Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 10 Issue 51
VISION-LIST Digest Mon Dec 02 10:59:35 PDT 91 Volume 10 : Issue 51
- 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:
LCD shutter glasses
Access to PERCEPTION magazine?
Segmentation of moving animals
Email addresses needed
Looking for Dr. S.P.Kim account
Re: POPI/pico source for Mac
Need some Info. on Neocognitron.
PostDoc Position starting April 15, 1992
Cognitive Science at Birmingham
CFP: Neural/Stochastic/Image/Signal
CFP: Associative Memory Networks and Applications
Society for Machines and Mentality Announcement
Workshop on Self-Organization and Unsupervised Learning in Vision
----------------------------------------------------------------------
Date: 25 Nov 91 08:43:52 GMT
From: antonio@qualcomm.com (Franklin Antonio)
Organization: Qualcomm, Inc., San Diego, CA
Subject: LCD shutter glasses
Where does one get info about LCD shutter glasses (used for viewing 3D
images on computer screens) ? Who makes 'em, how much they cost, etc.
Are there some that work with IBM PCs, and ordinary VGA boards?
------------------------------
Date: Thu, 28 Nov 91 15:56:06 +0100
From: broggi@prsun0in.cineca.it (Alberto Broggi)
Subject: Access to PERCEPTION magazine?
Do you have any access to a Computer Vision magazine called PERCEPTION ?
If so, can you take vol.20 n.1 from your library and contact me via e-mail ?
I'm writing my curriculum vitae and I THINK i have an abstract published
here, but I CANNOT verify!
my e-mail address is broggi@prsun0in.cineca.it
Thanks, Alberto
Alberto Broggi - Dip. Ing. dell'Informazione, V.le delle Scienze - PARMA, IT
E-Mail broggi@prsun0in.cineca.it - Ph. +39-521-580722 - Fax +39-521-580723
------------------------------
Date: Wed, 27 Nov 91 12:30 GMT
From: MARCHANT%NIAEA.AFRC.AC.UK@vtvm2.cc.vt.edu
Subject: Segmentation of moving animals
SEGMENTATION USING MOTION
I want to segment animals ( which may have a textured surface )
in natural scenes ( i.e. background fairly cluttered ). The an-
imals can be relied on to move. I need a fairly accurate boundary.
What previous work should I be aware of?
------------------------------
Date: Tue, 26 Nov 91 10:55:37 +0800
From: Geoff West <geoff@cutmcvax.cs.curtin.edu.au>
Subject: Email addresses needed
I am trying to reach one of the following three vision researchers:
G. Bongiovanni, P. Crescenzi or C. Guerra at Rome University,Italy.
Anyone know of their email addresses?
Thanks - Geoff West email: geoff@cutmcvax.cs.curtin.edu.au
------------------------------
Date: Mon, 2 Dec 1991 00:28:51 GMT
From: thanon@ccu1.aukuni.ac.nz
Organization: University of Auckland, New Zealand.
Subject: Looking for Dr. S.P.Kim account
I'm looking for e-mail address of Dr.S.P. Kim, Dept. Elec. Eng. and Comp. Sci.,
Polytechnic University, New York. If anyone know it please email to me.
Thanks in advance,
thanon@ccu1.aukuni.ac.nz
------------------------------
Date: Tue, 26 Nov 91 21:35:37 PDT
From: Greg Heil <gheil@dgi0.bbn.com>
Subject: Re: POPI/pico source for Mac
} I am trying to locate a Public domain implementation of
} POPI for the Mac. I have found pico-20.hqx by John Peterson
} at Apple but it is (apparently) w/o sources.
} I need a mac version to which i can add 32b color and the
} ability to import other formats
I've never received a Mac graphics driver for our implementation of popi,
but you're welcome to modify the sources yourself, and I'll happily add
it to the distribution.
The latest version of popi (v3.1 at patchlevel #5) is available from the
automatic mail archive server. Send nine messages to
rb-archive-server@Aus.Sun.COM, containing the line:
send popi partn
where n=1-9. Let me know if you'd like to be added to the popi mailing
list. It'll keep you informed about future patches.
------------------------------
Date: 27 Nov 91 17:55:31 GMT
From: vg@raybans.cis.ufl.edu (V. Girish)
Organization: UF CIS Dept.
Subject: Need some Info. on Neocognitron.
Hi,
I am working in the area of handwritten-char Recognition. Earlier I used the
nn of Barry.E.Kalman which used the conjugate-gradient method. I would like
to test my data set with another nn just for comparision. I know very little
of what goes inside nnets. Today, I was going thro "Handbook of neural
computing Applications" by Alianna Maren et al. where they had suggested use
of "NEOCOGNITRON" by Kunihiko Fukushima for handwritten character recognition.
They say that it handles rotated,scaled,distorted characters very well. Can
somebody suggest how effective the nn is? Further, I would like to know if the
software is available by ftp in public domain? Also, I would like to know if
I can find a bigger set of data of handwritten characters to train the nn?
My e-mail address on the internet is:vg@mosquito.cis.ufl.edu.
Thanks a lot,
Girish.
------------------------------
Date: Wed, 27 Nov 91 00:05:28 EST
From: kprasad@caip.rutgers.edu (K. Venkatesh Prasad)
Subject: PostDoc Position starting April 15, 1992
Laboratory of Vision Research, Rutgers University
POSTDOCTORAL FELLOWSHIP
Tenable for 1.5 - 2 years (or more) in the Laboratory of Vision
Research at Rutgers University to start Apr. 15, 1992 with Prof.
Bela Julesz. The project involves human visual perception of
stereopsis, motion, or texture with emphasis on the role focal
attention. Problems of perceptual constancies and learning are
of interest too. Experience in visual psychophysics is required.
Some mathematical sophistication and familiarity with C programming
is an asset. Those who think THAT THEY ARE CREATIVE AND BELIEVE
THAT DOING SCIENCE IS FUN, AND LIKE TO WORK ON STRATEGIC PROBLEMS
are asked to apply. Applications should be sent to Rutgers (*),
or between Jan. 10 - Apr. 10 1992 to Caltech (**), where Prof. Julesz
usually is during this period.
(*) Rutgers University
Laboratory of Vision Research
41 Gordon Road
PISCATAWAY NJ 08854-5930
(**) Division of Biology, 216-76
CALTECH
PASADENA CA 91125
------------------------------
Date: Fri, 29 Nov 91 15:10:52 GMT
From: D.M.Peterson@computer-science.birmingham.ac.uk
Subject: Cognitive Science at Birmingham
University of Birmingham
Graduate Studies in COGNITIVE SCIENCE
The Cognitive Science Research Centre at the University of Birmingham
comprises staff from the Departments/Schools of Psychology, Computer
Science, Philosophy and English, and supports teaching and research in
the inter-disciplinary investigation of mind and cognition. The Centre
offers both MSc and PhD programmes.
MSc in Cognitive Science
The MSc programme is a 12 month conversion course, including a 4 month
supervised project. The course places a particular stress on the
relation between biological and computational architectures.
Compulsory courses: AI Programming, Overview of Cognitive
Science, Knowledge Representation Inference and Expert Systems,
General Linguistics, Human Information Processing, Structures for Data
and Knowledge, Philosophical Questions in Cognitive Science,
Human-Computer Interaction, Biological and Computational
Architectures, The Computer and the Mind, Current Issues in Cognitive
Science.
Option courses: Artificial and Natural Perceptual Systems,
Speech and Natural Language, Parallel Distributed Processing.
It is expected that students will have a good first degree ---
psychology, computing, philosophy or linguistics being especially
relevant.
Funding is available through SERC and HTNT.
PhD in Cognitive Science
For 1992 studentships are expected for PhD level research into a range
of topics including:
o computational modelling of emotion
o computational modelling of cognition
o interface design
o computational and psychophysical approaches to vision
Computing Facilities
Students have access to ample computing facilities, including networks
of Hewlett-Packard, Sun and Sparc workstations in the Schools of Computer
Science and Psychology.
Contact
For further details, contact: The Admissions Tutor, Cognitive Science,
School of Psychology, University of Birmingham, PO Box 363, Edgbaston,
Birmingham B15 2TT, UK.
Phone: (021) 414 3683
Email: cogsci@bham.ac.uk
------------------------------
Date: Sat, 30 Nov 91 15:38:12 -0500
From: Jonathan Marshall <marshall@cs.unc.edu>
Subject: Call for Papers: Neural/Stochastic/Image/Signal
Announcement and Call for Papers
NEURAL AND STOCHASTIC METHODS IN IMAGE AND SIGNAL PROCESSING
Part of SPIE's 1992 International Symposium on Optical Applied Science
and Engineering <> 19-24 July 1992 <> San Diego Marriott Hotel and
Marina and San Diego Convention Center <> San Diego, California, USA
Conference Chair: Su-Shing Chen, National Science Foundation
Program Committee: Griff Bilbro, North Carolina State Univ.
Peter C. Doerschuk, Purdue Univ.
Ibrahim M. Elfadel, Massachusetts Inst. of Tech.
B.R. Frieden, Univ. of Arizona
Seth Hutchinson, Univ. of Illinois
Jonathan A. Marshall, Univ. of North Carolina/CH
Arturo A. Rodriguez, IBM Corp.
Guna Seetharaman, Univ. Southwestern Louisiana
Silvia S. Shen, Lockheed Palo Alto Res. Lab
Xinhua Zhauang, Univ. of Missouri/Columbia
In a real-world environment, images and signals are usually subject to
noise, and uncertainty prevails in mathematical models. A variety of
methodologies have been developed for the processing and understanding
of such images and signals. Some are stochastic, some are biological-
ly motivated, and others are of a different nature. This conference
will bring together researchers of various backgrounds, including
neural networks, markov random fields, simulated annealing, genetic
algorithms, probabilistic reasoning, stochastic processes, fuzzy rea-
soning, and other reasoning schemes with uncertainty.
Papers are solicited on the following and related topics:
<> image processing <> biologically motivated perception
<> signal processing <> simulated annealing algorithms
<> computer vision <> statistical pattern recognition
<> evidential reasoning <> bayesian inference networks
<> stochastic methods <> markov random fields
<> neural networks <> genetic algorithms
<> fuzzy reasoning
| Abstract Due Date: 23 December 1991* |
| Manuscript Due Date: 22 June 1992 |
| |
| *Note: Late abstract submissions may be considered, subject to |
| program time availability and chair's approval. |
Please limit your abstract to one page. Include title of abstract,
authors' full names, addresses, and telephone/fax/telex numbers and
e-mail addresses. List principal author first. Indicate for which
conference (Neural and Stochastic Methods in Image and Signal
Processing/Chen) within the Symposium (San Diego '92) the abstract is
intended, and whether the presentation is oral or a poster. Mark the
abstract "Response to electronic announcement M." The abstract
should be 200 words typed on white paper and should contain enough
detail to clearly convey the approach and the results of the research.
Government and company clearances to present and publish should be
final at the time of submission. Include, on the same page, a brief
(50-100 words) biographical sketch. Send four (4) copies of your
abstract by 23 December 1991 to: (Mailing address) San Diego '92,
SPIE, P.O. Box 10, Bellingham, WA 98227-0010, USA. (Shipping address)
1000 20th St., Bellingham, WA 98225, USA. (Fax) 206-647-1445.
Condition of Acceptance: Authors are expected to secure travel and
accommodation funding, independent of SPIE, through their sponsoring
organizations before submitting abstracts.
Placement: Submissions may be placed in an oral or poster session at
the chair's discretion. Applicants will be notified of acceptance by
23 March 1992.
Proceedings: These meetings will result in published Proceedings that
can be ordered through the Advance Program. Manuscripts are required
of all accepted applicants and must be submitted in English by 22 June
1992 on SPIE-provided paper. Copyright to the manuscript is expected
to be released for publication in the conference Proceedings.
Paper Review: Commercial papers, descriptions of papers with no
research content, and papers where supporting data or a technical
description cannot be given for proprietary reasons will not be
accepted for presentation in this symposium. To assure a high-quality
conference, all abstracts and Proceedings papers will be reviewed by
the Conference Chairs for technical merit and content.
Oral Presentation: Each author is generally allowed 20 minutes plus a
5-minute discussion period. SPIE will provide the following media
equipment free of charge: 35 mm carousel slide projectors, overhead
projectors, and electric pointers. Additional equipment may be
arranged by SPIE at the speaker's expense.
Author Benefits: An author or co-author who chooses to attend the
conference will be accorded a reduced-rate registration fee. Included
with fee payment are a copy of the Proceedings in which the author's
paper appears, a complimentary one-year nonvoting membership in SPIE
(if never before a member), and other special benefits.
In North America: SPIE, P.O. Box 10, Bellingham, WA 98227-0010, USA
Telephone 206-676-3290 (Pacific time),
Telex 46-7053, Fax 206-647-1445,
Opto-Link 206-733-2998, E-mail spie@nessie.wwu.edu
CompuServe 71630,2177
Shipping Address: 1000 20th Street, Bellingham, WA 98225, USA
In Europe: Xantener Strasse 22, D 1000 Berlin 15, FR Germany
Telephone 49-30-883-9507, Fax 49-30-882-2028,
Telex 181 479 speco d
In the Far East, c/o O.T.O. Research Corporation, Takeuchi Building,
Australia, and 1-34-12 Takatanobaba, Shinjuku-ku, Tokyo 160, Japan
New Zealand: Telephone 03/3208-7821, Fax 03/3200-2889,
Telex 232 4119 otores j
------------------------------
Date: Tue, 26 Nov 91 22:08:49 EST
From: aar@vnet.ibm.com
Subject: CFP: Associative Memory Networks and Applications
CALL FOR PAPERS
Session Theme
on
ASSOCIATIVE MEMORY NETWORKS AND APPLICATIONS
A special session on this theme has been planned for the upcoming
Neural and Stochastic Methods in Image and Signal Processing
conference of SPIE's 1992 International Symposium on Optical
Applied Science and Engineering. Neural network-based
associative memories have been shown to be successful in many
areas of image and signal processing. The goal of this session
will be to address challenges posed by practical problems and to
present successful solutions that employ associative memories.
Papers are solicited in all areas of neural network-based
associative memories, including, but not limited to:
- Linear and dynamic associative memories
- Higher-order networks
- Information capacity
- Learning and synthesis
- Signal and image processing applications of associative memories
including image segmentation and automated inspection
- Application to information storage and retrieval problems
Papers describing successful applications, case studies, and
theoretical expositions will be also welcomed.
The Associative Memory Networks and Applications Session is being
organized by:
S. I. Sudharsanan and Arturo A. Rodriguez
IBM Corporation
Conference Chair: Su-Shing Chen, National Science Foundation
Program Committee:
Griff Bilbro, North Carolina State Univ.
Peter C. Doerschuk, Purdue Univ.
Ibrahim M. Elfadel, Massachusettes Inst. Tech.
B. R. Frieden, Univ. of Arizona
Seth Hutchinson, Univ. Illinois
Jonathan Marshall, Univ. North Carolina/Chapel Hill
Arturo A. Rodriguez, IBM Corporation
Guna Seetharaman, Univ. Southwestern Louisiana
Silvia S. Shen, Lockheed Palo Alto Research Lab
Xinhua Zhuang, Univ. Missouri/Columbia
The conference will be held on July 19-24, 1992 at the San Diego
Marriott Hotel and Marina and San Diego Convention Center, San
Diego, California, USA. The deadline for paper submissions is
December 23, 1991. Four copies of a 500 word extended summary
(or greater) should be submitted to:
SPIE San Diego '92
Neural and Stochastic Methods in Image and Signal Processing
(Theme Session on Associative Memory Networks and Applications)
P.O. Box 10
Bellingham, WA 98227-0010 , USA
Shipping address: 1000 20th St., Bellingham, WA 98225
Telephone: (206) 676-3290
Telex: 46-7053
Telefax: (206) 647-1445
OPTO-LINK (206) 733-2998
Please include the following information:
1. Title of Paper
2. Authors' full names and affiliations
(Please include complete address, telephone/telex/telefax
number, and e-mail address).
3. A sentence stating that the paper is intended for the
Neural and Stochastic Methods in Image and Signal
Processing conference (Theme Session on Associative
Memory Networks and Applications)
4. Text of summary (greater than 500 words). Clearly
describe the approach and the results of the work.
5. Brief Author Biography (100 words)
Please also send an e-mail to aar@vnet.ibm.com and
sudha@bcrvmpc2.vnet.ibm.com if you plan to submit a paper for
this special session. Authors will be notified of acceptance by
23 March, 1992.
------------------------------
Date: 25 Nov 91 11:27:14 EST
From: James.H.Moor@dartmouth.edu
Subject: Society for Machines and Mentality Announcement
The Society for Machines and Mentality will hold its first annual
meeting at the Eastern Division meeting of the American Philosophical
Association in the Marriott Marquis Hotel, New York City, December 28, 1991
from 5:15 to 7:15 P.M. Professor William Bechtel will deliver an address
entitled "Currents in Connectionism" which will be followed by a reception in
honor of the journal MINDS AND MACHINES and its editor James H. Fetzer.
Questions about the society should be addressed to
William Rapaport, President, (rapaport @ cs.buffalo.edu)
David Cole, Vice-President, (dcole @ ub.d.umn.edu)
James Moor, Treasurer, (James.Moor @ Dartmouth.edu)
Membership fees for 1992 are due in December. The membership fee
continues to be only $5 per year. By special arrangement with Kluwer
Publishers the society is able to offer its members subscriptions to MINDS AND
MACHINES, an International Journal for Artificial Intelligence, Philosophy,
and Cognitive Science, at a reduced rate of $45 per year. The journal is
currently published with one volume of four issues per year, which appears in
February, May, August, and November. Back issues for 1991 are available from
the publisher.
For a 1992 membership in the Society for Machines and Mentality and a
one year subscription to MINDS AND MACHINES, please send a check for $50 (or
for membership only $5) payable to "Society for Machines and Mentality" to
James H. Moor, Treasurer
Society for Machines and Mentality
Department of Philosophy
Dartmouth College
6035 Thornton Hall
Hanover, NH 03755-3592
U.S.A.
Please feel free to distribute this announcement to anyone else who might
like to join our society and subscribe to the journal. (New members should
include their name, address, and e-mail address.)
Yours truly,
Jim Moor
------------------------------
Date: 29 Nov 91 23:15:42 GMT
From: marshall@marshall.cs.unc.edu (Jonathan Marshall)
Organization: University of North Carolina, Chapel Hill
Subject: Workshop on Self-Organization and Unsupervised Learning in Vision
PROGRAM: NIPS*91 Post-Conference Workshop on
SELF-ORGANIZATION AND UNSUPERVISED LEARNING IN VISION
December 6-7, 1991 in Vail, Colorado
Workshop Chair: Jonathan A. Marshall
Department of Computer Science, CB 3175, Sitterson Hall
University of North Carolina, Chapel Hill, NC 27599-3175, U.S.A.
919-962-1887, marshall@cs.unc.edu
Substantial neurophysiological and psychophysical evidence suggests
that visual experience guides or directs the formation of much of the
fine structure of animal visual systems. Simple unsupervised learning
procedures (e.g., Hebbian rules) using winner-take-all or local
k-winner networks have been applied with moderate success to show how
visual experience can guide the self-organization of visual mechanisms
sensitive to low-level attributes like orientation, contrast, color,
stereo disparity, and motion. However, such simple networks lack the
more sophisticated capabilities needed to demonstrate self-organized
development of higher-level visual mechanisms for segmentation,
grouping/binding, selective attention, representation of occluded or
amodal visual features, resolution of uncertainty, generalization,
context-sensitivity, and invariant object recognition.
A variety of enhancements to the simple Hebbian model have been
proposed. These include anti-Hebbian rules, maximization of mutual
information, oscillatory interactions, intraneuronal interactions,
steerable receptive fields, pre- vs. post-synaptic learning rules,
covariance rules, addition of behavioral (motor) information, and
attentional gating. Are these extensions to unsupervised learning
sufficiently powerful to model the important aspects of
neurophysiological development of higher-level visual functions?
Some of the specific questions that the workshop will address are:
o Does our visual environment provide enough information to direct
the formation of higher-level visual processing mechanisms?
o What kinds of information (e.g., correlations, constraints,
coherence, and affordances) can be discovered in our visual world,
using unsupervised learning?
o Can such higher-level visual processing mechanisms be formed by
unsupervised learning? Or is it necessary to appeal to external
mechanisms such as evolution (genetic algorithms)?
o Are there further enhancements that can be made to improve the
performance and capabilities of unsupervised learning rules for
vision?
o What neurophysiological evidence is available regarding these
possible enhancements to models of unsupervised learning?
o What aspects of the development of visual systems must be
genetically pre-wired, and what aspects can be guided or directed
by visual experience?
o How is the output of an unsupervised network stage used in
subsequent stages of processing?
o How can behaviorally relevant (sensorimotor) criteria become
incorporated into visual processing mechanisms, using unsupervised
learning?
This 2-day informal workshop brings together researchers in visual
neuroscience, visual psychophysics, and neural network modeling.
Invited speakers from these communities will briefly discuss their
views and results on relevant topics. In discussion periods, we will
examine and compare these results in detail.
The workshop topic is crucial to our understanding of how animal
visual systems got the way they are. By addressing this issue
head-on, we may come to understand better the factors that shape the
structure of animal visual systems, and we may become able to build
better computational models of the neurophysiological processes
underlying vision.
[ PROGRAM DELETED. phil... ]
------------------------------
End of VISION-LIST digest 10.51
************************
