brooks, Raja Chatila,
Scott Harmon, Stan Rosenschein, Chuck Thorpe, and
Chuck Weisbin.
HIGH-IMPACT FUTURE RESEARCH DIRECTIONS FOR ARTIFICIAL INTELLIGENCE
Tuesday, August 22, 11:10am.
members: Perry Thorndyke(Chair), Raj Reddy, and Toshio Yakoi
ARTIFICIAL INTELLIGENCE and SPACE EXPLORATION - Tuesday, August 22, 2:00pm
members: Peter Friedland(chair), David Atkinson, John Muratore,
and Greg Swietek.
(HOW) IS AI IMPACTING MANUFACTURING? - Friday, August 25, 9:00am.
members: Mark Fox (chair), E.J. van de Kraatz, Dennis O'Connor,
and Karl Kempf.
------------------------------
Date: Wed, 26 Jul 89 13:35:04 MET DST
From: mcvax!irst.it!bellutta@uunet.UU.NET (Paolo Bellutta)
Subject: color processing
I have a couple of problem about color procesing.
First: What is the best way to compress 24 bit color images in 8 bit color
images but using always the same colormap? I tryed to assign 3 bits
for red and green and 2 bits for blue but the results are not very
good (the image in general has a very high contrast).
Second: I want to compute from 24 bit rgb images one image that contains
luminance information (Y = 0.299 * R + 0.587 * G + 0.114 * B) and
another image with chrominance information (C = R / (R + G)).
In parentheses I wrote what I'm using.
I found that in general the Y image has high contrast and the C
image has poor color resolution. I mean that if two sides of an object
have the same color but one is too dark, on the C image it is seen
as black.
Are there better algorithms to use?
___ ___
/ ) / )
/--- /---\
/ __ _ / _ / ) _ / / /_ /_ __
/ (_/__(_)__/__(_) /_____/ (-'__/__/__/_/__/___/___(_/_
I.R.S.T.
loc. Pante' di Povo
38050 POVO (TN)
ITALY
vox: +39 461 810105
fax: +39 461 810851
e-mail: bellutta@irst.uucp
bellutta@irst.it
------------------------------
Date: Fri, 28 Jul 89 10:27:58 +0100
From: prlb2!ronse@uunet.UU.NET (Christian Ronse)
Subject: defocussing & Fourier domain.
Suppose that one makes a picture of an image with out-of-focus lenses.
The transformation from the original image to the blurred picture is
linear and translation-invariant (I think!). What is known about the
Fourier transform of this blurring transformation, in particular on
its phase spectrum?
Christian Ronse
Internet: maldoror@prlb.philips.be
UUCP: maldoror@prlb2.uucp
ARPA: maldoror%prlb.philips.be@uunet.uu.net
maldoror%prlb2.uucp@uunet.uu.net
BITNET: maldoror%prlb.philips.be@cernvax
maldoror%prlb2.uucp@cernvax
[ This is an interesting question. Krotkov, Pentland, and Subbarao
have looked at some of these issues as they relate to computer vision
(Krotkov recently published a paper in IJCV, and Pentland in PAMI).
I assume that you mean translation-invariant in the plane (since
translation in depth is what causes the blurring). Though lens effects
undermine this (e.g., diffraction, lens defects), the plane translation
invariance seems reasonable to me.
The blur function due to defocussing is in the optics literature.
It has been approximated by some as a gaussian (which, not coincidentally,
is well-suited for analytic analysis in the Fourier domain). The spread
function differs with the wavelength of light, and this introduces
some complexities. Subbarao has addressed this issue, though I don't
know of a specific reference (he is at SUNY Buffalo).
phil... ]
------------------------------
Date: Mon, 31 Jul 89 09:46:35 PDT
From: althea!pxjim@uunet.uu.net (James Conallen)
Subject: Need time sequences sampled in various ways
Hi there,
I just recently posted a request for image sequences on comp.graphics, and
a reply from Prof. Dave Chelberg [dmc@piccolo.ecn.purdue.edu) suggested I
post on the vision list. I am looking for image sequences time sequentialy
sampled with different sampling patterns. The ones I am interested in are:
lexicographic
2:1 line interlaced
2:1 dot interlaced
bit reversed line interlaced
bit reversed dot interlaced
I prefer 256x256x256 BW images, but I'm humble.
Can you offer me any help?
-jim conallen
BITNET: pxjim@widener
UUCP: pxjim@althea
AT&T: (215)499-1050
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/04/89)
Vision-List Digest Thu Aug 03 10:59:09 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re: defocussing & Fourier domain
Defocusing
Subbarao's address
----------------------------------------------------------------------
Date: Tue, 1 Aug 89 09:44:38 BST
From: alien%VULCAN.ESE.ESSEX.AC.UK@CUNYVM.CUNY.EDU (Adrian F. Clark)
Subject: Re: defocussing & Fourier domain
Christian Ronse asks about the effect of defocus blur on images. This
topic was looked at in detail in the paper
"Blind Deconvolution with Spatially Invariant Image Blurs with Phase"
by T. Michael Cannon, IEEE Trans ASSP vol ASSP-24 no. 1 pp58-63 (1976).
In a nutshell, what you do is form the cepstrum (effectively the
logarithm of the power spectrum) and look for the zero crossings: the
defocus blur adds a Bessel function (actually J1(r)/r for a circular
aperture imaging system) pattern. The same paper also treats linear
motion blur.
There are related papers of the same vintage by Cannon and colleagues
(including ones in Proc IEEE and Applied Optics, if I remember
correctly) which are also worth checking out.
Adrian F. Clark
JANET: alien@uk.ac.essex.ese
ARPA: alien%uk.ac.essex.ese@nsfnet-relay.ac.uk
BITNET: alien%uk.ac.essex.ese@ac.uk
Smail: Dept. of Electronic Systems Engineering, University of Essex,
Wivenhoe Park, Colchester, Essex C04 3SQ, U. K.
Phone: (+44) 206-872432 (direct)
------------------------------
Date: Tue, 1 Aug 89 11:22:32 PDT
From: GENNERY@jplrob.JPL.NASA.GOV
Subject: Defocusing
This is in reply to the question from Ronse. The point spread function
caused by an out of focus lens is an image of the aperture. For a clear,
circular aperture, this is a uniform circular disk, neglecting lens
distortion, and the Fourier transform of this is a J1(x)/x function,
where J1 is the Bessel function of the first kind. (See, for example,
D. B. Gennery, "Determination of Optical Transfer Function by Inspection
of Frequency-Domain Plot," Journal of the Optical Society of America 63,
pp. 1571-1577 (Dec. 1973).) The actual apertures of cameras usually are
more polygonal than circular (because of the adjustable iris). However,
a high-degree polygon can be approximated by a circle fairly well, so
the J1(x)/x function may be reasonably accurate in many cases. But the
Gaussian function is not a good approximation to this, as can be seen by
the fact that its phase is always 0 and its amplitude decays rapidly,
whereas J1(x)/x oscillates in sign (thus its phase jumps betw
0 and 180 degrees), with the amplitude decaying slowly. Of course, if
the blurring from focus is less than the blurring from other causes,
then what happens at the higher spatial frequencies doesn't matter much,
so almost any function will do. But with a large amount of defocus,
the precise nature of the function is important.
Don Gennery
------------------------------
Date: Tue, 1 Aug 89 15:20:54 EDT
From: sher@cs.Buffalo.EDU (David Sher)
Subject: Subbarao's address
I just thought that I'd correct a small error in the last posting:
last I heard Subbarao was at SUNY Stonybrook.
-David Sher
[ I apologize for this inadvertant error.
phil... ]
------------------------------
Date: Wed, 02 Aug 89 15:29:36 PDT
From: Shelly Glaser <GLASER%USCVM.BITNET@CUNYVM.CUNY.EDU>
Subject: Re: Vision-List delayed redistribution
Have you tried any textbook on modern optics? Try, for example, J. W.
Goodman's "Introduction to Fourier Optics" (McGraw, 1968).
If the geometrical-optics approximation would do, the FT of out-of-focus
point is the FT of a circle function; it becomes more complicated as you
add diffraction.
Shelly Glaser
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/12/89)
Vision-List Digest Fri Aug 11 18:06:48 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Two Research Posts - Computer Vision
least squares fitting.
Friend looking for a image processing job in a stable company
Grayscale Morphology software
----------------------------------------------------------------------
Date: Mon, 7 Aug 89 16:00:24 BST
From: Bob Fisher <rbf%edai.edinburgh.ac.uk@NSFnet-Relay.AC.UK>
Subject: Two Research Posts - Computer Vision
University of Edinburgh
Department of Artificial Intelligence
Two Research Posts - Computer Vision
Applications are invited for two researchers to work in the
Department of Artificial Intelligence on an European Institute of
Technology funded research project entitled ``Surface-Based Ob-
ject Recognition for Industrial Automation''. Principal investi-
gators on the project are Dr. Robert Fisher and Dr. John Hallam.
The project investigates the use of laser-stripe based range data
to identify and locate parts as they pass down a conveyor belt.
The vision research to be undertaken includes topics in: surface
patch extraction from range data, surface patch clustering,
geometric object modeling, model matching, geometric reasoning.
The project builds on substantial existing research.
The first researcher will be expected to take a leading role in
the day-to-day project management of this and a related project
(5 research staff total) as well as undertake scientific
research. Applicants for this post should have a PhD (or compar-
able experience) in an appropriate area, such as computer vision,
artificial intelligence, computer science or mathematics.
The second researcher will be more involved in software implemen-
tation and testing, but will be expected to undertake some origi-
nal research. Applicants should have at least a BSc in an ap-
propriate area.
Both applicants should have experience with the C programming
language. Applicants with experience in computer vision, the
UNIX operating system, the C++ language, or the Prolog language
would be preferred.
Both posts are funded for a period of three years starting No-
vember 1, 1989. The salaries will be in the range 10458-16665
(AR1a) for the first post and 9816-12879 (AR1b/a) for the second
post, with placement according to age, experience and qualifica-
tions.
Applications should include a curriculum vitae (3 copies) and the
names and addresses of two referees, and should be sent to the
Personnel Department, University of Edinburgh, 63 South Bridge,
Edinburgh, EH1 1LS by September 6, 1989, from whom further par-
ticulars can be obtained. In your application letter, please
quote reference number 1651, and indicate for which of the two
posts you are applying.
------------------------------
Date: Tue, 8 Aug 89 10:46:06 CST
From: George Travan <munnari!sirius.ua.oz.au!gtravan@uunet.UU.NET>
Subject: least squares fitting.
i interested in obtaining some pointers to C code which will do a least
squares fit on 2D and 3D shapes consisting of a number of discrete points.
also, are there any good reference sources to 2d or 3D shape analysis.
im particularly interested in mirror imaging and shape difference quantification
thanx -GeO George Travan
University of Adelaide
AUSTRALIA ACSnet: gtravan@sirius.ua.oz
------------------------------
Date: 10 Aug 89 17:15:48 GMT
From: hplabs!tripathy@hpscdc.hp.com (Aurobindo Tripathy)
Subject: Friend looking for a image processing job in a stable company
Organization: Hewlett-Packard, Santa Clara Div.
For all you folks doing work in computer vision in the industry,
I have a question! ...Why is this group so quiet ? There are never any
[ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
Good question.
phil...]
issues discussed here. Does every body work for the military ? ...
Let me make a start. I have a freind looking for a job in the image processing
area with a solid background to image processing hardware design and excellent
understanding of image processing algorithms. He has about six years
experience in the industry. Can any one recommend a stable :-) imaging,
image processing company.
aurobindo
------------------------------
Date: Thu, 10 Aug 89 15:30:03 pdt
From: maurinco@iris.ucdavis.edu (Eric Maurincomme)
Subject: Grayscale Morphology software
About 3 weeks ago, I posted a query about any existing public domain
morphology software. Firstly, I would like to thank all the people who
replied to my query, by giving me advices or answers.
Secondly, it appears that there is no public domain software for morphology
around. I was principally interested in grayscale operations.
Most of the replies I got were about general purpose software packages,
in which a few morphological operations are implemented.
I will try to give a brief compilation of the answers I got :
At the University of Washington, Linda Shapiro and her colleagues use a
a software package called GIPSY, that has about 400 commands, including
morphology, and that runs under UNIX. This is a general purpose package
that runs slowly but covers a lot of ground. The morphology is just one
command that can do dilations, erosions, openings and closings with the
user defining his own structuring element by means of entering a mask.
Finally, it costs something like $5000.
A few people at the University of Maryland working with Rosenfeld refered
me to a few existing software packages. There is one written by Serra's
team. It's called MORPHOLOG, or its new version which is called VISILOG;
the latter one is on sale by a French company (NOESIS) for about $8000.
If you want more information on MORPHOLOG, you may want to contact La"y
at the School of Mines in Paris. The software works on an hexagonal grid,
and a description of it can be found in :
B. La"y, Descriptors of the programs of the Software Package Morpholog,
Ecole des Mines, Paris.
They also refered me to an Image Processing Software package called IPS,
that has been created by a French lab in Grenoble, and they have quite a
few both binary and grayscale morphological operations running on it.
It's been developed on Appolo workstations, and is on sale for about
40000 French Francs, which is about $6000.
Apparently the same software has been implemented to work on a PC, and
is commercialized by the society Thomson-Titn, and is called SAMBA.
If you want more information on IPS, you may want to contact Guy Bourrel
at bourrel@imag.imag.fr who is implied in the development of this software.
His address is
Guy Bourrel
Equipe de Reconnaissance des Formes et de Microscopie Quantitative
Universite Joseph Fourier
CERMO BP 53X
38041 Grenoble cedex
France tel 76-51-48-13
Another general purpose image processing software package which includes
some of the basic morphology stuff is called HIPS, and is commercialized
by Mike Landy at Sharpimage Software in New York.
Finally, a word of comment to tell the netters why we are looking for
grayscale morphology tools. We have implemented some binary morphology
in our Image Processing lab (now called CIPIC (Center for Image Processing
and Integrated Computing), which is a campus-wide research unit).
It runs on an image processing board IP8500, mounted on a VAX. It does
all kind of opening/closing dilation/erosion, and can be used for
skeletonization, etc....
The next step is to implement gray scale morphology. I am working with
Professor Ralph Algazi (algazi@iris.ucdavis.edu), and we wanted to know
what the state-of-the-art is in this area.....
Thanks for listening,
Eric.
| Eric Maurincomme
| Dept. of Electrical Engineering and Computer Science
| University of California
| Davis, CA 95616.
| e-mail address : maurinco@iris.ucdavis.edu
| Phone : (916) 752-9706
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/19/89)
Vision-List Digest Fri Aug 18 10:18:42 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
ICIP'89 (IEEE 1989 Int Conf on Image Processing) last announcement
GYPSY
MORPHOLOG and VISILOG update information
some ideas on image analysis methods & vision
Sensor Fusion
Postdoctoral Positions-- Yale University
----------------------------------------------------------------------
Date: Mon, 14 Aug 89 14:12:02 -0500
From: teh@cs.wisc.edu (Cho-huak Teh)
Subject: ICIP'89 (IEEE 1989 Int Conf on Image Processing) last announcement
[ I significantly shortened this announcement please contact
teh@cs.wisc.edu for a full application form and more information.
phil... ]
This is the final announcement through email of IEEE ICIP'89 to be held
in Singapore from 5 to 8 September next month. There will be presentations
of about 250 papers from 25 countries covering 26 dynamic and high-tech
topics of image processing. The Conference and its related activities
will be conducted in English.
(A) In-depth tutorials will be held from 5 to 6 Sept :
The technical sessions include :
- Biomedical Image Processing I & II
- Applications of Machine Vision
- Computer Graphics
- 3D Vision I & II
- Image Coding I, II & III
- Feature Extraction I & II
- Character Recognition
- Image Registration
- Image Segmentation
- Artificial Intelligence Techniques
- Systems and Architectures I & II
- Edge Detection
- Image Enhancement and Restoration
- Remote Sensing
- Object Recognition
- 2D Signal Processing
- Dynamic Vision I & II
- Pattern Recognition
- Video Communications
------------------------------
Date: Wed, 16 Aug 89 03:29:55 GMT
From: us214777@mmm.3m.com (John C. Schultz)
Subject: GYPSY
Organization: 3M - St. Paul, MN 55144-1000 US
In a recent article I noticed a reference to GYPSY. I and my lab had the
misfortune to purchase GYPSY several years ago (for quite a bit more
than $5000). My opinion is that it is not worth $.10.
Our version ran very slowly on a VAX 11/780 under VMS. All operations
involved reading and writing disk files so disk performance was
critically important. Even such simple tasks as negating an image
would
chew up another 512 x 512 byte disk chunk (for example). This filled up
disks very rapidly needless to say.
The FORTRAN (or RATFOR I forget which) made it difficult for me to
maintain although I did manage to add some modules. The difficulty was
the semi-infinite number of functions, arguments were passed through
before the generally small routine to do the actual number crunching.
Perhaps the most disappointing aspect was that while there were lots of
seemingly neat functions (mostly based on Haralick's facet models if you
like those), the documentation only told you what the functions did, not
why or what preprocessing was required to permit operations.
For example, I never got the region-adjacency graph to work because I
could never get the proper file(s) preprocessed correctly.
My feeling is that GYPSY is intended to be used only by Haralick's
former students and close associates. I do not fall in either category.
We use a general purpose mathematical processing package called IDL
with the VAX. Vision work uses memory mapped devices with another
image processing
package I won't recommend, on smaller systems.
You mileage may vary.
------------------------------
Date: Wed, 16 Aug 89 17:37:29 +0200
From: mohr@saturne.imag.fr (Roger Mohr)
Subject: MORPHOLOG and VISILOG update information
A previously postinf wrote:
"A few people at the University of Maryland working with Rosenfeld refered
me to a few existing software packages. There is one written by Serra's
team. It's called MORPHOLOG, or its new version which is called VISILOG;
the latter one is on sale by a French company (NOESIS) for about $8000.
If you want more information on MORPHOLOG, you may want to contact La"y
at the School of Mines in Paris. The software works on an hexagonal grid,
and a description of it can be found in :
B. La"y, Descriptors of the programs of the Software Package Morpholog,
Ecole des Mines, Paris."
This has to updated :
First af all, Bruno La"y is no more at Ecole des Mines but with his
own company: Noesis
centre d'affaires de Jouy
5 bis rue du Petit-Robinson
78950 Jouy en Josas, France
tel :(33)(1)34 65 08 95
The product Visilog is also distributed by
Noesis Vision Inc
6800 Cote de Liesse
Suite 200
Monreal, Que, H4T2A7
CANADA
tel (514) 345 14 00
Il runs not only on hexagonal grid but also ond standard rectagular grid
and runs on PC with MS-DOS and almost all the Unix workstations and support
several external devices like Matrox or Imaging and integrates more than 200
functions with few tens devoted to mathematical morphology (including grey level).
Several academic research lab in France are using this software.
I have no information about the prices, but usually you can get an
academic discount.
Roger Mohr
------------------------------
Date: Thu, 17 Aug 89 16:00:36 +0100
From: prlb2!ronse@uunet.UU.NET (Christian Ronse)
Subject: some ideas on image analysis methods & vision
I have written down some ideas on the relevance of certain image analysis
methodologies (Fourier analysis and mathematical morphology) to vision.
They are not finalized, but a few people around have told me that the question
is interesting. I would like to have other people's thoughts on the subject.
So, if you think you have something to say about it, feel free to ask me a
copy of my working document, and if you are brave enough, send back any
comments.
To get that document, send me your complete PHYSICAL ("snail") mail address,
not the electronic one (I will not send source files, only printed text).
Don't forget your country, Belgian postmen can't guess it.
PRLB Working Document WD54, June 1989
Fourier analysis, mathematical morphology, and vision
Abstract:
Two opposite orientations in image analysis are given on the one hand by
linear filtering, spectrometry, and Fourier analysis, and on the other
hand by mathematical morphology, which emphasizes order relations and
set-theoretical properties. The former derives its appeal from its wide
application in the processing of sound signals, while the latter has
been sucessfully used in the analysis of materials or in cytology. We
make a fundamental study of issues at hand in the choice of such
methodologies in image analysis and vision. We start by outlining the
difference in purpose of vision and audition and its physical basis, the
scattering of waves. We criticize Serra's arguments on this matter. Then
we consider the general limitations of linear filtering methodologies
and the unsuitability of phase-independent spectrometry. We propose a
paradigm of concurrent processing and of sorting of information rather
than a single sequence of processing modules with a controlled loss of
information. Finally we analyse the domain of applicability of
mathematical morphology to the visual process and suggest that it is
restricted to certain types of tasks.
Christian Ronse
Internet: maldoror@prlb.philips.be
UUCP: maldoror@prlb2.uucp
ARPA: maldoror%prlb.philips.be@uunet.uu.net
maldoror%prlb2.uucp@uunet.uu.net
BITNET: maldoror%prlb.philips.be@cernvax
maldoror%prlb2.uucp@cernvax
Philips Research Laboratory Brussels
Av. E. Van Becelaere, 2 b. 8
B-1170 Brussels, Belgium
------------------------------
Date: Thu, 17 Aug 89 13:51 EDT
From: Bartholomew Tschi-Quen 5C40 <tschi-quen@lewis.crd.ge.com>
Subject: Sensor Fusion
I would like to know if anyone on this list has information
Concerning Sensor Fusion since we are looking into this area
and are very much interested in it. Thanks you.
-Tschi-Quen, Tech. liason
Com. Vision group, GE
[ You might check the Proceedings of the AAAI 1987 Workshop on
Spatial Reasoning and Sensor Fusion, Oct. 1987, Pheasant Run Resort,
St. Charles, IL; also, Rosenfeld's bibliography in CVGIP is always
useful (better than Science Citation Index). What are other sources?
phil... ]
------------------------------
Date: Fri, 18 Aug 89 11:41 EDT
From: DUNCAN%DUNCAN@Venus.YCC.Yale.Edu
Subject: Postdoctoral Positions-- Yale University
YALE UNIVERSITY
Postdoctoral Positions in Medical Image Analysis
One to two positions are open within a research group interested in
developing computer vision- and image understanding- based approaches
to several medical image analysis problems. We are particularly
interested in using model-based optimization strategies for locating
and quantifying anatomical structure, and are in the process of
extending these ideas to handle three-dimensional and four-dimensional
data sets now becoming available from several diagnostic imaging
modalities (including Magnetic Resonance). The group has four faculty
members performing medical image processing/image analysis research, 8
Ph.D. students and 2 full-time programmers. The positions are joint
between the Departments of Diagnostic Radiology and Electrical
Engineering. In addition, the research group has strong ties with
faculty members in the Computer Science Department. Those who apply
should have a Ph.D. in Electrical Engineering or Computer Science,
preferably with a strong programming background and some familiarity
with, and coursework in, image processing and computer vision. The
initial appointment will be for one year, renewable for a second year
contingent upon the availability of funds and by mutual agreement.
Salary will be based on background and experience, but is expected to
be in the $28K - $32K range. Review of applications will begin
immediately and will be accepted until the positions are filled.
Applicants should send a resume and the names and addresses of three
references to: Professor James Duncan, Departments of Diagnostic
Radiology and Electrical Engineering, Yale Unversity, 333 Cedar Street
(327 BML), New Haven, Connecticut, 06510, and/or contact him at
Duncan@Venus.YCC.Yale.edu.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/26/89)
Vision-List Digest Fri Aug 25 09:59:27 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Postdoctoral Research Position
----------------------------------------------------------------------
Date: Mon, 21 Aug 89 12:26:30 EDT
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: Postdoctoral Research Position
POSTDOCTORAL RESEARCH POSITION
Low-level vision/Face recognition/Neural networks/Edinburgh
Applications are invited for a FOUR YEAR research post with Dr Michael
Morgan at the University of Edinburgh and Dr Roger Watt at the University
of Stirling. The succesful applicant would be based at Edinburgh. The post
is supported by a special grant from the SERC, "Recognition of faces
using principles of low-level Vision". The aim of the project is to
apply the Watt/Morgan "MIRAGE" spatial filtering algorithm to face
recognition, using MIRAGE spatial primitives as an input to a neural
network. The idea applicant would have UNIX/C programming experience and
a background in visual psychophysics, but appropriate training could be
provided in one of these areas if necessary.
Starting salary is in the region of 11K (UKL), depending on age and
experience. Overseas applicants would be given help in finding suitable
living accomodation in Edinburgh.
Applications, with CV and names of THREE referees, should be sent to:
M.J. Morgan, 135 Mayfield Road, EDINBURGH EH93AN, Scotland. Preliminary
enquiries may be made by Email to: MJM@STIR.CS (JANET).
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/01/89)
Vision-List Digest Thu Aug 31 21:12:58 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
GIPSY
Re: some ideas on image analysis methods & vision
----------------------------------------------------------------------
Date: Sat, 26 Aug 89 15:15:28 PDT
From: rameshv@george.ee.washington.edu (Ramesh Visvanathan)
Subject: GIPSY
Organization: University of Washington
A recent article referenced GIPSY and cited that it ran very slowly
under VMS.
GIPSY was primarily written to provide a flexible environment for the
researcher and it was intended to be very user-friendly. Speed was
not of primary concern at the time of design of GIPSY. While all the
old GIPSY code was written in RATFOR (Rational Fortran), new code
being added to GIPSY is written in C. Further new GIPSY code provides
for dynamic memory allocation, unlike the old RATFOR version. Hence,
new GIPSY uses less memory.
As far as usage of disk space is concerned, unless the system we are
working with has unlimited image buffers one has to use the system's
disk space to save processed images. From the GIPSY environment the
user can delete or compress unwanted images.
I agree that the old version of GIPSY was slow because of
reading/writing from disk files. We are currently attempting to speed
up GIPSY by using a large internal buffer to manage the number of I/O
situations. We expect the speedup to be substantial.
About GIPSY's documentation and its ease of use, with SUN GIPSY we now
have a set of demo files which instructs the user about GIPSY file
formats and GIPSY commands which use them. In addition, the working
of each GIPSY command is tested by a GIPSY runfile (which is nothing
but a batch file to test the command) and often the kind of
preprocessing necessary for the command is given in the runfile. The
document files may not explain the preprocessing necessary, but the
runfiles give the sequence of GIPSY preprocessing commands that can be
used to generate the test data set for using a particular GIPSY
command. I give below the documentation file for the GIPSY RAG command
and also the run file used to test this command.
RAG.DOC
*RAG Region adjacency graph
VERSION: A.01 DATE: 09-15-80 AUTHOR: LINDA SHAPIRO , T.C.PONG
ACTION: Given a symbolic image the command RAG, this command outputs two
random access files representing the region adjacency graph of the
image.The point file contains the pointers to and the adjacency
lists for each region; point(i) has two fields: first is
the pointer to the adjacency list for region i in the link
file; second is the number of regions in this adjacency list
the link file contains 16 region numbers (integers) per
record; each adjacency list starts on a new record.
SOURCE: Disk, input file name ( symbolic )
DESTINATION: Disk, 2 Random access files: point file and link file
point file -- integer records
RECORD I: pointer and number of neighors for
region i
link file -- integer records
records in the link file are pointed to by the
point file; there are 16 elements/record.
FLAGS:(E) If the E flag is used then four neighbors are used.
(F) If the F flag is used then eight neighbors are used.
QUESTIONS: (1) The user is asked which band of the image to process and
for two integers representing the highest and lowest
numbered regions to be processed.
(2) An option is given on four or eight neighbor adjacency
COMMAND STRING EXAMPLE:
RAG POINT.FILE , LINK.FILE < IMAGE.LBL
Creates a region adjacency graph for the symbolic image named
IMAGE.LBL. Put the pointers and lengths of the adjacency lists
in POINT.FILE and the elements of the lists in LINK.FILE
(in binary).
ALGORITHM: For each line i in the image
for each pixel labeled j in line i
for each pixel labeld j' that is horizontally
adjacent to the pixel labeld j on line i
or vertically adjacent to it on line i+1
add j to adjacency list j' and
add j' to adjacency list j
end
end
end
COMMENTS: Currently the point and link files are binary files and
are initialized to have a maximum of 2000 records.
The point file contains the pointers to and the adjacency
lists for each region; point(i) has two fields: first is
the pointer to the adjacency list for region i in the link
file; second is the number of regions in this adjacency list
the link file contains 16 region numbers (integers) per
record; each adjacency list starts on a new record.
"rag.run"
$ ! TESTING THE COMMAND RAG
$ ! CREATE A CHECKERBOARD AND MAKE IT A SYMBOLIC IMAGE
$ !
$ MKCHK CHK.SYM
10 10 5 5 1 2 0
$ !
$ !
$ ! USE THE EXSIF COMMAND TO CHANGE THIS IMAGE TO SYMBOLIC IMAGE
$ !
$ EXSIF
OPEN CHK.SYM
PROT OFF
MID 1 1
MID 2 2
MID 18 1
DONE
$ !
$ ! TESTING THE COMMAND RAG
$ !
$ RAG CHK.PT4,CHK.LK4 < CHK.SYM
4
$ !
$ ! TEST THE COMMAND RAG USING THIS PROPERTY FILE
$ !
$ PRTRAG TT<CHK.PT4,CHK.LK4 (A)
$ !
$ !
The documentation for GIPSY is constantly undergoing updating
by people who are using the system in our lab. Anytime anyone has
had a question about a command, if the documentation did not explain
it in a clear way, the documentation was updated.
If anyone using GIPSY has questions they can send mail to:
gipsy@george.ee.washington.edu
------------------------------
Date: Sun, 27 Aug 89 14:09:32 +0200
From: Ingemar Ragnemalm <ingemar@isy.liu.se>
Subject: Re: some ideas on image analysis methods & vision
A previous posting wrote:
>I have written down some ideas on the relevance of certain image analysis
>methodologies (Fourier analysis and mathematical morphology) to vision.
>They are not finalized, but a few people around have told me that the question
>is interesting. I would like to have other people's thoughts on the subject.
>So, if you think you have something to say about it, feel free to ask me a
>copy of my working document, and if you are brave enough, send back any
>comments.
> PRLB Working Document WD54, June 1989
> Fourier analysis, mathematical morphology, and vision
>Abstract:
>etc...
Yes, please, I would like to read your working document. In my opinion this
is the kind of work that is needed in computer vision presently. I'm not
sure that morphology should be done away with like you suggest, but rather
combined with the signal processing methods. However, it is hard to comment
only on the abstract.
Btw, I'm a member of prof. Per-Erik Danielsson's image processing lab. I'm
primarily working with morphology algorithms, and I have published a few
conference papers. I believe that I'm knowledgable enough to comment on
your work.
Please send the copy to:
Ingemar Ragnemalm
Dept of Electrical Engineering
Link|ping University
S-58183 Link|ping
SWEDEN
. .
where the "|" are "o" with two dots above, like: O
Yours,
Ingemar
Dept. of Electrical Engineering ...!uunet!mcvax!enea!rainier!ingemar
..
University of Linkoping, Sweden ingemar@isy.liu.se
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/09/89)
Vision-List Digest Fri Sep 08 09:30:27 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
NIPS Registration
----------------------------------------------------------------------
Date: Thu, 7 Sep 89 07:36:41 -0400
From: jose@tractatus.bellcore.com (Stephen J Hanson)
Subject: NIPS Registration
**** NIPS89 Update ****
We've just finished putting the program for the conference together and
have a preliminary program for the workshops. A mailing to authors
will go out this week, with registration information. Those who
requested this information but are not authors will hear from us starting
in another week. If you received a postcard from us acknowledging
receipt of your paper, you are on our authors' mailing list.
If you haven't requested the registration packet, you can do so
by writing to
Kathie Hibbard
NIPS89 Local Committee
University of Colorado Eng'g Center
Campus Box 425
Boulder, CO 80309-0425
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/19/89)
Vision-List Digest Mon Sep 18 10:39:25 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
neural nets and optical character recognition
cfp - 6th IEEE Conference on AI Applications
----------------------------------------------------------------------
Date: 14 Sep 89 09:40:29 GMT
From: Smagt v der PPP <mcvax!cs.vu.nl!smagt@uunet.UU.NET>
Subject: neural nets and optical character recognition
Keywords: neural nets, OCR, references
Organization: V.U. Informatica, Amsterdam, the Netherlands
I'm writing a survey article on using neural nets for optical
character classification. I've extensively studied neural nets
for half a year and have conducted many experiments, which will
also be reported in my article. In order to write my paper, I
am in need of some references on the subject of NN and OCR.
Does anyone have any literature suggestions?
Please e-mail your answer to smagt@cs.vu.nl
Patrick van der Smagt
V.U. Amsterdam
The Netherlands
------------------------------
Date: 13 Sep 89 01:29:12 GMT
From: finin@prc.unisys.com (Tim Finin)
Subject: cfp - 6th IEEE Conference on AI Applications
Organization: Unisys Paoli Research Center, PO 517, Paoli PA 19301
CALL FOR PARTICIPATION
The Sixth IEEE Conference on
Artificial Intelligence Applications
Fess Parker's Red Lion Resort
Santa Barbara, California
March 5-9, 1990
Sponsored by: The Computer Society of IEEE
The conference is devoted to the application of artificial intelligence
techniques to real-world problems. Two kinds of papers are appropriate:
Case studies of knowledge-based applications that solve significant problems
and stimulate the development of useful techniques. Papers on AI techniques
and principles that underlie knowledge-based systems, and in turn, enable
ever more ambitious real-world applications. This conference provides a
forum for such synergy between applications and AI techniques.
Papers describing significant unpublished results are solicited along
three tracks:
- "Engineering/Manufacturing" Track. Contributions stemming from
the general area of industrial and scientific applications.
- "Business/Decision Support" Track. Contributions stemming from
the general area of business, law and various decision support
applications.
Papers in these two application tracks must: (1) Justfy the use
of the AI technique, based on the problem definition and an
analysis of the application's requirements; (2) Explain how AI
technology was used to solve a significant problem; (3) Describe
the status of the implementation; (4) Evaluate both the
effectiveness of the implementation and the technique used.
- "Enabling Technology" Track. Contributions focusing on techniques
and principles that facilitate the development of practical knowledge
based systems, and can be scaled to handle increasing problem complexity.
Topics include, but not limited to: knowledge
acquisition, representation, reasoning, searching, learning, software
life cycle issues, consistency maintenance, verification/validation,
project management, the user interface, integration, problem-
solving architectures, and general tools.
Papers should be limited to 5000 words. The first page of the paper should
contain the following information (where applicable) in the order shown:
- Title.
- Authors' names and affiliation. (specify student)
- Abstract: A 200 word abstract that includes a clear statement on
what the original contribution is and what new lesson is imparted
by the paper.
- AI topic: Knowledge acquisition, explanation, diagnosis, etc.
- Domain area: Mechanical design, factory scheduling, education,
medicine, etc. Do NOT specify the track.
- Language/Tool: Underlying language and knowledge engineering tools.
- Status: development and deployment status as appropriate.
- Effort: Person-years of effort put into developing the particular
aspect of the project being described.
- Impact: A 20 word description of estimated or measured (specify)
benefit of the application developed.
Each paper accepted for publication will be allotted seven pages in the
conference proceedings. Best papers accepted in the Enabling Technology
track will be considered for a special issue of IEEE Transactions on
Knowledge and Data Engineering (TDKE) to appear in late 1990. Best
papers accepted in the application tracks will be considered for a
special issue of IEEE EXPERT, also to appear in late 1990. In addition,
there will be a best student paper award of $1,500, sponsored by IBM
for this conference.
In addition to papers, we will be accepting the following types of
submissions:
- Proposals for Panel discussions. Topic and desired participants.
Indicate the membership of the panel and whether you are interested
in organizing/moderating the discussion. A panel proposal should
include a 1000-word summary of the proposed subject.
- Proposals for Demonstrations. Videotape and/or description of a live
presentation (not to exceed 1000 words). The demonstration should be
of a particular system or technique that shows the reduction to
practice of one of the conference topics. The demonstration or video
tape should be not longer than 15 minutes.
- Proposals for Tutorial Presentations. Proposals of both an
introductory and advanced nature are requested. Topics should relate
to the management and technical development of usable and useful
artificial intelligence applications. Particularly of interest are
tutorials analyzing classes of applications in depth and techniques
appropriate for a particular class of applications. However, all
topics will be considered. Tutorials are three hours in
duration; copies of slides are to be provided in advance to IEEE for
reproduction.
Each tutorial proposal should include the following:
* Detailed topic list and extended abstract (about 3 pages)
* Tutorial level: introductory, intermediate, or advanced
* Prerequisite reading for intermediate and advanced tutorials
* Short professional vita including presenter's experience in
lectures and tutorials.
- Proposals for Vendor Presentations: A separate session will be held
where vendors will have the opportunity to give an overview to
their AI-based software products and services.
IMPORTANT DATES
- September 29, 1989: Six copies of Papers, and four copies of all
the proposals are due. Submissions not received by that date will
be returned unopened. Electronically transmitted materials will not
be accepted.
- October 30, 1989: Author notifications mailed.
- December 12, 1989: Accepted papers due to IEEE. Accepted tutorial
notes due to Tutorial Chair, Donald Kosy
- March 5-6, 1990: Tutorials
- March 7-9, 1990: Conference
Submit Papers and Other Materials to:
Se June Hong (Room 31-206)
IBM T.J. Watson Research Center
P.O. Box 218
Yorktown Heights, NY 10598
USA
Phone: (914)-945-2265
CSNET: HONG@IBM.COM
FAX: (914)-945-2141
TELEX: 910-240-0632
Submit Tutorial Proposals to:
Donald Kosy
Robotics Institute
Carnegie Mellon University
Pittsburgh, Pennsylvania 15213
Phone: 412-268-8814
ARPANET: kosy@cs.cmu.edu
CONFERENCE COMMITTEES
General Chair
Mark S. Fox, Carnegie-Mellon University
Publicity Chair
Jeff Pepper, Carnegie Group Inc
Tutorial Chair
Donald Kosy, Carnegie Mellon University
Program Committee
Chair Se June Hong, IBM Research
At-large Jan Aikins, AION Corp.
John Gero, University of Sidney
Robert E. Filman, IntelliCorp
Gary Kahn, Carnegie Group
John Mc Dermott, DEC
Engineering/Manufacturing Track
Chair Chris Tong, Rutgers University (Visiting IBM)
Sanjaya Addanki, IBM Research
Alice Agogino, UC Berkeley
Miro Benda, Boeing Computer Services
Sanjay Mittal, Xerox PARC
Duvurru Sriram, MIT
Business/Decision Support Track
Chair Peter Hart, Syntelligence
Chidanand Apte, IBM Research
Vasant Dhar, New York University
Richard Fikes, Price-Waterhouse
Timothy Finin, Unisys Paoli Research Center
Daniel O'Leary, University of Southern California
Enabling Technology Track
Chair Howard Shrobe, Symbolics
Lee Erman, CIMFLEX-Teknowledge
Brian Gaines, University of Calgary
Eric Mays, IBM Research
Kathy McKeown, Columbia University
Katia Sycara, Carnegie-Mellon University
Additional Information
For registration and additional conference information, contact:
CAIA-90
The Computer Society of the IEEE
1730 Massachusetts Avenue, NW
Washington, DC 20036-1903
Phone: 202-371-0101
Tim Finin finin@prc.unisys.com (internet)
Unisys Paoli Research Center ..!{psuvax1,sdcrdcf,cbmvax}!burdvax!finin (uucp)
PO Box 517 215-648-7446 (office), 215-386-1749 (home),
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/26/89)
Vision-List Digest Mon Sep 25 12:40:06 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
New Service for Vision List: Relevant Journal Table of Contents
BBS Call for Commentators: Visual Search & Complexity
Subject: street address for IEEE CAIA-90 submissions
7th Intern. Conf. on Machine Learning
IEEE Jrnl of Robotics and Automation Aug 89
IEEE Trans on PAMI Jul 89
----------------------------------------------------------------------
Date: Mon, 25 Sep 89 12:14:29 PDT
From: Vision-List-Request <vision@deimos.ads.com>
Subject: New Service for Vision List: Relevant Journal Table of Contents
Thanks to Jon Webb and the Computer Science Library at CMU, the
Vision List will now be posting the table of contents for select
relevant journals. These table of contents will be placed at the
end of the List in order to avoid cluttering up subscriber
discussion and comments. The goal of these indices is to simplify
the identification of current relevant literature and help us all
better manage our time.
The journals include: IEEE Journal on Robotics and Automation (JRA),
IEEE Transactions on Pattern Analysis and Machine Intelligence
(TPAMI), International Journal on Computer Vision (IJCV), and
Perception. We may also include CVGIP and Spatial Vision. JRA often
has interesting vision articles, though it is not specifically vision
oriented: please let me know if you believe it should be omitted.
Comments are invited and encouraged.
phil...
----------------------------------------------------------------------
Date: 19 Sep 89 05:41:53 GMT
From: harnad@phoenix.princeton.edu (S. R. Harnad)
Subject: BBS Call for Commentators: Visual Search & Complexity
Keywords: computer vision, natural vision, complexity theory, brain
Organization: Princeton University, NJ
Below is the abstract of a forthcoming target article to appear in
Behavioral and Brain Sciences (BBS), an international,
interdisciplinary journal that provides Open Peer Commentary on
important and controversial current research in the biobehavioral and
cognitive sciences. Commentators must be current BBS Associates or
nominated by a current BBS Associate. To be considered as a
commentator on this article, to suggest other appropriate
commentators, or for information about how to become a BBS Associate,
please send email to:
harnad@princeton.edu or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
Analyzing Vision at the Complexity Level
John K. Tsotsos
Department of Computer Science,
University of Toronto and
The Canadian Institute for Advanced Research
The general problem of visual search can be shown to be
computationally intractable in a formal complexity-theoretic sense,
yet visual search is widely involved in everyday perception and
biological systems manage to perform it remarkably well. Complexity
level analysis may resolve this contradiction. Visual search can be
reshaped into tractability through approximations and by optimizing
the resources devoted to visual processing. Architectural constraints
can be derived using the minimum cost principle to rule out a large
class of potential solutions. The evidence speaks strongly against
purely bottom-up approaches to vision. This analysis of visual search
performance in terms of task-directed influences on visual information
processing and complexity satisfaction allows a large body of
neurophysiological and psychological evidence to be tied together.
Stevan Harnad
INTERNET: harnad@confidence.princeton.edu harnad@princeton.edu
srh@flash.bellcore.com harnad@elbereth.rutgers.edu harnad@princeton.uucp
CSNET: harnad%confidence.princeton.edu@relay.cs.net
BITNET: harnad1@umass.bitnet harnad@pucc.bitnet (609)-921-7771
------------------------------
Date: 25 Sep 89 18:33:33 GMT
From: finin@prc.unisys.com (Tim Finin)
Subject: street address for IEEE CAIA-90 submissions
Organization: Unisys Paoli Research Center, PO Box 517, Paoli PA 19301
REMINDER ----- IEEE CAIA-90 ----- DEAD LINE 9/29 ----- REMINDER
6th IEEE Conference on AI Applications
For those colleagues who depend on express mailing (don't we all?),
here is the street address to use:
Se June Hong (Room 31-206)
IBM T. J. Watson Research Center
Route 134 (Kitchawan) and Taconic
(PO box 218 if regular post)
Yorktown Heights, NY 10598
Tim Finin finin@prc.unisys.com (internet)
Unisys Paoli Research Center ..!{psuvax1,sdcrdcf,cbmvax}!burdvax!finin (uucp)
PO Box 517 215-648-7446 (office), 215-386-1749 (home),
------------------------------
Posted-Date: Thu, 21 Sep 89 13:46:14 CDT
From: ml90@cs.utexas.edu (B. Porter and R. Mooney)
Date: Thu, 21 Sep 89 13:46:14 CDT
Subject: 7th Intern. Conf. on Machine Learning@@
SEVENTH INTERNATIONAL CONFERENCE ON MACHINE
LEARNING: CALL FOR PAPERS
The Seventh International Conference on Machine Learning will be
held at the University of Texas in Austin during June 21--23,
1990. Its goal is to bring together researchers from all
areas of machine learning. The conference will include
presentations of refereed papers, invited talks, and poster
sessions. The deadline for submitting papers is February 1,
1990.
REVIEW CRITERIA
In order to ensure high quality papers, each submission will
be reviewed by two members of the program committee and
judged on clarity, significance, and originality. All sub-
missions should contain new work, new results, or major extensions
to prior work. If the paper describes a running system, it
should explain that system's representation of inputs and outputs,
its performance component, its learning methods, and its evalua-
tion. In addition to reporting advances in current areas of
machine learning, authors are encouraged to report results on
exploring novel learning tasks.
SUBMISSION OF PAPERS
Each paper must have a cover page with the title, author's
names, primary author's address and telephone number, and an
abstract of about 200 words. The cover page should also give
three keywords that describe the research. Examples of keywords
include:
PROBLEM AREA GENERAL APPROACH EVALUATION CRITERIA
Concept learning Genetic algorithms Empirical evaluation
Learning and planning Empirical methods Theoretical analysis
Language learning Explanation-based Psychological validity
Learning and design Connectionist
Machine discovery Analogical reasoning
Papers are limited to 12 double-spaced pages (including figures
and references), formatted with twelve point font. Authors
will be notified of acceptance by Friday, March 23, 1990 and
camera-ready copy is due by April 23, 1990.
Send papers (3 copies) to: For information, please contact:
Machine Learning Conference Bruce Porter or Raymond Mooney
Department of Computer Sciences ml90@cs.utexas.edu
Taylor Hall 2.124 (512) 471-7316
University of Texas at Austin
Austin, Texas 78712-1188
------------------------------
Date: Fri, 22 Sep 89 10:29:21 EDT
Subject: IEEE Jrnl of Robotics and Automation Aug 89
From: ES.Library@B.GP.CS.CMU.EDU
REFERENCES
[1] Ahmad, Shaheen and Luo, Shengwu.
Coordinated Motion Control of Multiple Robotic Devices for Welding and
Redundancy Coordination through Constrained Optimization in Cartesian
Space.
IEEE Journal of Robotics and Automation 5(4):409-417, August, 1989.
[2] ElMaraghy, Hoda A. and Payandeh, S.
Contact Prediction and Reasoning for Compliant Robot Motions.
IEEE Journal of Robotics and Automation 5(4):533-538, August, 1989.
[3] Hannaford, Blake.
A Design Framework for Teleoperators with Kinesthetic Feedback.
IEEE Journal of Robotics and Automation 5(4):426-434, August, 1989.
[4] Jacak, Witold.
A Discrete Kinematic Model of Robots in the Cartesian Space.
IEEE Journal of Robotics and Automation 5(4):435-443, August, 1989.
[5] Kumar, Vijay and Waldron, Kenneth J.
Suboptimal Algorithms for Force Distribution in Multifingered Grippers.
IEEE Journal of Robotics and Automation 5(4):491-498, August, 1989.
[6] Kusiak, Andrew.
Aggregate Scheduling of a Flexible Machining and Assembly System.
IEEE Journal of Robotics and Automation 5(4):451-459, August, 1989.
[7] Li, Chang-Jin.
An Efficient Method for Linearization of Dynamic Models of Robotic
Manipulators.
IEEE Journal of Robotics and Automation 5(4):397-408, August, 1989.
[8] Martin, D. P.; Baillieul, J.; and Hollerbach, J. M.
Resolution of Kinematic Redundancy Using Optimization Techniques.
IEEE Journal of Robotics and Automation 5(4):529-533, August, 1989.
[9] Murray, John J. and Lovell, Gilbert H.
Dynamic Modeling of Closed-Chain Robotic Manipulators and Implications
for Trajectory Control.
IEEE Journal of Robotics and Automation 5(4):522-528, August, 1989.
[10] Pfeffer, Lawrence E.; Khatib, Oussama; and Hake, J.
Joint Torque Sensory Feedback in the Control of a PUMA Manipulator.
IEEE Journal of Robotics and Automation 5(4):418-425, August, 1989.
[11] Rodriguez, Guillermo.
Recursive Forward Dynamics for Multiple Robot Arms Moving a Common Task
Object.
IEEE Journal of Robotics and Automation 5(4):510-521, August, 1989.
[12] Seraji, Homeyoun.
Configuration Control of Redundant Manipulators: Theory and
Implementation.
IEEE Journal of Robotics and Automation 5(4):472-490, August, 1989.
[13] Sorensen, Brett R.; Donath, Max; Yang, Guo-Ben; and Starr, Roland C.
The Minnesota Scanner: A Prototype Sensor for Three-Dimensional Tracking
of Moving Body Segments.
IEEE Journal of Robotics and Automation 5(4):499-509, August, 1989.
[14] Tsujimura, Takeshi and Yabuta, Tetsuro.
Object Detection by Tactile Sensing Method Employing Force/Torque
Information.
IEEE Journal of Robotics and Automation 5(4):444-450, August, 1989.
[15] Wang, Y. F. and Aggarwal, J. K.
Integration of Active and Passive Sensing Techniques for Representing
Three-Dimensional Objects.
IEEE Journal of Robotics and Automation 5(4):460-471, August, 1989.
------------------------------
Date: Fri, 22 Sep 89 10:30:50 EDT
Subject: IEEE Trans on PAMI Jul 89
From: ES.Library@B.GP.CS.CMU.EDU
REFERENCES
[1] Chen, David Shi.
A Data-Driven Intermediate Level Feature Extraction Algorithm.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):749-758, July, 1989.
[2] Chen, Ming-Hua and Yan, Ping-Fan.
A Multiscale Approach Based on Morphological Filtering.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):694-700, July, 1989.
[3] Gath, I. and Geva, A. B.
Unsupervised Optimal Fuzzy Clustering.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):773-781, July, 1989.
[4] Mallat, Stephane G.
A Theory for Multiresolution Signal Decomposition: The Wavelet
Representation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):674-693, July, 1989.
[5] Maragos, Petros.
Pattern Spectrum and Multiscale Shape Representation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):701-716, July, 1989.
[6] Peleg, Shmuel; Werman, Michael; and Rom, Hillel.
A Unified Approach to the Change of Resolution: Space and Grey-Level.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):739-742, July, 1989.
[7] Sanz, Jorge L. C. and Huang, Thomas T.
Image Representation by Sign Information.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):729-738, July, 1989.
[8] Shah, Y. C,; Chapman, R.; and Mahani, R. B.
A New Technique to Extract Range Information.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):768-773, July, 1989.
[9] Strobach, Peter.
Quadtree-Structured Linear Prediction Models for Image Sequence
Processing.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):742-748, July, 1989.
[10] Usner, Michael and Eden, Murray.
Multiresolution Feature Extraction and Selection for Texture
Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):717-728, July, 1989.
[11] Yeshurun, Yehezkel and Schwartz, Eric L.
Cepstral Filtering on a Columnar Image Architecture: A Fast Algorithm
for Binocular Stereo Segmentation.
IEEE Transactions on Pattern Analysis and Machine Intelligence
PAMI-11(7):759-767, July, 1989.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/30/89)
Vision-List Digest Fri Sep 29 09:57:55 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: TOC for journals Journal Info: Machine Vision and Applications ---------------------------------------- Date: Wed, 27 Sep 89 09:52:34 EDT From: jaenicke@XN.LL.MIT.EDU (Richard A. Jaenicke) Subject: TOC for journals Phil, I think that inclusion of table-of-contents in the Vision-List is a great idea. Hurray for John Web and the CMU CS library! I am for including any TOC's you can get your (electronic) hands on as long as they have some remote connection to computer vision. Richard Jaenicke Machine Intelligence Group jaenicke@xn.ll.mit.edu MIT Lincoln Laboratory [ In order to decrease clutter, I will eliminate article listings which do not have a connection to vision (e.g., path planning articles in the Journal of Robotics & Automation). We are currently working to increase the number of listed journals relevant to vision. We need to balance the helpfulness of information with clutter overload. All and any feedback is useful. phil... ] ------------------------------ Date: Fri, 29 Sep 89 09:42:25 PDT From: rossbach%engrhub@hub.ucsb.edu Subject: Machine Vision and Applications Machine Vision and Applications, An International Journal This journal is published four times a year and has a personal subscription rate of $45.00 (including postage and handling. The institutional rate is $105.00 (including postage and handling). If you would like a sample copy or subscription information, please send email to rossbach@hub.ucsb.edu. Volume 2, Issues 2 and 3 contain the following articles: Extraction of Graphic Primitives from Images of Paper-based Drawings by C. Shih and R. Kasturi. A Fruit-Tracking System for Robotic Harvesting by R. Harrell, D. Slaughter and P. Adsit. Range Estimation from Intensity Gradient Analysis by Ramesh Jain and Kurt Skifstad. Reconstruction of Two Dimensional Patterns by Fourier Descriptors by A. Krzyzak, S. Leung and C. Suen. Analysis of Textural Images Using the Hough Transform by S. Srihari and V. Govindaraju. Knowledge-directed Inspection for Complex Multi-layered Patterns by M. Ejiri, H. Yoda and H. Sakou. Which Parallel Architectures are Useful/Useless for Vision Algorithms? by J. L. C. Sanz. Expect to see the next issue of the journal, Volume 2, Issue 4, this November! For further information on submitting a paper or subscribing to the journal, please send email to rossbach@hub.ucsb.edu; or write to Springer-Verlag, 815 De La Vina Street, Santa Barbara, CA 93101; or call (805) 963-7960. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/07/89)
Vision-List Digest Fri Oct 06 10:28:40 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re: TOC for journals
Research positions at U-Geneva, Switzerland.
Workshop on Combining Multiple Strategies For Vision
----------------------------------------------------------------------
Date: Wed, 4 Oct 89 09:19:18 BST
From: alien%VULCAN.ESE.ESSEX.AC.UK@CUNYVM.CUNY.EDU (Adrian F. Clark)
Subject: Re: TOC for journals
I am pleased to see the inclusion of machine-readable tables of
contents for relevant journals. This is so useful that I am archiving
them locally and forwarding them to other (non-Vision-List readers) in
the UK and Europe. However, I would like to make two suggestions:
o I urge you not to omit articles which do not appear to be
vision-related. Apart from pedantic objections, there are many
cases where solutions to problems which have no immediate
application to vision (or, indeed, any other discipline) provide
useful insights into one's own problems. Futhermore, there are
a number of readers (such as myself) who are not working directly
on vision, but apply image understanding techniques to other problems.
o surely there is a case for distributing the contents lists in a format
which allows easy insertion into some bibliographic database
system? I would imagine that most readers produce papers by computer.
Unix `refer' or BibTeX spring to mind. Since there are a
number of widely-available tools for converting the former to the
latter, `refer' might be better. Or perhaps some generic mark-up
system, which can easily be converted into any particular format,
would be the best.
Adrian F. Clark
JANET: alien@uk.ac.essex.ese ARPA: alien%uk.ac.essex.ese@nsfnet-relay.ac.uk
BITNET: alien%uk.ac.essex.ese@ac.uk PHONE: (+44) 206-872432 (direct)
Dept ESE, University of Essex, Wivenhoe Park, Colchester, Essex, C04 3SQ, UK.
[ Ed.: Several readers have echoed the first comment. Especially
with regards to the J. Rob. & Auto. At the other end of the spectrum,
I am concerned with reducing clutter on the List which undermines
the focus of the List which discusses Vision issues. Feedback on
TOC and how they are maintained over the next several months
will better define where the line should be drawn.
The second comment regarding TOC format has also been echoed
by several readers. For now, I am posting the TOC in the
format I receive them in. They are alternatively available in
scribe format. A key advantage of the current form is that they
are clear and easy to rapidly scan and selectively pull apart.
Database formatted references (e.g., refer format) are much more
difficult and time consuming to visually scan. Yet, I also
appreciate the utility of maintaining a DB of relevant vision
articles. These issues are still being considered, and will be
deferred in the short run until an acceptable set of journals
has been agreed uupon and stabilized.
CVGIP will hopefully soon be brought on-line. I am attempting to
include more neurobiological journals which address structure
of biological vision systems as well. I am still trying to obtain
electronic TOC for: Journal of the Optical Society of America: A,
Spatial Vision, Vision Research, and perhaps (depending on reader
interest), Trends in Neuroscience and Biological Cybernetics.
Volunteers wishing to provide these TOC on a timely and consistent
basis are sought.
phil...]
------------------------------
Date: 05 Oct 89 18:48:26 GMT
From: Thierry Pun <pun@cui.unige.ch>
Subject: Research positions at U-Geneva, Switzerland.
AI and Vision Group, Computing Science Center
University of Geneva, Switzerland
We have THREE open positions, to be filled in as soon as possible, for
RESEARCH ASSISTANTS IN COMPUTER VISION
AND ARTIFICIAL INTELLIGENCE
The succesfull candidates will participate to our work in the context of the
Swiss National Research Program PNR 23 "Artificial intelligence and robotics".
The project concerns various aspects of the development of computer vision
systems for robotic applications.
The group currently consists of approximately 12 researchers, 6 in vision and
6 in AI. The AI and Vision group is part of the Computer Science Center, which
comprises approximately 60 researchers. Research facilities are excellent.
We offer advanced research with up-to-date computing facilities and a nice
environment. Salary starts at 4'020 SFR per month (1 SFR has been recently
oscillating between 1.6 and 1.8 US$).
We wish to hire a research oriented student, holding a university degree in
computing science or closely related field. The candidate must be oriented
towards computer vision and/or artificial intelligence.
If you are interested, please send your resume, interests, publications,
references to:
Prof. Thierry Pun, Computer Vision Group
Computing Science Center, U-Geneva
12, rue du Lac, CH-1207 Geneva SWITZERLAND
Phone : +41(22) 787 65 82; fax: +41(22) 735 39 05
E-mail: pun@cui.unige.ch, pun@cgeuge51.bitnet
------------------------------
Date: Friday, 6 Oct 1989 12:57:43 EST
From: m20163@mwvm.mitre.org (Nahum Gershon)
Subject: Workshop on Combining Multiple Strategies For Vision
Organization: The MITRE Corp., Washington, D.C.
Eighteenth Workshop on
Applied Imagery Pattern Recognition
Subject: Combining Multiple Strategies For Vision
October 11-13, 1989
Cosmos Club, Washington, DC
Contact ERIM (Kathleen) at (313) 994-1200, x 2237
Nahum
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/14/89)
Vision-List Digest Fri Oct 13 11:10:59 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Fractal scene modeling
Error in Swiss Fr to US $ conversion.
ICIP'89 successfully held in Singapore
TOC
----------------------------------------------------------------------
Date: Sat, 7 Oct 89 01:12:38 GMT
From: us214777@mmm.3m.com (John C. Schultz)
Subject: Fractal scene modeling
Organization: 3M - St. Paul, MN 55144-1000 US
I am looking for some routines which would compute the fractal "dimension"
of a natural texture. For example, given a texture I would like to
compute the fractal dimension for small (8x8 up to 64x64 pixels) blocks of
data.
I have seen many references to such algorithms in the literature but the
sections on how to actually compute a fractal dimension have been a trifle
light.
Perhaps someone could post an implementation to the net. A C implementation
would be preferable from my viewpoint.
John C. Schultz EMAIL: jcschultz@mmm.com
3M Company WRK: +1 (612) 733 4047
3M Center, Building 518-01-1 St. Paul, MN 55144-1000
------------------------------
Date: Sat, 7 Oct 89 19:04 N
From: THIERRY PUN <PUN%CGEUGE51.BITNET@CUNYVM.CUNY.EDU>
Subject: Error in Swiss Fr to US $ conversion.
In a previous posting regarding research assistant positions at
the University of Geneva, Switzerland, I mistakenly inverted the
exchange rate. You should read 1 US$ has been varying between
1.6 and 1.8 SFr.
Sorry....
Thierry Pun, CUI, U-Geneva, Switzerland.
pun@cui.unige.ch
------------------------------
Date: Mon, 9 Oct 89 23:18:12 -0500
From: teh@cs.wisc.edu (Cho-huak Teh)
Subject: ICIP'89 successfully held in Singapore
The First IEEE 1989 International Conference on Image Processing
was successfully held in Singapore from 5 to 9 of September.
The conference chair was K. N. Ngan of the National University of Singapore
and the keynote address were made by Takeo Kanade of CMU
on "Computer Vision and Physical Science".
There were about 200 delegates to the 19 sessions of the conference and
146 to the tutorials by T. S. Huang, B. G. Batchelor, R. J. Ahlers,
and F. M. Waltz.
Contact IEEE to obtain a copy of the conference proceedings.
The 2nd IEEE ICIP is being planned, possibly to be held in the Fall of 1991.
Cho-Huak TEH
------------------------------
Date: Tue, 10 Oct 89 21:52:18 IST
From: Shelly Glaser 011 972 3 545 0060 <GLAS%TAUNIVM.BITNET@CUNYVM.CUNY.EDU>
Subject: TOC
You may also consider "Optics Letters" and "Applied Optics" as well.
I am told that the "Current Contents" weekly is now available also on
diskettes. It also carries address list for the authors which may be of
use for those who do not have access to a specific journal.
Yours,
Shelly
Acknowledge-To: <GLAS@TAUNIVM>
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/24/89)
Vision-List Digest Mon Oct 23 13:27:15 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
BBS Call for Commentators: Visual Field Specialization
Proceedings of ICIP'89
Reference wanted
Facial Features: Computer Analysis
------------------------------
Date: Thu, 19 Oct 89 03:05:05 -0500
From: mendozag@ee.ecn.purdue.edu (Victor M Mendoza-Grado)
Subject: Reference wanted
I am looking for the exact reference to the following paper:
``Parallel Processing of a Knowledge-Based Vision System,''
by D. I. Moldovan and C. I. Wu.
It might have appeared as a conference paper around 1986 or 1987.
I'd appreciate any pointers. Thanks in advance
VMG
mendozag@ecn.purdue.edu
------------------------------
Date: Fri, 20 Oct 89 01:03:47 EDT
From: harnad@clarity.Princeton.EDU (Stevan Harnad)
Subject: Facial Features: Computer Analysis
I would like information about software and hardware for representing
and analyzing faces and facial features. Ideally, I would like
something that, like Susan Brennan's program for generating
caricatures, has been standardized across large samples of faces and is
able to pull out the facial parameters that carry the kind of
information we pick up when we look at faces.
The purpose of the project is to find detectable, quantifiable features
that will predict the degree of genetic relatedness between two people
from images of their faces.
Please send the replies to me, not the net. If anyone wants me to share
the responses with them, send me an email request.
Stevan Harnad
INTERNET: harnad@confidence.princeton.edu srh@flash.bellcore.com
harnad@elbereth.rutgers.edu UUCP: harnad@princeton.uucp
BITNET: harnad@pucc.bitnet harnad1@umass.bitnet Phone: (609)-921-7771
Department of Psychology, Princeton University, Princeton NJ 08544
------------------------------
Date: Thu, 19 Oct 89 20:45:36 -0500
From: teh@cs.wisc.edu (Cho-huak Teh)
Subject: Proceedings of ICIP'89
To obtain a copy of the proceedings of 1989 1st IEEE ICIP,
you should contact the following instead of IEEE :
Meeting Planners Pte Ltd
100 Beach Road
#33-01, Shaw Towers
Singapore 0718
Republic of Singapore
Attn : ICIP'89 Proceedings
Tel : (65)297-2822
Tlx : RS 40125 MEPLAN
Fax : (65)296-2670
-- Cho Huak TEH
----------------------------------------------------------------------
Date: Mon, 16 Oct 89 00:44:19 EDT
From: harnad@clarity.Princeton.EDU (Stevan Harnad)
Subject: BBS Call for Commentators: Visual Field Specialization
Below is the abstract of a forthcoming target article to appear in
Behavioral and Brain Sciences (BBS), an international,
interdisciplinary journal that provides Open Peer Commentary on important
and controversial current research in the biobehavioral and cognitive
sciences. Commentators must be current BBS Associates or nominated by a
current BBS Associate. To be considered as a commentator on this article,
to suggest other appropriate commentators, or for information about how
to become a BBS Associate, please send email to:
harnad@confidence.princeton.edu or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
Functional Specialization in the Lower and Upper Visual Fields in Man:
Its Ecological Origins and Neurophysiological Implications
by Fred H. Previc
Crew Technology Division
USAF School of Aerospace Medicine
Brooks AFB, TX 78235-5301
Abstract: Functional specialization in the lower and upper visual
fields in man is reviewed and interpreted with respect to the origins
of the primate visual system. Many of the processing differences
between the vertical hemifields are related to the distinction between
near (personal) and far (extrapersonal) space, which are biased towards
the lower and upper visual fields respectively. It is hypothesized that
a significant enhancement of these functional specializations occurred
in conjunction with the emergence of forelimb manipulative skills and
fruit-eating, in which the fruit or distal object is searched and
attended to in central vision while the reaching motion of the hand and
other related manipulations are monitored in the proximal lower visual
field. Objects in far vision are searched and recognized primarily
using linear/local perceptual mechanisms, whereas nonlinear/global
processing is required in the lower visual field in order to perceive
the optically degraded and diplopic images contained in near vision.
The functional differences between the lower and upper visual fields
are correlated with their disproportionate representations in the
dorsal vs. ventral divisions of visual association cortex,
respectively, and in the magnocellular and parvocellular pathways that
project to them. The division between near and far visual functions may
also have contributed to the transformations of the lateral geniculate
nucleus, superior colliculus, and frontal visual areas which occurred
during the evolution of primate vision.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/09/89)
Vision-List Digest Wed Nov 08 17:22:11 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Fractal description of images Re: Applications of distance maps Computer Vision in High Energy Physics 3-D Displays Research Fellowship ---------------------------------------------------------------------- Date: Tue, 7 Nov 89 03:03:56 GMT From: us214777@mmm.serc.3m.com (John C. Schultz) Subject: Fractal description of images Organization: 3M - St. Paul, MN 55144-1000 US Several weeks ago I asked if anyone had an algorithm they were willing to share on how to calculate image fractal dimensions. Although I still don't have an implementation, I DO have a readable reference that even provides pseudo-code. The reference comes from U of Missouri-Colombia and perhaps someone at that school could impose on the authors to provide their code? In any case, I will be working on a realization here for our specific hardware. Here is the reference and thanks to the authors for a well written paper. Keller JM, Chen S, & Crownover RM, "Texture Description and Segmentation through Fractal Geometry", Computer Vision, Graphics, and Image Processing, 45, 150-166 (1989) Academic Press. -- John C. Schultz EMAIL: jcschultz@mmm.3m.com 3M Company WRK: +1 (612) 733 4047 3M Center, Building 518-01-1 St. Paul, MN 55144-1000 The opinions expressed above are my own and DO NOT reflect 3M's ------------------------------ Date: Tue, 7 Nov 89 12:22:31 +0100 From: Ingemar Ragnemalm <ingemar@isy.liu.se> Subject: Re: Applications of distance maps In comp.ai.vision both you and I write: >I'm writing a thesis on distance mapping techniques, and I need more >references to applications. >There are a lot of applications, like: (I still need more of them! Please?) >(some of my junk deleted, including some simple examples) >These examples are with the crude "City Block" metric. There are far better >metrics [Borgefors], including the exact Euclidean metric [Danielsson]. >E-mail: ingemar@isy.liu.se >[ Please post responses to the Vision List... > > An aside: > City-block distance metric is particularly easy to compute. Initialized > chamfer image locations set to 0 for occupied positions; infinity otherwise > (i.e., a very large integer). Two passes (top-to-bottom/left-to-right and > bottom-to-top/right-to-left) then compute the chamfer. First pass takes the > MIN of the current location and the neighbors' chamfer values incremented > by the indicated values (CP is the current position): > +2 +1 +2 > +1 CP > Second pass uses the same mask flipped on both the vertical and horizontal > axes. Region labelled chamfer obtained by also propagating region labels. > Region growing in constant time by thresholding the distance chamfer. > Medial axis transform occurs at maxima in the distance chamfer. Sorry for > being long winded, but this algorithm (shown to me originally by Daryl > Lawton) has proven quite useful... N-nearest neighbor algorithms (for > N>1) get significantly more computationally complex (anyone know of good > algorithms?). > phil...] Actually, most efficient algorithms use this "scanning" technique. A far better algorithm with masks of the same size is: +4 +3 +4 +3 0 as suggested by Borgefors [CVGIP 1986]. It is proven the optimal 3*3 chamfer mask with integer weights. Borgefors also suggests the "5-7-11" mask for the 5*5 mask size. Danielsson [CGIP 1980] uses a similar technique for the Euclidean distance transform, as well as myself in some of my own work (published at the 6SCIA conference 1989). The big difference is that Euclidean DT *must* use more than two scans. Three or four should be used (as in my paper) or the equivalent two "double" scans (as in Danielsson's paper). An interesting point is that a canadian researcher, Frederic Leymarie, who I met at a conference claimed that the 4-neighbor version of the Euclidean distance transform is faster than everything but the City Block distance transform. I'm still waiting for the actual paper, though. So much for implementation. BTW, Phil, you didn't say what *you* used the CB distance maps for. Would you care to share that information? I'll be back when I've got some more replies. Ingemar Ragnemalm Dept. of Electrical Engineering ...!uunet!mcvax!enea!rainier!ingemar .. University of Linkoping, Sweden ingemar@isy.liu.se [ Very interesting mask modifications for computing CB chamfers. If I remember correctly, when the distance metric scale in pixels is important (i.e., the distance values are in pixel unit CB distance), an "extra pass" is required to reduce the resulting chamfer values to pixel units of distance (since I often desired the values in pixel units). What did I use the CB distance (chamfer) for? Pretty varied uses. Region growing in constant time (i.e., chamfer and threshold). Determining the closest surrounding regions to each image region (by propagating the region ID with the distance metric). I used this to form a graph in which textels are vertices connected by edges to all chamfer determined adjacent neighbors, and texture is described as topological properties of this Voronoi-related graph. (I never published this: CVPR88 had a paper or two that did something like this, but not quite). I have also used it to compute the probability dropoff of a vehicle detection against its background due to radar sensor distortion, occlusion, and uncertainty (suggested by Doug Morgan of ADS). Note that use of 1-nearest neighbor is very susceptible to noise, and its relationship to the Symmetric and Medial Axis Tranforms gives it some other nasty properties (e.g., small chamges in image topology can give rise to very large changes in chamfer/SAT/MAT topology). The n-nearest neighbor moves away from some of these problems. Thing is, I haven't seen (nor honestly, looked very hard), for n-nearest neighbor algorithms which are efficient. phil... ] ------------------------------ Date: Wed, 8 NOV 89 10:06 N From: DANDREA%ITNVAX.CINECA.IT%ICINECA2.BITNET@CUNYVM.CUNY.EDU Subject: Computer Vision in High Energy Physics I'm looking for informations regarding the application of Computer Vision or Image Processing techniques to experimental problems in High Energy Physics. What I'm thinking of could be the applications to the problem of track reconstruction and particle identification. If someone else is interested I'll post a summary to the list. Thanks, Vincenzo D'Andrea e-mail: DANDREA@ITNCISCA.BITNET Dipartimento di Fisica Universita` di Trento 38050 - POVO (TN) ITALY tel. +39 (461) 881565 ------------------------------ Date: 8 Nov 89 10:23:00 EST From: "V70NL::SCHLICHTING" <schlichting%v70nl.decnet@nusc.navy.mil> Subject: 3-D Displays Could you please tell me where I could obtain a copy of the papers listed in the recent vision list from ACM SIGGRAPH "Tutorial notes on stereo graphics"? Thank you, Christine Schlichting (Schlichting@nusc.navy.mil) ------------------------------ Date: Wed, 8 Nov 89 11:57:23 WET DST Subject: Research Fellowship From: M.Petrou%ee.surrey.ac.uk@NSFnet-Relay.AC.UK VISION, SPEECH AND SIGNAL PROCESSING GROUP University of Surrey, U. K. RESEARCH FELLOWSHIP A research fellowship has become available in the above group for the fixed term of three years. The research fellow will work on Renormalization Group techniques in Image Processing, a project funded by SERC. A good knowledge of a high level programming language is necessary. No previous experience in Image Processing or Computer Vision is needed, but a Mathematical background will be an advantage. Starting salary up to 13,527 pounds per annum. For more information contact Dr M Petrou (tel (483) 571281 ext 2265) or Dr J Kittler (tel (483) 509294). Applications in the form of a carriculum vitae (3 copies) including the names and addresses of two referees and a list of publications should be sent to the Personnel Office (JLC), University of Surrey, Guildford GU2 5XH, U. K., quoting reference 893 by 1 December 1989. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/18/89)
Vision-List Digest Fri Nov 17 15:52:33 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Rosenfeld's Computer Vision Bibliography online
Upcoming Conferences
Megaplus cameras and boundary tracing
Pseudocode for boundary tracking algorithms
Conference on pragmatics in AI
----------------------------------------------------------------------
Date: Mon, 13 Nov 89 13:23:26 PST
From: Vision-List-Request <vision@deimos.ads.com>
Subject: Rosenfeld's Computer Vision Bibliography online
Dr. Azriel Rosenfeld has been kind enough to provide on-line versions
of his outstanding bibliographies for Computer Vision and related
topics from 1984 to 1988 to the Vision List. Since the formatted text
for these bibliographies occupy about 1.25MB, I do not want to clog up
the net with them. Instead, I have placed them in the Vision List FTP
directory at ADS. Once anonymous FTP'ed to this account (described
below), these bibliographies may be found in
/pub/VISION-LIST-ARCHIVE/ROSENFELD-BIBLIOGRAPHIES . They may be
copied to your local site using the FTP 'get' command. Due to their
large size (about 225KB per year) and the labor required for me over
the large number of List subscribers, please note that I cannot mail
copies of these bibliographies to indivudal subscribers; FTP is the
only current access now available. Recommendations for alternative
distribution methods are invited, and these should be directed
directly to vision-list-request@ads.com.
I have also included the standard message mailed to new subscribers
which describes this list and how FTP access can be made. It is a
good idea to refloat this now and again.
I hope that Rosenfeld's comprehensive Computer Vision bibliography is a
valuable addition to your efforts in vision and image processing.
phil...
Subject: Welcome to Vision-List!
From: Vision-List moderator Phil Kahn <Vision-List-Request@ADS.COM>
The host site for the ARPAnet Vision List is Vision-List@ADS.COM for
list contributions, Vision-List-Request@ADS.COM for undistributed
correspondence. As the moderator, I am interested in stimulating
exchanges on research topics of significance to the vision community.
Here are a few administrative details about the list.
Requests
--------
If you have problems sending messages to the list, questions about
technical details of the list distribution, or the like, send mail to
Vision-List-Request@ADS.COM and we will respond personally to your
query.
PLEASE DO NOT send your request to be added to/deleted from the list
to Vision-List@ADS.COM. If you do, it may be automatically
redistributed as an article and appear in thousands of mailboxes around
the world. Always send these requests to the -Request address.
Submissions & Release Format
----------------------------
To submit an article to Vision-List, simply send it to:
Vision-List@ADS.COM
Submissions to the list are currently being delivered in a single batch
mailing once a week, on weeks when there is something to send. Caution:
the list moderator does not always edit the incoming messages before
they are redistributed. During those weeks, everything operates
automatically, with the attendant advantages and pitfalls. (If you fall
into one of those pits, please send me mail at Vision-List-Request and
we'll do our best to fix things up.)
The following details may help you in formatting and choosing appropriate
titles for your list submissions. Within a single release of
Vision-List, the format consists of an initial identifying header, a
list of topics covered in that release, and then each message as
received in chronological order, separated by dashed lines. Most of the
header information is automatically removed from each submission at
release time. When the software is working correctly, only "Date:",
"From:", and "Subject:" appear.
Archives
--------
Backissues of the Vision List Digest are available via anonymous FTP.
For those of you without FTP connection, limited backissues may be obtained
by mailing your request to Vision-List-Request@ADS.COM .
To access the Digest backissues from anonymous FTP:
1) FTP to ADS.COM
2) Login name is ANONYMOUS
3) Once you're logged on, change directory (cd) to
pub/VISION-LIST-ARCHIVE
4) Backissues are in the subdirectory BACKISSUES. Each file
contains an archived issue, and the file name is the date and
time the issue was created.
** ** ** ** ** **
The list is intended to embrace discussion on a wide range of vision
topics, including physiological theory, computer vision, machine
vision and image processing algorithms, artificial intelligence and
neural network techniques applied to vision, industrial applications,
robotic eyes, implemented systems, ideas, profound thoughts --
anything related to vision and its automation is fair game. I hope
you enjoy Vision-List.
Phil Kahn, moderator
Vision-List-Request@ADS.COM
------------------------------
Date: 17 Nov 89 9:11 -0800
From: John Ens <johne@ee.ubc.ca>
Subject: Upcoming Conferences
Does anybody have information on the following two conferences:
- Computer Vision and Pattern Recognition; and
- International Conference on Computer vision.
I am particularily interested in
- When and where the next conference is to be held; and
- When and to whom to submit papers.
Thanks,
John Ens johne@ee.ubc.ca
------------------------------
Date: Wed, 15 Nov 89 15:08:35 GMT
From: us214777@mmm.serc.3m.com (John C. Schultz)
Subject: Megaplus cameras and boundary tracing
Organization: 3M - St. Paul, MN 55144-1000 US
RE MEGAPLUS TO SUN:
Datacube, Inc (508) 535-6644 makes a whole line of VME bus based video rate
processing cards which amoung other things can acquire and display (on the SUN
display) Megaplus sized images and larger. You would need a MAXSCAN and
ROISTORE 2MB to acquire image data. Their connection to the Megaplus is
discussed in Datacube's Application Note MAX SC 011. The display board set is
called MAXVIEW and logically sits between the SUN cpu board video generator
and the SUN monitor. Setup parameters allow you to display real-time video in
this window assuming you have made the SUN cpu think that the window is black.
This system would be pretty expensive ($20,000) but if you would be satisfied
with VME bus transfer rates of video data the cost would be half that.
Another system is available from Perceptics (615) 966-9200 and runs on the
Nubus from a MAC II. If you have a MAC II with an Ethernet conection, this
would be a cheaper approach than purchasing the Datacube hardware but
obviously sending a lot of images over Ethernet from a MAC is going to take
awhile.
You might also try Recognition Concepts Inc (RCI) (702)831-0473 and Imaging
Technology Inc (617)938-8444
RE BOUNDARY TRACING:
Consider making a lookup table which outputs only the binary edge points and
then generate the (x,y) corrdinates of each boundary point. Software can then
do fancy processing such as shape descriptions etc. This approach would run
at video rates (30 times/sec) with appropriate hardware such as from
Datacube, Matrox, Perceptics, etc.
--
John C. Schultz EMAIL: jcschultz@mmm.3m.com
3M Company WRK: +1 (612) 733 4047
3M Center, Building 518-01-1 St. Paul, MN 55144-1000
The opinions expressed above are my own and DO NOT reflect 3M's
------------------------------
Date: Mon, 13 Nov 89 23:41:43 CST
From: shvaidya@uokmax.ecn.uoknor.edu (Shankar Vaidyanathan)
Subject: Re: Pseudocode for boundary tracking algorithms
Hi:
A request from Sridhar Balaji was relayed for pointers/pseudocode/code
for boudary tracking algorithms for binary images.
Since, I am also in need of them, I would be pleased to receive a copy of them
My E-mail address: shvaidya@uokmax.ecn.uoknor.edu
Address: 540 B Sooner Drive, Norman, Oklahoma 73072
Best Regards
Shankar
[ As usual, please post answer to questions of general interest to the List.
phil... ]
------------------------------
Date: 14 Nov 89 20:10:11 GMT
From: paul@nmsu.edu (Paul McKevitt)
Subject: CONFERENCE-ON-PRAGMATICS-IN-AI
Organization: NMSU Computer Science
CALL FOR PAPERS
Pragmatics in Artificial Intelligence
5th Rocky Mountain Conference on Artificial Intelligence (RMCAI-90)
Las Cruces, New Mexico, USA, June 28-30, 1990
PRAGMATICS PROBLEM:
The problem of pragmatics in AI is one of developing theories, models,
and implementations of systems that make effective use of contextual
information to solve problems in changing environments.
CONFERENCE GOAL:
This conference will provide a forum for researchers from all
subfields of AI to discuss the problem of pragmatics in AI.
The implications that each area has for the others in tackling
this problem are of particular interest.
ACKNOWLEDGEMENTS:
In cooperation with:
Association for Computing Machinery (ACM) (pending approval)
Special Interest Group in Artificial Intelligence (SIGART) (pending approval)
U S WEST Advanced Technologies and the Rocky Mountain Society
for Artificial Intelligence (RMSAI)
With grants from:
Association for Computing Machinery (ACM)
Special Interest Group in Artificial Intelligence (SIGART)
U S WEST Advanced Technologies and the Rocky Mountain Society
for Artificial Intelligence (RMSAI)
THE LAND OF ENCHANTMENT:
Las Cruces, lies in THE LAND OF ENCHANTMENT (New Mexico),
USA and is situated in the Rio Grande Corridor with the scenic
Organ Mountains overlooking the city. The city is
close to Mexico, Carlsbad Caverns, and White Sands National Monument.
There are a number of Indian Reservations and Pueblos in the Land Of
Enchantment and the cultural and scenic cities of Taos and Santa Fe
lie to the north. New Mexico has an interesting mixture of Indian, Mexican
and Spanish culture. There is quite a variation of Mexican and New
Mexican food to be found here too.
GENERAL INFORMATION:
The Rocky Mountain Conference on Artificial Intelligence is a
major regional forum in the USA for scientific exchange and presentation
of AI research.
The conference emphasizes discussion and informal interaction
as well as presentations.
The conference encourages the presentation of completed research,
ongoing research, and preliminary investigations.
Researchers from both within and outside the region
are invited to participate.
Some travel awards will be available for qualified applicants.
FORMAT FOR PAPERS:
Submitted papers should be double spaced and no more than 5 pages
long. E-mail versions will not be accepted.
Send 3 copies of your paper to:
Paul Mc Kevitt,
Program Chairperson, RMCAI-90,
Computing Research Laboratory (CRL),
Dept. 3CRL, Box 30001,
New Mexico State University,
Las Cruces, NM 88003-0001, USA.
DEADLINES:
Paper submission: March 1st, 1990
Pre-registration: April 1st, 1990
Notice of acceptance: May 1st, 1990
Final papers due: June 1st, 1990
LOCAL ARRANGEMENTS:
Jennifer Griffiths, Local Arrangements Chairperson, RMCAI-90.
(same postal address as above).
INQUIRIES:
Inquiries regarding conference brochure and registration form
should be addressed to the Local Arrangements Chairperson.
Inquiries regarding the conference program should be addressed
to the program Chairperson.
Local Arrangements Chairperson: E-mail: INTERNET: rmcai@nmsu.edu
Phone: (+ 1 505)-646-5466
Fax: (+ 1 505)-646-6218.
Program Chairperson: E-mail: INTERNET: paul@nmsu.edu
Phone: (+ 1 505)-646-5109
Fax: (+ 1 505)-646-6218.
TOPICS OF INTEREST:
You are invited to submit a research paper addressing Pragmatics
in AI , with any of the following orientations:
Philosophy, Foundations and Methodology
Knowledge Representation
Neural Networks and Connectionism
Genetic Algorithms, Emergent Computation, Nonlinear Systems
Natural Language and Speech Understanding
Problem Solving, Planning, Reasoning
Machine Learning
Vision and Robotics
Applications
Paul Mc Kevitt,
Computing Research Laboratory,
Dept. 3CRL, Box 30001,
New Mexico State University,
Las Cruces, NM 88003-0001, USA.
505-646-5109/5466
CSNET: paul@nmsu.edu
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/23/89)
Vision-List Digest Wed Nov 22 14:01:52 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Parallel Computers for Computer Vision
Bibliography: IEEE 1989 SMC Conference
6th Israeli AI & Vision Conference
----------------------------------------------------------------------
Date: Tue, 21 Nov 89 12:33:14 MEZ
From: Stefan Posch <posch@informatik.uni-erlangen.de>
Subject: Parallel Computers for Computer Vision
Return-Receipt-To: "Stefan Posch" <posch@informatik.uni-erlangen.de>
Hello,
I am looking for further material for a tutorial on
"Parallel Computers for Computer Vision" I plan to give next summer.
By computer vision I subsume here image processing, image
analysis as well as certain AI tasks.
To be more precise, I am interested in information/references
about/to:
- hardware architecture of parallel computers used/usefull for
computer vision
- software environment including programming languages,
communication primitives, mechanisms for data sharing
- applications, including speedup measurements and complexity estimation
My e-mail address is
RFC822: posch@informatik.uni-erlangen.de
UUCP: {pyramid,unido}!fauern!posch
X.400: <S=posch;OU=informatik;P=uni-erlangen;A=dbp;C=de>
Of cause I'll be happy to summarize to the net.
(How can I decide whether a summary is wanted or not?)
Thank you in advance, Stefan
Stefan Posch
Universitaet Erlangen-Nuernberg
Lehrstuhl 5 (Mustererkennung)
8520 Erlangen
West-Germany
------------------------------
Date: Mon, 20 Nov 89 14:54:39 EST
From: flynn@pixel.cps.msu.edu (Patrick J. Flynn)
Subject: Bibliography: IEEE 1989 SMC Conference
Here's a list of computer vision-related papers presented at the 1989
IEEE SMC conference in Cambridge on November 15-17. Apologies in
advance for any omissions; I tried to be liberal in my criteria for
deciding whether a paper is `computer vision-related' or not.
S. Grossberg, Recent Results on Neural Network Architectures
for Vision and Pattern Recognition, p. 1.
F. Arman, B. Sabata, and J.K. Aggarwal, Hierarchical Segmentation
of 3-D Range Images, pp. 156-161.
P. Flynn and A. Jain, CAD-Based Computer Vision: From CAD Models
to Relational Graphs, pp. 162-167.
C. Hansen, T. Henderson, and R. Grupen, CAD-Based 3-D Object
Recognition, pp. 168-172.
R. Hoffman and H. Keshavan, Evidence-Based Object Recognition
and Pose Estimation, pp. 173-178.
G. Medioni and P. Saint-Marc, Issues in Geometric Reasoning from
Range Imagery, pp. 179-185.
M. Trivedi, M. Abidi, R. Eason and R. Gonzalez, Object Recognition
and Pose Determination in Multi-Sensor Robotic Systems, pp. 186-193.
E. Feria, Predictive Transform for Optimum Digital Signal Processing,
pp. 1228-1237.
W. Wu and A. Kundu, A Modified Reduced Update Kalman Filter for
Images Degraded by Non-Gaussian Additive Noise, pp. 352-355.
C. Wright, E. Delp, and N. Gallagher, Morphological Based Target
Enhancement Algorithms to Counter the Hostile Nuclear Environment,
pp. 358-363.
R. Jha and M. Jernigan, Edge Adaptive Filtering: How Much and
Which Direction?, pp. 364-366.
B. Javidi, M. Massa, C. Ruiz, and J. Ruiz, Experiments on
Nonlinear Optical Correlation, pp. 367-369.
H. Arsenault, Similarity and Pathology in Neural Nets,
pp. 401-404.
E. Paek, J. Wullert, A. VonLehman, J. Patel, A. Sherer,
J. Harbison, H. Yu, and R. Martin, Vander Lugt Correlator
and Neural Networks, pp. 408-414.
B. Javidi, Optical Attentive Associative Memory with
Channel Dependent Nonlinearity in the Weight Plane,
pp. 415-420.
Z. Bahri and B. Vijaya Kumar, Design of Partial Information Filters
for Optical Correlators, pp. 421-426.
F. Palmieri and S. Shah, A New Algorithm for Training Multilayer
Perceptrons, pp. 427-428.
N. Nasarbadi, W. Li, B. Epranian and C. Butkus, Use of Hopfield
Network for Stereo Correspondence, pp. 429-432.
W. Owen, W. Hare, and A. Wang, The Role of the Bipolar Cell in
Retinal Signal Processing, pp. 435-442.
J. Troy and C. Enroth-Cugell, Signals and Noise in Mammalian
Retina, pp. 443-447.
R. Emerson, Linear and Nonlinear Mechanisms of Motion Selectivity
in Single Neurons of the Cat's Visual Cortex, pp. 448-453.
A. Dobbins and S. Zucker, Mean Field Theory and MT Neurons,
pp. 454-458.
M. Tuceryan and A. Jain, Segmentation and Grouping of Object
Boundaries, pp. 570-575.
Y. Shui and S. Ahmad, 3-D Location of Circular and Spherical
Features by Monocular Model-Based Vision, pp. 576-581.
M. Chantler and C. Reid, Integration of Ultrasonic and Vision
Sensors for 3-D Underwater Scene Analysis, pp. 582-583.
H. Fujii and T. Inui, Modelling the Spatial Recognition
Process in a Computer-Generated 3-D World, pp. 584-585.
C. Chang and S. Chatterjee, Depth from Stereo Image Flow,
pp. 586-591.
R. Safae-Rad, B. Benhabib, K. Smith, and Z. Zhou, Pre-Marking Methods
for 3D Object Recognition, pp. 592-595.
C. Bandera and P. Scott, Foveal Machine Vision Systems, pp. 596-599.
J. Kottas and C. Warde, Trends in Knowledge Base Processing Using
Optical Techniques, pp. 1250-1257.
J. Horner, Variations of the Phase-only Filter, p. 644 (abstract)
D. Gregory, J. Kirsch, and W. Crowe, Optical Correlator Guidance
and Tracking Field Tests, pp. 645-650.
Y. Fainman, L. Feng, and Y. Koren, Estimation of Absolute Spatial
Position of Mobile Systems by Hybrid Opto-Electronic Processor,
pp. 651-657.
T. Lu, X. Xu, and F. Yu, Hetero Associative Neural Network
Pattern Recognition, pp. 658-663.
M. Oguztoreli, Neural Computations in Visual Processes, pp. 664-670.
M. Jernigan, R. Belshaw, and G. McLean, Image Enhancement with
Nonlinear Local Interactions, pp. 676-681.
R. Pinter, R. Olberg, and E. Warrant, Luminance Adaptation of
Preferred Object Size in Identified Dragonfly Movement
Detectors, pp. 682-686.
A. Meyer, Z. Li, E. Haupt, K. Lu, and H. Louis, Clinical
Electrophysiology of the Eye: Physiological Modeling
and Parameter Estimation, pp. 687-692.
S. Levine and J. Kreifeldt, Minimal Information for the Unique
Representation of a Pattern of Points, pp. 828-830.
N. Ansari and E. Delp, Partial Shape Recognition: A Landmark-Based
Approach, pp. 831-836.
T. Fukuda and O. Hasegawa, Creature Recognition and Identification by
Image Processing Based on Expert System, pp. 837-842.
Y. Shiu and S. Ahmad, Grouping Image Features into Loops for
Monocular Recognition, pp. 843-844.
T. Matsunaga, A. Tokumasu, and O. Iwaki, A Study of Document
Format Identification Based on Table Structure, pp. 845-846.
T. Topper and M. Jernigan, On the Informativeness of Edges,
pp. 909-914.
C. Choo and H. Freeman, Computation of Features of 2-D Polycurve-Encoded
Boundaries, pp. 1041-1047.
A. Gross and T. Boult, Straight Homogeneous Generalized Cylinders,
Analysis of Reflectance Properties and a Necessary Condition for
Class Membership, pp. 1260-1267.
W. Yim and D. Joo, Surface Contour Mapping Using Cross-Shaped
Structured Light Beam, pp. 1048-1050.
A. Perry and D. Lowe, Segmentation of Non-random Texture Regions
in Real Images, pp. 1051-1054.
S. Lee and J. Pan, Tracing and Representation of Human Line
Drawings, pp. 1055-1061.
T. Taxt, P. Flynn, and A. Jain, Segmentation of Document Images,
pp. 1062-1067.
K. Yokosawa, Human-Based Character String Image Retrieval from Textual
Images, pp. 1068-1069.
S. Lee, Classification of Similar Line-Drawing Patterns with Attributed
Graph Matching, pp. 1070-1071.
That's all for now. Next week, I'll try to send citations from the 3-D
scene interpretation workshop in Austin, Texas.
Pat
------------------------------
Date: Mon, 20 Nov 89 15:46:36 +0200
From: hezy%TAURUS.BITNET@CUNYVM.CUNY.EDU
Comments: If you have trouble reaching this host as math.tau.ac.il
Please use the old address: user@taurus.bitnet
Subject: 6th Israeli AI & Vision Conference
Preliminary Program for the Sixth Israel Conference on
Artificial Intelligence and Computer Vision
Monday, 25 December 1989
18:00 Reception, Kfar Hamaccabiyah
AI TRACK:
Tuesday, 26 December 1989
9:00-10:30
Keynote Speaker --- Nils Nilsson, Stanford University, USA
Session 1.1
11:00-13:00
"On Learning and Testing Evaluation Functions"
B. Abramson, University of Southern California, USA
"Analogical Learning: A Cognitive Theory"
B. Adelson, Tufts University, USA
"An Expert System for Computer Aided Design of Man-Machine Interface"
D. Tamir, A. Kandel, Florida State University, USA
Session 1.3
14:15-15:15
"Why Can't I Smear Paint at the Wall"
M. Brent, Massachusetts Institute of Technology, USA
"Resolution of Lexical Synonymy at the Word Level"
S. Nirenburg, E. Nyberg, Carnegie Mellon University, USA
Session 1.3B
14:15-15:15
"From Local to Global Consistency in Constraint Networks:
Some New Results"
R. Dechter, The Technion, Israel
"Principles of Knowledge Representation and Reasoning in the
FRAPPE System"
Y. Feldman, Weizmann Institute of Science, Israel
C. Rich, Massachusetts Institute of Technology, USA
Session 1.5
15:30-17:00
"Multi-Agent Autoepistemic Predicate Logic"
Y. Jiang, Cambridge University, England
"A Framework for Interactions Among Agents of Disparate Capabilities"
O. Kliger, Weizmann Institute of Science, Israel
J. Rosenschein, Hebrew University of Jerusalem, Israel
"Function Characteristics System: An ITS for Integrating Algebraic and
Graphical Activities in Secondary School Mathematics"
N. Zehavi, B. Schwarz, A. Evers, Weizmann Institute of Science, Israel
Session 1.5B
15:30-17:00
"Intelligent Decision Support in Quasi-Legal Domains"
U. Schild, Bar-Ilan University, Israel
"Model Analysis in Model Based Diagnosis"
A. Abu-Hanna, R. Benjamins, University of Amsterdam, The Netherlands
"Planning in TRAUMAID"
R. Rymon, J. Clarke, B. Webber, University of Pennsylvania, USA
Wednesday, 27 December 1989
9:30-10:30
Keynote Speaker --- Bonnie Webber, University of Pennsylvania, USA
Session 2.1
11:00-13:00
"Corpus-Based Lexical Acquisition for Translation Systems"
J. Klavans, E. Tzoukermann, IBM Research, USA
"CARAMEL: A Flexible Model for Interaction between the Cognitive
Processes Underlying Natural Language Understanding"
G. Sabah, L. Nicaud, C. Sauvage, LIMSI, France
"Zihui Mishkalo Shel Shir b'Machshev"
U. Ornan, The Technion, Israel
"A Polymorphic Type Checking System for Prolog in HiLog"
T. Fruhwirth, SUNY, USA
Session 2.2
14:15-15:15
Invited Speaker --- Saul Amarel, Rutgers University, USA
"AI in Design"
Session 2.3
15:30-17:00
"A Model and a Prototype for a Knowledge-Base System for Graphic
Objects"
E. Naphtalovitch, E. Gudes, J. Addess, A. Noyman,
Ben-Gurion University of the Negev, Israel
"Rule Based Expert Systems Which Learn to Solve Problems Quicker"
D. Berlin, M. Schneider, Florida Institute of Technology, USA
"A System for Incremental Learning Based on Algorithmic Probability"
R. Solomonoff, Oxbridge Research, USA
VISION TRACK
Tue, December 26
Session 1.2
11:00 - 13:00 Keynote speaker:
P. Burt, David Sarnoff Research Center, USA
Dynamic Analysis of Image Motion
M. Costa, R.M. Haralick, L.G. Shapiro, University of Washington, USA
Optimal affine- invariant point matching
Session 1.4
14:15-15:15
S. negahdaripour & A. Shokrollahi, University of Hawaii, USA
Relaxing the brightness constancy assumption in computing optical flow
D. Keren, S. Peleg, A. Shmuel, Hebrew University, Israel
Accurate hierarchical estimation of optical flow
Session 1.6
15:30-17:00
D. Hung & O.R. Mitchell, New Jersey Institute of Technology, USA
Scaling invariant recognition of medium resolution, partially occluded objects
D. Keren, R. Marcus, M. Werman, Hebrew University
Segmenting and compressing waveforms by minimum length encoding
K. B. Thornton & L.G. Shapiro, University of Washington, USA
Image matching for view class construction
Wed, December 27
Session 2.5
9:15- 10:15 Keynote speaker
R. Bajcsy, University of Pennsylvania, USA
Perception via Active Exploration Examples of Disassembly
Hall 1
Session 2.6
10:45-12:45
H. Rom & S. Peleg, Hebrew University
Motion based segmentation of 2D scenes
S. Levy Gazit & G. Medioni, University of Southern California, USA
Multi scale contour matching in a motion sequence
Y. Pnueli, N.Kiryati, A. Bruckstein, Technion, Israel
On Navigation in moving influence fields
A. Meizles & R. Versano, Ben Gurion University, Israel
A multiresolution view of token textures
Session 2.7
14:15-15:15
S. Shimomura, Fujifacom Corporation, Japan
An application of high speed projecion module to document understatnding
N. Kiryati & A. Bruckstein, Technion, Israel
Efficient shape recognition by a probabilistic generalized hough transform
Session 2.8
15:30-17:00
A. Shmuel & M. Werman, Hebrew University, Israel
Active vision: 3D depth from an image sequence
F.Y. Shih and O.R.Mitchell, New Jersey Institute of Technology, USA
Euclidean distance based on grey scale morphology
D. Sherman & S. Peleg, Hebrew University, Israel
Stereo by incremental matching of contours
Hall 2
Session 3.1
10:45-12:45
M. Lindenbaum & A.Bruckstein, Technion, Israel
Geometric probing using composite probes
F.Y. Shih & C.S. Prathuri, New Jersey Institute of Technology, USA
Shape extraction from size histogram
M. Irani & S. Peleg, Hebrew University, Israel
Super resolution from image sequences
G. Ron & S. Peleg, Hebrew University, Israel
Linear shape from shading
Session 3.2
14:15-15:15
N. gershon, J. Cappelleti, S. Hinds, MITRE Corporation, USA
3D image processing, segmentation and visualization of PET brain images
V.F. Leavers, Kings College, England
Use of the Radon transform as a method of extracting information about
shape in 2D
Session 3.3
15:30-17:00
E. Shavit & J. Tsotsos, University of Toronto, Canada
A Prototype for intermediate level visual processing: A motion hierarchy as
a case study
D. Chetverikov, Computer Institute, Hungary
A data structure for fast neighborhood search in points set
D. Sher, E. Chuang, R. Venkatesan, SUNY Buffalo, USA
Generating object location systems from complex object descriptions
The Sixth Israeli Symposium on Artificial Intelligence
Vision and Pattern Recognition
December 26-27, 1989
Registration information from:
IPA --- Information Processing Association of Israel,
Kfar Hamaccabiah
Ramat Gan 52109
Israel
Phone: (972)-3-715772
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/07/89)
Vision-List Digest Wed Dec 06 10:34:59 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
We need "real world" images.
Program For Realistic Images Wanted
MATLAB
Accuracy measure
RE:Boundary tracking algorithms..
Computer Vision Position
Post-Doctoral Research Fellowship
New Journal: Journal of Visual Communication and Image Representation
Boundary Tracking -----> (collected Information).
Bibliography: 3D Scene Interp. Workshop (Austin, TX)
----------------------------------------------------------------------
Date: 27 Nov 89 19:48:16 GMT
From: rasure@borris.unm.edu (John Rasure)
Subject: We need "real world" images.
Organization: University of New Mexico, Albuquerque
We need images. Specifically, we need stereo pair images, fly by image
sequences, LANDSAT images, medical images, industrial inspection images,
astronomy images, images from lasers, images from interferometers, etc.
The best images are those that correspond to a "typical" image processing
problems of today. They need not be pleasing to look at, just representative
of the imaging technique and sensor that is being used.
Does anybody have such images that they can share?
John Rasure
rasure@bullwinkle.unm.edu
Dr. John Rasure
Department of EECE
University of New Mexico
Albuquerque, NM 87131
505-277-1351
NET-ADDRESS: rasure@bullwinkle.unm.edu
------------------------------
Date: Wed, 29 Nov 89 11:25:37 +0100
From: sro@steks.oulu.fi (Sakari Roininen)
Subject: Program For Realistic Images Wanted
We are preparing research project in the field of visual
inspection. In our research work we want to compute and simulate
highly realistic images.
Key words are: Shading - Illumination
We are looking for a software package including following
properties (modules):
- Geometric description of objects.
- Optical properties of the surfaces. Surfaces of interest are:
metal, wood, textile.
- Physical and geometrical description of the light sources.
- Physical and technological properties of the cameras.
Software should be written in C and source code should be
available so that we can customize the software to fit our
applications.
GOOD IDEAS ARE ALWAYS WELCOME !!!
Please, contact: Researcher Timo Piironen
Technical Research Centre of Finland
Electronics Laboratory
P.O.Box 200
SF-90571 OULU
Finland
tel. +358 81 509111
Internet: thp@vttko1.vtt.fi
------------------------------
Date: 1 Dec 89 18:00:26 GMT
From: Adi Pranata <pranata@udel.edu>
Subject: MATLAB
Hi,
I'm not sure where to posted this question, anyway Does any one
have any info, on convert raster images/picture to matlab matrix
format, since i am interested on use the matlab software to manipulate
it . Since it will be no problem to display the matlab file format
using the imagetool software. Any info including what other newsgroup
more appropriate to posted will be welcome. Thanks in advance.
You could reply to pranata@udel.edu
Sincerely,
Desiderius Adi Pranata
PS: Electromagnetig way
146.955 Mhz -600 KHz
Oldfashioned way
(302)- 733 - 0990
(302)- 451 - 6992
[ This is definitely appropriate for the Vision List. Answers to the
List please.
phil...]
------------------------------
Date: 2 Dec 89 17:41:18 GMT
From: muttiah@cs.purdue.edu (Ranjan Samuel Muttiah)
Subject: Accuracy measure
Organization: Department of Computer Science, Purdue University
I am looking for the various ACCURACY measures that are used in the
vision field. If you have any information on this, could you
email/post please ?
Thank you.
------------------------------
Date: Wed, 29 Nov 89 18:47:24 EST
Subject: RE:Boundary tracking algorithms..
From: Sridhar Ramachandran <Sridhar@UC.EDU>
I have pseudo code for a Boundary Tracking Algorithm for Binary
Images that uses Direction codes and Containment codes to track
the boundary. It is pretty efficient and works fine.
If interested, please e-mail requests to sramacha@uceng.uc.edu
(OR) sridhar@uc.edu (OR) sramacha@uc.edu.
Sridhar Ramachandran.
------------------------------
Date: Tue, 5 Dec 89 14:08:30 EST
From: peleg@grumpy.sarnoff.com (Shmuel Peleg x 2284)
Subject: Computer Vision Position - David Sarnoff Research Center
The computer vision research group at David Sarnoff Research Center has an
opening for a specialist in image processing or computer vision who has an
interest in computer architecture and digital hardware. Master's level or
equivalent experience is preferred.
This is a key position in an established research team devoted to the
development of high performance, real-time vision systems. The group is active
at all levels of research and development from basic research to applications
and prototype implementation. Current programs include object recognition,
motion analysis, and advanced architecture.
Please send your vitae or enquire with Peter Burt (Group Head), David Sarnoff
Research Center, Princeton, NJ 08543-5300; E-Mail: burt@vision.sarnoff.com.
------------------------------
Date: Wed, 29 Nov 89 19:11:55 WET DST
From: "D.H. Foster" <coa15%seq1.keele.ac.uk@NSFnet-Relay.AC.UK>
Subject: Post-Doctoral Research Fellowship
UNIVERSITY OF KEELE
Department of Communication & Neuroscience
POST-DOCTORAL RESEARCH FELLOWSHIP
Applications are invited for a 3-year appointment as a post-doctoral
research fellow to work in the Theoretical and Applied Vision Sciences
Group. The project will investigate early visual form processing, and
will entail a mixture of computational modelling and psychophysical
experiment. The project is part of an established programme of
research into visual information processing, involving a team of about
ten members working in several well-equipped laboratories with a range
of computing and very high resolution graphics display systems.
Candidates should preferably be experienced in computational vision
research, but those with training in computing science, physics,
experimental psychology, and allied disciplines are also encouraged to
apply. The appointment, beginning 1 January 1990, or soon thereafter,
will be on the Research IA scale, initially up to Point 5, depending
on age and experience.
Informal enquiries and applications with CV and the names of two
referees to Prof David H. Foster, Department of Communication &
Neuroscience, University of Keele, Keele, Staffordshire ST5 5BG,
England (Tel. 0782 621111, Ext 3247; e-mail D.H.Foster@uk.ac.keele).
------------------------------
Date: Thu, 23 Nov 89 16:48:13 EST
From: zeevi@caip.rutgers.edu (Joshua Y. Zeevi)
Subject: New Journal: Journal of Visual Communication and Image Representation
New Journal published by Academic Press
---------------------------------------
Dear Colleague,
The first issue of the Journal of Visual Communication and Image Representation
is scheduled to appear in September 1990. Since the journal will cover topics
in your area of expertise, your contribution will most likely have impact on
future advancements in this rapidly developing field.
Should you have questions regarding the suitability of a specific paper or
topic, please get in touch with Russell Hsing or with me. The deadline for
submission of papers for the first issue is Feb. 15, and for the second issue
May 15, 1990.
For manuscript submission and/or subscirption information please write or call
Academic press, Inc. 1250 6th Ave., San Diego, CA 92101. (619) 699-6742.
Enclosed please find the Aims & Scope (including list of preferred topics) and
list of members of the the Editorial Board.
JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
--------------------------------------------------------
Dr. T. Russell Hsing, co-editor, Research Manager, Loop Transmission &
Application District, Bell Communication Research, 445 South Street,
Morristown, NJ 07960-1910 (trh@thumper.bellcore.com (201) 829-4950)
Professor Yehoshua Y. Zeevi*, co-editor, Barbara and Norman Seiden Chair,
Department of Electrical Engineering, Technion - Israel Ins. of Technology,
Haifa, 32 000, Israel
* Present address: CAIP Center, Rutgers University, P. O. Box 1390,
Piscataway, NJ 08855-1390 (zeevi@caip.rutgers.edu (201) 932-5551)
AIMS & SCOPE
The Journal of Visual Communication and Image Representation is an archival
peer-reviewed technical journal, published quarterly. With the growing
availability of optical fiber links, advances of large scale integration, new
telecommunication services, VLSI-based circuits and computational systems, as
well as the rapid advances in vision research and image understanding, the
field of visual communication and image representation will undoubtedly
continue to grow. The aim of this journal is to combine reports on the state-
of-the-art of visual communication and image representation with emphasis on
novel ideas and theoretical work in this multidisciplinary area of pure and
pure and applied research. The journal consists of regular papers and research
reports describing either original research results or novel technologies. The
field of visual communication and image representation is considered in its
broadest sense and covers digital and analog aspects, as well as processing and
communication in biological visual systems.
Specific areas of interest include, but are not limited to, all aspects of:
* Image scanning, sampling and tessellation
* Image representation by partial information
* Local and global schemes of image representation
* Analog and digital image processing
* Fractals and mathematical morphology
* Image understanding and scene analysis
* Deterministic and stochastic image modelling
* Visual data reduction and compression
* Image coding and video communication
* Biological and medical imaging
* Early processing in biological visual systems
* Psychophysical analysis of visual perception
* Astronomical and geophysical imaging
* Visualization of nonlinear natural phenomena
Editorial Board
R. Ansari, Bell Communications Research, USA
I. Bar-David, Technion - Israel Institute of Technology, Israel
R. Bracewell, Stanford University, USA
R. Brammer, The Analytic Sciences Corporation, USA
J.-O. Eklundh, Royal Institute of Technology, Sweden
H. Freeman, Rutgers University, USA
D. Glaser, University of California at Berkeley, USA
B. Julesz, Caltech and Rutgers University, USA
B. Mandelbrot, IBM Thomas J. Watson Research Center, USA
P. Maragos, Harvard University, USA
H.-H Nagel, Fraunhofer-Institut fur Informations-und Datenverbeitung, FRG
A. Netravali, AT&T Bell Labs, USA
D. Pearson, University of Essex, England
A. Rosenfeld, University of Maryland, USA
Y. Sakai, Tokyo Institute of Technology, Japan
J. Sanz, IBM Almaden Research Center, USA
W. Schreiber, Massachusetts Institute of Technology, USA
J. Serra, Ecole Nationale Superieure des Mines de Paris, France
M. Takagi, University of Tokyo, Japan
M. Teich, Columbia University, USA
T. Tsuda, Fujitsu Laboratories Ltd., Japan
S. Ullman, Massachusetts institute of technology, USA
H. Yamamoto, KDD Ltd., Japan
Y. Yasuda, University of Tokyo, Japan
------------------------------
Date: Mon, 27 Nov 89 16:48 EDT
From: SRIDHAR BALAJI <GRX0446@uoft02.utoledo.edu>
Subject: Boundary Tracking -----> (collected Information).
X-Vms-To: IN%"Vision-List@ADS.COM"
Status: RO
/** This are some refs. and psedocode for the Boundary tracking I asked.
** Thanks so much for all the contributors. Since so many
** wanted this. I thought it may be useful to send it to the group.
S. Balaji */
*******
From: IN%"marra@airob.mmc.COM" 14-NOV-1989 15:28:27.22
CC:
Subj: Re: Boundary tracking.
Here is Pascal-pseudo code for our binary boundary tracker. A minor mod will
extend it to handle multiple objects. Good luck.
Pseudo Code for the ALV border tracing module
Program pevdcrok ( input,output );
(* include csc.si TYPE and VAR declarations *)
(* this causes declaration of the following data elements:
dir_cue
version
V_IM
O_IM
PB
*)
(* include peve.si TYPE and VAR declarations
the following are defined in peve.si:
pevdcrok_static_block.dc
pevdcrok_static_block.dc
*)
(* ____________________FORWARD DECLARATIONS____________________ *)
(* ----------OURS---------- *)
(* ----------THEIRS-------- *)
procedure pevdcrok(road,obst:imagenum)
TYPE
border_type_type = (blob,bubble)
direction_type = (north,south,east,west)
VAR
inside_pix : d2_point; (* Col,row location of a pixel on
the inside of a border *)
outside_pix : d2_point; (* Col,row location of a pixel on
the outside of a border *)
next_pix : d2_point; (* Col,row location of the next
pixel to be encountered during
the tracing of the border *)
next_8_pix : d2_point; (* Col,row location of the next
eight-neighbor pixel to be
encountered during the tracing of
the border *)
westmost_pix : d2_point; (* col,row location of the westmost
pixel visited so far this image *)
eastmost_pix : d2_point; (* col,row location of the eastmost
pixel visited so far this image *)
northmost_pix : d2_point; (* col,row location of the northmost
pixel visited so far this image *)
southmost_pix : d2_point; (* col,row location of the southmost
pixel visited so far this image *)
border_type : border_type_type; (* a processing control flag
indicating the type of border
assumed to be following *)
direction : direction_type; (* directions being searched *)
start_time,
end_time,
print_time : integer; (* recorded times for time debug *)
procedure find_border(inside_pix,outside_pix,direction)
begin (* find_border *)
Set a starting point for finding blob in the middle
of the bottom of the image
if PB.D[pevdcrok,gra] then
mark the starting point
Search in direction looking for some blob, being sure you
don't go off the top of the road image
Search in direction looking for a blob/non-blob boundary,
being sure you don't go off the top of the blob image
if PB.D[pevdcrok,gra] then
mark the inside_pix and the outside_pix
end (* find_border *)
procedure trace_border(border_type,inside_pix,outside_pix,direction)
TYPE
dir_type = (0..7); (* 0 = east
1 = northeast
2 = north
3 = northwest
4 = west
5 = southwest
6 = south
7 = southeast *)
VAR
dir : dir_type; (* relative orientation of the inside_pix
outside_pix 2-tuple *)
begin (* trace_border *)
remember the starting inside and outside pix's for bubble detection
set dir according to direction
while we haven't found the end of this border do
begin (* follow border *)
next_pix.col := outside_pix.col + dc[dir];
next_pix.row := outside_pix.row + dr[dir];
while road.im_ptr^[next_pix.col,next_pix.row] = 0 do
begin (* move the outside pixel clockwise *)
outside_pix = next_pix;
advance the dir
check for bubbles; if a bubble then
begin (* bubble has been found *)
border_type := bubble
exit trace_border
end (* bubble has been found *)
next_pix.col := outside_pix.col + dc[dir];
next_pix.row := outside_pix.row + dr[dir];
end (* move the outside pixel clockwise *)
update the direction for moving inside_pix
next_pix.col := inside_pix.col + dc[dir];
next_pix.row := inside_pix.row + dr[dir];
next_8_pix.col := inside_pix.col + dc[dir];
next_8_pix.row := inside_pix.row + dr[dir];
while road.im_ptr^[next_pix.col,next_pix.row] = 0 or
(road.im_ptr^[next_8_pix.col,next_8_pix.row] = 0
and mod(dir,2) = 0) do
begin (* move the inside pixel counter-clockwise *)
inside_pix := next_pix;
advance the dir
if road.im_ptr^[inside_pixel.col,inside_pixel.row] <> 0 then
begin
inside_pix := next_8_pix;
advance the dir;
end;
check for bubbles; if a bubble then
begin (* bubble has been found *)
border_type := bubble
exit trace_border
end (* bubble has been found *)
next_pix.col := outside_pix.col + dc[dir];
next_pix.row := outside_pix.row + dr[dir];
end (* move the inside pixel counter-clockwise *)
update the direction for moving outside_pix
update values of westmost_pix,eastmost_pix,northmost_pix,
southmost_pix
if mod(num_border_points,crock_rec.boundary_skip) = 1 then
record column and row values in V_IM.edge_record
end (* follow border *)
border_type := blob
end (* trace_border *)
begin (* pevdcrok *)
if PB.D[pevdcrok,time] then
clock(start_time);
AND the road image with the border image, leaving the
result in road image
border_type := bubble
while border_type = bubble do
begin
if PB.D[pevdcrok,tty]
writeln('PEVDCROK: Calling find_border');
find_border(inside_pix,outside_pix,west)
initialize IM edge_record; num_border_points := 0
if PB.D[pevdcrok,tty]
writeln('PEVDCROK: Calling trace_border');
trace_border(border_type,inside_pix,outside_pix,west)
end
complete IM edge_record
if PB.D[pevdcrok,time] then
begin (* time debug *)
clock(end_time);
print_time := end_time - start_time;
writeln('PEVDCROK: elapsed time = ',print_time,' msec');
end; (* time debug *)
end (* pevdcrok *)
*******
From: IN%"mv10801@uc.msc.umn.edu" 14-NOV-1989 16:04:34.13
CC:
Subj: Re: Motion tracking
See:
J.A.Marshall, Self-Organizing Neural Networks for Perception of Visual Motion,
to appear in Neural Networks, January 1990.
*******
From: IN%"pell@isy.liu.se" "P{r Emanuelsson" 15-NOV-1989 13:24:37.17
CC:
Subj: Re: Boundary tracking.
I think you want to do chain-coding. The best method I know was invented
by my professor (of course...) and is called "crack coding". It uses
a two-bit code and avoids backtracking problems and such. It's quite
easy to implement, but I don't think I have any code handy.
The algorithm is, however, given as flow charts in the second reference:
"Encoding of binary images by raster-chain-coding of cracks", Per-Erik
Danielsson, Proc. of the 6th int. conf. on Pattern Recognition, Oct. -82.
"An improved segmentation and coding algorithm for binary and
nonbinary images", Per-Erik Danielsson, IBM Journal of research and
development, v. 26, n. 6, Nov -82.
If you are working on parallel computers, there are other more suitable
algorithms.
Please summarize your answers to the vision list.
Cheers,
/Pell
Dept. of Electrical Engineering pell@isy.liu.se
University of Linkoping, Sweden ...!uunet!isy.liu.se!pell
------------------------------
Date: Thu, 30 Nov 89 13:20:28 EST
From: flynn@pixel.cps.msu.edu
Subject: Bibliography: 3D Scene Interp. Workshop (Austin, TX)
Here's a list of papers in the proceedings of the IEEE Workshop on
Interpretation of 3D Scenes held in Austin, Texas on November 27-29.
STEREO
------
R.P. Wildes, An Analysis of Stereo Disparity for the Recovery of
Three-Dimensional Scene Geometry, pp. 2-8.
S. Das and N. Ahuja, Integrating Multiresolution Image Acquisition and
Coarse-to-Fine Surface Reconstruction from Stereo, pp. 9-15.
S.D. Cochran and G. Medioni, Accurate Surface Description from Binocular
Stereo, pp. 16-23.
SHAPE FROM X
------------
R. Vaillant and O.D. Faugeras, Using Occluding Contours for Recovering
Shape Properties of Objects, pp. 26-32.
P.K. Allen and P. Michelman, Acquisition and Interpretation of 3D Sensor
Data from Touch, pp. 33-40.
P. Belluta, G. Collini, A. Verri, and V. Torre, 3D Visual Information
from Vanishing Points, pp. 41-49.
RECOGNITION
-----------
R. Kumar and A. Hanson, Robust Estimation of Camera Location and
Orientation from Noisy Data Having Outliers, pp. 52-60.
J. Ponce and D.J. Kriegman, On Recognizing and Positioning Curved 3D
Objects from Image Contours, pp. 61-67.
R. Bergevin and M.D. Levine, Generic Object Recogfnition: Building
Coarse 3D Descriptions from Line Drawings, pp. 68-74.
S. Lee and H.S. Hahn, Object Recognition and Localization Using
Optical Proximity Sensor System: Polyhedral Case, pp. 75-81.
MOTION
------
Y.F. Wang and A. Pandey, Interpretation of 3D Structure and Motion Using
Structured Lighting, pp. 84-90.
M. Xie and P. Rives, Towards Dynamic Vision, pp. 91-99.
ASPECT GRAPHS
-------------
D. Eggert and K. Bowyer, Computing the Orthographic Projection Aspect
Graph of Solids of Revolution, pp. 102-108.
T. Sripradisvarakul and R. Jain, Generating Aspect Graphs for Curved
Objects, pp. 109-115.
D.J. Kriegman and J. Ponce, Computing Exact Aspect Graphs of Curved Objects:
Solids of Revolution, pp. 116-121.
SURFACE RECONSTRUCTION
----------------------
C.I. Connolly and J.R. Stenstrom, 3D Scene Reconstruction from Multiple
Intensity Imagesm pp. 124-130.
R.L. Stevenson and E.J. Delp, Invariant Reconstruction of Visual Surfaces,
pp. 131-137.
P.G. Mulgaonkar, C.K. Cowan, and J. DeCurtins, Scene Description Using Range
Data, pp. 138-144.
C. Brown, Kinematic and 3D Motion Prediction for Gaze Control, pp. 145-151.
3D SENSING
----------
M. Rioux, F. Blais, J.-A. Beraldin, and P. Boulanger, Range Imaging Sensors
Development at NRC Laboratories, pp. 154-159.
REPRESENTATIONS
---------------
A. Gupta, L. Bogoni, and R. Bajcsy, Quantitative and Qualitative Measures
for the Evaluation of the Superquadric Models, pp. 162-169.
F.P. Ferrie, J. Lagarde, and P. Whaite, Darboux Frames, Snakes, and
Super-Quadrics: Geometry from the Bottom-Up, pp. 170-176.
H. Lu, L.G. Shapiro, and O.I. Camps, A Relational Pyramid Approach to View
Class Determination, pp. 177-183.
APPLICATIONS
------------
I.J. Mulligan, A.K. Mackworth, and P.D. Lawrence, A Model-Based Vision System
for Manipulator Position Sensing, pp. 186-193.
J.Y. Cartoux, J.T. Lapreste, and M. Richetin, Face Authentification or
Recognition by Profile Extraction from Range Images, pp. 194-199.
J.J. Rodriguez and J.K. Aggarwal, Navigation Using Image Sequence Analysis
and 3-D Terrain Matching, pp. 200-207.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/09/89)
Vision-List Digest Fri Dec 08 10:00:41 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re:MATLAB
Images Wanted
Submission to vision list
Re: MATLAB
----------------------------------------------------------------------
Date: Thu, 7 Dec 89 12:25:16 EST
Subject: Re:MATLAB
From: Sridhar Ramachandran <Sridhar@UC.EDU>
Hi,
Regarding Pranata's article on Matlab.
I am not sure about the Matlab Matrix file format, but if it is
an ASCII file, then you can write a small C program that converts
your Image file (binary, usually) to an ASCII text file that MATLAB
can use.
As mentioned, there is a large body of software, going under
the name of "Video Utilities", that do the reverse ie., convert
any format to raster format.
Sridhar Ramachandran.
Knowledge-Based Computer Vision Lab,
University of Cincinnati.
Replies to: Sridhar@UC.EDU || sramacha@uceng.uc.edu
------------------------------
Date: 7 Dec 89 10:02 -0800
From: <tate@cs.sfu.ca>
Subject: Images Wanted
We are doing research on the combination of laser and intensity imagery and
are looking for registered images of all levels of quality. Can anyone help
us out? Thanks in advance.
Kevin Tate
Dept. of Computing Sciences
Simon Fraser University
Burnaby, B.C.
V5A-1S6
e-mail: tate@cs.sfu.ca
[ As usual, please post answers to the List. These types of questions are of
particular interest to the readership.
phil... ]
------------------------------
Date: Thu, 07 Dec 89 12:28:19 PST
From: rossbach%engrhub@hub.ucsb.edu
Subject: Books from Springer-Verlag
Springer Series in Perception Engineering
A Book Series from Springer-Verlag Publishers edited by Ramesh C. Jain
For Information on any of the books in this series, please send email to
rossbach@hub.ucsb or call 1-800-SPRINGER.
Perception is the process of interpreting information gathered from a
variety of sensors. As a complex set of physiological functions it plays a
vital role in our life.
In recent years, the RbiologicalS concept of perception has beem extended
to artificial perception systems. In manufacturing, productivity and quality
are being significantly improved using machine perception. Perception systems
in medicine are improving diagnostic procedures and the ability to monitor
patients. The role of robots in hazardous environments and in space is
expanding. The success of automated machinery depends critically on systems
with the ability to both sense and understand the environment and determine
appropriate action.
In the last decade, research on perception systems has received
significant attention but, unfortunately, the progress in applications has been
slow. A lack of communication between researchers and practitioners, and, more
fundamentally, the lack of a well defined discipline of RPerception
EngineeringS has created a gap between the theoretical work on perception
systems and application oriented work.
In order to realize the factories, homes, hospitals, and offices of the
future, this gap needs to be bridged. Books in the Springer Series in
Perception Engineering will emphasize not only the rigorous theoretical and
experimental characterization of perception but also the engineering, design,
and application aspects of perception systems.
Published in the series:
Paul J. Besl: Surfaces in Range Image Understanding
ISBN 96773-7 $58.00
Jorge L. C. Sanz (ed.): Advances in Machine Vision
ISBN 96822-9 $79.00
R. C. Vogt: Automatic Generation of Morphological Set Recognition
Algorithms
ISBN 97049-5 $79.00
E. P. Krotkov: Active Computer Vision by Cooperative Focus and Stereo
ISBN 97103-3 $49.00
T. -J. Fan: Describing and Recognizing 3-D Objects Using Surface
Properties
ISBN 97179-3 $39.50
R. C. Jain and A.K. Jain: Analysis and Interpretation of Range Images
ISBN 97200-5 $59.00
Coming in the series:
R. Rao: A Taxonomy for Texture Description and Identification
T. Weymouth (ed.): Exploratory Vision: The Active Eye
Related Books in production:
P. Farelle: Data Compression and Recursive Block Coding ISBN 97235-8
------------------------------
Date: Fri, 8 Dec 89 08:14:54 GMT
From: tobbe@isy.liu.se (Torbjorn Kronander)
Subject: Re: MATLAB
Adi Pranata <pranata@udel.edu> writes:
>Hi,
> I'm not sure where to posted this question, anyway Does any one
>have any info, on convert raster images/picture to matlab matrix
>format, since i am interested on use the matlab software to manipulate
>it . Since it will be no problem to display the matlab file format
>using the imagetool software. Any info including what other newsgroup
>more appropriate to posted will be welcome. Thanks in advance.
>You could reply to pranata@udel.edu
> Sincerely,
> Desiderius Adi Pranata
>PS: Electromagnetig way
> 146.955 Mhz -600 KHz
> Oldfashioned way
> (302)- 733 - 0990
> (302)- 451 - 6992
>[ This is definitely appropriate for the Vision List. Answers to the
> List please.
> phil...]
I have done lots of work using images in MATLAB. It is fairly simple
to convert any structure to a matrix (.mat file).
It is also fairly simplr to use m-files to create image display oin
a color monitor such as a color sun.
I would however be nice to use mex-files instead of m-files as I did (no
mex facility available by then).
The following is example code. I do not even assume it will work
right on, but it may suit as a basis for further work. (it works for mew)
My image reading tool is kind of special so begin with adding you r
own reading routine.
/**********************************************************************
matc.h
Routines for input/Output of MATLAB matrices.
Peter Nagy 8712xx
rewritten by Torbjorn Kronander 8712xx+eps
-changed to std unix stream routines (fopen ...)
-added return values for routines. <=0 is failure, 1 is success.
-Only ONE variable read at the time in readmat, next call
will return next variable (if any).
-Similar in writemat, subsequent calls will add new elements to already open
file.
-New parameter added to call. "ctl", ctl is one of INIT,GO,FINIT as defined
INIT is file opening
GO is read/write one variable
FINIT is close.
-transpose added to get crrespondences in arhguments in matlab and C.
KNOWN PROBLEMS
-
**********************************************************************/
/**********************************************************************
int readmat(procctltyp ctl,char* fname,int* rows,int* cols,char* varname,boolean* iflag,double* rpart,double* ipart)
procctltyp ctl;
int *rows, *col, *iflag;
char *fname, *varname;
double *rpart, *ipart;
INPUT:
ctl, one of INIT,GO,FINIT (0,1,2) as described above
fname, filename if ctl=INIT, else not used
OUTPUT:
function return negative if read failure (normally premature eof)
0 if open failure
1 if success.
*rows,*cols Number of rows and columns. (first, second C-index!)
*iflag 0 if only real part
1 if complex
*rpart Pointer to eal part matrix.
*ipart Pointer to imaginary part matrix.
SIDE EFFECTS:
Be careful if the declared number of columns does not agree with the
return from the routine (cols). Indexing will collapse
PN mod TK
**********************************************************************/
typedef int procctltyp;
#define INIT 0
#define GO 1
#define FINIT 2
extern int readmat(procctltyp ctl,char* fname,int* rows,int* cols,char* varname,boolean* iflag,double* rpart,double* ipart);
/**********************************************************************
int writemat(procctltyp ctl,char* fname,int rows,int cols,char* varname,boolean iflag,double* rpart,double* ipart)
procctltyp ctl;
int rows, cols, iflag;
char fname[], varname[];
double *rpart, *ipart;
INPUT:
ctl, One of INIT,GO,FINIT (0,1,2) as described above
fname, Filename if ctl=INIT, else not used
rows,cols Number of rows and columns. (first, second C-index!)
varname variables name (matrix name)
iflag 0 if only real part
1 if complex
*rpart Pointer to real part matrix.
*ipart Pointer to imaginary part matrix.
OUTPUT:
function return negative if write failure (normally write access trouble)
0 if open failure
1 if success.
SIDE EFFECTS:
--
PN mod TK
**********************************************************************/
extern int writemat(procctltyp ctl,char* fname,int rows,int cols,char* varname,boolean iflag,double* rpart,double* ipart);
/**********************************************************************
matc.c
Routines for input/Output of MATLAB matrices.
Peter Nagy 8712xx
rewritten by Torbjorn Kronander 8712xx+eps
-changed to std unix stream routines (fopen ...)
-added return values for routines. <=0 is failure, 1 is success.
-Only ONE variable read at the time in readmat, next call
will return next variable (if any).
-Similar in writemat, subsequent calls will add new elements to already open
file.
-New parameter added to call. "ctl", ctl is one of INIT,GO,FINIT as defined
in tkctools.h
INIT is file opening
GO is read/write one variable
FINIT is close.
-transpose added to get crrespondences in arhguments in matlab and C.
KNOWN PROBLEMS
-
**********************************************************************/
#include <stdio.h>
#define MACHINECODE 1000 /* 1000 for SUN */
/**********************************************************************
double *getadress(row,col,mat,rows,cols)
int row,col;
double *mat;
returns pointer to mat(row,col)
INPUT:
row row of index
col column of index (here row is FIRST coordinate in C!!)
mat pointer to matrix of DOUBLE!!
rows dimensionality of first index of mat.
cols dimensionality of second index of mat.
OUTPUT:
function return: pointer to double mat[row][col]
Sides:
no known (be carefuul not to index out of mat !!)
**********************************************************************/
static double *getadress(row,col,mat,rows,cols)
int row,col;
double *mat;
{
register int ipnt,icols;
register double *pnt;
icols=(int) cols;
ipnt= row * icols + col;
pnt=mat + ipnt;
return( pnt);
}
/**********************************************************************
static void transpose(rows,cols,mat)
int rows,cols;
double *mat;
Transposes a matrix
INPUT:
rows dimensionality of first index in mat
cosl same for second index
mat pointer to matrix of double
OUTPUT:
-
Sides:
The matrix mat is transposed!
**********************************************************************/
static void transpose(rows,cols,mat)
int rows,cols;
double *mat;
{
double tmp, *adr1, *adr2;
int ix,iy;
for (ix=0; ix < rows; ix++)
for (iy=ix+1; iy < cols; iy++)
{
adr1=getadress(ix,iy,mat,rows,cols);
adr2=getadress(iy,ix,mat,rows,cols);
tmp = *adr1;
*adr1 = *adr2;
*adr2 = tmp;
}
}
/**********************************************************************
int readmat(ctl,fname,rows,col,varname,iflag,rpart,ipart)
procctltyp ctl;
int *rows, *col, *iflag;
char *fname, *varname;
double *rpart, *ipart;
INPUT:
ctl, one of INIT,GO,FINIT (0,1,2) as described above
fname, filename if ctl=INIT, else not used
OUTPUT:
function return negative if read failure (normally premature eof)
0 if open failure
1 if success.
*rows,*cols Number of rows and columns. (first, second C-index!)
*iflag 0 if only real part
1 if complex
*rpart Pointer to eal part matrix.
*ipart Pointer to imaginary part matrix.
SIDE EFFECTS:
Be careful if the declared number of columns does not agree with the
return from the routine (cols). Indexing will go balooney!!
PN mod TK
**********************************************************************/
int readmat(ctl,fname,rows,cols,varname,iflag,rpart,ipart)
procctltyp ctl;
int *rows, *cols, *iflag;
char *fname, *varname;
double *rpart, *ipart;
{
int sizint,retn, inum[5], i;
static FILE *infp;
switch(ctl)
{
case INIT:
infp = fopen(strcat(fname,".mat"), "r");
if (NULL != infp)
return(1);
else
return(0);
break;
case GO:
if (5 != fread(inum,sizeof(sizint),5,infp)) return(-1);
if (MACHINECODE != inum[0]) return(-2); /* wrong machine type ! */
*rows = inum[1];
*cols = inum[2];
*iflag= inum[3];
/* Real part */
retn=fread(varname,1, inum[4], infp);
if (inum[4] != retn) return(-3);
retn=fread(rpart,8,(*rows)*(*cols),infp);
if ((*rows)*(*cols) != retn) return(-4);
if ( (*rows >1) && (*cols>1)){
transpose(*rows,*cols,rpart);
}
/* Complex part */
if (*iflag) {
if (ipart == NULL) return(-5);
retn=fread(ipart,8,(*rows)*(*cols),infp);
if ((*rows)*(*cols) != retn) return(-6);
if ( (*rows >1) && (*cols>1)){
transpose(*rows,*cols,ipart);
}
}
return(1);
break;
case FINIT:
fclose(infp);
return(1);
}
}
/**********************************************************************
int writemat(ctl,fname,rows,cols,varname,iflag,rpart,ipart)
procctltyp ctl;
int rows, cols, iflag;
char fname[], varname[];
double *rpart, *ipart;
INPUT:
ctl, One of INIT,GO,FINIT (0,1,2) as described above
fname, Filename if ctl=INIT, else not used
rows,cols Number of rows and columns. (first, second C-index!)
varname variables name (matrix name)
iflag 0 if only real part
1 if complex
*rpart Pointer to real part matrix.
*ipart Pointer to imaginary part matrix.
OUTPUT:
function return negative if write failure (normally write access trouble)
0 if open failure
1 if success.
SIDE EFFECTS:
--
PN mod TK
**********************************************************************/
int writemat(ctl,fname,rows,cols,varname,iflag,rpart,ipart)
procctltyp ctl;
int rows, cols, iflag;
char fname[], varname[];
double *rpart, *ipart;
{
int sizint,retn, inum[5], i;
static FILE *outfp;
char filename[100];
switch(ctl)
{
case INIT:
strcpy(filename,fname);
outfp = fopen(strcat(filename,".mat"), "w");
if (outfp != NULL)
return(1);
else
return(0);
break;
case GO:
if ( (rows >1) && (cols>1)){
transpose(rows,cols,rpart);
if (iflag) transpose(rows,cols,ipart);
}
inum[0]=MACHINECODE;
inum[1]=rows;
inum[2]=cols;
inum[3]=iflag;
inum[4]=strlen(varname)+1;
retn=fwrite(inum,4,5,outfp);
if (5 != retn) return(-1);
#ifdef PRINTDEB
printf("inum %d %d %d %d %d\n",inum[0],inum[1],inum[2],inum[3],inum[4]);
printf("retn (inum) %d \n",retn);
#endif
retn=fwrite(varname,1, inum[4], outfp);
if (inum[4] != retn) return(-2);
#ifdef PRINTDEB
printf("varname %d\n",retn);
#endif
/* Real part */
retn=fwrite(rpart,8,rows*cols,outfp);
if (rows*cols != retn) return(-3);
#ifdef PRINTDEB
printf("real part %d\n",retn);
#endif
/* Complex part */
if (iflag) {
if (ipart == NULL) return(-4);
retn=fwrite(ipart,8,(rows)*(cols),outfp);
if (rows*cols != retn) return(-5);
}
if ( (rows >1) && (cols>1)){
transpose(rows,cols,rpart); /* redo rpart and ipart to original */
if (iflag) transpose(rows,cols,ipart);
}
return(1);
break;
case FINIT:
fclose(outfp);
return(1);
}
} /* writemat */
/* imtomat.c */
/**********************************************************************
Converts an image file (256 x 256) to a matlab .mat file.
Tobbe K 880123
**********************************************************************/
#include <stdio.h>
#include <string.h>
im256typ ima;
double fima[256][256];
main(argc,argv)
int argc;
char *argv[];
{
int ix,iy;
char fname[100];
/* THIS IS WHERE YOUR WORK GOES...
readopenim256("");
*/
printf("Matlab filename without extension (.mat assumed)>");
scanf("%s",fname);
/* THIS IS WHERE YOUR WORK GOES...
readim256(ima);
*/
for (ix=0; ix <= 255; ix++)
for (iy=0; iy <=255; iy++)
fima[ix][iy]=ima[ix][iy];
if (1 != writemat(INIT,fname,256,256,fname,FALSE,fima,NULL)) {
printf("Error in open of tstmat!!");
exit(1);
}
if (1 != writemat(GO,fname,256,256,fname,FALSE,fima,NULL)) {
printf("Error in write of tstmat!!");
exit(2);
}
}
/**********************************************************************
mat2im.c
Converts a matlab matrix .mat file to a info standard .256 file
Note must be 256 x 256 image presently !!
Tobbe 880122
**********************************************************************/
#include <stdio.h>
#include <math.h>
#include <string.h>
im256typ ima;
double fima[256][256];
main(argc,argv)
int argc;
char *argv[];
{
int ret,xrows,yrows,iflag;
register int ix,iy,tmpi;
float ifima;
char varname[30],fname[30];
double fa[3][3];
if (argc > 0) {
strcpy(fname,argv[1]);
}
else {
printf("Filename without extension (.256 and .mat assumed)>");
scanf("%s",fname);
}
xrows=256;
yrows=256;
/* THIS IS WHERE YOUR WORK GOES...
if (!writeopenim256(fname)) {
printf("Sorry there was some error in open of image file/n");
exit(1);
}
if (1 != readmat(INIT,fname,&xrows,&yrows,varname,&iflag,fima,&ifima)) {
printf("Error in open of %s.mat",fname);
exit(2);
}
*/
do
{
if (1 != readmat(GO,fname,&xrows,&yrows,varname,&iflag,fima,&ifima)) {
break;
}
printf("varname is: %s, iflag is; %d, xdim,ydim are (%d,%d)\n"
,varname,iflag,xrows,yrows);
for (ix=0; ix < 256; ix++)
for (iy=0; iy < 256; iy++) {
tmpi=rint(fima[ix][iy]);
ima[ix][iy]=MAX(0,MIN(255,tmpi));
}
/* THIS IS WHERE YOUR WORK GOES...
writeim256(ima);
*/
}
while (ret =1);
}
Torbjorn Kronander tobbe@isy.liu.se
Dept. of EE Linkoping University Sweden
ph +46 13 28 22 07
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/16/89)
Vision-List Digest Fri Dec 15 10:55:52 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re: range images
stereo pair images wanted
Moment Invariants
raster to matlab
----------------------------------------------------------------------
Date: Mon, 11 Dec 89 13:54:28 BST
From: Guanghua Zhang <guanghua%cs.heriot-watt.ac.uk@NSFnet-Relay.AC.UK>
Subject: Re: range images
It was mentioned before that several sets of range images can be obtained
from the M. Rioux and L. Cournoyer. They can also provide with the registered
pairs of the intensity and range images ( I think for one set ). But I don't
know how they register the two images, two perspective, two orthogonal or
one perspective and one orthogonal with converting parameters.
Their address is:
Photonics and Sensors Section
Laboratory for Intelligent Systems'Division of Electrical Enfineering
Natonal Research Council of Canada
Ottawa, Otntario, Canada
K1A 0R8
------------------------------
Date: Tue, 12 Dec 89 17:44 +0100
From: KSEPYML%TUDRVA.TUDELFT.NL@CUNYVM.CUNY.EDU
Subject: stereo pair images wanted
I am in need of stereo pair images, both real world and constructed, as
input for a human stereo-vision algorithm.
Does anybody have such images available?
Alexander G. van der Voort
Koninklijke Shell Exploratie en Produktie Laboratorium
Volmerlaan 6
2288 GD Rijswijk
The Netherlands
[ As usual, please post answers to the List.
phil... ]
------------------------------
Date: 15 Dec 89 15:45:05 GMT
From: Manickam Umasuthan <suthan%cs.heriot-watt.ac.uk@NSFnet-Relay.AC.UK>
Subject: Moment Invariants
Organization: Computer Science, Heriot-Watt U., Scotland
I am very much interested to know whether any one has done research on
the application of moment invariants to practical problems ( mainly 3D
images using 3D moment invariants ).
M.UMASUTHAN
------------------------------
Date: Fri, 8 Dec 89 15:03:17 PST
From: ramin@scotty.Stanford.EDU (Ramin Samadani)
Subject: raster to matlab
Regarding raster to matlab conversion. I've taken some licensed stuff out of
the code we use and came up with the following which has the main parts
for converting a file containing unsigned chars (rows*cols of them) to a
matlab readable format. It is currently hardwired for a vax but could
easily be modified for suns and macs, etc. Also, since I took the licensed
stuff out, the rows and cols are hardwired right now but that should be
easy to fix. The code follows, with no guarantees at all!
Ramin Samadani
/* imagetomat.c - writes a matrix matlab can
* read. Double format output,byte
* format input for now.
*
* usage: matrix-name <in.hpl >out.mat
*
* to load: cc -o name name.c -O
*
* Ramin Samadani - 6 May 88
*/
int rows = 128;
int cols = 128;
#include <stdio.h>
typedef struct {
long type; /*type*/
long mrows; /* row dimension */
long ncols; /* column dimension */
long imagf; /* flag indicating imag part */
long namlen; /* name length (including NULL) */
} Fmatrix;
char *prog;
main(argc,argv)
int argc;
char *argv[];
{
/* VARIABLES */
int rows,cols, i,j;
unsigned char *ifr;
double *ofr;
/*
* Matlab declarations
*/
char *pname; /* pointer to matrix name */
float *pr; /* pointer to real data */
FILE *fp;
Fmatrix x;
int mn;
prog = argv[0];
/*
* check passed parameters
*/
if (argc < 2) {
fprintf(stderr,"use: %s matrix name <filein >fileout\n",prog);
exit(1);
}
if ((pname = (char *) calloc(80,sizeof(char))) == NULL) {
fprintf(stderr,"%s: can't allocate matrix name\n",prog);
exit(1);
}
pname = argv[1];
x.type = 2000;
x.mrows = (long) cols;
x.ncols = (long) rows;
x.imagf = 0;
x.namlen = strlen(pname) + 1;
fprintf(stderr,"matrix %s has %ld rows, %ld cols, double precision\n",
pname, x.mrows,x.ncols);
rows = rows; cols = cols;
if ((ifr = (unsigned char *) calloc(rows*cols,sizeof(char))) == NULL){
fprintf(stderr,"%s: can't allocate input frame\n",prog);
exit(1);
}
if ((ofr = (double *) calloc(rows*cols,sizeof(double))) == NULL){
fprintf(stderr,"%s: can't allocate output frame\n",prog);
exit(1);
}
if (read(0,ifr,rows*cols*sizeof(char)) == -1) {
fprintf(stderr,"%s: can't read frame\n",prog);
exit(1);
}
/* MAIN PROCESSING */
mn = x.mrows*x.ncols;
for (i = 0; i < mn; i++) {
ofr[i] = (double) (ifr[i]&0377);
}
/*
* write the matrix
*/
if(write(1,&x,sizeof(Fmatrix)) != sizeof(Fmatrix)) {
fprintf(stderr,"%s: can't write matrix header\n",prog);
exit(1);
}
if(write(1,pname,(int)x.namlen*sizeof(char)) !=
(int)x.namlen*sizeof(char)) {
fprintf(stderr,"%s: can't write name of matrix\n",prog);
exit(1);
}
if (write(1,ofr,mn*sizeof(double)) != mn*sizeof(double)){
fprintf(stderr,"%s: can't write matrix data\n",prog);
exit(1);
}
}
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/23/89)
Vision-List Digest Fri Dec 22 09:42:22 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
multidimensional image data request
Suggestions for a range-finder
Study of Consciousness within Science--Intl' Conference
----------------------------------------------------------------------
Date: 18 Dec 89 19:43:04 GMT
From: jwbrandt@ucdavis.edu (Jon Brandt)
Subject: multidimensional image data request
Organization: U.C. Davis - Department of Electrical Engineering and Computer Science
I am looking for the following types of image data:
1) time sequences from stationary or moving platforms
2) 3D or higher, scalar or vector, simulation data (e.g. flow vortices)
3) 3D reconstructions (MR, CT, confocal optics, etc.)
4) other multidimensional data that I haven't thought of
Can anyone point to an ftp source? Are there standard test sets in these
areas? Size is no object: the bigger the better (within reason).
Thanks,
Jon Brandt
brandt@iris.ucdavis.edu
[ Please post all responses directly to the List. Since the Vision List has
an FTP connection, it would be nice if some of this data couldn't be
stored here...
phil... ]
------------------------------
Date: Wed, 20 Dec 89 09:01:57 EST
From: Dmitry Goldgof <goldgof@SOL.USF.EDU>
Subject: Suggestions for a range-finder
We are looking into buying inexpensive (~20K) range-finder
for robotics applications. For this amount we can probably
only get structured-light system. Does anybody has suggestions
on the subject (we do have Paul Besl's paper). Our requirements
are standoff distance ~ 0.5m, depth of field ~ 1-2m or better,
i.e. not a system with very small depth of field.
Dmitry Goldgof
Department of Computer Science and Engineering
University of South Florida
------------------------------
Date: 19 Dec 89 14:04:37 GMT
From: bvi@cca.ucsf.edu (Ravi Gomatam)
Subject: STUDY OF CONSCIOUSNESS WITHIN SCIENCE--INTL' CONFERENCE
Organization: Computer Center, UCSF
------- FIRST INTERNATIONAL CONFERENCE --------
on the study of
CONSCIOUSNESS WITHIN SCIENCE
Feb. 17-18, 1990
Cole Hall, UCSF, San Francisco
CALL FOR REGISTRATION
ORGANIZING COMMITTEE ADVISORY BOARD
T.D. Singh Henry Stapp
R.L. Thompson Karl Pribram
Ravi Gomatam E.C.G. Sudarshan
K.P. Rajan David Long
PURPOSE:
In this century, developments in a variety of fields including
quantum physics, neuro sciences and artificial intelligence have
revealed the necessity for gaining an understanding of the nature
of consciousness and its causal interplay in the study of even
matter. The present conference will examine the the
methodological tools and problems in the study of consciousness
from the perspective of a wide range of scientific fields.
Prominent scholars will share and discuss their research through
invited presentations and question and answer sessions. The
discussions will focus on the role of consciousness as a vital
component of the scientific investigation of the natural world.
INVITED PRESENTATIONS INCLUDE:
NEW CONCEPTS ON THE MIND-BRAIN PROBLEM
JOHN ECCLES Neurosciences, Switzerland Nobel Laureate
A QUANTUM THEORY OF CONSCIOUSNESS
HENRY STAPP Theoretical Physics, Lawrence Berkeley Labs.
BRAIN STATES AND PROCESSES AS DETERMINANTS OF THE CONTENTS OF
CONSCIOUSNESS
KARL PRIBRAM Neuropsychology, Stanford University
CONSCIOUSNESS: IMMANENT OR TRANSCENDENT?
ROBERT ROSEN Biophysics, Dalhousie University
USE OF CONSCIOUS EXPERIENCE IN UNDERSTANDING REALITY
BRIAN JOSEPHSON TCM Group, Cambridge University Nobel Laureate
WAVE MECHANICS OF CONSCIOUSNESS - ROBERT JAHN
Engineering Anomalies Group, Princeton University
ENGINEERING ANOMALIES RESEARCH - BRENDA DUNNE
Engineering Anomalies Group, Princeton University
SPONTANEITY OF CONSCIOUSNESS: A PROBABILISTIC THEORY OF MEANINGS
AND SEMANTIC ARCHITECTONICS OF PERSONALITY - V. NALIMOV
Mathematical Theory of Experiments, Moscow State University
EVOLUTION AND CONSCIOUSNESS
A.G. CAIRNS-SMITH Molecular Chemistry, Glasgow University
PATTERNS IN THE UNIVERSE
E.C.G. SUDARSHAN Theoretical Physics, Univ. of Texas, Austin
WHAT IS WRONG WITH THE PHILOSOPHY OF MIND?
JOHN SEARLE Cognitive Philosophy, U.C., Berkeley
A TRANS-TEMPORAL APPROACH TO MIND-BRAIN INTERACTION
R. L. THOMPSON Mathematical Biology, Bhaktivedanta Institute, SF
BIOLOGICAL COHERENCE--CONNECTIONS BETWEEN MICRO AND MACRO PHYSICS
H. FROHLICH Theoretical Physics, University of Liverpool
Participation is by registration. Besides these invited
talks, there will be question/answer sessions, panels and a poster
session. The program format will afford registered participants
ample opportunity for interaction with the distinguished guests.
Early registration is encouraged.
REGISTRATION FEE: $125.00 before January 15, 1990;
$75.00 Full time students (limited seats)
[Fee includes luncheon on both days]
$150/$85 after January 15.
To register, please send check/money order (in U.S. dollars
only) drawn in favor of the Bhaktivedanta Institute to the
conference secretariat. Please include name, address,
institutional affliation and research interests (if any) of the
registrant.
CALL FOR PAPERS:
While all oral presentations are by invitation only,
opportunities exist for registered participants to present papers
in poster sessions on any topic related to the broad theme of the
conference. Three hard-copies of a full paper (8000 words) or
extended abstract (1000 words) submitted before December 29, 1989
are assured of full consideration.
Please direct all registration requests, paper submissions and
inquiries to:
Ravi V. Gomatam, Organizing Secretary
THE BHAKTIVEDANTA INSTITUTE
84 Carl Street
San Francisco, CA 94117 U.S.A.
Tel: (415)-753-8647/8648
E-Mail: INTERNET: bvi@cca.ucsf.edu
BITNET: bvi@ucsfcca
CONFERENCE HOST: The Bhaktivedanta Institute - A private non-
profit research organization promoting international discussions
on consciousness-based perspectives in relation to outstanding
problems in various areas of modern science. The institute has
centers in Bombay and San Francisco and a staff of twenty
concerned scientists from different fields.
* * * * *
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (12/30/89)
Vision-List Digest Fri Dec 29 09:09:56 PDT 89 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: multidimensional data NASA IP Package? ---------------------------------------------------------------------- Date: Wed, 27 Dec 89 10:24:45 EST From: Stephen M. Pizer <smp@cs.unc.edu> Subject: multidimensional data jwbrandt@ucdavis.edu writes that he needs to know of sources of multidimensional data. A collection of medical (magnetic resonance image) and molecular electron density data is available on magnetic tape from payne@unc.cs.edu or Pamela Payne, Softlab, Dept. of Computer Science, Sitterson Hall, Univ. of NC, Chapel Hill, NC 27599-3175. This collection was produced as a result of the Chapel Hill Volume Visualization Workshop in May 1989 and consists of data contributed by Siemens, Inc. and Michael Pique of Scripps. The cost is $50. I believe a second tape is under preparation for an additional charge. ------------------------------ Date: Thu, 28 Dec 89 11:17:26 PST From: Scott E. Johnston <johnston@ads.com> Subject: NASA IP Package? I've heard rumors of an extensive, well-documented IP package available from NASA. A search of vision-list backissues didn't uncover any references. Anybody with further info? ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (01/11/90)
Vision-List Digest Wed Jan 10 10:47:34 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Digital Darkroom (popi)
3D-glasses
CVGIP Abstract
Conference on Photogrammetry Meets Machine Vision
RMCAI 90
----------------------------------------------------------------------
Date: Thu, 4 Jan 90 03:14:23 GMT
From: us214777@mmm.serc.3m.com (John C. Schultz)
Subject: Digital Darkroom (popi)
Organization: 3M - St. Paul, MN 55144-1000 US
I recently grabbed a public domain version of an X window based image
generation? processing? analysis? package called DigitalDarkroom (or popi).
This seems to me to be an interesting package with a lot of potential for
image processing. I particularly like the simple syntax to access image
pixels and the transparent conversion from rectangular to polar coordinates.
Does anyone use this package for image analysis? Any analysis routines
available (e.g. morphology, blob analysis, filtering, transforms)?
If you don't have a copy you might want to pick one up from the net.
John C. Schultz EMAIL: jcschultz@mmm.3m.com
3M Company WRK: +1 (612) 733 4047
3M Center, Building 518-01-1 St. Paul, MN 55144-1000
The opinions expressed above are my own and DO NOT reflect 3M's
------------------------------
Date: 4 Jan 90 18:55:00 GMT
From: tjeerd@mbfys4.sci.kun.nl (Tjeerd Dijkstra)
Subject: 3D-glasses
Keywords: 3D-glasses, liquid crystal
I want to use glasses with liquid crystal shutters in an
experimental setup that opens the visual feedback loop.
Until now I was unable to obtain any information on shops,
brandnames etc. Does anyone have any pointers?
I have a SUN4/260 CXP which has a framerate of 66Hz
Tjeerd Dijkstra
E-mail: tjeerd@sci.kun.nl
------------------------------
Date: Thu, 4 Jan 90 17:24:50 -0800
From: bertolas@cs.washington.edu (William Bertolas)
Subject: CVGIP Abstract
Computer Vision, Graphics, and Image Processing
Volume 49, Number 2, February 1990
CONTENTS
Kwangyoen Wohn and Allen M. Waxman. The Analytic Structure of
Image Flows: Deformation and Segmentation, p.127
Michael T. Goodrich and Jack Scott Snoeyink. Stabbing Parallel
Segments with a Convex Polygon, p.152.
J.P. Oakley and M.J. Cunningham. A Function Space Model for
Digital Image Sampling and Its Application in Image
Reconstruction, p.171.
Per-Erik Danielsson and Olle Seger. Rotation Invariance in
Gradient and Higher Order Derivative Detectors, p. 198.
Daphna Weinshall. Qualitative Depth from Stereo, with Applications, p. 222.
NOTE
Yuh-Tay Liow and Theo Pavlidis. Use of Shadows for Extracting
Buildings in Aerial Images, p. 242.
------------------------------
Date: Mon, 8 Jan 90 09:30:00 EST
From: ELHAKIM@NRCCIT.NRC.CA
Subject: conference on photogrammetry meets machine vision
Second Announcement and Call for Papers
ISPRS Symposium
Close-Range Photogrammetry Meets Machine Vision
ETH Zurich, Switzerland
September 3 - 7, 1990
Organised by
- Institute of Geodesy and Photogrammetry
- ISPRS Commission V
Sponsored by
SGPBF - Swiss Society for Photogrammetry, Image Analysis
and Remote Sensing
Cooperating Organisations
SPIE - The International Society for Optical Engineering
IEEE - IEEE, The Computer Society, TC on Pattern Analysis
and Machine Intelligence
FIG - Federation Internationale des Geometres
ITG - Information Technology Society of the SEV
SGBT - Swiss Association of Biomedical Engineering
INVITATION TO ZURICH
You are invited to attend this international and interdisciplinary Symposium
of the International Society for Photogrammetry and Remote Sensing
(ISPRS) and to share your knowledge in photogrammetry and the various
vision disciplines with an expert group of photogrammetrists, geodesists,
mathematicians, physicists, system engineers, electrical engineers, computer
scientists, mechanical engineers, architects, archaeologists and others, whose
concern is precise and reliable spatial measurements using imaging systems.
We hope that this Symposium, according to its title "Close-Range Photo-
grammetry Meets Machine Vision", will provide the stage where ideas and
experience can be exchanged in a stimulating environment. The conference
will take place at ETH-Hoenggerberg, a campus of the Swiss Federal
Institute of Technology (ETH) Zurich, which is conveniently located close to
downtown Zurich in a restful and delightful natural environment.
Zurich is a captivating city of many contrasts. It is a world-famous
banking and stock-exchange centre and at the same time an idyllic
place with all the charm of a small city. It is a bastion of the arts
and sciences - and also a friendly and hospitable city. A paradise
for shoppers, it also offers a host of entertainment and leisure
activities. Zurich is situated on a celebrated lake and river, between
gentle hills, with the snow-capped peaks of the Alps on the skyline.
Aircraft from most countries of every continent land at Zurich's
airport and a day excursion is enough to reach any part of
Switzerland.
The conference will feature tutorials, technical sessions, a scientific
exhibition and a variety of social and cultural events. We will spare no effort
in providing an interesting program for both regular participants and
accompanying persons.
May I cordially invite you to participate in this Symposium and to submit a
paper dealing with the topics of interest to ISPRS Commission V.
Armin Gruen
President of ISPRS Commission V
GENERAL OBJECTIVES
In recent years the modern vision disciplines of computer vision, machine
vision and robot vision have found widespread interest in the scientific and
engineering world. The further development of these disciplines is crucial
for advancements in various other fields of science, technology and industry.
As the scientific and engineering concepts of vision systems are increasingly
being examined in practical application environments, the need for precise,
reliable and robust performance with respect to quantitative measurements
becomes very obvious. Quantitative measurement on the other hand has been
a familiar domain to photogrammetrists for many years. The intention of this
symposium is to combine the longstanding, application-proven expertise of
classical photogrammetric procedures with the up-to-date, forward-looking
vision hardware and algorithmic concepts in order to overcome current
limitations and to arrive at truly efficient and reliable systems which in turn
will open up new and promising fields of application. The aim is to bring
together experts from various disciplines who are concerned with the design,
development and application of modern analogue, digital and hybrid vision
systems which operate in a close-range environment.
This conference is designed for scientists, engineers and users in the fields of
photogrammetry, machine vision and robot vision; from universities,
research institutes, industry, governmental organisations and engineering
firms.
The topics to be addressed should be related, but are not restricted to, the
terms of reference of the Working Groups of ISPRS Commission V:
WG V/1: Digital and Real-Time Close-Range Photogrammetry Systems
Chairmen: Dr. Sabry El-Hakim, Prof.Dr. Kam Wong
- Real-time vision systems for metric measurements
- System hardware and software integration
- Demonstration of systems in actual application environments
WG V/2: Close-Range Imaging Systems - Calibration and Performance
Chairmen: Prof. Dr. John G. Fryer, Prof. Dr. Wilfried Wester-
+ Ebbinghaus
- Geometric and radiometric characteristics of CCD and hybrid
imaging systems
- Procedures and strategies for calibration and orientation
- High precision photogrammetry (<10-5) with large format
photographic images and CCD matrix sensors in image space
WG V/3: Image Analysis and Image Synthesis in Close-Range
Photogrammetry
Chairmen: Dr. Dieter Fritsch, Dr. Jan-Peter Muller
- Algorithmic aspects in image analysis
- Visualisation techniques in image synthesis
- Hardware architecture for real-time image analysis and image
synthesis
WG V/4: Structural and Industrial Measurements with
Consideration of CAD/CAM Aspects
Chairmen: Dr. Clive S. Fraser, Prof.Dr. Heinz Ruther
- Integration of CAD/CAM into the photogrammetric
measurement process
- Digital photogrammetric systems for industrial mensuration
- Transfer of photogrammetric technology to the industrial
design, engineering and manufacturing sector
WG V/5: Photogrammetry in Architecture and Archaeology
Chairmen: Mr. Ross W.A. Dallas, Dr. Rune Larsson
- Application of new photogrammetric technology to
architectural and archaeological surveying and recording
- Possibilities offered by new low-cost photogrammetric systems
and video-based systems
- Study of appropriate applications of CAD/CAM and LIS/GIS
WG V/6: Biostereometrics and Medical Imaging
Chairmen: Prof.Dr. Andreas Engel, Prof.Dr. Peter Niederer
- Human motion analysis and biological surface measurements
- 3D medical imaging and anthropometry; 3D microscopy
- Hardware and software for use in medical imaging
Associate Group: Robot Vision
Chairman: Dr. Reimar Lenz
- Recent developments
- Applications
CALL FOR PAPERS
Deadline for abstracts: January 31, 1990
Notification of acceptance: March 31, 1990
Deadline for complete manuscripts: June 15, 1990
A separate Abstract Form can be obtained from the symposium organisation.
Instructions for authors and forms for papers will be mailed out in due course.
The papers of this Symposium are to be published as Proceedings in the
Archives series of the ISPRS (Volume 28, Part V), which will be made
available prior to the conference. This implies that the deadline for complete
manuscripts has to be observed strictly.
LANGUAGE
Papers may be presented in any of the three official ISPRS languages
English, French and German. The operating language of the Symposium will
be English. Simultaneous translation will not be provided.
GENERAL INFORMATION
SYMPOSIUM SITE
ETH-Hoenggerberg, Zurich, a campus of the Swiss Federal Institute of
Technology (ETH) Zurich.
The location for the technical sessions, tutorials, exhibition and the
information and registration desk will be the HIL-Building.
FACILITIES
The lecture rooms are equipped with slide projectors (5x5 cm) and overhead
projectors. Video installations (projection and monitor display) can be
arranged on request.
TECHNICAL SESSIONS
The technical sessions will be arranged from September 4 to 7, 1990. If
necessary, two sessions will be held in parallel.
TUTORIALS
The following tutorials are offered on September 3, 1990:
(A) Full-day tutorial "Fundamentals of Real-Time Photogrammetry"
Lecturers: Dr. D. Fritsch*, Dr. R. Lenz*, Dipl.-Ing. E. Baltsavias,
Dipl.-Ing. ETH H. Beyer (*Technical Univ. Munich, FRG and ETH Zurich,
Switzerland).
Time: 9.00 to 17.30
A one-day tutorial covering algorithmic and hardware aspects of Real-Time
Photogrammetry is to be presented.
System design aspects and hardware components of Real-Time
Photogrammetric Systems are to be analysed. Emphasis will be placed on the
performance in 3-D vision and measurement tasks. The principal topics will
include: system design, data acquisition, data transfer, processing, storage,
and display. Image acquisition will be analysed in more detail and an outline
will be given of the characteristics of CCD-sensors, cameras, video signals
and frame grabbers that influence image quality and measurement accuracy.
Algorithmic aspects of image analysis and computer vision techniques for
processing image data for 3-D applications will be presented. The main
topics include: image enhancement, edge detection and segmentation,
morphological and geometric operations, feature detection and object
recognition, image and template matching, point determination and
optimisation, surface measurement and reconstruction.
The presentation will be supported by practical demonstrations of the
hardware and algorithmic performance of digital close-range photogram-
metric systems.
This tutorial is designed for engineers and applied researchers with interest
in image analysis, machine vision, robotics and digital photogrammetry.
Basic knowledge of photogrammetry and image processing will be assumed.
(B) Half-day tutorial "Computer Vision and Dynamic Scene Analysis"
Lecturer: Prof.Th.S. Huang (Univ. of Illinois, Urbana- Champaign, USA)
Time: 13.30 to 17.30
A half-day tutorial covering computer vision with the emphasis on dynamic
scene analysis will be presented. The goal is to expose to researchers in
photogrammetry some of the important results in dynamic scene analysis.
Photogrammetry and computer vision have many common problems such as
stereo, pose determination, and camera calibration. The two fields can
certainly learn much from each other.
After an overview of computer vision, several examples of motion detection
and high-level spatial-temporal reasoning will be given. Then a detailed
discussion will be presented on the use of feature matching for pose
determination, camera calibration, and 3D motion determination. The key
issues include: extracting and matching of point and line features in images,
minimum numbers of features required for unique solution, linear vs.
nonlinear (esp. polynomial) equations, and robust algorithms.
It is hoped that this tutorial will provide a forum for the exchange of ideas
between researchers in photogrammetry and computer vision.
Registration for a tutorial should be made on the attached Registration Form.
Since participation will be restricted due to space limitations, the organisers
reserve the right of refusal.
EXHIBITION
A scientific/commercial exhibition will feature the latest developments in
systems, components, software and algorithms in close-range photogram-
metry and machine vision. Application forms for interested exhibitors can be
obtained from the Symposium Secretariat.
REGISTRATION
Registration of all participants (including accompanying persons) should be
made on the Registration Form which can be obtained from the congress
organisation. Please note that a separate form must be used for the hotel
reservation.
Correspondence concerning registration should be mailed to the Symposium
Secretariat.
Registration Fees
Before June 1 after
+ June 1
Active Participants SFr. 350.-- SFr. 400.--
Accompanying Persons SFr. 150.-- SFr. 175.--
Tutorial (A) SFr. 250.-- SFr. 275.--
Tutorial (B) SFr. 150.-- SFr. 175.--
For active participants the registration fee includes admission to all sessions,
a copy of the Proceedings and the Welcome Party. Included in the regist-
ration fee for accompanying persons are the Opening and Closing Sessions,
the Welcome Party, and the right to participate in the program for
accompanying persons at the announced prices.
The registration fee and other charges payable to the Symposium Secretariat
should be enclosed with the Registration Form as a bank draft (drawn on a
Swiss bank, payable to the ISPRS-Symposium Secretariat) or a copy of a
bank transfer. Credit cards are not accepted.
CONFIRMATION
Confirmation of registration will be mailed to participants after receipt of the
Registration Form and payment.
INFORMATION
A reception desk will be open for registration and information on the ground
floor of the HIL-Building from September 3 to 7, 8.00-17.30.
ACCOMMODATION
The Verkehrsverein Zurich will arrange the hotel accommodation for all
participants. The Hotel Reservation Form should be mailed to the
Verkehrsverein Zurich (it can be obtained from the congress organisation).
The hotel will confirm the room reservations in the order in which the forms
and the hotel deposit payments are received. Please observe July 23, 1990
as the deadline for hotel reservation.
SOCIAL EVENTS
S1 Reception for Tutorial Participants
Monday, September 3, 17.30 free
S2 Welcome Party for Symposium Participants
Tuesday, September 4, 17.30 free
S3 An Evening on the Lake. Dinner Cruise on Lake Zurich
Wednesday, September 5, 19.00 SFr. 55.--
A 3 hour cruise on the Lake of Zurich. Whilst the boat takes you
along the beautiful shores, traditional Swiss dishes will be served
("Bauernbuffet") and you can enjoy the view of vineyards, villages and
some distinguished residential areas.
S4 Medieval Night. Dinner at Castle Lenzburg
Thursday, September 6, 19.00 SFr. 98.--
Busses will take you to the impressive Lenzburg Castle. Set aloft
a precipitous base of rock, with its massive walls and profusion of
towers and battlements, Lenzburg Castle presents the classical picture
of a medieval fortress. Before having dinner at the Knight's Lodge,
drinks will be served in the courtyard and picturesque French
Gardens. A Swiss folk-music group will entertain you during and after
dinner. At midnight the busses will take you back to Zurich.
PROGRAM FOR ACCOMPANYING PERSONS
AP1 "Goldtimer Tram" ride: A nostalgia-awakening veteran tram
dating from 1928 takes you on a pleasure trip all through the city. An
excellent way to get a first impression (1 h).
Afterwards a hostess will take you for a stroll through the Old Town,
including a sight of the famous Chagall-windows (1 1/2 h).
Tuesday, September 4, 14.00 - 17.00 SFr. 25.--
AP2 Visit to the Lindt-Sprungli chocolate factory: A bus takes you
to Kilchberg where a hostess will welcome you and guide you through
the chocolate factory.
Wednesday, September 5, 9.00 - 12.30 SFr. 15.--
AP3 Half-day excursion to the Rhine waterfalls and Schaff-
hausen: Bus tour through Zurich's wine-growing districts to the falls
of the Rhine, which offer the visitor the glorious spectacle of the
largest waterfall in Europe. Transfer to the city of Schaffhausen, a
picturesque town with well preserved medieval architecture,
overlooking the upper reaches of the Rhine.
Wednesday, September 5, 13.00 - 17.00 SFr. 42.--
AP4 Full-day excursion to Rigi and Luzern: Bus tour through
beautiful countryside to Luzern, a picturesque old town right in the
heart of Switzerland, surrounded by Lake Luzern and highrising
mountains. Sightseeing tour by bus. Then you will have free time for
shopping and lunch. The bus takes you to Vitznau where a
cogwheel-railway takes you to the Rigi (5900 ft) with its spectacular
views of the Alps, their foothills and valleys. By bus back to Zurich.
Thursday, September 6, 8.30 - 17.00 SFr. 75.--
Visits to the Kunsthaus (Art Gallery), Landesmuseum (Museum of History)
and a full-day excursion to the Stein cheese-dairy, Appenzell can be booked
at the Verkehrsverein desk. In addition, the official tourist agency
Verkehrsverein Zurich will offer a great variety of interesting activities and
excursions to mountains, lakes and cultural places of interest, folklore,
dancing and nightclub entertainment, as well as diverse sports. Pre- and
postconference activities are also handled by this local tourist office. The
Verkehrsverein will operate an information and reservation desk next to the
registration desk.
GENERAL CONDITIONS FOR REGISTRATION AND TOURS
Registration and booking of social events and tours should be made on the
enclosed Registration Form. All payments must be made in full. All
payments will be refunded, after deduction of a 25% administration charge,
for all cancellations received before August 15, 1990. After this date no
refunds can be made for cancellation. No charge is made for children under
4 years for the social events and excursions.
SYMPOSIUM ORGANISATION
Director: Prof. Dr. A. Gruen
President of ISPRS Commission V
Secretary: Dipl. Ing. ETH H. Beyer
Secretary of ISPRS Commission V
Members of the organising committee:
Dipl.Ing. E. Baltsavias; Dipl.Ing. H.-G. Maas; Dipl.Ing. M. Meister,
Dipl.Ing. Z. Parsic; L. Steinbruckner (ETH Zurich)
Dipl.Ing. L. Cogan; Dr.T. Luhmann; M. Streit; Dr. R. Zumbrunn (Kern & Co.AG)
ADDRESS FOR CORRESPONDENCE AND INQUIRIES:
Symposium of ISPRS Commission V
Institute of Geodesy and Photogrammetry
ETH-Hoenggerberg
CH-8093 Zurich
Switzerland
Tel.: +41-1 377 3051 Telex: 823 474 ehpz ch
Fax: +41-1 371 55 48 email: chezpp@igpho.uucp
HOW TO GET TO THE ETH-HOENGGERBERG
Zurich International Airport, 11 km from the city centre, is served by most
International Airlines.
The Swiss Federal Railways run a feeder service to the main railway station
in Zurich by means of its Airport Line. During airport operational hours
trains run every 20 to 30 minutes between the underground station at the
Airport and the Main Station and vice versa.
Public transport City - ETH-Hoenggerberg: Tram Nos. 11 and 15 to Buch-
eggplatz or tram Nos. 7, 9, 10 and 14 to Milchbuck and then from each, Bus
69 to ETH-Hoenggerberg. (The printed version contains a map of the symposium
and Zurich)
ABSTRACT FORMS and REGISTRATION MATERIAL can be obtained from
the Symposium organisation.
------------------------------
Date: 10 Jan 90 05:57:44 GMT
From: news%beta@LANL.GOV (Usenet News)
Subject: RMCAI 90
Organization: NMSU Computer Science
Updated CFP:
PRAGMATICS IN AI PRAGMATICS IN AI PRAGMATICS IN AI PRAGMATICS IN AI PRAGMATICS
Cut---------------------------------------------------------------------------
SUBJECT: Please post the following in your Laboratory/Department/Journal:
CALL FOR PAPERS
Pragmatics in Artificial Intelligence
5th Rocky Mountain Conference on Artificial Intelligence (RMCAI-90)
Las Cruces, New Mexico, USA, June 28-30, 1990
PRAGMATICS PROBLEM:
The problem of pragmatics in AI is one of developing theories, models,
and implementations of systems that make effective use of contextual
information to solve problems in changing environments.
CONFERENCE GOAL:
This conference will provide a forum for researchers from all
subfields of AI to discuss the problem of pragmatics in AI.
The implications that each area has for the others in tackling
this problem are of particular interest.
COOPERATION:
American Association for Artificial Intelligence (AAAI)
Association for Computing Machinery (ACM)
Special Interest Group in Artificial Intelligence (SIGART)
IEEE Computer Society
U S WEST Advanced Technologies and the Rocky Mountain Society
for Artificial Intelligence (RMSAI)
SPONSORSHIP:
Association for Computing Machinery (ACM)
Special Interest Group in Artificial Intelligence (SIGART)
U S WEST Advanced Technologies and the Rocky Mountain Society
for Artificial Intelligence (RMSAI)
INVITED SPEAKERS:
The following researchers have agreed to present papers
at the conference:
*Martin Casdagli, Los Alamos National Laboratory, Los Alamos USA
*Arthur Cater, University College Dublin, Ireland EC
*Jerry Feldman, University of California at Berkeley, Berkeley USA
& International Computer Science Institute, Berkeley USA
*Barbara Grosz, Harvard University, Cambridge USA
*James Martin, University of Colorado at Boulder, Boulder USA
*Derek Partridge, University of Exeter, United Kingdom EC
*Philip Stenton, Hewlett Packard, United Kingdom EC
*Robert Wilensky, University of California at Berkeley Berkeley USA
THE LAND OF ENCHANTMENT:
Las Cruces, lies in THE LAND OF ENCHANTMENT (New Mexico),
USA and is situated in the Rio Grande Corridor with the scenic
Organ Mountains overlooking the city. The city is
close to Mexico, Carlsbad Caverns, and White Sands National Monument.
There are a number of Indian Reservations and Pueblos in the Land Of
Enchantment and the cultural and scenic cities of Taos and Santa Fe
lie to the north. New Mexico has an interesting mixture of Indian, Mexican
and Spanish culture. There is quite a variation of Mexican and New
Mexican food to be found here too.
GENERAL INFORMATION:
The Rocky Mountain Conference on Artificial Intelligence is a major
regional forum in the USA for scientific exchange and presentation
of AI research.
The conference emphasizes discussion and informal interaction
as well as presentations.
The conference encourages the presentation of completed research,
ongoing research, and preliminary investigations.
Researchers from both within and outside the region
are invited to participate.
Some travel awards will be available for qualified applicants.
FORMAT FOR PAPERS:
Submitted papers should be double spaced and no more than 5 pages
long. E-mail versions will not be accepted. Papers will be published
in the proceedings and there is the possibility of a published book.
Send 3 copies of your paper to:
Paul Mc Kevitt,
Program Chairperson, RMCAI-90,
Computing Research Laboratory (CRL),
Dept. 3CRL, Box 30001,
New Mexico State University,
Las Cruces, NM 88003-0001, USA.
DEADLINES:
Paper submission: April 1st, 1990
Pre-registration: April 1st, 1990
Notice of acceptance: May 1st, 1990
Final papers due: June 1st, 1990
LOCAL ARRANGEMENTS:
Local Arrangements Chairperson, RMCAI-90.
(same postal address as above).
INQUIRIES:
Inquiries regarding conference brochure and registration form
should be addressed to the Local Arrangements Chairperson.
Inquiries regarding the conference program should be addressed
to the Program Chairperson.
Local Arrangements Chairperson: E-mail: INTERNET: rmcai@nmsu.edu
Phone: (+ 1 505)-646-5466
Fax: (+ 1 505)-646-6218.
Program Chairperson: E-mail: INTERNET: paul@nmsu.edu
Phone: (+ 1 505)-646-5109
Fax: (+ 1 505)-646-6218.
TOPICS OF INTEREST:
You are invited to submit a research paper addressing Pragmatics
in AI, with any of the following orientations:
Philosophy, Foundations and Methodology
Knowledge Representation
Neural Networks and Connectionism
Genetic Algorithms, Emergent Computation, Nonlinear Systems
Natural Language and Speech Understanding
Problem Solving, Planning, Reasoning
Machine Learning
Vision and Robotics
Applications
PROGRAM COMMITTEE:
*John Barnden, New Mexico State University
(Connectionism, Beliefs, Metaphor processing)
*Hans Brunner, U S WEST Advanced Technologies
(Natural language interfaces, Dialogue interfaces)
*Martin Casdagli, Los Alamos National Laboratory
(Dynamical systems, Artificial neural networks, Applications)
*Mike Coombs, New Mexico State University
(Problem solving, Adaptive systems, Planning)
*Thomas Eskridge, Lockheed Missile and Space Co.
(Analogy, Problem solving)
*Chris Fields, New Mexico State University
(Neural networks, Nonlinear systems, Applications)
*Roger Hartley, New Mexico State University
(Knowledge Representation, Planning, Problem Solving)
*Victor Johnson, New Mexico State University
(Genetic Algorithms)
*Paul Mc Kevitt, New Mexico State University
(Natural language interfaces, Dialogue modeling)
*Joe Pfeiffer, New Mexico State University
(Computer Vision, Parallel architectures)
*Keith Phillips, University of Colorado at Colorado Springs
(Computer vision, Mathematical modelling)
*Yorick Wilks, New Mexico State University
(Natural language processing, Knowledge representation)
*Scott Wolff, U S WEST Advanced Technologies
(Intelligent tutoring, User interface design, Cognitive modeling)
REGISTRATION:
Pre-Registration: Professionals: $50.00; Students $30.00
(Pre-Registration cutoff date is April 1st 1990)
Registration: Professionals: $70.00; Students $50.00
(Copied proof of student status is required).
Registration form (IN BLOCK CAPITALS).
Enclose payment made out to New Mexico State University.
(ONLY checks in US dollars will be accepted).
Send to the following address (MARKED REGISTRATION):
Local Arrangements Chairperson, RMCAI-90
Computing Research Laboratory
Dept. 3CRL, Box 30001, NMSU
Las Cruces, NM 88003-0001, USA.
Name:_______________________________ E-mail_____________________________ Phone__________________________
Affiliation: ____________________________________________________
Fax: ____________________________________________________
Address: ____________________________________________________
____________________________________________________
____________________________________________________
COUNTRY__________________________________________
Organizing Committee RMCAI-90:
Paul Mc Kevitt Yorick Wilks
Research Scientist Director
CRL CRL
cut------------------------------------------------------------------------
--
Paul Mc Kevitt,
Computing Research Laboratory,
Dept. 3CRL, Box 30001,
New Mexico State University,
Las Cruces, NM 88003-0001, USA.
E-mail: INTERNET: paul@nmsu.edu
Fax: (+1 505)-646-6218
Phone: (+1 505)-646-5109/5466
Nil an la an gaothaithe la na scolb!!
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (01/16/90)
Vision-List Digest Mon Jan 15 09:38:15 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Request for Public Domain Image Processing Packages
3D-glasses
Connected Component Algorithm
Posting Call-for-papers of ICCV'90
Call for Papers Wang Conference
------------------------------
Date: Fri, 12 Jan 90 13:02:20 PST
From: Scott E. Johnston <johnston@odin.ads.com>
Subject: Request for Public Domain Image Processing Packages
Status: RO
I am collecting any and all public-domain image processing packages.
I plan on making them available to all via the vision-list FTP site
(disk space permitting). Send pointers and packages themselves to
johnston@ads.com (not vision-list@ads.com). Thanks.
----------------------------------------------------------------------
Subject: 3D-glasses
Date: Thu, 11 Jan 90 01:17:23 EST
From: Edward Vielmetti <emv@math.lsa.umich.edu>
Here's a pointer to info on the Sega 3D glasses. --Ed
------- Forwarded Message
From: jmunkki@kampi.hut.fi (Juri Munkki)
Subject: [comp.sys.mac.hardware...] Sega 3D glasses document fix 1.2
Date: 8 Jan 90 20:16:53 GMT
Followup-To: comp.sys.mac.hardware
Approved: emv@math.lsa.umich.edu (Edward Vielmetti)
This is patch 1.2 of the Sega 3D glasses interface document. It
supersedes versions 0.9, 1.0 and 1.1 of the document. Version 1.2 is
available with anonymous ftp from vega.hut.fi [130.233.200.42].
pub/mac/finnish/sega3d/
Version 0.9 and 1.0 of the document have the TxD+ and TxD- pins
reversed. This causes problems only with my demo software and can
be noticed easily, because both lenses show the same image. Fix
this problem by pulling out the TxD+ and TxD- pins from the miniDIN
connector, swap them and push back in.
Version 1.1 (which is what you have after you make the previous
change) has the tip and center of the glasses connector switched.
Again this doesn't cause any problems unless you use the demo
software. The spiro and Macintosh demos will clearly be inside
the screen and their perspectives will look wrong. To fix the
problem resolder the connector or change the software to swap
the meanings of left and right. If you intend to write for the
glasses, it might be a good idea to include an option to switch
left and right.
Juri Munkki jmunkki@hut.fi jmunkki@fingate.bitnet I Want Ne |
Helsinki University of Technology Computing Centre My Own XT |
------- End of Forwarded Message
------------------------------
Date: Thu, 11 Jan 90 14:16:52 EST
From: palumbo@cs.Buffalo.EDU (Paul Palumbo)
Subject: Connected Component Algorithm
I was wondering if anybody out there in net-land knows an image analysis
technique to locate connected components in digital images. In particular,
I am looking for an algorithm that can be implemented in hardware that makes
only one pass through the image in scan-line order and reports several simple
component features such as component extent (Minimum and Maximum X and Y
coordinates) and the number of foreground pixels in the component.
The project I am on is planning to design and develop custom image analysis
hardware to do this. We have developed an algorithm locally and was wondering
if somebody else has an easier method.
I know about the LSI Logic "Object Contour Tracer Chip" but this chip appears
to be too powerful (and slow) for this application. I had found some papers
by Gleason and Agin dated about 10 years ago but could not find the exact
details of their algorithm.
Does anybody else have a need for such hardware?
Any help or pointers on locating such an algorithm would be appreciated.
Paul Palumbo internet:palumbo@cs.buffalo.edu
Research Associate bitnet: palumbo@sunybcs.BITNET
226 Bell Hall csnet: palumbo@buffalo.csnet
SUNY at Buffalo CS Dept.
Buffalo, New York 14260
(716) 636-3407 uucp: ..!{boulder,decvax,rutgers}!sunybcs!palumbo
------------------------------
Date: Fri, 12 Jan 90 11:11:31 JST
From: tsuji%tsuji.ce.osaka-u.JUNET@relay.cc.u-tokyo.ac.jp (Saburo Tsuji)
Subject: Posting Call-for-papers of ICCV'90
Call for Papers
THIRD INTERNATIONAL CONFERENCE ON COMPUTER VISION
International House Osaka, Osaka, Japan
December 4-7, 1990
CHAIRS
General Chair:
Makoto Nagao, Kyoto University, Japan
E-mail: nagao@kuee.kyoto-u.ac.jp
Program Co-chairs:
Avi Kak, Purdue University, USA
E-mail:kak@ee.ecn.purdue.edu
Jan-Olof Eklundh, Royal Institute of Technology, Sweden
joe@bion.kth.se
Saburo Tsuji, Osaka University, Japan
tsuji@tsuji.ce.osaka-u.ac.jp
Local Arrangement Chair:
Yoshiaki Shirai, Osaka University, Japan
shirai@ccmip.ccm.osaka-u.ac.jp
THE CONFERENCE
ICCV'90 is the third International Conference devoted solely to
computer vision. It is sponsored by the IEEE Computer Society.
THE PROGRAM
The program will consist of high quality contributed papers on
all aspects of computer vision. All papers will be refereed by
the members of the Program Committee. Accepted papers will
be presented as long papers in a single track or as short pa-
pers in two parallel tracks.
PROGRAM COMMITTEE
The Program Committee consists of thirty prominent members
representing all major facets of computer vision.
PAPER SUBMISSION
Authors should submit four copies of their papers to Saburo Tsuji
at the address shown below by April 30, 1990. Papers must con-
tain major new research contributions. All papers will be re-
viewed using a double-blind procedure, implying that the identi-
ties of the authors will not be known to the reviewers. To make
this possible, two title pages should be included, but only one
containing the names and addresses of the authors; the title page
with the names and addresses of the authors will be removed prior
to the review process. Both title pages should contain the title
of the paper and a short (less than 200 words) abstract. Au-
thors must restrict the lengths of their papers to 30 pages; that
length should include everything, meaning the title pages, texts
(double-spaced), figures, bibliography, etc. Authors will be no-
tified of acceptance by mid-July. Final camera-ready papers,
typed on special forms, will be due mid-August.
Send To: Saburo Tsuji,
Osaka University, Department of Control Engineering, Toyonaka,
Osaka 560, Japan.
E-mail tsuji@tsuji.ce.osaka-u.ac.jp
------------------------------
Date: Fri, 12 Jan 90 02:06:41 EST
From: mike@bucasb.bu.edu (Michael Cohen)
Subject: Call for Papers Wang Conference
CALL FOR PAPERS
NEURAL NETWORKS FOR AUTOMATIC TARGET RECOGNITION
MAY 11--13, 1990
Sponsored by the Center for Adaptive Systems,
the Graduate Program in Cognitive and Neural Systems,
and the Wang Institute of Boston University
with partial support from
The Air Force Office of Scientific Research
This research conference at the cutting edge of neural network science and
technology will bring together leading experts in academe, government, and
industry to present their latest results on automatic target recognition
in invited lectures and contributed posters. Invited lecturers include:
JOE BROWN, Martin Marietta, "Multi-Sensor ATR using Neural Nets"
GAIL CARPENTER, Boston University, "Target Recognition by Adaptive
Resonance: ART for ATR"
NABIL FARHAT, University of Pennsylvania, "Bifurcating Networks for
Target Recognition"
STEPHEN GROSSBERG, Boston University, "Recent Results on Self-Organizing
ATR Networks"
ROBERT HECHT-NIELSEN, HNC, "Spatiotemporal Attention Focusing by
Expectation Feedback"
KEN JOHNSON, Hughes Aircraft, "The Application of Neural Networks to the
Acquisition and Tracking of Maneuvering Tactical Targets in High Clutter
IR Imagery"
PAUL KOLODZY, MIT Lincoln Laboratory, "A Multi-Dimensional ATR System"
MICHAEL KUPERSTEIN, Neurogen, "Adaptive Sensory-Motor Coordination
using the INFANT Controller"
YANN LECUN, AT&T Bell Labs, "Structured Back Propagation Networks for
Handwriting Recognition"
CHRISTOPHER SCOFIELD, Nestor, "Neural Network Automatic Target Recognition
by Active and Passive Sonar Signals"
STEVEN SIMMES, Science Applications International Co., "Massively Parallel
Approaches to Automatic Target Recognition"
ALEX WAIBEL, Carnegie Mellon University, "Patterns, Sequences and Variability:
Advances in Connectionist Speech Recognition"
ALLEN WAXMAN, MIT Lincoln Laboratory, "Invariant Learning and
Recognition of 3D Objects from Temporal View Sequences"
FRED WEINGARD, Booz-Allen and Hamilton, "Current Status and Results of Two
Major Government Programs in Neural Network-Based ATR"
BARBARA YOON, DARPA, "DARPA Artificial Neural Networks Technology
Program: Automatic Target Recognition"
CALL FOR PAPERS---ATR POSTER SESSION: A featured poster session on ATR
neural network research will be held on May 12, 1990. Attendees who wish to
present a poster should submit 3 copies of an extended abstract
(1 single-spaced page), postmarked by March 1, 1990, for refereeing. Include
with the abstract the name, address, and telephone number of the corresponding
author. Mail to: ATR Poster Session, Neural Networks Conference, Wang
Institute of Boston University, 72 Tyng Road, Tyngsboro, MA 01879. Authors
will be informed of abstract acceptance by March 31, 1990.
SITE: The Wang Institute possesses excellent conference facilities on a
beautiful 220-acre campus. It is easily reached from Boston's Logan
Airport and Route 128.
REGISTRATION FEE: Regular attendee--$90; full-time student--$70.
Registration fee includes admission to all lectures and poster session,
abstract book,
one reception, two continental breakfasts, one lunch, one dinner, daily
morning and afternoon coffee service. STUDENTS FELLOWSHIPS are available.
For information, call (508) 649-9731.
TO REGISTER: By phone, call (508) 649-9731; by mail, write for further
information to: Neural Networks, Wang Institute of Boston University, 72 Tyng
Road, Tyngsboro, MA 01879.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/01/90)
Vision-List Digest Wed Jan 31 11:37:36 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re: 3D-glasses
CFP, Israeli Conference
British Machine Vision Conference 1990
----------------------------------------------------------------------
Date: Fri, 26 Jan 90 16:31:16 IST
From: Shelly Glaser 011 972 3 545 0060 <GLAS%TAUNIVM.BITNET@CUNYVM.CUNY.EDU>
Subject: Re: 3D-glasses
Try also contacting Stereographics, at Box 2309, San Rafael, CA 94912
(415)459-4500, for information on special hardware/software for 3-D
display with computers from the PC up. It would be more expensive than
the Sega, but there are other differences as well. Tektronix, too, makes
3-D display equipment, but I do not have the address/phone for the
particular department that sells it.
Both systems use polarization encoding to switch one image to the right
eye and the next to the left; high refresh rate is used to avoide
flicker. Tektronix uses Liquid Crystal shutter on the monitor and plain
polarizers on eye glasses, so extra observers are cheap and there is no
electrical cord connected to the Glasses. Stereographics puts the
electronic shutter on the glasses and a plain polarizer on the screen,
which comes out less expensive for just few observers. Both systems have
color, and are available in several resolutions.
yours
Shelly Glaser
Department of Electronic, Communication, Control and Computer Systems
Faculty of Engineering
Tel-Aviv University
Tel-Aviv, Israel
TELEPHONE: 972 3 545-0060
FAX: 972 3 5413752
Computer network: GLAS@TAUNIVM.BITNET
glas@taunivm.tau.ac.il
glas%taunivm.bitnet@cunyvm.cuny.edu
Acknowledge-To: <GLAS@TAUNIVM>
------------------------------
Date: Fri, 26 Jan 90 10:05:12 EST
From: peleg@grumpy.sarnoff.com (Shmuel Peleg x 2284)
Subject: CFP, Israeli Conference
CALL FOR PAPERS
7th Israeli Conference on Artificial Intelligence and Computer Vision
Tel-Aviv, December 26-27, 1990
The conference is the joint annual meeting of the Israeli Association for
Artificial Intelligence, and the Israeli Association for Computer Vision
and Pattern Recognition, which are affiliates of the Israeli Information
Processing Association. The language of the conference is English.
Papers addressing all aspects of AI and Computer Vision, including, but
not limited to, the following topics, are solicited:
Image Processing, Computer Vision, and Pattern Recognition.
Visual Perception, Robotics, and Applications of Robotics and Vision.
Inductive inference, Knowledge Acquisition, AI and Education, AI Languages,
Logic Programming, Automated Reasoning, Cognitive Modeling, Expert Systems,
Natural Language Processing, Planning and Search, Knowledge Theory, Logics
of Knowledge.
Submitted papers will be refereed by the program committee, listed below.
Authors should submit 4 copies of a full paper. Accepted papers will appear
in the conference proceedings.
Papers should be received by the conference co-chairmen at the following
address by June 1st, 1990. Authors will be notified of accepted papers by
August 1st 1990.
VISION: AI:
Prof. A. Bruckstein Dr. Y. Feldman
7th AICV 7th AICV
Faculty of Computer Science Dept of Computer Science
Technion Weizmann Institute
32000 Haifa, Israel 76100 Rehovot, Israel
freddy@techsel.bitnet
Program Committee:
M. Balaban, M. Ben Bassat, R. Dechter, E. Gudes, T. Flash, D. Lehmann,
M. Luria, Y. Moses, U. Ornan, J. Rosenschein, E. Shapiro
Z. Meiri, A. Meizles, S. Peleg, M. Porat, M. Sharir, S. Ullman, M. Werman
H. Wolfson, Y. Yeshurun
------------------------------
Date: Mon, 29 Jan 90 14:42 GMT
From: Rob Series 0684 895784 <"SP4IP::SERIES%hermes.mod.uk"@relay.MOD.UK>
Subject: British Machine Vision Conference 1990
ANNOUNCEMENT AND CALL FOR PAPERS
BMVC 90
British Machine Vision Conference 1990
University Of Oxford
24th - 27th September 1990
Organised by:
The British Machine Vision Association and Society for Pattern Recognition
The Alvey Vision Conference became established as the premiere
annual UK national conference for Machine Vision and related
topics. The merger of the BPRA and Alvey Vision Club to form the
BMVA enables this successful series of conferences to be continued
with a similar flavour.
The emphasis will continue to be on UK research being undertaken
through national or international collaborative projects,
providing a forum for the presentation and discussion of the
latest results of investigations. Papers from other nations,
especially those collaborating with UK groups, are also very
welcome. A printed copy of the Proceedings will be available to
delegates at the conference, and a selection of the best papers
will be published separately in a special issue of Image and
Vision Computing Journal.
Contributions are sought on any novel aspect related to:
o Image Processing and Feature Extraction
o Robotic Vision and Sensor Fusion
o Object Recognition and Scene Analysis
o Practical Applications of Machine Vision
o Reconstruction of 3D Shape
o Model Based Coding
o Advanced Pattern Analysis
o Architectures for Vision Systems
o Computational Issues in Visual Perception
Papers will be reviewed by the BMVA Committee. Papers must not
exceed 6 pages of A4 including figures, double column in 10 point
type. A Poster session will again be held. Authors considering
submitting short papers describing preliminary results may prefer
to use this route. Note that posters (up to 4 sides) will be
included in the proceedings. Standard format headers to assist in
preparation of camera ready copy available from:
bmvc90@uk.ac.ox.robots
Separate cash prizes will be given for the two papers which are
judged by the programme committee:
(i) to make the best scientific contribution (sponsored by the
BMVA committee),
or
(ii) to have the greatest industrial potential (sponsored by
Computer Recognition Systems Ltd).
TIMETABLE OF DEADLINES (1990)]
7th May Six copies of short-form paper (1500 words), or
draft final-format papers (see above), to be
submitted to Dr A. Zisserman
4th June Last date for early registration at preferential
rate
11th June Notification of acceptance of papers.
16th July Camera-ready final paper (plus four additional
photocopies) to be received by the Programme
Chairman. Final date for posters.
24th Sept Conference registration.
REGISTRATION PROGRAMME
Dr RW Series, Dr A Zisserman,
BMVC90, BMVC90,
RSRE, Dept Engineering Science,
St Andrews Rd, Parks Road,
MALVERN, OXFORD.
Worcs. WR14 3PS OX1 3PJ
series@uk.mod.rsre az@uk.ac.ox.robots
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/09/90)
Vision-List Digest Thu Feb 08 19:53:44 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Edge detectors
Multisource Data Integration in Remote Sensing
NIPS-90 WORKSHOPS Call for Proposals
systematic biology & computing workshop
----------------------------------------------------------------------
Date: 1 Feb 90 16:30:17 GMT
From: Robert A Nicholls <ran@doc.imperial.ac.uk>
Subject: Edge detectors
Keywords: Edge Detectors, Canny
Organization: Dept. of Computing, Imperial College, London
Can anyone point me in the direction of an alternative source of J.Canny's
"Finding Edges and Lines in Images". It was originally a MIT AI Lab Report,
AI-TR-720, 1983. However, I can not find this report, I am sure I have seen
it or a similar article in a journal, though I can't remember which.
If anyone has implemented Canny's algorithms and wouldn't mind e-mailing them
to me I would be eternally grateful.
I am a third year research student looking at methods of incorporating
high-level knowledge into image segmentation.
Thanks for any help,
Bob.
------------------------------
Date: Thursday, 8 February 1990 17:06:44 EST
From: Dave.McKeown@maps.cs.cmu.edu
Subject: Conference on Multisource Data Integration in Remote Sensing
IAPR TC 7 Workshop on
Multisource Data Integration in Remote Sensing
University of Maryland University College
Center of Adult Education
College Park, Maryland, U. S. A.
June 14-15, 1990
The International Association for Pattern Recognition's Technical
Committee 7 on Applications in Remote Sensing is organizing a Workshop
on Multisource Data Integration in Remote Sensing. The workshop, which
is being co-sponsored by the NASA Goddard Space Flight Center,
Greenbelt, MD, will consist of invited and submitted papers in the
following areas:
o Remote-Sensing data sources and their characteristics
o Integrative methods for across-sensor data registration
o Gathering, validating and registering of ground reference data
o Development of multi-source data sets, and
o The utilization of multi-source data sets in Earth Science
applications.
Time will be scheduled for discussing tactics for facilitating the
exchange of multi-source data sets between investigators.
The NASA Goddard Space Flight Center will publish the Workshop
Proceedings as a NASA Conference Publication. The Workshop is scheduled
so as to feed into the IAPR's 10th International Conference on Pattern
Recognition, which will be held on June 17-21, 1990 at Atlantic City,
NJ. If interest warrants, a bus will be chartered to transport the
participants from College Park, MD to Atlantic City, NJ after the
Workshop.
Deadlines
February 28, 1990 Paper summary submission*
April 1, 1990 Author notification
June 14, 1990 Camera-ready manuscript due at Workshop
* 4 page, double spaced paper summary plus a 300 word single spaced
abstract on a separate (single) page. The abstract page should
include the paper title, and the name, mailing address,
affiliation, phone number, FAX number and electronic mail address
(if any) for each author. Abstracts will be published in final
program.
Paper Submission
Submit papers to: Dr. James C. Tilton, Mail Code 636, NASA Goddard
Space Flight Center, Greenbelt, MD 20771, U.S.A. Phone: (301) 286-9510.
Fax: (301) 286-3221. E-Mail: tilton@chrpisis.gsfc.nasa.gov
(tilton@[128.183.112.25]).
------------------------------
Date: Tue, 6 Feb 90 18:28:54 EST
From: jose@neuron.siemens.com (Steve Hanson)
Subject: NIPS-90 WORKSHOPS Call for Proposals
REQUEST FOR PROPOSALS
NIPS-90 Post-Conference Workshops
November 30 and December 1, 1990
Following the regular NIPS program, workshops on current topics
on Neural Information Processing will be held on November 30 and
December 1, 1990, at a ski resort near Denver. Proposals by
qualified individuals interested in chairing on of these
workshops are solicited.
Past topics have included: Rules and Connectionist Models;
Speech; Vision; Neural Network Dynamics; Neurobiology;
Computational Complexity Issues; Fault Tolerance in Neural
Networks; Benchmarking and Comparing Neural Network Applications;
Architectural Issues; Fast Training Techniques; VLSI; Control;
Optimization, Statistical Inference, Genetic Algorithms.
The format of the workshop is informal. Beyond reporting on past
research, their goal is to provide a forum for scientists
actively working in the field to freely discuss current issues of
concern and interest. Sessions will meet in the morning and in
the afternoon of both days, with free time in between for the
ongoing individual exchange or outdoor activities. Specific open
or controversial issues are encouraged and preferred as workshop
topics. Individuals interested in chairing a workshop must
propose a topic of current interest and must be willing to accept
responsibility for their group's discussion. Discussion leaders'
responsibilities include: arrange brief informal presentations
by experts working on this topic, moderate or lead the
discussion, and report its high points, findings and conclusions
to the group during evening plenary sessions, and in a short (2
page) summary.
Submission Procedure: Interested parties should submit a short
proposal for a workshop of interest by May 17, 1990. Proposals
should include a title and a short description of what the
workshop is to address and accomplish. It should state why the
topic is of interest or controversial, why it should be discussed
and what the targeted group of participants is. In addition,
please send a brief resume of the prospective workshop chair,
list of publications and evidence of scholarship in the field of
interest.
Mail submissions to:
Dr. Alex Waibel
Attn: NIPS90 Workshops
School of Computer Science
Carnegie Mellon University
Pittsburgh, PA 15213
Name, mailing address, phone number, and e-mail net address
(if applicable) must be on all submissions.
Workshop Organizing Committee:
Alex Waibel, Carnegie-Mellon, Workshop Chairman;
Kathie Hibbard, University of Colorado, NIPS Local Arrangements;
Howard Watchel, University of Colorado, Workshop Local Arrangements;
PROPOSALS MUST BE RECEIVED BY MAY 17,1990
Please Post
------------------------------
Date: Sat, 3 Feb 1990 10:54:52 PST
From: "Michael G. Walker" <walker@sumex-aim.stanford.edu>
Subject: systematic biology & computing workshop
WORKSHOP ANNOUNCEMENT:
Artificial Intelligence and Modern Computer Methods
in Systematic Biology (ARTISYST Workshop)
The Systematic Biology Program of the National Science Foundation is
sponsoring a Workshop on Artificial Intelligence, Expert Systems, and
Modern Computer Methods in Systematic Biology, to be held September 9
to 14, 1990, at the University of California, Davis. There will be
about 45 participants representing an even mixture of biologists and
computer scientists.
Expenses for participants will be paid, including hotel (paid directly
by the workshop organizers), food (per diem of US $35), and travel
(with a maximum of US $500 for travel expenses). Attendance at the
workshop is by invitation only.
These are the subject areas for the workshop:
Machine vision and feature extraction applied to systematics.
Expert systems, expert workstations and other tools for identification;
Phylogenetic inference and mapping characters onto tree topologies;
Literature data extraction and geographical data;
Scientific workstations for systematics;
The workshop will examine state-of-the-art computing methods and
particularly Artificial Intelligence methods and the possibilities
they offer for applications in systematics. Methods for knowledge
representation as they apply to systematics will be a central focus of
the workshop. This meeting will provide systematists the opportunity
to make productive contacts with computer scientists interested in
these applications. It will consist of tutorials, lectures on
problems and approaches in each area, working groups and discussion
periods, and demonstrations of relevant software.
Participants will present their previous or proposed research in a
lecture, in a poster session, or in a software demonstration session.
In addition, some participants will present tutorials in their area of
expertise.
Preference will be given to applicants who are most likely to continue
active research and teaching in this area. The Workshop organizers
welcome applications from all qualified biologists and computer
scientists, and strongly encourage women, minorities, and persons with
disabilities to apply.
If you are interested in participating, please apply by sending to the
workshop organizers the information suggested below:
1) your name, address, telephone number, and electronic mail address;
2) whether you apply as a computer scientist or as a biologist;
3) a short resume;
4) a description of your previous work related to the workshop topic;
5) a description of your planned research and how it relates to the workshop;
6) whether you, as a biologist (or as a computer scientist), have
taken or would like to take steps to establish permanent collaboration
with computer scientists (or biologists). A total of two pages or
less is preferred. This material will be the primary basis for
selecting workshop participants.
If you have software that you would like to demonstrate at the
workshop, please give a brief description, and indicate the hardware
that you need to run the program. Several PC's and workstations will
be available at the workshop.
Mail your completed application to:
Renaud Fortuner, ARTISYST Workshop Chairman,
California Department of Food and Agriculture
Analysis & Identification, room 340
P.O. Box 942871
Sacramento, CA 94271-0001
(916) 445-4521
E-mail: rfortuner@ucdavis.edu
APPLICATIONS RECEIVED AFTER APRIL 15, 1990 WILL NOT BE ACCEPTED
Notification of acceptance of proposal will be made before May 31, 1990
For further information, contact Renaud Fortuner, Michael Walker,
Program Chairman, (Walker@sumex-aim.stanford.edu), or a member of the
steering committee:
Jim Diederich, U.C. Davis (dieder@ernie.berkeley.edu)
Jack Milton, U.C. Davis (milton@eclipse.stanford.edu)
Peter Cheeseman, NASA AMES (cheeseman@pluto.arc.nasa.gov)
Eric Horvitz, Stanford University (horvitz@sumex-aim.stanford.edu)
Julian Humphries, Cornell University (lqyy@crnlvax5.bitnet)
George Lauder, U.C Irvine (glauder@UCIvmsa.bitnet)
F. James Rohlf, SUNY (rohlf@sbbiovm.bitnet)
James Woolley, Texas A&M University (woolley@tamento.bitnet)
The following is a brief description of problems in systematics
related to machine vision. Abstracts for the four other topic areas are
available from Renaud Fortuner or Michael Walker.
MACHINE VISION AND FEATURE EXTRACTION APPLIED TO SYSTEMATICS
F. James Rohlf
Department of Ecology and Evolution
State University of New York
Stony Brook, NY 11794-5245
Most data presently used in systematics are collected through the
visual examination of specimens. Features are usually found by the
visual comparison of specimens and most measurements are taken
visually. These activities can be quite time consuming. Thus there is
the potential for saving a systematist's time if appropriate hardware
and software were available that would enable routine measurements to
be made automatically. This would permit more extensive large- scale
quantitative studies.
But automation is difficult in systematics since the features to
be measured are usually not easily separated from the background,
i.e., the visual scene is often cluttered, and the structures of
interest may not have distinct colors or intensities as in many
industrial applications of image analysis. The problem is especially
difficult for certain groups of organisms. The problem is further
complicated due to biological variability. One usually cannot depend
upon homologous structures having consistent geometrical features that
can be used to automatically identify landmarks of interest. Other
important complications are that most structures of interest are
3-dimensional and that the "texture" of surfaces often contains
taxonomically useful information. Both aspects are difficult to
capture with presently available hardware and software.
For these reasons present applications of image analysis in
systematics have been quite modest. In studies where data are
recorded automatically, time is spent simplifying the image. For
example, structures of interest are physically separated from the rest
of the specimen and placed upon a contrasting plain background so the
outline can be found with little error. Alternatively, an
investigator can identify structures of interest by pointing to them
with a mouse, watching how a program finds an outline, and them
editing the trace if necessary. Working from this outline, additional
landmarks can be identified by the operator. In some cases these
landmarks can be associated with geometrical features of the outline
and it will be possible for the software to help the operator to
accurately locate these points. Due to the difficulty of solving the
general problems of the automatic analysis of complex biological
scenes, a more immediate goal should be to develop powerful tools that
a systematist can interact with to isolate structures, locate
landmarks, and compute various measurements. In addition, it would be
desirable for the software to "learn" how to recognize the structures
so that the process will go faster as both the software and the
systematist become more experienced.
Once the structures and landmarks have been found they are usually
recorded so that, if necessary, additional measurements can be made
without having to go back to the original image. These are usually in
the form of x,y-coordinates of landmarks or chain-coded outlines. For
very large studies, methods to compress this raw descriptive
information need to be used.
The features that are measured are usually the same types of
features that would have been measured by hand -- 2-dimensional
distances between landmarks or angles between pairs of landmarks. In
some studies the features used are parameters from functions (such as
Fourier, cubic splines, Bezier curves) fitted to the shapes of
structures or of entire outlines of organisms. More work is needed to
develop new types of features and to evaluate the implications of
their use relative to traditional methods.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/21/90)
Vision-List Digest Tue Feb 20 17:40:23 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Others ways to do triangulation sought
Request for advice on equipment
Range data archive
Currently available packages for image processing
digital photography
CFP: IEEE TPAMI Special Issue on 3D Scene Interpretation
CVGIP TOC, Vol. 50, No. 1, March 1990
Conference on Visual Information Assimilation in Man and Machine
VBC - 90 Preliminary Conference Announcement
----------------------------------------------------------------------
Date: 19 Feb 1990 11:52:39-GMT
From: aa538 <aa538%city.ac.uk@NSFnet-Relay.AC.UK>
Subject: Others ways to do triangulation sought
I am developing a representation for image structure which involves
triangulating a set of (mostly) irregularly spaced data points. The
heuristic triangulation algorithm I developed is quite fast, but regularly
makes mistakes. I would be grateful if anyone could provide code (preferably C)
to perform the triangulation more robustly. Delauny triangulation is the only
type I know, but any one would probably be fine.
Paul Rosin
Machine Vision Group
Centre for Information Engineering
Dept. Electronic, Electrical, and Information Engineering
City University
Northampton Square
London, ECIV OHB
------------------------------
Date: Sun, 18 Feb 90 23:18:12 EST
From: yehuda@acsu.buffalo.edu (yehuda newberger)
Subject: request for advice on equipment
I need information on what kind of monitor and video card would be
appropriate for work in image analysis on MSDOS type equipment. I have
a 386 running MSDOS. Typically, I want to display 256 by 256 pixels
with 256 different simultaneous shades of gray or colors. I would prefer
to spend less than $1000 . My address is Edward Newberger
90 Huntington Avenue
Apt 104
Buffalo, New York 14214
------------------------------
Date: Mon, 19 Feb 90 11:45:59 EST
From: flynn@pixel.cps.msu.edu (Patrick J. Flynn)
Subject: Range data archive
I've made 44 range images (obtained from our Technical Arts
scanner) available for anonymous ftp from:
styrofoam.cps.msu.edu (IP address 35.8.56.144)
in the pub/images directory.
Some images contain one object, some contain several, with various
amounts of occlusion.
Direct *specific* questions about the images to me (flynn@cps.msu.edu).
General questions about range sensing are best answered by reading
the surveys by Jarvis (PAMI '83), Nitzan (PAMI '88), or Besl
(in the `Advances in Machine Vision' book by J. Sanz, pub. by Springer).
Here is the text of the README file in the images directory.
This directory contains a bunch of range images produced by the
MSU Pattern Recognition and Image Processing Lab's Technical
Arts 100X scanner (aka `White scanner'). You are free to use
these images to test your algorithms. If the images are to appear
in a published article, please acknowledge the MSU PRIP Lab as
the source of the images (you don't have to mention my name, though).
File format: rather than deal with all the goofy standards out
there for images (and to preserve the floating-point representation),
these images are compressed ASCII text files. Beware: they expand by
about 10x when uncompressed. I recommend that you keep them
compressed to save disk space. Many of you will probably convert
these files to your own `local' image format anyway.
Each image file has a three-line header giving the number of rows and
columns. This is followed by four images. The first is the
so-called 'flag' image, where a pixel value of 1 means the corresponding
(x,y,z) values at that pixel are valid. If the flag value is zero, you
should ignore the (x,y,z) components for that pixel.
Following the flag image is the image of X-coordinates, the image
of Y-coordinates, and the image of Z-coordinates. All are
floating-point images. Our White scanner is configured so that
each stripe of range values occupies one column in the image. We
sweep the object under the stripe with an XY table to get an image.
So the X coordinate image is a linear ramp; the X value is taken
from the absolute position of the X stage in the XY table (we don't
do anything in the Y direction at present). The Y value depends
on the column number of the pixel, and the Z value is the measured
range (in our lab, Z is the height above a table).
You can use the 3D coordinates of each range pixel, or you can
throw away the X and Y images, and concern yourself with the Z-value
alone. Note that the `aspect ratio' of the image doesn't
have to be 1, although I try to keep it in the neighborhood of 1.
Availability: I will try to keep these images available on
styrofoam.cps.msu.edu (35.8.56.144) until I leave MSU this summer.
If my next job has machines with internet access and some disk space,
I'll put them there.
Remember to use binary mode when you transfer the images.
------------------------------
Date: Wed, 14 Feb 90 17:25:43 PST
From: Scott E. Johnston <johnston@zooks.ads.com>
Subject: Currently available packages for image processing
The following is a list of currently available packages of image
processing source code. Some packages are public domain, others are
one-time licenses. I would welcome any additions or corrections to
this list. Thank you for all contributions for date.
Scott E. Johnston
johnston@ads.com
Advanced Decision Systems, Inc.
Mountain View, CA 94043
***********
ALV Toolkit
Contact: alv-users-request@uk.ac.bris.cs
Description:
Public domain image processing toolkit written by Phill Everson
(everson@uk.ac.bris.cs). Supports the following:
- image display
- histogram display
- histogram equalization
- thresholding
- image printing
- image inversion
- linear convolution
- 27 programs, mostly data manipulation
***********
BUZZ
Contact: Tehnical: Licensing:
John Gilmore Patricia Altman
(404) 894-3560 (404) 894-3559
Artificial Intelligence Branch
Georgia Tech Research Institute
Georgia Institute of Technology
Atlanta, GA 30332
Description:
BUZZ is a comprehensive image processing system developed at Georgia
Tech. Written in VAX FORTRAN (semi-ported to SUN FORTRAN), BUZZ
includes algorithms for the following:
- image enhancement
- image segmentation
- feature extraction
- classification
***********
LABO IMAGE
Contact: Thierry Pun Alain Jacot-Descombes
+(4122) 87 65 82 +(4122) 87 65 84
pun@cui.unige.ch jacot@cuisun.unige.ch
Computer Science Center
University of Geneva
12 rue du Lac
CH-1207
Geneva, Switzerland
Description:
Interactive window based software for image processing and analysis.
Written in C. Source code available. Unavailable for use in
for-profit endeavours. Supports the following:
- image I/O
- image display
- color table manipulations
- elementary interactive operations:
- region outlining
- statistics
- histogram computation
- elementary operations:
- histogramming
- conversions
- arithmetic
- images and noise generation
- interpolation: rotation/scaling/translation
- preprocessing: background subtraction, filters, etc;
- convolution/correlation with masks, image; padding
- edge extractions
- region segmentation
- transforms: Fourier, Haar, etc.
- binary mathematical morphology, some grey-level morphology
- expert-system for novice users
- macro definitions, save and replay
Support for storage to disk of the following:
- images
- vectors (histograms, luts)
- graphs
- strings
***********
NASA IP Packages
VICAR
ELAS -- Earth Resources Laboratory Applications Software
LAS -- Land Analysis System
Contact: COSMIC (NASA Facility at Georgia Tech)
Computer Center
112 Barrow Hall
University of Georgia
Athens, GA 30601
(404) 542-3265
Description:
VICAR, ELAS, and LAS are all image processing packages available from
COSMIC, a NASA center associated with Georgia Tech. COSMIC makes
reusable code available for a nominal license fee (i.e. $3000 for a 10
year VICAR license).
VICAR is an image processing package written in FORTRAN with the
following capability:
- image generation
- point operations
- algebraic operations
- local operations
- image measurement
- annotation and display
- geometric transformation
- rotation and magnification
- image combination
- map projection
- correlation and convolution
- fourier transforms
- stereometry programs
"ELAS was originally developed to process Landsat satellite data, ELAS
has been modified over the years to handle a broad range of digital
images, and is now finding widespread application in the medical
imaging field ... available for the DEC VAX, the CONCURRENT, and for
the UNIX environment." -- from NASA Tech Briefs, Dec. 89
"... LAS provides a flexible framework for algorithm development and
the processing and analysis of image data. Over 500,000 lines of code
enable image repair, clustering, classification, film processing,
geometric registration, radiometric correction, and manipulation of
image statistics." -- from NASA Tech Briefs, Dec. 89
***********
OBVIUS
Contact: for ftp --> whitechapel.media.mit.edu
otherwise --> heeger@media-lab.media.mit.edu
MIT Media Lab Vision Science Group
(617) 253-0611
Description:
OBVIUS is an object-oriented visual programming language with some
support for imaging operations. It is public domain CLOS/LISP
software. It supports a flexible user interface for working with
images. It provides a library of image processing routines:
- point operations
- image statistics
- convolutions
- fourier transforms
***********
POPI (DIGITAL DARKROOM)
Contact: Rich Burridge
richb@sunaus.sun.oz.AU
-- or --
available for anonymous ftp from ads.com
(pub/VISION-LIST-BACKISSUES/SYSTEMS)
Description:
Popi was originally written by Gerard J. Holzmann - AT&T Bell Labs.
This version is based on the code in his Prentice Hall book, "Beyond
Photography - the digital darkroom," ISBN 0-13-074410-7, which is
copyright (c) 1988 by Bell Telephone Laboratories, Inc.
***********
VIEW (Lawrence Livermore National Laboratory)
Contact: Fran Karmatz
Lawrence Livermore National Laboratory
P.O. Box 5504
Livermore, CA 94550
(415) 422-6578
Description:
Window-based image-processing package with on-line help and user
manual. Multidimensional (2 and 3d) processing operations include:
- image display and enhancement
- pseudocolor
- point and neighborhood operations
- digital filtering
- fft
- simulation operations
- database management
- sequence and macro processing
Written in C and FORTRAN, source code included. Handles multiple
dimensions and data types. Available on Vax, Sun 3, and MacII.
------------------------------
Date: Tue, 20 Feb 90 18:38 EST
From: DONNELLY@AMY.SKIDMORE.EDU
Subject: digital photography
Please help me obtain information about the manipulation of
photographic images digitally.
What are the best products that can be used with a MacIIcx?
Did anyone attend the recent conference on Digital Photography
that took place in Wash DC?
Are there any new interesting products?
Are there any good books on the subject?
Thanks for your assistance.
Denis Donnelly
donnelly@amy.skidmore.edu
------------------------------
Date: Mon, 19 Feb 90 11:33:25 EST
From: flynn@pixel.cps.msu.edu (Patrick J. Flynn)
Subject: CFP: IEEE TPAMI Special Issue on 3D Scene Interpretation
Call for Papers
Special Issue of the IEEE Transactions on
Pattern Analysis and Machine Intelliegnce
on
Interpretation of 3D Scenes
Papers are solicited for a Special Issue of the IEEE Transactions on
Pattern Analysis and Machine Intelligence which will address the
subject of Interpretation of 3D Scenes. The issue is scheduled for
publication in September, 1991. The Guest Editors for the special issue
will be Anil Jain of Michigan State University and Eric Grimson of
M.I.T.
The interpretation of 3D scenes is a difficult yet an important area of
research in computer vision. Advances in sensors that directly sense in
3D and progress in passive 3D sensing methods have resulted in a steady
but not spectacular progress in 3D scene interpretation. The quality of
sensed data is getting better and faster hardware presents more
alternatives for processing it. However, the problems of object
modeling and matching still pose difficulties for general real world
scenes. Problems in 3D sensing, modeling, and interpretation are being
investigated by a number of vision researchers in a variety of
contexts. The goal of the special issue is to gather significant
research results on sensing, modeling, and matching into one volume
which specifically addresses these issues.
Papers describing novel contributions in all aspects of 3D scene interpretation
are invited, with particular emphasis on:
-- 3D sensing technologies, both active (laser, sonar, etc.) and
passive (stereo, motion vision, etc.),
-- 3D object recognition, both from 3D data and from 2D data,
-- 3D navigation and path planning
-- novel object representations that support 3D interpretation
-- applications (e.g. cartography, inspection, assembly, navigation)
-- representation and indexing of large libraries of objects
-- CAD-based 3d vision
-- architectures for 3D interpretation
We particularly encourage papers that address one or more of these
issues or related issues in 3D interpretation, especially in the context
of complex scenes. While both theoretical and experimental contributions
are welcomed, contributions in which new ideas are
tested or verified on real data are specially sought.
All papers will be subjected to the normal PAMI review process. Please
submit four copies of your paper to:
Eric Grimson
M.I.T. AI Laboratory
545 Technology Square
Cambridge, MA 02139
The deadline for submission of manuscript is October 1, 1990. For further
information, contact Anil Jain (517-353-5150, jain@cps.msu.edu)
or Eric Grimson (617-253-5346, welg@ai.mit.edu).
------------------------------
Date: Fri, 16 Feb 90 14:59:58 -0800
From: bertolas@cs.washington.edu (William Bertolas)
Subject: CVGIP TOC, Vol. 50, No. 1, March 1990
Computer Vision, Graphics, and Image Processing
Volume 50, Number 1, March 1990
CONTENTS
M.J. Korsten and Z. Houkes. The Estimation of Geometry and Motion of a
Surface from Image Sequences by Means of Linearization of a Parametric
Model, p. 1.
Clifford A. Shaffer and Hanan Samet. Set Operations for Unaligned Linear
Quadtrees, p. 29.
Phillip A. Veatch and Larry S. Davis. Efficient Algorithms for Obstacle
Detection Using Range Data, p. 50.
David C. Knill and Daniel Kersten. Learning a Near-Optimal Estimator for
Surface Shape from Shading, p. 75.
NOTE
Amelia Fong. Algorithms and Architectures for a Class of Non-Linear
Hybrid Filters, p. 101.
Hug-Tat Tsui, Ming-Hong Chan, Kin-Cheong Chu, and Shao-Hua Kong.
Orientation Estimation of 3D Surface Patches, p. 112.
BOOK REVIEW
Michael Lachance. An Introduction to Splines for Use in Computer
Graphics and Geometric Modeling. By R.H. Bartels, J.C. Beatty,
and B.A. Barsky, p. 125.
ABSTRACTS OF PAPERS ACCEPTED FOR PUBLICATION, p. 000.
------------------------------
Date: 16 Feb 90 20:23 GMT
From: sinha@caen.engin.umich.edu (SARVAJIT S SINHA)
Subject: Conference on Visual Information Assimilation in Man and Machine
Keywords: Conference, Call for Participation, Vision, Information Assimilation
Organization: U of M Engineering, Ann Arbor, Mich.
CALL FOR PARTICIPATION
CONFERENCE ON VISUAL INFORMATION ASSIMILATION
IN MAN AND MACHINE
University of Michigan,
Ann Arbor, MI
June 27-29, 1990
In the last 20 years a variety of computational, psychological and neuro-
biological models of vision have been proposed. Few of these models have
presented integrated solutions; most have restricted themselves to a
single modality such as stereo, shading, motion, texture or color.
We are hosting a 3 day conference be held June 27-29, 1990 at the University
of Michigan, which will bring together leading researchers from each of
these academic areas to shed new light on the problem of how visual
information is assimilated in both man and machine. We have invited
researchers from both academic instituitions and research centers in order
to increase the cross-pollenation of ideas.
Among the questions that we anticipate to be addressed by all
perspectives are: What are the possible stages and representations
for each visual modality? How is contradictory visual information
dealt with? Is there in natural vision systems (and should there be
in computer vision) one coherent representation of the world---a
single model? If a single model will suffice, how (and where in
neurobiology) can visual information be combined into such a model?
If a single model will not suffice, or are there reasons to
believe that there are ways of partitioning visual information
among multiple models that are more likely to be used in man and
useful in machines?
Invited Talks
Irving Biederman (University of Minnesota)
Human Object Recognition
Stephen M. Kosslyn (Harvard University)
Components of High-Level Vision
Whitman Richards (MIT) and Allen Jepson (Univ. of Toronto)
What is Perception?
Geoffrey R. Loftus (Univ. of Washington)
Effects of Various Types of Visual Degradation
on Visual Information Acquisition
Barry J. Richmond (National Inst. of Mental Health)
How Single Neuronal Responses Represent Picture
Features Using Multiplexed Temporal Codes
Patrick Cavanagh (Harvard University)
3D Representation
Daniel Green (University of Michigan)
Control of Visual Sensitivity
Laurence Maloney (New York University)
Visual Calibration
Misha Pavel (Stanford University)
Integration of Motion Information
Brian Wandel (Stanford University)
Estimation of Surface Reflectance and Ambient Illumination
Klaus Schulten (Univ. of Illinois)
A Self-Organized Network for Feature Extraction
John K. Tsotsos (Univ. of Toronto)
Attention and Computational Complexity of
Visual Information Processing
Shimon Ullman (Weizmann Inst-MIT)
Visual Object Recognition
For an extended e-mail announcement, send a message to
iris@caen.engin.umich.edu
For further information contact the University of Michigan Extension Service,
Department of Conferences and Institutes, 200 Hill Street, Ann Arbor, MI
48104-3297. Telephone 313-764-5305.
Sarvajit Sinha sinha@caen.engin.umich.edu
157, ATL Bldg,University of Michigan 313-764-2138
------------------------------
Date: 19 Feb 90 14:08:42 GMT
From: arkin%pravda@gatech.edu (Ronald Arkin)
Subject: VBC - 90 Preliminary Conference Announcement
Keywords: visualization, conference, biomedical
Organization: Georgia Tech AI Group
VBC '90
PRELIMINARY CONFERENCE PROGRAM
Georgia Institute of Technology
and
Emory University School of Medicine
host the
First Conference on
Visualization in Biomedical Computing
May 22-25, 1990
RITZ-CARLTON BUCKHEAD
ATLANTA, GEORGIA
PURPOSE
The goal of the First Conference on Visualization in Biomedical Computing
(VBC) is to help define and promote the emerging science of visualization
by bringing together a multidisciplinary, international group of researchers,
scientists, engineers, and toolmakers engaged in all aspects of scientific
visualization in general, and visualization in biomedical computing in
particular.
THEME
Visualization in scientific and engineering research is a rapidly emerging
discipline aimed at developing approaches and tools to facilitate the inter-
pretation of, and interaction with, large amounts of data, thereby allowing
researchers to "see" and comprehend, in a new and deeper manner, the systems
they are studying. Examples of approaches to scientific visualization include
the dynamic presentation of information in three dimensions, development of
dynamic methods to interact with and manipulate multidimensional data, and
development of models of visual perception that enhance interpretive and
decision-making processes. Examples of visualization tools include graphics
hardware and software to graphically display and animate information, as well
as environments that facilitate human-machine interaction for the interpreta-
tion of complex systems. Examples of applications of visualization in biomed-
ical computing include presentation of anatomy and physiology in 3D, animated
representation of the dynamics of fluid flow, and graphical rendering of bio-
molecular structures and their interactions.
AUDIENCE
The presentations, discussions, and interactions by and between participants
will be of interest to scientists, engineers, medical researchers, clini-
cians, psychologists, and students interested in various aspects of visualiza-
tion.
COOPERATING/CO-SPONSORING ORGANIZATIONS
Alliance for Engineering in Medicine and Biology
American Association of Physicists in Medicine
Emory-Georgia Tech Biomedical Technology Research Center
Emory University School of Medicine
Georgia Institute of Technology
IEEE CS Technical Committee on Computer Graphics
IEEE Computer Society
IEEE Engineering in Medicine and Biology Society
Institute of Electrical and Electronics Engineers (IEEE)
International Federation for Medical and Biological Engineering
International Medical Informatics Association
National Science Foundation
OVERVIEW OF VBC 90
The technical program of VBC 90 will consist of:
o One day of tutorial courses by leading experts
o A plenary session highlighting invited speakers
o Two parallel tracks of contributed papers representing both
theoretical and application areas of visualization in biomedical
computing
o A series of panels on issues of controversy or of current interest,
open for discussions among all attendees
o Technical exhibits by numerous commercial vendors of visualization
technologies
The remainder of the VBC 90 program includes continental
breakfast each morning, refreshment breaks each day, an evening
reception, and dinner accompanied by a laser show at Stone
Mountain. Registrants who wish to do so may also obtain
continuing medical education credit. A tear-off registration
panel is included with this program announcement.
TUTORIALS Tutorial courses take place Tuesday May 22 from 8 AM
through 6:30 PM. Each course lasts one half-day (approximately
four hours) and there are a total of four courses offered from
which each registrant can choose two. The four tutorials are:
Morning Afternoon
Tu1a Volume Rendering Tu2a Biomedical Visualization
Tu1b Human Visual Performance Tu2b Stereoscopic Visualization
Techniques
PLENARY SESSION Invited papers will be presented during the first
morning session (W1) Wednesday at 8:30 AM. The distinguished
speakers and their respective talks are:
Dr. HENRY FUCHS, University of North Carolina
Future High-Speed Systems for Biomedical Visualization
Dr. RICHARD FELDMANN, National Institutes of Health
Visualizing The Very Small: Molecular Graphics
___________________________
TECHNICAL PRESENTATIONS Two parallel tracks of contributed
papers will be offered, representing diverse theoretical and
applications-related research topics in biomedical visualization.
The presentation topics and their respective sessions are
organized as follows:
WEDNESDAY AM
o Volume Visualization (W2a)
o Biomedical Applications I: Cells, Molecules, and Small Systems (W2b)
WEDNESDAY PM
o Models of Visualization (W3a)
o Computer Vision in Visualization I: Segmentation (W3b)
THURSDAY AM
o Artificial Intelligence and Inexact Visualization (T1a)
o Biomedical Applications II: Cardiovascular system (T1b)
o Visual Perception (T2a)
o Biomedical Applications III: Flow and MRI Studies (T2b)
THURSDAY PM
o Human-Machine Interfaces (T3a)
o Systems and Approaches I: System Design (T3b)
FRIDAY AM
o Systems and Approaches II: Algorithms (F1a)
o Computer Vision II: Analysis of Imagery II (F1b)
o Mathematical and Computational Models (F2a)
o Biomedical Applications IV: Treatment Planning (F2b)
FRIDAY PM
o Visualization in Medical Education and General Applications (F3a)
o Biomedical Applications V: Tools and Techniques (F3b)
PANELS Two concurrent panels will take place on the afternoons of
both Wednesday and Thursday. The panels are:
Wednesday Afternoon
o Surface Versus Volume Rendering (W4a)
o Chaos and Fractals in Electroencephalography (W4b)
Thursday Afternoon
o The Role of 3D Visualization in Radiology and Surgery (T4a)
o Visualization in the Neurosciences (T4b)
CONFERENCE REGISTRATION
The registration fee for members of Cooperating/Co-sponsoring Organizations
is $295 prior to March 31. The registration fee after this date is $345. For
non-members, the registration fee is $345 prior to march 31 and $395 after
this date. The special student rate is $50. (Proceedings and reception
tickets are not included at the special student rate, but may be purchased
separately.) The registration fee includes conference registration,
proceedings, reception, refreshments, and other amenities involved in making
this a rewarding learning experience.
TUTORIAL REGISTRATION
The tutorial registration fee is $175 per tutorial for attendees registering
prior to March 31 and $215 for attendees registering after this date.
Attendees will receive the special discounted rate of $275 for two tutorials
before March 31. The special tutorial registration fee for students is $95
per tutorial or $150 for two tutorials prior to March 31, and $125 per
tutorial or $190 for two tutorials after this date. The tutorial registration
fee includes course notes and refreshments.
ACCOMMODATIONS
Hotel arrangements are to be handled by the individual directly with The
Ritz-Carlton Buckhead. To reserve your room, you may call the hotel directly
toll free at (800) 241-3333 or (404) 237-2700. A limited number of rooms
have been made available at the special group rate of $110 single or $119
double (plus tax). Please mention "Visualization in Biomedical Computing."
Reservations should be made as soon as possible but not later than March 31.
DISCOUNT AIR TRANSPORTATION
We have made special arrangements to provide you with a 40% discount off the
normal coach fare, no penalties, on Delta Air Lines. Discounts on restricted
supersaver fares are also available. To make your reservations, call
(800) 288-4446 toll free and refer to "Emory University's Delta File No.
A18445.
IMPORTANT DATES
Early registration: March 15 1990
Special hotel room rate guaranteed through: March 15 1990
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (02/23/90)
Vision-List Digest Thu Feb 22 16:46:13 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: shape decomposition Refs for Visual Analysis Programming Series 100 frame grabber (Imaging Tech. Inc.) ---------------------------------------------------------------------- From: mtc%aifh.edinburgh.ac.uk@NSFnet-Relay.AC.UK Date: Wed, 21 Feb 90 13:57:17 GMT Subject: shape decomposition Can anybody out there mention references about shape decomposition in 3D? The main concern is how to define a "subpart" in a 3D shape, the applicative problem how to segment a range image into significant subparts (subvolumes) Thanks in advance Manuel Trucco Dept. of Artif. Intelligence, University of Edinburgh, 5 Forrest Hill, EH1 2QL, Edinburgh, Scotland. E-mail: mtc@edai.ed.ac.uk ------------------------------ Date: 21 Feb 90 16:20:42 GMT From: M Cooper <maggie@castle.edinburgh.ac.uk> Subject: Refs for Visual Analysis Organization: Edinburgh University Computing Service I'm looking for references to work on analysis of the meaning of shapes within images, e.g. the machine equivalent of the human knowledge that * is an asterisk, or that a picture of a pig represents a pig. I'm interested in work that looks at semantic image analysis, beyond the early robotic vision systems. The problem I'm looking at may be seen as abstracting physical features or regularities from a class of images, then matching the images to linguistically based knowledge. We could use a template based approach or some kind of visual-spatial grammar to describe the morphology of object-images, and mapping rules for semantics. I guess you'll have gathered that this is all new to me, so any references for work on visual languages, image analysis, graphical lexicons, etc. will be gratefully received. Thanks, Maggie ------------------------------ Date: 22 Feb 90 17:02:11 GMT From: walt.cc.utexas.edu!ycy@cs.utexas.edu (Joseph Yip) Subject: Programming Series 100 frame grabber (Imaging Tech. Inc.) Organization: The University of Texas at Austin, Austin, Texas We bought a Series 100 frame grabber board from Imaging Technology Inc. The software that comes with the board should include the Toolbox software which has some source programs on how to program the board. We are installing the board on a Sun system. Does anyone out there who has the Toolbox software and would like to send it to me? Or does anyone have any experience in programming the Series 100 frame grabber board on the Sun or Unix system? Thank Joseph Yip Email: ycy@happy.cs.utexas.edu ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/02/90)
Vision-List Digest Thu Mar 01 10:23:53 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
3D IMAGE Reconstruction.
Pixar for image processing
range-hardware
Workshop: Adap. Neural Nets & Statistical Patt. Recog.
----------------------------------------------------------------------
Date: Fri, 23 Feb 90 10:48:12 +0000
From: P.Refenes@Cs.Ucl.AC.UK
Subject: 3D IMAGE Reconstruction.
Can anyone out there mention references about 3-D image
reconstruction. I am looking for the best review paper on techniques
for 3D Image reconstruction. Failing that I could do with the second
best, or with any paper or descent reference. The particular problem
that we have is to re-construct a 3-D image of slides of skin
(histopathology).
Thanks in advance.
Paul Refenes
Department of Computer Science
University College London
Gower Street, WC1 6BT.
------------------------------
Date: Fri, 23 Feb 90 09:35:07 CST
From: fsistler@gumbo.age.lsu.edu
Subject: Pixar for image processing
I am using a Pixar II with a SparcStation 4/370 for image analysis and
processing, and am trying to find a users group network where Pixar
users communicate. Can anyone tell me if such a group exists, and how
I can join?
I would appreciate any help that anyone would offer.
Fred Sistler
Louisiana State University
------------------------------
Date: Wed, 28 Feb 90 11:37:02 est
From: "Y." (Greg)Shiu <yshiu@thor.wright.edu>
Subject: range-hardware
Does anybody know of companies that sell dense ranging devices, using
time of flight or triangulation? And what are their approximate prices?
I have heard that ranging system are expensive (around 100K),
so I may want to buy a plane laser projector for building my own
triangulation based range sensor but I dont know which companies
sells plane laser devices.
Greg Shiu
Department of Electrical Engineering
Wright State University, Dayton, OH 45435
phone: (513) 873-4254
email: yshiu@cs.wright.edu
------------------------------
Date: Mon, 26 Feb 90 19:08:29 EST
From: flynn@pixel.cps.msu.edu (Patrick J. Flynn)
Subject: Workshop: Adap. Neural Nets & Statistical Patt. Recog.
Workshop on
Artificial Neural Networks & Pattern Recognition
Sponsored by
The International Association for Pattern Recognition (IAPR)
Sands Hotel
Atlantic City, New Jersey
June 17, 1990
Recent developments in artificial neural networks (ANN's) have caused a
great deal of excitement in the academic, industrial, and defense
communities. Current ANN research owes much to several decades of work
in statistical pattern recognition (SPR); indeed, many fundamental
concepts from SPR have recently found new life as research topics when
placed into the framework of an ANN model.
The aim of this one-day workshop is to provide a forum for itneraction
between the leading researchers from the SPR and ANN fields. As
pattern recognition practioners, we seek to address the following
issues:
**In what ways do artificial neural networks differ from the well-known
paradigms of statistical pattern recognition? Are there concepts in
ANN for which no counterpart in SPR exists (and vice versa?)
**What benefits can come out of interaction between ANN and SPR researchers?
**What advantages, if any, does ANN techniques have over SPR methods in
dealing with real world problems such as object recognition, pattern
classification, and visual environment learning?
Tentative Program
8:00 Registration
8:30 Issues in ANN and SPR, Laveen Kanal, University of Maryland
9:15 Links Between ANN's & SPR, Paul Werbos, National Science Foundation
10:00 Coffee Break
10:30 Generalization & Discovery in Adaptive Pattern Recognition, Y. Pao,
Case Western Reserve University
11:15 Character Recognition, Henry Baird, AT&T Bell Labs
12:00 LUNCH
1:30 Target Recognition, Steven Rogers, U.S. Air Force
2:15 Connectionist Models for Speech Recognition, Renato DeMori, McGill
University
3:00 Coffee Break
3:30 Panel Discussion, Moderators: Anil Jain, Michigan State University &
Ishwar Sethi, Wayne State University
Registration Information:
Advance Registration (by 5/15/90): $100
Late Registration: $120
Contact: Ms. Cathy Davison (Workshop on ANN and PR)
Department of Computer Science, A-714 Wells Hall
Michigan State University, East Lansing, MI 48824
Tel. (517)355-5218, email: davison@cps.msu.edu, FAX: (517)336-1061
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (03/16/90)
Vision-List Digest Thu Mar 15 09:39:46 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Vector correlation
Use of Artificial Neural Networks in Image Processing
Additions to List of IP Source Code Packages
Australian AI Conference
Call for discussion: comp.robotics
----------------------------------------------------------------------
Date: Tue, 13 Mar 90 04:00:21 GMT
From: us214777@mmm.serc.3m.com (John C. Schultz)
Subject: vector correlation
Organization: 3M - St. Paul, MN 55144-1000 US
A friend gave me a copy of an article from the Jan 1990 (p 138-9) Photonics
Spectra on "Vector Correlation" which was the first I have heard of the
concept of vector correlation.
As I understand what the author was talking about, you use a high-pass filter
such as a Sobel to determine edge magnitude and gradient (the article only
discussed 4 angles vs. Sobel's 8). The correlation for object location can
then be done much more robustly wrt lighting variations by correlating the 4
(or 8 for Sobel?) images for each direction vector and summing the resulting
correlation images.
The advantages of this approach would seem to be:
1. insensivity to light level even as compared to normalized correlation
2. greater location precision since the object location is completely
determined by its edge location(s)
The disadvantage is the computational complexity - what was one correlation
has suddenly become 4 (or 8 in the case of Sobel?).
My questions:
Why vector correlation? Seems to me this is just a fancy name for object edge
correlation.
Does anyone know have any references for this technique? Possibly under a
different name? The author was from Applied Intelligent Systems Inc. and
neglected to include any references :-).
Anyone have any experience with this technique? Any code they would be
willing to share?
As a final note, I think this is what Intelledex uses internally to their
"turn-key" vision system and they do get 1/10 pixel location precision under a
lot of variable and/or poor lighting conditions.
John C. Schultz EMAIL: jcschultz@mmm.3m.com
3M Company, Building 518-01-1 WRK: +1 (612) 733 4047
1865 Woodlane Drive, Dock 4
Woodbury, MN 55125
------------------------------
Date: Wednesday, 14 Mar 1990 13:37:03 EST
From: m20163@mwvm.mitre.org (Nahum Gershon)
Subject: Use of Artificial Neural Networks in Image Processing
I am looking for references on the use of Artificial Neural Networks
in image processing and also in biomedical imaging. Does anyone have
any information?
* * Nahum
------------------------------
Date: Tue, 13 Mar 90 12:09:16 PST
From: Scott E. Johnston <johnston@odin.ads.com>
Subject: Additions to List of IP Source Code Packages
In a recent posting to the vision-list I listed packages of image
processing source code, available in the public domain or for a
one-time license. I inadvertently left out the HIPS software package
developed by Michael Landy. My apologies to Professor Landy. Here is
the information on HIPS. In addition I received information about
a package called XVision available from the University of New
Mexico. Once again, I welcome any additions or corrections to this list.
Scott E. Johnston
johnston@ads.com
Advanced Decision Systems, Inc.
Mountain View, CA 94043
========================================================================
HIPS
Contact: SharpImage Software
P.O. Box 373
Prince St. Station
NY, NY 10012
Michael Landy (212) 998-7857
landy@nyu.nyu.edu
Description:
HIPS consists of general UNIX pipes that implement image processing
operators. They can be chained together to implement more complex
operators. Each image stores history of transformations applied.
HIPS is available, along with source code, for a $3000 one-time
license fee.
HIPS supports the following:
- simple image transformations
- filtering
- convolution
- Fourier and other transforms
- edge detection and line drawing manipulation
- image compression and transmission
- noise generation
- image pyramids
- image statistics
- library of convolution masks
- 150 programs in all
========================================================================
XVision
Contact: John Rasure
Dept. of EECE
University of New Mexico
Albuquerque NM 87131
505-277-1351
rasure@bullwinkle.unm.edu
XVision is a C-based system developed at the University of New Mexico.
It includes: 1) an image processing library of 150 algorithms from early
processing to classification and shape analysis
2) a graphical form/menu interface and a command line interface
3) a visual language for configuring complex image processing
pipelines
4) an extensive 2d and 3d plotting capability
5) an interactive image analysis capability
6) code generators for generating the command line user
interface and the X windows user interface C code.
The system runs on most UNIX systems and they have a limited number of
licenses that they can give at no cost.
------------------------------
Date: Wed, 14 Mar 90 13:24:11 +0800
From: les@wacsvax.cs.uwa.oz.au (Les Kitchen)
Subject: Australian AI Conference
CALL FOR PAPERS
4th Australian Joint Conference on Artificial Intelligence
AI'90
21-23 November, 1990
Hyatt Regency, Perth, Western Australia
Everyday AI - New Tools for Society
This conference is a major regional forum for
the presentation of recent research on the
theory and practical applications of Artificial
Intelligence. It acts as a catalyst to
stimulate further research and cooperation in
this important area within the Australasia and
Indian-Pacific region. The theme of this year's
conference aims to encourage and promote AI
techniques and tools for solving everyday
problems.
Topics Include (but not limited to):
* Logic and Reasoning
* Knowledge Representation and Acquisition
* Machine Learning
* Artificial Neural Networks
====> * Computer Vision and Robotics
* Natural Language and Speech Recognition
* Expert Systems and development tools
* Applied AI in Civil, Electrical, Electronic, and Mechanical
Engineering
* Knowledge Engineering in Business Applications
* Applications in Government and Mining
Criteria for acceptance
This conference welcomes high quality papers which have a
significant contribution to the theory or practice of A.I.
Papers in the application areas will be judged by their
novelty in the application, its formulation, application of
new A.I. techniques, and the success of the application
project.
Requirement for submission
Authors must submit four copies of their full papers to AI'90
Programme Committee by 11th May 1990. Submissions after the
deadline may be returned without being opened. Notification of
acceptance and format of the camera ready copy will be posted
by the 27th July 1990. The camera ready final paper will be
due on 24th August 1990.
Paper Format for Review
The paper should be about 5000 words in length. It should be
at least one and a half spacing and clearly legible. Authors
should try to limit their paper to not more than 15 pages not
including diagrams. Each paper must include a title, an
abstract about 100 words, but no other identifying marks. The
abstract of 100 words with the title, authors names, and
correspondence address should accompany the submission on a
separate page.
Publication
All papers accepted in the conference will be published in the
conference proceedings. Following the tradition of this
conference, effort will also be made to publish selected
papers from the conference in book form for wider circulation.
Submission Check List
When submitting your paper, please include the following: Name
of contact, postal address, telephone (with country code if
applicable), fax number, e-mail address, FOUR copies of the
paper, an abstract, and a biographical note of the authors.
Submit papers to:
AI'90 Programme Committee
c/o Department of Computer Science,
University of Western Australia,
Nedlands, W.A. 6009,
AUSTRALIA
Enquiries to:
Dr. C.P.Tsang, AI'90 Programme Chair,
Tel: +61-9-380-2763
Fax: +61-9-382-1688
email: ai90paper@wacsvax.oz.au
This conference is sponsored by the Australian Computer
Society through the National Artificial Intelligence and
Expert Systems Committee.
------------------------------
Date: 9 Mar 90 00:18:30 GMT
From: ttidca.TTI.COM!hollombe%sdcsvax@ucsd.edu (The Polymath)
Subject: Call for discussion: comp.robotics
Organization: Citicorp/TTI, Santa Monica
[ I post this for your information only. Please direct responses to
the poster of this message.
phil... ]
The broad distribution of this proposal should give some idea as to why I
consider the creation of this group appropriate. The subject of robotics
can draw on information from all of these groups and more, yet none is
particularly appropriate to it. There is no one group I could go to with
a specific robotics problem with a high probability of finding anyone who
even has the same problem, let alone a solution. Rather than broadcast
such questions to the net, I'd like to see a dedicated group formed.
I therefore propose a new group:
Name: comp.robotics
Moderation: Unmoderated
Charter: The discussion and exchange of information on the practical
aspects of real-world robots and their applications --
industrial, personal and experimental.
I put in the "real-world" qualification deliberately to exclude
discussions of positronic brains, R2D2 and who, if anyone, was really
inside Robbie in "Forbidden Planet." I suggest that Asimov's laws are also
best left to a more philosophically or socially oriented group.
For those interested in leading edge research, AI, machine vision, etc. a
sci.robotics group might be more appropriate and can also be discussed at
this time. I don't think the two groups are mutually exclusive. (i.e.:
Creation of one doesn't necessarily remove the need for the other).
Follow-ups are directed to news.groups
The Polymath (aka: Jerry Hollombe, hollombe@ttidca.tti.com) Illegitimis non
Citicorp(+)TTI Carborundum
3100 Ocean Park Blvd. (213) 450-9111, x2483
Santa Monica, CA 90405 {csun | philabs | psivax}!ttidca!hollombe
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/07/90)
Vision-List Digest Fri Apr 06 09:46:31 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Chevreul illusion
Stereo Sequence Wanted
Pointers to image archives
Image database
WANTED: image processing/pattern recognition job
Fulbright Lecturer/Researcher Position
CALL FOR PARTICIPATION: AAAI-90 Workshop on Qualitative Vision
Call for votes: comp.robotics
----------------------------------------------------------------------
Date: Mon, 2 Apr 90 13:26:01 +0200
From: ronse@prlb.philips.be
Subject: Chevreul illusion
Can someone explain what is the Chevreul illusion seen in a luminance
staircase composed of two step edges? References appreciated. Thanks.
Christian Ronse
Internet: ronse@prlb.philips.be
BITNET: ronse%prlb.philips.be@cernvax
[ As usual, please respond to the List. phil... ]
------------------------------
Date: Fri, 30 Mar 90 14:57:45 +0200
From: Meng-Xiang Li <mxli@bion.kth.se>
Subject: Stereo Sequence Wanted
We are trying to create a stereo sequence of an indoor scene with a camera
mounted on a robot arm. But we have encountered some problems due to the
calibration of the system. We wonder if anyone out there has such stereo
sequences or the like. The point is that we need the necessary (calibration)
data in order to reconstruct the 3D scene. Does anyone have or know such data?
If you do, please let us know. Any help is appreciated very much.
(The data is going to be used in a joined ESPRIT project)
Mengxiang Li
E-mail: mxli@bion.kth.se
Mail : Computational Vision & Active Perception Lab. (CVAP)
Royal Institute of Technology, S-10044 Stockholm, SWEDEN
phone : +46 8 7906207
------------------------------
Date: Tue, 3 Apr 90 16:17:36 EDT
From: Rshankar@top.cis.syr.edu
Subject: Pointers to image archives
I am looking for pointers to existing archives for intensity/range/
stereo/motion images. I would also need information about the
availability of these images to outside users. I can summarize the
replies and post it to the net.
- Ravi
------------------------------
Date: Wed, 4 Apr 90 12:08:53 EDT
From: nar@cs.wayne.edu
Subject: Image database
Hi,
I am looking for a database of 2-D shape (preferably industrial
shapes) to use in a shape recognition system that I am
currently implementing. I would appreciate if anybody
out there could give me one, or give me pointers as to where
I could find them.
Thanx in advance,
Nagarajan Ramesh ! internet- nar@cs.wayne.edu
Dept. of Computer Science, ! uucp - ..!umich!wsu-cs!nar
Wayne State University,
Detroit MI 48202
------------------------------
Date: 5 Apr 90 17:52:41 GMT
From: Justine Stader <jussi@aiai.edinburgh.ac.uk>
Subject: WANTED: image processing/pattern recognition job
Summary: German hunting jobs in Edinburgh
Organization: AIAI, University of Edinburgh, Scotland
A German lad without net-access asked me for help so here goes:
He is coming to Edinburgh in August 1990 and he would like to
start working in Edinburgh around then.
By August he will have a German degree in Computer Science.
His main interests and experiences (from Summer jobs etc.)
are in the field of image processing and pattern recognition.
If you know or hear of any vacancies I (and he) would be
grateful if you could let me know.
Thanks in advance
Jussi.
Jussi Stader, AI Applications Institute, 80 South Bridge, Edinburgh EH1 1HN
E-mail jussi@aiai.ed.ac.uk, phone 031-225 4464 extension 213
------------------------------
Date: Mon, 2 Apr 90 11:56:35 +0200
From: mkp@stek7.oulu.fi (Matti Pietik{inen)
Subject: Fulbright Lecturer/Researcher Position
The Computer Vision Group at the University of Oulu, Finland, is engaged in
research into industrial machine vision, investigating problems
associated with robot vision, visual inspection and parallel vision
systems. With a staff of about 15, it is the largest group of its kind
in Finland.
The Group requests for a Fulbright lecturer/researcher scholar for one
semester during the academic year 1991-92 in the field of computer vision.
The scholar should participate in collaborative research and to teach
an advanced post-graduate course in computer vision. The scholar
should be a U.S. citizen and have a Ph.D with some years of experience
in computer vision.
The research collaboration can be in any of our interest areas,
including computer vision algorithms, vision for intelligent robots,
parallel algorithms and architectures for vision, or automated visual
inspection.
The students of the computer vision course will have at least an MSEE
degree with some experience in computer vision research. The course
will have 2 classroom hours per week. The students' comprehension
level in English is good. An estimated size of the class is 15.
The library of the Department of Electrical Engineering has all
major journals and a large number of books and conference proceedings
in the field of computer vision. The computer facilities of the
Computer Vision Group include several SUN-3 workstations, a Symbolics
3645 and IBM PC's. A dedicated image analysis system, consisting of
boards manufactured by Datacube, Inc., is used for high speed analysis
tasks. A multiprocessor system NTP 1000 based on transputers is used
for studying the problems of parallel processing. Shortly the facilities
will also include an industrial robot equipped with a CCD camera
and a range image sensor.
The Group provides office space, access to computer facilities and some
support from graduate assistants for the scholar. In addition to the
grant provided by the Fulbright program, an additional salary of at
least US$ 2000/month will be arranged from our research funds.
The University of Oulu also provides housing for the scholar.
The Council for International Exchange of Scholars will advertise the
position in the "Fulbright Scholar Program. Faculty Grants. 1991-92."
This booklet will be distributed to all American colleges and
universities in March/April 1990.
The application period for the grant will end on September 15, 1990.
Prof. Matti Pietikainen
Head, Computer Vision Group
Computer Vision Group email: mkp@steks.oulu.fi
Dept. of Electrical Engineering tel: +358-81-352765
University of Oulu fax: +358-81-561278
SF-90570 Oulu, Finland
------------------------------
Date: Fri, 6 Apr 90 11:56:35 +0200
From: pkahn@ads.com (Philip Kahn)
Subject: CALL FOR PARTICIPATION: AAAI-90 Workshop on Qualitative Vision
Sunday, July 29 1990 Boston, Massachusetts
Qualitative descriptions of the visual environment are receiving
greater interest in the computer vision community. This recent
increase in interest is partly due to the difficulties that often
arise in the practical application of more quantitative methods.
These quantitative approaches tend to be computationally expensive,
complex and brittle. They require constraints which limit generality.
Moreover inaccuracies in the input data do not often justify such
precise methods. Alternatively, physical constraints imposed by
application domains such as mobile robotics and real-time visual
perception have prompted the exploration of qualitative mechanisms
which require less computation, have better response time, focus on
salient and relevant aspects of the environment, and use enviromental
constraints more effectively.
The one-day AAAI-90 Workshop on Qualitative Vision seeks to bring
together researchers from different disciplines for the active
discussion of the technical issues and problems related to the
development of qualitative vision techniques to support robust
intelligent systems. The Workshop will examine aspects of the
methodology, the description of qualitative vision techniques, the
application of qualitative techniques to visual domains and the role
of qualitative vision in the building of robust intelligent systems.
Topics to be discussed include:
o What is Qualitative Vision? (e.g., definitions, properties,
biological/psychophysical models or bases)
o Qualitative Visual Features and their Extraction (e.g., 2D/3D
shape, depth, motion)
o High level Qualitative Vision (e.g., qualitative 2D/3D models,
properties, representations)
o Qualitative Vision and Intelligent Behavior (e.g., navigation,
active or directed perception, hand-eye coordination, automated
model building)
Since the number of participants is limited to under 50, invitations
for participation will be based on the review of extended technical
abstracts by several members of the Qualitative Vision research
community. The extended abstract should address one of the above
topic areas, be 3 to 5 pages in length (including figures and
references), and it should begin with the title and author name(s) and
address(es). Extended abstracts (6 copies) should be sent, by
*April 15, 1990*, to:
William Lim
Grumman Corporation
Corporate Research Center
MS A01-26
Bethpage, NY 11714
Decisions on acceptance of abstracts will be made by May 15, 1990.
ORGANIZING COMMITTEE:
* William Lim, Grumman Corporation, Corporate Research Center,
(516) 575-5638 or (516) 575-4909, wlim@ai.mit.edu (temporary) or
wlim@crc.grumman.com (soon)
* Andrew Blake, Department of Engineering Science, Oxford University,
ab@robots.ox.ac.uk
* Philip Kahn, Advanced Decision Systems, (415) 960-7457, pkahn@ads.com
* Daphna Weinshall, Center for Biological Information Processing, MIT,
(617) 253-0546, daphna@ai.mit.edu
------------------------------
Date: 29 Mar 90 00:15:16 GMT
From: ttidca.TTI.COM!hollombe%sdcsvax@ucsd.edu (The Polymath)
Subject: Call for votes: comp.robotics
Followup-To: news.groups
Organization: Citicorp/TTI, Santa Monica
This is the call for votes on the creation of COMP.ROBOTICS .
Name: comp.robotics
Moderation: Unmoderated
Charter: The discussion and exchange of information on all
aspects of real-world robots and their applications --
industrial, personal and experimental.
To cast your vote:
DO NOT post your vote or Followup this article (followups are directed to
news.groups). Send it to me by replying to this article or via e-mail to
the address below. If possible, include "comp.robotics YES" or
"comp.robotics NO" in the Subject: line as appropriate (put it in the
message body too). The polls are now open and will remain so through the
month of April. On May 1st I will tally the responses and post the
results and vote summaries to news.groups and news.announce.newgroups.
A little electioneering, while I'm at it:
The response to the call for discussion has been 100% favorable. However,
I'd like to see this group created cleanly and unambiguously. Please be
sure that _all_ persons interested at your site send their "YES" votes to
me for tallying. ("NO" voters are on their own. (-: [Yes, of course I'll
tally them too].).
The Polymath (aka: Jerry Hollombe, M.A., CDP, aka: hollombe@ttidca.tti.com)
Citicorp(+)TTI Illegitimis non
3100 Ocean Park Blvd. (213) 450-9111, x2483 Carborundum
Santa Monica, CA 90405 {csun | philabs | psivax}!ttidca!hollombe
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (04/12/90)
Vision-List Digest Wed Apr 11 15:02:18 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Info wanted about 3D reconstruction
Looking for a frame grabber board (MacIIx)
Post-Doctoral Research Positions
Research Associate Position In Robot Vision
Re: Job wanted in Computer Vision area
Neural Network Chips
----------------------------------------------------------------------
Date: Tue, 10 Apr 90 10:57 EST
From: V079SPF5@ubvmsc.cc.buffalo.edu
Subject: Info wanted about 3D reconstruction
Dear Colleagues,
I just begin studying 2D and 3D image reconstruction and am particularly
interested in cone-beam algorithms. I would be deeply grateful should you
recommend some papers (specially good review papers) to me.
Also, It is said that there are a lot of public domain software on the network.
People can get the software using FTP (File Transform Protol). Does anyone
know such kind of stuff for image reconstruction in C?
Thank you very much! Best wishes.
Sincerely yours,
Wang, Ge
Email Addr: ge@sun.acsu.buffalo.edu
V079SPF5@UBVMS.BITNET
------------------------------
Date: Wed, 11 Apr 90 11:20 N
From: David Roessli <ROESSLI%CGEUGE52.BITNET@CUNYVM.CUNY.EDU>
Subject: Looking for a frame grabber board (MacIIx)
Hello everybody,
We are looking for a frame grabber board (color), for capturing,
processing and displaying color images on a Macintosh IIx.
The main features would be
- "real-time" capture from color video cameras and VCRs
(grab speed of 1/25s or more).
- Multiple input connections (PAL).
- "genLock" output (CCIR RGB, PAL 50Hz preferred).
- High pixel resolution (something >= 768x512).
- Graphic/text overlay.
- Supported by TIFF24-compatible softwares packages (Studio/8,
PhotoShop, ..).
Any suggestions, proposals, comments, experiences, criticisms,
ideas and invitations will receive a warm welcome !
David C. Roessli Email: roessli@sc2a.unige.ch (preferred)
Dpt. Anthropologie et Ecologie roessli@CGEUGE52.BITNET
University of Geneva david@scsun.unige.ch
12, rue Gustave-Revilliod Phone: +41(22)436.930
CH-1227 SWITZERLAND Fax: +41(22)3000.351
'Any program that as been fully debugged is probably obsolete' [Murphy et al.]
------------------------------
Date: Mon, 9 Apr 90 11:31:50 CDT
From: Dan Kersten <kersten@eye.psych.UMN.EDU>
Subject: Post-Doctoral Research Positions
UNIVERSITY OF MINNESOTA
POST-DOCTORAL RESEARCH POSITIONS
Two research positions available to study the linkages between the
initial stages of human perception and later recognition. The
research uses psychophysical and computational methods to understand
these problems.
Applicants must have a Ph.D. Background in computer modeling,
psychoacoustics, visual psychophysics, perception, or supercomputers
is highly desirable. Applicants capable of forging links between
audition and vision will be given consideration. The research will
be conducted at the Center for the Analyses of Perceptual
Representations (CAPER) at the University of Minnesota . This Center
encompasses four vision laboratories and one hearing laboratory in
the Psychology and Computer Science departments, and includes ample
facilities for simulation and experimental studies. Center faculty
members are: Irving Biederman, Gordon Legge, Neal Viemeister, William
Thompson, and Daniel Kersten. Salary level: $26,000 to $32,000
depending on the candidate's qualifications and experience.
Appointment is a 100% time, 12-month appointment as post-doctoral
fellow. (Appointment may be renewable, contingent on satisfactory
performance and AFOSR funding.) Starting date is July 1, 1990 or as
soon as possible.
Candidates should submit a vita, three letters of reference,
representative reprints and preprints, and a statement of long-term
research interests to:
Professor Irving Biederman,
Department of Psychology,
University of Minnesota,
75 East River Road,
Minneapolis, Minnesota, 55455.
Applications must be received by June 15, 1990.
The University of Minnesota is an equal opportunity educator and
employer and specifically invites and encourages applications from
women and minorities.
------------------------------
Date: Mon, 9 Apr 90 15:18:14 EDT
From: Jean Gray <jean@csri.toronto.edu>
Subject: Research Associate Position In Robot Vision
UNIVERSITY OF TORONTO
RESEARCH ASSOCIATE IN ROBOT VISION
The Government of Canada has established a Network of Centres
of Excellence named IRIS (Institute for Robotics and Intelligent
Systems), with one of its projects ("Active Vision for Mobile
Robots") based in the Department of Computer Science at the
University of Toronto. A research associate position is available,
funded by this project, with funding guaranteed for up to four years.
The successful applicant must hold a PhD in Computer Science or
Electrical Engineering with specialty in areas related to robot vision,
and must possess a strong research record. Experience with stereo-vision
robot heads would be an important asset. Ideal candidates will have
broad interests and talents across such areas as biological models
of vision and motor control, computational vision and image understanding,
attention and active perception, robot navigation, and planning.
Applications should be sent by May 21, 1990 to:-
Professor Derek G. Corneil, Chairman
Department of Computer Science
University of Toronto
Toronto, Ontario
M5S 1A4, Canada.
In accordance with Canadian Immigration regulations, priority will be
given to Canadian citizens and permanent residents of Canada.
The University of Toronto encourages both women and men to apply for
positions.
------------------------------
From: Nora Si-Ahmed <nora@ral.rpi.edu>
Date: Mon, 9 Apr 90 14:08:27 EDT
Subject: Re: Job wanted in Computer Vision area
Hi,
I am seeking for a researcher position, Area= Computer Vision, Pattern
Recognition and Artificial Intelligence.
I am, for the time being visiting scholar for a post-doc at RPI
in the RAL lab.
I will be available (and jobless) next July.
I would like to find a Job in either USA, Canada, France (I speak fluently
french and was graduated there) or UK.
My resume will be sent on request.
Thanks a lot
Nora
Phone num: 518-276-8042 & 276-2973 (work)
518-274-8735 (home)
nora@ral.rpi.edu
Nora Si-Ahmed
RPI, CII8015
Troy NY 12180
------------------------------
Date: Mon, 9 Apr 90 14:42:29 CDT
From: shriver@usl.edu (Shriver Bruce D)
Subject: Neural Network Chips
There are several researchers who are using analog VLSI in vision
research, e.g. Carver Mead at CalTech comes to mind. I thought
the posting might also identify others.
I am interested in learning what experiences people have had using
neural network chips. In an article that Colin Johnson did for PC
AI's January/February 1990 issue, he listed the information given
below about a number of NN chips (I've rearranged it in
alphabetical order by company name). This list is undoubtedly
incomplete (no efforts at universities and industrial research
laboratories are listed, for example) and may have inaccuracies in
it.
Such a list would be more useful if it would contain the name,
address, phone number, FAX number, and electronic mail address of
a contact person at each company would be identified.
Information about the hardware and software support (interface and
coprocessor boards, prototype development kits, simulators,
development software, etc.) is missing.
Additionally, pointers to researchers who are planning to or have
actually been using these or similar chips would be extremely
useful. I am interested in finding out the range of intended
applications.
Could you please send me:
a) updates and corrections to the list
b) company contact information
c) hardware and software support information
d) information about plans to use or experiences with having used
any of these chips (or chips that are not listed)
In a few weeks, if I get a sufficient response, I will resubmit an
enhanced listing of this information.
Thanks,
Bruce Shriver (shriver@usl.edu)
=================================================================
Company: Accotech
Chip Name: AK107
Description: an Intel 8051 digital microprocessor with its on-
chip ROM coded for neural networks
Availability: available now
Company: Fujitsu Ltd.
Chip Name: MB4442
Description: one neuron chip capable of 70,000 connections per
second
Availability: available in Japan now
Company: Hitachi Ltd.
Chip Name: none yet
Description: information encoded in pulse trains
Availability: experimental
Company: HNC Inc.
Chip Name: HNC-100X
Description: 100 million connections per second
Availability: Army battlefield computer
Company: HNC
Chip Name: HNC-200X
Description: 2.5 billion connections per second
Availability: Defense Advanced Research Projects Agency (DARPA)
contract
Company: Intel Corp
Chip Name: N64
Description: 2.5 connections per second 64-by-64-by-64 with
10,000 synapses
Availability: available now
Company: Micro Devices
Chip Name: MD1210
Description: fuzzy logic combined with neural networks in its
fuzzy comparator chip
Availability: available now
Company: Motorola Inc.
Chip Name: none yet
Description: "whole brain" chip models senses, reflex, instinct-
the "old brain"
Availability: late in 1990
Company: NASA, Jet Propulsion Laboratory (JPL)
Chip Name: none yet
Description: synapse is charge on capacitors that are refreshed
from RAM
Availability: experimental
Company: NEC Corp.
Chip Name: uPD7281
Description: a data-flow chip set that NEC sells on PC board
with neural software
Availability: available in Japan
Company: Nestor Inc.
Chip Name: NNC
Description: 150 million connections per second, 150,000
connections
Availability: Defense Dept. contract due in 1991
Company: Nippon Telephone and Telegraph (NTT)
Chip Name: none yet
Description: massive array of 65,536 one-bit processors on 1024
chips
Availability: experimental
Company: Science Applications International. Corp.
Chip Name: none yet
Description: information encoded in pulse trains
Availability: Defense Advanced Research Projects Agency (DARPA)
contract
Company: Syntonic Systems Inc.
Chip Name: Dendros-1
Dendros-2
Description: each has 22 synapses, two required by any number can
be used
Availability: available now
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/09/90)
Vision-List Digest Fri Jun 08 16:37:23 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
List of industrial vision companies
Curvature for 2-D closed boundary description
Array Technologies Color Scanner
CVGIP table of contents: Vol. 51, No. 2, August 1990
ECEM6 1991 Eye-Movements Conference, First Call
Evans & Sutherland PS390 FOR SALE!!
----------------------------------------------------------------------
Date: 4 Jun 90 19:45:50 GMT
From: Brian Palmer <bpalmer@BBN.COM>
Subject: List of industrial vision companies
Organization: Bolt Beranek and Newman Inc., Cambridge MA
Well Samir and my attempts to generate a list of Industrial Vision
companies is going slowly. Please continue to send info! I will post
the summary.
The final posting will contain all related information but for now
here is the list of companies mentioned.
Automatix
Cognex
Datacube
View Engineering (still alive?)
Adept
GMF
Intelledex
Focus Systems
Please send more names and a little info on the company. Also, if you know
anything about the above (some descriptions were short) please pass that
along too.
Thanks,
Brian
------------------------------
Date: 6 Jun 90 23:17:11 GMT
From: zeitzew@CS.UCLA.EDU (Michael Zeitzew)
Subject: Curvature for 2-D closed boundary description
Organization: UCLA Computer Science Department
From:
O. Mitchell and T. Grogan
"Global and Partial Shape Discrimination for Computer Vision"
Optical Engineering,
Volume 23, Number 5, September 1984. pg.484-491
A portion (section on the Fourier-Mellin Correlation) can
be summarized as follows :
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
If the boundary function $z(i) = x(i) + \jmath y(i)$ is twice differentiable,
the the curvature function, denoted by $\kappa(i)$ is given by :
\[ \kappa(t) = \partial / \partial t \;\; \arctan \dot{y}(t) / \dot{x}(t) \]
A discrete approximation of the curvature is :
\begin{eqnarray}
\kappa(i) = \arctan \frac{y_{i} - y_{i-1}}{x_{i} - x{i-1}} - \\
\arctan \frac{y_{i-1} - y_{i-2}}{x_{i-1} - x_{i-2}} \;\;i=0,\ldots,N-1 \nonumber
\end{eqnarray}
The curvature function provides a contour description which is invariant
under translation and rotation.....
+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
Does anyone know why the definition of curvature is given as the
partial derivative with respect to "time", and not "arc length" as
one would see in a first year Calculus book ? What are the
assumptions/implications here ?
If this is a stupid/obvious/boring question, I'm sorry. If you care
to e-mail me a response, thank you in advance.
Mike Zeitzew
zeitzew@lanai.cs.ucla.edu
------------------------------
Date: Thu, 7 Jun 90 10:07:32 EDT
From: marra@jargon.whoi.edu (Marty Marra)
Subject: Array Technologies Color Scanner
Does anyone have experience working with an Array Technologies Color
Scanner? Ideally I'd like to control their "image server" from my Sun
via GPIB. Any general info about these scanners would also be greatly
appreciated.
Thanks.
/\/\ /\/\ Marty Marra, Woods Hole Oceanographic Institution (WHOI DSL)
/ \ / \ Woods Hole, MA 02543 "marra@jargon.whoi.edu" (508)457-2000x3234
------------------------------
Date: Fri, 1 Jun 90 13:08:02 -0700
From: graham@cs.washington.edu (Stephen Graham)
Subject: CVGIP table of contents: Vol. 51, No. 2, August 1990
COMPUTER VISION, GRAPHICS, AND IMAGE PROCESSING .
Volume 51, Number 2, August 1990
CONTENTS
A. Huertas, W. Cole, and R. Nevatia. Detecting Runways in Complex Airport
Scenes, p. 107.
Maylor K. Leung and Yee-Hong Yang. Dynamic Strip Algorithm in Curve Fitting,
p. 146.
Josef Bigun. A Structure Feature for Some Image Processing Applications Based
on Spiral Functions, p. 166.
Lawrence O'Gorman. k x k Thinning, p. 195.
ANNOUNCEMENTS, p. 216.
ABSTRACTS OF PAPERS ACCEPTED FOR PUBLICATION, p. 217.
------------------------------
Date: Fri, 08 Jun 90 15:36:42 +0200
From: ECEM6 <FPAAS91%BLEKUL11.BITNET@CUNYVM.CUNY.EDU>
Subject: ECEM6 1991 Eye-Movements Conference, First Call
Organization: 6th European Conference on Eye Movements
6th European Conference on Eye Movements
15 - 18 september 1991
Leuven, Belgium
First Announcement & Call for Papers
AIM
This is the sixth meeting of the European Scientists actively
involved in eye movement research and is the successor to the
first meeting held in Bern (Switzerland) in 1981, an
initiative of the European Group for Eye Movement Research
(for more information on the Group: R. Groner, Laupenstrasse
4, CH-3008 Bern, Switzerland). The aim of the Conference is to
promote the wider exchange of information concerning eye
movement research in all its diverse fields, and to encourage
contact between basic and applied research. The Conference
will be of interest to psychologists, educational scientists,
neurophysiologists, medical doctors, bioengineers, ergonomists
and others interested in visual science.
VENUE
The Conference will be held at the Department of Psychology,
University of Leuven, Belgium, and many presentations will be
given in the Michotte Lecture Hall of the Department.
CALL FOR PAPERS AND POSTERS
If you wish to present a paper or a poster, please send a one-
page abstract by January 31, 1991, at the very latest. The
selection of posters or papers to be presented will be made by
a committee including all preceding organizers of E.C.E.M.
(with notifications to the proposers in April 1991). Papers
and posters on the following topics are welcome:
Neurophysiology of eye movements, oculomotor system,
measurement techniques, eye movements in perceptual and
cognitive tasks, eye movements and reading, oculomotor
disorders, and applied research. Papers integrating sensory
sciences and higher-order studies will be favored. Papers and
posters should be in English, and the presentation of the
paper should not exceed 20 minutes.
CONFERENCE PUBLICATIONS
If your paper is selected for presentation, you will be asked
to resubmit your abstract in the form specified for the
publication in the Congress Proceedings. This volume will be
made available at the beginning of the Conference. An edited
volume of selected papers will be published after the
Conference by North-Holland Publishing Company in the new
series "Studies in Visual Information Processing" (Series
Editors: R. Groner & G. d'Ydewalle).
SECOND AND FINAL CALL
The second and final call will be forwarded to all those who
submitted a paper and poster abstract. If you do not submit an
abstract and you want to receive the final call, please give
your address in the attached information sheet. The final call
will include more details on the programmes as well as
information on registration and accommodation.
The organizers of the conference will be happy to answer any
questions you may have. Our address is given here at the
bottom line of the letter.
___ __
/ / 6th European Conference on Eye Movements
/--- / 15 - 18 september 1991
/___ /____ Leuven, Belgium
___ __ __ l
/ / l / l l___ Laboratory of Experimental Psychology
/--- / l/ l l l Katholieke Unversiteit Leuven
/___ / l l___l B-3000 Leuven, Belgium
FPAAS91@BLEKUL11.EARN Presidents: Gery d'Ydewalle & Eric De Corte
tel: (32)(16) 28 59 65 Organizer: Johan Van Rensbergen
fax: (32)(16) 28 60 99 99
------------------------------
Date: Mon, 4 Jun 90 15:48:52 CDT
From: ssmith (Sean Smith)
Subject: Evans & Sutherland PS390 FOR SALE!!
Evans & Sutherland PS390 (includes):
Graphics Control processor with 2 dual-sided Floppies
2 Megabytes Memory
Display Processor
19" Color Raster Monitor
RS-232C interface
PS390 System Firmware, Host Software and License
5 Volume user set
Ethernet Interface
1 Megabyte Memory
Keyboard w/led display
Control Dials w/LED display
Tablet 6" x 6" (active area)
*****Please contact Sean Smith
(713)363-8494
ssmith@bcm.tmc.edu
Please pass this message on to interested users.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (06/15/90)
Vision-List Digest Thu Jun 14 11:11:27 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Focus of attention in human and computer vision
Computer Controllable Lenses
Work at BMW
RE: List of industrial vision companies..
CANCELLED: ANN Workshop, Atlantic City, Jun. 17
----------------------------------------------------------------------
Date: 13 Jun 90 16:14:43+0200
From: milanese ruggero <milanese@cuisun.unige.ch>
Subject: Focus of attention in human and computer vision
Hallo,
I am at the beginning of my PhD work concerning the subject
of focus of attention applied to visual perception. Good sources of
information about the underlying mechanisms seem to be provided by
psychologists and, to a given extent, by neurophysiologists. Rather
than analysis of elementar phenomena, what I am more interested in
are frameworks and theories that try to explain the global process
of attention in vision. Since I am a computer scientist, I shall
also be interested in applying these concepts into a working machine
vision system.
Therefore, I would be grateful for any information, reference,
discussion or pointers about work done in this field.
Many thanks,
Ruggero Milanese
E-mail: milanese@cuisun.unige.ch
Address: Centre Universitaire d'Informatique
12, rue du Lac
1207 - Geneve
Switzerland
------------------------------
Date: Tue, 12 Jun 90 08:46:42 BST
From: Alan McIvor <bprcsitu!alanm@relay.EU.net>
Subject: Computer Controllable Lenses
Hi,
We are currently looking for a lens for our vision system with
computer controllable focus, focal length, and aperture. Do any of you
know of a source of such lenses? We have found many motorized lenses
but most have auto-apertures and no feedback of settings.
I recall several years ago that a company called Vicon made such
a lens but I don't have any details. Anybody know how to get hold of
them?
Thanks,
Dr Alan M. McIvor
BP International Ltd ukc!bprcsitu!alanm
Research Centre Sunbury alanm%bprcsitu.uucp@uk.ac.ukc
Chertsey Road bprcsitu!alanm@relay.EU.NET
Sunbury-on-Thames uunet!ukc!bprcsitu!alanm
Middlesex TW16 7LN Tel: +44 932 764252
U.K. Fax: +44 932 762999
[ Please post responses to the List!!
phil... ]
------------------------------
Date: Fri, 8 Jun 90 10:24:13 +0200
From: jost@bmwmun.ads.com (Jost Bernasch)
Subject: Work at BMW
[ I received this as part of a correspondence, and I thought it would
be of general interest (with permission to post from Jost).
phil... ]
I am with a research group at BMW and at the Technical University of Munich.
We are developing a selfguided driving car, which is lateral controled.
The car actually is driving on the BMW test route with about 60mph without
needing white lanes or something like that.
We are just working towards a more stable system (brightness, shadows)
and we will identify, track and classify objects (cars, trucks, pedestrians).
Furthermore we are developing an attentive vision modul, which focuses
automatically attention to important parts of the image.
Naturally, we are confronted with problems which need adaptive
control (lateral guidance depending on the car's changing status
and the environment, adaptiv, intelligently controlled attentive
vision, adapting a lot of parameters in the vision modules etc.).
Yours
Jost Bernasch,
BMW AG Muenchen, Dep. EW-13, P.O. BOX 40 02 40, D-8000 Muenchen 40, Germany
Tel. ()89-3183-2822 FAX ()89-3183-4767 jost@bmwmun.uucp.dbp.de
------------------------------
Date: Mon, 11 Jun 90 14:49:33 -0500
From: krishnan@cs.wisc.edu (Harikrishnan Krishna)
Subject: RE: List of industrial vision companies..
It would be great if the addresses were also posted along with the
names of the companies.
Thanks.
Krishna.
------------------------------
Date: Mon, 11 Jun 90 20:20:56 EDT
From: raja@pixel.cps.msu.EDU
Subject: CANCELLED: ANN Workshop, Atlantic City, Jun. 17
The following workshop has been CANCELLED. Any
inconvenience caused is regretted.
Workshop on
Artificial Neural Networks & Pattern Recognition
Sponsored by
The International Association for Pattern Recognition (IAPR)
Sands Hotel
Atlantic City, New Jersey
June 17, 1990
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/06/90)
Vision-List Digest Thu Jul 05 10:47:27 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
IEEE Workshop on Directions in Automated ``CAD-Based'' Vision
----------------------------------------------------------------------
Date: Fri, 29 Jun 90 08:59:19 EDT
From: Dr Kevin Bowyer <kwb@SOL.USF.EDU>
Subject: IEEE Workshop on Directions in Automated ``CAD-Based'' Vision
IEEE Workshop on Directions in Automated ``CAD-Based'' Vision
June 2-3, 1991 Maui, Hawaii (just prior to CVPR '91)
The purpose of this workshop is to foster dialogue and debate which
will more sharply focus attention on important unsolved problems, so
that better working solutions can be produced. The program will
consist of a small number of submitted papers, ``proponent/respondent''
discussions on selected topics, panel sessions, and presentations by
some potential ``consumers'' of machine vision on what they feel are
important real problems in need of a solution. Participants should be
willing (preferably eager) to engage in open discussion, in the best
collegial spirit, of both their own work and that of others.
A list of possible themes for submitted papers, meant to be suggestive
rather than exclusive, is:
Derivation of Vision-Oriented Object Models from CAD Models
Model-Driven Extraction of Relevant Features from Images
Strategies for Matching Image Features to Object Models
Capabilities of Current CAD-to-Vision Systems
``Qualitative Vision'' and Automated Learning
Submission of Papers: Submit three copies of your paper to the program
chairman to be received on or before January 1, 1991. Papers should not
exceed a total of 25 double-spaced pages. Authors will be notified of
reviewing decisions by March 1, and final versions will be due by April 1.
General Chairman:
Linda Shapiro (shapiro@cs.washington.edu)
Dept. of Computer Science and Engineering
University of Washington
Seattle, Washington 98195
Program Chairman:
Kevin Bowyer (kwb@sol.usf.edu)
Dept. of Computer Science & Engineering
University of South Florida
Tampa, Florida 33620
Program Committee:
Avi Kak, Purdue University Joe Mundy, General Electric Corp. R.&D.
Yoshiaki Shirai, Osaka Univ. George Stockman, Michigan State Univ.
Jean Ponce, Univ. of Illinois Katsushi Ikeuchi, Carnegie-Mellon Univ.
Tom Henderson, Univ. of Utah Horst Bunke, Universitat Berne
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/12/90)
Vision-List Digest Wed Jul 11 09:51:04 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Help ! Rotated molecules & rotating physics student canonical vision book list Summary of Responses Received to generate Needle Diagrams Camera Mount Ideas Needed for Manned Exploration of Moon and Mars Character Recognition Bibliography? OCR Refs/Software? Job vacancies ---------------------------------------------------------------------- Date: 10 Jul 90 10:34:49 GMT From: uh311ae@LRZSUN4_7.lrz.de (Henrik Klagges) Subject: Help ! Rotated molecules & rotating physics student Keywords: Correllation filters, rotated pattern recognition, GA Organization: LRZ, Bavarian Academy of Sciences, W. Germany Hi, netwise, I need help ! The problem: A Scanneling Tunnel Microscope (STM) produces a picture of a flat surface covered with macromolecules, forming a loose grid or just being scattered around. For simplicity, it is assumed that there exist only 3 free para- meters, namely two translatoric and one rotational for the molecules. A single molecule gives a noisy image, so it is desired to combine many individual molecule-images into a single one. To accomplish this task several ways might be possible: 1) Have a clever program walking over the image and saying 'Wow ! That's a molecule turned foo degrees and translated bar units, let's add it to our data base !' (Ugh). 2) Run a fantastic correllation filter (fcf:) over the image that is able to recognize the correllation between any (!) rotated and x,y-displaced structures and amplify those structures (Does this exist yet ? Does one exist that matches all affine transformations ?). 3) If that is too much, select a "good" molecule, calculate its turned image for each degree, move over the whole image and try to match these 360 turns with the image and mark this place as occupied (Calculate 'n crunch for ever ?). 4) Make a FF- or Hartley- or another integral transform of the image. That means no spatial parameters anymore, and then turn and match the transformed image on itself, correllate, amplify, re-transform (Who knows if that works !). Questions: 1) Who knows about a fcf ? 2) Which methods are suited for the task of matching two images that are rotated and/or linearly displaced against each other ? (I heard about a genetic algorithm from Fitzgerald, Grevenstette et al.). 3) How do You walk over a surface and recognize noisy molecules ? 4) ANY hint or comment desperately welcome ! Thanks a lot Henrik Klagges STM group at LMU Munich EMail: uh311ae@LRZSUN4_7.lrz.de SMail: Stettener Str. 50, 8210 Prien, FRG ------------------------------ Date: Tue, 10 Jul 90 12:39:23 +0200 From: ronse@prlb.philips.be Subject: canonical vision book list I received many references of books on vision, but of only one on image analysis (Serra's first volume). So here is my "canonical" list of fundamental vision books. Please send me also the references for your preferred books on image processing and analysis. D.H. Ballard & C.M. Brown: "Computer Vision", Prentice-Hall, 1982. B.K.P. Horn: "Robot Vision", MIT Press, Cambridge, Mass., USA, 1986. T. Kanade : "Three Dimensional Machine Vision", Kluwer Ac. Press. J.J. Koenderink: "Solid Shape", MIT Press, Cambridge, Mass., USA., 1990. M.D. Levine: "Vision in Man and Machine", McGraw-Hill, New York, USA, 1985. D. Marr: "Vision", W.H. Freeman & Co., San Francisco, CA, 1982. P.H. Winston (ed.): "The Psychology of Computer Vision", McGraw-Hill, 1975. The books by Ballard & Brown and by Horn are "winners". Several people suggested them. Christian Ronse Internet: ronse@prlb.philips.be BITNET: ronse%prlb.philips.be@cernvax ------------------------------ Date: Fri, 6 Jul 90 17:09:41 EDT From: ramamoor@cmx.npac.syr.edu (Ganesh Ramamoorthy) Subject: Summary of Responses Received to generate Needle Diagrams >From: jonh@tele.unit.no Subject: Needle Diagrams If you use matlab, ver. 3.5 you can use the command "quiver" to generate nice needle diagrams. Unfortunately, ver 3.5 of matlab may still not be available on SUN. However it is available for VAX. I have taken the m-file "quiver.m" from Matlab ver. 3.5 running on VAX and used it with old matlab versions on SUN. This works fine. If you would like to try this out and have problems getting hold of "quiver.m", let me know and I will mail you a copy. >From: Keith Langley <kl@robots.oxford.ac.uk> Subject: needles I did it the easy way by looking at FIG format for lines and piping out a needle diagram that way. >From: hmueller@wfsc4.tamu.edu (Hal Mueller) Subject: Needle Diagrams The graphics package called DISSPLA, sold by Computer Associates (formerly sold by ISSCO), has an extra cost option for an automatic code generator. One of the things this code generator produces is needle plots. DISSPLA runs on a Sun 3, and I would presume also on a Sun 4. Reach them at (800) 645-3003. The package is expensive, fairly difficult to learn, is extremely powerful, and is as close to bug free as any commercial product I've ever seen. >From: oskard@vidi.cs.umass.edu Subject: re: Programs for generating Needle Diagrams Hi. I don't know if you've found any programs for displaying flow fields yet, but we use KBVision here and it has a system called the image examiner that displays flow fields among other things. Anyway, their address is: Amerinex Artificial Intelligence Inc. 274 N. Pleasant St. Amherst, MA 01002 413-256-8941 >From: johnston@george.lbl.gov (Bill Johnston) Subject: flow field diagramw The NCAR (National Center for Atmospheric Research, Boulder CO) graphics library has several routines for displaying flow fields. It sits on top of GKS, so any GKS package that supports a Sun should allow you to use the NCAR package. ------------------------------ Date: Sun, 8 Jul 90 12:38:29 -0400 (EDT) From: "Ethan Z. Evans" <ee0i+@andrew.cmu.edu> Subject: Camera Mount Vision Wizards: I need to find a 2 degree of freedom camera mount (rotation and pitch). The mobile platform I work on is only about a foot tall, and the top is cluttered with various hardware etc. Thus to give the robot a view of its world, we need to set the camera up on a pole. Once its up their it needs to be able to turn around and either look down at what the arm is doing, or out at where the base is going. Point is, I don't have the slightest idea where to look for such a device. If anyone could give me a starting point as to where to get such a mount, especially one easily controlled through a PC parallel or serial port, I would be most greatful. Thanks in advance, Ethan Evans ee0i@andrew.cmu.edu Disclaimer: I'm the lab rat, how could *I* have an opinion? [ Please post responses to the List phil... ] ------------------------------ Date: 9 Jul 90 07:15:53 GMT From: guyton%randvax.UUCP@usc.edu (Jim Guyton) Subject: Ideas Needed for Manned Exploration of Moon and Mars Keywords: PROJECT OUTREACH Organization: Rand Corp., Santa Monica, Ca. PROJECT OUTREACH Ideas Needed for Manned Exploration of Moon and Mars. NASA is seeking innovative approaches to mission concepts and architectures, as well as technologies that could cut costs and improve mission schedule and performance. The RAND Corporation will provide an independent assessment of all suggestions. The procedure for submitting ideas is simple. For an information kit call 1-800-677-7796. Call now. The deadline for submissions is August 15, 1990. ------------------------------ Date: Mon, 9 Jul 90 19:56:22 EDT From: atul k chhabra <Atul.Chhabra@UC.EDU> Subject: Character Recognition Bibliography? I am looking for a character recognition bibliography. I am interested in all aspects of character recognition, i.e., preprocessing and segmentation, OCR, typewritten character recognition, handwritten character recognition, neural network based recognition, statistical and syntactic recognition, hardware implementations, and commercial character recognition systems. If someone out there has such a bibliography, or something that fits a part of the above description, I would appreciate receiving a copy. Even if you know of only a few references, please email me the references. Please email the references or bibliography to me. I will summarize on the vision-list. Thanks, Atul Chhabra Department of Electrical & Computer Engineering University of Cincinnati, ML 030 Cincinnati, OH 45221-0030 Phone: (513)556-6297 Email: achhabra@uceng.uc.edu ------------------------------ Date: Wed, 11 Jul 90 14:57:00 +0200 From: nagler@olsen.ads.com (Robert Nagler) Subject: OCR Refs/Software? Organization: Olsen & Associates, Zurich, Switzerland Keywords: OCR, Pattern Recognition Status: R Could someone send me a good reference(s) on OCR/Pattern Recognition? Pointers to PD software (source) would be nice, too. Thanks. Rob nagler@olsen.uu.ch ------------------------------ Date: Wed, 4 Jul 90 11:29:00 WET DST Subject: job vacancy From: J.Illingworth@ee.surrey.ac.uk UNIVERSITY OF SURREY: Dept of Electronics and Electrical Engineering. ********************************************************************* RESEARCH FELLOW IN COMPUTER VISION AND IMAGE PROCESSING ********************************************************************* Research Fellows are required for projects in Computer Vision. The projects are concerned with the following problems: * robust 2D and 3D shape representation and analysis; * high-level scene interpretation; * automatic inspection of loaded printed circuit boards; * relaxation labelling and neural net computation in vision by associative reasoning. The projects will be carried out within an active Vision, Speech and Signal Processing research group which comprises about 35 members. The group has extensive computing resources including SUN Sparc stations, VAX and Masscomp computers as well as specialised image processing facilities. The successful candidates will be required to develop, implement in software and experimentally evaluate computer vision algorithms. Applicants for these posts should have a degree in mathematics, statistics, electronics, computer science, artificial intelligence or physics. Previous experience in computer vision, image analysis, knowledge based methods or pattern recognition will be an advantage. One of the posts may be reserved for an applicant able to provide hardware and software support for the Group across projects. The appointments will be initially for two years with a salary in the range 10458 -16665 pa (under review) depending upon age, qualifications and experience, with superannuation under USS conditions. Applications in the form of a curriculum vitae ( 3 copies) including the names and addresses of two referees should be sent to the Personnel Office (JLG), University of Surrey, Guildford, Surrey GU2 5XH by 30 June 1990 quoting reference Further information may be obtained from Dr J Kittler, Department of Electronic and Electrical Engineering on (0483) 509294 or from Dr J Illingworth on (0483) 571281 ext. 2299. PROJECT DESCRIPTION DETECTION OF LINEAR FEATURE IN IMAGE DATA The aim of the project is to investigate and develop the Hough transform and associated pre-processing and postprocessing techniques with the application to the problem of detecting linear image features in noisy and cluttered background of changing polarity. The emphasis of the approach will be on statistical hypothesis testing and robust estimation methods. An important component of the research will be to develop the theory and methodology for the design of post processing filters to enhance the Hough transform performance. The problem of detecting higher level features such as corners and parallels using the same framework will also be considered. LOCATION AND INSPECTION WITH RANGE DATA The project is concerned with the problem of segmenting depth image data into parametric surfaces. Robust hypothesis testing methods of which the Hough transform is just one example will be investigated in this context. The research issues to be addressed include the problems of surface parameterisation, efficient transform calculation and reliable transform space analysis. Other approaches to range data segmentation such as energy minimisation methods and knowledge based methods will be investigated. AUTOMATIC INSPECTION OF LOADED PRINTED CIRCUIT BOARDS The aim of the project is to investigate and develop machine vision techniques for advanced automated inspection of loaded printed circuit boards (PCBs) and of surface mounted ceramic substrates with the view to enable real time fault correction to increase production yields, maintain and optimise product quality and to maximize manufacturing process control capabilities. A particular emphasis will be on two aspects of the inspection task: i) the use of 3D sensor data to address the problem of inspecting soldered joints, active device pins, component leads and the mounting of special devices, ii) development of knowledge based approaches to guide and control the above surface based inspection problem and to verify component identity. The strategic objectives of the project include the following: Development of 3D scene modelling and surface segmentation methods specifically in the context of the loaded PCB inspection domain; Development of surface inspection approaches; Representation and application of geometric, attribute and relational models of objects and their arrangements in the application domain of electronic system assembly. The research problems to be addressed in order to meet these objectives are generic in nature. It is anticipated therefore that the research results will have bearing on other application areas of computer vision. The proposed research will advance the state of the art in automatic loaded PCB inspection by: 1 evaluating existing 3D surface segmentation methods in the context of loaded PCB inspection, 2 developing robust surface modelling methods, 3 providing techniques and algorithms for surface inspection, 4 enhancing the methods of component identification and verification, and 5 developing inspection strategies that will allow full integration of automatic printed circuit assembly, inspection and rework. VISION BY ASSOCIATIVE REASONING The project is concerned with the study of relaxation labelling processes in the computer vision context. The aim of the research will be to develop and apply existing probabilistic and discrete relaxation algorithms to image interpretation problems at intermediate levels of processing where the prior world knowledge may most naturally be specified in terms of explicit rules. It will be necessary to develop a suitable interface that facilitates the conversion of such rules into a form that can be used directly by the evidence combining scheme employed in the relaxation process. The work will also involve the development of evidence combining methods for multilevel relaxation, development of hierarchical models and corresponding hierarchical relaxation processes. The relationship of relaxation processes and neural net computation will be investigated. ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/13/90)
Vision-List Digest Thu Jul 12 10:52:42 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Technology Transfer Mailing List
AAAI information (including workshop info)
Seventh IEEE Conference on Artificial Intelligence Applications
IJCAI'91 Call for Participation
IJCAI'91 Call for Workshops
IJCAI'91 Call for Tutorials
IJCAI'91 Call for Awards
----------------------------------------------------------------------
Date: Tue, 10 Jul 90 09:02:36 -0400
From: weh@SEI.CMU.EDU
Subject: Technology Transfer Mailing List
Organization: Software Engineering Institute, Pittsburgh, PA
Keywords: technology transfer, communication, mailing list
The Technology Applications group of the Software Engineering Institute is
pleased to announce the creation of a new electronic mailing list:
technology-transfer-list. This mailing list, focused on technology transfer
and related topics, is intended to foster discussion among researchers and
practitioners from government and industry who are working on technology
transfer and innovation.
Relevant topics include:
* organizational issues (structural and behavioral)
* techno-economic issues
* business and legal issues, such as patents, licensing, copyright, and
commercialization
* technology transfer policy
* technology maturation to support technology transition
* lessons learned
* domestic and international technology transfer
* transition of technology from R&D to practice
* planning for technology transition
* models of technology transfer
* studies regarding any of these topics
The technology-transfer-list is currently not moderated, but may be
moderated or digested in the future if the volume of submissions warrants.
The electronic mail address for submissions is:
technology-transfer-list@sei.cmu.edu
To request to be added to or dropped from the list, please send mail to:
technology-transfer-list-request@sei.cmu.edu
Please include the words "ADD" or "REMOVE" in your subject line.
Other administrative matters or questions should also be addressed to:
technology-transfer-list-request@sei.cmu.edu
The SEI is pleased to provide the facilities to make this mailing list
possible. The technology-transfer-list is the result of two SEI activities:
* transitioning technology to improve the general practice of software
engineering
* collaborating with the Computer Resource Management Technology program
of the U.S. Air Force to transition technology into Air Force practice
The SEI is a federally funded research and development center sponsored by
the U.S. Department of Defense under contract to Carnegie Mellon University.
------------------------------
Date: Sat, 7 Jul 90 11:34:42 -0400
Subject: AAAI information (including workshop info)
WORKSHOP REGISTRATION
Workshop registration begins at 7:30 am on Sunday the 29th (the day of the
workshop) in Hall B of the Hynes Conference Center. The workshop will get
under way at 9:00 am. Unfortunately there is no advance registration, and
there is no putting the registration off 'til later either: registering
is how you (and I) find out which room the workshop is in. The registration
desk may be a zoo, so please get there early.
There is a $50 registration fee for workshops, in addition to the fees
for any other technical or tutorial sessions you choose to attend. You
can attend a workshop without registering for the whole conference.
CONFERENCE REGISTRATION
To advance register for the AAAI conference, send a check for the amount
listed below to AAAI-90, 445 Burgess Drive, Menlo Park, CA 94025, or you
can call (415) 328-3123 and use a credit card.
onsite registration (starting Sunday July 29th):
regular AAAI member $335
regular non-member $375
student AAAI member $200
student non-member $220
AIR TRAVEL
Reduced air fares to the workshop and/or conference are available from
Northwest Airlines and TWA. The reduction is 45% for round-trip or circle
trip, coach class, fares over $100, within the continental US. Tickets
must be issued at least 10 days in advance of travel. Flight reservations
must be made through one of the following:
Custom Travel Consultants (in Woodside, CA)
(800)367-2105 or (415)369-2105, 9am - 5pm PST
Northwest Airlines
(800)328-1111 (use ID code 17379)
TWA
(800)325-4933 (use ID code B9912829)
CAR RENTAL
Special rates are available from Hertz when booked through Custom Travel
Consultants (see above). Use code CV 5522.
ACCOMMODATION
Economical accommodation is MIT dormitory housing (twin beds with linens,
laundry facilities available, no private baths or air conditioning), 6 blocks
from the conference center, $35 single, $50 double. Requests for dormitory
housing must be received by Rogal by July 1st, and must be accompanied by
full prepayment. Parking is an extra $5.
Here follows a list of a few hotels you might use. Whether or not you're
staying for the rest of the conference, you can obtain a room at "special
conference rates" by contacting Rogal America, 313 Washington Street suite
300, Newton Corner, MA 02158, phone (617)965-8000. Deadline for obtaining
these reduced rates at June 29th.
Back Bay Hilton
1 block from conference center
Single room rates: $125
Double room rates: $140
The Midtown
2 blocks from conference center
Single room rates: $80
Double room rates: $90
Boston Marriott Copley Place
2 blocks from conference center
Single room rates: $126, $137, $144
Double room rates: $140, $152, $160
Copley Square Hotel
3 blocks from conference center
Single room rates: $86, $96
Double room rates: $100
57 Park Plaza
8 blocks from conference center
Single room rates: $90
Double room rates: $100
Howard Johnson Cambridge
13 blocks from conference center
Single room rates: $90
Double room rates: $100
------------------------------
Date: Sat, 7 Jul 90 11:34:42 -0400
From: finin@PRC.Unisys.COM
Subject: Seventh IEEE Conference on Artificial Intelligence Applications
Organization: Unisys Center for Advanced Information Technology
The Seventh IEEE Conference on Artificial Intelligence Applications
Fontainbleau Hotel, Miami Beach, Florida
February 24 - 28, 1991
Call For Participation
(submission deadline 8/31/90)
Sponsored by The Computer Society of IEEE
The conference is devoted to the application of artificial
intelligence techniques to real-world problems. Two kinds of papers
are appropriate: case studies of knowledge-based applications that
solve significant problems and stimulate the development of useful
techniques and papers on AI techniques and principles that underlie
knowledge-based systems, and in turn, enable ever more ambitious
real-world applications. This conference provides a forum for such
synergy between applications and AI techniques.
Papers describing significant unpublished results are solicited along
three tracks:
o "Scientific/Engineering" Applications Track. Contributions stemming
from the general area of industrial and scientific applications.
o "Business/Decision Support" Applications Track. Contributions stemming
from the general area of decision support applications in business,
government, law, etc.
Papers in these two application tracks must: (1) Justify the use
of the AI technique, based on the problem definition and an
analysis of the application's requirements; (2) Explain how AI
technology was used to solve a significant problem; (3) Describe
the status of the implementation; (4) Evaluate both the
effectiveness of the implementation and the technique used.
Short papers up to 1000 words in length will also be accepted for
presentation in these two application tracks.
o "Enabling Technology" Track. Contributions focusing on techniques
and principles that facilitate the development of practical knowledge
based systems that can be scaled to handle increasing problem
complexity. Topics include, but are not limited to: knowledge
representation, reasoning, search, knowledge acquisition, learning,
constraint programming, planning, validation and verification, project
management, natural language processing, speech, intelligent
interfaces, natural language processing, integration, problem-solving
architectures, programming environments and general tools.
Long papers in all three tracks should be limited to 5000 words and
short papers in the two applications tracks limited to 1000 words.
Papers which are significantly longer than these limits will not be
reviewed. The first page of the paper should contain the following
information (where applicable) in the order shown:
- Title.
- Authors' names and affiliation. (specify student status)
- Contact information (name, postal address, phone, fax and email address)
- Abstract: A 200 word abstract that includes a clear statement describing
the paper's original contributions and what new lesson is imparted.
- AI topic: one or more terms describing the relevant AI areas, e.g.,
knowledge acquisition, explanation, diagnosis, etc.
- Domain area: one or more terms describing the problem domain area,
e.g., mechanical design, factory scheduling, education, medicine, etc.
Do NOT specify the track.
- Language/Tool: Underlying programming languages, systems and tools used.
- Status: development and deployment status, as appropriate.
- Effort: Person-years of effort put into developing the particular
aspect of the project being described.
- Impact: A twenty word description of estimated or measured (specify)
benefit of the application developed.
Each paper accepted for publication will be allotted seven pages in
the conference proceedings. The best papers accepted in the two
applications tracks will be considered for a special issue of IEEE
EXPERT to appear late in 1991. An application has been made to
reserve a special issue of IEEE Transactions on Knowledge and Data
Engineering (TDKE) for publication of the best papers in the enabling
technologies track. IBM will sponsor an award of $1,500 for the
best student paper at the conference.
In addition to papers, we will be accepting the following types of
submissions:
- Proposals for Panel discussions. Provide a brief description of the
topic (1000 words or less). Indicate the membership of the panel and
whether you are interested in organizing/moderating the discussion.
- Proposals for Demonstrations. Submit a short proposal (under 1000
words) describing a videotaped and/or live demonstration. The
demonstration should be of a particular system or technique that
shows the reduction to practice of one of the conference topics.
The demonstration or videotape should be not longer than 15 minutes.
- Proposals for Tutorial Presentations. Proposals for three hour
tutorials of both an introductory and advanced nature are
requested. Topics should relate to the management
and technical development of useful AI applications. Tutorials
which analyze classes of applications in depth or examine
techniques appropriate for a particular class of applications are of
particular interest. Copies of slides are to be provided in advance to
IEEE for reproduction.
Each tutorial proposal should include the following:
* Detailed topic list and extended abstract (about 3 pages)
* Tutorial level: introductory, intermediate, or advanced
* Prerequisite reading for intermediate and advanced tutorials
* Short professional vita including presenter's experience in
lectures and tutorials.
- Proposals for Vendor Presentations. A separate session will be held
where vendors will have the opportunity to give an overview to
their AI-based software products and services.
IMPORTANT DATES
- August 31, 1990: Six copies of Papers, and four copies of all proposals
are due. Submissions not received by that date will be returned
unopened. Electronically transmitted materials will not be accepted.
- October 26, 1990: Author notifications mailed.
- December 7, 1990: Accepted papers due to IEEE. Accepted tutorial
notes due to Tutorial Chair.
- February 24-25, 1991: Tutorial Program of Conference
- February 26-28, 1991: Technical Program of Conference
Submit Papers and Other Materials to:
Tim Finin
Unisys Center for Advanced Information Technology
70 East Swedesford Road
PO Box 517
Paoli PA 19301
internet: finin@prc.unisys.com
phone: 215-648-2840; fax: 215-648-2288
Submit Tutorial Proposals to:
Daniel O'Leary
Graduate School of Business
University of Southern California
Los Angeles, CA 90089-1421
phone: 213-743-4092, fax: 213-747-2815
For registration and additional conference information, contact:
CAIA-91
The Computer Society of the IEEE
1730 Massachusetts Avenue, NW
Washington, DC 20036-1903
phone: 202-371-1013
CONFERENCE COMMITTEES
General Chair: Se June Hong, IBM Research
Program Chair: Tim Finin, Unisys
Publicity Chair: Jeff Pepper, Carnegie Group, Inc.
Tutorial Chair: Daniel O'Leary, University of Southern California
Local Arrangements: Alex Pelin, Florida International University, and
Mansur Kabuka, University of Miami
Program Committee:
AT-LARGE SCIENTIFIC/ENGINEERING TRACK
Tim Finin, Unisys (chair) Chris Tong, Rutgers (chair)
Jan Aikins, AION Corp. Sanjaya Addanki, IBM Research
Robert E. Filman, IntelliCorp Bill Mark, Lockheed AI Center
Ron Brachman, AT&T Bell Labs Sanjay Mittal, Xerox PARC
Wolfgang Wahlster, German Res. Center Ramesh Patil, MIT
for AI & U. of Saarlandes David Searls, Unisys
Mark Fox, CMU Duvurru Sriram, MIT
ENABLING TECHNOLOGY TRACK BUSINESS/DECISION SUPPORT TRACK
Howard Shrobe, Symbolics (chair) Peter Hart, Syntelligence (chair)
Lee Erman, Cimflex Teknowledge Chidanand Apte, IBM Research
Eric Mays, IBM Research Vasant Dhar, New York University
Norm Sondheimer, GE Research Steve Kimbrough, U. of Pennsylvania
Fumio Mizoguchi, Tokyo Science Univ. Don McKay, Unisys
Dave Waltz, Brandeis & Thinking Machines
+----------------------------------------------------------------------+
| Tim Finin finin@prc.unisys.com |
| Center for Advanced Information Technology 215-648-2840, -2288(fax) |
| Unisys, PO Box 517, Paoli, PA 19301 USA 215-386-1749 (home) |
+----------------------------------------------------------------------+
------------------------------
From: Kimberlee Pietrzak-Smith <kim@cs.toronto.edu>
Subject: IJCAI'91 Call for Participation
Date: Fri, 6 Jul 1990 16:15:06 -0400
CALL FOR PARTICIPATION: IJCAI-91
TWELFTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE
August 24 - 30, 1991, Sydney, Australia
The biennial IJCAI conferences are the major forums for the
international scientific exchange and presentation of AI research.
The next IJCAI conference will be held in Sydney, Australia, 24-30 August
1991. IJCAI-91 is sponsored by the International
Joint Conferences on Artificial Intelligence, Inc. (IJCAII), and
co-sponsored by the National Committee on Artificial Intelligence
and Expert Systems of the Australian Computer Society.
The conference technical program will include workshops, tutorials,
panels and invited talks, as well as tracks for paper and videotape
presentations.
1. Paper Track: Submission Requirements and Guidelines
Topics of Interest
Submissions are invited on substantial, original, and previously
unpublished research in all aspects of AI, including, but not limited
to:
* Architectures and languages for AI (e.g. hardware and
software for building AI systems, real time and distributed AI)
* Automated reasoning (e.g. theorem proving, automatic
programming, planning and reasoning about action, search, truth
maintenance systems, constraint satisfaction)
* Cognitive modelling (e.g. user models, memory models)
* Connectionist and PDP models
* Knowledge representation (e.g. logics for knowledge, belief and
intention, nonmonotonic formalisms, complexity analysis, languages and
systems
for representing knowledge)
* Learning and knowledge acquisition
* Logic programming (e.g. semantics, deductive databases, relationships
to AI knowledge representation)
* Natural language (e.g. syntax, semantics, discourse, speech recognition
and understanding, natural language front ends)
* Philosophical foundations
* Principles of AI applications (e.g. intelligent CAI, design,
manufacturing, control)
* Qualitative reasoning and naive physics (e.g. temporal and spatial
reasoning, reasoning under uncertainty, model-based reasoning, diagnosis)
* Robotics (e.g. kinematics, manipulators, navigation, sensors, control)
* Social, economic and legal implications
* Vision (e.g. colour, shape, stereo, motion, object recognition,
active vision, model-based vision, vision architectures and hardware,
biological modelling)
Timetable
1. Submissions must be received by December 10, 1990.
Submissions received after that date will be returned unopened.
Authors should note that ordinary mail can sometimes be considerably
delayed and should take this into account when timing their
submissions.
Notification of receipt will be mailed to the first author (or
designated author) soon after receipt.
2. Notification of acceptance or rejection: on or before March 20, 1991.
Notification will be sent to the first author (or designated author).
3. Edited version to be received by April 19, 1991.
General
Authors should submit five (5) copies of their papers in hard copy
form. All paper submissions should be to one of the Program Committee
CoChairs. Electronic or FAX submissions cannot be accepted.
Appearance
Papers should be printed on 8.5" x 11" or A4 sized paper,
double-spaced (i.e. no more than 28 lines per page), with 1.5" margins,
and with 12 point type. Letter quality print is required. (Normally, dot-matrix
printout will be unacceptable unless truly of letter quality. Exceptions will
be made for submissions from countries where high quality printers are not
widely available.)
Length
Papers should be a minimum of 2500 words (about nine pages double
spaced) and a maximum of 5500 words (about 18 pages double spaced),
including figures, tables and diagrams. Each full page of figures
takes the space of about 500 words.
Title Page
Each copy of the paper must include a title page, separate from the
body of the paper. This should contain:
1. Title of the paper.
2. Full names, postal addresses, phone numbers and email addresses of all
authors.
3. An abstract of 100-200 words.
4. The area/subarea in which the paper should be reviewed.
5. A declaration that this paper is not currently under review for
a journal or another conference, nor will it be submitted during
IJCAI's review period. See IJCAI's policy on multiple submissions
below.
Policy on Multiple Submissions
IJCAI will not accept any paper which, at the time of submission, is
under review for a journal or another conference. Authors are also
expected not to submit their papers elsewhere during
IJCAI's review period. These restrictions apply only to journals and
conferences, not to workshops and similar specialized presentations
with a limited audience.
Review Criteria
Papers will be subject to peer review. Selection criteria include
accuracy and originality of ideas, clarity and significance of
results and the quality of the presentation. The decision of the
program committee will be final and cannot be appealed. Papers
selected will be scheduled for presentation and will be printed in the
proceedings. Authors of accepted papers, or their representatives, are expected
to present their papers at the conference.
Video Enhancement of Paper Presentations
In addition to an oral presentation, the authors of accepted papers
may, if they so choose, submit a videotape which will be presented in the
video track session. These tapes will not be refereed but only reviewed for the
quality of the presentation. They are intended to provide additional support to
the written and oral presentation such as demonstrations, illustrations or
applications. For details concerning tape format, see the video track
description below. Reviewing criteria do not apply to these tapes. Only the
submitted papers will be peer-reviewed. Authors wishing to augment their paper
presentation with a video should submit a tape only after their paper
has been accepted. All such arrangements should be made with the video track
chair.
Distinguished Paper Awards
The Program Committee will distinguish one or more papers of
exceptional quality for special awards. This decision will in no way depend on
whether the authors choose to enhance their paper with a video presentation.
2. Videotape Track: Submission Requirements and Guidelines
This track is reserved for displaying interesting research on applications
to real-world problems arising in industrial, commercial, government, space and
educational arenas. It is designed to demonstrate the current levels of
usefulness of AI tools, techniques and methods.
Authors should submit one copy of a videotape of 15 minutes maximum
duration, accompanied by a submission letter that includes:
* Title,
* Full names, postal addresses, phone numbers and email addresses of all
authors,
* Tape format (indicate one of NTSC, PAL or SECAM; and one of VHS or .75"
U-matic),
* Duration of tape in minutes,
* Three copies of an abstract of one to two pages in length, containing the
title of the video, and full names and addresses of the authors,
* Author's permission to copy tape for review purposes.
The timetable and conditions for submission, notification of acceptance or
rejection, and receipt of final version are the same as for the paper
track. See above for details.
All tape submisssions must be made to the Videotape Track Chair.
Tapes cannot be returned; authors should retain extra copies for making
revisions. All submissions will be converted to NTSC format before review.
Tapes will be reviewed and selected for presentation during the
conference. Abstracts of accepted videos will appear
in the conference proceedings. The following criteria will guide
the selection:
* Level of interest to the conference audience
* Clarity of goals, methods and results
* Presentation quality (including audio, video and pace).
Preference will be given to applications that show a high level of
maturity. Tapes that are deemed to be advertising commercial products,
propaganda, purely expository materials, merely taped lectures or
other material not of scientific or technical value will be rejected.
3. Panels, Tutorials, Workshops
The IJCAI-91 technical program will include panels, tutorials and
workshops, for which separate calls for proposals have been issued. For
details about organizing one of these, contact the appropriate chair in
the following list.
4. IJCAI-91 Conference Contacts
Program CoChairs
Paper submissions, reviewing, invited talks, awards and all
matters related to the technical program:
Prof. John Mylopoulos
Department of Computer Science
University of Toronto
Toronto, Ont. M5S 1A4
CANADA
Tel: (+1-416)978-5379
Fax: (+1-416)978-1455
email: ijcai@cs.toronto.edu
Prof. Ray Reiter
Department of Computer Science
University of Toronto
Toronto, Ont. M5S 1A4
CANADA
Tel: (+1-416)978-5379
Fax: (+1-416)978-1455
email: ijcai@cs.toronto.edu
Videotape Track Chair
Videotape submissions, editing and scheduling of video presentations:
Dr. Alain Rappaport
Neuron Data
444 High Street
Palo Alto, CA 94301
USA
Tel: (+1-415)321-4488
Fax: (+1-415)321-3728
email: atr@ml.ri.cmu.edu
Tutorial Chair
Enquiries about tutorial presentations:
Dr. Martha Pollack
Artificial Intelligence Center, SRI International
333 Ravenswood Ave.
Menlo Park, CA 94025
USA
Tel: (+1-415)859-2037
Fax: (+1-415)326-5512
email: pollack@ai.sri.com
Workshop Chair
Enquiries about workshop presentations and scheduling:
Dr. Joe Katz
MITRE Corporation
MS-K318
Burlington Rd.
Bedford, MA 01730
USA
Tel: (+1-617)271-8899
Fax: (+1-617)271-2423
email: katz@mbunix.mitre.org
Panel Chair
Enquiries about panels:
Dr. Peter F. Patel-Schneider
AT&T Bell Labs
600 Mountain Ave.
Murray Hill, NJ 07974
USA
Tel: (+1-201)582-3399
Fax: (+1-201)582-5192
email: pfps@research.att.com
Australian National Committee Secretariat
For enquiries about registration, accommodation and other local
arrangements:
Ms. Beverley Parrott
IJCAI-91
Parrish Conference Organizers
PO Box 787
Potts Point NSW 2011
AUSTRALIA
Tel: (+61-2)357-2600
Fax: (+61-2)357-2950
IJCAI-91 Exhibition Secretariat
For enquiries concerning the exhibition:
Ms. Julia Jeffrey
Jeffrey Enterprises
104 Falcon Street
Crows Nest NSW 2065
AUSTRALIA
Tel: (+61-2)954-0842
Fax: (+61-2)925-0735
Australian National Committee Chair
For enquiries about general Australian arrangements:
Prof. Michael A. McRobbie
Centre for Information Science Research
I Block
Australian National University
GPO Box 4
Canberra ACT 2601
AUSTRALIA
Tel: (+61 6)249-2035
Fax: (+61-6)249-0747
email: mam@arp.anu.oz.au
Conference Chair
For other general conference related matters:
Prof. Barbara J. Grosz
Aiken Computation Lab 20
Harvard University
33 Oxford Street
Cambridge MA 02138, USA
Tel: (+1-617)495-3673
Fax: (+1-617)495-9837
email: grosz@endor.harvard.edu
IJCAII and IJCAI-91 Secretary-Treasurer
Dr. Donald E. Walker
Bellcore, MRE 2A379
445 South Street, Box 1910
Morristown, NJ 07960-1910
USA
Tel: (+1-201)829-4312
Fax: (+1-201)455-1931
email: walker@flash.bellcore.com
------------------------------
Date: Fri, 6 Jul 1990 16:16:01 -0400
From: Kimberlee Pietrzak-Smith <kim@cs.toronto.edu>
Subject: IJCAI'91 Call for Workshops
Call for Workshop Proposals: IJCAI-91
The IJCAI-91 Program Committee invites proposals for the Workshop
Program of the International Joint Conference on Artificial Intelligence
(IJCAI-91),to be held in Sydney, Australia, 24-30 August 1991.
Gathering in an informal setting, workshop participants will have the
opportunity to meet and discuss selected technical topics in an atmosphere
which fosters the active exchange of ideas among researchers and
practitioners. Members from all segments of the AI community are invited
to submit proposals for review.
To encourage interaction and a broad exchange of ideas, the workshops
will be kept small, preferably under 35 participants. Attendance should be
limited to active participants only. The format of workshop presentations
will be determined by the organizers proposing the workshop, but ample time
must be allotted for general discussion. Workshops can vary in length , but
most will last a half day or a full day. Proposals for workshops
should be between one and two pages in length, and should contain:
1. A brief description of the workshop identifying specific technical issues
that will be its focus.
2. A discussion of why the workshop is of interest at this time,
3. The names, postal addresses, phone numbers and email addresses of the
organizing committee, consisting of three or four people knowledgeable in the
field and not all at the same organization,
4. A proposed schedule for organizing the workshop and a preliminary
agenda.
Proposals should be submitted as soon as possible, but no
later than 21 December 1990. Proposals will be reviewed as they are received
and resources allocated as workshops are approved. Organizers will be notified
of the committee's decision no later than 15 February 1991.
Workshop organizers will be responsible for:
1. Producing a Call for Participation in the workshop, open to all members
of the AI community, which will be distributed by IJCAI.
2. Reviewing requests to participate in the workshop and selecting the
participants.
3. Scheduling the workshop activities. All organizational arrangements
must be completed by May 15, 1991.
4. Preparing a review of the workshop for publication.
IJCAI will provide logistical support and a meeting place
for the workshop, and, in conjunction with the organizers, will determine the
workshop date and time. IJCAI reserves the right to cancel any workshop
if deadlines are missed.
To cover costs, it will be necessary to charge a fee of $US50 for each
participant.
Please submit your proposals, and any enquiries to:
Dr. Joseph Katz
MITRE Corporation
MS-K318
Burlington Road
Bedford, MA 01730
USA
Tel: (+1-617) 271-8899
Fax: (+1-617) 271-2423
email: katz@mbunix.mitre.org
------------------------------
Date: Fri, 6 Jul 1990 16:16:36 -0400
From: Kimberlee Pietrzak-Smith <kim@cs.toronto.edu>
Subject: IJCAI'91 Call for Tutorials
Call for Tutorial Proposals: IJCAI-91
The IJCAI-91 Program Committee invites proposals for the
Tutorial program of the International Joint Conference on Artificial
Intelligence (IJCAI-91) to be held in Sydney, Australia, 24-30 August 1991.
Tutorials will be offered both on standard topics and on new
and more advanced topics. A list of topics from the IJCAI-89 Tutorial
Program is given below, to suggest the breadth of topics that can be
covered by tutorials, but this list is only a guide. Other topics,
both related to these and quite different from them, will be
considered:
* Introduction to Artificial Intelligence
* Logic Programming
* Planning and Reasoning about Time
* Evaluating Knowledge-Engineering Tools
* Truth Maintenance Systems
* Knowledge-Acquisition
* Natural Language Processing
* Artificial Intelligence and Education
* Common Lisp Object System
* Advanced Architectures for Expert Systems
* Computer Vision
* Uncertainty Management
* Model-Based Diagnosis
* Case-Based Reasoning
* Real-Time Knowledge-Based Systems
* Neural Network Architectures
* Managing Expert Systems Projects
* Knowledge Representation
* Artificial Intelligence and Design
* Reasoning about Action and Change
* Inductive Learning
* Verifying and Validating Expert Systems
* Constraint-Directed Reasoning
* Integrating AI and Database Technologies
Anyone interested in presenting a tutorial should submit a
proposal to the 1991 Tutorial Chair, Martha Pollack. Proposals from a
pair of presentors will be strongly favored over ones from a single
individual. A tutorial proposal should contain the following information:
1. Topic.
2. A brief description of the tutorial, suitable for inclusion in
the conference registration brochure.
3. A detailed outline of the tutorial.
4. The necessary background and the potential target audience for
the tutorial.
5. A description of why the tutorial topic is of interest to a
substantial segment of the IJCAI audience (for new topics only).
6. A brief resume of the presentor(s), which should include name,
mailing address, phone number, email address if available, background
in the tutorial area, any available examples of work in the area
(ideally, a published tutorial-level article on the subject), evidence
of teaching experience (including references that address the
proposer's presentation ability), and evidence of scholarship in
AI/Computer Science (equivalent to a published IJCAI conference paper
or tutorial syllabus).
Those submitting a proposal should keep in mind that tutorials are
intended to provide an overview of a field; they should present
reasonably well agreed upon information in a balanced way. Tutorials
should not be used to advocate a single avenue of research, nor should
they promote a product.
Proposals must be received by Jan. 4, 1991. Decisions about topics and
speakers will be made by Feb. 22, 1991. Speakers should be prepared to submit
completed course materials by July 1, 1991.
Proposals should be sent to:
Dr. Martha Pollack
Artificial Intelligence Center
SRI International
333 Ravenswood Ave.
Menlo Park, CA 94025
USA
email: pollack@ai.sri.com
Tel: (+1-415) 859-2037
Fax: (+1-415) 326-5512 (NOTE: Indicate clearly on the first page
that it is intended for "Martha Pollack, Artificial Intelligence Center".)
------------------------------
Date: Fri, 6 Jul 1990 16:17:08 -0400
From: Kimberlee Pietrzak-Smith <kim@cs.toronto.edu>
Subject: IJCAI'91 Call for Awards
CALL FOR NOMINATIONS FOR IJCAI AWARDS: IJCAI-91
THE IJCAI AWARD FOR RESEARCH EXCELLENCE
The IJCAI Award for Research Excellence is given at an IJCAI, to a
scientist who has carried out a program of research of consistently
high quality yielding several substantial results. If the research
program has been carried out collaboratively, the Award may be made
jointly to the research team. Past recipients of this Award are
John McCarthy (1985) and Allen Newell (1989).
The Award carries with it a certificate and the sum of $US2,000 plus
travel and living expenses for the IJCAI. The researcher(s) will
be invited to deliver an address on the nature and significance of
the results achieved and write a paper for the conference proceedings.
Primarily, however, the Award carries the honour of having one's
work selected by one's peers as an exemplar of sustained research
in the maturing science of Artificial Intelligence.
We hereby call for nominations for The IJCAI Award for Research
Excellence to be made at IJCAI-91 which is to be held in Sydney,
Australia, 24-30 August 1991. The accompanying note on Selection
Procedures for IJCAI Awards provides the relevant details.
THE COMPUTERS AND THOUGHT AWARD
The Computers and Thought Lecture is given at each International
Joint Conference on Artificial Intelligence by an outstanding young
scientist in the field of Artificial Intelligence. The Award
carries with it a certificate and the sum of $US2,000 plus travel
and subsistence expenses for the IJCAI. The Lecture is presented
one evening during the Conference, and the public is invited to
attend. The Lecturer is invited to publish the Lecture in the
conference proceedings. The Lectureship was established with
royalties received from the book Computers and Thought, edited by
Feigenbaum and Feldman; it is currently supported by income from
IJCAI funds.
Past recipients of this honour have been Terry Winograd (1971),
Patrick Winston (1973), Chuck Rieger (1975), Douglas Lenat (1977),
David Marr (1979), Gerald Sussman (1981), Tom Mitchell (1983),
Hector Levesque (1985), Johan de Kleer (1987) and Henry Kautz
(1989).
Nominations are invited for The Computers and Thought Award to be
made at IJCAI-91 in Sydney. The note on Selection Procedures for
IJCAI Awards describes the nomination procedures to be followed.
SELECTION PROCEDURES FOR IJCAI AWARDS
Nominations for The IJCAI Award for Research Excellence and The
Computers and Thought Award are invited from all members of the
Artificial Intelligence international community. The procedures
are the same for both awards.
There should be a nominator and a seconder, at least one of whom
should not have been in the same institution as the nominee. The
nominators should prepare a short submission of less than 2,000
words, outlining the nominee's qualifications with respect to the
criteria for the particular award.
The award selection committee is the union of the Program, Conference
and Advisory Committees of the upcoming IJCAI and the Board of
Trustees of International Joint Conferences on Artificial Intelligence,
Inc., with nominees excluded.
Nominations should be sent to the Conference Chair for IJCAI-91 at the
address below. They must be sent in hardcopy form; electronic
submissions cannot be accepted. The deadline for nominations is
1 December 1990. To avoid duplication of effort, nominators are
requested to submit the name of the person they are nominating by
1 November 1990 so that people who propose to nominate the same
individual may be so informed and can coordinate their efforts.
Prof. Barbara J. Grosz
Conference Chair, IJCAI-91
Aiken Computation Lab 20
Harvard University
33 Oxford Street
Cambridge, MA 02138, USA
tel: (+1-617) 495-3673
fax: (+1-617) 495-9837
grosz@endor.harvard.edu
Due Date for nominations: 1 December 1990.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (07/26/90)
Vision-List Digest Wed Jul 25 10:10:21 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
vision book list: addendum
Camera Mount
Anybody working in visualization in Israel?
IJPRAI CALL FOR PAPERS
(Summary) Re: Character Recognition Bibliography?
----------------------------------------------------------------------
Date: Thu, 19 Jul 90 15:42:52 +0200
From: ronse@prlb.philips.be
Subject: vision book list: addendum
I received a few more suggestions of important books on vision since I
sent my summary to the list. Here they are:
M.A. Fischler & O. Firschein: "Readings in Computer Vision: Issues,
Problems, Principles, and Paradigms", Morgan Kaufmann, Los Altos, CA,
1987.
A.P. Pentland: "From Pixels to Predicates", Ablex Publ. Corp., Norwood,
NJ, (1986).
Blake & Zisserman: "Visual Reconstruction"
Besl: "Range image Understanding"
Someone also suggested a special issue from a serial journal:
"Artificial Intelligence", special isue on Computer Vision, Vol. 17
(1981).
Christian Ronse
Internet: ronse@prlb.philips.be
BITNET: ronse%prlb.philips.be@cernvax
------------------------------
Date: Tue, 17 Jul 90 17:34 PDT
From: H. Keith Nishihara <hkn@natasha.ads.com>
Subject: Camera Mount
Phone: (415)328-8886
Us-Mail: Teleos Research, 576 Middlefield Road, Palo Alto, CA 94301
Date: Sun, 8 Jul 90 12:38:29 -0400 (EDT)
From: "Ethan Z. Evans" <ee0i+@andrew.cmu.edu>
Vision Wizards:
I need to find a 2 degree of freedom camera mount (rotation and pitch).
The mobile platform I work on is only about a foot tall, and the top is
cluttered with various hardware etc. Thus to give the robot a view of
its world, we need to set the camera up on a pole. Once its up their it
needs to be able to turn around and either look down at what the arm is
doing, or out at where the base is going. Point is, I don't have the
slightest idea where to look for such a device. If anyone could give me
a starting point as to where to get such a mount, especially one easily
controlled through a PC parallel or serial port, I would be most
greatful.
Thanks in advance,
Ethan Evans
ee0i@andrew.cmu.edu
[ Please post responses to the List
phil... ]
We are in the process of developing a small two axis camera mount as
part of a third generation video-rate sign-correlation stereo and motion
system that we are building this summer at Teleos Research.
The camera mount has the following approximate specs:
Pan range: infinite (or till your camera wires break)
Pitch range: -90 to 90 degrees
Accuracy: 11 min of arc
Height: 21 cm
Diameter: 9.7 cm
Weight: 0.68 kg
Controller boards (for the IBM PC, VME, STD, and Multibus) are available for
operating the pan-pitch head in absolute position mode, incremental position
mode, or velocity mode. We plan to use this device to hold a stereo camera
fixture that also provides vergence control for binocular stereo work.
We have not thought about making this device commercially available but that
is a possibility. If interested contact Jeff Kerr or myself at Teleos
Research.
Keith
------------------------------
Subject: Anybody working in visualization in Israel?
Date: Wed, 18 Jul 90 13:01:51 -0400
From: haim@hawk.ulowell.edu
Hi,
I'm trying to establish contact with researchers in the visualization
field who work in Israel.
If you are, or you know somebody who is, I'd appreciate you sending me
a message (please send me a presonal message, even if you are also
posting it on this list).
Thanks,
Haim Levkowitz
Institute for Visualization and Perception Research
University of Lowell
Lowell, MA 01854
508-934-3654
------------------------------
Date: Sun, 22 Jul 90 15:27:59 PDT
From: skrzypek@CS.UCLA.EDU (Dr. Josef Skrzypek)
Subject: IJPRAI CALL FOR PAPERS
IJPRAI CALL FOR PAPERS IJPRAI
We are organizing a special issue of IJPRAI (Intl. Journal of
Pattern Recognition and Artificial Intelligence) dedicated to the
subject of neural networks in vision and pattern recognition.
Papers will be refereed. The plan calls for the issue to be
published in the fall of 1991. I would like to invite your
participation.
DEADLINE FOR SUBMISSION: 10th of December, 1990
VOLUME TITLE: Neural Networks in Vision and Pattern Recognition
VOLUME GUEST EDITORS: Prof. Josef Skrzypek and Prof. Walter Karplus
Department of Computer Science, 3532 BH
UCLA
Los Angeles CA 90024-1596
Email: skrzypek@cs.ucla.edu or karplus@cs.ucla.edu
Tel: (213) 825 2381
Fax: (213) UCLA CSD
DESCRIPTION
The capabilities of neural architectures (supervised and
unsupervised learning, feature detection and analysis through
approximate pattern matching, categorization and self-organization,
adaptation, soft constraints, and signal based processing) suggest
new approaches to solving problems in vision, image processing and
pattern recognition as applied to visual stimuli. The purpose of
this special issue is to encourage further work and discussion in
this area.
The volume will include both invited and submitted peer-reviewed
articles. We are seeking submissions from researchers in relevant
fields, including, natural and artificial vision, scientific
computing, artificial intelligence, psychology, image processing
and pattern recognition. "We encourage submission of: 1) detailed
presentations of models or supporting mechanisms, 2) formal
theoretical analyses, 3) empirical and methodological studies. 4)
critical reviews of neural networks applicability to various
subfields of vision, image processing and pattern recognition.
Submitted papers may be enthusiastic or critical on the
applicability of neural networks to processing of visual
information. The IJPRAI journal would like to encourage
submissions from both , researchers engaged in analysis of
biological systems such as modeling
psychological/neurophysiological data using neural networks as well
as from members of the engineering community who are synthesizing
neural network models. The number of papers that can be included
in this special issue will be limited. Therefore, some qualified
papers may be encouraged for submission to the regular issues of
IJPRAI.
SUBMISSION PROCEDURE
Submissions should be sent to Josef Skrzypek, by 12-10-1990. The
suggested length is 20-22 double-spaced pages including figures,
references, abstract and so on. Format details, etc. will be
supplied on request.
Authors are strongly encouraged to discuss ideas for possible
submissions with the editors.
The Journal is published by the World Scientific and was
established in 1986.
Thank you for your considerations.
------------------------------
From: atul k chhabra <Atul.Chhabra@UC.EDU>
Subject: (Summary) Re: Character Recognition Bibliography?
Date: Sat, 21 Jul 90 14:08:04 EDT
Here is a summary of what I received in response to my request for references
on character recognition. I had asked for references in all aspects of
character recognition -- preprocessing and segmentation, OCR, typewritten
character recognition, handwritten character recognition, neural network based
recognition, statistical and syntactic recognition, hardware implementations,
and commercial character recognition systems. THANKS TO ALL WHO RESPONDED.
IF ANYONE OUT THERE HAS MORE REFERENCES, PLEASE EMAIL ME. I WILL SUMMARIZE NEW
RESPONSES AFTER ANOTHER TWO WEEKS. THANKS.
Atul Chhabra
Department of Electrical & Computer Engineering
University of Cincinnati, ML 030
Cincinnati, OH 45221-0030
Phone: (513)556-6297
Email: achhabra@uceng.uc.edu
***************
From: Sol <sol@iai.es>
Sol Delgado
Instituto de Automatica Industial
La Poveda Arganda del Rey
28500 MADRID
SPAIN
sol@iai.es
[ 1]_ Off-Line cursive script word recognition
Radmilo M. Bozinovic, Sargur N. Srihari
IEEE transactions on pattern analysis and machine intelligence.
Vol. 11, January 1989.
[ 2]_ Visual recognition of script characters. Neural networt architectures.
Jodef Skrzypek, Jeff Hoffman.
MPL (Machine Perception Lab). Nov 1989.
[ 3]_ On recognition of printed characters of any font and size.
Simon Kahan, Theo Pavlidis, Henry S. Baird.
IEEE transactions on pattern analysis and machine intelligence
Vol PAMI_9, No 2, March 1987.
[ 4]_ Research on machine recognition of handprinted characters.
Shunji Mori, Kazuhiko Yamamoto, Michio Yasuda.
IEEE transactions on pattern analysis and machine intelligence.
Vol PAMI_6, No 4. July 1984.
[ 5]_ A pattern description and generation method of structural
characters
Hiroshi nagahashi, Mikio Nakatsuyama.
IEEE transactions on pattern analysis and machine intelligence
Vol PAMI_8, No 1, January 1986.
[ 6]_ An on-line procedure for recognition of handprinted alphanumeric
characters.
W. W. Loy, I. D. Landau.
IEEE transactions on pattern analysis and machine intelligence.
Vol PAMI_4, No 4, July 1982.
[ 7]_ A string correction algorithm for cursive script recognition.
Radmilo Bozinovic, Sargur N. Srihari.
IEEE transactions on pattern analysis and machine inteligence.
Vol PAMI_4, No 6, November 1982.
[ 8]_ Analisys and design of a decision tree based on entropy reduction
and its application to large character set recognition
Qing Ren Wang, Ching Y. Suen.
IEEE transactions on pattern analysis and machine intelligence.
Vol PAMI_6, No 4, July 1984.
[ 9]_ A method for selecting constrained hand-printed character shapes
for machine recognition
Rajjan Shinghal, Ching Y. Suen
IEEE transactions on pattern analysis and machine intelligence.
Vol PAMI_4, No 1, January 1982
[10]_ Pixel classification based on gray level and local "busyness"
Philip A. Dondes, Azriel Rosenfeld.
IEEE transactions on pattern analysis and machine intelligence.
Vol PAMI_4, No 1, January 1982.
[11]_ Experiments in the contextual recognition of cursive script
Roger W. Ehrich, Kenneth J. Koehler
IEEE transactions on computers, vol c-24, No. 2, February 1975.
[12]_ Character recognition by computer and applications.
Ching Y. Suen.
Handbook of pattern recognition and image procesing.
ACADEMIC PRESS, INC. August 1988.
[13]_ A robust algorithm for text string separation from mixed
text/graphics images
Lloyd Alan Fletcher, Rangachar Kasturi
IEEE transactions on pattern analysis and machine intelligence.
Vol 10, No 6, November 1988.
[14]_ Segmentation of document images.
Torfinn Taxt, Patrick J. Flynn, Anil K. Jain
IEEE transactions on pattern analysis and machine intelligence.
Vol 11, No 12, december 1989.
[15]_ Experiments in text recognition with Binary n_Gram and Viterbi
algorithms.
Jonathan J. Hull, Sargur N. Srihari
IEEE transactions on pattern analysis and machine intelligence
Vol PAMI-4, No 5, september 1982.
[16]- Designing a handwriting reader.
D. J. Burr
IEEE transactions on pattern analysis and machine intelligence
Vol PAMI-5, No 5, september 1983.
[17]_ Experiments on neural net recognition of spoken and written text
David J. Burr
IEEE transactions on acoustics, speech and signals processing
vol 36, No 7, july 1988
[18]_ Experimets with a connectionist text reader
D. J. Burr
Bell communications research
Morristow, N. J. 07960
[19]_ An Algorithm for finding a common structure shared by a family of
strings
Anne M. Landraud, Jean-Francois Avril, Philippe Chretienne.
IEEE transactions on pattern analysis and machine intelligence
Vol 11, No 8, august 1989
[20]_ Word_level recognition of cursive script
Raouf F. H. Farag
IEEE transactions on computers
Vol C-28, No 2, february 1979
[21]_ Pattern Classification by neural network: an experimental system
for icon recognition
Eric Gullichsen, Ernest Chang
Marzo, 1987
[22]_ Recognition of handwritten chinese characters by modified hough
transform techniques.
Fang-Hsuan Cheng, Wen-Hsing Hsu, Mei-Ying Chen
IEEE transactions on pattern analysis and machine intelligence
Vol 11, No 4, April 1989
[23]_ Inheret bias and noise in the Hough transform
Christopher M. Brown
IEEE transactions on pattern analysis and machine intelligence
Vol PAMI-5, No 5, september 1983.
[24]_ From pixels to features
J. C. Simon
North-Holland
_ Feature selection and Language syntax in text recognition.
J.J. Hull
_ Feature extraction for locating address blocks on mail pieces.
S.N. Srihari.
[25]_ A model for variability effects in hand-printing, with implications
for the design of on line character recognition systems.
J.R. Ward and T. Kuklinski.
IEEE transactions on systems, man and cybernetics.
Vol 18, No 3, May/June 1988.
[26]_ Selection of a neural network system for visual inspection.
Paul J. Stomski, Jr and Adel S. Elmaghraby
Engineering Mathematics And Computer Science
University of Louisville, Kentucky 40292
[27]_ Self-organizing model for pattern learning and its application to
robot eyesight.
Hisashi Suzuki, Suguru Arimoto.
Proceedings of the fourth conference on A.I.
san Diego, March 1988.
The computer society of the IEEE.
***************
From: J. Whiteley <WHITELEY-J@OSU-20.IRCC.OHIO-STATE.EDU>
I only have five references I can offer, all are from the Proceedings of the
1989 International Joint Conference on Neural Networks held in Washington D.C.
Yamada, K.
Kami, H.
Tsukumo, J.
Temma, T.
Handwritten Numeral Recognition by Multi-layered Neural Network
with Improved Learning Algorithm
Volume II, pp. 259-266
Morasso, P.
Neural Models of Cursive Script Handwriting
Volume II, pp.539-542
Guyon, I.
Poujaud, I.
Personnaz, L.
Dreyfus, G.
Comparing Different Neural Network Architectures for Classifying
Handwritten Digits
Volume II, pp.127-132
Weideman, W.E.
A Comparison of a Nearest Neighbor Classifier and a Neural Network for
Numeric Handprint Character Recognition
Volume I, pp.117-120
Barnard, E.
Casasent, D.
Image Processing for Image Understanding with Neural Nets
Volume I, pp.111-115
Hopefully you are being deluged with references.
Rob Whiteley
Dept. of Chemical Engineering
Ohio State University
email: whiteley-j@osu-20.ircc.ohio-state.edu
***********
From: avi@dgp.toronto.edu (Avi Naiman)
%L Baird 86
%A H. S. Baird
%T Feature Identification for Hybrid Structural/Statistical Pattern Classification
%R Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
%D June 1986
%P 150-155
%L Casey and Jih 83
%A R. G. Casey
%A C. R. Jih
%T A Processor-Based OCR System
%J IBM Journal of Research and Development
%V 27
%N 4
%D July 1983
%P 386-399
%L Cash and Hatamian 87
%A G. L. Cash
%A M. Hatamian
%T Optical Character Recognition by the Method of Moments
%J Computer Vision, Graphics and Image Processing
%V 39
%N 3
%D September 1987
%P 291-310
%L Chanda et al. 84
%A B. Chanda
%A B. B. Chaudhuri
%A D. Dutta Majumder
%T Some Algorithms for Image Enhancement Incorporating Human Visual Response
%J Pattern Recognition
%V 17
%D 1984
%P 423-428
%L Cox et al. 74
%A C. Cox
%A B. Blesser
%A M. Eden
%T The Application of Type Font Analysis to Automatic Character Recognition
%J Proceedings of the Second International Joint Conference on Pattern Recognition
%D 1974
%P 226-232
%L Frutiger 67
%A Adrian Frutiger
%T OCR-B: A Standardized Character for Optical Recognition
%J Journal of Typographic Research
%V 1
%N 2
%D April 1967
%P 137-146
%L Goclawska 88
%A Goclawska
%T Method of Description of the Alphanumeric Printed Characters by Signatures for Automatic Text Readers
%J AMSE Review
%V 7
%N 2
%D 1988
%P 31-34
%L Gonzalez 87
%A Gonzalez
%T Designing Balance into an OCR System
%J Photonics Spectra
%V 21
%N 9
%D September 1987
%P 113-116
%L GSA 84
%A General Services Administration
%T Technology Assessment Report: Speech and Pattern Recognition; Optical Character Recognition; Digital Raster Scanning
%I National Archives and Records Service
%C Washington, District of Columbia
%D October 1984
%L Hull et al. 84
%A J. J. Hull
%A G. Krishnan
%A P. W. Palumbo
%A S. N. Srihari
%T Optical Character Recognition Techniques in Mail Sorting: A Review of Algorithms
%R 214
%I SUNY Buffalo Computer Science
%D June 1984
%L IBM 86
%A IBM
%T Character Recognition Apparatus
%J IBM Technical Disclosure Bulletin
%V 28
%N 9
%D February 1986
%P 3990-3993
%L Kahan et al. 87
%A A. Kahan
%A Theo Pavlidis
%A H. S. Baird
%T On the Recognition of Printed Characters of any Font and Size
%J IEEE Transactions on Pattern Analysis and Machine Intelligence
%V PAMI-9
%N 2
%D March 1987
%P 274-288
%L Lam and Baird 86
%A S. W. Lam
%A H. S. Baird
%T Performance Testing of Mixed-Font, Variable-Size Character Recognizers
%R AT&T Bell Laboratories Computing Science Technical Report No. 126
%C Murray Hill, New Jersey
%D November 1986
%L Lashas et al. 85
%A A. Lashas
%A R. Shurna
%A A. Verikas
%A A. Dosimas
%T Optical Character Recognition Based on Analog Preprocessing and Automatic Feature Extraction
%J Computer Vision, Graphics and Image Processing
%V 32
%N 2
%D November 1985
%P 191-207
%L Mantas 86
%A J. Mantas
%T An Overview of Character Recognition Methodologies
%J Pattern Recognition
%V 19
%N 6
%D 1986
%P 425-430
%L Murphy 74
%A Janet Murphy
%T OCR: Optical Character Recognition
%C Hatfield
%I Hertis
%D 1974
%L Nagy 82
%A G. Nagy
%T Optical Character Recognition \(em Theory and Practice
%B Handbook of Statistics
%E P. R. Krishnaiah and L. N. Kanal
%V 2
%I North-Holland
%C Amsterdam
%D 1982
%P 621-649
%L Pavlidis 86
%A Theo Pavlidis
%T A Vectorizer and Feature Extractor for Document Recognition
%J Computer Vision, Graphics and Image Processing
%V 35
%N 1
%D July 1986
%P 111-127
%L Piegorsch et al. 84
%A W. Piegorsch
%A H. Stark
%A M. Farahani
%T Application of Image Correlation for Optical Character Recognition in Printed Circuit Board Inspection
%R Proceedings of SPIE \(em The International Society for Optical Engineering: Applications of Digital Image Processing VII
%V 504
%D 1984
%P 367-378
%L Rutovitz 68
%A D. Rutovitz
%T Data Structures for Operations on Digital Images
%B Pictorial Pattern Recognition
%E G. C. Cheng et al.
%I Thompson Book Co.
%C Washington, D. C.
%D 1968
%P 105-133
%L Smith and Merali 85
%A J. W. T. Smith
%A Z. Merali
%T Optical Character Recognition: The Technology and its Application in Information Units and Libraries
%R Library and Information Research Report 33
%I The British Library
%D 1985
%L Suen 86
%A C. Y. Suen
%T Character Recognition by Computer and Applications
%B Handbook of Pattern Recognition and Image Processing
%D 1986
%P 569-586
%L Wang 85
%A P. S. P. Wang
%T A New Character Recognition Scheme with Lower Ambiguity and Higher Recognizability
%J Pattern Recognition Letters
%V 3
%D 1985
%P 431-436
%L White and Rohrer 83
%A J.M. White
%A G.D. Rohrer
%T Image Thresholding for Optical Character Recognition and Other Applications Requiring Character Image Extraction
%J IBM Journal of Research and Development
%V 27
%N 4
%D July 1983
%P 400-411
%L Winzer 75
%A Gerhard Winzer
%T Character Recognition With a Coherent Optical Multichannel Correlator
%J IEEE Transactions on Computers
%V C-24
%N 4
%D April 1975
%P 419-423
***************
From: nad@computer-lab.cambridge.ac.uk
Hi,
I've only got two references for you - but they have 42 and 69 references,
respectively (some of the refs will be the same, but you get at least 69
references!).
They are:
"An overview of character recognition methodologies"
J. Mantas
Pattern Recognition, Volume 19, Number 6, 1986
pages 425-430
"Methodologies in pattern recognition and image analysis - a brief survey"
J. Mantas
Pattern Recognition, Volume 20, Number 1, 1987
pages 1-6
Neil Dodgson
*************
From: YAEGER.L@AppleLink.Apple.COM
I presume you know of "The 1989 Neuro-Computing Bibliography" edited by Casimir
C. Klimasauskas, a Bradford Book, from MIT Press. It lists 11 references for
character recognition in its index.
- larryy@apple.com
***********
From: Tetsu Fujisaki <TETSU@IBM.COM>
1. Suen, C. Y., Berthod, M., and Mori, S.,
"Automatic Recognition of Handprinted Characters - The State
of the Art", Proc. IEEE, 68, 4 (April 1980) 469-487
2. Tappert, C. C., Suen, C. Y., and Wakahara T,
"The State-of-the-Art in on-line handwriting recognition",
IEEE Proc. 9th Int'l Conf. on Pattern Recognition, Rome Italy,
Nov. 1988. Also in IBM RC 14045.
***********
From: burrow@grad1.cis.upenn.edu (Tom Burrow)
Apparently, the state of the art in connectionism, as a lot of people
will tell you, I'm sure, is Y. Le Cun et al's work which can be found
in NIPS 90. Other significant connectionist approaches are
Fukushima's neocognitron and Denker et al's work which I *believe* is
in NIPS 88.
I am interested in handprinted character recognition. Type set
character recognition is basically solved, and I believe you shouldn't
have any trouble locating texts on this (although I've only looked at
the text edited by Kovalevsky (sp?), which I believe is just entitled
"Reading Machines". Bayesian classifiers, which you can read about in
any statistical pattern recognition text (eg, Duda and Hart, Gonzalez,
etc), are capable of performing recognition, since one can choose
reliable features present in machine printed text (eg, moments,
projections, etc), and the segmentation problem is fairly trivial).
Perhaps the greatest problem in handprinted recognition is the
segmentation problem. Unfortunately, most connectionist approaches
fail miserably in this respect, relying on traditional methods for
segmentation which become a bottleneck. I am inspecting connectionist
methods which perform segmentation and recognition concurrently, and I
recommend you do not inspect the problems independently.
I am by no means expert in any area which I've commented on, but I
hope this helps. Also, again, please send me your compiled responses.
Thank you and good luck.
Tom Burrow
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/02/90)
Vision-List Digest Wed Aug 01 12:47:50 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Line length using Hough Transform
Where to find jobs in Image/ digital signal processing?
Displaying 24bit/pix images on 8bit/pix device
fractals and texture analysis
postdoctoral position available
3 Research Posts - Computer Vision
----------------------------------------------------------------------
Date: 26 July 90, 17:32:19 UPM
From: FACC005@SAUPM00.BITNET
Subject: Line length using Hough Transform
Can anyone give me any pointer to literature on finding the length
(not parameters) of a line using Hough Transform. The line may
be short i.e. it may not cross the full image.
Thanks in advance.
ATIQ (facc005@saupm00.bitnet)
------------------------------
Date: Thu, 26 Jul 90 16:15 EST
From: CHELLALI@northeastern.edu
Subject: Where to find jobs in Image/ digital signal processing?
Hi,
Can anyone tell me what's a good place to look for a job in Electrical
Engineering (Image/ digital signal processing) with a Ph.D degree.
Also, I would like to add that the job should not require US citizen...
I am in Boston right now, and jobs are not comming easy.
Thanks a lot.
M Chellali
------------------------------
Date: 27 Jul 90 20:56:07 GMT
From: surajit@hathi.eng.ohio-state.edu (Surajit Chakravarti)
Subject: Displaying 24bit/pix images on 8bit/pix device
Organization: The Ohio State University Dept of Electrical Engineering
Hi folks,
We have a few images in 24 bits/pixel format (one byte each of Red, Green
and Blue per pixel). We need to convert these images into sun raster 8 bit
color format or GIF format in order to display on X windows. Is there any
available programs or formulae that would let us either convert these images
to a compatible form or let us display them directly on the X windows?
Any information in this regard will be greatly appreciated.
Thanks in advance.
Surajit Chakravarti * surajit@hathi.eng.ohio-state.edu
* Office: 679 Dreese Labs
Electrical Engineering * SPANN Lab: 512 Dreese Labs
The Ohio State University * SPANN Phone: (614)-292-6502
------------------------------
Date: Mon, 30 Jul 90 17:52:44 bst
From: Eduardo Bayro <eba@computing-maths.cardiff.ac.uk>
Subject: fractals and texture analysis
Organization: Univ. of Wales Coll. of Cardiff, Dept. of Electronic & Systems Engineering
Does anybody knows about the use of fractals in image processing
for texture analysis. Fractals are used in chaos theory and non-
linearities. Answers by e-mail are appreciate. Many thanks.
Eduardo Bayro
Eduardo Bayro, School of Electrical, Electronic and Systems Engineering,
University of Wales College of Cardiff, Cardiff, Wales, UK.
Internet: eba%cm.cf.ac.uk@nsfnet-relay.ac.uk Janet: eba@uk.ac.cf.cm
UUCP: eba@cf-cm.UUCP or ...!mcsun!ukc!cf-cm!eba
------------------------------
Date: Tue, 31 Jul 90 00:12 EDT
From: GINDI%GINDI@Venus.YCC.Yale.Edu
Subject: postdoctoral position available
YALE UNIVERSITY
Postdoctoral Position in Neural Networks for Vision
One position is open within a research group interested in developing
neural network-based approaches to computer vision and image understanding
problems. We are particularly interested in using model-based optimization
strategies for locating and quantifying objects and other image structures,
and automatically learning the characteristics of new ones; we are in the
process of extending these ideas to scale-space and other continuation
methods for optimization. The group includes three faculty members,
three Ph.D. students and a full time programmer. Collaboration with
researchers in biomedical and neurobiological image processing is also
possible. The position is joint between the Departments of Computer
Science and Diagnostic Radiology. In addition, the research group has
strong ties with faculty members in the Electrical Engineering Department.
Those who apply should have a Ph.D. in a neural network-related field such
as computer science, electrical engineering, applied mathematics or physics,
preferably with a strong background and coursework in image processing and
computer vision. A strong programming ability is also preferred. The
initial appointment will be for one year, renewable for a second year
contingent upon the availability of funds and by mutual agreement. Salary
will be based on background and experience, but is expected to be in the
$28K - $32K range. Review of applications will begin immediately and will
be accepted until the position is filled.
Applicants should send a resume and the names and addresses of three
references to:
Professor Eric Mjolsness,
Department Computer Science, Yale Unversity
P.O. Box 2158 Yale Station
51 Prospect Street
New Haven, Connecticut, 06520,
and should also, if possible, contact him by electronic mail at
mjolsness@cs.yale.edu
OR write and email to:
Professor Gene Gindi
Department of Electrical Engineering
Yale University
P.O. Box 2157 Yale Station
New Haven, Connecticut 06520
gindi@venus.ycc.yale.edu
------------------------------
Date: Wed, 1 Aug 90 12:06:50 BST
From: D K Naidu <dkn@aifh.edinburgh.ac.uk>
Subject: 3 Research Posts - Computer Vision
Three Research Posts - Computer Vision
University of Edinburgh
Department of Artificial Intelligence
Applications are invited for three researchers to work in the
Department of Artificial Intelligence on a European Institute of
Technology funded research project entitled "Surface-Based Object
Recognition for Industrial Automation" and a SERC funded IED pro-
ject entitled "Location and Inspection from Range Data". Princi-
pal investigators on the projects are Dr. Robert Fisher and Dr.
John Hallam.
The projects investigate the use of laser-stripe based range data
to identify and locate parts as they pass down a conveyor belt.
The vision research to be undertaken includes topics in: surface
patch extraction from range data, surface patch clustering,
geometric object modeling, model matching, geometric reasoning
and parallel image processing. The projects build on substantial
existing research.
One researcher will be expected to take a leading role in the
scientific direction of the projects (5 research staff total) as
well as undertake scientific research. The second researcher
will be more involved in software implementation and testing, but
will be expected to undertake some original research. The third
researcher will be mainly investigating parallel re-
implementations of existing serial vision algorithms on
transputer-based systems. Applicants for the first two posts
should have a PhD (or comparable experience) in an appropriate
area, such as computer vision, image processing, computer science
or mathematics. Applicants for the third post should have at
least a BSc in an appropriate area.
In general, applicants should have experience with the C program-
ming language. Applicants with experience in computer vision,
the UNIX operating system, the C++ language or parallel process-
ing on transputer systems will be preferred.
The details are:
Post Salary (Pounds) Scale Duration Start Date
==========================================================================
1 11399-20372 AR1a/AR2 1 year (probable 2nd year) Nov 1st
2 11399-14744 AR1b/AR1a 2 years Now
3 11399-14744 AR1b/AR1a 1 year (probable 2nd year) Nov 1st
Placement for all posts is according to age, experience and qual-
ifications.
Applications should include a curriculum vitae (3 copies) and the
names and addresses of two referees, and should be sent to the
Personnel Department, University of Edinburgh, 63 South Bridge,
Edinburgh, EH1 1LS by August 21, 1990, from whom further particu-
lars can be obtained. In your application letter, please quote
reference number 5796, and indicate for which of the posts you
are applying.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/10/90)
Vision-List Digest Thu Aug 09 14:11:54 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Suppliers of real time digital video display equipment ??
Gould image processor for trade
A bug in PBM software ( .pcx => pbm)
Research Associate post in Neural Networks and Image Classification
New book
CVPR-91 CALL FOR PAPERS
Vision Conference
Summary of Computer Controllable Lenses (long)
----------------------------------------------------------------------
Date: Tue, 7 Aug 90 09:17:24 +0200
From: jonh@tele.unit.no
Subject: Suppliers of real time digital video display equipment ??
Hi!
Does anybody know of any suppliers of equipment for
real time display of digitized video sequences? Here is some
background:
Our signal processing group has for some time been involved in
in research work in still image coding and to a lesser extent in coding
of image sequences. As we are planning to increase our activities
in the coding of image sequences, we are contemplating on acquiring equipment
for real time display digitized sequences, both monochrome and color.
All the coding algoriths will be runnning on a network of SUN SPARC stations.
We are planning to work on various image formats ranging from 352x288 pels
and up to HDTV resolution and at various frame rates.
Also, we would prefer equipment that is based on RAM rather
than real-time disks.
Any advice would be greately appreciated!
John Haakon Husoy
The Norwegian Institute of Technology
Department of Electical and Computer Engineering
7034 Trondheim - NTH
NORWAY
email: jonh@tele.unit.no
tel: ++ 47 + 7 + 594453
fax: ++ 47 + 7 + 944475
------------------------------
Date: 8 Aug 90 16:40:35 GMT
From: hughes@azroth.csee.usf.edu (Ken Hughes)
Subject: Gould image processor for trade
Organization: University of South Florida, College of Engineering
The department of Computer Science and Engineering here has a Gould IP8400
image processor that they are considering decomissioning and selling. It
was suggested to us that instead of selling this system we might consider
trading it with another organization for a mobile robot platform somewhere
along the lines of a Cybermation robot. If you or someone you know
might be interested in stch a trade, please contact me via e-mail.
Ken Hughes (hughes@sol.csee.usf.edu) | "If you were happy every day of
sysadm (root@sol.csee.usf.edu) | your life you wouldn't be human,
Dept of Comp Sci and Eng | you'd be a game show host."
University of South Florida | Winona Ryder, in "Heathers"
------------------------------
Date: Tue, 7 Aug 90 20:03:07 GMT
From: brian@ucselx.sdsu.edu (Brian Ho)
Subject: A bug in PBM software ( .pcx => pbm)
Organization: San Diego State University Computing Services
I have found a bug (may not appear in other system) in the PBM software.
The bug is in the program which converts a .PCX (paint brush image format)
to a Pbm portable bitmap.
The bug (very small) appear at line 102 in program "pcxtopbm.c" which is
under /pbmplus/pbm/. The orignal code read :
if (b & 0xC0 == 0xC0)
..
..
However, some system (e.g. Sun 3/50) does not like this. It miss interpret it
as
if (b & (OxCO == 0xC0)
..
..
Therefore, I have simply put a parentesis around the '&' clause
if ((b & OxC0) == 0xC0)
..
..
and it works Great!!!!!!!
I don't if it (the bug) appears in other system.. keep me posted...
my E-mail address is
brian@yucatec.sdsu.edu
eden@cs.sdsu.edu
------------------------------
Date: 6 Aug 1990 12:35:37 GMT
From: austin@minster.york.ac.uk
Subject: Research Associate post in Neural Networks and Image Classification
University of York
Departments of Computer Science, Electronics and Psychology
Research Associate post in
Neural Networks and Image Classification
Applications are invited for a three year research associ-
ateship within the departments of Computer Science, Elec-
tronics and Psychology on a SERC image interpretation
research initiative. Applicants should preferably have pro-
gramming and research experience of image interpretation,
neural networks and psychology.
The project is aimed at the development of neural models of
classification tasks and involves characterizing the
processes involved in learning and applying classification
skills in clinical screening tasks. A major aim is to
develop models based on current advances in neural networks.
Salaries will be on the 1A scale ( 11,399 --- 13495).
Informal enquiries may be made to Dr. Jim Austin (0904
432734, email: austin@uk.ac.york.minster). Further particu-
lars may be obtained from The Registrar's Department,
University of York, Heslington, York, YO1 5DD, UK to whom
three copies of a curriculum vitae should be sent. The clos-
ing date for applications is 24 Aug 1990. Please quote
reference number J2.
August 6, 1990
------------------------------
Date: Tue, 7 Aug 90 09:47:36 PDT
From: shapiro@lillith.ee.washington.edu (Linda Shapiro)
Subject: new book
One more entry in the vision books category. A new vision book by
Robert Haralick and Linda Shapiro is being completed this summer. It
will be published by Addison-Wesley. The following is the table of
contents.
COMPUTER AND ROBOT VISION
Table of Contents
1. Computer Vision Overview
2. Binary Machine Vision: Thresholding and Segmentation
3. Binary Machine Vision: Region Analysis
4. Statistical Pattern Recognition
5. Mathematical Morphology
6. Neighborhood Operators
7. Conditioning and Labeling
8. The Facet Model
9. Texture
10. Image Segmentation
11. Arc Extraction and Segmentation
12. Illumination Models
13. Perspective Projection Geometry
14. Analytic Photogrammetry
15. Motion and Surface Structure
from Time Varying Image Sequences
16. Image Matching
17. The Consistent Labeling Problem
18. Object Models and Matching
19. Knowledge--Based Vision
20. Accuracy
21. Glossary of Computer Vision Terms
------------------------------
Date: Tue, 7 Aug 1990 10:43:32 PDT
From: Gerard Medioni <medioni%iris.usc.edu@usc.edu>
Subject: CVPR-91 CALL FOR PAPERS
CALL FOR PAPERS
IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION
Maui Marriott on Kaanapali Beach
Lahaina, Maui, HI 96761
June 3-6, 1991
GENERAL CHAIR:
Shahriar Negahdaripour, Department of Electrical Engineering
Department, University of Hawaii, Honolulu, HI 96822,
E-mail: shahriar@wiliki.eng.hawaii.edu
PROGRAM CO-CHAIRS:
Berthold K.P. Horn, MIT Artificial Intelligence Lab, 545 Technology
Square, Cambridge, MA 02139, E-mail: bkph@ai.mit.edu
Gerard Medioni, Institute for Robotics and Intelligent,
232 Powell Hall, University of Southern California, Los Angeles, CA 90089,
E-mail: medioni@iris.usc.edu
LOCAL ARRANGEMENTS CHAIR:
Tep Dobry, Department of Electrical Engineering, University of
Hawaii Manoa, Honolulu, HI 96822, E-mail tep@wiliki.eng.hawaii.edu
PROGRAM COMMITTEE
N. Ahuja A. Blake K. Ikeuchi J. Malik R. Szeliski
N. Ayache A. Bovik K. Kanatani J. Mundy D. Terzopoulos
D. Ballard E. Delp C. Koch R. Nevatia W. Thompson
H. Baker K. Ganapathy C. Liedtke H. Samet A. Yuille
B. Bhanu D. Huttenlocher J. Little B. Schunck S. Zucker
THE PROGRAM
The program consists of high quality contributed papers on all aspects
of computer vision and pattern recognition. Papers will be
refereed by the members of the program committee. Accepted papers will
be presented as long papers in a single track, short papers in two
parallel tracks, and poster papers.
PAPER SUBMISSION
Four copies of complete papers should be sent to Gerard Medioni at the address
given above by November 12, 1990. The paper should include two title
pages, but only one containing the names and addresses of the authors, to
permit an anonymous review process. Both title pages should contain the title
and a short (up to 200 words) abstract. Authors MUST restrict the
length of the papers to 30 pages, which includes everything, meaning the two
title pages, text (double-spaced), figures, tables, bibliography, etc.
Authors will be notified of acceptance by February 15, 1991. Final
camera-ready papers, typed on special forms, will be due no later than March
15, 1991.
FOR FURTHER INFORMATION
Please write to:
CVPR-91, The Computer Society of IEEE, 1730 Massachusetts Ave, N.W.,
Washington, DC 20036-1903.
------------------------------
Date: 9 Aug 90 16:17:29 GMT
From: colin@nrcaer.UUCP (Colin Archibald)
Subject: Vision Conference
Keywords: Call for Papers
Organization: NRCC-Aeroacoustics, Ottawa, Ontario
V i s i o n I n t e r f a c e ' 9 1
Calgary, Alberta, Canada
3-7 June 1991
CALL FOR PAPERS
Vision Interface '91 is the fifth Canadian Conference devoted to
computer vision, image processing, and pattern recognition. This is
an annual conference held in various Canadian cities and is sponsored
by the Canadian Image Processing and Pattern Recognition Society. The 1991
conference will be held in Calgary, Alberta, June 3-7 1991 in conjunction
with Graphics Interface '91.
IMPORTANT DATES:
Four copies of a Full Paper due: 31 Oct. 1990
Tutorial Proposals due: 15 Nov. 1990
Authors Notified: 1 Feb. 1991
Cover Submissions due: 1 Feb. 1991
Final Paper due: 29 Mar. 1991
TOPICS:
Contributions are solicited describing unpublished research results and
applications experience in vision, including but not restricted to the
following areas:
Image Understanding and Recognition Modeling of Human Perception
Speech Understanding and Recognition Specialized Architecture
Computer Vision VLSI Applications
Image Processing Realtime Techniques
Robotic Perception Industrial Applications
Pattern Analysis & Classification Biomedical Applications
Remote Sensing Intelligent Autonomous Systems
Multi-sensor Data Fusion Active Perception
Four copies of full papers should be submitted to the Program Co-chairmen
before Oct.31 1990. Include with the paper full names, addresses, phone
numbers, fax numbers and electronic mail addresses of all the authors. One
author should be designated "contact author"; all subsequent correspondence
regarding the paper will be directed to the contact author. The other
addresses are required for follow-up conference mailings, including the
preliminary program.
FOR GENERAL INFORMATION: SUBMIT PAPERS TO:
Wayne A. Davis Colin Archibald and Emil Petriu
General Chairman VI '91 Program Co-chairmen
Department of Computing Science Laboratory for Intelligent Systems
University of Alberta National Research Council
Edmonton, Alberta, Canada Ottawa, Ontario, Canada
T6G 2H1 K1A 0R6
Tel: 403-492-3976 Tel: 613-993-6580
------------------------------
Date: Tue, 7 Aug 90 14:17:40 BST
From: Alan McIvor <bprcsitu!alanm@relay.EU.net>
Subject: Summary of Computer Controllable Lenses
Hi,
I recently placed the following request:
> Subject: Computer Controllable Lenses
>
> Hi,
> We are currently looking for a lens for our vision system with
> computer controllable focus, focal length, and aperture. Do any of you
> know of a source of such lenses? We have found many motorized lenses
> but most have auto-apertures and no feedback of settings.
> I recall several years ago that a company called Vicon made such
> a lens but I don't have any details. Anybody know how to get hold of
> them?
>
> Thanks,
>
> Dr Alan M. McIvor
> BP International Ltd ukc!bprcsitu!alanm
> Research Centre Sunbury alanm%bprcsitu.uucp@uk.ac.ukc
> Chertsey Road bprcsitu!alanm@relay.EU.NET
> Sunbury-on-Thames uunet!ukc!bprcsitu!alanm
> Middlesex TW16 7LN Tel: +44 932 764252
> U.K. Fax: +44 932 762999
>
What follows is a summary of the responses that I received.
Many companies make motorized lenses but few make them with
feedback facilities for accurate control of the position. The feedback
is almost invariably provided by potentiometers.
Several compaines make lenses with potentiometer feedback of the
zoom and focus setting but not the aperture. This is either auto-iris or
open-loop. Examples are:
- Cosmicar (Chori America, Inc.)
F. Maliwat
Electronics Division
350 fifth Ave., Suite 3323
New York, N.Y. 10118
(800) 445-4233
(212) 563-3264
Vista Vision Systems
Levanroy House
Deanes Close
Steventon
Oxfordshire OX136SR
UK
tel: +44 235 834466
fax: +44 235 832540
Ernitec Mechatronic Lenses
[Henrik I. Christensen <hic@vision.auc.dk> and Kourosh Pahlavan
<kourosh@ttt1.bion.kth.se> are using these. ]
Ernitec A/S
Fjeldhammervej 17
DK 2610 Rodovre
Denmark
Tel +45 31 70 35 11
Fax +45 31 70 11 55
* Ernitec UK
39/41 Rowlands Road
Worthing
West Sussex BN11 3JJ
tel: 0903 30482
fax: 0903 213333
* Molynx Ltd
Albany Street
Newport
Gwent NP9 5XW
UK
Tel: +44 633 821000
Fax: +44 633 850893
* Vicon Industries, Inc.
525 Broad Hollow Rd.
Melville, NY 11747 USA
Phone: 800-645-9116
[ Chuck Steward <stewardc@turing.cs.rpi.edu> claims that the rotational
accuracy is only 1 degree ]
* Video-Tronic
Lahnstrasse 1
2350 Neumunster 6
Germany
Phone 0 43 21 8 79 0
Fax 0 43 21 8 79 97
Telex 2 99 516 vido d
The only lens that I could find that had potentiometer feedback of
all three axes is:
* TecSec TLZMNDP12575
Vista Vision Systems
Levanroy House
Deanes Close
Steventon
Oxfordshire OX136SR
UK
tel: +44 235 834466
fax: +44 235 832540
Other approaches to the construction of a computer controllable lens
that were suggested are:
* take a normal zoom lens, mount a collar around the
focus sleeve, the aperture sleeve and the zoom barrel separately, and
then turn each collar with a high precision stepper motor.
Chuck Steward <stewardc@turing.cs.rpi.edu> is currrently doing
this.
[ This has the benefit of allowing you to use 35mm camera lenses which
have better optical performance than CCTV lenses]
* from Don Gennery <GENNERY@jplrob.jpl.nasa.gov>
We also recently talked to Mechanical Technology Inc. of Latham, N. Y.,
about the possibility of them making some computer-controlled lenses for us.
* from Lynn Abbott <abbott@vtcpe4.dal.ee.vt.edu>
I assembled a camera system with 2 motorized lenses about 3 years ago
at the Univ. of Illinois, with N. Ahuja. At the time, several companies
sold motorized lenses, but we could not locate any company which
produced a controller for these lenses which would interface with a
host processor.
We located a small company which specialized in dc servo controllers.
This company, TS Products, was willing to customize a pair of motorized
Vicon lenses so that one of their controllers would drive the lens actuators.
This controller accepts commands from a host over an RS-232 line or
via the IEEE-488 bus. They were willing to work with us in specifying
the system, and we were happy with the results.
They were at
TS Products, Inc.
12455 Branford St.
Bldg-22
Arleta, CA 91331 USA
Phone: 818-896-6676
* Use a auto-everything 35mm lens and a lens adaptor.
I have heard that at the Harvard Robotics Lab they use Canon EOS
lenses which include all the motors, etc, and talk to the camera body
via a 4pin serial connection, the protocol for which they have decoded.
* from Shelly Glaser 011 972 3 545 0060 <GLAS@taunivm.earn>
vandalizing an amateur video cam-corder
* use a Sony B-mount teleconferencing lens via a mount adaptor. These
have a serial interface for remote control. Very good optics - broadcast
quality, but quite heavy units.
Canon UK Ltd.,
Canon House, Manor Road,
Wallington, Surrey SM6 OAJ, UK
(081) 773-3173
Fujinon Inc.,
3N, 125 Springvale,
West Chicago, IL 60185
(312) 231-7888
* from Reg Willson <Reg.Willson@ius1.cs.cmu.edu>
A second alternative is to have a motorized lens custom made. Computer
Optics is a small company that will build a motorized lens to your specs,
but we found them to be far too expensive. They quoted us $US 30,000 for
the lens we specified - at which point we decided to build our own.
Computer Optics Inc.,
G. Kane
120 Derry Road,
P.O. Box 7
Hudson, New Hampshire 03051
(603) 889-2116
Vista Vision Systems
Levanroy House
Deanes Close
Steventon
Oxfordshire OX136SR
UK
tel: +44 235 834466
fax: +44 235 832540
Given a controllable lens with DC servo motors and potentiometer
feedback, there is also the question of how to control it. Unfortunately
most available servo motor controllers assume feedback via resolvers or
optical encoders, so are unapplicable. Possible solutions are:
1) Replace the motors on the lens with servo motors with optical encoders
or stepper motors, and use an available controller
- from Reg Willson <Reg.Willson@ius1.cs.cmu.edu>
The current lens we have is a Cosmicar C31211 (C6Z1218M3-2) TV grade zoom
lens (apx $US 560). We replaced the DC servo motors and drive train with AX
series digital micro stepping motors from Compumotor. The stepping motors
have a simple RS232 interface and have far more accuracy and precision than
the DC servo motors they replaced. Unfortunately they're rather expensive
($US 1700 / degree of freedom). We also had to have a machinist build an
assembly for the lens and motors.
Compumotor Division, Parker Hannifin Corporation
5500 Business Park Drive
Rohnert Park, CA 94928
(800) 358-9070
(707) 584-7558
- Galil motor controllers for DC Servo motors
Galil Motion Control, Inc.
1054 Elwell Court
Palo Alto, CA 94303
tel: (415) 964-6494
fax: (415) 964-0426
Naples Controls Ltd
White Oriels
Chaddleworth
Berkshire RG16 0EH
UK
tel: 04882 488
fax: 04882 8802
- Digiplan motor controllers for Stepper motors
- Themis 4-axis motor controller for servos
- MDS-330 Servo Interface Card
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
- PeP VMIC intelligent motion controller
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
2) Use a dedicated PID controller for the control loop and a Digital to
Analog convertor in the computer to provide the setpoint (i.e., desired
zoom, focus, aperture) - one per axes.
Example PID controllers are:
RS Servo Control Module
Stock Number 591-663
RS Components, UK.
PVP 142 Linear Servo Amplifier
Naples Controls Ltd
White Oriels
Chaddleworth
Berkshire RG16 0EH
UK
tel: 04882 488
fax: 04882 8802
Example DACs are:
PeP VDAD
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
MDS-330 Servo Interface Card
UKP 1195
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
MDS-620 Analogue Output card
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
BVME240 Analogue Output Module
BVM Limited
Flanders Road
Hedge End, Southampton
SO3 3LG
tel 0703 270770
fax 0489 783589
ACROMAG AVME9210/15
Universal Engineering and Computing Systems
5/11 Tower St
Newtown
Birmingham B19 3UY
tel: 021-359 1749
fax: 021-333 3137
Motorola MVME605
Thame Microsystems
Thame Park Road, Thame
Oxford OX9 3UQ
Tel: 0844 261456
Fax: 0844 261682
Burr-Brown MVP904
Thame Microsystems
Thame Park Road, Thame
Oxford OX9 3UQ
Tel: 0844 261456
Fax: 0844 261682
3) Use an ADC to read the feedback potentiometer and a DAC to provide the
motor drive voltage (via a power amp):
Example ADCs are:
PeP VADI
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
MDS-310
AMC Ltd
Unit 2, Deseronto Industrial Estate
St Mary's Road, Langley, Berks SL3 7EW
tel: (0753) 580660 Fax: (0753)580653
BVME250 Analogue Input Module
BVM Limited
Flanders Road
Hedge End, Southampton
SO3 3LG
tel 0703 270770
fax 0489 783589
ACROMAG AVME9320
Universal Engineering and Computing Systems
5/11 Tower St
Newtown
Birmingham B19 3UY
tel: 021-359 1749
fax: 021-333 3137
Burr-Brown MVP901
Thame Microsystems
Thame Park Road, Thame
Oxford OX9 3UQ
Tel: 0844 261456
Fax: 0844 261682
Example combined systems are (with onboard CPUs):
Burr Brown MPV940 controller + ACX945 Analog I/O module
Thame Microsystems
Thame Park Road, Thame
Oxford OX9 3UQ
Tel: 0844 261456
Fax: 0844 261682
Scan Beam A/S SB100
Scan Beam A/S
Rosendalsvej 17
DK-9560 Hadsard
Tel: +45 98 57 15 99
Fax: +45 98 57 48 87
[this has the advantage of onboard power amps. It is being used by
Henrik I. Christensen <hic@vision.auc.dk> who warns that the
company is unstable.]
BVME347 + IP-DAC + IP-ADC
BVM Limited
Flanders Road
Hedge End, Southampton
SO3 3LG
tel 0703 270770
fax 0489 783589
Dr Alan M. McIvor
BP International Ltd ukc!bprcsitu!alanm
Research Centre Sunbury alanm%bprcsitu.uucp@uk.ac.ukc
Chertsey Road bprcsitu!alanm@relay.eu.net
Sunbury-on-Thames uunet!ukc!bprcsitu!alanm
Middlesex TW16 7LN Tel: +44 932 764252
U.K. Fax: +44 932 762999
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/14/90)
Vision-List Digest Mon Aug 13 12:56:33 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Small camera lens
KBVision
Rotated Email Address
Non-interlaced rs-170 monitor?
Info Wanted: Vision Chip/Hardware Manufacturers
----------------------------------------------------------------------
Date: Fri, 10 Aug 90 9:27:10 MET DST
From: bellutta@irst.it (Paolo Bellutta)
Subject: small camera lens
Where I could find a source for small lenses for a CCD camera? The lenses
should be small enough to be glued directly on the CCD chip. I was thinking
to the lenses mounted on the disposable cameras or the more expensive
compact size cameras. The quality of the lens itself is not a major concern.
An non auto-iris wide angle lens would be better but I'm open to suggestions.
Please e-mail, in case I will receive a lot of "me too" responses I'll
summarize to the list.
Paolo Bellutta
I.R.S.T. vox: +39 461 814417
loc. Pante' di Povo fax: +39 461 810851
38050 POVO (TN) e-mail: bellutta@irst.uucp
ITALY bellutta%irst@uunet.uu.net
------------------------------
Date: 10 Aug 90 20:20:19 GMT
From: cc@sam.cs.cmu.edu (Chiun-Hong Chien)
Subject: KBVision
Organization: Carnegie-Mellon University, CS/RI
I am in a process of evaluating the feasibility of using KBVision for vision
research. I would appreciate any comments on and experiences with KBVision.
I am particularly interested in knowing the following.
1) How powerful/flexible/popular is the constraint module? It seems to me
while quite a few people are actually impressed by Excutive Interface
(for image dispaly) and Image Examiner, very few people have much
experience on the constraint module? What are the reasons?
2) How is the knowledge module compared with other intelligent system tools
such as KEE.
3) Can KBVision be used in a real time environemnt? embedded into a
robotics system? If not how much overhead involved in the conversion
between programs for KBVision and regular C programs?
4) Others.
Thanks in advance, Chien
------------------------------
Date: 10 Aug 90 14:41:11 GMT
From: uh311ae@sun7.lrz-muenchen.de (Henrik Klagges)
Subject: Rotated Email Address
Keywords: Thanks & Address Change
Organization: LRZ, Bavarian Academy of Sciences, W. Germany
Hello,
thanks a lot for the replies to my article concerning pattern
recognition of rotated molecules scattered over a surface ("Rotated
molecules & rotating physics student"). I think the "best" solution is
using a genetic optimizer that gets a parameter vector (angle &
displacement) as input and scans for a given pattern. If anyone likes
the C++ (cfront 2.0) code for a genetic algo- rithm (with bugs 8-)),
please email me. To circumvent infinite mail problems there is a new
BITNET address that worked, at least a message from
koza@Sunburn.Stanford.EDU came through.
Best regards,
Henrik Klagges
Scanning Tunnel Microscope Group at University of Munich
and LRZ, Bavarian Academy of Sciences
Stettener Str. 50, 8210 Prien
Try : uh311ae@DM0LRZ01.BITNET (works !)
uh311ae@sun7.lrz-muenchen.de (?)
------------------------------
Date: Fri, 10 Aug 90 18:42 PDT
From: H. Keith Nishihara <hkn@natasha>
Subject: non-interlaced rs-170 monitor?
Phone: (415)328-8886
Us-Mail: Teleos Research, 576 Middlefield Road, Palo Alto, CA 94301
I'm looking for a video monitor to use with cameras capable of
producing RS-170 like video but non-interlaced (Panasonic
GP-MF-702's). We need this mode to support a pipelined Laplacian of
Gaussian convolver we are building.
Any suggestions for a good (but not too expensive monitor)? Someone
suggested one of the newer multisync monitors made for PC's and the
like, anyone know if that works?
thanks -- Keith hkn@teleos.com
------------------------------
Date: Mon, 13 Aug 90 16:45:03 BST
From: S.Z.Li@ee.surrey.ac.uk
Subject: Info Wanted: Vision Chip/Hardware Manufacturers
Organization: University of Surrey, Guildford, Surrey, UK. GU2 5XH
Hi, netters:
I am interested in contacting chip/hardware manufacturers for vision
and neural nets. Do you know who/where they are? If you do, could
you e-mail me the information? My address is: S.Z.Li@ee.surrey.ac.uk.
Many thanks in advance.
Stan
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/19/90)
Vision-List Digest Sat Aug 18 14:15:59 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Re: DataCube Users Group
Hand-Eye Calibration for Laser Range Sensors
Suppliers of real-time digital video equipment
Post-Doc Postion in Medical Imaging, CAS at the Stanford Robotics Lab
SIEMENS Job Announcement
Proceedings for the AAAI-90 Workshop on Qualitative Vision
NEW JOURNAL -SYSTEMS ENGINEERING- SPRINGER VERLAG
----------------------------------------------------------------------
Date: 14 Aug 90 01:01:15 GMT
From: razzell@cs.ubc.ca (Dan Razzell)
Subject: Re: DataCube Users Group ???
Organization: University of British Columbia, Vancouver, B.C., Canada
There is a mailing list called
<datacube-list@media-lab.media.mit.edu>.
To get on the list, send a message to
<datacube-list-request@media-lab.media.mit.edu>.
.^.^. Dan Razzell <razzell@cs.ubc.ca>
. o o . Laboratory for Computational Vision
. >v< . University of British Columbia
____mm.mm____
------------------------------
Date: Tue, 14 Aug 90 15:47:19 EDT
From: Jean Lessard <sade%ireq-robot.UUCP@Larry.McRCIM.McGill.EDU>
Subject: Hand-Eye Calibration for Laser Range Sensors
We are in the process of completing the installation of two
different laser range finders (one axis type) in our robotics lab. The
first one, having a working distance of 15 cm to 100 cm, with a field
of view of approx. 45 deg. and weighing 1.2 Kg, is intended to be
mounted on a PUMA-760 robot for telerobotics research applied to live
line maintenance and repair. The other one, more compact and with a
much smaller work distance, will be mounted on a custom designed 6 dof
robot which itself is mounted on a rail for turbine blade repair.
I am looking for information and/or references on:
1) Sensor positioning and mounting on the robot. I expect
difficulties with the sensor and wires causing limited robot
movements, etc.
2) Hand-Eye calibration algorithms for this type of sensor. Are
there any techniques developed to accurately link the sensor
reference frame to the robot reference frame? Any good practical
algorithms would be welcome.
Jean Lessard jlessard@ireq-robot.hydro.qc.ca
Institut de recherche d'Hydro-Quebec jlessard@ireq-robot.uucp
Varennes, QC, Canada J3X 1S1
PHONE: +1 514 652-8136 FAX: +1 514 652-8435
------------------------------
Date: Wed, 15 Aug 90 09:35:53 BST
From: Adrian F Clark <alien%sx.ac.uk@pucc.PRINCETON.EDU>
Subject: Suppliers of real-time digital video equipment
Someone was recently asking about equipment for digitising image
sequences in real time. Here at Essex we do a lot of work on coding
moving sequences, packet video and the like, and we have recently
looked at similar equipment. Our choice came down to two:
1. the Abekas A60 (which we eventually chose and with which we're very
satisfied). This is based on two parallel transfer discs and holds 30
seconds worth of digital video as luminance/chrominance (the latter
sampled at half the rate, as you'd expect). There's also a four-disc
system which holds 60 seconds. The A60 expects to input
CCIR601-format video, but Abekas sell the A20, which converts RGB to
CCIR601 in real time. Just plug them together and you're away. The
A60 outputs CCIR601, RGB or lum/chrom. In terms of display, the
system is limited to the size of a standard TV frame (575x768), though
you can load and read smaller frames if you want. The A60 is hosted
off Ethernet and supports rcp, rsh, etc, which makes it easy to
transfer image data to/from it. The main disadvantage is that it's
very noisy -- keep it in a soundproofed room or invest in some ear
plugs at the same time. In the UK, Abekas is at Portman House, 12
Portman Road, Reading, Berks, RG3 1EA. Tel: +44 734-585421. Fax: +44
734-597267. They don't do educational discounts (boo, hiss).
2. DVS of Hannover (Abekas is US/UK, incidentally) sell a RAM-based
system which is more flexible (in terms of image sizes) than the A60.
However, when I looked at them, they couldn't hold anything like as
much as the A60 and were somewhat more expensive. I don't have any
info to hand, not even an address, but I believe their systems came in
VME cages, so you stand a chance of interfacing one to a SparcStation.
Dunno about drivers, though. If interested parties want to contact
DVS, mail me and I'll have a look for their address.
Adrian F. Clark JANET: alien@uk.ac.essex
INTERNET: alien%uk.ac.essex@nsfnet-relay.ac.uk FAX: (+44) 206-872900
BITNET: alien%uk.ac.essex@ac.uk PHONE: (+44) 206-872432 (direct)
Dept ESE, University of Essex, Wivenhoe Park, Colchester, Essex, C04 3SQ, UK.
------------------------------
Date: 15 Aug 90 17:52:02 GMT
From: sumane@zsazsa.stanford.edu (Thilaka Sumanaweera)
Subject: Post-Doc Postion in Medical Imaging, CAS at the Stanford Robotics Lab
Post Doctoral Research Position
Stanford Computer Aided Surgery Group
(Starting Fall, 1990)
Summery:
The Stanford Computer Aided Surgery group, whose original
goal was to provide intelligent software tools for Stereotaxis
Surgery, is now moving onto new areas such as: Frameless
Stereotaxis Surgery, Geometric and Biomechanic Modelling of the
Spine, Stereotaxic Guided Clipping of AVM Feeders, Feature Space
Merging of MR and CT data and Robotic Manipulator Assisted
Stereotaxic Surgery. The systems developed at this group are now
being used at the Stanford Hospital during brain tumor retraction.
In this group, we are concentrating on applying the techniques
available in Computer Vision, Signal Processing and Robotics
into medicine, especially surgery.
The new Post-Doc has the following duties:
1). To carry out independant research in related areas and
assist graduate students and surgeons in problem-solving.
2). Provide professional-quality systems administration support
in maintaining the computer system which is being used at
the operating room during surgery.
3). To facilitate building a set of state of the art surgical
tools system which will be standard in the future.
Requirements:
1). PhD in Computer Science, Electrical ENgineering,
Mechanical Engineering or a related field.
2). Expertice in system building in Unix environment
in C, X-windows, LISP.
3). Start working in the Fall, 1990.
4). Some knowledge in medicine is a plus but not necessary.
Our computer facilities include:
1). Silicon Graphics Personal IRIS 4D/25 machines.
2). SONY NEWS Networkstations.
3). Symbolics LISP machines.
4). DEC 3100 Workstations.
5). A fully equipped Computer Vision Lab.
6). Accessibility to General Electric MR and CT scanners.
Please send your resume' to:
Hiring Committee
C/O Prof. Thomas O. Binford
Post Doctoral Research Position in CAS
Robotics Laboratory
Computer Science Department
Stanford University
Stanford, CA 94305
Internet: binford@cs.stanford.edu
Fax: (415)725-1449
------------------------------
Date: Tue, 14 Aug 90 11:24:31 PDT
From: kuepper@ICSI.Berkeley.EDU (Wolfgang Kuepper)
Subject: SIEMENS Job Announcement
IMAGE UNDERSTANDING and ARTIFICIAL NEURAL NETWORKS
The Corporate Research and Development Laboratories of Siemens AG,
one of the largest companies worldwide in the electrical and elec-
tronics industry, have research openings in the Computer Vision
as well as in the Neural Network Groups. The groups do basic and
applied studies in the areas of image understanding (document inter-
pretation, object recognition, 3D modeling, application of neural
networks) and artificial neural networks (models, implementations,
selected applications). The Laboratory is located in Munich, an
attractive city in the south of the Federal Republic of Germany.
Connections exists with our sister laboratory, Siemens Corporate
Research in Princeton, as well as with various research institutes
and universities in Germany and in the U.S. including MIT, CMU and
ICSI.
Above and beyond the Laboratory facilities, the groups have a
network of Sun and DEC workstations, Symbolics Lisp machines,
file and compute servers, and dedicated image processing hardware.
The successful candidate should have an M.S. or Ph.D. in Computer
Science, Electrical Engineering, or any other AI-related or
Cognitive Science field. He or she should prefarably be able to
communicate in German and English.
Siemens is an equal opportunity employer.
Please send your resume and a reference list to
Peter Moeckel
Siemens AG
ZFE IS INF 1
Otto-Hahn-Ring 6
D-8000 Muenchen 83
West Germany
e-mail: gm%bsun4@ztivax.siemens.com
Tel. +49-89-636-3372
FAX +49-89-636-2393
Inquiries may also be directed to
Wolfgang Kuepper (on leave from Siemens until 8/91)
International Computer Science Institute
1947 Center Street - Suite 600
Berkeley, CA 94704
e-mail: kuepper@icsi.berkeley.edu
Tel. (415) 643-9153
FAX (415) 643-7684
------------------------------
Date: Mon, 13 Aug 90 18:43:05 -0700
From: pkahn@deimos (Philip Kahn)
Subject: Proceedings for the AAAI-90 Workshop on Qualitative Vision
Copies of the proceedings from the AAAI-90 Workshop on Qualitative
Vision are available for $35 (in North America) and $45US
(international), and can be obtained by writing:
AAAI-90 Workshop on Qualitative Vision
Advanced Decision Systems
Mountain View, CA 94043-1230
When requesting a copy of the Proceedings, please make your check
(payable in US $) to Advanced Decision Systems (this includes postage
and handling), specify the complete mailing address to which the
proceedings should be mailed, and (if available) include your e-mail
address in case there are any questions or problems.
AAAI-90 WORKSHOP ON QUALITATIVE VISION
July 29, 1990
Boston, MA
Qualitative descriptions of the visual environment are receiving
greater interest in the computer vision community. This recent
increase in interest is partly due to the difficulties that often
arise in the practical application of more quantitative methods.
These quantitative approaches tend to be computationally expensive,
complex and brittle. They require constraints which limit generality.
Moreover inaccuracies in the input data do not often justify such
precise methods. Alternatively, physical constraints imposed by
application domains such as mobile robotics and real-time visual
perception have prompted the exploration of qualitative mechanisms
which require less computation, have better response time, focus on
salient and relevant aspects of the environment, and use enviromental
constraints more effectively.
The one-day AAAI-90 Workshop on Qualitative Vision seeks to bring
together researchers from different disciplines for the active
discussion of the technical issues and problems related to the
development of qualitative vision techniques to support robust
intelligent systems. The Workshop examines aspects of the
methodology, the description of qualitative vision techniques, the
application of qualitative techniques to visual domains and the role
of qualitative vision in the building of robust intelligent systems.
------------------------------
Date: Tue, 14 Aug 90 07:41:38 bst
From: eba@computing-maths.cardiff.ac.uk
Subject: NEW JOURNAL -SYSTEMS ENGINEERING- SPRINGER VERLAG
Organization: Univ. of Wales Coll. of Cardiff, Dept. of Electronic & Systems Engineering
**** NEW JOURNAL *** NEW JOURNAL *** NEW JOURNAL *** NEW JOURNAL ****
-----------------------------------------
[ JOURNAL OF SYSTEMS ENGINEERING ]
[ SPRINGER - VERLAG - INTERNATIONAL ]
-----------------------------------------
AIMS AND SCOPE
The Journal of Systems Engineering will be a
refereed academic journal which publishes both fundamental
and applied work in the field of systems engineering.
Its aim will be to provide an active forum for
disseminating the results of research and advanced
industrial practice in systems engineering, thereby
stimulating the development and consolidation of this field.
The scope of the journal will encompass all subjects
pertinent to systems engineering: systems analysis,
modelling, simulation, optimisation, synthesis, operation,
monitoring, identification, evaluation, diagnosis, control
etc. The journal will encourage the reporting of new
theories, tools, algorithms, and techniques to support these
activities . It will also cover critical discussions of
novel applications of systems principles and methods and
of original implementations of different engineering systems,
including intelligent systems. 'Hard' and 'soft' systems from
all branches of engineering will be of interest to the
journal. Papers on any systems aspects, from accuracy,
stability, noise inmunity, complexity, to efficiency,
quality and reliability, will be considered.
ADDRESS
Please submit contributions to:
The Editor: Prof. D.T. Pham,
Journal of Systems Engineering,
University of Wales,
School of Electrical, Electronic and
Systems Engineering.
P.O. Box 904, Cardiff CF1 3YH,
United Kingdom
Tel. 0222- 874429
Telex 497368
Fax 0222- 874192
email PhamDT@uk.ac.cardiff
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/23/90)
Vision-List Digest Wed Aug 22 21:02:05 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: Range sensors Call for papers: Vision Interface '91 ---------------------------------------------------------------------- Date: Wed, 22 Aug 90 17:30:32 -0500 From: dmc@piccolo.ecn.purdue.edu (David M Chelberg) Subject: Range sensors I am considering acquiring a range sensor for our lab here at Purdue. I am interested in any technical contacts at companies producing such devices. The requirements (which are somewhat flexible at this stage) are: 1.) At least 128x128 resolution (preferably 512x512) 2.) 1m working distance, with at least .5 meter range, and 1-5mm depth resolution (preferable < 1mm). Preferably scalable. i.e. if we are working at .25 meter, the accuracy should increase proportionately. 3.) 5 frames per second (preferable > 10 fps). Data rate should apply to recovery of a calibrated dense scan. I would especially appreciate technical contacts at companies, as sales contacts do not normally have the background to competently discuss the technical merits of the products. I would appreciate a quick response, as at least a preliminary choice to be included in a proposal needs to be made soon. Thanks in advance, -- Prof. David Chelberg (dmc@piccolo.ecn.purdue.edu) ------------------------------ Date: 22 Aug 90 18:00:18 GMT From: colin@nrcaer.UUCP (Colin Archibald) Subject: call for papers Keywords: vision , image processing, robotics Organization: NRCC-Aeroacoustics, Ottawa, Ontario V i s i o n I n t e r f a c e ' 9 1 Calgary, Alberta, Canada 3-7 June 1991 CALL FOR PAPERS Vision Interface '91 is the fifth Canadian Conference devoted to computer vision, image processing, and pattern recognition. This is an annual conference held in various Canadian cities and is sponsored by the Canadian Image Processing and Pattern Recognition Society. The 1991 conference will be held in Calgary, Alberta, June 3-7 1991 in conjunction with Graphics Interface '91. IMPORTANT DATES: Four copies of a Full Paper due: 31 Oct. 1990 Tutorial Proposals due: 15 Nov. 1990 Authors Notified: 1 Feb. 1991 Cover Submissions due: 1 Feb. 1991 Final Paper due: 29 Mar. 1991 TOPICS: Contributions are solicited describing unpublished research results and applications experience in vision, including but not restricted to the following areas: Image Understanding and Recognition Modeling of Human Perception Speech Understanding and Recognition Specialized Architecture Computer Vision VLSI Applications Image Processing Realtime Techniques Robotic Perception Industrial Applications Pattern Analysis & Classification Biomedical Applications Remote Sensing Intelligent Autonomous Systems Multi-sensor Data Fusion Active Perception Four copies of full papers should be submitted to the Program Co-chairmen before Oct.31 1990. Include with the paper full names, addresses, phone numbers, fax numbers and electronic mail addresses of all the authors. One author should be designated "contact author"; all subsequent correspondence regarding the paper will be directed to the contact author. The other addresses are required for follow-up conference mailings, including the preliminary program. FOR GENERAL INFORMATION: SUBMIT PAPERS TO: Wayne A. Davis Colin Archibald and Emil Petriu General Chairman VI '91 Program Co-chairmen Department of Computing Science Laboratory for Intelligent Systems University of Alberta National Research Council Edmonton, Alberta, Canada Ottawa, Ontario, Canada T6G 2H1 K1A 0R6 Tel: 403-492-3976 Tel: 613-993-6580 ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (08/30/90)
Vision-List Digest Wed Aug 29 13:05:54 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
MRF and simulated annealing for image restoration
Vision equipment references
Survey of vision systems for automated inspection
Help : Separate bitmap characters
Position available in Human Visual Perception
----------------------------------------------------------------------
Date: Thu, 23 Aug 90 16:23:01 BST
From: Guanghua Zhang <guanghua@cs.heriot-watt.ac.uk>
Subject: MRF and simulated annealing for image restoration
Dear readers,
Anybody on in the group familar with using MRF and Simulated Annealing
for the image restoration?
It was orginally proposed in Gemans' paper and the success and robustness
of the technique was desmontrated. A series of subsequent work were reported.
Extension were made from the constant depth to piecewise smooth surfaces
[Marroquin 1984]. But nearly all I have read just modied the original
version for different applications.
It is diffcult to understand how the enery is assigned to each of the
clique configurations. It is related to the observations and the estimats
-- the Gaussian model, but how ?
Although most of the authors claim that the parameters are chosen on a
trial-and-error bases, it can be seen some of the common points in the
parameters.
I would like to hear comments on the technique and experiences in using it.
guanghua zhang
Computer Science
Heriot-Watt University
Edinburgh, Scotland
------------------------------
Date: Wed, 29 Aug 90 13:06:57 bst
From: Eduardo Bayro <eba@computing-maths.cardiff.ac.uk>
Subject: Vision equipment references
Organization: Univ. of Wales Coll. of Cardiff, Dept. of Electronic & Systems
Engineering
Dear friends !!
Does anybody knows about the Pi030 image processing system
from the company: Performance Imaging (2281 Dunstan Street,
Oceanside , CA 92054, USA). Because its convenient price
we are thinking to buy it. This will be used by research
fellows involved with industrial real-time applications of
computer vision . Answers by e-mail are appreciate.
Eduardo//
Eduardo Bayro, School of Electrical, Electronic and Systems Engineering,
University of Wales College of Cardiff, Cardiff, Wales, UK.
Internet: eba%cm.cf.ac.uk@nsfnet-relay.ac.uk Janet: eba@uk.ac.cf.cm
UUCP: eba@cf-cm.UUCP or ...!mcsun!ukc!cf-cm!eba
------------------------------
Date: Tue, 28 Aug 90 15:07:54 BST
From: Netherwood P J <cs_s424@ux.kingston.ac.uk>
Subject: Survey of vision systems for automated inspection
I am currently doing a survey of vision systems to perform automated
visual inspection of surface mount solder joints. Anybody know of
any systems? (comercial or academic) If so send replys to me.
Thanks in advance
Paul Netherwood janet : P.J.Netherwood@uk.ac.kingston
Research internet : P.J.Netherwood@kingston.ac.uk
phone : (+44) 81 549 1366 ext 2923
local : cs_s424@ux.king
School of Computer Science and Electronic Systems,
|/ingston |>olytechnic, Penrhyn Road, Kingston-upon-Thames, Surrey KT1 2EE, UK.
|\--------|--------------------------------------------------------------------
\
------------------------------
Date: Mon, 27 Aug 90 17:26:55 GMT
From: brian@ucselx.sdsu.edu (Brian Ho)
Subject: Help : Separate bitmap characters
Organization: San Diego State University Computing Services
Hello out there,
I have some interesting problem that you may find interested and may be
you can give me a hand/hint.
I am currently working on a OCR (optical Character Recogniation) project.
I am now in the stage that I need to scan a page of document, and sperate
each character appears in the document. The image of the document from the
scanner will converted into (binary) bitmap format. e.g
0001111111100000000000000111000000000000000000000000000000000000000000
0001110000000000000000000111000000000110000001101110000000000000000000
0001100000000111111100001111111000011111100001111110000000000000000000
0001100000000111101110001111000000110000110001110000000000000000000111
0001111110000111000110000111000001111111110001100000000000000000011110
0001100000000111000110000110000001111111110001100000000000000000001111
0001100000000111000110000111000001110000000001100000000000000000000011
0001100000000111000110000111000000111001110001100000000000000000000000
0001111111100111000110000011111000011111100001100000000000000000000000
0001111111100010000000000000000000000000000000000000000000000000000000
And I have a function that can sperate each character from the document.
My function work fine when two characters are sperated by one or more
(blank) column, as the example shown in above.
My problem is when two characters are sperated less than one blank column,
I can not distinguish/sperate the two character. (P.S. the character has
unknown size) e.g.
000111111110000000000001110000000000000000000000000000000000000000
000111000000000000000001110000000110000001101110000000000000000000
000110000001111111000011111110011111100001111110000000000000000000
000110000001111011100011110000110000110001110000000000000000000111
000111111001110001100001110001111111110001100000000000000000011110
000110000001110001100001100001111111110001100000000000000000001111
000110000001110001100001110001110000000001100000000000000000000011
000110000001110001100001110000111001110001100000000000000000000000
000111111111110001100000111110011111100001100000000000000000000000
000111111110100000000000000000000000000000000000000000000000000000
The characters "En" and "te" are eventually appears side by side with the other
character.
I am wondering if anybody out there that can give me some advices, how to solve
this problem. Or even someone who is facing the same type of problem, I'll like
to hear about it.. Thank you .. Thank you.....
Thank you for advance..
Brian
Contact me at :
brian@yucatec.sdsu.edu
brian@ucselx.sdsu.edu
------------------------------
Date: Tue, 28 Aug 90 14:12:23 EDT
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: CVNet- Position Available.
Position available in Human Visual Perception
in the Department of Experimental Psychology,
University of Oxford.
A pre- or post-doctoral research position will be available from 1st October (or
as soon as possible thereafter) for one year in the first instance (with the
possibility of renewal). The project is funded by the Science and Engineering
Research Council of U.K. and the European Community Esprit programme.
The project is concerned with the perception and representation of 3-D surfaces
from disparity and optic flow information. Applicants should have a background
in human psychophysics or computational vision and have an interest/experience
of research in 3-D or motion perception.
For further information, please contact:
Dr Brian Rogers,
Department of Experimental Psychology,
South Parks Road,
Oxford, OX1 3UD,
U.K.
Email: BJR@vax.oxford.ac.uk
(I shall be at the E.C.V.P meeting in Paris, 5th-7th September)
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/15/90)
Vision-List Digest Sat Sep 15 08:50:58 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: grouping Locating edges in a field of view Industrial Vision Metrology Conference VISION and NN; special issue of IJPRAI available document MAC AI demos ---------------------------------------------------------------------- Date: 11 Sep 90 14:57:28+0200 From: Tilo Messer <messer@suncog1.informatik.tu-muenchen.dbp.de> Subject: grouping I am interested in grouping regions (not edges!) for increasing the performance of an object identification system. It is part of a planned real-time interpretation system of scenes taken from a moving camera. I found a few articles and papers about grouping of egdes (Lowe et. al.), but these don't fit. Is anybody else interested in this topic or does anybody know some theoretical and practical work in this area? I would be glad about some useful hints. Thanks, Tilo | |\ /| voice: ++ 49 89 48095 - 224 | | \/ | FORWISS, FG Cognitive Systems fax: ++ 49 89 48095 - 203 | | | Orleansstr. 34, D - 8000 Muenchen 80, Germany ------------------------------ Date: Wed, 12 Sep 90 11:05:03 EDT From: ICR - Mutual Group <rjspitzi@watserv1.waterloo.edu> Subject: Locating edges in a field of view Here is an interesting real-world problem for you comp.ai.vision'aries out there: I have built a scanning unit which basically produces a picture in memory of a 2-D object (such as a peice of paper) passing under the scanning unit. The image is made only of a series of points outlining the object itself. The object passing under the scanner is roughly rectangular (i.e. four edges) but the edges can be somewhat bowed to make slightly concave or convex edges. There should be definate corners however. The problem is this. Given the limited information that I receive from the image, I must locate the edges of the object and calculate each side's length. The result should be a *very* accurate estimate of the height and width of the object and hence the area it covers. Oh ya, one other twist, the object can come through in any orientation. There is no guarantee a corner will always be first. Any ideas you have for algorithms, or documents you could point me toward would be greatedly appreciated! Like I said, an interesting problem. ------------------------------ Date: Tue, 11 Sep 90 11:05:00 EDT From: ELHAKIM@NRCCIT.NRC.CA Subject: Industrial Vision Metrology Conference ANNOUNCEMENT AND CALL FOR PAPERS INTERNATIONAL CONFERENCE ON INDUSTRIAL VISION METROLOGY Location: The Canadian Institute for Industrial Technology Winnipeg, Manitoba, Canada Date: July 11-13, 1991 Organized by: -International Society for Photogrammetry & Remote Sensing Commission V: Close-Range Photogrammetry and Machine Vision WG V/1: Digital and Real-time Close-range Photogrammetry Systems -National Research Council of Canada Proceeding published by: SPIE- The International Society for Optical Engineering Focusing on: Industrial applications of metric vision techniques Topics include: -Vision metrology techniques -Real-time systems -3-D object reconstruction -Decision algorithms -System calibration -Shop-floor metrology problems -Applications such as dimensional inspection 500-1000 words abstracts are to be submitted before January 1, 1991 to: Dr. S. El-Hakim National Research Council 435 Ellice Avenue Winnipeg, Manitoba, Canada R3B 1Y6 tel:(204) 983-5056 / Fax:(204) 983-3154 ------------------------------ Date: Thu, 13 Sep 90 15:29:49 PDT From: skrzypek@CS.UCLA.EDU (Dr. Josef Skrzypek) Subject: VISION and NN; special issue of IJPRAI Because of repeat enquiries about the special issue of IJPRAI (Intl. J. of Pattern Recognition and AI) I am posting the announcement again. IJPRAI CALL FOR PAPERS IJPRAI We are organizing a special issue of IJPRAI (Intl. Journal of Pattern Recognition and Artificial Intelligence) dedicated to the subject of neural networks in vision and pattern recognition. Papers will be refereed. The plan calls for the issue to be published in the fall of 1991. I would like to invite your participation. DEADLINE FOR SUBMISSION: 10th of December, 1990 VOLUME TITLE: Neural Networks in Vision and Pattern Recognition VOLUME GUEST EDITORS: Prof. Josef Skrzypek and Prof. Walter Karplus Department of Computer Science, 3532 BH UCLA Los Angeles CA 90024-1596 Email: skrzypek@cs.ucla.edu or karplus@cs.ucla.edu Tel: (213) 825 2381 Fax: (213) UCLA CSD DESCRIPTION The capabilities of neural architectures (supervised and unsupervised learning, feature detection and analysis through approximate pattern matching, categorization and self-organization, adaptation, soft constraints, and signal based processing) suggest new approaches to solving problems in vision, image processing and pattern recognition as applied to visual stimuli. The purpose of this special issue is to encourage further work and discussion in this area. The volume will include both invited and submitted peer-reviewed articles. We are seeking submissions from researchers in relevant fields, including, natural and artificial vision, scientific computing, artificial intelligence, psychology, image processing and pattern recognition. "We encourage submission of: 1) detailed presentations of models or supporting mechanisms, 2) formal theoretical analyses, 3) empirical and methodological studies. 4) critical reviews of neural networks applicability to various subfields of vision, image processing and pattern recognition. Submitted papers may be enthusiastic or critical on the applicability of neural networks to processing of visual information. The IJPRAI journal would like to encourage submissions from both , researchers engaged in analysis of biological systems such as modeling psychological/neurophysiological data using neural networks as well as from members of the engineering community who are synthesizing neural network models. The number of papers that can be included in this special issue will be limited. Therefore, some qualified papers may be encouraged for submission to the regular issues of IJPRAI. SUBMISSION PROCEDURE Submissions should be sent to Josef Skrzypek, by 12-10-1990. The suggested length is 20-22 double-spaced pages including figures, references, abstract and so on. Format details, etc. will be supplied on request. Authors are strongly encouraged to discuss ideas for possible submissions with the editors. The Journal is published by the World Scientific and was established in 1986. Thank you for your consideration. ------------------------------ Date: Wed, 5 Sep 90 13:21:08 +0200 From: ronse@prlb.philips.be Subject: available document The following unpublished working document is available. If you want a copy of it, please send me: - Your complete postal (snail mail) address, preferably formatted as on an enveloppe (cfr. mine below); an e-mail address is useless in this context. - The title of the working document. Christian Ronse Internet: ronse@prlb.philips.be BITNET: ronse%prlb.philips.be@cernvax Philips Research Laboratory Avenue Albert Einstein, 4 B-1348 Louvain-la-Neuve Belgium Tel: (32)(10) 470 611 (central) (32)(10) 470 637 (direct line) Fax: (32)(10) 470 699 ========================================================================= A twofold model of edge and feature detection C. Ronse September 1990 ABSTRACT. Horn's model of surface reflectance shows that edges in three-dimensional surfaces lead to grey-level edges combining in various ways sharp or rounded steps, lines and roofs. The perceptual analysis of extended edges necessicates the localization not only of step and line edges, but also of roof edges and Mach bands, and more generally of discontinuities and sharp changes in the n-th derivative of the grey-level. Arguments are given which indicate the inadequacy of locating features at zero-crossings of any type of smooth operator applied to the image, and the necessity of orientationally selective operators. The null space of feature detection is defined; it contains in particular all constant signals. Oriented local features are modelled as the linear superposition of a featureless signal (in the null space), an even-symmetric and/or an odd-symmetric feature, measured by convolution with respectively even-symmetric and odd-symmetric functions. Advantages of energy feature detectors are given. KEY WORDS. Edge types, zero-crossings and peaks, orientational selectivity, linear processing, feature symmetry, energy feature detector. ------------------------------ Date: Wed, 12 Sep 90 02:41:16 GMT From: pegah@pleiades.cps.msu.edu (Mahmoud Pegah) Subject: MAC AI demos Organization: Computer Science, Michigan State University, E. Lansing Greetings; I am trying to find freeware demos of AI that run on the MAC. This will be used in a classroom setting (not in a lab) and will be projected on a large screen from the video on the MAC. Demos having to do with search space techniques, natural language processing, vision, neural nets, knowledge based systems... would all be items I would like to FTP for use here. These demos will be used in an intro grad level survey course in AI. Reply to me directly, and indicate whether you would like your demo to be listed in a catalogue of AI educational demos that I will prepare from the mail I get. I will post the composed directory back to the net in two weeks time. Please indicate an FTP host (with internet number) from which your demo can be FTPed. Thanks in advance. -Mahmoud Pegah pegah@pleiades.cps.msu.edu AI/KBS Group pegah@MSUEGR.BITNET Comp Sci Dept ... uunet!frith!pegah Mich State Univ ------------------------------ End of VISION-LIST ********************
Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/20/90)
Vision-List Digest Wed Sep 19 11:55:22 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Address correction for requesting the Workshop on Qualitative Vision
Shallice/Neuropsychology: BBS Multiple Book Review
NN workshop
------------------------------
Date: Wed, 19 Sep 90 10:16:34 -0700
From: pkahn@deimos (Philip Kahn)
Subject: Address correction for requesting the Workshop on Qualitative Vision
The address for requesting the proceedings failed to include the
street address. It should have read:
Copies of the proceedings from the AAAI-90 Workshop on Qualitative
Vision are available for $35 (in North America) and $45US
(international), and can be obtained by writing:
AAAI-90 Workshop on Qualitative Vision
Advanced Decision Systems
1500 Plymouth Street
Mountain View, CA 94043-1230
When requesting a copy of the Proceedings, please make your check
(payable in US $) to Advanced Decision Systems (this includes postage
and handling), specify the complete mailing address to which the
proceedings should be mailed, and (if available) include your e-mail
address in case there are any questions or problems.
------------------------------
Date: Mon, 17 Sep 90 23:02:16 EDT
From: Stevan Harnad <harnad@clarity.Princeton.EDU>
Subject: Shallice/Neuropsychology: BBS Multiple Book Review
Below is the abstract of a book that will be accorded multiple book
review in Behavioral and Brain Sciences (BBS), an international,
interdisciplinary journal that provides Open Peer Commentary on
important and controversial current research in the biobehavioral and
cognitive sciences. Commentators must be current BBS Associates or
nominated by a current BBS Associate. To be considered as a commentator
on this book, to suggest other appropriate commentators, or for
information about how to become a BBS Associate, please send email to:
harnad@clarity.princeton.edu or harnad@pucc.bitnet or write to:
BBS, 20 Nassau Street, #240, Princeton NJ 08542 [tel: 609-921-7771]
To help us put together a balanced list of commentators, please give some
indication of the aspects of the topic on which you would bring your
areas of expertise to bear if you are selected as a commentator.
BBS Multiple Book Review of:
FROM NEUROPSYCHOLOGY TO MENTAL STRUCTURE
Tim Shallice
MRC Applied Psychology Unit
Cambridge, UK
ABSTRACT: Studies of the effects of brain lesions on human behavior are
now cited more widely than ever, yet there is no agreement on which
neuropsychological findings are relevant to our understanding of normal
function. Despite the range of artefacts to which inferences from
neuropsychological studies are potentially subject -- e.g., resource
differences between tasks, premorbid individual differences and
reorganisation of function -- they are corroborated by similar findings
in studies of normal cognition (short-term memory, reading, writing,
the relation between input and output systems and visual perception).
The functional dissociations found in neuropsychological studies suggest
that not only are input systems organized modularly, but so are central systems.
This conclusion is supported by considering impairments of knowledge,
visual attention, supervisory functions, memory and consciousness.
----------------------------------------------------------------------
Date: Mon, 17 Sep 90 13:54:54 EDT
From: sankar@caip.rutgers.edu (ananth sankar)
Subject: NN workshop
The following is an announcement of a neural network workshop to be
held in East Brunswick, New Jersey. The workshop is sponsored by the
CAIP Center of Rutgers University, New Jersey. In the recent past
there has been a lot of neural network research with direct
applications to Machine Vision and Image Processing. Applications in
vision and image processing include early vision, feature extraction,
pattern classification and data compression. It is hoped that this
workshop will be of interest to the members of vision-list.
Thank you.
Ananth Sankar
Announcement follows:
=====================================================================
Rutgers University
CAIP Center
CAIP Neural Network Workshop
15-17 October 1990
A neural network workshop will be held during 15-17 October 1990 in
East Brunswick, New Jersey under the sponsorship of the CAIP Center of
Rutgers University. The theme of the workshop will be
"Theory and impact of Neural Networks on future technology"
Leaders in the field from government, industry and academia will
present the state-of-the-art theory and applications of neural
networks. Attendance will be limited to about 100 participants.
A Partial List of Speakers and Panelists include:
J. Alspector, Bellcore
A. Barto, University of Massachusetts
R. Brockett, Harvard University
L. Cooper, Brown University
J. Cowan, University of Chicago
K. Fukushima, Osaka University
D. Glasser, University of California, Berkeley
S. Grossberg, Boston University
R. Hecht-Nielsen, HNN, San Diego
J. Hopfield, California Institute of Technology
L. Jackel, AT&T Bell Labs.
S. Kirkpatrick, IBM, T.J. Watson Research Center
S. Kung, Princeton University
F. Pineda, JPL, California Institute of Technology
R. Linsker, IBM, T.J. Watson Research Center
J. Moody, Yale University
E. Sontag, Rutgers University
H. Stark, Illinois Institute of Technology
B. Widrow, Stanford University
Y. Zeevi, CAIP Center, Rutgers University and The
Technion, Israel
The workshop will begin with registration at 8:30 AM on Monday, 15
October and end at 7:00 PM on Wednesday, 17 October. There will be
dinners on Tuesday and Wednesday evenings followed by special-topic
discussion sessions. The $395 registration fee ($295 for participants
from CAIP member organizations), includes the cost of the dinners.
Participants are expected to remain in attendance throughout the entire
period of the workshop. Proceedings of the workshop will subsequently
be published in book form.
Individuals wishing to participate in the workshop should fill out the
attached form and mail it to the address indicated.
If there are any questions, please contact
Prof. Richard Mammone
Department of Electrical and Computer Engineering
Rutgers University
P.O. Box 909
Piscataway, NJ 08854
Telephone: (201)932-5554
Electronic Mail: mammone@caip.rutgers.edu
FAX: (201)932-4775
Telex: 6502497820 mci
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (09/29/90)
Vision-List Digest Fri Sep 28 11:52:53 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Vision Through Stimulation of Phosphors
Still Image Compression JPEG
Image scaling
Grey-level interpolation
Preprints available on color algorithms
Symposium on Automated Inspection of Flat Rolled Metal Products
Third ISAI in Mexico
----------------------------------------------------------------------
Date: Fri, 28 Sep 90 12:47:48 GMT
From: nigel@ATHENA.MIT.EDU (Sublime + Perfect One)
Subject: Vision Through Stimulation of Phosphors
Organization: Massachusetts Institute of Technology
About two (?) weeks ago I heard or read something about research
in the area of hooking up signals from a small video camera to the
cells in the brain responsible for those groovy color patterns
you see when you rub your eyes or when you stare at bright lights.
Does anyone have any references about this work or similar work
that they would not mind e-mailing to me. If there is a large
request for this info I'll post it etc...
thanks
nigel
------------------------------
Date: 20 Sep 90 19:51:31 GMT
From: bedros@umn-ai.cs.umn.edu
Subject: Still Image Compression JPEG
Keywords: visual quantization matrix needed
Organization: University of Minnesota, Minneapolis
I am trying to implement the JPEG algorithm and compare it to other algorithms.
Can somebody please send me the visual quatization matrix for Y,U,V
of the JPEG algorithm , and the Hoffman table of the quantizer.
I would appreciate some results on the Lena image ( snr,mse) .
Thanks
Saad Bedros
U.of Minnesota
bedros@ee.umn.edu
------------------------------
Date: Tue, 25 Sep 90 16:27:59 +0200
From: vlacroix@prlb.philips.be
Subject: image scaling
Suppose a digitalized image of NxN pixels. How would you transform it to
have a MxM pixels image? (M>N)
Clearly there are many possible transformations, but some of them will
produce nice looking images, while other won't.
Please send me yours ideas or pointers to literature, I'll summarize them
for the net.
------------------------------
Date: Wed, 26 Sep 90 01:22:27 CDT
From: stanley@visual1.tamu.edu (Stanley Guan)
Subject: grey-level interpolation
Hi,
Does there exist a canned method to solve the gray level interpolation
for a deformed image. The deformation is quivalent to a mapping which
may be expressed as
x' = r(x, y)
and
y' = s(x,y).
If r(x, y) and s(x, y) were known analytically it might be possible in
principle to find non-integer values for (x, y) given integer values
of the coordinates(x', y'). Then methods such as bilinear interpolation,
cubic convolution interpolation may be applied for calculating the gray
level at (x', y').
The deformation I am interested in has no easy way to find the inverse
mapping. So, the question is how am I going to solve the gray-level
assignment for my deformed image efficiently and systematically.
Any suggestion or helpful hints ? Please email me at
stanley@visual1.tamu.edu
Thanks in advance!
Stanley
Visualization Lab
Computer Science Dept
Texas A&M University
College Station, TX 77843-3112
Tel: (409)845-0531
------------------------------
Date: 20 Sep 90 8:33 -0700
From: mark@cs.sfu.ca
Subject: Preprints available on color algorithms
Technical report and preprint available.
Using finite dimensional models one can recover from camera RGB values
the spectra of both the illumination and the reflectances participating
in interreflections, to reasonable accuracy.
As well, one recovers a geometrical form factor that
encapsulates shape and orientation information.
Mark S. Drew and Brian V. Funt
School of Computing Science
Simon Fraser University
Vancouver, British Columbia, CANADA V5A 1S6
(604) 291-4682
e-mail: mark@cs.sfu.ca
@TechReport( FUNT89D
,title = "Color constancy from mutual reflection"
,author = "B.V. Funt, M.S. Drew, and J. Ho"
,key = "Funt"
,Institution= "Simon Fraser University School of Computing Science"
,Number = "CSS/LCCR TR 89-02"
,year = "1989"
)
@InProceedings( DREW90C
,title = "Calculating surface reflectance using a single-bounce
model of mutual reflection"
,author = "M.S. Drew and B.V. Funt"
,key = "Drew"
,organization = "IEEE"
,booktitle = "Proceedings: International Conference on Computer
Vision, Osaka, Dec.4-7/90"
,pages = " "
,year = "1990"
)
------------------------------
Date: Thu, 20 Sep 90 10:57:56 -0400
From: Herb Schilling <schillin@SCL.CWRU.Edu>
Subject: Symposium on Automated Inspection of Flat Rolled Metal Products
CALL FOR PAPERS
12th Advanced Technology Symposium on Automated
Inspection of Flat Rolled Metal Products
The Advanced Technology Committee of the Iron and Steel Society will
sponsor this symposium on November 3-6, 1991 in Orlando, Florida. The
Symposium will focus on automated inspection - surface and internal - of
flat rolled metal products at all stages of production. Inspection methods
will include those for defect detection as well as those for determination
of physical properties. Non-contact vision methods are of particular
interest. The committee is soliciting abstracts on the
following topics :
From Instrumentation Suppliers / Researchers
--------------------------------------------
- Advanced sensors/ automated systems
- New applications
- Research results
- Technology trends
From Users of Inspection Systems
--------------------------------
- Experiences with current inspection technologies
- Inspection system start-up/tuning challenges
- Benefits derived from the application of automated
inspection systems
- Future inspection needs
Reply, by January 15, 1991 , to :
Mr. E. A. Mizikar
Senior Director, Process Development
LTV Technology Center
6801 Brecksville Road
Independence, Ohio 44131
USA
Telephone : (216) 642-7206
Fax No : (216) 642-4599
Or send email to : Herb Schilling at schillin@scl.cwru.edu
------------------------------
Date: Fri, 28 Sep 90 09:40:06 CST
From: "Centro de Inteligencia Artificial(ITESM)" <ISAI@TECMTYVM.MTY.ITESM.MX>
Subject: THIRD ISAI IN MEXICO
To whom it may concern:
Here you will find the information concerning the
"THIRD INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE".
Please also display it in your bulletin board.
Thank you very much in advance.
Sincerely,
The Symposium Publicity Committee.
====================================================================
THIRD INTERNATIONAL SYMPOSIUM ON
ARTIFICIAL INTELLIGENCE:
APPLICATIONS OF ENGINEERING DESIGN & MANUFACTURING IN
INDUSTRIALIZED AND DEVELOPING COUNTRIES
OCTOBER 22-26, 1990
ITESM, MEXICO
The Third International Symposium on Artificial Intelligence will
be held in Monterrey, N.L. Mexico on October 22-26, 1990.
The Symposium is sponsored by the ITESM (Instituto Tecnologico y
de Estudios Superiores de Monterrey) in cooperation with the
International Joint Conferences on Artificial Intelligence Inc.,
the American Association for Artificial Intelligence, the Sociedad
Mexicana de Inteligencia Artificial and IBM of Mexico.
GOALS:
* Promote the development and use of AI technology in the
solution of real world problems. Analyze the state-of-the-art
of AI technology in different countries. Evaluate efforts
made in the use of AI technology in all countries.
FORMAT:
ISAI consists of a tutorial and a conference.
Tutorial.- Oct. 22-23
Set of seminars on relevant AI topics given in two days.
Topics covered in the Tutorial include:
"Expert Systems in Manufacturing"
Mark Fox, Ph.D., Carnegie Mellon University, USA
"A.I. as a Software Development Methodology"
Randolph Goebel, Ph.D., University of Alberta, Canada
Conference.- Oct. 24-26
Set of lectures given during three days. It consists of
invited papers and selected papers from the "Call for Papers"
invitation. Areas of application include: computer aided product
design, computer aided product manufacturing, use of industrial
robots, process control and ES, automatic process inspection and
production planning.
Confirmed guest speakers:
Nick Cercone, Ph.D, Simon Fraser University, Canada
"Expert Information Management with Integrated Interfaces"
Mitsuru Ishizuka, Ph.D, University of Tokyo, Japan
"Fast Hypothetical Reasoning System as an Advanced
Knowledge-base Framework"
Alan K. Mackworth, Ph.D, University of British Columbia, Canada
"Model-based Computational Vision"
Antonio Sanchez, Ph.D, Universidad de las Americas, Mexico
Sarosh N. Talukdar, Ph.D, Carnegie Mellon University, USA
"Desing System Productivity: Some bottlenecks and potential
solutions".
Carlos Zozaya Gorostiza, Ph.D, CONDUMEX, Mexico
IMPORTANT:
Computer manufacturers, AI commercial companies,
universities and selected papers with working programs could
present products and demonstrations during the conference.
In order to encourage an atmosphere of friendship and exchange
among participants, some social events are being organized.
For your convinience we have arranged a free shuttle bus
service between the hotel zone and the ITESM during the three
day conference.
FEES:
Tutorial.-
Professionals $ 250 USD + Tx(15%)
Students $ 125 USD + Tx(15%)
Conference.-
Professionals $ 180 USD + Tx(15%)
Students $ 90 USD + Tx(15%)
Simultaneous Translation $ 7 USD
Formal dinner $ 25 USD *
*(Includes dinner, open bar, music (Oct 26))
Tutorial fee includes:
Tutorial material.
Welcoming cocktail party (Oct.22)
Conference fee includes:
Proceedings.
Welcoming cocktail party (Oct.24)
Cocktail party. (Oct.25)
HOTELS:
Call one to the hotels listed below and mention that you
are going to the 3rd. ISAI. Published rates are single or
double rooms.
HOTEL PHONE* RATE
Hotel Ambassador 42-20-40 $85 USD + Tx(15%)
Gran Hotel Ancira 42-48-06 $75 USD + Tx(15%)
91(800) 83-060
Hotel Monterrey 43-51-(20 to 29) $60 USD + Tx(15%)
Hotel Rio 44-90-40 $48 USD + Tx(15%)
* The area code for Monterrey is (83).
REGISTRATION PROCEDURE:
Send personal check payable to "I.T.E.S.M." to:
"Centro de Inteligencia Artificial,
Attention: Leticia Rodriguez,
Sucursal de Correos "J", C.P. 64849,
Monterrey, N.L. Mexico"
INFORMATION:
CENTRO DE INTELIGENCIA ARTIFICIAL, ITESM.
SUC. DE CORREOS "J", C.P. 64849 MONTERREY, N.L. MEXICO.
TEL. (83) 58-20-00 EXT.5132 or 5143.
TELEFAX (83) 58-07-71, (83) 58-89-31,
NET ADDRESS:
ISAI AT TECMTYVM.BITNET
ISAI AT TECMTYVM.MTY.ITESM.MX
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/03/90)
Vision-List Digest Tue Oct 02 11:09:51 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Information-Based Complexity in Vision (request)
Paper Needs .......!!! (Urgent)
Length of a line
Vision research in Estonia
International Workshop on Robust Computer Vision
----------------------------------------------------------------------
Date: Mon, 1 Oct 90 14:12:38 +0200
From: Dario Ringach <dario%TECHUNIX.BITNET@CUNYVM.CUNY.EDU>
Subject: Information-Based Complexity in Vision (request)
Comments: Domain style address is "dario@techunix.technion.ac.il"
I would be grateful for any references on information-based complexity
works (in the sense of [1]) to vision and image processing. Thanks in advance.
[1] J. Traub, et al "Information-Based Complexity", Academic Press, 1988.
BITNET: dario@techunix | ARPANET: dario%techunix.bitnet@cunyvm.cuny.edu
Domain: dario@techunix.technion.ac.il | UUCP: ...!psuvax1!techunix.bitnet!dario
Dario Ringach, Technion, Israel Institute of Technology,
Dept. of Electrical Engineering, Box 52, 32000 Haifa, Israel
------------------------------
Date: Sat, 29 Sep 90 23:20:10 GMT
From: brian@ucselx.sdsu.edu (Brian Ho)
Subject: Paper Needs .......!!! (Urgent)
Organization: San Diego State University Computing Services
Hello folks,
I am urgently looking for a paper which has just presented at : International
conf. on Automation, robotics, and computer vision, the conf. was held
in Singapore Sept 18 - 21, 1990. The paper I am looking for is:
Title : Recongition of cursive writing - a method of segmentation
of word into characters.
Arthors: M. Leroux and J.C. Salome.
I will be greatly appreciate if anyone who can send me a copy or tell
me where I can get hold of the paper.
PS.
Special thanks to Dr. M. Atiquzzaman (Department of Electrical Engineering)
from King Fahd University of Petroleum & Minerals (Saudi Arabia), who
has passed that information to me.
Thanks in advance..
Please Send me E-mail at:
brian@ucselx.sdsu.edu
brian@cs.sdsu.edu
Brian
------------------------------
Date: Tue, 2 Oct 90 05:39:09 PDT
From: facc005%saupm00.bitnet@cunyvm.cuny.edu:
Subject: Length of a line
Does anyone know of any references on finding the "length of a line"
using the Hough Transform ?
Thanks,
ATIQ (facc005@saupm00.bitnet)
------------------------------
Date: Tue, 2 Oct 90 11:52:15 EDT
From: Michael Black <black-michael@CS.YALE.EDU>
Subject: Vision research in Estonia.
I am planning a visit to Tallinn, Estonia. While there, I would
like to make contact with anyone interested in computer vision.
I'm not even sure where to look. Any pointers to people, or even
institutions, who are interested in vision would be greatly
appreciated.
Michael Black
black@cs.yale.edu
------------------------------
Date: Thu, 27 Sep 90 13:56:23 -0700
From: graham@cs.washington.edu (Stephen Graham)
Subject: International Workshop on Robust Computer Vision
International Workshop on Robust Computer Vision
in cooperation with
IEEE Computer Society
International Society for Photogrammetry
and Remote Sensing
Robert M. Haralick, Co-Chairman
University of Washington, USA
Wolfgang Forstner, Co-Chairman
Institut fur Photogrammetrie, BRD
Program
University Plaza Hotel
400 NE 45th St
Seattle, Washington, 98105, USA
30 September-3 October 1990
Copies of the Proceedings are available from
Workshop on Robust Computer Vision
Stephen Graham
Department of Electrical Engineering FT-10
University of Washington
Seattle, WA 98195
USA
Sunday, 30 September 1990
Tutorials
9:00-10:30 AM Quality Analysis, Wolfgang Forstner
10:30-10:45 AM Break
10:45-12:00 Noon Robust Methods, Wolfgang Forstner
12:00-1:30 PM Lunch
1:30-2:45 PM Robust Pose Estimation, Robert Haralick
2:45-3:00 PM Break
3:00-4:15 PM Bias Robust Estimation, Doug Martin
Monday, 1 October 1990
8:00-10:00 AM Robust Techniques I
Robust Computational Vision, Brian G. Schunck, University
of Michigan, USA
Developing Robust Techniques for Computer Vision, Xinhua
Zhuang, University of Missouri, Columbia, and Robert M.
Haralick, University of Washington, USA
Robust Vision-Programs Based on Statistical Feature
Measurements, Chien-Huei Chen and Prasanna G.
Mulgaonkar, SRI International, USA
10:20-12:20 AM Robust Techniques II
A Robust Model Based Approach in Shape Recognition, Kie-
Bum Eom and Juha Park, The George Washington
University, USA
Robust Statistical Methods for Building Classification
Procedures, David S. Chen and Brian G. Schunck, University
of Michigan, USA
Noise Insensitivity of an Associative Image Classification
System, Giancarlo Parodi and Rodolfo Zunino, University
of Genoa, Italy
2:00-4:00 PM Line and Curve Fitting I
WhatUs in a Set of Points?, N. Kiryati and A.M. Bruckstein,
Technion Israel Institute of Technology, Israel
Robust Recovery of Precursive Polynomial Image Structure,
Peter Meer, Doron Mintz, and Azriel Rosenfeld, University
of Maryland, USA
Fitting Curves with Discontinuities, Robert L. Stevenson and
Edward J. Delp, Purdue University, USA
4:20-5:40 PM Line and Curve Fitting II
Non-Linear Filtering for Chaincoded Contours, Yuxin Chen
and Jean Pierre Cocquerez, ENSEA, and Rachid Deriche,
INRIA Sophia Antipolis, France
Using Geometrical Rules and a Priori Knowledge for the
Understanding of Indoor Scenes, M. Straforini, C. Coelho,
M. Campani, and V. Torre, University of Genoa, Italy
Tuesday, 2 October 1990
8:00-9:50 AM Pose Estimation and Surface
Reconstruction
Analysis of Different Robust Methods for Pose Refinement,
Rakesh Kumar and Allen R. Hanson, University of
Massachusetts, USA
A Robust Method for Surface Reconstruction, Sarvajit S.
Sinha and Brian G. Schunck, University of Michigan, USA
Dense Depth Maps from 2-D Cepstrum Matching of Image
Sequences, Dah Jye Lee, Sunanda Mitra, and Thomas F.
Krile, Texas Tech University, USA
10:10AM-12:20 PM Smoothing and Differential Operators
Accuracy of Regularized Differential Operators for
Discontinuity Localization in 1D and 2D Intensity Functions,
Heiko Neumann and H. Siegfried Stiehl, Universitat
Hamburg, and Karsten Ottenberg, Philips
Forschungslaboratorium Hamburg, Federal Republic of
Germany
On Robust Edge Detection, Linnan Liu, Brian G. Schunck,
and Charles C. Meyer, University of Michigan, USA
A Statistical Analysis of Stack Filters with Application to
Designing Robust Image Processing Operators, N. Pal, C.H
Chu, and K. Efe, The University of Southwestern Louisiana
Image Segmentation through Robust Edge Detection, Amir
Waks and Oleh J. Tretiak, Drexel University
2:00-4:00 PM Robust Hough Techniques
A Probabilistic Hough Transform, N. Kiryati, Y. Eldar, and
A.M. Bruckstein, Technion Israel Institute of Technologu,
Israel
Generalized Minimum Volume Ellipsoid Clustering with
Application in Computer Vision, Jean-Michel Jolion,
Universite Claude Bernard, France, and Peter Meer and
Azriel Rosenfeld, University of Maryland, USA
Random Sampling for Primitive Extration, Gerhard Roth,
National Research Council of Canada
4:20-5:40 PM Panel
Wednesday, 3 October 1990
8:00-10:00 AM Motion Estimation & Stereo I
Robust Motion Estimation Using Stereo Vision, Juyang Weng,
Ecole Polytechnique, Montreal, and Paul Cohen, Centre de
Recherche Informatique de Montreal, Canada
Robust Obstacle Detection Using Optical Flow, Giulio
Sandini and Massimo Tistarelli, University of Genoa, Italy
10:20-12:20 AM Motion Estimation & Stereo II
An Algebraic Procedure for the Computation of Optical Flow
from First Order Derivatives of the Image Brightness,
Alessandro Verri and Marco Campani,.University of Genoa,
Italy
Robust Dynamic Stereo for Incremental Disparity Map
Refinement, Arun Tirumalai, Brian Schunck, and Ramesh C.
Jain, University of Michigan, USA
An Efficient, Linear, Sequential Formulation for Motion
Estimation from Noisy Data, Subhasis Chaudhuri and Shankar
Chatterjee, University of California, San Diego, USA
2:00-4:00 PM Working Group
4:20-5:40 PM Working Group Presentation
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/06/90)
Vision-List Digest Fri Oct 05 18:07:46 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Address to Kontron?
Superquadrics from range data
What is the State of the Art of Artificial Vision?
Image Compression Routines for UNIX Systems
Proceedings of the International Workshop on Robust Computer Vision
Call for Papers: Geometric Methods in Computer Vision
----------------------------------------------------------------------
Date: Fri, 5 Oct 90 14:51:41 +0100
From: pell@isy.liu.se
Subject: Address to Kontron?
Hello. Does anyone have the (snail-mail) address to Kontron,
a manufacturer of Image Processing systems in Munich, Germany?
Thanks!
Dept. of Electrical Engineering pell@isy.liu.se
University of Linkoping, Sweden ...!uunet!isy.liu.se!pell
------------------------------
Date: Tuesday, 2 Oct 1990 23:43:24 EDT
From: Bennamoun Mohamed <MOHAMEDB@QUCDN.QueensU.CA>
Subject: Pentland's research.
Organization: Queen's University at Kingston
Hello !
Is anybody familiar with Pentland's research concerning the recovery of
superquadrics from range data?
I have problems understanding what he means by minimal length encoding, and
how his algorithm performs segmentation !!
I will appreciate any help.
Thanks in advance.
Mohamed.
------------------------------
Date: 4 Oct 90 12:21:07 GMT
From: loren@tristan.llnl.gov (Loren Petrich)
Subject: What is the State of the Art of Artificial Vision?
Organization: Lawrence Livermore National Laboratory
I wish to ask how much has been accomplished in the field of
Artificial Vision. What sorts of things have been achieved in the
field of computerized visual perception? To put it another way, what
things is it possible to "perceive" with the computerized vision
systems that have been devised to date? What progress has been made in
artificial-vision algorithms and in artificial-vision hardware?
I am sure that appropriate specialized hardware will be
essential for artificial-vision applications, since the amount of raw
data to be processed is enormous, and many of the fundamental
operations are relatively simple and can be done in parallel. And that
is why I asked about hardware.
Has anyone published the kind of overview of the
artificial-vision field that I have been asking for?
Loren Petrich, the Master Blaster: loren@sunlight.llnl.gov
Since this nodename is not widely known, you may have to try:
loren%sunlight.llnl.gov@star.stanford.edu
------------------------------
Date: 4 Oct 90 19:14:58 GMT
From: boulder!boulder!domik@ncar.UCAR.EDU (Gitta Domik)
Subject: Image Compression Routines for UNIX Systems
Keywords: Image compression, ADCT, UNIX Sources
Organization: University of Colorado, Boulder
I have the problem of storing large amounts of digitized images, and
want to compress them for long term archive. For our purposes, ADCT or
the items of this kind work best. I have tested Kodak's 'Colorsqueeze'
software for the MAC, and the results are okay, except for speed, but
I am looking for similar software to be run on UNIX machines. For me,
the optimal solutions would be public-domain UNIX sources. Can anyone
help?
I am not on Usenet, so please e-mail directly to my address:
[ Also please post to the List so others may benefit from the answers.
phil... ]
fkappe@tugiig.uucp
Frank Kappe, Technical University Graz
Institute for Computer Based New Media
Graz, Austria
------------------------------
Date: Thu, 4 Oct 90 14:52:27 -0700
From: graham@cs.washington.edu (Stephen Graham)
Subject: Proceedings of the International Workshop on Robust Computer Vision
The Proceedings of the International Workshop on Robust Computer Vision
are now available. The cost is US$40 per copy, including postage.
To order, please send a check or money order made out to the
International Workshop on Robust Computer Vision to the following
address:
Workshop on Robust Computer Vision
c/o Stephen Graham
Dept. of Electrical Engineering FT-10
University of Washington
Seattle, WA 98195 USA
Further information may be obtained by calling (206) 543-8115 or
by e-mail to graham@cs.washington.edu
Stephen Graham
------------------------------
Date: Fri, 5 Oct 90 15:17:04 -0400
From: Baba Vemuri <vemuri@scuba.cis.ufl.edu>
Subject: CAll for Papers
Announcement and Call for Papers
Geometric Methods in Computer Vision
(Part of SPIE's 36th Annual International Symp. on Optical
and Optoelectronic Applied Science and Engineering)
Dates: 25-26th July 1991
Location: San Diego, California USA
San Diego Convention Center and marriott Hotel & Marina
Conference Chair:
Baba C. Vemuri, Dept. of CIS, University of Florida, Gainesville, Fl
Cochairs: Ruud M. Bolle, IBM T. J. Watson Research Ctr., Yorktown Heights NY
Demetri Terzopoulos, Dept. of CS, Univ. of Toronto, Canada
Richard Szeliski, CS Research labs, DEC, Boston, MA
Gabriel Taubin, IBM T. J. Watson Research Ctr., Yorktown Heights NY
The theme of this conference is application of geometric methods in
low-level vision tasks, specifically for shape and motion estimation.
Over the past few years, there has been increased interest in the use
of differential geometry and geometric probability methods for various
low-level vision problems. Papers describing novel contributions in
all aspects of geometric and probabilistic methods in low-level vision
are solicited, with particular emphasis on:
(1) Differential Geometric Methods for Shape Representation
(2) Probability and Geometry (Geometric Probability)
(3) Energy-based Methods for Shape Estimation
(4) Geometry and Motion Estimation
Deadlines:
Abstract Due Date: 24 December 1990
Manuscript Due Date: 24th June 1991
You may recieve the author application kit by sending email requests
to vemuri@scuba.cis.ufl.edu. Late abstract submissions may be
considered, subject to program time availability and chair's approval.
Submit To:
SPIE Technical Program Committee/San Diego'91
P. O. Box 10, Bellingham, WA 98227-0010 USA
Telephone: 206/676/-3290 (Pacific Time)
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (10/17/90)
Vision-List Digest Tue Oct 16 15:15:27 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
3-D Object Recognition
Parallel Languages for Computer Vision
Image processing at Siemens
Fractals & data compression
Performance Evaluation
Call for Papers and Referees: Special Issue of IEEE COMPUTER
----------------------------------------------------------------------
Date: 16 Oct 90 20:10:22 GMT
From: eleyang@ubvmsd.cc.buffalo.edu (Yang He)
Subject: 3-D Object Recognition
Organization: University at Buffalo
I have just developed a shape classification algorithm. It has
shown a 100% classification result for 2-D shapes. The algorithm can
be easily extended to 3-D case. But I don't have 3-D data for the
experiments.
Could anybody out there tell me where I can get 3-D object data
suitable for classification? My requirements are as follows:
1. Each 2-D slice should be a closed boundary without inner
contour.
2. Binary data preferred. But grey level images may also be
used after boundary extraction.
3. I need 5+ classes, 20+ shapes for each class.
4. The shapes within a class have contour perturbation, i.e.,
the shapes are NOT different ONLY in size and orientation.
If anybody has the information, please send E-mail to
eleyang@ubvms.bitnet. Your help is very much appreciated.
------------------------------
Date: Fri, 12 Oct 90 15:33:10 -0400
From: Pierre Tremblay <pierre@sol.McRCIM.McGill.EDU>
Subject: Parallel Languages for Computer Vision
I'm doing research as part of my Master's thesis on parallel
programming models and languages appropriate for "intermediate-level"
computer vision (i.e. no SIMD processing, less emphasis on graph
searching).
Does anyone have references to parallel programming languages
specifically designed for computer vision programming, or references
to general purpose parallel programming languages used in such a
capacity?
Please reply by E-mail, and I'll post back to the net with a summary.
Many thanks,
Pierre
* Pierre P. Tremblay Internet: pierre@larry.mcrcim.mcgill.edu *
* Research Assistant Surface: 3480 University Street *
* McGill Research Centre Montreal, Quebec, Canada *
* for Intelligent Machines H3A 2A7 *
* Phone: (514) 398-8204 or 398-3788 *
------------------------------
Date: Fri, 12 Oct 90 17:15:01 +0100
From: br%bsun3@ztivax.siemens.com (A. v. Brandt)
Subject: Image processing at Siemens
I'd like to introduce to you the Image Processing Group of Siemens Corporate
Research, Munich, Germany. We are about twenty researchers doing basic
and applied studies in the areas of image understanding
(document interpretation, object recognition, motion estimation, 3D modeling)
and artificial neural networks (models, implementations, selected applications) The Laboratory is located in Munich, an attractive city in the south of the
Federal Republic of Germany (i. e., in Bavaria).
Connections exist with our sister laboratory, Siemens Corporate Research
in Princeton, NJ, as well as with various research institutes and universities
in Germany and in the U.S. including MIT, CMU and ICSI.
Above and beyond the Laboratory facilities, the group has a network of
Sun and DEC workstations, Symbolics Lisp machines, file and compute servers,
and dedicated image processing hardware.
My personal interests are in image sequence analysis, moving object recognition
for surveillance and traffic monitoring, depth from stereo and motion,
optical flow estimation, autonomous navigation etc. If someone is interested
in more details, or if someone would like to participate in one of our
projects (we have openings), please send a message to:
Achim v. Brandt
Siemens AG
ZFE IS INF 1
Otto-Hahn-Ring 6
D-8000 Muenchen 83
(West) Germany
email: brandt@ztivax.siemens.com
Tel. +49-89-636-47532
FAX +49-89-636-2393
------------------------------
Date: Fri, 12 Oct 90 20:33:00 +0100
From: Eduardo Bayro <eba@computing-maths.cardiff.ac.uk>
Subject: fractals & data compression
Organization: Univ. of Wales Coll. of Cardiff, Dept. of Electronic & Systems
Engineering
Hello friends!!
I asked a cupple of months ago for bibliography on fractals. I am very
thankfull to everybody wo answer me. The literature I have got,
actually, comprise of a some books and nearly ten articles. It is
anyway not worthy for mailing it as a representative one. Now friends,
what I am really interested on is in fractals for image compression.
Please, if anybody knows suitable references or have suggestions post
them by e-mail. Many Thanks, Eduardo.
Eduardo Bayro, School of Electrical, Electronic and Systems Engineering,
University of Wales College of Cardiff, Cardiff, Wales, UK.
Internet: eba%cm.cf.ac.uk@nsfnet-relay.ac.uk Janet: eba@uk.ac.cf.cm
UUCP: eba@cf-cm.UUCP or ...!mcsun!ukc!cf-cm!eba
------------------------------
Date: Thu, 11 Oct 90 17:55:57 PDT
From: tapas@george.ee.washington.edu
Subject: Performance Evaluation
We are compiling a survey of work done on performance evaluation
of low level vision algorithms. The kind of papers we are looking
for are:
(i) Any work on general methodology of performance evaluation.
(ii) Performance evaluation of specific type of algorithms,
e.g., edge detection algorithms, corner detection algorithms, etc.
I have appended a list of references we have already collected.
We will appreciate any references to this kind of work. I'll summerize
the responses to the net.
Thanks in advance.
Tapas Kanungo <tapas@george.ee.washington.edu>
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
@article{ DeF:eval,
author = "Deutsch, E. S. and J. R. Fram",
title = "A quantitative study of the
Orientational Bias of some Edge Detector Schemes",
journal = "IEEE Transactions on Computers",
month = "March",
year = 1978}
@article{FrD:human,
author = "Fram, J.R. and E.S. Deutsch",
title = "On the quantitative evaluation of edge detection schemes and
their comparisions with human performance",
journal = "IEEE Transaction on Computers",
volume = "C-24",
number = "6",
pages = "616-627"
year = 1975}
@article{AbP:eval,
author = "Abdou, I.E. and W. K. Pratt",
title = "Qualitative design and evaluation of enhancement/thresholding
edge detector",
journal = "Proc. IEEE",
volume = "67",
number = "5",
pages = "753-763",
year = 1979}
@article{PeM:eval,
author = "Peli, T. and D. Malah",
title = "A study of edge detection algorithms",
journal = "Computer Graphics and Image Processing",
volume = "20",
pages ="1-21",
year = 1982}
@article{KiR:eval,
author = "Kitchen, L. and A. Rosenfeld",
title = "Edge Evaluation using local edge coherence",
journal = "IEEE Transactions on Systems, Man and Cybernetics",
volume = "SMC-11",
number = "9",
pages = "597-605",
year = 1981}
@article{HaL:eval,
author = "Haralick, R.M. and J. S. J. Lee",
title = "Context dependent edge detection and evaluation",
journal = "Pattern Recognition",
volume = "23",
number = "1/2",
pages = "1-19",
year = 1990}
@article{Har:performance,
author = "Haralick, R.M.",
title = "Performance assessment of near perfect machines",
journal = "Journal of machine vision algorithms",
year = 1988}
------------------------------
Date: Fri, 12 Oct 90 00:39:31 EDT
From: choudhar@cat.syr.edu (Alok Choudhary)
Subject: Call for Papers and Referees: Special Issue of IEEE COMPUTER
Call for Papers and Referees
for A Special Issue of IEEE COMPUTER on
Parallel Processing for Computer Vision and Image Understanding (CVIU)
The February 1992 issue of IEEE Computer will be devoted to
Parallel Processing for Computer Vision and Image Understanding (CVIU).
Tutorial, survey, case-study of architectures, performance evaluation
and other manuscripts are sought. Sub-areas of interest include, but are
not limited to :
Architectures : Multiprocessor architectures and special purpose architectures
for CVIU.
Algorithms : Design, mapping and implementations of parallel algorithms
for CVIU problems.
Languages : Design of languages for efficient implementation of CVIU
programs, specially for parallel processing and architecture
independent implementations.
Software Development Tools : Software development tools for parallel CVIU
applications.
Performance Evaluation : Benchmarking, performance evaluation of
architectures and algorithms; performance evaluation of
integrated CVIU systems.
Real-time vision architectures and applications.
Instructions for submitting manuscripts
Manuscripts must not have been previously published or currently under
consideration for publication elsewhere. Manuscripts should be no longer
8000 words (approximately 30 double-spaced, single sided pages using a 12-point
type) including all text, figures and references).
Manuscripts should include a title page containing: paper title;
full name(s), affiliations(s), postal address, e-mail address, telephone,
and fax number of all authors; a 300-word abstract; and a list of key words.
Deadlines
- Eight (8) Copies of the Full Manuscript March 1, 1991
- Notification of Decisions August 1, 1991
- Final Version of the Manuscript October 1, 1991
- Date of Special Issue February 1992
Send submissions and Questions to
Prof. Alok N. Choudhary Prof. Sanjay Ranka
Electrical and Computer Engineering School of Computer and Information
Department Science
121 Link Hall 4-116, Center for Science and
Technology
Syracuse University Syracuse University
Syracuse, NY 13244 Syracuse, NY 13244
(315) 443-4280 (315) 443-4457
choudhar@cat.ece.syr.edu ranka@top.cis.syr.edu
Referees
If you are willing to referee papers for the special issue, please send a note
with research interests to:
Prof. John T. Butler,
Associate Technical Editor, Computer
Department of Electrical and
Computer Engineering
Naval Postgraduate School, Code EC/Bu
Monterey, CA, 92943-5004
Office: (408) 646-3299
or (408) 646-3041
fax: (408) 646-2760
email: butler@cs.nps.navy.mil.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/01/90)
Vision-List Digest Wed Oct 31 12:22:21 PDT 90
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Call for Suggestions: Workshop on Shape Description/Representation
Optical Flow in Realtime
Image-restoration and image reconstruction software?
Paper needed!
Canny's edge detector
CVNet- Open house during OSA Annual Meeting
Abstract: Neural Network System for Histological Image Understanding
CNS Program at Boston University Hiring 2 Assistant Professors
Submission for comp-ai-vision
research post
CVNet- Two tenure track positions
----------------------------------------------------------------------
Date: Tue, 30 Oct 90 14:08:20 +0100
From: henkh@cwi.nl
Subject: Call for Suggestions: Workshop on Shape Description/Representation
CALL FOR SUGGESTIONS
We are intending to organise a workshop on shape description and
representation of 2-D (binary and greylevel) images.
The emphasis will be put on the underlying theory by
(contemporary) mathematics and algorithms for application.
Keywords are: theory of shape, category theory, scale space methods,
differential geometry and topology, mathematical morphology,
graph representation, computational geometry.
If you have any suggestions regarding the topics or persons working on
the subject, please let us know.
Kind regards, O Ying-Lie, Lex Toet, Henk Heijmans.
Please e-mail your suggestions to:
Henk Heijmans
CWI
Kruislaan 413
NL-1098 SJ Amsterdam
The Netherlands
e-mail: henkh@cwi.nl
------------------------------
Date: Thu, 25 Oct 90 18:53:25 +0100
From: jost@bmwmun.uucp.dbp.de (Jost Bernasch)
Subject: Optical Flow in Realtime
Help! Is there anybody who could give me some hints or
answers to the following questions:
1. Is there any company or research lab which could
compute on grey images (256x256) image flow in
real time? Is a chip or a board anywhere available?
2. Has anybody *practical* experience in computing
qualitative depth information from optical flow?
How sensitive is optical flow (from image sequences)
to noise?. Are there any basic problems?
3. Computing depth information from *normal* flow,
is this theoretically possible?
We at BMW are developing a lateral and longitudinal
controlled car, which should (for experiments) drive
automatically and which might be in the future an intelligent
assistent to the driver, in which form soever.
We will use (if available) this techniques to detect
obstacles, that are lying or driving on the street,
by comparing the expected optical flow or the expected depth
of the plane (we assume, the street is a plane) to the
computed optical flow or depth. From the differences
we will conclude to obstacels NOT being in the plane.
Any help is very much welcomed!
Yours
Jost Bernasch,
BMW AG Muenchen, Dep. EW-13, Tel. ()89-3183-2822
P.O. BOX 40 02 40, FAX ()89-3183-4767
D-8000 Muenchen 40, Germany jost@bmwmun.uucp.dbp.de
------------------------------
Date: Fri, 26 Oct 90 08:06:42 +0100
From: Reiner Lenz <reiner@isy.liu.se>
Subject: Image-restoration and image reconstruction software?
Are there any (public domain or commercial) software packages for image
restoration and image reconstruction available?
If there is enough response I will summarize.
"Kleinphi macht auch Mist"
Reiner Lenz | Dept. EE. |
| Linkoeping University | email: reiner@isy.liu.se
| S-58183 Linkoeping/Sweden |
------------------------------
Date: Fri, 26 Oct 90 12:34:57 -0700
From: zeitzew@CS.UCLA.EDU (Michael Zeitzew)
Subject: Paper needed!
Hello,
I am looking for a paper from the conference "Speech Technology" 1985....
J.F. Mari and S. Roucos, "Speaker Independent Connected Digit Recognition
Using Hidden Markov Models", Proc. Conf. "Speech Technology", New York, April
1985
I know the publisher is Media Dimensions, but they won't sell or give me
just one paper, I'd have to buy the entire proceedings ($150+).
I you have it, or know where to get it and wouldn't mind mailing it to me,
I'll be glad to pay for postage, etc. If you know a library that has it, please
let me know.
Mike Zeitzew
zeitzew@cs.ucla.edu
------------------------------
Date: Mon, 29 Oct 90 22:36:42 EST
From: namuduri@ziggy.cmd.usf.edu (Kameswara Namuduri)
Subject: Canny's edge detector
I need the program for Canny's edge detector. I appreciate it if some one can send it to the following adress.
namuduri@ziggy.usf.edu
Thanks in advance -namuduri
------------------------------
Date: Tue, 30 Oct 90 06:31:48 EST
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: CVNet- Open house during OSA Annual Meeting
Open House with the MIT Media Lab Vision Group:
For those of you who will be attending the OSA meeting in Boston, the
Vision and Modeling group of the MIT Media Lab invites you to visit
on Wednesday, Nov. 7, from 10:0am to 1:00pm. We will be showing
our current work on such topics as face recognition, motion analysis,
image coding, physical modeling, and 3-D sensing.
The Media Lab is in the Wiesner Building (also known as E15),
at 20 Ames St., in Cambridge. It is near the Kendall subway stop on the
Red Line. From the conference, take the Green Line to Park Station,
then change for the Red Line toward Harvard. Get off at Kendall, walk
1/2 block to Legal Seafoods Restaurant, then turn left and go 3/4 block
on Ames.
Hope to see you!
Ted Adelson
Sandy Pentland
------------------------------
Date: Mon, 29 Oct 90 17:43:30 +0000
Subject: Abstract: Neural Network System for Histological Image Understanding
From: P.Refenes@cs.ucl.ac.uk
The following pre-print (SPIE-90, Boston, Nov. 5-9 1990) is available.
(write or e-mail to A. N. Refenes at UCL)
AN INTEGRATED NEURAL NETWORK SYSTEM for HISTOLOGICAL IMAGE UNDERSTANDING
A. N. REFENES, N. JAIN & M. M. ALSULAIMAN
Department of Computer Science, University College London, London, UK.
This paper describes a neural network system whose
architecture was designed so that it enables the
integration of heterogeneous sub-networks for performing
specialised tasks. Two types of networks are integrated: a)
a low-level feature extraction network for sub-symbolic
computation, and b) a high-level network for decision
support.
The paper describes a non trivial application from
histopathology, and its implementation using the Integrated
Neural Network System. We show that with careful network
design, the backpropagation learning procedure is an
effective way of training neural networks for histological
image understanding. We evaluate the use of symmetric and
asymmetric squashing functions in the learning procedure
and show that symmetric functions yield faster convergence
and 100% generalisation performance.
------------------------------
Date: Tue, 30 Oct 90 14:43:52 -0500
From: mike@park.bu.edu
Subject: CNS Program at Boston University Hiring 2 Assistant Professors
Boston University seeks two tenure track assistant or associate
professors starting in Fall, 1991 for its M.A. and Ph.D. Program
in Cognitive and Neural Systems. This program offers an
intergrated curriculum offering the full range of psychological,
neurobiological, and computational concepts, models, and methods
in the broad field variously called neural networks,
connectionism, parallel distributed processing, and biological
information processing, in which Boston University is a leader.
Candidates should have extensive analytic or computational
research experience in modelling a broad range of nonlinear
neural networks, especially in one or more of the areas: vision
and image processing, speech and language processing, adaptive
pattern recognition, cognitive information processing, and
adaptive sensory-motor control Candidates for associate
professor should have an international reputation in neural
network modelling. Send a complete curriculum vitae and three
letters of recommendation to Search Committee, Cognitive and
Neural Systems Program, Room 240, 111 Cummington Street, Boston
University, Boston, MA 02215, preferably by November 15, 1990 but
no later than January 1, 1991. Boston University is an Equal
Opportunity/Affirmative Action employer.
Boston University (617-353-7857) Email: mike@bucasb.bu.edu
Smail: Michael Cohen 111 Cummington Street, RM 242
Center for Adaptive Systems Boston, Mass 02215
Boston University
------------------------------
Date: 30 Oct 90 16:38:08 GMT
From: Paul Lewis <P.H.Lewis@ecs.soton.ac.uk>
Subject: research post
University of Southampton
Department of Electronics and Computer Science
Research Post in Image Understanding
Applications are invited for a research fellow at post-doctoral
level to work on a SERC funded project entitled "Enhanced Methods
of Extracting Features of Engineering Significance from Remotely
Sensed Images".
The aim of the project is to develop and apply recent work on knowledge
based feature extraction to the provision of tools for extractiong
features such as roads and river networks from satellite images.
The work will be set in a GIS context and will make use of transputer
based imaging workstations.
Applicants should be post-doctoral or similar level, ideally having
recent research experience in image understanding, artificial
intelligence and software development in C, Prolog and Lisp.
The appointment will be for one year in the first instance with the
expectation of remnewal for two further years. The starting salary
will be 13495 pounds per annum and the post is available from
January 1st 1991.
Applications, including a curriculum vitae and the names and
addresses of two referees, should be sent to Mr H. F. Watson,
Staffing Department, the University, Southampton, UK, SO95NH,
to arrive before November 23rd 1990.
Preliminary informal enquiries may be made to Dr Paul Lewis
by telephone (0703 593715 or 0703 593649).
Dr Paul H. Lewis,
Dept. of Electronics and Computer Science,
The University of Southampton, Southampton, U.K., SO95NH.
e-mail phl@ecs.soton.ac.uk
Tel. 0703 593715
Fax. 0703 593045
------------------------------
Date: Wed, 31 Oct 90 10:19:26 EST
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: CVNet- Two tenure track positions
The Department of Psychology of the Ohio State University seek Asst.
Prof applications for two tenure-track positions, starting in September of
1991. One position is in visual perception and one is for a scientist
interested in the relation of visual cognition to neuroscience.
Salary will be in the range of $34,080 to $40,920 and considerable
start-up funds are available. Research areas might include visual
electrophysiology, object recognition, visual attention and memory,
visual/neural modeling and/or visuo-motor coordination. Candidates
should send vita, work sample, and five reference letters to
Mari Riess Jones, Chair Visual Perception Search, 142 Townshend
Hall, Dept Psychology, The Ohio State University, Columbus, Ohio, 43210.
The deadline for applications is December 15, 1990.
------------------------------
End of VISION-LIST
********************Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (11/06/90)
Vision-List Digest Mon Nov 05 09:59:09 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: RE: Optical Flow in Realtime Standard (or at least famous) pictures - where to find them SGI and ground-truth for shape from motion algorithm Fingerprint ID Abstract of Talk on Computer Vision and Humility ---------------------------------------------------------------------- Date: Fri, 2 Nov 90 23:33:13 GMT From: Han.Wang@prg.oxford.ac.uk Subject: RE: Optical Flow in Realtime > (1) Is there any company or research lab which could >compute on grey images (256x256) image flow in real time? I have achieved the rate of 2~4 seconds in computing optic flow using 8 T800 transputers on 128x128 images. This is only along edge contours (Canny). >We at BMW are developing a lateral and longitudinal >controlled car, which should (for experiments) drive >automatically and which might be in the future an intelligent >assistent to the driver, in which form soever. > >We will use (if available) this techniques to detect >obstacles, that are lying or driving on the street, In oxford, we are building a system of bybrid architecture using Sparc station, Transputer array and Datacube to compute a 3D vision system DROID (Roke Manor Research) in real time which can effectively detect obstacles in an unconstraint 3D space. This is however not based on optic flow. It uses corner matching instead. So far, we have succeed in testing many sequences including a video camera carried by a robot vehicle. This experiment will be demonstrated in Brussels during the ESPRIT conference (9th - 16th Nov. 1990). regards Han ------------------------------ Date: Fri, 2 Nov 90 11:40:06 EST From: John Robinson <john@watnow.waterloo.edu> Subject: Standard (or at least famous) pictures - where to find them We are searching for raster versions of "famous" monochrome and colour images. Actually, any format will do if we can also get access to a format to raster convertor. We are particularly interested in getting hold of: Girl and toys, Boy and toys, Gold hill (steep village street with countryside) Boilerhouse (picture with lots of shadows), Side view of man with camera on a tripod (actually there are at least two pictures of that description around - we'd prefer the one with the overcoat), The various portraits from the 60s of one or two people that are often used, Any single frames taken from videoconference test sequences. Anything else that fulfils the following would be appropriate: Good dynamic range, Low noise, No restrictions on copyright, Portraits completely devoid of sexist overtones (e.g. not Lena), Is there an FTP site with a good selection of these? Thanks in anticipation John Robinson john@watnow.UWaterloo.ca [ The Vision List Archives are on the build. Currently, of static imagery, they contain Lenna (girl with hat) and mandrill. A collection of motion imagery built for the upcoming Motion Workshop (including densely sampled and stereomotion imagery) is also in the FTP accessible archive. If you have imagery which may be of interest and may be distributed to the general vision community, please let me know at vision-list-request@ads.com. phil... ] ------------------------------ Date: Thu, 01 Nov 90 19:38:35 IST From: AER6101%TECHNION.BITNET@CUNYVM.CUNY.EDU Organization: TECHNION - I.I.T., AEROSPACE ENG. Subject: SGI and ground-truth for shape from motion algorithm I am presently working with 3-D scene reconstruction from a sequence of images. The method I am using is based on corner matching between a pair of consecutive images. The output is the estimated depth at the corner pixels. The images are rendered by a perspective projection of 3-D blocks whose vertices are supplied by me as input to the program. However, the detected corners are not necessarily close to those vertices. In order to obtain a measurement of the accuracy of the algorithm I am using, the actual depth at that pixel is needed and I tried to recover it from the z-buffer. I thought that (my station is a SilliconGraphics 4D-GT) the z-buffer values (between 0 and 0x7fffff) were linearly mapped to the world z-coordinates between the closest and farthest planes used in the perspective projection procedure available in the Sillicon's graphic library. The results however don't match the above hypothesis. I tested the values of the z-buffer obtained when viewing a plane at a known depth and it was clear that the relation was not linear. Can someone enlighten me about how the z-buffer values are related to actual depth? I know there is a clipping transformation that transforms the perspective pyramid into a -1<x,y,z<1 cube, but perhaps I am missing something else. If anybody has an opinion or reference that could help me I would be very pleased to receive it in my E-mail (aer6101@technion.bitnet). I would summarize the received answers and post a message with the conclusions. Thanking you in advance, jacques- ------------------------------ Date: Mon, 5 Nov 90 10:07:37 EST From: perry@dewey.CSS.GOV (John Perry) Subject: Fingerprint ID Does anyone know of any review articles or recent textbooks in fingerprint ID systems, research, etc. Thanks, John ------------------------------ Date: 2 Nov 90 01:59:57 GMT From: sher@wolf.cs.buffalo.edu (David Sher) Subject: Abstract of Talk on Computer Vision and Humility Organization: State University of New York at Buffalo/Comp Sci I thought the people who read these lists may find this talk abstract of interest: Computer Vision Algorithms with Humility David Sher Nov 1, 1990 Often computer vision algorithms are designed in this way - a plausible and mathematically convenient model of some visual phenomenon is constructed which defines the relationship between an image and the structure to be extracted. For example: the image is modeled as broken up into regions with constant intensities degraded by noise and the region boundaries are defined to be places in the undegraded image with large gradients. Then an algorithm is derived that generates optimal or near optimal estimates of the image structure according to this model. This approach assumes that constructing a correct model of our complex world is possible. This assumption is a kind of arrogance that yields algorithms that are difficult to improve, since the problems with this algorithm result from inaccuracy in the model. How one changes an algorithm given changes in its model often is not obvious. I propose another paradigm which follows the advice of Rabbi Gamliel, "Provide thyself a teacher" and Hillel, "He who does not increase his knowledge decreases it." We are designing computer algorithms that translate advice and correction into perceptual strategies. Because these algorithms can incorporate a large variety of statements about the world into their models they can be easily updated and initial inaccuracies in their models can be automatically corrected. I will illustrate this approach by discussing 6 results in computer vision 3 of which directly translate human advice and correction into computer vision algorithms, 3 of which indirectly use human advice. David Sher ARPA: sher@cs.buffalo.edu BITNET: sher%cs.buffalo.edu@ubvm.bitnet UUCP: {apple,cornell,decwrl,harvard,rutgers,talcott,ucbvax,uunet}!cs.buffalo.edu!sher ------------------------------ End of VISION-LIST ********************