Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) (05/31/91)
VISION-LIST Digest Thu May 30 11:36:50 PDT 91 Volume 10 : Issue 25
- Send submissions to Vision-List@ADS.COM
- Vision List Digest available via COMP.AI.VISION newsgroup
- If you don't have access to COMP.AI.VISION, request list
membership to Vision-List-Request@ADS.COM
- Access Vision List Archives via anonymous ftp to ADS.COM
Today's Topics:
Khoros 1.0 (short announcement)
Info. needed about DATACUBE
Industrial Robot/Vision Systems
Low-level image processing with an Artificial neural network
Discrete relaxation
Available Research Position
An International Standard for Image Processing and Interchange (long)
Travel, Registration and Hotel Info: Geometric Methods in CV Conf.
Vision Interface '91 - Final Program
----------------------------------------------------------------------
Date: 29 May 91 02:57:12 GMT
From: rasure@pprg.unm.edu (John Rasure)
Organization: University of New Mexico, Albuquerque
Subject: Khoros 1.0 (short announcement)
SHORT ANNOUNCEMENT OF KHOROS 1.0
Khoros is an integrated software development environ-
ment for information processing and visualization, based on
X11R4. Khoros components include a visual programming
language, code generators for extending the visual language
and adding new application packages to the system, an
interactive user interface editor, an interactive image
display package, an extensive library of image processing,
numerical analysis and signal processing routines, and 2D/3D
plotting packages.
Khoros is available via anonymous ftp from pprg.unm.edu (129.24.13.10).
If you have questions, comments or problems of a general nature,
mail the Khoros mailing list, khoros@chama.unm.edu. To subscribe
to the mailing list, mail to khoros-request@chama.unm.edu.
Once you have the system and want to report bugs, mail to
khoros-bugs@chama.unm.edu.
For a more detailed announcement, mail to rasure@chama.unm.edu or
see comp.windows.x.announce or comp.newprod.
Dr. John Rasure rasure@chama.unm.edu
Department of EECE
University of New Mexico Albuquerque, NM 87131
------------------------------
Date: Tue, 28 May 91 11:47:32 EDT
From: nar@cs.wayne.edu
Subject: Info. needed about DATACUBE
Hi Vision Experts,
We recently got some money from NSF to buy some equipment
for our Vision and Neural Network Lab including a DATACUBE machine.
Since we have had no experience in that domain, I would appreciate
if any users of the machine out there can give me some advice.
I will summerize the information to the net at a later date.
In addition to general information pertaining to the DATACUBE
machine, I would like to know users experience with a suitable
front end for the processor. It would also help if you can describe
the Computing facilities you have at your end.
Does a Sparc 2 do any good?.
Should we go for a a different work station?.
How about OS-9 as an operating system?.
Thank you all in advance,
Nagarajan Ramesh ! internet- nar@cs.wayne.edu
Vision & Neural Network Lab. ! uucp - ..!umich!wsu-cs!nar
Dept. of Computer Science, ! Phone: (313)-577-2477
Wayne State University, ! Fax : (313)-577-6868
Detroit MI 48202 !
------------------------------
From: Wayne Sincarsin <dynacon@utcs.utoronto.ca>
Date: Fri, 24 May 1991 12:14:32 -0400
Subject: Industrial Robot/Vision Systems
Dear Fellow Netters:
I am conducting a survey of industrial robot/vision systems. Such a
system would consist of an industrial manipulator that uses a `smart'
vision sensor to assist in trajectory planning. This survey is
related to Space Station robotics technology development. Helpful
information would include:
i) name of robot/vision system;
ii) brief description of system (where possible);
iii) name of manufacturers/distributers;
iv) follow-up contacts.
Please e-mail to me directly [and post to the Vision List. phil...].
Thank you in advance.
Frank Naccarato
dynacon@gpu.utcs.utoronto.ca
------------------------------
Date: Tue, 28 May 91 09:44:39 +0200
From: guedalia@bimacs.cs.biu.ac.il (David Guedalia)
Comments: Internet address: bimacs.cs.biu.ac.il. Bitnet address: bimacs.bitnet.
Old internet address (bimacs.biu.ac.il) is available only temporarily.
Subject: Low-level image processing with an Artificial neural network
Hi,
I recently came across an article by Atam P. Dhawan and Thmas Dufresne titled
"Low level image processing and edge enhancement using a self organizing neural
network" in ijcnn 1990 vol I pp503-510.
I was wondereing if any one else is doing low level image processing with an
ANN? If so can they please mail me refrences?
thank you
david
------------------------------
Date: Mon, 27 May 91 12:50:50 +0200
From: mohr@rhea.imag.fr (Roger Mohr)
Subject: discrete relaxation
Dear Eric,
in article 201 you asked for references for discrete relaxation.
Here are references two of them from my personnal work. If you have some
dificulties to get the second one, I can make a copy for you.
@ARTICLE{mohr86a,
AUTHOR = {R. Mohr and T.C. Henderson},
TITLE = {{Arc and Path Consistency Revisited}},
KEYWORDS = {ac4, contraintes discr\`{e}tes, \'{e}tiquetage, complexit\'{
e}},
YEAR = {1986},
JOURNAL = {Artificial Intelligence},
PAGES = {225--233},
VOLUME = {28},
}
%========= Optimal arc consistency algorithm (simple and effective, buy it!)
@INPROCEEDINGS{mohr88a,
DATE = {},
AUTHOR = {R. Mohr and G. Masini},
TITLE = {{Good Old Discrete Relaxation}},
KEYWORDS = {gac4, ac4, relaxation discrete, contrainte, erreur, relaxati
on, etiquetage},
YEAR = {1988},
ADDRESS = {Munich},
BOOKTITLE = {Proc. of the European Conference on Artificial Intelligence},
PAGES = {651--656}
}
%=== provide an extension of the optimal algorithm to n-ary constraints ====
and here a refrence of our work with short description to a vision application:
@INPROCEEDINGS{mohr88b,
DATE = {Tue Aug 29 1989},
AUTHOR = {R. Mohr and G. Masini},
TITLE = {{Running efficiently arc consistency}},
KEYWORDS = {consistence d'arc, complexite,},
YEAR = {1988},
EDITOR = {A. Sanfeliu, Th. Pavlidis},
PUBLISHER = {Springer Verlag, NATO-ASI series},
BOOKTITLE = {Syntactic and Structural Pattern Recognition},
PAGES = {217--231}
}
Roger
Roger MOHR Imag-Lifia, 46 av. Felix Viallet, 38031 Grenoble FRANCE
tel: (33) 76 57 46 53 -- fax : 76 57 46 02 email : mohr@rhea.imag.fr
secretariat : Daniele Herzog : 76 57 48 06
------------------------------
Date: Wed, 29 May 91 16:46:47 EDT
From: Bjorn Jawerth <bj@maxwell.math.scarolina.edu>
Subject: Available Research Position
A full-time (permanent) or Postdoc position is available immediately
within the Industrial Mathematics Initiative (IMI) at The University
of South Carolina, Columbia, SC.
Required Skills:
(1) Solid foundation in mathematics.
(2) Highly competent programming in "C".
(3) Familiarity with X-Windows programming environment.
Experience in the areas of:
(1) Signal processing or
(2) Computer vision
Research areas include the application of wavelets for image
compression, fast PDE solvers and computer-aided design (CAD).
Title: Senior Research Associate
Qualifications:
A Ph.D. degree is desired but candidates with an
M.S. degree and three to five years of relevant
experience are encouraged to apply.
Salary: Highly competitive.
Please submit resume and names of three references to:
Professor Bjorn Jawerth
Department of Mathematics
LeConte, Rm 307
University of South Carolina
Columbia, SC 29208
Phone: (803) 777-6218
E-mail: BJ@LOKI.MATH.SCAROLINA.EDU
------------------------------
Date: Fri, 24 May 91 09:39:07 BST
From: Adrian F Clark <alien@essex.ac.uk>
Subject: An International Standard for Image Processing and Interchange (long)
The following is an article I wrote for the v14n2 of the IAPR
Newsletter. I thought people might be interested in hearing what's
going on on the standards front.
How many readers have been given a tapeful of images for some
important work, only to find that no information has been supplied
about the tape format? In such cases, the effort involved in ensuring
that the tape has been read correctly and converted into one's own
file format is usually at least as great as the effort involved in
processing it. Equally irritating, how many times have you received a
program from someone, only to find it uses an image processing library
which you do not have? You might be surprised -- and hopefuly pleased --
to learn that many of these problems could disappear in the near
future due to work on an international standard for Image Processing
and Interchange (IPI).
Initial work has been proceeding for over two years now, but the
project really started in earnest at a recent International Standards
Organisation (ISO) meeting in Norwich, UK. The standardisation effort
is to take place under the aegis of ISO SC24 (`Computer Graphics and
Computer Imaging') and will be the first standard in this area to
cover both an Application Programmer's Interface (API) and an Image
Interchange Format (IIF). Both the API and the IIF will be based on a
Common Imaging Architecture (CIA). The time is not yet opportune to
discuss the content of the standard in detail, but an outline of some
aspects is appropriate. (However, the reader should be aware that
even these may change as the standard develops.)
Part I, the CIA, will describe a general model for the processing of
imagery (an `architectural' model), including aspects such as the
effects of regions in both source and destination images. The CIA
will also define models for image data-types and several non-image
data-types such as histograms. It will also indicate the
`specialisations' necessary to tie down the other parts of the
standard. For example, an image will be presented as an N-dimensional
object, but the current API will only support images of up to five
dimensions (three spatial, time and spectral).
Part II, the API, is based on the Programmer's Imaging Kernel (PIK)
being developed in the USA. This API will support most common
operations on images, of both the image-to-image (e.g., FFT) and the
image-to-non-image (e.g., histogram) varieties. Some facilities for
manipulating non-image data-types will also be included. Both image
and non-image data-types may be based on several basic representations
-- integer, floating-point, complex, etc. The API is designed to
support operations on pixel data, and explicitly excludes `image
understanding' operations, which typically involve non-pixel
representations.
There are likely to be several levels of conformance to the standard,
and the API in particular, but the mechanism for achieving this has
not yet been discussed. It is worth noting that a number of PIK and
PIK-like image processing packages are now available; these give a
reasonable idea of the functionality that the API will offer, though
the packages themselves will probably require significant modification
to conform to the standard.
The final part of the standard will describe the IIF. There are many
widely-used image formats already in existance, some of which are de
facto standards in particular applications areas (e.g., FITS in the
astronomical community) or are already standardised (there is an ANSI
image tape format standard for electronic pre-press). Of course,
recent standards from JPEG and MPEG, among others, involve some
compression, and the IIF is likely to incorporate their
recommendations.
At the abovementioned Norwich meeting, editors for the various parts
of the standard were appointed:
Adrian F. Clark, University of Essex, UK
William K. Pratt, Sun Microsystems, USA
Rainer Hofmann, Fraunhofer Group, Germany
and a timetable for the development of the standard was laid out.
Most of the standard will be written, distributed for comment, and
edited in 1991; trial implementations and further editiing will take
place during 1992-3. The final International Standard is timetabled
for early 1994. (Be warned, however, that such timetables almost
invariably slip somewhat.)
What will the impact of the standard be? Its effect will obviusly be
greater in some areas of interest to the IAPR than others: for
example, greater functionality is likely to be available to support
image restoration and reconstruction than computational vision, simply
because the former includes a larger proportion of pixel manipulation.
However, be assured of one thing: the standard will affect you,
particularly as add-on hardware which interfaces to the programmer via
the API becomes available. Hence, it is important to have as wide a
consideration of the drafts of the standard as possible. If you would
like to be involved, contact your national standards body or, if they
are unable to help you, the author of this article.
Dr 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: Fri, 24 May 91 12:49:47 -0400
From: "Baba Vemuri" <vemuri@scuba.cis.ufl.edu>
Subject: Travel, Registration and Hotel Info: Geometric Methods in CV Conf.
Travel, Registration and Hotel Information
for
GEOMETRIC METHODS IN COMPUTER VISION CONFERENCE (SPIE'91)
July 25-26, 1991
Location: Convention Center, Harbor Drive, San Diego, CA
The `Geometric Methods in Computer Vision,'' is going to be held in
San Diego at the convention center next to the Marriot on Harbor
drive on 25th and 26th of July 1991.
Room cost at the Marriot:
Single Double
City View $120 $140
Bay View $130 $150
There are other hotels around the vicinity. You may receive more
information on the same from SPIE directly by calling 206/676-3290
(ask for Marilyn Gorsuch who is the technical program coordinator) and
asking for the pre-registration and hotel information forms.
For travel arrangements:
The official airlines are:
USAIR
United Airlines
For reservations, call SPIE's official travel company, Conventions in
America for all discounted rates and lowest fares on all carriers.
Call 1-800-535-1492, and use the Group ID No. 493.
or call USAIR or United Airlines Directly and use the group ID number.
Registration fee:
Member Nonmember Student Student
Member Nonmember
Advance: $305 $355 $40 $50
On Site: $325 $375 $60 $70
For, advance registration material, please contact SPIE at
206/676-3290 (Pacific Time), Telex 46-7053, Telefax: 206/647-1445,
in Europe, Telephone 49-30-883 9507, Telefax: 49-30-882 2028.
------------------------------
Date: Thu, 23 May 1991 17:23:51 GMT
From: samackay@watcgl.waterloo.edu (Stephen MacKay)
Organization: National Research Council, Canada
Subject: Vision Interface '91 - Final Program
V I S I O N I N T E R F A C E '9 1 F I N A L P R O G R A M
University of Calgary
Calgary, Alberta, Canada
June 5-7, 1991
For Registration Information Please Contact:
University of Calgary Conference Office: (403) 220-4987
Direct questions regarding this program to Colin Archibald
(archibald@iit.nrc.ca) - do not reply to the poster.
June 5, 1991
Session 1 3-D Vision
Inferring Volumetric Descriptions from Slice Data
Emanuele Trucco, Dept. of Artificial Intelligence, University of
Edinburgh, Scotland
3-D Object Model Synthesis in a Monocular Imaging System
Mark Earnshaw and Andrew K. C. Wong, Dept. of Systems Design,
University of Waterloo
A Survey of 3-D Thinning Algorithms
Paul C. Kwok and Vishwa Ranjan, Dept. of Computer Science, University
of Calgary
Session 2 Robotics
Behaviour Based Assembly Experiments using Vision Sensing
Prabhas Chongstitvatana and Alistair Conkie, Dept. of Artificial
Intelligence, University of Edinburgh, Scotland
Robot Localization by Sensor Data Fusion
Goksin Bakir and Hong Zhang, Dept. of Computing Science, University of
Alberta
Evolving Speed Control in Mobile Robots: From Blindness to Kinetic Vision
J. G. Donnett and B. O. McGonigle, Dept. of Artificial Intelligence,
University of Edinburgh, Scotland
Invited Speaker
Real-time Systems for Tracking Articulated 3-D Objects
David Lowe, Dept. of Computer Science, University of British Columbia
Session 3 Model-based Scene Analysis
Delaying Committment in Dynamic Stereo Vision
John D. Lewis and Ian H. Witten, Dept. of Computer Science, University
of Calgary
Automatic Configuration of Medium-level Vision Routines Using Domain
Knowledge
Tilo Messer and Michael Schubert, FORWISS, FG Cognitive Systems,
Munchen, Germany
Experiments in Parallel Scene Labeling
Monroe Thomas and Xiaobo Li, Dept. of Computing Science, University of
Alberta
On Circles Recognition
Anca Tamas, Territorial Computing Center, Clug-Napoca, Romania
June 6, 1991
Session 4 Feature Extraction
Perceptual Grouping and Directionality Determination Using an
Electromagnetic Model
Thierry Pun, Michel Regamey, Philippe Narbel and Juan Mosig, Computer
Science Center, University of Geneva, Switzerland
Roof Edge Detection by Mathematical Morphology
Jin-Chang Cheng and Hon-Son Don,Dept. of Electrical Engineering, State
University of New York, Stoney Brook, NY, U.S.A.
Phase-Based Edge and Bar Detection
Zhengyan Wang and Michael Jenkin, Dept. of Computer Science, York
University
Random Sampling for Pose Determination and Refinement
Gerhard Roth and Martin Levine, Institute for Information Technology,
National Research Council
Invited Speaker
Robust High Breakdown Estimation and Consensus
Peter Meer, Dept. of Electrical and Computer Engineering, Rutgers
University
Session 5 Perception and Image Processing Architectures
Visuo-Tactual Coarseness Estimation Tasks 1. Experiments 2. Modeling
Isidore Rigoutsos, Robotics Lab. New York University, New York, NY,
U.S.A.
A Data Flow Digital Image Processing System and Its Real-Time Morphological
Algorithms
Ning Xu and Xiaoqing Ding, Dept. of Electronic Engineering, Tsinghua
University, Bejing, China
Architecture parallele basee sur des TMS320C30 pour la comparaison de
signaux
Pierre Frechette, Laboratoire Scribens et Les systemes electroniques
Matrox Ltee., Quebec, and Rejean Plamondon, Laboratoire Scribens et
ecole Polytechnique de Montreal
Session 6 Neural Networks For Image Analysis
ARisTotle: A Neural Net Architecture for the Auto-classification, Grouping
and Recognition of Partially Distorted Binary Images
D. Boulanger and D. Poussart, Laboratoire de Vision et Systemes
Numeriques, Department de genie electrique, Universite Laval
Multi-font Alpha-numeric Recognition using Multi-layer Neural Networks with
a Rejection Function
Keiji Yamada, C&C Information Technology Research Laboratories, NEC
Corporation, Kawasaki, Japan
June 7, 1991
Session 7 Biomedical Image Processing
Supervised Mitotic Index Scoring as a Tool in Cytotoxicity Studies
Maria Garza-Jinich, Claudia Rodriguez-Carranza, Gabriel Corkidi,
Ricardo Toledo, Regina Montero, Patricia Ostrosky-Wegman, Instituto de
Investigaciones en Matematicas Aplicadas y en Sistemas, UNAM, Mexico
Homology Mapping between an Atlas and a Biological Section
Sheng-Yih Guan and Bruce H. McCormick, Scientific Visualization Lab.,
Dept. of Computer Science, Texas A & M University, U.S.A.
Analysis of Retinal Images Using Mathematical Morphology
Piotr Jasiobedzki and Chris J. Taylor, Wolfson Image Analysis Unit,
Dept. of Medical Biophysics, University of Manchester, United Kingdom
Session 8 Texture and Image Analysis
Visual Textural Properties Based on Feature Frequency Matrices
H. C. Shen and C. Y. C. Bie, Dept. of Systems Design Engineering,
University of Waterloo
An Adaptive Convex Projection Method for Resolution Enhancement of
Tomographic Images
Shyh-shiaw Kuo and Richard J. Mammone, Dept. of Electrical and
Computer Engineering, Rutgers University, U.S.A.
Image Restoration by Using Adaptive Row Action Projection Method
Shyh-shiaw Kuo and Richard J. Mammone, Dept. of Electrical and
Computer Engineering, Rutgers University, U.S.A.
Invited Speaker
An Overview of Industrial Machine Vision in Canada
Laval Trembely, Matrox Ltd., Dorval, Quebec
Session 9 Applications
A Multi-Operator Approach for the Segmentation of 3-D Images of Dental
Imprints
Jean Cote, Denis Laurendeau and Denis Poussart, Computer Vision and
Digital Systems, Department of Electrical Engineering, Laval
University
Curvature Analysis for Recognition and Structural Verification of
Industrial Objects
Q. M. Wu and M. G. Rodd, Dept. of Electrical and Electronic Eng.,
University College of Swansea, United Kingdom
The Chirplet Transform: A Generalization of Gabor's Logon Transform
Steve Mann and Simon Haykin, Communications Research Lab., Dept. of
Electrical Engineering, McMaster University
A Multi-Surface Model of Sonar Range Sensing
David Wilkes, Greg Dudek, Michael Jenkin, and Evangelos Milios, Dept.
of Computer Science, University of Toronto
------------------------------
End of VISION-LIST digest 10.25
************************