dmocsny@uceng.UC.EDU (daniel mocsny) (01/09/89)
Several years ago I read about some image processing techniques for generating facial caricatures from facial photos. The researchers responsible expressed the geometry of a face with a few tens of variables. They then measured these variables for several hundred photographs of different faces, from which they developed composite male and female faces. Then for any given face, they computed how each of its variables differed from the corresponding value for the composite face. They multiplied each difference by some constant, and used the exaggerated valued to generate a caricature. An interesting result of the work occurred when they generated caricatures of famous faces. They found that test subjects could recognize the caricature faster than they could the original. Thus they concluded that our brain remembers a face by a process similar to computing how it differs from the average face. This may also be at the root of a common observation between two dissimilar ethnic groups that meet for the first time: each group thinks the members of the other group all look very similar. Perhaps some time must pass before the members of one group can generate a composite face for the other group. Are any comp.ai readers familiar with this work? If so, I would appreciate the original reference. Cheers, Dan Mocsny dmocsny@uceng.uc.edu
demers@beowulf.ucsd.edu (David E Demers) (01/10/89)
In article <564@uceng.UC.EDU> dmocsny@uceng.UC.EDU (daniel mocsny) writes: >Several years ago I read about some image processing techniques for >generating facial caricatures from facial photos. The researchers [...] > >Are any comp.ai readers familiar with this work? If so, I would >appreciate the original reference. > >Dan Mocsny If anyone does have this reference, please post. It sounds fascinating, and I'd like to read some more about it... Dave DeMers
keller@ficc.uu.net (Curtis Keller) (01/10/89)
In article <5730@sdcsvax.UUCP>, demers@beowulf.ucsd.edu (David E Demers) writes: > In article <564@uceng.UC.EDU> dmocsny@uceng.UC.EDU (daniel mocsny) writes: > >Several years ago I read about some image processing techniques for > >generating facial caricatures from facial photos. The researchers > [...] > >Are any comp.ai readers familiar with this work? If so, I would > >appreciate the original reference. > > > >Dan Mocsny > > If anyone does have this reference, please post. It sounds fascinating, > and I'd like to read some more about it... > > Dave DeMers I saved a copy of a Scientific American "Computer Recreations" article from ~ 3 years ago ( I did not write the issue date on the copy :-( ) by A.K. Dewdney. In the article, he describes the master's thesis of Susan Brennan at MIT. Susan (at the date of the article was a staff scientist at HP Labs in Palo Alto) developed a program to experiment with "her interest in the cognitive processes underlying face recognition." Curtis Keller Software Development Leader Ferranti International Controls Corporation 12808 W. Airport Blvd. Sugar Land, Tx 77478 UUCP: uunet!ficc!keller OR keller@ficc.uu.net Phone: (713) 274-5089
hwh@edai.ed.ac.uk (Howard Hughes) (01/10/89)
From article <564@uceng.UC.EDU>, by dmocsny@uceng.UC.EDU (daniel mocsny): > Several years ago I read about some image processing techniques for > generating facial caricatures from facial photos........... [More deleted] I'd like this reference too if anyone out there has it. A.
chuck@virgil.UUCP (Chuck Cartledge) (01/11/89)
In article <564@uceng.UC.EDU>, dmocsny@uceng.UC.EDU (daniel mocsny) writes: > Several years ago I read about some image processing techniques for > generating facial caricatures from facial photos. > ... [Stuff deleted] ... > Are any comp.ai readers familiar with this work? If so, I would > appreciate the original reference. > While I don't have a copy of the original articles, I have run across a writeup that may have the information that you are after. A. K. Dewdney (Scientific American) has collected many of his articles into a very easily read and fun book called "The Armchair Universe, An Exploration of Computer Worlds" (published by Freeman). In the book he discusses a program called FACEBENDER. The article has the (X,Y) coordinates of major facial characteristics, and talks about how the data can be manipulated to generate various caricatures. He in turn references the following: Brennan, Susan E."Caricature Generator: The Dynamic Exaggeration of Faces by Computer." Leonardo 18, no. 3 (1985): 170-178. McDermott. Jeanne. "Face to Face: It's the Expression that Bears the Message." Simthsonian, March, 1986, 112-123. Hope these help. -- Chuck Cartledge (804)498-1012 chuck@virgil.UUCP EDO Coporation (804)424-1004 Government Systems Division 814 Greenbrier Circle, Chesapeake Va. 23320
holmer@rigel (Bruce K. Holmer) (01/12/89)
[] The exact reference is Scientific American, October 1986, p. 20.
shah@ucf-cs.ucf.edu (01/15/89)
There was an article in Scientific American in 1986 (or 1987) regarding this kind of work, which was based on a master thesis done at MIT. They actually gave a list of coordinates of a default face. I think it was not a regular article, but appeared in "Computer Recreation" sort of section. Mubarak Shah UCF, Orlando
bph@buengc.BU.EDU (Blair P. Houghton) (01/19/89)
In article <22200002@ucf-cs.ucf.edu> shah@ucf-cs.ucf.edu writes: > >There was an article in Scientific American in 1986 (or 1987) regarding this >kind of work, which was based on a master thesis done at MIT. They >actually gave a list of coordinates of a default face. I like that. "You have a face like the default." --Blair "Kind of catchy..."