Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 11 Issue 38
VISION-LIST Digest Fri Nov 06 01:55:05 PDT 92 Volume 11 : Issue 38
- 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:
***** Vision List is moving *****
Good color TV camera wanted
Active Stereo Vision Systems
Looking for Medical X-ray images?
Biomedical image sequences needed
C-Source code for A FAST LINEAR SHAPE FROM SHADING
Software for pattern recognition
Curvilinear Feature Extraction
Research Assistant (Computer Vision), U-Geneva, Switzerland
Machine Vision and Applications Journal Info
NIST Special Databases and Software (neat & long)
Correction to fl3 distribution
JET POSTE'93
International Handwriting Recognition Workshop
----------------------------------------------------------------------
From: vision (Vision-List-Request)
Date: Wed, 28 Oct 92 11:27:53 -0800
Subject: ***** Vision List is moving *****
Status: R
I have moved from Advanced Decision Systems, a division of Booz*Allen
& Hamilton to Teleos Research. I will move the Vision List to Teleos
with me, and that transition period will impact the Vision List and
the Archives.
Plans are to maintain all the current services including the ftp Vision
List Archive. I will notify all of you when the switchover has occured, and
mail forwarding and aliases will keep the old addresses alive for a time.
I suggest that you access the archives within the next several days
to avoid a possible outage of the ftp service that may occur for several
days or more during this transition.
I would appreciate it if you notify me of all problems you encounter so
that they can be fixed as soon as possible. With a bit of patience and
some wrenches, this transition should be relatively painless.
Please continue sending mail to Vision-List-Request@ADS.COM and
Vision-List@ADS.COM until notified to do otherwise.
cheers,
phil...
------------------------------
Date: 26 Oct 92 13:29:34 CET
From: "Vladimir Smutny" <SMUTNY@vision.felk.cvut.cs>
Organization: Czech Technical University
Subject: Good color TV camera wanted
Dear friends,
I am working on the analysis and measurement of color images.
I am looking for reasonably good color TV camera for this purpose.
We have PANASONIC WV CL 110e, which does not satisfy my requirements.
We suppose that the good camera which enables also some kind of
quantitative evaluation of color images has probably 3 chips (for
RGB) and RGB vystup. My upper limit of budget is about 4000 U.S. $.
Have you any tips for type of camera or another experiences or
recomandations (bad experiences are also helpful).
Thank you in advance for your messages
Vladimir Smutny
Vladimir Smutny Karlovo nam. 13
Computer Vision Laboratory 121 35 Prague 2
Faculty of Electrical Engineering Czechoslovakia
Czech Technical University of Prague phone ++42 2 295664
e-mail smutny@vision.felk.cvut.cs fax ++42 2 290159
or smutny@cspuni12.bitnet
------------------------------
Date: Thu, 29 Oct 92 18:50:56 +0000
From: J.Pretlove@mech.surrey.ac.uk
Subject: Active Stereo Vision Systems
I am interested in Active Stereo Vision Systems particularly for
robotic based research although any controllable stereo based vision
system would be of interest.
I know about systems at: Harvard, AUC (Denmark), CVAP (Sweden), Trish
(Toronto), Pennsylvania, Surrey (of course),......
Does anyone know of any other systems and if so could
they e-mail me at:
j.pretlove@mech.surrey.ac.uk
I will post a summary if there is enough interest.
Thank you very much
John Pretlove
* John Pretlove * Phone: +44 (0)483 300800 x2376 *
* Mechatronics & Robotics * Fax : +44 (0)483 306039 *
* Research Group * *
* Dept of Mechanical Engineering* Email: j.pretlove@uk.ac.surrey *
* University of Surrey * *
* Guildford, Surrey * *
* GU2 5XH, England * *
------------------------------
Date: Thu, 15 Oct 92 15:59:32 CDT
From: schultz@hivehom.serc.3m.com (John C. Schultz)
Subject: Looking for Medical X-ray images?
Does anyone have some ftp'able medical X-ray images?
Things like hands, skulls,... 8 bits or more per pixel would be
adequate.
Thanks.
------------------------------
Posted-Date: Mon, 26 Oct 92 10:36:08 CST
Date: Mon, 26 Oct 92 10:36:08 CST
From: keith@vision.ee.utexas.edu (Keith A. Bartels)
Subject: biomedical image sequences needed
Hi all,
I'm doing research into shape change analysis in biomedical images. I was
wondering if anyone has any or knows of any images sequences that I can use
for my work. Particularly, I need a sequence of three-dimensional images
(e.g. MRI data, confocal microscope images) from any imaging modality. I
could also use some 2D image sequences of any biological process. Can anyone
help?
Thanks, Keith Bartels
------------------------------
Date: Thu, 22 Oct 92 11:29:19 EDT
From: shah (Mubarak Shah)
Subject: C-Source code for A FAST LINEAR SHAPE FROM SHADING
The C source code and images are available for anonymous ftp.
A FAST LINEAR SHAPE FROM SHADING
By
PING-SING TSAI AND MUBARAK SHAH
DEPARTMENT OF COMPUTER SCIENCE
UNIVERSITY OF CENTRAL FLORIDA
ORLANDO, FL 32816
Abstract
In this paper, we present an extremely simple algorithm for shape from
shading, which can be implemented in 25 lines of C code (code included),
and which converges in one to two iterations.
The algorithm is very fast, taking .2 seconds on a Sun SparcStation-1 for a
$128 \times 128$ image, and is purely local and highly parallelizable
(parallel implementation included). The algorithm gives a solution which
is proveably convergent and unique, and is general in that it works for
both the Lambertian and Specular reflectance functions. In our approach, we
employ a linear approximation of the reflectance function, as used by others.
However, the major difference is that we first use the discrete approximations for
surface normal, $p$ and $q$, using finite differences, and
then linearize the reflectance function
in depth, $Z(x,y)$, instead of $p$ and $q$. The algorithm has been
tested on several synthetic and real images of both Lambertian and
specular surfaces, and good results have been obtained.
It gives good results even for the spherical surfaces, in contrast to
other linear methods.
sono 124% ftp eustis.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 (132.170.108.100,1045) (0 bytes).
shading
shading.tar.Z
tec24.ps.Z
226 ASCII Transfer complete.
36 bytes received in 0.48 seconds (0.074 Kbytes/s)
ftp> get shading.tar.Z
200 PORT command successful.
150 ASCII data connection for shading.tar.Z (132.170.108.100,1046) (55702 bytes).
226 ASCII Transfer complete.
local: shading.tar.Z remote: shading.tar.Z
56060 bytes received in 0.65 seconds (85 Kbytes/s)
ftp> quit
221 Goodbye.
sono 127% uncompress shading.tar.Z
sono 128% tar -xvf shading.tar
x shading/shading.c, 3301 bytes, 7 tape blocks
x shading/ucfimgs/lenna128.ucf, 16396 bytes, 33 tape blocks
x shading/ucfimgs/mask128.ucf, 16396 bytes, 33 tape blocks
x shading/ucfimgs/sphere128.ucf, 16396 bytes, 33 tape blocks
x shading/ucfimgs/README, 338 bytes, 1 tape blocks
x shading/shading, 32768 bytes, 64 tape blocks
x shading/README, 2261 bytes, 5 tape blocks
sono 129% cd shading
sono 130% ls
README shading* shading.c* ucfimgs/
------------------------------
Date: Thu, 15 Oct 92 17:47:47 PDT
From: jeh@windrider.llnl.gov (Jose E. Hernandez)
Subject: Software for pattern recognition
hi,
I would like to know what software packages are available out there for
UNIX workstations for addressing problems in statistical pattern recognition
such as feature selection, clustering, and classification (back prop. or
others).
thank you!
jeh
------------------------------
Date: Thu, 29 Oct 92 08:27:11 PST
From: ibarroda@ra.UVic.CA
Subject: Curvilinear Feature Extraction
Given a digital image of a natural scene containing curvilinear
features (e.g. rivers, roads, sandwaves), we wish to extract this
information in vector form. Is there a (public domain) package
available which will allow us to experiment with different algorithms
for this task?
[ Check the most recent CVPR proceedings... phil...]
------------------------------
Date: Wed, 21 Oct 1992 16:26:55 +0100
From: Thierry PUN <pun@cui.unige.ch>
Subject: Research Assistant (Computer Vision), U-Geneva, Switzerland
AI and Vision Group
Computing Science Center
University of Geneva
October 8, 1992
We have one open position, to be filled in as soon as possible, for a
RESEARCH ASSISTANT
The succesfull candidate will participate in our work in computer vision, in
the framework of the Swiss National Priority Research Program SPP-IF in
Computer Science. The AI and Vision group currently comprises 16 persons, 9
of whom work primarily in computer vision.
Our main research topic in computer vision is the realization of an artificial
system for primal indexing (the Geneva Vision System); the central recognition
mechanism relies upon asynchronous identification in a 2D scene of
tridimensional objects whose models are a priori known. We also have
activities in several other domains, including the realization of an
agricultural robot (the Potato Operation).
The new research assistant will be responsible for the integration into a
common architecture of the various modules that we have developed so far, as
well as of the development of a full working prototype. The prototype will be
used for one or two real applications.
This work implies not only an ability to analyze and understand the various
pieces of work, but also to be capable of proposing alternatives where
problems exist. It must be however stressed that the objective of this
research is not the redoing of all the modules, but rather the realization of
a system. In short, we are looking for someone with a good practical sense,
together with an interest for advanced research and development.
In consequence, we are looking for a person having the following profile:
- a university degree in computer science or closely related field
(equivalent to a Diploma or M.Sc.);
- a strong knowledge and appreciation of software engineering;
- good knowledge of image processing and analysis, and at least some
background in computer vision and artificial intelligence;
- experience, preferably in an industrial environment, with the
realization of fairly large projects (ideally but not necessarily in
computer vision).
We mostly work on Sun platforms, in C++ and Lisp. The main group language is
French (mais la connaissance de l'anglais est cependant necessaire ...). The
salary is fixed by the Canton of Geneva; it currently starts at 4'660 Swiss
francs per month. The initial grant is for a 2 year period, with yearly
renewal. An extension of the initial grant is foreseen; it will depend on the
results obtained.
Letters of application including a resume and references should be sent to:
Prof. Thierry Pun,
Centre Universitaire Informatique,
University of Geneva,
24 rue du General Dufour,
CH-1211 Geneva 4, Switzerland.
PLEASE: if absolutely necessary, short questions can be sent by e-mail to
pun@cui.unige.ch, but applications and resume should be sent by POSTAL mail.
------------------------------
Date: Thu, 29 Oct 92 12:45:19 PST
From: clayton@almaden.ibm.com
Subject: Machine Vision and Applications Journal Info
MACHINE VISION AND APPLICATIONS
An International Journal
This journal is published four times a year and has a personal subscription
rate of US $54.00 including postage and handling. The institutional rate
is US $106.00 plus $11.00 postage and handling. If you would like a
sample copy with information on how to order, or information on submitting
a paper for publication, please send e-mail to: Donna Moore, Editorial
Coordinator at the following address:
Clayton@almaden.com
The Winter, 1992 issue has just been published. The table of Contents is
as follows:
A Method for Detection of Circular ARCS Based on the Hough Transform
by Par Kierkegaard
Local Association Based Recognition of Two-Dimensional Objects
by Ishwar K. Sethi and Nagarajan Ramesh
An Image Analysis System for Coaxially Viewed Weld Scenes
by Kim L. Boyer and Wayne A. Penix
------------------------------
Date: Thu, 15 Oct 92 12:10:31 EDT
From: Darrin Dimmick X4147 <dld@magi.ncsl.nist.gov>
Organization: National Institute of Standards and Technology
formerly National Bureau of Standards
Subject: NIST Special Databases and Software (neat & long)
This posting contains a list of special databases and software available from
the Image Recognition group at NIST. The newest additions to this list are
Special Database 6 - NIST Structured Forms Reference Set 2 of Binary Images
Special Database 7 - NIST Test Data 1: Binary Images of Handprinted Segmented
Characters
Special Software 1 - NIST Scoring Package Release 1.0 available in November.
_______________________________________________________________________________
NIST Special Databases and Software from the Image Recognition Group
Last Revised 10/15/92
=======================================================
Special Database 1 - NIST Binary Images of Printed Digits, Alphas, and Text
Special Database 2 - NIST Structured Forms Reference Set of Binary Images
Special Database 3 - NIST Binary Images of Handwritten Segmented Characters
Special Database 4 - NIST 8-bit Gray Scale Images of Fingerprint Image Groups
Special Database 6 - NIST Structured Forms Reference Set 2 of Binary Images
Special Database 7 - NIST Test Data 1: Binary Images of Handprinted Segmented
Characters
Special Software 1 - NIST Scoring Package Release 1.0
Prices
======
Special Database 1 - $895.00
Special Database 2 - $250.00
Special Database 3 - $895.00
Special Database 4 - $250.00
Special Database 6 - $250.00
Special Database 7 - $1,000.00
Special Software 1 - $1,150.00
For more information or to order please contact:
=======================================================
Standard Reference Data
National Institute of Standards and Technology
221/A323
Gaithersburg, MD 20899
(301) 975-2208
(301) 926-0416 (FAX)
******************************************************************************
+-----------------------------+
| "NIST Special Database 1" |
+-----------------------------+
Binary Images of Printed Digits, Alphas, and Text
(HWDB)
The NIST handprinted character database consists of 2,100 pages of
bilevel, black and white image data of handprinted numerals and text
with a total character count of over 1,000,000 characters. This
significant new database totals approximately 3 gigabytes of image data
with 273,000 numerals and 707,700 alphabetic characters. With the
sample taken from the Bureau of Census field staff and also geographically
sampled, the database has the following features:
+ over 1,000,000 characters images
+ 300 pixel/inch resolution
+ images of full pages of data
+ images of numbers with 2, 3, 4, 5, and 6 digits
+ images of full alphabets
+ images of unconstrained text
Suitable for both character recognition systems research, development,
and evaluation, the data set can be used for:
+ field isolation: locating the text on the page
+ character segmentation: separating the text into characters
+ character recognition: identifying specific characters
The database is a valuable tool for measurement of system performance
and system comparison. The system requirements are a 5.25" CD-ROM drive
with software to read ISO-9660 format.
If you have any further technical questions please contact:
Michael D. Garris
mdg@magi.ncsl.nist.gov
(301)975-2928
******************************************************************************
+-----------------------------+
| "NIST Special Database 2" |
+-----------------------------+
Structured Forms Reference Set
(SFRS)
The NIST database of structured forms contains 5,590 full page images of
simulated tax forms completed using machine print. THERE IS NO REAL TAX DATA IN
THIS DATABASE. The structured forms used in this database are 12 different
forms from the 1988, IRS 1040 Package X. These include Forms 1040, 2106, 2441,
4562, and 6251 together with Schedules A, B, C, D, E, F and SE. Eight of these
forms contain two pages or form faces making a total of 20 form faces
represented in the database.
Each image is stored in bi-level black and white raster format. The images in
this database appear to be real forms prepared by individuals but the images
have been automatically derived and synthesized using a computer and contain no
"real" tax data. The entry field values on the forms have been automatically
generated by a computer in order to make the data available without the danger
of distributing privileged tax information.
In addition to the images the database includes 5,590 answer files, one for
each image. Each answer file contains an ASCII representation of the data found
in the entry fields on the corresponding image. Image format documentation and
example software are also provided.
The uncompressed database totals approximately 5.9 gigabytes of data.
"NIST Special Database 2" has the following features:
+ 5,590 full-page images
+ 5,590 answer files
+ 12 pixel per millimeter resolution
+ image format documentation and example software
Suitable for automated document processing system research and development, the
database can be used for:
+ algorithm development
+ system training and testing
The system requirements are a 5.25" CD-ROM drive with software to read ISO-9660
format.
If you have any further technical questions please contact:
Darrin L. Dimmick
dld@magi.ncsl.nist.gov
(301)975-4147
******************************************************************************
+-----------------------------+
| "NIST Special Database 3" |
+-----------------------------+
Binary Images of Handwritten Segmented Characters
(HWSC)
The NIST database of handwritten segmented characters contains 313,389
isolated character images segmented from the 2,100 full-page images
distributed with "NIST Special Database 1". The database includes the
2,100 pages of binary, black and white, images of hand-printed numerals
and text. This significant new database contains 223,125 digits, 44,951
upper-case, and 45,313 lower-case character images. Each character image
has been centered in a separate 128 by 128 pixel region and has been
assigned a classification which has been manually corrected so that the
error rate of the segmentation and assigned classification is less than
0.1%. The uncompressed database totals approximately 2.75 gigabytes of
image data and includes image format documentation and example software.
"NIST Special Database 3" has the following features:
+ 313,389 isolated character images including classifications
+ 223,125 digits, 44,951 upper-case, and 45,313 lower-case images
+ 2,100 full-page images
+ 12 pixel per millimeter resolution
+ image format documentation and example software
Suitable for automated hand-print recognition research, the database
can be used for:
+ algorithm development
+ system training and testing
The database is a valuable tool for training recognition systems on a
large statistical sample of hand-printed characters. The system
requirements are a 5.25" CD-ROM drive with software to read ISO-9660
format.
If you have any further technical questions please contact:
Michael D. Garris
mdg@magi.ncsl.nist.gov
(301)975-2928
******************************************************************************
+-----------------------------+
| "NIST Special Database 4" |
+-----------------------------+
8-Bit Gray Scale Images of Fingerprint Image Groups
(FIGS)
The NIST database of fingerprint images contains 2000 8-bit gray scale
fingerprint image pairs. Each image is 512 by 512 pixels with 32 rows of
white space at the bottom and classified using one of the five following
classes: A=Arch, L=Left Loop, R=Right Loop, T=Tented Arch, W=Whirl. The
database is evenly distributed over each of the five classifications with
400 fingerprint pairs from each class. The images are compressed using a
modified JPEG lossless compression algorithm and require approximately
636 Megabytes of storage compressed and 1.1 Gigabytes uncompressed
(1.6 : 1 compression ratio). The database also includes format
documentation and example software.
"NIST Special Database 4" has the following features:
o 2000 8-bit gray scale fingerprint image pairs including
classifications
o 400 fingerprint pairs from each of the five classifications Arch,
Left and Right Loops, Tented Arch, Whirl
o each of the fingerprint pairs are two completely different
rollings of the same fingerprint
o 19.6850 pixels per millimeter resolution
o image format documentation and example software
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 on a
statistical sample of fingerprints which is evenly distributed over the
five major classifications. The system requirements are a 5.25" CD-ROM
drive with software to read ISO-9660 format. The cost is $250.
If you have any further technical questions please contact:
Craig I. Watson
craig@magi.ncsl.nist.gov
(301)975-4402
******************************************************************************
+-----------------------------+
| "NIST Special Database 6" |
+-----------------------------+
Structured Forms Reference Set 2
(SFRS2)
The second NIST database of structured forms contains 5,595 full page images of
simulated tax forms completed using hand-print. THERE IS NO REAL TAX DATA IN
THIS DATABASE. The structured forms used in this database are 12 different
forms from the 1988, IRS 1040 Package X. These include Forms 1040, 2106, 2441,
4562, and 6251 together with Schedules A, B, C, D, E, F and SE. Eight of these
forms contain two pages or form faces making a total of 20 form faces
represented in the database.
Each image is stored in bi-level black and white raster format. The images in
this database appear to be real forms prepared by individuals but the images
have been automatically derived and synthesized using a computer and contain no
"real" tax data. The entry field values on the forms have been automatically
generated by a computer in order to make the data available without the danger
of distributing privileged tax information.
In addition to the images the database includes 5,595 answer files, one for
each image. Each answer file contains an ASCII representation of the data found
in the entry fields on the corresponding image. Image format documentation and
example software are also provided.
The uncompressed database totals approximately 5.95 gigabytes of data.
"NIST Special Database 6" has the following features:
+ 5,595 full-page images containing hand-print
+ 5,595 answer files
+ 12 pixel per millimeter resolution
+ image format documentation and example software
Suitable for automated document processing system research and development, the
database can be used for:
+ algorithm development
+ system training and testing
The system requirements are a 5.25" CD-ROM drive with software to read ISO-9660
format.
If you have any further technical questions please contact:
Darrin L. Dimmick
dld@magi.ncsl.nist.gov
(301)975-4147
******************************************************************************
+-----------------------------+
| "NIST Special Database 7" |
+-----------------------------+
NIST Test Data 1: Binary Images of Handprint
Segmented Characters (TST1)
This NIST database contains almost 83,000 binary, black and white images of
handprinted numerals and letters segmented from 500 forms of the same type used
for NIST Special Database 3. However, the forms were filled out by a very
different writer population then the Bureau of Census field workers who filled
out the 2,100 forms used for that database. NIST Test Data 1 is the database that was used for testing in the first Census OCR Systems Conference in May 1992.
"NIST Test Data 1" has the following features
5.25" CD-ROM
+ approximately 83,000 isolated character images without classifications
+ approximately 59,000upper-case and lower-case images
+ 12 pixel per millimeter resolution
+ assumes access to NIST Special Database 3 and associated documentation
5.25" floppy disk
+ keyed classifications for all character images on the CD-ROM
+ keyed index to 500 writers
This database is suitable for use in testing OCR systems againist the results
obtained by over 40 systems in the First Census OCR Systems Conference and for
use as a database for training OCR systems.
The system requirements are a 5.25" CD-ROM drive with software to read ISO-9660
format and a 5.25" floppy drive with the software to read high density MS-DOS
format.
If you have any further technical questions please contact:
R. Allen Wilkinson
urt@magi.ncsl.nist.gov
(301)975-3383
******************************************************************************
+-------------------------+
| NIST Special Software 1 |
+-------------------------+
NIST Scoring Package Release 1.0
(SP)
The NIST Scoring Package is a reference implementation of the draft, "Standard
Method for Evaluating the Performance of Systems Intended to Recognize
Hand-printed Characters from Image Data Scanned from Forms", which has been
submitted to ANSI X.3A. This software was used to score the results from the
First Census Optical Character Recognition (OCR) System Conference sponsored by
the Bureau of the Census and hosted by NIST. A User's Guide is provided which
presents the concepts of scoring forms processing systems and character
classifiers, discusses the concepts and the algorithm used for dynamic string
alignment, defines the files and their formats required as input to the Scoring
Package, and documents how the Scoring Package software is installed and
invoked.
This software release has the following features:
+ supports both form-based and character-based scoring
+ applicable to a wide variety of structured forms
+ can be used in conjunction with NIST Special Databases (SD1, SD2, SD3,
SD6, & SD7)
+ supports user-defined form structures
+ includes scoring examples from forms and isolated characters
+ includes an extensive 66-page User's Guide
The NIST Scoring Package can be used to:
+ determine if OCR technology is economically advantageous to deploy for
a specific application
+ determine which OCR product is best suited for a specific application
+ choose from a large variety of diverse algorithmic approaches when
developing OCR systems
The NIST Scoring Package has the following attributes and requirements:
+ written in the `C' programming language and UNIX shell languages
+ developed to run on a UNIX system running SunOS 4.1.1
+ distributed on a 5.25" CD-ROM
+ requires a CD-ROM drive with ISO-9660 format software
+ utilizes 5 megabytes of magnetic disk storage upon installation and
compilation
If you have any further technical questions please contact:
Stan Janet
stan@magi.ncsl.nist.gov
(301)975-2916
------------------------------
Date: Tue, 27 Oct 92 14:04:27 EST
From: Darrin Dimmick X4147 <dld@magi.ncsl.nist.gov>
Organization: National Institute of Standards and Technology
formerly National Bureau of Standards
Subject: Correction to fl3 distribution
National Institute of Standards and Technology
It has been brought to my attention that some of the character images
contained in the fl3 distribution of isolated hand-print digit images,
available via anonymous ftp, were compressed contrary to my previous posting.
I have decompressed these images and recreated the tar file containing the fl3
distribution. This corrected fl3 distribution, also named fl3.tar.Z, has
replaced the previous distribution on the ftp site and can be obtained using
the instructions found in the original posting.
If you obtained the fl3 distribution prior to seeing this posting I recommend
obtaining the updated distribution.
I apologize for any inconvenience this error may have caused.
Darrin L. Dimmick
National Institute of Standards and Technology
Bldg. 225/A216
Gaithersburg, MD. 20899
------------------------------
From: michel@srtp.srt-poste.fr (Michel Gilloux)
Subject: JET POSTE'93
Organization: Service de Recherche Technique de la Poste
Date: 28 Oct 92 15:46:50 GMT
C A L L F O R P A P E R S
J E T P O S T E ' 9 3
1st European Meeting on Postal Technologies
Nantes, France, June 14-16, 1993
Organized by La Poste
The 1st European meeting on Postal Technologies (JET POSTE'93) is scheduled for
June 14-16, 1993 at the Nantes (France) Congress Hall. The meeting is designed
to be an exchange of ideas among active researchers and practitioners from a
variety of specialities with interest in technologies which might be applied in
the domains of mail, parcel, and bank services.
SCOPE
The scope of this congress includes, but is not limited to, the following
topics:
Pattern recognition and machine vision
- Image acquisition and processing
- Handwriting recognition
- Process control by machine vision
- Multi-expert recognition
- Parallel architectures for pattern recognition
- High speed image acquisition
- Objective assessment of image acquisition and processing system
- Neural nets
- Probabilistic models
- Fuzzy logic
Archiving and viewing systems
- Video encoding of mail
- Video encoding of checks
Human factors
- Ergonomics
- Computer-human interaction
Post office equipments
- Postal automata
- Meters
System engineering
- Mail processing scenarios
- Delivery organization
- Transport vectors equipment
- Transfer (hub, docks, transshipment)
- Containers handling
- Containers (matters and functions)
- Optimization under constraints
- Supervision of flows
- Handling simulation
- Reliability
- Workshops organization
Identification/Id tags
- Bar codes
- Tracing/tracking
- Automatic identification
- Electronic labels
- Standardization
Future sorting machines
- Stackers and destackers
- Flow fusion, and parallel machines
- Automatic feeding
- Temporary stocking systems
- High speed conveyors
- High speed deviators
Deadline for summary submissions January 1st, 1993
Notification of acceptance or reject February 1st, 1993
Final camera ready copy due April 1st, 1993
General chair
J.-J. Viard (La Poste, France)
Program chair
J.-C. Burbaud (La Poste, SRTP, France)
Program Committee
D. Barba (Univ. de Nantes, France)
M. Dannawi (Ecole centrale de Nantes, France)
B. Dolphin (Univ. d'Amiens, France)
M. Feuillas (SRTP, France)
F. Fogelman (Univ. de Paris-Orsay, France)
T. Fritz (Deustche Bundespost, Germany)
M. Gilloux (SRTP, France)
M. Grolee (Alisa, France)
J. Helard (SRTP, France)
G. Lorette (Univ. de Rennes, IRISA, France)
O. Palmieri (Ministry of P. and T., Italy)
K. Phillips (Royal Mail, England)
D. Scapin (INRIA, France)
L. Simonet (SRTP, France)
V. Uzylevsky (Technopost, Russia)
W. Veenstra (PTT Research, The Netherlands)
Local arrangements
D. Heitz (SRTP, France)
Phone: +33.40.69.98.78
SUBMISSION OF PAPERS
Authors are invited to submit 5 copies of a summary of their paper no later than
January, 1st, 1993 to the program chair. Summaries should be of 1000 words or
less. Proposals and requests for panel discussions and working groups should be
sent to the Program Chair as soon as possible, but no later than February, 1st,
1993.
Notification of acceptance or reject for each summary will be posted February
1st, 1993. Final manuscripts (10 pages including figures) must be received by
April 1st, 1993 for inclusion in the conference proceedings.
ADDRESS
Summaries and all requests for information concerning the content of papers
should be sent to:
Mr Jean-Claude Burbaud
SRTP
10, Rue de l'ile Mabon
F-44038 Nantes Cedex 01, France
Tel.: +33.40.69.98.04
Fax: +33.40.89.60.00
IMPORTANT DATES
January 1st, 1993: deadline for summary submissions
February 1st, 1993: notification of acceptance or reject
April 1st, 1993: final version due
ABOUT NANTES
Nantes is located 400 km west from Paris and only 70 km from the Atlantic Ocean.
It takes only one hour by plane from either Paris Charles-de-Gaulle or
Paris-Orly airports to Nantes International Airport and two hours by high speed
train (TGV) from Paris Montparnasse Station. There also exist airline
connections with major european cities.
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Pre-registration form
Return as soon as possible to: Mr Jean-Claude BURBAUD, SRTP, 10, Rue de l'Ile
Mabon, F-44038 Nantes Cedex 01, France
Name ...........................................................................
First Family
Affiliation ....................................................................
Mailing Address ................................................................
City Country Zip
Phone ................................ Fax ...................................
E-mail .........................................................................
(Please tick if appropriate)
[] I intend to submit a paper
Title of the paper: ........................................
[] I wish to receive further information and the registration form
[] I intend to participate in the conference
------------------------------
Date: Mon, 26 Oct 1992 20:15:21 GMT
From: fenrich@acsu.buffalo.edu (Richard Fenrich)
Subject: International Handwriting Recognition Workshop
Organization: State University of New York at Buffalo / CEDAR Research Group
The International Workshop on Frontiers in Handwriting
Recognition is a premier forum for researchers working in handwriting
recognition technology. The first two workshops were held in Montreal,
Canada and Bonas, France. For the first time, this workshop will be
held in the United States. This event, organized by the Center of
Excellence in Document Analysis and Recognition, will be held in
Buffalo, New York from May 25 to May 27, 1993. The workshop series
serves as a world-wide forum for exchange of research and development
in the fields of on-line (pen-based) and off-line (scanned images)
handwriting recognition. Many of these fields' top research and
development personalities will attend this workshop.
A primary component of the workshop will be vendor exhibits and
demonstrations. These exhibits increase research and commercial/industrial
awareness to advancements in off-line and on-line handwriting
recognition applications. They also foster new ideas and alliances
in these important fields.
If you are interested in giving a demonstration or in obtaining more
information, please contact me via telephone, fax, or mail. In
addition, if you know of an organization/individual that you think
might like to give such a demonstration, please let them know about
the workshop and forward this message to them. My phone number is
(716) 645-6164 extension 121 and my fax number is (716) 645-6176. My
mailing addresses are
Richard Fenrich
Project Manager
CEDAR
226 Bell Hall
Buffalo, New York 14260 USA
and
fenrich@cs.buffalo.edu
Thank you for your interest in this workshop.
-Richard (Rick) Fenrich
CEDAR
------------------------------
End of VISION-LIST digest 11.38
************************
