Date: 31 Oct 90 12:22:21-PST
From: Vision-List moderator Phil Kahn <Vision-List-Request@ADS.COM>
Errors-to: Vision-List-Request@ADS.COM
Reply-to: Vision-List@ADS.COM
Subject: Vision-List delayed redistribution
To: Vision-List@ADS.COM

Vision-List Digest	Wed Oct 31 12:22:21 PDT 90

 - Send submissions to Vision-List@ADS.COM
 - Send requests for list membership to Vision-List-Request@ADS.COM

Today's Topics:

 Call for Suggestions: Workshop on Shape Description/Representation
 Optical Flow in Realtime
 Image-restoration and image reconstruction software?
 Paper needed!
 Canny's edge detector
 CVNet- Open house during OSA Annual Meeting
 Abstract: Neural Network System for Histological Image Understanding
 CNS Program at Boston University Hiring 2 Assistant Professors
 Submission for comp-ai-vision
 research post
 CVNet- Two tenure track positions

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

Date: Tue, 30 Oct 90 14:08:20 +0100
From: henkh@cwi.nl
Subject: Call for Suggestions: Workshop on Shape Description/Representation

CALL FOR SUGGESTIONS

We are intending to organise a workshop on shape description and 
representation of 2-D (binary and greylevel) images.

The emphasis will be put on the underlying theory by 
(contemporary) mathematics and algorithms for application.

Keywords are: theory of shape, category theory, scale space methods, 
     differential geometry and topology, mathematical morphology, 
     graph representation, computational geometry. 


If you have any suggestions regarding the topics or persons working on
the subject, please let us know.


Kind regards,  O Ying-Lie, Lex Toet, Henk Heijmans. 

Please e-mail your suggestions to:
Henk Heijmans
CWI 
Kruislaan 413
NL-1098 SJ Amsterdam
The Netherlands

e-mail: henkh@cwi.nl

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

Date: Thu, 25 Oct 90 18:53:25 +0100
From: jost@bmwmun.uucp.dbp.de (Jost Bernasch)
Subject: Optical Flow in Realtime

Help! Is there anybody who could give me some hints or
answers to the following questions:

  1. Is there any company or research lab which could
     compute on grey images (256x256) image flow in 
     real time? Is a chip or a board anywhere available?

  2. Has anybody *practical* experience in computing
     qualitative depth information from optical flow?
     How sensitive is optical flow (from image sequences)
     to noise?. Are there any basic problems?

  3. Computing depth information from *normal* flow,
     is this theoretically possible?

We at BMW are developing a lateral and longitudinal
controlled car, which should (for experiments) drive
automatically and which might be in the future an intelligent
assistent to the driver, in which form soever.

We will use (if available) this techniques to detect
obstacles, that are lying or driving on the street,
by comparing the expected optical flow or the expected depth
of the plane (we assume, the street is a plane) to the
computed optical flow or depth. From the differences
we will conclude to obstacels NOT being in the plane.

Any help is very much welcomed!

Yours
Jost Bernasch,                                                        
BMW AG Muenchen, Dep. EW-13, 		      Tel. ()89-3183-2822     
P.O. BOX 40 02 40, 			      FAX ()89-3183-4767      
D-8000 Muenchen 40,  Germany		      jost@bmwmun.uucp.dbp.de 

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

Date: Fri, 26 Oct 90 08:06:42 +0100
From: Reiner Lenz <reiner@isy.liu.se>
Subject: Image-restoration and image reconstruction software?

Are there any (public domain or commercial) software packages for image 
restoration and image reconstruction available?

If there is enough response I will summarize.

"Kleinphi macht auch Mist"
Reiner Lenz | Dept. EE.                 |
            | Linkoeping University     | email:        reiner@isy.liu.se
            | S-58183 Linkoeping/Sweden |

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

Date: Fri, 26 Oct 90 12:34:57 -0700
From: zeitzew@CS.UCLA.EDU (Michael Zeitzew)
Subject: Paper needed!

Hello,

I am looking for a paper from the conference "Speech Technology" 1985....

J.F. Mari and S. Roucos, "Speaker Independent Connected Digit Recognition
Using Hidden Markov Models", Proc. Conf. "Speech Technology", New York, April 
1985

I know the publisher is Media Dimensions, but they won't sell or give me
just one paper, I'd have to buy the entire proceedings ($150+).

I you have it, or know where to get it and wouldn't mind mailing it to me,
I'll be glad to pay for postage, etc. If you know a library that has it, please
let me know.

Mike Zeitzew
zeitzew@cs.ucla.edu

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

Date: Mon, 29 Oct 90 22:36:42 EST
From: namuduri@ziggy.cmd.usf.edu (Kameswara Namuduri)
Subject: Canny's edge detector

I need the program for Canny's edge detector. I appreciate it if some one can send it to the following adress.

namuduri@ziggy.usf.edu
	
Thanks in advance			-namuduri

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

Date: 	Tue, 30 Oct 90 06:31:48 EST
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: CVNet- Open house during OSA Annual Meeting

Open House with the MIT Media Lab Vision Group:

For those of you who will be attending the OSA meeting in Boston, the
Vision and Modeling group of the MIT Media Lab invites you to visit
on Wednesday, Nov. 7, from 10:0am to 1:00pm.  We will be showing
our current work on such topics as face recognition, motion analysis,
image coding, physical modeling, and 3-D sensing.

The Media Lab is in the Wiesner Building (also known as E15),
at 20 Ames St., in Cambridge.  It is near the Kendall subway stop on the
Red Line.  From the conference, take the Green Line to Park Station,
then change for the Red Line toward Harvard.  Get off at Kendall, walk
1/2 block to Legal Seafoods Restaurant, then turn left and go 3/4 block
on Ames.

Hope to see you!

Ted Adelson
Sandy Pentland

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

Date: Mon, 29 Oct 90 17:43:30 +0000
Subject: Abstract: Neural Network System for Histological Image Understanding
From: P.Refenes@cs.ucl.ac.uk

The following pre-print (SPIE-90, Boston, Nov. 5-9 1990) is available.
(write or e-mail to A. N. Refenes at UCL)

AN INTEGRATED NEURAL NETWORK SYSTEM for HISTOLOGICAL IMAGE UNDERSTANDING

A. N. REFENES, N. JAIN & M. M. ALSULAIMAN
Department of Computer Science, University College London, London, UK.

This  paper  describes  a  neural  network   system   whose
architecture   was   designed   so   that  it  enables  the
integration of heterogeneous  sub-networks  for  performing
specialised tasks. Two types of networks are integrated: a)
a low-level feature  extraction  network  for  sub-symbolic
computation,  and  b)  a  high-level  network  for decision
support.

The  paper  describes  a  non  trivial   application   from
histopathology, and its implementation using the Integrated
Neural Network System. We show that  with  careful  network
design,   the  backpropagation  learning  procedure  is  an
effective way of training neural networks for  histological
image  understanding.  We evaluate the use of symmetric and
asymmetric squashing functions in  the  learning  procedure
and  show that symmetric functions yield faster convergence
and 100% generalisation performance.

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

Date: Tue, 30 Oct 90 14:43:52 -0500
From: mike@park.bu.edu
Subject: CNS Program at Boston University Hiring 2 Assistant Professors

Boston University seeks two tenure track assistant or associate
professors starting in Fall, 1991 for its M.A. and Ph.D. Program
in Cognitive and Neural Systems.  This program offers an
intergrated curriculum offering the full range of psychological,
neurobiological, and computational concepts, models, and methods
in the broad field variously called neural networks,
connectionism, parallel distributed processing, and biological
information processing, in which Boston University is a leader. 
Candidates should have extensive analytic or computational
research experience in modelling a broad range of nonlinear
neural networks, especially in one or more of the areas: vision
and image processing, speech and language processing, adaptive
pattern recognition, cognitive information processing, and
adaptive sensory-motor control  Candidates for associate
professor should have an international reputation in neural
network modelling.  Send a complete curriculum vitae and three
letters of recommendation to Search Committee, Cognitive and
Neural Systems Program, Room 240, 111 Cummington Street, Boston
University, Boston, MA 02215, preferably by November 15, 1990 but
no later than January 1, 1991.  Boston University is an Equal
Opportunity/Affirmative Action employer.  
Boston University (617-353-7857) Email: mike@bucasb.bu.edu
Smail: Michael Cohen                     111 Cummington Street, RM 242
       Center for Adaptive Systems        Boston, Mass 02215
       Boston University

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

Date: 30 Oct 90 16:38:08 GMT
From: Paul Lewis <P.H.Lewis@ecs.soton.ac.uk>
Subject: research post

                University of Southampton
       Department of Electronics and Computer Science
           Research Post in Image Understanding

Applications are invited for a  research fellow at post-doctoral 
level to work on a SERC funded project entitled "Enhanced Methods 
of Extracting Features of Engineering Significance from Remotely 
Sensed Images".

The aim of the project is to develop and apply recent work on knowledge
based feature extraction to the provision of tools for extractiong 
features such as roads and river networks from satellite images. 
The work will be set in a GIS context and will  make use of transputer 
based imaging workstations.

Applicants should be post-doctoral or similar level, ideally having 
recent research experience in image understanding, artificial 
intelligence and software development in C, Prolog and Lisp.

The appointment will be for one year in the first instance with the 
expectation of remnewal for two further years. The starting salary 
will be  13495 pounds per annum and the post is available from 
January 1st 1991.

Applications, including a curriculum vitae  and the names and 
addresses of two referees, should be sent to Mr H. F. Watson, 
Staffing Department, the University, Southampton, UK, SO95NH,
to arrive before November 23rd 1990.

Preliminary informal enquiries may be made to Dr Paul Lewis
by  telephone (0703 593715 or 0703 593649).

Dr Paul H. Lewis,
Dept. of Electronics and Computer Science,
The University of Southampton, Southampton, U.K., SO95NH.

e-mail  phl@ecs.soton.ac.uk
Tel. 0703 593715
Fax. 0703 593045 

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

Date: 	Wed, 31 Oct 90 10:19:26 EST
From: Color and Vision Network <CVNET%YORKVM1.bitnet@ugw.utcs.utoronto.ca>
Subject: CVNet- Two tenure track positions

The Department of Psychology of the Ohio State University seek Asst.
Prof applications for two tenure-track positions, starting in September of
1991. One position is in visual perception and one is for a scientist
interested in the relation of visual cognition to neuroscience.
Salary will be in the range of $34,080 to $40,920 and considerable
start-up funds are available. Research areas might include visual
electrophysiology, object recognition, visual attention and memory,
visual/neural modeling and/or visuo-motor coordination. Candidates
should send vita, work sample, and five reference letters to
Mari Riess Jones, Chair Visual Perception Search, 142 Townshend
Hall, Dept Psychology, The Ohio State University, Columbus, Ohio, 43210.
The deadline for applications is December 15, 1990.

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

End of VISION-LIST
********************
