Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 12 Issue 24
VISION-LIST Digest Mon May 24 14:42:35 PDT 93 Volume 12 : Issue 24
- ***** 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:
Archive of aircraft images ??.
Help requested on pattern recognition project
NIST Special Database 9 (Mated Fingerprint Card Pairs)
PSRI classification of labels
Datacube
Quadtree modeling
Optical Character Recognition
Score recognition system
R&D position available in Singapore
Computer Vision Research Vacancy in the UK
Book announcement: Three-Dimensional Object Recognition Systems
CFP - Machine Vision Applications in Industrial Inspection
CFP: Image and Video Compression
Workshop
----------------------------------------------------------------------
Date: Tue, 18 May 93 19:19:24 EDT
From: nar@isis.cs.wayne.edu
Subject: Archive of aircraft images ??.
Hi Folks,
Does anybody know of an archive of aircraft images - binary,
gray or color?.
Thanks very much in advance,
Nagraj
Nagarajan Ramesh ! internet- nar@cs.wayne.edu
Vision & Neural Network Lab. ! uucp - ..!umich!wsu-cs!nar
Dept. of Computer Science, ! Phone: (313)-577-2477
Wayne State University, ! Fax : (313)-577-6868
Detroit MI 48202 !
------------------------------
Date: Wed, 19 May 1993 08:07:50 GMT
From: sjaak@cca.vu.nl (Jacques Schuurman)
Organization: VU Amsterdam - dienst CCA
Subject: Help requested on pattern recognition project
This message is containing a request for help from a colleague whose site
does not carry the forums in which this message is posted. If you are
replying to this, we would kindly ask you to send it directly to the e-mail
address <hagers@htsa.aha.nl>. Thank you ever so much in advance.
sjaak
I am seeking
ideas;
hints on information;
useable literature references;
working software;
on contour fitting and pattern matching.
This to realise the recognition of individual Fin-back-whales,
and thereby assist Mingan Island Cetacean Study, MICS, (Quebec, Canada)
in their behavioural studies on Fin-back-whales. The job by hand
is becoming very time-consuming since the set of known whales
grows every season.
As a final assignment project for my study (technische informatica) at
PHTO-Amsterdam I am doing research on the possibilities of a
solution to the MICS problem.
This may require:
-photograph scanning
-picture enhancement
-extraction of typical data for a certain animal
-matching facility (unknown versus database of known animals)
contour fitting of the shape of its dorsal fin
pattern matching on the pigment spots on the animal's back
Any help would greatly be appreciated.
Andre Hagers <hagers@htsa.aha.nl>
Jacques Schuurman VU Amsterdam | The world is my homeland, science my religion.
Telefoon +31 20 548 26 63 | De wereld is mijn vaderland, wetenschap mijn
Email sjaak@cca.vu.nl | religie. --- Christiaan Huygens
------------------------------
Date: Tue, 18 May 1993 12:25:34 GMT
From: craig@magi.ncsl.nist.gov (Craig Watson)
Organization: National Institute of Standards and Technology, Gaithersburg, MD
Subject: NIST Special Database 9 (Mated Fingerprint Card Pairs)
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 1-3
have been released and volumes 4 and 5 will be released by the middle of
June. 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: 19 May 93 15:27:59 GMT
From: samprabh@hercules.acpub.duke.edu
Organization: Duke University; Durham, N.C.
Subject: PSRI classification of labels
Hi!
I am starting work on a project which requires the identification of labels on
packages. The labels are approximately 1" X 0.75" in a corner of the package.
The labels have characters on them by which they are identified. The
characters are a mix of upper-case and lower-case letters and digits. The
identification needds to be postion, scale, and rotation invariant and also
insensitive to variations in lighting. The task would involve isolating the
region of interest, processing it and then obtaining appropriate features to
do the classification. Given a x X y image, I would appreciate pointers to
work done in selecting appropriate features for the above task and classifying
the images into appropriate categories.
I will summarize all the replies I receive, one month from now.
Thanks in advance.
Sameer M. Prabhu
samprabh@raphael.acpub.duke.edu
------------------------------
Subject: Datacube
Date: Thu, 20 May 93 16:55:20 -0400
From: John Soong <soong@cs.columbia.edu>
Hi,
My group is trying to put together an old MaxVideo-10 system
(Digimax, ROI-Store 2048, ROI-Store 512, MaxMux, VFIR MK II, Euclid) with
a Sparc IPX. The problem we have is we only have the Maxware software which
is for VMEbus/VMEbus. Sparc IPX only has Sbus and no VME-bus. When we bought
the S-bus/VME-bus repeater, we didn't realize we didn't have the right
device drivers (e.g. Imageflow or some kind of Maxware that is for Sbus/VMEbus).
Rewriting the Maxware software is far beyong our capabilities.
Did anybody try to change the Maxware software so that it can work
with a SBus/VMEbus environment (say, Sparc IPX/2 and repeater from
Performance Technologies)? Even if you have change the codes of
Maxware for Digimax, it'll be a big help. Thanks.
John Soong (soong@cs.columbia.edu)
Dept of Computer Science
Columbia University
New York, NY 10027
------------------------------
Date: 18 May 93 15:12:48 GMT
From: salbert@sarastro.inria.fr (Sebastien Albertus)
Organization: INRIA, Sophia-Antipolis (Fr)
Subject: Quadtree modeling
Dear netters,
I am making an internship tackling space planning problems
using the quadtree modeling and would like to get any piece
of information about it.
Thanks.
Sebastien Albertus INRIA Sophia Antipolis salbert@sophia.inria.fr
------------------------------
Date: Mon, 24 May 1993 15:02:29 GMT
From: phammond@cs.tcd.ie (Paul Hammond)
Organization: Trinity College, Dublin (Computer Science)
Subject: Optical Character Recognition
Summary: Help needed in tracking down fundamental and important papers
Keywords: OCR, papers, references
I am looking for information regarding the history of algorithmic development
in Optical Character Recognition from early fundamentals to the latest and best
techniques.
What I require is a short list of the important algorithms in chronological
order and some starting points to find out more about them.
I am very new to the area and it is difficult to wade through 100's of
references and pick out the relevant ones. Somebody well up in this area
may be able to narrow the field for me.
As an analogy of what I need, consider the area of sorting.
One would have linear sort, shell-sort, bubble sort etc. all the way to
QuickSort and HeapSort with a brief 1 or 2 line description and a main
paper reference to each one.
Can anybody contribute to such a list or can they point me to other internet
sources (particularly newsgroups) where I can get this information readily ?
Any help would be very much appreciated.
Thank you.
Paul
------------------------------
Date: Fri, 21 May 93 09:24:19 KDT
From: dmyoon@violet.kotel.co.kr (Doo Man Yoon)
Subject: Score recognition system
Hi, everyone.
I'm surveying computer-aided digital music system.
Do you have any information on the printed score
recognition system which reads the scanned score image
and extracts codes of each note ?
And I also welcome the advices on the standard format
to express a piece of music in digital musical instruments.
Thanks in advance....
Doo-man Yoon
Korea Telecom | Tel:+82-2-526-6791
S/W research Laboratories | FAX:+82-2-526-6785
HiTEL DB section. | E-mail:dmyoon@rcunix.kotel.co.kr
------------------------------
Date: Wed, 19 May 1993 07:34:30 GMT
From: mengyong@iss.nus.sg (Goh Meng Yong)
Organization: Institute of Systems Science, NUS, Singapore
Subject: R&D position available in Singapore
The Apple-ISS Research Center is a joint venture between Apple
Computer, Inc. and ISS (Institute of System Science) at NUS (National
University of Singapore). The Center will be doing various research
in computer processing of Asian languages. Currently, the Chinese
Text-to-Speech research is underway and quite successful. The Center
is now looking for a qualified candidate to be the project leader of
the Chinese handwriting recognition research project. A candidate
should have practical experience in Chinese handwriting recognition
and preferably holds a PhD degree. Practical experience in
handwriting recognition systems and the ability to lead a team of
three or more are highly desirable.
Interested candidates kindly contact me (Meng-Yong Goh).
My email address is:
mengyong@iss.nus.sg
Thank you.
------------------------------
Date: Mon, 24 May 93 11:39:37 BST
From: pycockd@eee.bham.ac.uk (Mr D. Pycock)
Subject: Computer Vision Research Vacancy in the UK
COMPUTER VISION RESEARCH VACANCY
at
School of Electronic and Electrical Engineering
The University of Birmingham
THERMO-OPTICAL IMAGE PROCESSING
FOR THE INSPECTION OF ELECTRONIC POWER MODULES
There is an opportunity to join the Computer Vision Research Team in the
School of Electronic and Electrical Engineering. This opportunity
exists as a result of a 3 year grant, made to The University by the
SERC. Candidates should have a PhD or equivalent experience in an
appropriate discipline. Skills sought include experience in advanced
software development, mathematics, electronic design, good verbal and
written communication abilities. The successful candidate will be
appointed as a Research Fellow a starting salary of up to 16,437 pounds,
sterling, a year.
The closing date for applications is 5th June 1993.
Further particulars and an application form are
available from:
The Director of Staffing Services
The University of Birmingham
Edgbaston
Birmingham
B15 2TT
Telephone (24 hour answering service): 021 414 3699
Please quote reference number: G10617/93
The University is an equal opportunities employer
Posted by:
David Pycocck
School of Electronic and Electrical Engineering
The University of Birmingham
Birmingham
B15 2TT
Email: D.Pycock@uk.ac.bham
------------------------------
Date: Tue, 18 May 93 11:11:43 PDT
From: Patrick J. Flynn <flynn@irl.eecs.wsu.edu>
Subject: Book announcement: Three-Dimensional Object Recognition Systems
Editors: A.K. Jain, Michigan State University
P.J. Flynn, Washington State University
Publisher: Elsevier
Series: _Advances in Image Communication_ (volume 1)
x + 470 pages
ISBN: 0-444-89797-6
Price: US$160.00 / Dfl. 280.00
Chapter titles and authors:
"3D Object Recognition: Inspirations and Lessons from Biological Vision" --
Caelli, Johnston, and Robison (University of Melbourne)
"Range Sensing for Computer Vision" -- Jarvis (Monash University)
"Feature Extraction for 3-D Model Building and Object Recognition" --
Ferrie, Mathur, and Soucy (McGill University)
"Three-Dimensional Surface Reconstruction: Theory and Implementation" --
Stevenson (University of Notre Dame), Delp (Purdue University)
"CAD-Based Object Recognition in Range Images Using Pre-Compiled Strategy Trees" -- Arman (Siemens Corporate Research) and Aggarwal (University of Texas
at Austin)
"Active 3D Object Models" -- Bolle, Califano, Kjeldsen, and Mohan (IBM T.J.
Watson Research Center)
"Image Prediction for Computer Vision" -- Camps (Penn State University),
Shapiro and Haralick (University of Washington)
"Tools for 3D Object Location from Geometrical Features by Monocular Vision" --
Dhome, Lapreste, Richetin, and Rives (Blaise Pascal University of
Clermont-Ferrand)
"Part-Based Modeling and Qualitative Recognition" -- Dickinson (University of
Toronto)
"Appearance-Based Vision and the Automatic Generation of Object Recognition
Programs" -- Gremban and Ikeuchi (Carnegie Mellon University)
"Recognizing 3D Objects Using Constrained Search" -- Grimson, Lozano-Perez,
and White (Massachusetts Institute of Technology), Noble (SOCS Research)
"Recognition of Superquadric Models in Dense Range Data" -- Gupta (Siemens
Corporate Research), Bajcsy (University of Pennsylvania)
"Recognition by Alignment" -- Huttenlocher (Cornell University)
"Representations and Algorithms for 3D Curved Object Recognition" --
Ponce, Petitjean, Sullivan (University of Illinois), Kriegman, Vijayakumar
(Yale University), Taubin (IBM T.J. Watson Research Center)
"Structural Indexing: Efficient Three Dimensional Object Recognition" --
Stein and Medioni (University of Southern California)
"Building a 3-D World Model for Outdoor Scenes from Multiple Sensory Data" --
Asada (Osaka University)
"Understanding Object Configurations" -- DeCurtins, Mulgaonkar, and Cowan
(SRI International)
"Modal Descriptions for Modeling, Recognition, and Tracking" -- Pentland,
Sclaroff, Horowitz, and Essa (Massachusetts Institute of Technology)
------------------------------
Date: Tue, 18 May 93 12:12:27 EDT
From: "Frederick Y. Wu (914-945-2498 t/l 862)" <fwu@watson.ibm.com>
Subject: CFP - Machine Vision Applications in Industrial Inspection
Announcement and Call for Papers
MACHINE VISION APPLICATIONS IN INDUSTRIAL INSPECTION II
1994 SPIE/IS&T Symposium on Electronic Imaging Science and
Technology
February 6 - 10, 1994
San Jose Convention Center
San Jose, California
Conference Chairs: Benjamin M. Dawson
MIT and Imaging Technology, Inc.
Stephen S. Wilson
Applied Intelligent Systems, Inc.
Frederick Y. Wu
IBM T.J. Watson Research Center
Program Committee:
Chris Bowman Industrial Research Ltd.
Robert M. Haralick University of Washington
John Jordan Tencor Instruments
A. Ravishankar Rao IBM T.J. Watson Research Center
Jorge Sanz IBM Almaden Research Center
Machine vision systems can replace and improve on human vi-
sion in repetitive or high-speed industrial inspection tasks
or when precise visual measurement and inspection are re-
quired. These systems improve manufacturing speed, quality,
and compliance with product standards, and thus provide a
competitive advantage. Improvements in machine vision hard-
ware, algorithms, and software increase the industrial in-
spection areas in which this technology can be successfully
applied.
This conference brings together practitioners and research-
ers in machine vision to share recent developments in vision
hardware, algorithms, and software for industrial inspection
tasks. Papers are solicited in the areas of:
o Novel hardware designs for machine vision systems
o New or improved algorithms for industrial inspection
o Automatic defect classification
o Use of 3-D or color imaging in automatic inspection
o Software systems for flexible automatic inspection sys-
tems
o Applications of machine vision to microelectronics manu-
facturing
o Applications of machine vision to other areas of indus-
trial inspection, such as food products, web and paper
products, glass and steel inspection, agriculture, and
pharmaceuticals
Papers emphasizing fundamental methods that are widely ap-
plicable to industrial inspection are especially welcome.
All submissions will be peer reviewed. Please note that ab-
stracts MUST BE AT LEAST 500 WORDS in length in order to re-
ceive full consideration.
Submission of Abstracts (Deadline July 12, 1993)
Please include in your submission:
1. Title of Paper
2. Authors' Listing (as it should appear in the program)
3. Full address of each author, including phone, fax, and
e-mail
4. Name of conference to which paper is being submitted
(Machine Vision Applications in Industrial Inspection II/
EI '94)
5. Text of Abstract (500 to 1000 words)
6. Brief biography of principal author (50 to 100 words)
Please send your submission:
o by e-mail to Internet: abstracts@mom.spie.org (ASCII
format)
o or by fax to SPIE at (206) 647-1445
o or by mail (four copies) to
SPIE/IS&T EI '94
SPIE
P O Box 10
Bellingham, WA 98227-0010
Shipping Address: 1000 20th Street
Bellingham, WA 98225
phone: 206-676-3290
Abstract Due Date: July 12, 1993
Acceptance notification: October 21, 1993
Camera Ready Abstract due date: November 15, 1993
Manuscript due date: January 10, 1994
For further information, contact:
Fred Wu
phone: (914) 945-2498
FAX: (914) 945-2141
internet: fwu@watson.ibm.com
------------------------------
Date: 21 May 93 14:51:03 GMT
From: rjs@alice.att.com (Bob Safranek)
Organization: AT&T Bell Laboratories, Murray Hill NJ
Subject: Call For Papers: Image and Video Compression
Keywords: CFP: Image and video compression
CALL FOR PAPERS:
IMAGE AND VIDEO COMPRESSION
Part of IS&T/SPIE Symposium on Electronic Imaging: Science & Technology
San Jose Convention Center, San Jose, California, February 6-10, 1994
Recent advances in digital image acquisition and reconstruction
technology, couples with breakthroughs in the
price/performance of digital hardware and firmware, have
resulted in an ever increasing need for storage and
transmission of digital images. Diverse applications include
consumer imaging, facsimile transmission, image archiving,
remote sensing, medicine, broadcasting, entertainment,
education and video teleconferencing.
Image compression refers to the techniques that aim at
reducing the redundancy of the image data to save storage
space, transmission time, channel capacity, or to improve data
access rate.
This conference serves as a forum where advances in digital
image compression techniques and associated software and
hardware implementations can be presented and discussed.
Papers are solicited in the following areas:
* noiseless coding applied to image data (arithmetic
coding, LZW coding, etc.)
* lossless image compression algorithms
* lossy compression of still and sequential
continuous-tone images
* algorithms for the compression of bilevel images
* image compression standards (JPEG, MPEG, JBIG, HDTV,
Photo-CD, etc.)
* VLSI, hardware, and software implementation of image
compression algorithms
* systems issues involving image compression (rate
control, manipulation of compressed bitstreams, integration
with other media, etc).
Conference Chairs:
Majid Rabbani, Eastman Kodak Company
Bob Safranek, AT&T Bell Laboratories
Program Committee:
Charles Bouman, Purdue University
David Neuhoff, University of Michigan
Mike Orchard, Universitry of Illinois
Amy Riebman, AT&T Bell Laboratories
Eve Riskin, University of Washington
INSTRUCTIONS FOR AUTHORS
Each paper will be reviewed by members of the program committee. The
deadline for paper submissions is 12 July 1993. Please submit four copies
by mail, or one copy by email or fax, of a 500 word (or greater) summary
and other requested information to:
IS&T/SPIE EI94
Digital Video Compression and Processing on Personal Computers
P.O. Box 10
Bellingham, WA 98227-0010 USA
Shipping address: 1000 20th St., Bellingham, WA 98225
Telephone: (206) 676-3290
Telefax: (206) 647-1445
Internet abstracts@mom.spie.org
Please include the following information:
1. Title of Paper
2. Authors' full names, affiliations, address, phone, fax and email
3. Include a sentence indicating that the paper is intended for the
Image and Video Compression conference
4. Summary text (500 words or greater)
5. Authors' Biographies
The Conference Chairs and Program Committee will select the best papers
for the conference.
Bob Safranek
rjs@research.att.com
------------------------------
Date: Tue, 18 May 93 15:06:18 BST
From: sta6cag@gps1.leeds.ac.uk
Subject: Workshop
SECOND NOTICE SECOND NOTICE SECOND NOTICE SECOND NOTICE
13TH LEEDS STATISTICAL RESEARCH WORKSHOP
JULY 12 - 14, 1993
SHAPE RECOGNITION IN 2-D AND 3-D IMAGES
KEYNOTE LECTURES
Professor Josef Kittler, Electronics and Electrical Engineering,
University of Surrey, UK, (Parametric shape detection based on robust
statistical hypothesis testing with applications in computer vision and
image analysis).
Professor Michael Miller, Electrical Engineering, Washington University,
Missouri, USA, (Jump-diffusion processes for inferring 1, 2, and 3-D
shape as used in electron microscopy and automatic target tracking and
recognition).
SHORT TALKS
Dr Ian Dryden, Statistics, Leeds University
Professor Colin Goodall, Statistics, Penn State, USA
Professor David Hogg, Computer Studies, Leeds University
Dr John Marchant, SILSOE, UK
Professor Kanti Mardia, Statistics, Leeds University
Professor Michael Werman, Computer Science, Hebrew University of
Jerusalem, Israel
POSTER DISPLAY HANDS-ON SUN WORKSTATIONS
TIMETABLE Monday 1.00 p.m.(registration) - Wednesday 4.00 p.m.
Registration fee : 78 UK pounds (students 58 pounds)
The workshop will be held in Fairbairn House, part of the University of
Leeds campus, and which offers conference and associated facilities to a
high standard.
Fees include lunch on Tuesday and Wednesday, light refreshments, car
parking and course material.
Conference dinner (Tuesday):12.50pounds, payable with registration fee.
Fees should be paid in advance, cheques payable to UNIVERSITY OF LEEDS.
Accommodation in nearby hotels at reasonable prices can be arranged
if required. Individuals must settle their own accommodation expenses.
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
SHAPE RECOGNITION IN 2-D AND 3-D IMAGES 12 - 14 JULY 1993
REGISTRATION FORM Please detach and return to Dr C. A. Gill, Department
of Statistics, University of Leeds, Leeds LS2 9JT.
NAME:............................... Fee enclosed(pounds)
ADDRESS:............................... 78 or 58 ....
............................... Dinner 12.50 ....
............................... TOTAL ....
Please tick if you require:-
conference dinner.... car park space.... sandwich lunch on Monday.....
If accommodation required, please indicate
Monday night.... Tuesday night.... en suite.... price range.......
------------------------------
End of VISION-LIST digest 12.24
************************
