Date: 03 Dec 92 10:31:17-PST
From: Vision-List moderator Phil Kahn <Vision-List-Request@ADS.COM>
Reply-to: Vision-List@ADS.COM
Subject: VISION-LIST digest 11.42
To: Vision-List@ADS.COM

VISION-LIST Digest    Thu Dec 03 10:31:17 PDT 92     Volume 11 : Issue 42

 - ***** The List is moving sites soon: you will be notified ****
 - 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:

 C-Source code for Combining Shape from Shading and Stereo
 Request for Road Images
 Survey request: 3-D model acquisition from multiple range views
 Re: Handling Interlaced Video
 test imagery for lossless compression
 References on snakes wanted
 Biological Cell Images Wanted
 Intellectual Property Rights
 Yale University Assistant Professor Opening
 Jobs in Chapel Hill & Durham, NC
 Research Positions Available
 HPCC Workshop Report, Vision, Natural Language and Speech Proc., and AI
 Last CFP: CAIP 93

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

Date: Tue, 1 Dec 92 15:57:32 EST
From: shah@eola.cs.ucf.edu (Mubarak Shah)
Subject: C-Source code for Combining Shape from Shading and Stereo

The C source code and images are available for anonymous ftp from 
eustis.cs.ucf.edu (  132.170.108.42).  

This program implements Cryer-Tsai-Shah method for combining 
shape from shading and stereo depth maps. 

\title{\Large\bf Combining Shape from Shading and Stereo Using Human Vision Model}

\author{James Edwin Cryer, Ping-Sing Tsai and Mubarak Shah \\
Computer Science Department\\
University of Central Florida\\
Orlando, FL 32816}

\maketitle

\begin{small}
\centerline {\em Abstract}
{\em
 Stereo algorithms suffer from the lack of
   local surface texture due to smoothness  of depth constraint,  or
   local miss-matches in disparity estimates.
   Thus, the stereo methods only provide a coarse depth map 
   which can be associated with a low
   pass image of the depth map. On the other hand,
   shape from shading algorithms produce better estimates of
   local surface areas, but some of them have problems with variable albedo and 
spherical surfaces.
   Thus, shape from shading
   methods produce better detailed depth information, and
   can be associated with the high pass image of the 
   depth map image.
In order to compute a better depth map,
we present a method for integrating  the high frequency
information from the shape from shading 
and the low frequency information from stereo.
%  In this paper, we present a method for integrating  the high frequency%  information from the shape
%  from shading, and the low frequency information from
%  the stereo  in order to
%  produce a better depth map. 
Our method is motivated by the 
human vision system, and follows Hall and Hall's model.  
The proposed algorithm is very simple, takes about $.7$ seconds for 
a $128 \times 128$ image on a 
Sun SparcStation-1, is non-iterative, and  
does not use any thresholds. The results obtained with 
a variety of 
synthetic and real images are discussed.  
The quality of depth obtained by integrating shading and stereo is 
compared with the ground truth (range image) using average surface 
gradient error measure, and improvement ranging from 30\% to 50\% 
over stereo, and from 65\% to 98\% over shading is demonstrated.  

}
\end{small}

Script started on Tue Dec  1 15:44:20 1992
sono 101% ftp es ustis.cs.ucf.edu
Connected to eustis.
220 eustis FTP server (SunOS 4.1) ready.
Name (eustis.cs.ucf.edu:shah): anonymous
331 Guest login ok, send ident as password.
Password:
230 Guest login ok, access restrictions apply.
ftp> cd pub
250 CWD command successful.
ftp> ls
200 PORT command successful.
150 ASCII data connection for /bin/ls (132.170.108.100,1098) (0 bytes).
combine
combine.tar.Z
log
manne.ucf
manne_128.asc
nmmoz128.asc
shading
shading.tar.Z
tec24.ps.Z
tec25.ps.Z
226 ASCII Transfer complete.
117 bytes received in 0.51 seconds (0.22 Kbytes/s)
ftp> get cp,  ombine.tar.Z
200 PORT command successful.
150 ASCII data connection for combine.tar.Z (132.170.108.100,1099) (297136 bytes).
226 ASCII Transfer complete.
local: combine.tar.Z remote: combine.tar.Z
298918 bytes received in 3.4 seconds (85 Kbytes/s)
ftp> quit
221 Goodbye.
sono 102% c unompre     compress combine.tar. .Z
sono 103% tar -xvf combo ine.tar
x combine/Depth.rimg, 65548 bytes, 129 tape blocks
x combine/combine.c, 15982 bytes, 32 tape blocks
x combine/mozart-sh.rimg, 65548 bytes, 129 tape blocks
x combine/H.rimg, 65548 bytes, 129 tape blocks
x combine/L.rimg, 65548 bytes, 129 tape blocks
x combine/lambert, 40960 bytes, 80 tape blocks
x combine/lambert.c, 7931 bytes, 16 tape blocks
x combine/mozart-st.rimg, 65548 bytes, 129 tape blocks
x combine/disp3, 32768 bytes, 64 tape blocks
x combine/combine, 73728 bytes, 144 tape blocks
x combine/combine-depth.ascii, 207492 bytes, 406 tape blocks
x combine/README, 4225 bytes, 9 tape blocks
x combine/bread-sh.rimg, 16396 bytes, 33 tape blocks
x combine/lambert.iimg, 65548 bytes, 129 tape blocks
x combine/bread-st.rimg, 16396 bytes, 33 tape blocks
sono 104% exit
sono 105% 
script done on Tue Dec  1 15:46:13 1992

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

Date: Wed, 2 Dec 1992 21:24:58 GMT
From: brassard@cs.sfu.ca (Louis Brassard)
Organization: CSS, Simon Fraser University, Burnaby, B.C., Canada
Subject: Request for Road Images
Keywords: road sign , road images

I am interested to get sequence of road images (24 bits color)  taken from a moving car. Road sign of any type should be visible along the road.

Thanks,
 
Louis Brassard
brassard@cs.sfu.ca
Simon Fraser University
School of Engineering Science
Burnaby, British Columbia, Canada

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

From: mtc@aifh.edinburgh.ac.uk
Date: Mon, 30 Nov 92 12:34:39 GMT
Subject: Survey request: 3-D model acquisition from multiple range views

The Machine Vision Unit of the Department of Artificial Intelligence
at Edinburgh (Scotland) has just started a three-year research programme
focused on 3-D model acquisition from multiple range views. The object
considered are small (say 20 cubic cm max) machined mechanical components.

One of the first tasks is compiling a comprehensive survey in order to
get a sound idea of
	* what has been done (paper references and unpublished work),
	* with which applications in mind,
	* what are the applications expected to benefit from and/or
	  to adopt automatic model acquisition systems,
	* which companies are interested in this technology,
	* ongoing european and non-european research programmes/projects,

The final reference/information list will be made public through this bullettin.
I invite everybody interested in discussing model acquisition to contact
me any time for an exchange of ideas.

Dr. Emanuele Trucco		             Research Fellow

Dept. of Artificial Intelligence  | Email: mtc@aifh.ed.ac.uk
University of Edinburgh		  | Tel.:    +44 31 650.3087
5 Forrest Hill, Edinburgh,	  |   (Vision Lab)  650.4504
EH1 2QL,			  | FAX:     +44 31 225.9370
SCOTLAND			  | TELEX:   727442 UNIVED G

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

Date:     Tue, 1 Dec 92 9:40:19 EST
From: rshankar@top.cis.syr.edu
Organization: Syracuse University, CIS Dept.
Subject: Re: Handling Interlaced Video

>From: wilbur@constitution.ucr.edu (Wilhelm Burger)
>Subject: Handling Interlaced Video
>
>(2) What is the "standard" method to remove interlace flicker from
>    still images used by professional TV studios (or in good VCRs)?

A simple technique which often does a good job is to separate out the
interlaced image into two images, one containing the odd-numbered lines 
alone and the other, the even ones alone from the interlaced image. 
Duplicating rows brings the image to the standard size for viewing. IMHO,
it hardly ever makes sense to do something like contour following on an
interlaced image. 

-- Ravi Shankar

[ When pixel displacements are not too large, you'd be shocked how well 
  temporal smoothing helps (i.e., gausian smooth pixel values over frames).
				phil...		]

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

Date: Sat, 28 Nov 1992 01:59:12 -0600
From: Whoi-Yul Kim <wyk@utdallas.edu>
Subject: test imagery for lossless compression

We have developed lossless compression algorithms especially for progressive
transmission. Is there any imagery to test the performance of our
algorithms?  They could be medical images or a set of standard images for
compression research.
Would appreciate if one can provide us any pointers.
	Thanks in advance,
	yura

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

Date: Tue, 1 Dec 92 13:20:08 GMT
From: nde@scs.leeds.ac.uk
Subject: References on snakes wanted

I'm looking for references detailing practical applications of snakes
or other 'active contour models'. I'm already aware of work by Kass and
colleagues, and I'm interested in papers dealing with the implementation
of their ideas, especially in a biomedical context. Please reply via email
to nde@scs.leeds.ac.uk. I'll summarize if there's a significant response.

Also, does anyone know of any freely-available code to handle snakes
and related objects? - I'd hate to reinvent the wheel...

Many thanks,

Nick Efford
School of Computer Studies,
Leeds University, Leeds, UK

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

Date: Thu, 3 Dec 92 15:12:22 GMT
From: S.Tan@ee.surrey.ac.uk
Subject: Biological Cell Images Wanted

Hi all,
     I am looking for possible ftp site that store biological
     cell images in colour. I am working on colour texture
     analysis and such images will be very helpful to test 
     the representation power. Any inputs are welcomed.

					Tele Tan

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

Date: Mon, 30 Nov 92 17:28:04 -0500
From: cfwol@mvax.cc.conncoll.edu (Wally aka Wallie)
Dear list members,

At a recent Center for Arts and Technology meeting at Connecticut College, I
was charged with the responsibility of asking faculty at other institutions 
about their repsective institutions' "Intellectual Property Rights" as 
relates to copyright, patents and royalties.

Please send specific information via email or snail mail to the address
below.  Names of the authorities at different schools to contact would also
be helpful.

Send responses to cfwol@mvax.cc.conncoll.edu (internet)
		  cfwol@conncoll.bitnet      (bitnet)

		Claus Wolter			(snail mail)
		Box 5611 Connecticut College
	    	270 Mohegan Ave
		New London, CT  06320-4196 USA
		(203)-439-2557			(voice mail)

Thanking you for you kind assistance in advance.
Sincerely,
Claus Wolter
Head Coach of Rowing/Adjunct Assistant Professor of Physical Education
Resident Department Computer Geek  :-)

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

Date: Wed, 2 Dec 1992 10:50:26 -0500
From: hager-greg@CS.YALE.EDU (Greg Hager)
Subject: Yale University Assistant Professor Opening


The following is our "official" job posting.  In the AI group we
are particularly interested in candidates in the area of machine
vision and robotics.

                              YALE UNIVERSITY
                       DEPARTMENT OF COMPUTER SCIENCE



We expect to have one or more junior faculty positions available for the
1993-94 academic year.  We are particularly interested in applicants in
the areas of artificial intelligence, theoretical computer science,
numerical analysis, and programming languages and systems.  Applications
should be submitted before April 30, 1993,

Duties will include teaching graduate and undergraduate courses.
Applicants are expected to engage in a vigorous research program.

Candidates should hold a Ph.D. in computer science or related discipline.

Qualified women and minority candidates are encouraged to apply.  Yale
is an affirmative action/equal opportunity employer.

Send vitae and names of three references to: Faculty Recruiting Committee,
Department of Computer Science, Yale University, P.O. Box 2158, Yale
Station, New Haven, CT  06520.

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

Date: Wed, 2 Dec 92 16:42:52 -0500
From: Jonathan A. Marshall <marshall@cs.unc.edu>
Subject: Jobs in Chapel Hill & Durham, NC

The following two jobs are both open to strong vision researchers.  An
opportunity also exists for the new vision faculty member(s) to participate
in (and receive support from) a collaborative research effort on models of
human vision, under the MIP (Medical Image Presentation) program project
grant at UNC-Chapel Hill; contact Prof. Stephen Pizer, smp@cs.unc.edu, for
further information.  Researchers with interests in computational and
neurobiological models of cognition and of vision would find several
collaborative opportunities here in the Research Triangle area of North
Carolina.

**********

1.  The Psychology Department of the University of North Carolina at Chapel
Hill seeks to hire a cognitive psychologist in a tenure track assistant
professor position for the fall of 1993.  Responsibilities include graduate
and undergraduate teaching, research, and research supervision.  Applicants
in any area of cognitive psychology will be considered.  Have 3 letters of
recommendation sent and submit a curriculum vitae, up to 3 (p)reprints, and
a statement of teaching and programmatic research interests to: Thomas S.
Wallsten, Cognitive Search Committee, Department of Psychology, University
of North Carolina at Chapel Hill, Chapel Hill, NC 27599-3270.  Applications
must be received by December 15, 1992.  UNC-CH is an Affirmative Action/
Equal Opportunity Employer.  Questions can be directed to Tom Wallsten at
tom_wallsten@unc.edu.

**********

2.  The Department of Experimental Psychology at Duke University has a
tenure-track assistant professor position beginning in the Fall, 1993 in the
general area of Behavioral Neuroscience with theoretical interests in neural
plasticity, learning, motivation, or sensory perception development.
Candidates with strong research and teaching interests should send a vitae,
representative reprints, and three or more letters of recommendation to:
Faculty Search Committee, Department of Experimental Psychology, Duke
University, Durham, NC, 27706.  Duke is an equal opportunity/affirmative
action employer.

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

Date: Fri, 27 Nov 92 19:59:12 EST
From: Bjorn Jawerth <bj@loki.math.scarolina.edu>
Subject: Research Positions Available

Research opportunities are available IMMEDIATELY within
the South Carolina Initiative for Computational Science (SCICS)
at The University of South Carolina, Columbia, SC.

Starting Date: January 1993.

Duration: Up to three years.

Required Skills for Post-Doctorate and Senior Research Associate positions:
         (1) Solid foundation in mathematics.
         (2) Highly competent programming in "C".
         (3) Familiarity with X-Windows programming  environment.
Experience in the areas of:
	 (1) Signal processing, (2) Computer vision or (3) Numerical PDE's

These positions may later be converted to tenure-track with the Departments of
Computer Science and/or Mathematics.


Required skills for Research Associate positions:
         (1) Highly competent programming in "C".
         (2) Familiarity with X-Windows programming environment.

Research areas include the application of wavelets for image compression,
numerical PDE's for advanced manufacturing techniques and 
computer-aided design (CAD) and related applications.

Qualifications:
        A Ph.D. degree is required for Senior Research Associates
          and Post-Doctorate positions.
        A M.S. degree or B.S. degree with experience is required
          for Research Associate positions.

Salary: Highly competitive.

Please submit resume and names of three references to:

                 Professor Bjorn Jawerth
		 Department of Mathematics
                 LeConte, Rm 307
                 University of South Carolina
		 Columbia, SC  29208

                 Phone:  (803) 777-6218 (Office)
                         (803) 777-4321 (Secretary)
	         E-mail: BJ@LOKI.MATH.SCAROLINA.EDU
                 FAX: (803) 732-5977


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

Date: 29 Nov 1992 00:17:46 GMT
From: wah@aquinas.crhc.uiuc.edu (Benjamin W. Wah)
Organization: University of Illinois at Urbana-Champaign
Subject: HPCC Workshop Report, Vision, Natural Language and Speech Proc., and AI
Keywords: HPCC, Computer Vision, Speech Processing, Natural Language Processing, Artificial Intelligence


This message contains the executive summary of our Workshop on
HPCC for Grand Challenge Applications: Computer Vision, Speech and
Natural Language Processing, and Artificial Intelligence.

The entire report (48 pages) can be obtained by anonymous ftp from
manip.crhc.uiuc.edu (128.174.197.211) in directory /pub/hpcc.

There are three files in this directory.

   text.ps     PostScript version of the entire article
   text.ascii  ASCII version of the entire article
   text.me     file that can be processed by tbl, eqn, ditroff,
               and psdit to generate the PostSscript file.

Please let me know if you have questions regarding this article.

Benjamin W. Wah
Professor
Coordinated Science Laboratory
University of Illinois, Urbana-Champaign
(217) 333-3516
wah@manip.crhc.uiuc.edu


   
   
   



                   Report on Workshop on High Performance Computing
                 and Communications for Grand Challenge Applications:
               Computer Vision, Speech and Natural Language Processing,
                             and Artificial Intelligence
   
   
   
   
   
            Benjamin W. Wah       University of Illinois, Urbana-Champaign
            Thomas S. Huang       University of Illinois, Urbana-Champaign
            Aravind K. Joshi      University of Pennsylvania
            Dan Moldovan          University of Southern California
            John Aloimonos        University of Maryland, College Park
            Ruzena K. Bajcsy      University of Pennsylvania
            Dana Ballard          University of Rochester
            Doug DeGroot          Texas Instruments
            Kenneth DeJong        George Mason University
            Charles R. Dyer       University of Wisconsin, Madison
            Scott E. Fahlman      Carnegie-Mellon University
            Ralph Grishman        New York University
            Lynette Hirschman     Massachusetts Institute of Technology
            Richard E. Korf       University of California, Los Angeles
            Stephen E. Levinson   AT&T Bell Laboratories
            Daniel P. Miranker    University of Texas, Austin
            Nelson H. Morgan      University of California, Berkeley
            Sergei Nirenburg      Carnegie-Mellon University
            Tomaso Poggio         Massachusetts Institute of Technology
            Edward M. Riseman     University of Massachusetts, Amherst
            Craig Stanfill        Thinking Machines Corporation
            Salvatore J. Stolfo   Columbia University
            Steven L. Tanimoto    University of Washington
            Charles Weems         University of Massachusetts, Amherst
   



   
   
   
   
                                    November 1992
   
   
   

   
   ____________________
   
   This workshop was supported by National  Science  Foundation  under  grant  IRI-
   9212592.
   
   Any opinions, findings, conclusions, and recommendations expressed in  this  re-
   port  are  those  of the authors and do not necessarily reflect the views of the
   National Science Foundation.
   
   




   
                                  TABLE OF CONTENTS




   
   
   Workshop Participants .....................................................    i
   
   Publication and Distribution of this Report ...............................   ii
   
   1.  EXECUTIVE SUMMARY .....................................................    1
   
   2.  INTRODUCTION ..........................................................    2
       2.1.  Origin of the Workshop ..........................................    2
       2.2.  The Workshop Charter ............................................    2
       2.3.  Organization of this Report .....................................    3
   
   3.  COMPUTER VISION .......................................................    4
       3.1.  Grand Challenge Applications ....................................    4
       3.2.  Fundamental Science and Enabling Technologies ...................    6
       3.3.  Implications for System Architectures ...........................   10
       3.4.  Infrastructure Support ..........................................   12
   
   4.  SPEECH AND NATURAL LANGUAGE PROCESSING ................................   14
       4.1.  Grand Challenge Applications ....................................   14
       4.2.  Fundamental Science and Enabling Technologies ...................   16
       4.3.  Implications for System Architectures ...........................   18
       4.4.  Infrastructure Support ..........................................   20
   
   5.  ARTIFICIAL INTELLIGENCE ...............................................   21
       5.1.  Grand Challenge Applications ....................................   21
       5.2.  Fundamental Science and Enabling Technologies ...................   24
       5.3.  Implications for System Architectures ...........................   26
       5.4.  Infrastructure Support ..........................................   27
   
   6.  FINAL REMARKS .........................................................   29
   
   ACKNOWLEDGEMENTS ..........................................................   30
   
   AUTHOR BIOGRAPHIES ........................................................   31
   
   AUTHOR ADDRESSES ..........................................................   36
   
   
   
   November 28, 1992                                                              i
   
   
                                WORKSHOP PARTICIPANTS
   
   
   
   Workshop Chair
   
         Benjamin W. Wah                University of Illinois, Urbana-Champaign
   
   Computer Vision Area
         Thomas Huang (Area Vice Chair) University of Illinois, Urbana-Champaign
         John Aloimonos                 University of Maryland, College Park
         Ruzena K. Bajcsy               University of Pennsylvania
         Dana Ballard                   University of Rochester
         Charles R. Dyer                University of Wisconsin, Madison
         Tomaso Poggio                  Massachusetts Institute of Technology
         Edward M. Riseman              University of Massachusetts, Amherst
         Steven L. Tanimoto             University of Washington
   
   Speech and Natural Language Processing Area
   
         Aravind K. Joshi (Area Vice Chair) University of Pennsylvania
         Ralph Grishman                 New York University
         Lynette Hirschman              Massachusetts Institute of Technology
         Stephen E. Levinson            AT&T Bell Laboratories
         Nelson H. Morgan               University of California, Berkeley
         Sergei Nirenburg               Carnegie-Mellon University
         Craig Stanfill                 Thinking Machines Corporation
   
   Artificial Intelligence and Computer Architecture Area
         Dan Moldovan (Area Vice Chair) University of Southern California
         Doug DeGroot                   Texas Instruments
         Kenneth DeJong                 George Mason University
         Scott E. Fahlman               Carnegie-Mellon University
         Richard E. Korf                University of California, Los Angeles
         Daniel P. Miranker             University of Texas, Austin
         Salvatore J. Stolfo            Columbia University
         Benjamin W. Wah                University of Illinois, Urbana-Champaign
   
   National Science Foundation Observers
   
         Syed Kamal Abdali        Numeric, Symbolic, and Geometric Computations
         Paul G. Chapin           Linguistics
         Su-Shing Chen            Knowledge Models and Cognitive Systems
         Bernard Chern            Microelectronic Information Processing Systems
         Y. T. Chien              Information, Robotics, and Intelligent Systems
         John H. Cozzens          Circuits and Signal Processing
         John D. Hestenes         Interactive Systems
         Richard Hirsch           Supercomputer Center
         Howard Moraff            Robotics and Machine Intelligence
         John Lehmann             Microelectronic Information Processing Systems
         Pen-Chung Yew            Microelectronic Systems Architecture
         Zeke Zalcstein           Computer Systems Architecture
   
   

   
   November 28, 1992                                                              1

   
   
   1.  EXECUTIVE SUMMARY
   
        This article reports the findings of the Workshop on High Performance  Com-
   puting  and  Communications  (HPCC)  for  Grand Challenge Applications: Computer
   Vision, Speech and Natural Language Processing (SNLP), and  Artificial  Intelli-
   gence  (AI).   The  goals of the workshop are to identify applications, research
   problems, and designs of HPCC  systems  for  supporting  applications  in  these
   areas.
   
        In computer vision, we  have  identified  the  main  scientific  issues  as
   machine  learning, surface reconstruction, inverse optics and integration, model
   acquisition, and perception and action.  Since vision algorithms operate in dif-
   ferent  levels of granularity, computers for supporting these algorithms need to
   be heterogeneous and modular.  Advances in technology,  new  architectural  con-
   cepts, and software design methods are essential for this area.
   
        In SNLP, we have identified issues in statistical analysis in  corpus-based
   speech  and  language  understanding,  search  strategies for language analysis,
   auditory and vocal-tract modeling, integration of multiple levels of speech  and
   language analyses, and connectionist systems.  Similar to algorithms in computer
   vision, algorithms in SNLP require high computational power, ranging  from  gen-
   eral  purpose supercomputing to special purpose VLSI systems.  As processing has
   various requirements, a hybrid heterogeneous computer system is the most  desir-
   able.
   
        In AI, important issues that need immediate attention include the  develop-
   ment  of  efficient machine learning and heuristic search methods that can adapt
   to different architectural configurations, and the design  and  construction  of
   scalable  and verifiable knowledge bases, active memories, and artificial neural
   networks.  A computer system for supporting AI  applications  is  heterogeneous,
   requiring  research  in high speed computer networks, mass storage and efficient
   retrieval methods, computer languages, and hardware and software design tools.
   
        Research in these areas is inherently multidisciplinary  and  will  require
   active  participation of researchers in device and networking technologies, sig-
   nal processing,  computer  architecture,  software  engineering,  and  knowledge
   engineering.   Besides  extending  current  frontiers  in research, an important
   aspect to be emphasized is the integration of existing  components  and  results
   into working systems.

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

Date: Thu, 26 Nov 1992 12:06:13 +0100
From: "Prof. Dr. Reinhard Klette" <klette@cs.tu-berlin.de>
Subject: CAIP 93

                      LAST CALL FOR PAPERS

              5th International Conference CAIP'93
            Computer Analysis of Images and Patterns
Sponsored by IAPR - International Association for Pattern Recognition

                       Budapest, Hungary
                     September 13-15, 1993

Chairman:  Gerald Sommer (Germany)

Organizing Committee:  Elvira Bahn (Germany)
                       Eva Sos     (Hungary)

Program Committee:

   D.Chetverikov (Chairman, Hungary)   C.-E.Liedtke (Germany)
   I.Bajla (Czecho-Slovakia)           I.Pitas (Greece)
   W.Coy (Germany)                     A.Rosenfeld (USA)
   V.Di Gesu (Italy)                   W.Skarbek (Poland)
   M.J.B.Duff (Great Britain)          J.Sklansky (USA)
   J.-O.Eklundh (Sweden)               F.Solina (Slovenia)
   B.Gudmundsson (Sweden)              V.Valev (Bulgaria)
   V.Hlavac (Czecho-Slovakia)          K.Voss (Germany)
   R.Klette (Germany)                  L.P.Yaroslavsky (Russia)
   W.Kropatsch (Austria)

CAIP is a traditional Central European conference devoted to all aspects of
image processing and analysis, computer vision, and pattern recognition.
Its main goal is to promote scientific cooperation and contribute to free
exchange of ideas, knowledge, and experience between Eastern and Western
Europe. Papers devoted to new trends in image analysis, including theory,
algorithms and applications, are especially welcome at CAIP'93.
Topics of interest include, but are not limited to, the following:

   - theory of computer vision and image analysis
   - theoretical and experimental evaluation of algorithms
   - comparative studies of different approaches
   - hierarchical and model-based methods
   - new fast and reliable algorithms
   - successful applications in real environments
   - novel application areas

The scientific program will include regular contributions as well as invited
talks given by key speakers sponsored by IAPR. All accepted papers will be
published in the Conference Proceedings.

Language: The official language of the conference is English.

Submission of papers: Prospective authors should submit 3 copies of
full-length draft papers (max. 10 A4 size pages) to

D.Chetverikov, Computer and Automation Institute, Budapest, P.O.Box 63,
               H-1518 HUNGARY

               Fax: +36.1.1667503
               E-mail: h1180cse@ella.hu (no electronic submissions, please)

Deadlines:     Submission of draft papers:    January 15, 1993
               Notification of acceptance:    April 15, 1993
               Camera-ready papers:           July 15, 1993


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

End of VISION-LIST digest 11.42
************************
