Date: 14 Sep 93 10:42:51-PST
From: Vision-List moderator Phil Kahn <Vision-List-Request@TELEOS.COM>
Errors-to: Vision-List-Errors@TELEOS.COM
Reply-to: Vision-List@TELEOS.COM
Subject: VISION-LIST digest 12.41
To: Vision-List@TELEOS.COM

VISION-LIST Digest    Tue Sep 14 10:42:51 PDT 93     Volume 12 : Issue 41

 - ***** The Vision List has changed hosts to TELEOS.COM *****
 - Send submissions to Vision-List@TELEOS.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@TELEOS.COM
 - Access Vision List Archives via anonymous ftp to FTP.TELEOS.COM

Today's Topics:

 Centroid from boundary 
 CAD package for modeling of 3-D objects
 Recognition of objects with movable joints
 Algorithm for autostereograms
 E-mail address of A Nowak, A Florek or T Piascik
 Signature Database
 Research Fellow Post - Leeds, UK
 REQUEST FOR INFO: Experts for AI in sci.data.processing in Europe
 Re: Breakthrough technologies
 Final Program: Machine Learning in Computer Vision: What, Why and How?

------------------------------

Date:  8 Sep 93 16:08 -0700
From: Esfandiar Bandari <bandari@cs.ubc.ca>
Subject: Centroid from boundary 

Is there a way of finding the centriod (and higher order moments) of a closed
curve.  These curves can have concavities, and there is no information as
to where the inside of the curve is -- i.e. no real region growing option.

Thanks in advance.
				--- Esfandiar

----------------------------------------------------------------------

Date: Sat, 11 Sep 1993 09:20:13 GMT
From: e9209h60@v9000.ntu.ac.sg
Subject: CAD package for modeling of 3-D objects
Organization: Nanyang Technological University - Singapore

I am working on range images for recognition of 3-d objects. For the 
automatic construction of models I require a suitable CAD package. If anybody 
can help me obtaining literature for CAD packages for modelling of
objects with sculptured surfaces, it shall be of great help to me.
I want the E-mail addresses of the supplier's contact person.

I am doing my Ph.D at NTU, Singapore. My E-mail address is 
e9209h60@ntuvax.ntu.ac.sg

Thanks.

------------------------------

Date: Fri, 10 Sep 93 11:25:39 EDT
From: jeanlaur@mailbox.syr.edu (Jean-Laurent)
Organization: Syracuse University, Syracuse, NY
Subject: Recognition of objects with movable joints

Hi,

I am looking for any articles, books or other references that may deal with
the recognition of objects with movable joints. I would appreciate any help
or lead about this topic at the following email address:

jeanlaur@mailbox.syr.edu

Thanks in advance.

P.J.L.

------------------------------

Date: Sat, 11 Sep 1993 07:26:51 GMT
From: Marco  Bertamini <mb2p@fermi.clas.virginia.edu>
Organization: University of Virginia
Subject: Algorithm for autostereograms

We plan to start a project on binocular vision which will require
producing autostereograms on a computer screen. However, we have not
been able to find any published algorithm for generating
autostereograms or information on the logic of their generation.
Does anybody on the net know where we could find this
information?

Replies to brunon@univ.trieste.it
or
             mb2p@virginia.edu

Thanks a lot.

------------------------------

Date: 11 Sep 93 06:50:38 GMT
From: image@cs.curtin.edu.au (Image)
Organization: Curtin University of Technology
Subject: E-mail address of A Nowak, A Florek or T Piascik

Hi there,

I need to contact the following people from 

    Laborartory of Automation and Robotics Technical University
    of Poznan, Poland.

    Andrzej Nowak
    Andrzej Florek
    Tomasz Piascik

If you know their email addresses or if you are Andrzej, or Tomasz please 
respond by mailing me at chowkc@cs.curtin.edu.au 

------------------------------

Date: Tue, 7 Sep 93 22:29:40 EDT
From: keh@usha.cs.wayne.edu
Subject: Signature Database

Dear Sir:

I am interested in the subject of signature verification. Do you have any 
signature database that is set up for signature research. If you have some,
I would appreciate it if you could tell me how to access your database.

Thank you very much for your.

 Ke Han
 Vision and Nueral Network Laboratory
 Department of Computer Science
 Wayne State University
 Detroit, MI 48201
 Tel: (313) 577-5070
 Fax: (313) 577-6868

------------------------------

From: Ian Dryden <iand@amsta.leeds.ac.uk>
Date: Mon, 13 Sep 93 16:24:47 BST
Subject: Research Fellow Post - Leeds, UK

THE UNIVERSITY OF LEEDS
 
DEPARTMENT OF STATISTICS
 
Research Fellow
 
A research project on ESTIMATING POPULATION CHARACTERISTICS AND MOVEMENTS
OF BIOLOGICAL OBJECTS THROUGH IMAGE SEQUENCES has been funded by the 
AFRC for three years from 1st October, 1993. It is a joint link
project with Silsoe Research Institute, Bedfordshire. A research fellow
is required to work on this project under the supervision
of Professor K.V. Mardia, Professor J.T. Kent (University of Leeds) and 
Robin  Tillett (Silsoe Research Institute). The large image analysis group
in the Department of Statistics will also be involved in the work.

The main objectives of the project are to estimate population characteristics
such as mean size and shape of biological objects and to statistically
summarize the movement of biological objects through image sequences. 
The methodology will be focused on two applications in fisheries and agriculture.

Applicants should have a good background in Statistics/Mathematics
with a Ph.D (or near completion), preferably related to image analysis or
spatial statistics, and some computing experience.

The appointment, tenable for a period of three years, will commence on
1st October, 1993 or soon after and the salary will be on the scale for 
Research Staff Grade 1A (12,828-20,442 Pounds) according to qualifications
and experience.

Informal enquiries may be made to 

Professor K.V. Mardia. Tel: 0532 - 335101
e-mail: k.v.mardia@uk.ac.leeds 

or

Dr. C.C. Taylor. Tel: 0532 - 335168
e-mail: charles@uk.ac.leeds.amsta 

Application forms and further particulars may be obtained from the
Personnel Office (Academic Section), The University of Leeds, Leeds, LS2 9JT.
Tel: 0532 - 335771, quoting reference number 53/1. Closing date for
applications will be announced in the press advertisement.

The University of Leeds promotes an equal opportunities policy.

------------------------------

Date: Wed, 8 Sep 93 11:52:59 +0200
From: joachim@wgs.estec.esa.nl
Subject: REQUEST FOR INFO: Experts for AI in sci.data.processing in Europe

Dear netters,

the subject says it almost completely:

I would like to compile a list with the names of the experts or institutes
which have a particular interest in the field of applying Artificial Intelligence
to scientific data processing (low level feature extraction to high level fusion
and interpretation of data). They should be in Europe (it seems somehow much
easier to get information from the States - are we over here not doing relevant
work?).

If those people have some connections to the space domain, this would be an
additional plus. We would like to get some activity started in this domain and
need a clear view of what the state of the art is. If anybody is interested I
can mail the results.

Thanks for your time and effort

joachim fuchs
European Space Agency

= esa/estec-WGS             c/o Joachim Fuchs                           =
= Keplerlaan 1              Telephone: +31/1719-85296                   =
= Postbus 299               Telefax:   +31/1719-85419                   =
= NL-2200 AG Noordwijk      Email:     joachim@wgs.estec.esa.nl   or    =
= The Netherlands                      jfuchs@estec.estec.esa.nl        =

------------------------------

Date: Mon, 13 Sep 93 20:52:57 -0500
From: "Igor Tulchinsky" <p00867@psilink.com>
Subject: Re: Breakthrough technologies

|    I am seeking breakthrough technologies.	|
|						|
|    Properly developing such technologies	|
|    requires a combination of resources	|
|    that its owners are unlikely to have	|
|    simply because the acquisition of such	|
|    resources is an industry in itself.	|
|						|
|    Timely access to capital markets,		|
|    connections in the industry necessary	|
|    for forming corporate partnerships,	|
|    and reputation are all needed to		|
|    take a technology to its full potential.	|
|						|
|    If you are an owner of a breakthrough	|
|    technology, whether you are a scientist	|
|    or a corporation, I may be able to 	|
|    provide you with all the key ingredients	|
|    for developing your technology to the	|
|    fullest extent.				|
|						|
|    Please send me e-mail and I will be	|
|    glad to give you more specific 		|
|    information.				|
|						|				
|    Sincerely,					|
|						|
|						|
|    Igor Tulchinsky				|

------------------------------

Date: Mon, 13 Sep 93 17:05:09 EDT
From: Dr Kevin Bowyer <kwb@tortugas.csee.usf.edu>
Subject: Final Program: Machine Learning in Computer Vision: What, Why and How?


                       AAAI Fall Symposium Series

          Machine Learning in Computer Vision: What, Why and How?

                            Final Program

                         October 22 - 24, 1993

            Sheraton Imperial Hotel and Convention Center
                       Research Triangle Park
                       Raleigh, North Carolina

  (registration is limited-- e-mail fss@aaai.org for registration information)


Friday, October 22

9:00 - 10:30-- Exciting and Controversial Invited talks on Learning and Vision

   Task-Oriented Vision Learning, Tom Mitchell, Carnegie-Mellon University

   In what sense might vision be learned?, Chris Brown, University of Rochester


11:00 - 12:30-- moderated by Diane Cook, University of Texas at Arlington

   Incremental Modelbase Updating: Learning New Model Sites
   Kuntal Sengupta and Kim L. Boyer, The Ohio State University 

   Learning Image to Symbol Conversion 
   Malini Bhandaru, Bruce Draper and Victor Lesser, University of Massachusetts at Amherst 

   Transformation-invariant Indexing and Machine Discovery for Computer Vision 
   Darrell Conklin, Queen's University 

   Recognition and Learning of Unknown Objects in a Hierarchical Knowledge-base
   L. Dey, P.P. Das,  and S. Chaudhury, I.I.T., Delhi

   Unsupervised Learning of Object Models
   C. K. I. Williams, R. S. Zemel, Univ. of Toronto; M. C. Mozer, Univ. of Colorado 

2:00 - 3:30-- moderated by Pat Langley, Siemens Corporate Research

   Learning and Recognition of 3-D Objects from Brightness Images 
   Hiroshi Murase and Shree K. Nayar, Columbia University 

   Adaptive Image Segmentation Using Multi-Objective Evaluation and Hybrid Search Methods 
   Bir Bhanu, Sungkee Lee, Subhodev Das, University of California 

   Learning 3D Object Recognition Models from 2D Images 
   Arthur R. Pope and David G. Lowe, University of British Columbia 

   Matching and Clustering: Two Steps Towards Automatic Objective Model Generation 
   Patric Gros, LIFIA, Grenoble, France 

   Learning About A Scene Using an Active Vision System 
   P. Remagnino, M. Bober and J. Kittler, University of Surrey, UK 


4:00 - 5:30-- moderated by Bruce Draper, University of Massachusetts

   Learning Indexing Functions for 3-D Model-Based Object Recognition 
   Jeffrey S. Beis and David G. Lowe, University of British Columbia 

   Non-accidental Features in Learning
   Richard Mann and Allan Jepson, University of Toronto 

   Feature-Based Recognition of Objects 
   Paul A. Viola, Massachusetts Institute of Technology 


   Learning Correspondences Between Visual Features and Functional Features 
   Hitoshi Matsubara, Katsuhiko Sakaue and Kazuhiko Yamamoto, ETL, Japan 

   A Self-Organizing Neural Network that Learns to Detect and Represent
   Visual Depth from Occlusion Events
   Johnathon A. Marshall and Richard K. Alley, University of North Carolina


Saturday, October 23
9:00 - 10:30-- Exciting and Controversial Invited talks on Learning and Vision

   Machine Learning and Computer Vision: An odd couple that could be ideal
   Ramesh Jain, University of California at San Diego.

   Reinforcement Learning and Computer Vision
   Rich Sutton, GTE Research Labs 


11:00 - 12:30-- moderated by Sridhar Mahadevan, University of South Florida


   Learning from the Schema Learning System
   Bruce Draper, University of Massachusetts
   
   Learning Symbolic Names for Perceived Colors
   J.M. Lammens and S.C. Shapiro, SUNY Buffalo
   
   Extracting a Domain Theory from Natural Language to 
      Construct a Knowledge Base for Visual Recognition  
   Lawrence Chachere and Thierry Pun, University of Geneva 
   
  Symbolic and Subsymbolic Learning for Vision: Some Possibilities
   Vasant Honavar, Iowa State University 

  A Vision-Based Learning Method for Pushing Manipulation,
  Marcos Salganicoff, Univ. of Pennsylvania; Giorgio Metta, Andrea Oddera
  and Giulio  Sandini, University of Genoa.


2:00 - 3:30-- moderated by Randall Nelson, University of Rochester 

   A Classifier System for Learning Spatial Representations Based 
      on a Morphological Wave Propagation Algorithm 
   Michael M. Skolnick, R.P.I. 

   Evolvable Modeling: Structural Adaptation Through Hierarchical Evolution 
      for 3-D Model-based Vision
   Thang C. Nguyen, David E. Goldberg, Thomas S. Huang, University of Illinois 

   Developing Population Codes for Object Instantiation Parameters 
   Richard S. Zemel, Geoffrey E. Hinton, University of Toronto 

   Integration of Machine Learning and Vision into an Active Agent Paradigm
    Peter W. Pachowicz, George Mason University 

   Assembly plan from observation
   K. Ikeuchi and S.B. Kang, Carnegie-Mellon University


4:00 - 5:30-- moderated by Robin Murphy, Colorado School of Mines


   Learning Shape Models for a Vision Based Human-Computer Interface
   Jakub Segen, A.T.\&T. Bell Laboratories 

   Learning Visual Speech 
   G. J. Wolff, K. V. Prasad, D. G. Stork & M. Hennecke, Ricoh California Research Center 

   Learning open loop control of complex motor tasks
   Jeff Schneider, University of Rochester

   Issues in Learning from Noisy Sensory Data
   J. Bala and P. Pachowicz, George  Mason University

   Learning combination of evidence functions in object recognition
   D. Cook, L. Hall, L. Stark and K. Bowyer, University of South Florida


Sunday, October 24

9:00 - 10:30-- moderated by Abraham Waksman, Air Force Office of Scientific Research
   Exciting and Controversial Panel Discussion:
      Managing resource boundedness and achieving scale-up 
         with the help of machine learning

11:00 - 12:30-- moderated by Bir Bhanu, University of California at Riverside

   Learning for Vision: Up with the Gigabyte! Death to the Functional View!
   Randal Nelson, University of Rochester

   Learning to Eliminate Background Effects in Object Recognition 
   Robin R. Murphy, Colorado School of Mines 

   The Prax Approach to Learning a Large Number of Texture Concepts
   J. Bala, R. Michalski, and J. Wnek, George Mason University

   Non-Intrusive Gaze Tracking Using Artificial Neural Networks
   Dean A. Pomerleau and Shumeet Baluja, Carnegie Mellon University

   Toward a General Solution to the Symbol Grounding Problem: Combining 
   Machine Learning  and Computer Vision 
   Paul Davidsson, Lund University 



------------------------------

End of VISION-LIST digest 12.41
************************
