Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 11 Issue 41
VISION-LIST Digest Wed Nov 25 16:03:18 PDT 92 Volume 11 : Issue 41
- 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 FTP.ADS.COM
Today's Topics:
seeking collaboration, machine learning in vision
Survey of Stereo Matching
SHAPE NUMBERS for closed or open boundaries
Handling Interlaced Video
Color database
Inspection of Surface Defects
Position Available: Research Associate
CVNet- PostDoc Position
CFP Hough transform Colloquium
CFP
yet another one
----------------------------------------------------------------------
X400-Received: by mta chx400.switch.ch in /PRMD=switch/ADMD=arcom/C=CH/;
Relayed; Wed, 25 Nov 1992 17:55:19 +0100
X400-Received: by /PRMD=SWITCH/ADMD=ARCOM/C=CH/; Relayed;
Wed, 25 Nov 1992 17:55:16 +0100
X400-Received: by /PRMD=switch/ADMD=arcom/C=ch/; Relayed;
Wed, 25 Nov 1992 17:55:12 +0100
Date: Wed, 25 Nov 1992 17:55:12 +0100
X400-Originator: chachere@cui.unige.ch
X400-Recipients: Vision-List@ADS.com
X400-Mts-Identifier: [/PRMD=switch/ADMD=arcom/C=ch/;921125175512]
X400-Content-Type: P2-1984 (2)
Content-Identifier: 652
From: Lawrence Chachere <chachere@cui.unige.ch>
Subject: seeking collaboration, machine learning in vision
Status: R
I am looking for contacts who are doing research similar to mine
in machine learning for computer vision. My research involves
determination of characteristic features for object recognition.
For the past year and a half I have been developing a a knowledge-based
approach, using natural language as the knowledge source to determine
which attributes to extract from an image. One of the major goals
is to enable learning on small numbers of examples for each target
class. The majority of existing machine learning programs rely on
large numbers of training examples which is atypical of human learning.
Lawrence Chachere
chachere@cui.unige.ch
------------------------------
Date: Wed, 25 Nov 92 16:35:29 EST
From: suchi@pollux.cs.uga.edu (Suchi Bhandarkar)
Subject: Survey of Stereo Matching
Status: R
Could some one give the reference to a good and recent survey article
or articles that deal(s) with the problem of 3-D surface reconstruction
from binocular (or trinocular) stereo. Please reply to suchi@pollux.cs.uga.edu
Thanks
Suchi Bhandarkar
------------------------------
(5.65c/IDA-1.3.5 for uunet!comp-ai-vision); Tue, 24 Nov 1992 08:35:33 -0800
Path: ibarroda
From: ibarroda@sol.UVic.CA (Ian Barrodale)
Subject: SHAPE NUMBERS for closed or open boundaries
Nntp-Posting-Host: csr.uvic.ca
Organization: University of Victoria
Date: 24 Nov 92 16:34:18 GMT
Status: R
Q: Has anyone used ''SHAPE NUMBERS'' to measure differences in
closed or open boundaries? SHAPE NUMBERS are described in 'How
to describe pure form and how to measure differences in shapes
using shape numbers', by Ernesto Bribiesca and Adolfo Guzman,
Pattern Recognition Vol 12, pp. 101-112, 1980. Is there a more
recent reference to the use of this technique than the 1980 paper?
------------------------------
Date: Tue, 24 Nov 92 10:50:04 PST
From: wilbur@constitution.ucr.edu (Wilhelm Burger)
Subject: Handling Interlaced Video
Status: R
Frame interlacing is a traditional nuisance when working with standard
TV motion sequences, but it's apparently hardly ever addressed in the
motion analysis literature (?). I was wondering if someone on this list
could give an answer to the following:
(1) Are there any CCTV systems (cameras, VCRs, monitors) that support
non-interlaced video at full TV resolution?
(2) What is the "standard" method to remove interlace flicker from
still images used by professional TV studios (or in good VCRs)?
Any additional hints (references) are appreciated.
W. Burger
College of Engineering
Univ. of California
Riverside, CA 92521-0425
Tel: (714) 787 2299
Email: wilbur@constitution.ucr.edu
------------------------------
Subject: Color database
Date: Wed, 25 Nov 92 08:08:31 +0100
From: Reiner Lenz <reiner@isy.liu.se>
Status: R
Has someone a database with spectral reflectance data of Munsell color chips?
Perhaps with the description in other systems like RGB, IHS, YIQ?
---
"Kleinphi macht auch Mist"
Reiner Lenz | Dept. EE. |
| Linkoeping University | email: reiner@isy.liu.se
| S-58183 Linkoeping/Sweden |
------------------------------
Subject: Inspection of Surface Defects
Date: Wed, 25 Nov 92 15:01:46 +0100
From: herbert@efads1.tuwien.ac.at
X-Mts: smtp
Status: R
Hello,
I have just started my doctoral thesis. The topic is Automatic
Inspection of Surface Defects on Metals (e.g. cast metals).
I am looking for paper references about this topic - segmentation
techniques, connected component labeling algorithms, already existing
applications...
Any suggestions are also welcome.
Thank you, Herbert
Herbert Hufnagl
Technical University of Vienna
Institute of Flexible Automation
Gusshausstr. 27-29/361
A-1040 Vienna/AUSTRIA
Tel: ++43/1/58801/3681
Fax: ++43/1/5055983
Email: herbert@efads1.tuwien.ac.at
------------------------------
Date: Wed, 25 Nov 92 14:01:51 EST
From: dwj@research.nj.nec.com (David Jacobs)
Subject: Position Available: Research Associate
Status: R
I would like to post the following ad on the vision list.
Thank you,
David Jacobs
POSITION AVAILABLE: RESEARCH ASSOCIATE
The NEC Research Institute in Princeton, NJ has an immediate opening
for a Research Associate in the area of computer vision. NECI was
established in 1989 to conduct long range fundamental research in the
physical and computer sciences.
We are looking for someone to work on research projects in such
areas of computer vision as: perceptual organization, motion
understanding and object recognition. The type of contributions
expected of the research associate will depend on their background,
level of experience, and interests. However, we hope to find someone
who can contribute to the development and testing of vision
algorithms, and who is capable of initiating new lines of research, or
of suggesting new approaches to problems arising in our current work.
While a background in computer vision is desirable for this
position, we are also interested in applicants with expertise in
related fields, such as computational geometry, AI, or psychology, as
long as such applicants have experience and an interest in
implementing experimental computational systems. Software will be
developed using C and LISP on Unix workstations.
Interested applicants should send resumes, with references, to:
David Jacobs
NEC Research Institute
4 Independence Way
Princeton, NJ 08540
(email) dwj@research.nj.nec.com
(fax) (609) 951-2482
------------------------------
Date: Wed, 25 Nov 92 9:52:26 PST
From: pkahn@akbar.teleos.com
Status: R
Date: Wed, 25 Nov 1992 07:11:57 -0500
From: cvnet%yorkvm1.bitnet@utcs.utoronto.ca
Subject: CVNet- PostDoc Position
Status: R
Postdoctoral Position Available in Texture and Motion Processing
(visual psychophysics, mathematical modelling, primate studies)
Contact: Jonathan Victor
Department of Neurology and Neuroscience
Cornell University Medical College
1300 York Avenue
New York, NY 10021
email: victor@rockvax.bitnet
voice: 212 746 2343
fax: 212 746 8532
Term: 12 to 18 months, beginning 1/1/93 or 1/7/93
Salary: negotiable; subsidized housing available
Please send statement of research interests,
term desired, salary/housing requirements,
and names of three references.
------------------------------
From: Farzin Deravi <eederavi@pyr.swan.ac.uk>
Date: Mon, 23 Nov 92 12:49:03 GMT
Subject: CFP Hough transform Colloquium
Status: R
Call for Papers
Institution of Electrical Engineers
Colloquium on
HOUGH TRANSFORMS
7 May 1993
IEE, Savoy Place, London
IEE Professional Group E4 (Image Processing and Vision) are organizing a
colloquium on "Hough Transforms" to be held at Savoy Place on Friday, 7
May 1993.
Contributions are invited from those engaged in research into Hough
transforms and related techniques for pattern recognition in digital
images and other multi-dimensional signals. Significant advances have
been made in this area in recent years, with the development of fast
and efficient algorithms, parallel hardware implementations and novel
applications. The colloquium aims to bring together researchers active
in all of the above three areas of algorithms, architecture and
applications.
Those wishing to present a paper at the colloquium are asked to submit
a 200 word abstract to the Programme Co-ordinator:
Dr F Deravi
Department of Electrical and Electronic Engineering
University of Wales
Swansea SA2 8PP
Wales, UK
Tel: 0792 295583
Fax: 0792 295686
Email: eederavi@pyr.swan.ac.uk
Please ensure all abstracts are received by Wednesday, 10 March 1993.
------------------------------
Date: Wed, 25 Nov 92 11:06:38 PST
From: pkahn@akbar.teleos.com
Subject: CFP
Status: R
Date: Wed, 25 Nov 92 10:14:40 -0800
From: Tod Levitt <levitt@flamingo.Stanford.EDU>
Subject: yet another one
Status: R
From heckerma@CS.UCLA.EDU Tue Nov 24 10:42:22 1992
Return-Path: <heckerma@CS.UCLA.EDU>
Received: from Lanai.CS.UCLA.EDU by ads.com (5.65+/1.34v1.3)
Received: by lanai.cs.ucla.edu
Tue, 24 Nov 92 10:42:15 -0800
Date: Tue, 24 Nov 92 10:42:15 PST
From: David Heckerman <heckerma@CS.UCLA.EDU>
Message-Id: <921124.184215z.24028.heckerma@lanai.cs.ucla.edu>
To: levitt@ads.com
Subject: call for papers
Status: RO
Todd,
I just noticed that you are moderator of VISION-LIST@ADS.COM.
If you think it's appropriate, please distribute the UAI
call for papers. It was great to see you and your work
in St. Louis.
David
To: uai-list
Subject: Call for Papers
-------
NINTH ANNUAL CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE
July 9-11, 1993, Washington D.C.
CALL FOR PAPERS
The ninth annual Conference on Uncertainty in Artificial Intelligence will be
devoted to methods for reasoning under uncertainty as applied to problems in
artificial intelligence. The conference's scope covers the full range of
approaches to automated and interactive reasoning and decision making under
uncertainty, including both qualitative and numeric methods.
We seek papers on fundamental theoretical issues, on computational techniques
for uncertain reasoning, and on the foundations of alternative paradigms of
uncertain reasoning. Topics of interest include:
- Foundations of uncertainty concepts
- Representations of uncertain knowledge and their semantics
- Knowledge acquisition
- Construction of uncertainty models from data
- Uncertainty in machine learning
- Automated planning and decision making under uncertainty
- Algorithms for uncertain inference
- Pooling of uncertain evidence
- Belief updating and inconsistency handling in uncertain knowledge bases
- Explanation and summarization of uncertain information
- Control of reasoning and real-time architectures
This year, we hope to attract more contributions that emphasize real-world
applications of uncertain reasoning. Questions of particular interest
include:
- Why was it necessary to represent uncertainty in your domain?
- What kind of uncertainties does your application address?
- Why did you decide to use your particular uncertainty formalism?
- What theoretical problems, if any, did you encounter?
- What practical problems did you encounter?
- Did users of your system find the results or recommendations useful?
- Did the introduction of your system lead to improvements in reasoning
or decision making?
- What methods were used to validate the effectiveness of the systems?
Papers will be carefully refereed for originality, significance, technical
soundness, and clarity of exposition. Papers may be accepted for presentation
in plenary or poster sessions. Some key applications oriented work may be
presented both in a plenary session and in a poster session where more
technical details can be discussed. All accepted papers will be included in
the published proceedings. Outstanding student papers may be selected for
special distinction.
Five copies of each paper should be sent to one of the Program Co-Chairs by
February 5, 1993. The first page should include a descriptive title, the
names, addresses, and student status of all authors, a brief abstract, and
salient keywords or other topic indicators. Acceptance notices will be sent
by March 29, 1993. Final camera-ready papers, incorporating reviewers'
suggestions, will be due approximately five weeks later. There will be an
eight-page limit on proceedings papers, with a few extra pages available for
a fee.
Program Co-Chairs (paper submissions):
David Heckerman
Department of Computer Science, UCLA
Boelter Hall, Room 3531
405 Hilgard Avenue
Los Angeles, CA 90024-1596
tel: (310) 825-2695, fax: (310) 825-2273
email: heckerman@cs.ucla.edu
Abe Mamdani
Deptartment of Electronic Engineering
Queen Mary & Westfield College
Mile End Road
London E1 4NS
tel: +44-71-975-5341, fax: +44-81-981-0259
e-mail: e.h.mamdani@qmw.ac.uk
General Co-Chair (conference inquiries):
Michael P. Wellman
Department of EECS, University of Michigan
Artificial Intelligence Laboratory
Ann Arbor, MI 48109
tel: (313) 764-6894, fax: (313) 763-1260
email: wellman@engin.umich.edu
Conference Committee: Piero Bonissone, Peter Cheeseman, Mike Clarke, Bruce
D'Ambrosio, Didier Dubois, Max Henrion, John Fox, Rudolf Kruse, Henry Kyburg,
John Lemmer, Tod Levitt, Ramon Lopez de Mantaras, Serafin Moral, Ramesh Patil,
Judea Pearl, Enrique Ruspini, Ross Shachter, Glenn Shafer, Philippe Smets,
Kurt Sundermeyer, Lotfi Zadeh.
------------------------------
End of VISION-LIST digest 11.41
************************
