Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 12 Issue 21
VISION-LIST Digest Mon May 03 12:07:46 PDT 93 Volume 12 : Issue 21
- ***** 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:
NIH Image V1.44
CCD camera and Motorola chip
New NIST Mated Fingerprint Card Pairs Database
Re: Commercial Information about FLIR cameras
Evidence updating in hierarchical synthesis
Director Position in Image Processing/Understanding
Final Program for the IEEE Workshop on Qaulitative Vision (June 14, 1993)
CFP: First IEEE International Conference on Image Processing
13th Leeds Statistical Research Workshop
Parallel Vision Algorithms Workshop
Intn'l Handwriting Recognition Wkshp
----------------------------------------------------------------------
Date: Sat, 1 May 1993 15:47:44 -0400 (EDT)
From: Wayne Rasband <wayne@helix.nih.gov>
Subject: NIH Image V1.44
[ Thanks to Tim Allen for cross-posting this. phil... ]
Announcing NIH Image V1.44
NIH Image V1.44, including documentation and source code, is now
available by anonymous ftp from zippy.nimh.nih.gov[128.231.98.32],
in the directory /pub/image. NIH Image is an image processing and
analysis application for the Macintosh that is in the public domain.
It has painting and image manipulation tools, a macro language,
tools for measuring areas, distances and angles, and for counting
things. Using a frame grabber card, it can record sequences of
images to be played back as a movie. It can invoke user-defined
convolution matrix filters, such as Gaussian. It can import raw
data in tab-delimited ASCII, or as 1 or 2-byte quantities. It also
does histograms and even 3-D plots. It is limited to 8-bits/pixel,
though the 8 bits map into a color lookup table. It runs on any Mac
that has a 256-color screen and a FPU (or get the NonFPU version
from zippy.nimh.nih.gov)
------------------------------
Date: Thu, 29 Apr 93 11:22:13 MEZ
From: He-Ping Pan <ULM101@IBM.rhrz.uni-bonn.de>
Subject: CCD camera and Motorola chip
Help needed: A Cheapest Configuration of An Active Vision System
I am trying to build a testbed for active vision research. On a long
term, I plan to build an Artificial Insect which has six legs and two
eyes. As the first step, I just want to have one eye and a brain.
Therefore, I need a CCD camera and a microprocessor e.g. Motorola
chip. The CCD camera should be controlled by three motors: two spatial
rotations and one zoom (focus). The CCD camera provides instant input
images to the microprocessor, the instant output of the microprocessor
will be control signals to the motors of CCD camera. My problem is
thus: what is the cheapest configuration of a CCD camera, a
Microprocessor, and three motors that I can simply purchase from shops
or companies ?
The reason for the cheapest configuration is that I plan in the near
future to purchase a large number of these components, give them to
MSc level or above students. Let students build experimental active
vision systems as a basic first-hand practice of computer vision and
artificial life.
Applications of such active vision systems are e.g. human face
recognition, interest moving object following, autonomous
vehicle navigation, etc.
Any help will be highly appreciated.
He-Ping Pan
Institut fuer Photogrammetrie
Universitaet Bonn
Nussallee 15, 5300 Bonn 1, Germany
Tel: 0228-732721-732905
Fax: 0228-733281
Email: ulm101@dbnrhrz1.bitnet
------------------------------
Date: Thu, 29 Apr 1993 15:22:16 GMT
From: craig@magi.ncsl.nist.gov (Craig Watson)
Organization: National Institute of Standards and Technology, Gaithersburg, MD
Subject: New NIST Mated Fingerprint Card Pairs Database
National Institute of Standards and Technology
announces a new database
NIST Special Database 9
8-Bit Gray Scale Images of Mated Fingerprint Card Pairs (MFCP)
The NIST database of mated fingerprint card pairs will consist of multiple
volumes. Currently five volumes are scheduled to be released. Volumes 1 and
2 have been released and volumes 3-5 will be released at intervals of
approximately one month. Each volume will be a 3 CD-ROM set with each CD-ROM
containing 90 mated card pairs of segmented 8-bit gray scale fingerprint images
(900 fingerprint image pairs per CD-ROM). Each segmented image is 832 by 768
pixels and classified using the National Crime Information Center (NCIC)
classes given by the FBI. The images are compressed using a modified JPEG
lossless compression algorithm. Each CD-ROM contains approximately
630-660 Megabytes of data compressed and 1.0-1.2 Gigabytes uncompressed
(1.8 : 1 average compression ratio). The database also includes example
software which was written on a UNIX environment workstation. The software
is the same code used with NIST Special Database 4.
NIST Special Database 9 has the following features:
o Each Volume has 270 mated card pairs of segmented 8-bit gray scale
fingerprint images.
o NCIC classifications given by the FBI.
o Cards selected randomly thus approximating a natural horizontal
slice of the NCIC classifications.
o Resolution of approximately 11.0 line pairs per millimeter resolution. Scanned at 19.6850 pixels per mm.
o Image format documentation and example software (written on a
UNIX environment workstation)
o Software is the same code used with NIST Special Database 4.
Suitable for automated fingerprint classification research, the database can
be used for:
o algorithm development
o system training and testing
The database is a valuable tool for evaluating fingerprint systems using a
statistical sample of fingerprints which approximate a natural horizontal
slice of the NCIC classifications. The system requirements are a CD-ROM drive
with software to read ISO-9660 format and the ability to compile the C source
code, which was written using a SUN C compiler. Cost per volume of the
database: $750.00.
If you have further questions, please contact:
Craig Watson
National Institute of Standards and Technology
225/A214
Gaithersburg, MD 20899
phone -> (301)975-4402
e-mail -> craig@magi.ncsl.nist.gov
------------------------------
Date: Wed, 21 Apr 93 09:00:53 +0200
From: Juerg Uhlmann <juerg@textil.mabp.ethz.ch>
Subject: Re: Commercial Information about FLIR cameras
In comp.ai.vision you write:
>We are interested in getting commercial information about thermal imaging
>sensors or infrared cameras.
>Does anybody know any company who manufacture these products?
>Email: jadiaz@santiago.isdefe.es
I've been out of the thermal camera field for a few years, but this
is what I recall: The new high-tech stuff is semiconductor sensors.
These often have to be cooled with liquid nitrogen, and whether they
do or don't they are pretty costly. The previous generation technology
uses a vacuum-tube sensor called a pyroelectric vidicon. These have
limitations, but if your application fits within them they can save
you a bundle. Basically, they suffer from lag so fast moving objects
leave a trail behind them. Also, they actually sense *change* in IR,
so they need to be fitted with a shutter when viewing a fixed scene.
I used to work at a company that builds and sells shuttered pyro-
electric vidicon cameras that output NTSC video (I don't know about
PAL & SECAM). The company is called Electrophysics; it is located
somewhere in New Jersey, and the phone # is 800-759-9577.
(disclaimer: I still have good friends there. Tell 'em I said "hey!")
- Lee Campbell
elwin@media.mit.edu
------------------------------
Date: Sun, 2 May 93 12:23:14 +0200
From: ihle@iki101.inf.tu-dresden.de (Torsten Ihle)
Organization: Technical University Dresden, CS-Dept.
Subject: Evidence updating in hierarchical synthesis
Dear fellow netters !
I am currently writing my diploma thesis about hierarchical abstraction
(also known as hierarchical synthesis)
in model based image understanding.
I have already developed a system performing this task, but I want to improve
it significantly by introducing some sort of vagueness/uncertainty/fuzzyness, as
I am never able to expect perfect images due to noise and distortion.
Can anybody give me some hints about updating evidence (or certainty) in
hierachical models, preferable in AI- or IP-magazines (due to our poor library),
especially in image processing tasks. I already read some basic works concerning
the usage of Dempster/Shafer-Theory or Bayes-Theory (see my references below),
but I am still not able to "match" that with my image understanding task.
Any help would be appreciated
References :
\bibitem{Duda1976}
R.~O. Duda et~al.
Subjective bayesian methods for rule-based inference systems.
In {\em Proceedings of the National Computer Conference}, pages
1075--1082, 1976.
\bibitem{Gordon85}
J.~Gordon and E.~H. Shortliffe.
A method for managing evidential reasoning in a hierarchical
hypothesis space.
{\em Artificial Intelligence}, 26:323--357, 1985.
\bibitem{Johnson86}
R.~W. Johnson.
Independence and bayesian updating methods.
In {\em Artificial Intelligence\/} \cite{Duda1976}, pages 217--222.
\bibitem{Pearl86a}
J.~Pearl.
Fusion, propagation, and structuring in belief networks.
{\em Artificial Intelligence}, 29:241--288, 1986.
\bibitem{Pearl86}
J.~Pearl.
On evidential reasoning in a hierarchy of hypotheses.
In {\em Artificial Intelligence\/} \cite{Duda1976}, pages 9--15.
*******
Torsten Ihle, cand. inf., TU-Dresden
EMail: ihle@iki101.inf.tu-dresden.de
------------------------------
Date: Thu, 29 Apr 1993 01:53:52 -0500
From: Whoi-Yul Kim <wyk@utdallas.edu>
Subject: Director Position in Image Processing/Understanding
Call 214-991-3555 (Fax:214-980-4317) and ask for Scott Robson if you
are interested in this position. Feel free to redistribute this article.
The following info is an excerpt from their adversement.
=========x=========x=========x=========x=========x=========x=========x=========
E-Systems, a major worldwide developer and producer of high technology
electronic systems and products, has an opening for Director position
of the lab, Garland Division, located at Dallas, TX. The lab
specializes image processing and image understanding, and consists of
40 professionals including Ph.D.'s.
Position: Director
Salary: 100K - 130K/year
Qualification:
. Ph.D. required. Educational background should be in Physics, Math,
or Electrical Engineering.
. Management background must include 5+ years in the management of
technical groups which may include similar image processing R&D
organizations, engineering departments with major universities, or
similar engineering research and development groups within the DoD
industry.
. Technical background must include five plus years of experience in
the development of algorithms for image processing and/or image
understanding
. Must be familiar with start-of-the-art techniques of image
processing/understanding.
. Must have knowledge of start-of-the-art computer systems and
computing concepts, as well as experience in computer programming in
languages such as Fortran and C.
. Highly desirable that the final candidate be familiar with E-Systems
proprietary programs and be recommended for such by the E-Systems
proprietary customers.
. Experienced in managing research and contract budgets of several
million dollars per year. Cost center experience desired.
. Experienced and capable of acquiring funded studies and research in
the other of several million dollars per year.
. Must have the "big picture" and the "vision" of where image
processing technology, networks, computer systems and software are going.
. Must be creative in developing new business areas and new research
that will lead to new business.
. Ability to present technical information and concepts into high
ranking government officials and internal management.
. Capable of recruiting motivating, leading and retaining a highly
educated group of Research Scientists.
. Possion of Top Secret and SCI DoD Clearance is requried. If
candidate does not possess current clearance, must be capable of
obtaining both in a timely manner.
. Capable of being promoted to the Vice President of Engineering
position within the Division within 1-2 years.
Specific responsibilities include:
. Lead, motivate, and retain a very competent group (35-50) of
research scientists, managers, and technicians involved in
state-of-the art image processing/understanding research and
development efforts that support various product lines within the
Division.
. Provide the business acumen and technical leadership skills to
broaden the R&D efforts throughout the Division and strategically
plan the technical path that the Division needs to take over the
next 5-10 years.
. Be a primary interface with the customer on technical issues.
Explain complex technical concepts, approaches, and solutions to
senior administrators, customers, and in-house management team.
. Manage the budget and schedule of several million dollars per year
including capital equipment, research, and contract labor.
. Be creative in developing new business areas and new research that
will lead to new business for the Division. Continually evaluate
research from a business perspective.
------------------------------
Date: Fri, 30 Apr 1993 10:41:27 -0700
From: Philip Kahn <pkahn>
Subject: Final Program for the IEEE Workshop on Qaulitative Vision (June 14, 1993)
Program Announcement & Registration
===================================
IEEE WORKSHOP ON QUALITATIVE VISION
===================================
Monday, June 14, 1993
Omni Park Central, New York City, NY
WORKSHOP THEME
==============
Understanding, representing and incorporating information on object
qualities from disparate sources is key to building more general and
functional computer vision systems. Effective representation depends
upon:
* object attributes captured by a representation or description
* the interplay and synthesis of these qualities when multiple
object descriptions are available
* the computational aspect of object qualities that participate in
an effective representation
* functional object qualities that guide visual reasoning.
The goal of the IEEE Workshop on Qualitative Vision is to bring
together researchers from different disciplines for the active
discussion of the technical issues and problems related to the
development of qualitative vision techniques. This one day Workshop
will be held in New York City preceding CVPR93. Sessions will be led
by an invited talk, and reviewed papers will be discussed and
published in a Workshop proceedings distributed by IEEE. Issues to be
discussed include:
* the synthesis of multiple visual qualities (e.g., perceptual
grouping, reasoning over disparate sources)
* the study of salient features or object qualities (e.g., robust
features which are invariant under image transformations)
* efficient and innovative visual qualities to support purposive
operations (e.g., as exploited by active vision systems)
* discussion of differences between qualitative and reconstructive
approaches.
PRELIMINARY WORKSHOP PROGRAM
============================
8:00 - 8:20 Registration
8:20 - 8:25 Opening Remarks
8:25 - 9:00 Tutorial: Qualitative Reasoning
(Leo Joskowicz, IBM T.J. Watson Research Center)
9:00 - 10:00 Session 1: Reasoning & Recognition (Invited Talks)
-- W.B. Thompson, University of Utah
-- D. Ballard, University of Rochester
10:00 - 10:30 Coffee/Tea Break
Session 1: Reasoning & Recognition
10:30 - 11:40 Contributor Talks
- "Object recognition using steerable filters at
multiple scales ", D.H. Ballard & L.E. Wixson
- "Function-based recognition from incomplete
knowledge of shape," L. Stark, A. Hoover, D.B.
Goldof & K. Bowyer
- "Using Causal scene analysis to direct focus
of attention." L. Birnbaum, M. Brand & P. Cooper
- "Qualitatively describing objects using
spatial prepositions," A. Abella & J.R. Kender
- "Learning and recognition of 3D objects from
appearance," H. Murase & S.K. Nayar
- "Studying control of selective perception
using T-World and TEA," R.D. Rimey
- "Dynamic shading, motion parallex, and
qualitative shape," S. Walden & C.R. Dyer
- "Verifying the 'consistency' of shading
patterns and 3-D structures," P. Sinha &
E. Adelson
11:40 - 12:30 Discussion
12:30 - 2:00 Lunch
2:00 - 3:00 Session 2: Representation & Navigation (Invited Talks)
-- O.D. Faugeras, INRIA
-- G. Sandini, University of Genoa
3:00 - 3:30 Coffee/Tea Break
Session 2: Representation & Navigation
3:30 - 4:40 Contributor Talks
- "Motion understanding from qualitative visual
dynamics," E. Shavit & A. Jepson
- "On the use of size functions for shape
analysis," A. Verri, C. Uras, P. Frosini &
M. Ferri
- "A hierarchy of invariant representations of
3D shape," D. Weinshall
- "A geometric invariant for visual recognition
and 3D reconstruction from two
perspective/orthographic views," A. Shashua
- "On a study of invariant features in nonrigid
transformations," C. Kambhamettu, D.B. Goldof
& M. He
- "Motion constraint patterns," C. Fermuller
- "Finite resolution aspect graphs of polyhedral
objects," I. Shimshoni & J. Ponce
4:40 - 5:30 Discussion
5:30 - 7:30 Posters, Discussion, Snacks & Refreshments
WORKSHOP COMMITTEE
==================
Philip Kahn, Teleos Research, 576 Middlefield Road, Palo Alto, CA 94010
(415) 328-8879, FAX: 328-8879, Internet: pkahn@teleos.com
Yiannis Aloimonos, Computer Science Department,
University ofMaryland, College Park, MD 20742-3411
(301) 405-4526, FAX: 314-9115, Internet: yiannis@alv.umd.edu
Daphna Weinshall, Institute of Computer Science,
The Hebrew University of Jerusalem, 91904 Jerusalem, ISRAEL
FAX: 972-2-585-439, Internet: daphna@cs.huji.ac.il
FOR FURTHER INFORMATION
=======================
For additional Workshop information, please contact Philip Kahn,
Teleos Research, 576 Middlefield Road, Palo Alto, CA 94301, (415)
328-8879, email: pkahn@teleos.com .
ADVANCE REGISTRATION (before May 21, 1993)
==========================================
PLEASE ADVANCE REGISTRATION MAIL TO: WQV Advance Registration
IEEE Computer Society
1730 Massachusetts Avenue NW
Washington, D.C. 20036-1992
OR FAX TO: (202) 728-0884
Name:
Company:
Address/Mailstop:
City/State/Zip/Country:
Daytime Number: FAX Number:
IEEE Membership Number: Email:
Do you have any special needs?
Workshop fees:
+-----------------------+-----------+-------------+------------+
| | Member | Non-Member | Student |
+-----------------------+-----------+-------------+------------+
| Advance Registration | $90 | $110 | $35 |
| (until 5/14/93) | | | |
+-----------------------+-----------+-------------+------------+
| Late/On-Site | | | |
| Registration | $110 | $135 | $45 |
| (after 5/14/93) | | | |
+-----------------------+-----------+-------------+------------+
Total Enclosed: $
PAYMENT MUST BE ENCLOSED. MAKE ALL CHECKS PAYABLE TO: IEEE COMPUTER SOCIETY.
ALL CHECK MUST BE IN U.S. DOLLARS DRAWN ON U.S. BANKS.
Method of payment accepted (check only one):
o Personal check o Company check o Traveller's check
o MasterCard o VISA o American Express o Diner's Club
o Purchase order (original included with this form)
Credit Card Number: Exp. Date:
Cardholder Number:
Signature:
Written requests for refund must be received in the APPROPRIATE office
no later than May 21, 1993. Refunds are subject to a $50 processing
fee. All no-show registrations will be billed in full. Registration
after May 21, 1993 will be accepted on-site only.
Do not include my mailing address on (check all that apply):
o Non-Society Mailing Lists o Meeting Attendee Lists
LOCAL ARRANGEMENTS FOR CVPR93 WILL BE USED FOR THE WORKSHOP.
BELOW IS LODGING AND TRAVEL INFORMATION PROVIDED FOR CVPR93
(thanks to T. Boult at Columbia).
HOTEL INFORMATION
=================
The hotel is:
Park Central Hotel
870 Seventh Avenue
56th and Seventh
New York, NY 10019
(800) 346-1359 or (212) 484-3300
Fax: (212) 484-3374
Reserved rooms will be held until 6pm unless payment is guaranteed by first
night's deposit or an accepted credit card number and signature. All WQV/CVPR
reservations must be in by 5pm Friday May 21. Reservations will be accepted
after this date based on availability of accommodations and will be confirmed
at the convention rate.
Rates:
$109 --- Single
$119 --- Double 1 bed
$119 --- Double 2 bed
call --- Suites
No charge for children under 17 years when sharing room with parents.
STUDENT HOUSING
===============
There is a limited amount of student housing available on Columbia's campus.
Columbia is located on the #1 subway line making it a short ride to the
conference hotel. More information and directions are available via ftp.
Student housing must be paid in advance. A non-refundable 15% deposit is
DUE BY APRIL 15, AND FULL PAYMENT BY MAY 15. There is, no ``block'' of rooms,
so their is no guarantee of a room until the deposit is received. There are
two types of rooms: type-1 which are air conditioned suites with 2 or 4
(separate) bedrooms sharing a a living/dining room with TV, a kitchen and
bathroom/shower), and type-2 which are NOT air conditioned and which have a
bathroom/shower and TV lounge shared by 15-20 rooms. All student housing is
co-ed.
The earlier you book the room the better the chance of getting type 1 rooms.
``Grouping" of rooms can be arranged ONLY IF THE REQUESTS are send in the same
package. If you request type one housing and none is left you should let us
know if you want a type 2 instead (with a refund of the difference) or a full
refund.
This ``student'' housing is available as follows:
From -- To Plan Type-1 | Plan Type-2
3pm -- 10am Code Cost | Code Cost
Sat 6/12 -- Sat 6/19 A-t1 $208 | E-t2 $160
Sat 6/12 -- Fri 6/18 B-t1 $178 | F-t2 $137
Sun 6/12 -- Fri 6/18 C-t1 $148 | G-t2 $115
Mon 6/12 -- Fri 6/18 D-t1 $118 | H-t2 $90
Send email to cvpr_student_housing@cs.columbia.edu as soon as possible with
your requests. We reiterate there is no ``block'' of rooms, so their is no
guarantee of a room until the 15% deposit is processed. Send plan choice and a
check, payable in US dollars to Columbia University, to:
CVPR Student Housing c/o T. Boult
450 Comp. Sci Building
Department of Computer Science
Columbia University, NYC NY 10027.
The number of ``student" rooms is rather limited; if you are interested do not
delay, send email today.
TRAVEL, MISC INFO
=================
There is no ``special'' airline, call your travel agent for best prices. NYC
is one of the cheapest airline destinations, and it may pay to shop around a
little. NYC is served by 3 airports: JFK, LaGuardia and Newark (NJ).
There is a shuttle bus (Grayline, Inc.) between the hotel and the area airports
at a cost of $15 (JFK), $12 (LaGuardia) and $17 (Newark). Book your shuttle
by calling 1-800-451-0455 or (212)315-3006 or calling the hotel and asking for
extension 175. If you plan to arrive as a group, a discount can be
prearranged. You can also take a cab, the cost between $25 and $35, can also
be split. For the really budget conscious, there are bus/subway combinations
which only cost 1-3 dollars, get details via ftp.
There is a garage right next to the hotel. A car is not very useful in NYC,
parking is a hassel or is expensive ($\approx$ $10 a day). Consider using
public transportation if you can, otherwise ftp driving_directions.
If you are coming from the east coast, don't forget the train, which is
generally cheaper and sometimes more convenient. Amtrak trains will take you
to 34th st Penn Station NY. From there take a cab to the hotel or take the #1
or A or C line subway's to 59th street and walk (get a local map via ftp if
you like).
For those with children, the hotel does not, unfortunately, have a day care
center. They suggest contacting the Babysitting Guild (212)682-0227, who will
do in-hotel sitting.
If you are interested in theater tickets to a play, a musical, or an opera,
consider booking them now. Popular times for some shows, e.g Les Miserables
and Phantom of the Opera, are nearly sold-out 3-6 months in advance. Call the
hotel and ask for the theater desk (x175). They also book a variety of NYC
sightseeing tours including ones to Liberty and/or Ellis islands.
------------------------------
Date: Sun, 2 May 1993 23:18:25 -0500
From: bovik@cs.utexas.edu (Alan C. Bovik)
Subject: CFP: First IEEE International Conference on Image Processing
FIRST IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
November 13-16, 1994
Austin Convention Center, Austin, Texas, USA
PRELIMINARY CALL FOR PAPERS
Sponsored by the Institute of Electrical and Electronics En-
gineers (IEEE) Signal Processing Society, ICIP-94 is the inaugur-
al international conference on theoretical, experimental and ap-
plied image processing. It will provide a centralized, high-
quality forum for presentation of technological advances and
research results by scientists and engineers working in Image
Processing and associated disciplines such as multimedia and
video technology. Also encouraged are image processing applica-
tions in areas such as the biomedical sciences and geosciences.
SCOPE:
1. IMAGE PROCESSING: Coding, Filtering, Enhancement, Restoration,
Segmentation, Multiresolution Processing, Multispectral Process-
ing, Image Representation, Image Analysis, Interpolation and Spa-
tial Transformations, Motion Detection and Estimation, Image Se-
quence Processing, Video Signal Processing, Neural Networks for
image processing and model-based compression, Noise Modeling,
Architectures and Software.
2. COMPUTED IMAGING: Acoustic Imaging, Radar Imaging, Tomography,
Magnetic Resonance Imaging, Geophysical and Seismic Imaging, Ra-
dio Astronomy, Speckle Imaging, Computer Holography, Confocal Mi-
croscopy, Electron Microscopy, X-ray Crystallography, Coded-
Aperture Imaging, Real-Aperture Arrays.
3. IMAGE SCANNING DISPLAY AND PRINTING: Scanning and Sampling,
Quantization and Halftoning, Color Reproduction, Image Represen-
tation and Rendering, Graphics and Fonts, Architectures and
Software for Display and Printing Systems, Image Quality, Visual-
ization.
4. VIDEO: Digital video, Multimedia, HD video and packet video,
video signal processor chips.
5. APPLICATIONS: Application of image processing technology to
any field.
PROGRAM COMMITTEE:
GENERAL CHAIR: Alan C. Bovik, U. Texas, Austin
TECHNICAL CHAIRS: Tom Huang, U. Illinois, Champaign and
John W. Woods, Rensselaer, Troy
SPECIAL SESSIONS CHAIR: Mike Orchard, U. Illinois, Champaign
EAST EUROPEAN LIASON: Henri Maitre, TELECOM, Paris
FAR EAST LIASON: Bede Liu, Princeton University
SUBMISSION PROCEDURES
Prospective authors are invited to propose papers for lecture or
poster presentation in any of the technical areas listed above.
To submit a proposal, prepare a 2-3 page summary of the paper in-
cluding figures and references. Send five copies of the paper
summaries to:
John W. Woods
Center for Image Processing Research
Rensselaer Polytechnic Institute
Troy, NY 12180-3590, USA.
Each selected paper (five-page limit) will be published in the
Proceedings of ICIP-94, using high-quality paper for good image
reproduction. Style files in LaTeX will be provided for the con-
venience of the authors.
SCHEDULE
Paper summaries/abstracts due: 15 February 1994
Notification of Acceptance: 1 May 1994
Camera-Ready papers: 15 July 1994
Conference: 13-16 November 1994
CONFERENCE ENVIRONMENT
ICIP-94 will be held in the recently completed state-of-the-art
Convention Center in downtown Austin. The Convention Center is
situated two blocks from the Town Lake, and is only 12 minutes
from Robert Meuller Airport. It is surrounded by many modern
hotels that provide comfortable accommodation for $75-$125 per
night.
Austin, the state capital, is renowned for its natural hill-
country beauty and an active cultural scene. Within walking dis-
tance of the Convention Center are several hiking and jogging
trails, as well as opportunities for a variety of aquatic sports.
Live bands perform in various clubs around the city and at night
spots along Sixth Street, offering a range of jazz, blues,
country/Western, reggae, swing and rock music. Day temperatures
are typically in the upper sixties in mid-November.
An exciting range of EXHIBITS, VENDOR PRESENTATIONS, and SOCIAL
EVENTS is being planned. Innovative proposals for TUTORIALS, and
SPECIAL SESSIONS are invited.
For further details about ICIP-94, please contact:
Conference Management Services
3024 Thousand Oaks Drive
Austin, Texas 78746
Tel: 512/327/4012; Fax:512/327/8132
email: icip@pine.ece.utexas.edu
PRELIMINARY CALL FOR PAPERS
FIRST IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
November 13-16, 1994
Austin Convention Center, Austin, Texas, USA
------------------------------
Date: Fri, 30 Apr 93 11:00:47 BST
From: sta6cag@gps1.leeds.ac.uk
Subject: 13th Leeds Statistical Research Workshop
FIRST NOTICE 13th LEEDS STATISTICAL RESEARCH WORKSHOP FIRST NOTICE
JULY 12 - 14, 1993
SHAPE RECOGNITION IN 2-D AND 3-D IMAGES
Keynote lectures:
Professor Josef Kittler, University of Surrey, UK, will present a
paper on parametric shape detection based on robust statistical
hypothesis testing with applications in computer vision and image
analysis.
Professor Michael Miller, University of Washington, Missouri, USA,
will give two talks on jump-diffusion processes for inferring 1, 2,
and 3-D shape as used in electron microscopy and automatic target
tracking and recognition.
Other contributions:
There will be short talks from other contributors, including Professor
Colin Goodall, Penn State, USA, Professor David Hogg, Leeds, UK, and
Professor Michael Werman, Jerusalem, Israel, describing recent
developments in 2-D and 3-D shape pertaining to their own particular
research area, and a poster session.
If you would like to present a short talk or a poster, or just to come
along to the workshop then for more details contact
Dr. Christine Gill, Department of Statistics,
University of Leeds, Leeds LS2 9JT.
telephone - Leeds (0532) 335157 email - sta6cag@uk.ac.leeds.gps
CLOSING DATE FOR CONTRIBUTIONS - FRIDAY 21ST MAY 1993
CLOSING DATE FOR BOOKINGS - FRIDAY 25TH JUNE 1993
------------------------------
Date: 30 Apr 93 13:55:26 GMT
From: icw@ecs.soton.ac.uk (I C Wolton)
Organization: Electronics and Computer Science, University of Southampton
Subject: Parallel Vision Algorithms Workshop
One-day Workshop on Parallelising Vision Algorithms
Chilworth Manor Conference Centre, Southampton, UK
20 May 1993
The richness of information offered by artificial vision makes it an
attractive sensing option for automated systems such as intelligent
autonomous robots, surveillance and monitoring, inspection and
manipulation, and the teleloperation of remote effectors/vehicles in
hostile environments (space, underwater, nuclear, mining...). All of these
tasks demand realtime response from vision, a requirement rarely achievable
with currently available serial processors.
The desire for greater computational performance has encouraged vision
research towards parallelism, particularly the use of transputer arrays.
In bringing together researchers active in the development of these
realtime vision systems with those in parallel processing, we hope not only
to promote the most recent advances in parallelising visual algorithms, but
to increase awareness of the latest developments in concurrent computation
within the vision community.
Presenters drawn from academia and industry will describe the
parallelisation of vision algorithms developed initially for serial
implementation and their transfer to parallel architectures, as well as
algorithms developed specifically for parallelism. An overview of
forthcoming developments in parallel systems and software will also be
included. This one-day workshop is intended to promote interaction between
these two research areas and will close with an informal discussion on the
future potential of parallel vision.
Provisional Programme
Dynamic and Adaptive Contours R. Curwen,
University of Oxford
Parallel Attentive Vision J. Roberts,
University of Southampton
A Parallel Implementation of the DROID vision E. Spark,
system Roke Manor Research
Parallel Image Segmentation R. Dawkins,
Sowerby Research Centre (BAe)
An Heterogenous Architecture for Machine Vision A. Sheen,
Sowerby Research Centre (BAe)
A Parallel Pipelined Architecture for Real-time P. McLauchlan,
Vision on Transputers University of Oxford
Real-Time Image Processing and Control at GEC D. Castelow,
GEC Hirst Research Centre
+ 2 other speakers to be arranged,
The workshop fee will be 50 pounds to include coffee, lunch and tea.
Cheques should be made payable in pounds sterling to "University of Southampton"
Bookings should be sent to: Technical enquiries to:
Christine Collier Dr. D. Charnley
Dept. of Electronics & Computer Science Dept. of Aeronautics & Astronautics
University of Southampton University of Southampton
Southampton S09 5NH Southampton S09 5NH
Tel: 0703 592069 Tel: 0703 592318
Fax: 0703 593045 Fax: 0703 593058
Email: cdc@uk.ac.soton.ecs Email: debra@uk.ac.soton.aero
------------------------------
Date: Sat, 1 May 1993 17:51:54 GMT
From: srihari@acsu.buffalo.edu (Sargur Srihari)
Organization: SUNY at Buffalo / Ctr for Document Analysis and Recog (CEDAR)
Subject: Intn'l Handwriting Recognition Wkshp
P R O G R A M
THIRD INTERNATIONAL WORKSHOP
on
FRONTIERS IN HANDWRITING RECOGNITION
Sponsored by
IAPR Technical Committee on Text Processing (TC-11)
Supported by
United States Postal Service
Center of Excellence for Document Analysis and Recognition
Monday, May 24, 1993
4:00 pm - 8:00 pm Registration
Tuesday, May 25
7am Registration
8:00 Welcome Aaron Bloch Provost, SUNY at Buffalo
Sargur N. Srihari Director, CEDAR, SUNY at Buffalo
** Session 1: Digit Recognition
Chair: Richard Casey
8:30 Recognition of Unconstrained Handwritten Numerals Based
on Dual Cooperative Neural Network
Sukhan Lee, Yeongwoo Choi University of Southern California, USA
9:00 An Optimal Method of Combining Multiple Experts for Hand-
written Numerical Recognition
Y.S. Huang, C.Y. Suen Concordia University, Canada
9:30 Automated Feature Generation for Handwritten Digit Recognition
by Neural Networks
Paul D. Gader, Mohamed Ali Khabou U. of Missouri-Columbia, USA
10:00 Break
** Session 2: Character Recognition
Chair: Shunji Mori
10:30 Refining Curvature Feature Extraction to Improve Handwriting Recognition
R. Legault, C.Y. Suen Concordia University, Canada
11:00 The Interpretation and Reconstruction of Interfering Strokes
D. S. Doermann, A. Rosenfeld U. of Maryland at College Park, USA
11:30 Off-Line Recognition of Large-set Handwritten Hangul (Kore-
an script) with Hidden Markov Models
H.S. Park, Seong-Whan Lee Chunbuk National University, Korea
12:00 A Model of Structural Pattern Transformation of Handwritten
Characters
Hirobumi Nishida, Shunji Mori Ricoh, Japan
12:30 Lunch University Inn and Conference Center
** Session 3: Word Recognition 1
Chair: Gilles Houle
2:00 Holistic Lexicon Reduction
Sriganesh Madhvanath, Venu Govindaraju SUNY at Buffalo, USA
2:30 An Alternative to Variable Duration HMM in Handwritten Word Recognition
Mou-Yen Chen, Amlan Kundu SUNY at Buffalo, USA
3:00 Handwritten Word Recognition Using Collective Learning
Systems Theory
G. Houle, C. Radelat, S. Resnick, P. Bock Arthur D. Little, Inc., USA
3:30 Break
** Session 4: Pictograms, Databases
Chair: Mindy Bokser
4:00 Approximate Matching of Hand-Drawn Pictograms
Daniel P. Lopresti, Andrew Tompkins MITL, USA
4:30 Concerns in Creation of Image Databases
Richard Fenrich, Jonathan Hull SUNY at Buffalo, USA
5:00 Database Panel: Chair: Jonathan Hull
Brief presentations by several organizations that handle large
databases. Baseline performance on the CEDAR CD-ROM will be discussed.
6:30 Reception Student Union, SUNY at Buffalo Amherst Campus
(Transportation from/to University Inn provided)
8:30 CEDAR Tour
Wednesday, May 26
7:00 am Registration
8:00 Plenary Session
On the Robustness of Recognition of Degraded Line Images
Jean-Claude Simon A2IA, France
** Session 5: Word Recognition 2
Chair: Sebastiano Impedovo
9:00 Lexicon Directed Segmentation-Recognition Procedure for
Unconstrained Handwritten Words
F. Kimura, M. Shridhar, U. of Michigan-Dearborn, USA
N. Narasimhamurthi
9:30 An Off-Line Handwriting Recognition System Using Recurrent
Error Propagation Networks
Andrew Senior, F. Fallside University of Cambridge, UK
10:00 Break
** Session 6: Digit Recognition 2
Chair: Ching Suen
10:30 Using Mixtures of Deformable Models to Capture Variations
in Hand Printed Digits
M. Revow, C. K.I. Williams, G. E. Hinton Univ. of Toronto, Canada
11:00 Handprinted Digit Recognition: A Comparison of Algorithms
Dar-Shyang Lee, Sargur N. Srihari SUNY at Buffalo, USA
11:30 Handwritten Numeral Recognition Using LAT with Structural
Information
Toru Wakahara Ministry of Posts and Telecommunications, Japan
12:00 Pattern Recognition by Stochastic Modeling
Eugene M. Kleinberg, Tin Kam Ho SUNY at Buffalo/AT&T Bell Laboratories, USA
12:30 Lunch University Inn and Conference Center
** Session 7: Handwriting Interpretation Systems
Chair: Andrew Downton
2:00 Is Recognition and Interpretation of Handwritten Text A Scene
Analysis Problem?
G. Lorette, Y. Lecourtier University of Rennes, France
2:30 Interpretation of Handwritten Addresses in US Mail Stream
Venu Govindaraju, Ajay Shekhawat, SUNY at Buffalo, USA
Sargur N. Srihari
3:00 A Fuzzy Approach to Handwritten Address Verification
Hendrawan, A. C. Downton, C. G. Leedham University of Essex, UK
3:30 Break
4:00 Poster Session 1: Character Recognition
6:30 Workshop Dinner Marine Midland Tower, Buffalo
(Transportation provided)
Ray Morgan, Guest Speaker Manager of Advanced Research,
United States Postal Service
Thursday, May 27
7:00 am Registration
** Session 8: On-Line Recognition 1
Chair: Rejean Plamondon
8:00 Description of On-Line Script Based on Hollerbach's Generation Model
G. H. Abbink, H. L. Teulings, University of Nijmegen,
L. R. B. Schomaker Netherlands
8:30 On-Line Handwriting Recognition Based Upon Continuous
Parameter Mixture Densities
Eveline J. Bellegarda, Jerome R. Bellegarda, IBM T.J. Watson Research
David Nahamoo, Krishna Nathan Center, USA
9:00 On-Line Unconstrained Handwriting Recognition by a Proba-
bilistic Method
Tetsu Fujisaki, Krishna Nathan, Wongyu Cho, IBM Research Division, USA
Homayoon Beigi
9:30 On-Line Handwritten Kanji Character Recognition Using Hypothesis
Generation in the Space of Hierarchical Knowledge
Kenji Ohmori Hosei University, Japan
10:00 Break
10:30 Poster Session 2: Word Recognition
12:30 Lunch University Inn and Conference Center
** Session 9: On-Line Recognition 2
Chair: Hans-Leo Teulings
2:00 Allograph Adjacency Constraints for Cursive Script Recognition
Marc Parizeau, Rejean Plamondon Ecole Polytechnique de Montreal, Canada
2:30 A Signature Verification System Based on a Dynamical Segmentation
Technique
G. Dimauro, S. Impedovo, G. Pirlo Universita degli Studi di Bari, Italy
3:00 Performance Analysis of Handwritten Strokes Generation Models
Adel Alimi, Rejean Plamond Ecole Polytechnique de Montreal, Canada
3:30 Break
** Session 10: Language Models in On-Line Systems
Chair: Guy Lorette
4:00 Use of Language Models in On-line Sentence/Phrase Recognition
Rohini K. Srihari, Stayvis Ng, SUNY at Buffalo, USA
Charlotte M. Baltus, Jackie Kud
4:30 A Blackboard Approach to On-line Cursive Handwriting Recognition
for Pen-Based Computing
P. E. Bramall, C. A. Higgins The University of Nottingham, UK
5:00 Applications Panel:
Several members of the industrial community will provide
their insights on directions for handwriting recognition vis-a-vis
commercially available products.
6:30 Niagara Falls Tour
POSTER SESSIONS
Wednesday, May 26
Poster Session 1: Character Recognition
Experiments with the CENPARMI Data Base Combining Different
Classification Approaches
Jurgen Franke, Daimler-Benz Research Center,Ulm, Germany;
Louisa Lam, Raymond Legault, Concordia University, Canada
Christine Nadal, Ching Y. Suen
THETA(1) Feature Extraction for Handwritten Character Recognition
Phil Rhee, Ju-hyoung Yoo Inha University, Korea
Gradient Representation for Handwritten Character Recognition
Geetha Srikantan
Hand Printed Numeral Recognition with the Learning Distance Function
Takahiko Kawatani NTT Corp., Japan
Invariant Handwritten Numeral Recognition with Spatio-temporal
Feature Representation
Sukhan Lee, Jack C. Pan U. of Southern California, USA
A New Pattern Recognition Method Using Non-Linear Transformation
Bunpei Irie Toshiba Corporation, Japan
Normalization-Cooperation Feature Extraction Method for Hand
Printed Kanji Character Recognition
M. Hamanaka, Keiji Yamada, Jun Tsukumo NEC Corp., Japan
A PC Based Handwritten Chinese Character Recognition system
Lo-Ting Tu, Win-Win Lin, Industrial Technology Research
Yung-Kuan Chan, Ing-Shyh Shyu Institute, Chutung, Taiwan
Recognition of Handwritten Characters by Quasi-monotonic
Programmed Array Grammars with Attribute Vectors
Rudolf Freund Technical University of Vienna, Austria
Recognition of Handwritten Characters Using A Character
Reduction Methodology
N. Pereira, N. Bourbakis SUNY at Binghamton, USA
The Writing Instruction Script Hebrew (WISH) System
Jon W. McKeeby, Rachelle S. Heller, George Washington Univ., USA
Yael Moses
Thursday, May 27
Poster Session 2: Word Recognition
Cursive Handwriting Word Spotting Using A Discrete Dynamic
Approach
Yoram Singer, Naftali Tishby The Hebrew University of Jerusalem,
Israel
Hypothesis Evaluation for Word Recognition
Chien-Huei Chen, Gregory K. Myers SRI International, USA
On-Line Handwritten Word Recognition: An Approach Based on
Hidden Markov Models
S. Bercu, G. Lorette University of Rennes, France
Partition of Documents Based on a Complexity Measure for the
Purpose of Text-Independent Writer Identification
Isao Yoshimura, Mitsu Yoshimura, Science University of Tokyo, Japan
Hajime Uno
A Principled Performance Measure for Handwriting Recognition
Eric Sven Ristad Princeton University, USA
Reading Cursive Script by Parts
Mohamed Cheriet Universite du Quebec, Canada
Recognition of Handwritten Word Images by Statistical Methods
Torsten Caesar, Joachim Gloger, Daimler-Benz Research Center
Alfred Kaltenmeier, Eberhard Mandler Ulm, Germany
Recognition of Handwritten Words in a Limited Dynamic
Vocabulary
Michel Gilloux, Jean-Michel Bertille, Service de Recherche Technique
Manuel Leroux de la Poste, France
Recognition of State Name Abbreviations
Jian Zhou, Venu Govindaraju, SUNY at Buffalo, USA
Raj S. Acharya, Sargur N. Srihari
SCRIPTOR: An On-Line Recognition Engine of Cursive
Handwriting with Incremental Learning Capabilities
P. Morosso, L. Gismondi, E. Musante, Universita di Genova, Italy
A. Pareto
Segmentation & Recognition of Cursive Handwriting with Improved
Structured Lexica
Ingolf Karls, Gerd Maderlechner, Volkmar Pflug, Siemens AG, Germany
Stephen Baumann, Achim Weigel, Andreas Dengel
Demonstrations
Demonstrations will be shown concurrently with pa-
per presentations. They will also be available during
breaks and the poster sessions. Scheduled demon-
strations include, but are not limited to:
% CCL On-Line/Off-Line Chinese Character ITRI, Taiwan
Recognition System
% Handwritten Address Interpretation SUNY at Buffalo, USA
% Handwritten Word Recognition Paragraph International, USA
% On-Line Digit/Word Recognition SUNY at Buffalo, USA
% Use of Language Models SUNY at Buffalo, USA
% Lexicon Directed Handwritten Word University of
Recognition Michigan at Dearborn, USA
% On-Line Cursive Handwriting Recognition Nijmegen Institute for
Cognition and Information, Netherlands
% On-Line Cursive Script Recognition KAIST, Korea
Open House
An open house will be held at CEDAR on the morning
of Friday May 28, 1993 from 8:00 am to 12:00 noon.
SUNY at Buffalo Amherst Campus and University Inn and Conference Center
Committees
General Chairman
Sargur (Hari) Srihari
SUNY at Buffalo, USA
** Program Committee
Mindy Bokser
Calera Recognition Systems, USA
Richard Casey
IBM Almaden Res. Center, USA
Andrew Downton
University of Essex, UK
Richard Fenrich
SUNY at Buffalo, USA
Venu Govindaraju
SUNY at Buffalo, USA
Jonathan Hull
SUNY at Buffalo, USA
Sebastiano Impedovo
Universita de Bari, Italy
Guy Lorette
IRISA, France
Shunji Mori
Ricoh Corporation, Japan
Rejean Plamondon
Ecole Polytechnique Montreal Canada
Jean-Claude Simon
A2I, Paris, France
Ching Suen
Concordia University, Canada
Hans-Leo Teulings
Nijmegen Institute, Netherlands
** Local Organizing Committee
Richard Fenrich (Chairman)
Heike Berlind
Rita Hamilton
Joseph Piazza
Eugena Smith
Tim Stives
Program Summary
May 25-27, 1993
Monday, May 24, 1993
4:00 pm P 8:00 pm Registration
Tuesday, May 24, 1993
8:00 am Welcome
8:30 Session 1: Digit Recognition 1
10:00 Break
10:30 Session 2: Character Recognition
12:00 Lunch
2:00 Session 3: Word Recognition 1
3:30 Break
4:00 Session 4: Pictograms, Databases
5:00 Database Panel
6:30 Reception
8:30 CEDAR Tour
Wednesday, May 25, 1993
8:00 am Plenary Session
9:00 Session 5: Word Recognition 2
10:00 Break
10:30 Session 6: Digit Recognition 2
12:30 Lunch
2:00 Session 7: Interpretation Systems
3:30 Break
4:00 Poster Session 1
6:30 Workshop Dinner
Thursday, May 25, 1993
8:00 am Session 8: On-Line Recognition 1
10:00 Break
10:30 Poster Session 2
12:30 Lunch
2:00 Session 9: On-Line Recognition 2
3:30 Break
4:00 Session 10: Use of Language Models
5:00 Applications Panel
6:30 Niagara Falls Tour
Friday, May 25, 1993
9:00 am - 12 noon CEDAR Open House
General Information
Registration
The registration/help desk will be available from
7:00 am to 5:30 pm on May 25-27, 1993. In addition,
the desk will open on May 24, 1993 from 4:00 pm to
8:00 pm.
Questions may be directed to:
Rita Hamilton or Natalie Leaver
UB Commons
520 Lee Entrance, Suite 202
Amherst NY 14228-2576
(716) 645-6164 extension 112 or 114
Fax: (716)J645-6176
email: hamilton@cs.buffalo.edu, leaver@cs.buffalo.edu
A limited number of late registrations are available.
To register for the IWFHR III please complete the following:
Name: ______________________________________
Organization: ______________________________
Address:____________________________________
City: __________ State ________ Zip ________
Country: ___________________________________
Phone number: ______________________________
Fax number: ________________________________
Email address: _____________________________
Registration fees:
Student: $120 (Proof of student status required.
Photocopy of student ID acceptable).
Author: $330
Non-Author: $480
Luncheons provided daily during the Workshop.
Workshop dinner held on the evening of May 26th.
Payment Information:
We will accept checks, money orders, bank drafts,
and Mastercard, Visa and Diners Club.
Please contact CEDAR Research Group, UB Commons,
520 Lee Entrance, Suite 202, Amherst, NY 14228-2567
(Phone: 716-645-6164; Fax: 716-645-6167).
Accommodations:
The University Inn (Conference site) (716) 636-7500; (fax) (716) 636-8296
Single: $68; Double $78; Parlor only suite: $90; Parlor & 1 Bedroom $135\
Hampton Inn Amherst (716) 689-4414; (fax) (716) 689-4382
Single: $59; Double $66
Heritage House Country Inn (716) 633-4900 (same number for fax)
Single: $40; Double $50
Marriott Inn (716) 689-6900; (fax) (716) 689-0483
Single: $78; Double $78
------------------------------
End of VISION-LIST digest 12.21
************************
