Copy Link
Add to Bookmark
Report
VISION-LIST Digest Volume 13 Issue 05
VISION-LIST Digest Mon Jan 31 13:48:27 PDT 94 Volume 13 : Issue 5
- ***** The Vision List host is 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:
STEREO DATA with GROUND TRUTH
3DVIEWNIX
Edge Detection: Illumination-independent
Looking for Julesz Images by ftp
Multidimensional Hough Transform
Request for Relaxation Algorithms
enquiry on character recognition system
Looking for PD Edge Detection Software
New book: Scale-Space Theory in Computer Vision
IAPR/IEEE Workshop on Visual Behaviors
Extended deadline: CFP
Boston U. Ctr. for Adaptive Systems Spring 1994 Colloquia
----------------------------------------------------------------------
Date: Mon, 31 Jan 94 11:56:17 EST
From: Mark.Maimone@A.GP.CS.CMU.EDU
Subject: STEREO DATA with GROUND TRUTH
******************************************************************************
ANNOUNCING: STEREO DATA SETS WITH GROUND TRUTH
******************************************************************************
The Calibrated Imaging Laboratory at Carnegie Mellon University is
releasing some stereo image datasets (with ground truth!) to the Net. Two
such datasets are now available, and more will be forthcoming. Feel free to
send in your suggestions to CIL@CMU.EDU!
These datasets contain multiple images of static scenes with
accurate information about object locations in 3D. They are being provided
by Carnegie Mellon as a service to the Net community to address the current
lack of stereo image data with ground truth (noted in [1]).
The images were taken with a scientific camera in an indoor setting,
the Calibrated Imaging Laboratory at CMU. The types of objects in the
images vary from simple polyhedra to complex model train sets. Actual 3D
locations are given in X-Y-Z coordinates with a simple text description, and
the CORRESPONDING IMAGE COORDINATES ARE PROVIDED for all images. Eleven
images of each scene were taken in an attempt to address the needs of
binocular stereo, multi-baseline stereo and optical flow researchers.
These data are provided under Contract No. F49620-92-C-0073, ARPA
Order No. 8875, and the NASA Ames Graduate Student Researchers Program.
The README file describes the imaging process, calibration methods
and data representations.
Mark Maimone
mwm@cmu.edu
31 January 1994
******
The current datasets can be retrived by anonymous FTP:
ftp ftp.cs.cmu.edu [128.2.206.173 in Jan 1994, but may change]
login: anonymous
passwd: [your email address]
cd /usr0/anon/project/cil
binary
dir
get README
get cil-0001.tar
get cil-0002.tar [and so on]
by World Wide Web (WWW) clients (e.g., NCSA Mosaic):
http://www.cs.cmu.edu:8001/usr0/anon/project/cil/html/cil-ster.html
by remote filesystem (AFS or Alex):
cp /afs/cs.cmu.edu/project/cil/ftp/README .
cp /afs/cs.cmu.edu/project/cil/ftp/cil-0001.tar .
cp /alex/edu/cmu/cs/ftp/project/cil/README .
cp /alex/edu/cmu/cs/ftp/project/cil/cil-0001.tar .
or by email (but this is your last resort!!):
% mail ftpmail@decwrl.dec.com
Subject: none [this is ignored]
reply your-email-address [use your INTERNET-style address]
connect ftp.cs.cmu.edu
binary
cd /usr0/anon/project/cil
get README
**OR**
get cil-0001.tar [each dataset is 2.6 MEGAbytes]
quit
(Send "help" alone in the message body for more details about the FTPmail
service)
REFERENCES
[1] ``The JISCT Stereo Evaluation'' by R. C. Bolles, H. H. Baker, and M. J.
Hannah, in April 1993 ARPA Image Understanding Workshop Porceedings, pp.
263-274. Sample images and results are available by anonymous FTP from
ftp.teleos.com [131.119.250.108 in Dec 1993] in directory
/VISION-LIST-ARCHIVE/IMAGERY/JISCT.
*****************************************************************************
FOR MORE INFORMATION ABOUT THIS DATA PLEASE SEND EMAIL TO CIL@CMU.EDU
*****************************************************************************
------------------------------
Date: Tue, 25 Jan 94 16:48:52 EST
From: Vhelp@mipgsun.mipg.upenn.edu
Subject: 3DVIEWNIX
> I am interested in a software that does 3D visualization of MR and CT
> images. I am working on angio data and my images are 256X256X 128 slices.
> If anyone knows of any software that is acessible via FTP, that does
> 3D visualization of MR/CT images, please let me know the places from where
> I can access such a software.
> Thanks in advance.
> Arun
Recently someone wanted to know about some of imaging softwares available
from FTP sites around the world. This is in response to that. The University
of Pennsylvania has a new medical imaging software available from a FTP site.
I am enclosing some details about the same. Please note that this is NOT a
solicited advertisement.
=========================================================================
3DVIEWNIX has been picked up as the TOP 10 GRAPHICS SOFTWARE PRODUCT OF
THE YEAR by IEEE Computer Graphics and Applications (January 1994, pp. 87)
=========================================================================
3 D V I E W N I X
-----------------
3DVIEWNIX is a transportable, very inexpensive software system
developed by the Medical Image Processing Group, Department of Radiology,
University of Pennsylvania, Philadelphia. It has state-of-the-art
capabilities for visualizing, manipulating, and analyzing multidimensional,
multimodality image information. It is designed to run on UNIX machines
with X-windows. It uses a data protocol that is a multidimensional
generalization of the ACR-NEMA standards. We have tested it fairly well
on SGI and Sun worksatations. It also runs on IBM RS6000, HP 700 series
and even PCs. We charge $1000.00 for the software which comes with source
code and manuals. You can modify and do whatever else you want as long as
it is for your own noncommercial use. For further information contact :
Dr. J.K. Udupa
Medical Image Processing Group
Univeristy of Pennsylvania
Department of Radiology
418 Service Drive - 4th Floor Blockley Hall
Philadelphia, PA 19104-6021.
Phone : (215)-662-6780
Fax : (215)-898-9145
e-mail: Vhelp@mipgsun.mipg.upenn.edu.
Please note that an anonymous FTP version of 3DVIEWNIX is available at no
cost to test the software. The FTP site is mipgsun.mipg.upenn.edu
(130.91.180.111) and the directory is /pub/3DVIEWNIX1.0/BINARIES.
------------------------------
Date: 31 Jan 1994 03:00:44 GMT
From: bhuiyan@mars.elcom.nitech.ac.jp (Md. Shoaib Bhuiyan)
Organization: Nagoya Institute of Technology, Nagoya, Japan
Subject: Edge Detection: Illumination-independent
Hello everybody,
I have seen very little work done on illumination-independent Edge
Detection except early works of Land and McCann, and later, by R. P.
Johnson. Is it possible for any kind soul to give me a clue for some
additional literature?
Besides, I have noticed several ftp sites of standard/ widely used
test images, but almost none for images with varying illumination.
Widely used lena, house, etc are almost uniformly illuminated images.
Similarly, a lot of sites offer source codes for widely used edge
detectors like canny, sobel, etc. But, it seems that they always need
something else to compile them. So, is it supposed that every image
processing/vision researcher should not only develop his/her own
program, but also ALL past algorithms to compare the results?
In short, I want to know whether there is any source that will offer
(1) test images with varying illumination (2) Sobel, Canny, or any
other edge detection algorithm written in standard C source code that
can be compiled in a SUN workstation requiring no specialized library
modules.
Thank you for your time.
Sincerely,
Shoaib.
$@!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~"!!~(J
Md. Shoaib Bhuiyan | What's latest in Neuro-computing?
Graduate School of Engineering | Lab: +81-(52)-732-2111 Ext.2861
Nagoya Institute of Technology | Home: +81-(52)-741-8185 Room#A-508
Dept. Electrical & Computer Engg. | Fax: +81-(52)-733-6589 c/o Bhuiyan
Gokiso, Showa, Nagoya, JAPAN 466 | E-mail: bhuiyan@mars.elcom.nitech.ac.jp
------------------------------
Date: Wed, 26 Jan 94 09:18:02 +0100
From: palagi@tirf.grenet.fr (Patricia Palagi)
Subject: Looking for Julesz Images by ftp
Hello,
I would like to be informed if there is any ftp address were I can look for
Bela Julesz images.
Would you please answer directly to my personnal e-mail? I'm NOT connected
to News. This request is very URGENT.
Thank you very much.
Patricia Monteiro Palagi
palagi@tirf.grenet.fr
------------------------------
Date: Wed, 26 Jan 1994 13:50:31 -0500
From: Yu Tian <tian@cs.ucf.edu>
Subject: Multidimensional Hough Transform
I am currently using multidimensional hough transform to solve a
vision problem. Is there any way to find local maxima in
multidimensional parameter space, rather than exhaustive search? Can
clustering technique be used in find these local maxima? I would very
appreciate it if anyone let me know the solution.
Yu Tian
email: tian@cs.ucf.edu
------------------------------
Date: Thu, 27 Jan 94 17:39:08 GMT
From: phillipm@eee.bham.ac.uk (Mark Phillips)
Subject: Request for Relaxation Algorithms
I am working on caching techniques for image processing applications running
on uni-processor machines. I would like to obtain any practical
implementations of relaxation algorithms written in C or C++ so that I may
trace these applications recording addresses accessed.
Any code or advice would be much appreciated.
Mark Phillips
Dept. Electroninc & Electrical Eng.
University of Birmingham
Pritchatts Road
Edgbaston
B15 2TT
United Kingdom
email: phillipm@uk.ac.bham.eee
------------------------------
Date: Mon, 31 Jan 1994 10:08:29 GMT
From: jitshiew@iti.gov.sg (Han Jit Shiew)
Organization: National Computer Board, Singapore
Subject: enquiry on character recognition system
Is everybody know any commerical character recognition system used to
recognise thousands of different handwriting in the market ? If you do
know, I would appreciate it very much if you can tell me the product
name and which company that I can contact.
Thank you.
My E-mail address is jitshiew@ncb.gov.sg
------------------------------
Date: Thu, 27 Jan 94 17:37:12 -0600
From: holder@cse.uta.edu (Larry Holder)
Subject: Looking for PD Edge Detection Software
We are looking for public domain software for edge detection in images
(specifically satellite images like LANDSAT). Ideally, we would like
to extract the edge information in the form of line-segments and
intersection/joins, not just identifying which pixels fall on lines
and which do not. We hope to use this information to build a
structural representation of the image.
Thanks,
Larry Holder (holder@cse.uta.edu)
University of Texas at Arlington, Department of Computer Science Engineering
Box 19015, Arlington, TX 76019-0015, Phone: 817-273-2596, FAX: 817-273-3784
------------------------------
Date: Fri, 28 Jan 1994 12:34:20 +0100
From: Tony.Lindeberg@bion.kth.se
Subject: New book: Scale-Space Theory in Computer Vision
New book on multi-scale representation of image data:
SCALE-SPACE THEORY IN COMPUTER VISION
by Tony Lindeberg,
Royal Institute of Technology,
Stockholm, Sweden
SHORT DESCRIPTION:
We perceive objects in the world as having structures both at coarse
and fine scales. A tree, for instance, may appear as having a roughly
round or cylindrical shape when seen from a distance, even though it
is built up from a large number of branches. At a closer look,
individual leaves become visible, and we can observe that they in turn
have texture at an even finer scale. This fact, that objects in the
world appear in different ways depending upon the scale of observation,
has important implications when analysing measured data, such as
images, with automatic methods.
"Scale-Space Theory in Computer Vision" describes a formal framework,
called scale-space representation, for handling the notion of scale
in image data. It gives an introduction to the general foundations of
the theory and shows how it applies to essential problems in computer
vision such as computation of image features and cues to surface
shape. The subjects range from the mathematical underpinning to
practical computational techniques. The power of the methodology is
illustrated by a rich set of examples.
This book is the first monograph on scale-space theory. It is intended
as an introduction, reference, and inspiration for researchers,
students, and system designers in computer vision as well as related
fields such as image processing, photogrammetry, medical image analysis,
and signal processing in general.
CONTENTS:
Foreword by Jan Koenderink
Preface
Abstract
1 Introduction and overview
2 Linear scale-space and related multi-scale representations
3 Scale-space for 1-D discrete signals
4 Scale-space for N-D discrete signals
5 Discrete derivative approximations with scale-space properties
6 Feature detection in scale-space
7 The scale-space primal sketch
8 Behaviour of image structures in scale-space: Deep structure
9 Algorithm for computing the scale-space primal sketch
10 Detecting salient blob-like image structures and their scales
11 Guiding early visual processing with qualitative scale and
region information
12 Summary and discussion
13 Scale selection for differential operators
14 Direct computation of shape cues by scale-space operations
15 Non-uniform smoothing
Appendix, Bibliography, Index
435 pages, ISBN 0-7923-9418-6, Kluwer Academic Publishers, 1994.
The complete table of contents, foreword, preface, and abstract are
available by anonymous ftp from world.std.com (192.74.137.5)
>ftp world.std.com
Name: anonymous
Password: <email address>
ftp>cd ftp/Kluwer/books
ftp>get scale_space
The list price has been set to Dfl 275.00 (USD 130). For ordering
information, see the file at the ftp site or contact Mike Casey at
Kluwer Academic Publishers (casey@wkap.nl / PO Box 17, NL-3300 AA
Dordrecht, Netherlands). He is offering a prepublication discount
until March 31, 1994.
------------------------------
Date: Thu, 27 Jan 1994 22:44:25 GMT
From: Worthy Martin <iaprwks@ruby.cs.virginia.edu>
Organization: University of Virginia Computer Science Department
Subject: IAPR/IEEE Workshop on Visual Behaviors
CALL FOR PARTICIPATION
IAPR / IEEE
Workshop on Visual Behaviors
The Westin Hotel --- Seattle, Washington
June 19, 1994
in conjunction with CVPR'94
Few vision researchers question the statement,
"Vision must be understood as a spatio-temporal process."
However, there is still considerable debate about the
fundamental nature of that process. One major approach
claims that vision (and any perceptual process) can only be
understood properly in the context of motivating actions or
tasks. A further pragmatic observation is that the
complexity concerns require that limited system resources be
allocated dynamically in processing only restricted spatial
and temporal regions (at restricted resolutions). The
purpose of this workshop is to foster debate and dialogue on
the fundamental issues involved in systems that tightly
couple perception and behavior to perform tasks. The
program will consist of previously unpublished, contributed
and invited papers. A list of possible themes for submitted
papers [a suggestive rather than exclusive list] is:
dynamic integration of visual information
multiple-goal mediation
gaze control/tracking/vergence
space-variant sensors
local-frame formulations
selective data reduction
overt and covert attention mechanisms
incremental planning/action
imaging parameter manipulation
hand-eye coordination
indexial referencing
preattentive/attentive processing integration
camera/head mechanisms
peripheral guidance/alerting
planning visual probes
agent/task/behavior description methods
exploratory/episodic behavior
These themes may be addressed in a variety of formats:
algorithm specifications, analysis of underlying theory,
empirical studies, cognitive studies, position papers, and
application descriptions.
PAPER SUBMISSION
Four copies of complete manuscript should be received by
Tuesday, February 1, 1994 at the address:
W.N. Martin
Department of Computer Science
University of Virginia
Thornton Hall
Charlottesville, Virginia 22903-2442
U.S.A.
Papers should include
(a) A title page containing the names and addresses of the
authors (including e-mail), an abstract of up to 200
words
(b) A second title page - title and abstract only (to allow
for double blind reviewing),
(c) Paper - limited to 25 double-space pages (12 points, 1
inch margins), including figures, references, etc.
PROGRAM COMMITTEE:
Worthy Martin University of Virginia, General Chair
Dana Ballard University of Rochester
Ruzena Bajcsy University of Pennsylvania
Tom Olson University of Virginia
Mike Swain University of Chicago
John Tsotsos University of Toronto
Linda Shapiro University of Washington, Local Arrangements
------------------------------
Date: Sat, 29 Jan 1994 20:32:57 -0500
From: <laine@cis.ufl.edu>
Subject: Extended deadline: CFP
Please note extended deadline below:
---> CALL FOR PAPERS <---
Conference Title: "Mathematical Imaging: Wavelet Applications in
Signal and Image Processing II"
Part of SPIE`s Annual International Symposium on
Optoelectronic Applied Science and Engineering
July 27-29, 1994
San Diego, California
San Diego Convention Center, Marriot Hotel Marina
Conference Chairs:
Andrew Laine, University of Florida
Michael Unser, National Institutes of Health
Program Committee:
Bjorn Jawerth, University of South Carolina
Martin Vetterli, University of California, Berkeley
Ronald Coifman, Yale University
Stephane Mallat, New York University
Victor Wickerhauser, Washington University
Akram Aldroubi, National Institutes of Health
Charles Chui, Texas A&M University
Arun Kumar, Southwestern Bell Technology Resources
Alan Bovik, University of Texas, Austin
KEYNOTE ADDRESS: Ingrid Daubechies, Princeton University
and AT&T Bell Laboratories
The analysis of signals and images at multiple scales
is an attractive framework for many problems in computer vision,
signal and image processing. Wavelet theory provides
a mathematically precise understanding of the concept of multiresolution.
The conference shall focus on novel applications of wavelet methods of
analysis and processing techniques, refinements of existing methods,
and new theoretical models. When possible, papers should compare
and contrast wavelet based approaches to traditional techniques.
Topics for the conference may include but are not limited to:
- image pyramids
- frames and overcomplete representations
- multiresolution algorithms
- wavelet-based noise reduction and restoration
- multiscale edge detection
- wavelet texture analysis and segmentation
- Gabor transforms and space-frequency localization
- wavelet-based fractal analysis
- multiscale random processes
- wavelets and neural networks
- image representations from wavelet maxima or zero-crossings
- wavelet compression, coding and signal representation
- wavelet theory and multirate filterbanks
- wavelets in medical imaging
--> EXTENDED DEADLINES <---
Abstract Due Date: February 15, 1994.
MANUSCRIPT DUE DATE: June 27, 1994
(Proceeding will be made available at the conference)
Applicants shall be notified of acceptance by March 1, 1993.
Your abstract should include the following:
1. Abstract Title.
2. Author Listing (Principal author first and affiliations).
3. Correspondence address for EACH author (email, phone/FAX, ect.).
4. Submitted to: Mathematical Imaging: Wavelet Applications
in Signal and Image Processing,
Andrew Laine, Chairman.
5. Abstract: 500-1000 word abstract.
6. Brief Biography: 50-100 words (Principal author only).
Please send FOUR copies of your abstract to the address below
via FAX, email (one copy) or carrier:
San Diego '94
SPIE, P.O. Box 10, Bellingham, WA 98227-0010
Shipping Address: 1000 20th Street, Bellington, WA 98225
Phone: (206) 676-3290
email: abstracts@mom.spie.org
FAX: (206) 647-1445
CompuServe: 71630,2177
Notice: Late submissions may be considered subject to program
time availability and approval of the program committee.
Andrew Laine, Assistant Professor
Computer and Information Sciences Department
University of Florida
Gainesville, FL 32611
Phone:(904) 392-1239
Email:LAINE@CIS.UFL.edu
------------------------------
Date: 24 Jan 1994 22:04:42 GMT
From: announce@space.bu.edu (Boston University Center for Adaptive Systems)
Organization: Center for Adaptive Systems, Boston University, Boston, MA, USA
Subject: Boston U. Ctr. for Adaptive Systems Spring 1994 Colloquia
Spring 1994 Colloquium Series
CENTER FOR ADAPTIVE SYSTEMS
AND
DEPARTMENT OF COGNITIVE AND NEURAL SYSTEMS
BOSTON UNIVERSITY
February 8
NEW RESULTS ON ILLUSORY CONTOURS
Professor Robert Shapley, Department of Psychology, New York University
February 15
DYNAMICS OF INTERLIMB RHYTHMIC COORDINATION
Professor Michael Turvey, Department of Psychology,
University of Connecticut
March 1
REPRESENTATION OF SHAPE INFORMATION IN TEMPORAL CORTEX OF THE PRIMATE
Professor Paul Gochin, Department of Psychology, Princeton University
March 15
AN ARCHITECTURE FOR UNIFIED VISUAL CONTRAST AND BRIGHTNESS PERCEPTION
Dr. Heiko Neumann, Department of Computer Science, University of Hamburg
March 22
COVERT OPERATIONS: HOW WE DEPLOY VISUAL ATTENTION
Professor Jeremy Wolfe, Center for Ophthalmic Research,
Brigham & Womens Hospital
March 29
RECOVERING HEADING FOR VISUALLY GUIDED NAVIGATION IN THE
PRESENCE OF MOVING OBJECTS
Professor Ellen Hildreth, Department of Computer Science, Wellesley College
April 5
SUBTYPING MAJOR DEPRESSIVE DISORDERS: EMPIRICAL AND CLINICAL APPROACHES
Professor Jacqueline A. Sampson, Department of Psychiatry,
Harvard Medical School, and the Depression Research Facility,
McLean Hospital
April 12
SKILL ACQUISITION, COARTICULATION, AND RATE EFFECTS IN A
NEURAL MODEL OF SPEECH PRODUCTION
Professor Frank Guenther, Department of Cognitive and Neural Systems,
Boston University
April 19
FROM `NEUROTHINKING' TO NEUROCONTROL
Dr. Andras Lorincz, Institute of Isotopes,
Hungarian Academy of Sciences
April 26
WORDS AND RULES
Professor Steven Pinker, Department of Brain and Cognitive Sciences, MIT
All Talks on Tuesdays at 3:30 PM in Room 101
Refreshments at 3:00 PM in Room 101
2 Cummington Street, Boston
PLEASE POST
------------------------------
End of VISION-LIST digest 13.5
************************
