Date: 28 Jan 93 13:21:24-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 12.5
To: Vision-List@TELEOS.COM

VISION-LIST Digest    Thu Jan 28 13:21:24 PDT 93     Volume 12 : Issue 5

 - ***** 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:

 Common problems, framegrabbers & cameras
 Framegrabber with adjustable gain ?
 Literature on map recognition
 Combination of multiple 3d views to form model
 Wanted:Feature Extraction Method
 Looking for Marr-Hildreth Algorithm
 Call for papers: AI Symposium
 BVMA: Neural Networks for Vision
 RecPad93 - 5th Portuguese Conf. on Pat. Recognition

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

Date: Wed, 27 Jan 1993 16:48:10 -0800
From: Matthew Turk <turk>
Organization: Teleos Research, Palo Alto, CA
Subject: Common problems, framegrabbers & cameras

We all know how important hardware and software tools are to our
research -- one very useful function of the Vision-List would be to
serve as a collective for info, specs, and opinions on workstations,
cameras, image processing software, digitizers and other IP boards,
and so on.  Perhaps we can keep files on these subjects in the
archives, updated whenever someone cares to add information.

[ I agree with Matt. I have created a new Vision List Archive directory
  EQUIPMENT for Vision List postings on video, control, storage, 
  computing, etc. Relevant postings will be redistributed into files in
  these areas that can be assessed via anon FTP. 
			phil...			] 

In the meantime, let me send out pointers for a couple specifics.
We're looking for color cameras and S-bus digitizers, with at least
the following constraints:

  Camera: color, RGB output
          $2-3k (this probably rules out 3-chip cameras)
          C mount lens
          control of (or at least ability to turn off auto-) gain and iris
          accept genlocking
          low blooming

  Digitizer:
          S-bus (or directly into Sun memory slots)
          color, accepts RGB
          memory-mapped preferred (i.e. random access of pixels)

E-mail to me; I'll gather responses and post them soon.
Thanks,

	Matthew Turk
	turk@teleos.com


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

Date: Mon, 25 Jan 93 16:09:44 WST
From: ces@cs.uwa.edu.au (Cesar Bertino)
Subject: Framegrabber with adjustable gain ?

Does anybody know of a framegrabber that allows gain adjustment of the
video signal prior to digitisation. I need a gain adjustment from 1 to
around 50. 

Ces Bertino
ces@cs.uwa.edu.au
Department of Computer Science
The University of Western Australia

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

Date: Wed, 27 Jan 1993 15:40:03 +0100 (MET)
From: bru@ipfo.bau-verm.uni-karlsruhe.de (Regine Bruegelmann)
Subject: Literature on map recognition

Hi all!
I'm looking for literature (papers, articles, books...) on
automatic or semi-automatic map recognition (feature extraction
from raster scanned maps). Any help will be greatly appreciated.
Please send your hints to my email address:

          bru@ipfo.bau-verm.uni-karlsruhe.de

If others are interested, I will send a summary to the vision-list.
Thanks in advance, Regine

Regine Bruegelmann, IPF-University of Karlsruhe, Englerstr. 7, D-7500 Karlsruhe
Phone: +49 721 608 3092                            Fax: +49 721 694 568
Internet:bru@ipfo.bau-verm.uni-karlsruhe.de

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

Date: Sun, 24 Jan 1993 19:10:35 GMT
From: c92aja@comlab.ox.ac.uk (Asim Javed)
Organization: Oxford University Computing Laboratory, UK
Subject: Combination of multiple 3d views to form model

Could someone please provide references to articles that discuss
the combinination of multiple 3-D views of an object.

The problem is as follows:

A laser rangefinder and colour sensor are being used to obtain
a data set of X,Y,Z, and R,G,B values for an object.  2 or
more data sets are recorded from different directions.  There is
necessarily some overlap in the areas scanned.

The idea is to combine the views to provide a complete digital
representation of the object being scanned.  The overlapped areas
would be used to position and 'lock' the different views together.

I'm looking for any work that has been already done in this area.

Thanks in advance for the refrences.

(email me directly at:  Asim.Javed@prg.oxford.ac.uk)

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

Date: Tuesday, 26 Jan 1993 12:49:46 EST
From: <IO10047@MAINE.MAINE.EDU>
Organization: University of Maine System
Subject: Wanted:Feature Extraction Method

Dear Sir/Madam,

	I am a graduate student in the Master's program at the University of
Maine in Orono.
	My thesis mainly focuses on recognition of handwritten numbers using
Neural Networks. The numbers that we are trying to use are "United States
Postal Service Office of Advanced Technology Handwritten ZIP Code Database
(1987)" supplied by the US Postal Service in Washington DC. This database
contains images of handwritten ZIP Codes.
	We are trying to use a set of features for the identification task.
We would be grateful if you could supply us with a database of features that
you might have used in your research.
	Even if you don't have the database available, any software that can
provide us with the following functions would be highly appreciated:
		- Binarization
		- Normalization
		- Separation
		- Feature Extraction
		- Identification using Neural Networks

	You can call me at: (207) 581-2025 / (207) 866-3606    or
	     	  email at: sharma@watson.eece.maine.edu

	Thanking You.

	Sincerely
	Lalit Sharma

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

Date: Wed, 27 Jan 1993 13:10:50 UTC+0100
From: Albert Larre <alarre@esaii.upc.es>
Subject: Looking for Marr-Hildreth Algorithm

Hi,

	I am Ph. D. student working with Edge Detection algorithms. I am 
looking for the Marr-Hildreth algorithm for edge detection. Can anybody
help me?.

						Thanks.

Albert Larre
Email: alarre@esaii.upc.es

Automatic Control and Computer Engineering Dept.
Facultat d'Informatica de Barcelona.
Catalonia.

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

Date:        Thu, 28 Jan 93 16:26:12 AST
Subject:     Call for papers: AI Symposium
From: POCHEC@unb.ca

               Call for Participation
              The 5th UNB AI Symposium

          *********************************
          *                               *
          *     Theme:                    *
          *     ARE WE MOVING AHEAD?      *
          *                               *
          *********************************


                August 11-14, 1993
                Sheraton  Inn
                Fredericton


          Advisory Committee
          ==================

              N. Ahuja, Univ.of Illinois, Urbana
              W. Bibel, ITH, Darmstadt
              D. Bobrow, Xerox PARC
              M. Fischler, SRI
              P. Gdrdenfors, Lund Univ.
              S. Grossberg, Boston Univ.
              J. Haton, CRIN
              T. Kanade, CMU
              R. Michalski, George Mason Univ.
              T. Poggio, MIT
              Z. Pylyshyn, Univ. of Western Ontario
              O. Selfridge, GTE Labs
              Y. Shirai, Osaka Univ.


          Program Committee
          =================

          The international program committee will consist of
          approximately 40 members from all main fields of AI and
          from Cognitive Science.



          We invite researchers from the various areas of Artificial
          Intelligence, Cognitive Science and Pattern Recognition,
          including Vision, Learning, Knowledge Representation and
          Foundations, to submit articles which assess or review the
          progress made so far in their respective areas, as well as
          the relevance of that progress to the whole enterprise of
          AI. Other papers which do not address the theme are also
          invited.


          Feature
          =======

          Four 70 minute invited talks and five panel discussions are
          devoted to the chosen topic: "Are we moving ahead: Lessons
          from Computer Vision." The speakers include (in
          alphabetical order)

                   * Lev  Goldfarb
                   * Stephen  Grossberg
                   * Robert  Haralick
                   * Tomaso  Poggio

          Such a concentrated analysis of the area will be undertaken
          for the first time.  We feel that the "Lessons from Computer  r
          Vision" are of relevance to the entire AI community.



          Information for Authors
          =======================


          Now: Fill out the form below and email it.
          ---

          March 30, 1993:
          --------------
          Four copies of an extended abstract (maximum of 4 pages
          including references) should be sent to the conference
          chair.


          May 15, 1993:
          -------------
          Notification of acceptance will be mailed.


          July 1, 1993:
         -------------
          Camera-ready copy of paper is due.


          Conference  Chair: Lev Goldfarb
                      Email: goldfarb@unb.ca


          Mailing address:
              Faculty of Computer Science
              University of New Brunswick
              P. O. Box 4400
              Fredericton, New Brunswick
              Canada  E3B 5A3

              Phone: (506) 453-4566
              FAX:   (506) 453-3566


          Symposium  location

          The symposium will be held in the Sheraton Inn, Fredericton   , which
          which overlooks the beautiful Saint John River.


[ Questions to goldfarb@unb.ca . 		]

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

Date: Mon, 25 Jan 93 08:47:08
From: erh@minster.york.ac.uk
Subject: BVMA: Neural Networks for Vision

           BRITISH MACHINE VISION ASSOCIATION

               Neural Networks for Vision


    One Day Technical Meeting to be held on 17th February, 1993

            at British Institute of Radiology, 
               36 Portland Place, London


Chairman: Dr. Edwin Hancock (York University) erh@uk.ac.york.minster


10.30  Arrive and coffee 

11.00  Adaptive Modelling. 
Prof Harry Barrow, Sussex University. 


11:45  Neural Networks for Control.  
Prof John Mayhew, University of Sheffield. 


12:30  LUNCH 

13:30  Logical Neural Networks for Image Analysis. 
Prof John Stonham, Brunel University. 


14:15  Bayesian Analysis of Neural Networks. 
Dr David Mackay, Cambridge University. 

15:00  TEA  

15:30  Connectionist Models of Attention. 
Dr Herman Muller, Birbeck College London. 

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

Date: Thu, 28 Jan 1993 12:10:33 GMT
From: Miguel Pimenta <apm@garfield.fe.up.pt>
Subject: RecPad93 - 5th Portuguese Conf. on Pat. Recognition

                          CALL FOR PAPERS
RecPad 93
5th Portuguese Conference on Pattern Recognition

RecPad 93 is the 5th annual Conference promoted and organized by APRP,
the Portuguese Association for Pattern Recognition, member of IAPR.

It will be held in Porto, Portugal, on May 13-14, 1993.  Its aim is to
cover all aspects of pattern recognition theory and applications as well
as to promote the exchange of ideas among researchers working in those
fields.

Papers presenting original work in these fields are invited.
Submissions for regular sessions are candidates for a special award and
prize (Pte. 100.000) and may include, but are not limited to, the following
topics:

	. Pattern Recognition Theory and Methods
	. Neural Networks
	. Signal and Image Processing
	. Computer Vision
	. Speech Recognition
	. Document Processing
	. Robotics
	. Industrial Applications
	. Biomedical Applications
	. Special Hardware and Software Systems

Deadlines:
Submission of complete papers (8 pages max.)(award candidates) or
Extended summaries (3 pages max.)(not award candidates)... March 1, 1993
Notification of acceptance ............................... April 2, 1993
Submission of camera-ready paper ........................ April 23, 1993

Contact and submission of papers:
Prof. Armando Jorge Neves Padilha
Faculdade de Engenharia da Universidade do Porto
Dep. Engenharia Electrotecnica e Computadores
R. dos Bragas
P-4099 PORTO CODEX
PORTUGAL

Telephone: +351-2-317105/07 ext. 1448/1436
Telefax: +351-2-319280
E-mail: apm@garfield.fe.up.pt

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

End of VISION-LIST digest 12.5
************************
