Copy Link
Add to Bookmark
Report
VISION-LIST Digest 1989 01 14
Vision-List Digest Sat Jan 14 12:40:07 PDT 89
- Send submissions to Vision-List@ADS.COM
- Send requests for list membership to Vision-List-Request@ADS.COM
Today's Topics:
Request for Industrial Research Topics
How to evaluate computer vision techniques?
Course announcement: Computational Neuroscience
Role of Vision List (posted to comp.graphics)
IEEE 1989 Int Conf on Image Processing (Last Call for Paper)
----------------------------------------------------------------------
Date: Mon, 09 Jan 89 08:42:03 -0500
Subject: Request for Industrial Research Topics
<8901060238.AA28121@ads.com>
From: "Kenneth I. Laws" <klaws@note.nsf.gov>
Most engineers start with real problems and do research
to find appropriate tools and solutions. Most academics
start with tools and do research to find appropriate
problems and funding agencies. Perhaps Vision-List
could help bring the two together by generating a list
of real-world problems that need to be solved. This would
help the master's students and the companies with the
problems. I've been told that it would also be a big
help to the funding agencies, particularly the NSF
Small Business program. (It seems that publishing a
specific problem description usually draws good proposals,
whereas vague RFPs may draw nothing.)
I'm not thinking about generic research topics such as
shape from shading or stereo vision -- everyone knows about
those. I'm thinking about applications such as inspecting
solder joints or nose cone windings. Are there specific
problems which seem solvable but for which no off-the-shelf
technology is available? Could some startup or small business
profit by helping your production line with a particular
inspection task? What specific capabilities should the funding
agencies be trying to develop in the next five years?
Academics usually don't wish to reveal their ideas until
they can put together at least a conference paper -- at which
time there is little motivation for publishing in Vision-List.
The field also suffers from lack of definitive solutions for
any problem, making it impossible for any researcher to
declare victory and close out a line of research. I hope that
the engineers will be less reticent in sharing the problems
they are working on (or have insufficient time or interest
to work on). Making a problem widely known may be the
quickest way of uncovering an easy solution or a worthwhile
research priority.
-- Ken
------------------------------
Date: Fri, 6 Jan 89 14:26:14 pst
From: ramin@scotty.stanford.edu (Ramin Samadani)
Subject: How to evaluate computer vision techniques?
I am looking for published results in "quality of results" of computer vision
techniques.
In reading some of the computer vision literature, I get the feeling that
many techniques are proposed, but are not fully tested. Is this true or have
I missed some body of work out there? Are there any standard or published
methods for testing new techniques? Could someone point me to any
literature on evaluation of the "quality" of computer vision techniques? Are
there studies where the techniques have been tried on a large number of
images?
Ramin Samadani
202 Durand Bldg.
Electrical Engineering
Stanford, CA 94305
ramin@scotty.stanford.edu
------------------------------
Date: Thu, 12 Jan 89 09:19:51 EST
From: tony@cortex.psych.nyu.edu (Tony Movshon)
Subject: Course announcement: Computational Neuroscience
Cold Spring Harbor Laboratory Course Announcement, Summer 1989
COMPUTATIONAL NEUROSCIENCE: VISION
Instructors:
Ellen C. Hildreth, Massachusetts Institute of Technology
J. Anthony Movshon, New York University
July 2 - 15
Computational approaches to neuroscience have produced important advances
in our understanding of neural processing. Prominent successes have come in
areas where strong inputs from neurobiological, behavioral and computational
approaches can interact. Through a combination of lectures and hands-on
experience with a computer laboratory, this intensive course will examine
several areas, including feature extraction, motion analysis, binocular
stereopsis, color vision, higher level visual processing, visual neural net-
works, and oculomotor function. The theme is that an understanding of the com-
putational problems, the constraints on solutions to these problems, and the
range of possible solutions can help guide research in neuroscience. Students
should have experience in neurobiological or computational approaches to
visual processing. A strong background in mathematics will be beneficial.
Past lecturers have included: Richard Andersen, Peter Lennie, John Maun-
sell, Gerard Medioni, Michael Morgan, Ken Nakayama, Tomaso Poggio, Terrence
Sejnowski, William Thompson, Shimon Ullman, and Brian Wandell.
The deadline for application is March 15, 1989. Applications and addi-
tional information may be obtained from:
REGISTRAR
Cold Spring Harbor Laboratory
Box 100
Cold Spring Harbor, New York 11724
Telephone: (516) 367-8343
------------------------------
Date: Sat, 14 Jan 89 12:37:03 PST
From: Vision-List-Request <vision@deimos.ads.com>
Subject: Role of Vision List (posted to comp.graphics)
[ Apparently, the role of comp.ai.vision and the Vision List has been
discussed on comp.graphics. E.g., they wanted to know if image processing
was appropriate for this List. The following is a copy of the message I
posted to that group.
phil... ]
The role of comp.ai.vision has been discussed in this group, and as
moderator, I thought it would be appropriate to outline the role of
the vision newsgroup.
The Vision List is a moderated newsgroup for which messages may be
posted by mailing to Vision-List@ADS.COM. Administrative questions
(e.g., to get added/deleted, editorial comments, etc) should be sent
to Vision-List-Request@ADS.COM. The Vision List is distributed
through comp.ai.vision and via direct mail accounts for users which do
not have access to USENET.
The Vision List is intended to embrace discussion on a wide range of
vision topics, including physiological theory, computer vision,
machine vision and image processing algorithms, artificial
intelligence and neural network techniques applied to vision,
industrial applications, robotic eyes, implemented systems, ideas,
profound thoughts -- anything related to vision and its automation is
fair game.
Since this is a graphics newsgroup, let me carefully distinguish what
I believe the primary difference between the graphics and vision
newsgroups. Quite simply, in graphics one goes from the computer to a
screen; in vision, one goes from the sensor to the computer. I.e., the
difference is one of generation versus interpretation. So, for example, an
image processing algorithm which is of use only in image generation would
best appear in comp.graphics or a similar netgroup. Conversely,
image filtering techniques can quite useful in the initial stages of imagery
interpretation. The bottom line: If when you ask yourself "Would this be
of use in understanding imagery?" you get a "Yes!", then it should be
posted to Vision-List@ADS.COM.
Hope this has helped to clarify things a bit.
Philip Kahn
moderator, Vision List
(administrative) Vision-List-Request@ADS.COM
(submissions) Vision-List@ADS.COM
------------------------------
Date: Mon, 9 Jan 89 08:56 H
From: <CHTEH%NUSEEV.BITNET@CUNYVM.CUNY.EDU>
Subject: IEEE 1989 Int Conf on Image Processing (Last Call for Paper)
IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING
(ICIP'89)
5-8 September, 1989, Singapore
CALL FOR PAPERS (Updated)
The 1989 IEEE International Conference on Image
Processing (ICIP'89) will be held in Singapore on 5-8
September, 1989. The conference is jointly organized by the
Computer Chapter, IEEE Singapore Section and the Department
of Electrical Engineering, National University of Singapore.
The conference will include regular sessions on all aspects
of the theory and applications of image processing. In
addition, tutorials by eminent speakers presenting the
state-of-the-art in selected areas of image processing will
be offered. An exhibition will be held in conjunction with
the conference.
Papers describing original work in all aspects of image
processing are invited. Topics for regular sessions
include, but are not limited to, the following :
Image analysis/modeling Office image processing
Image restoration/enhancement Machine vision
Video communications AI vision techniques
Image pattern recognition VLSI implementation
Remote sensing System architecture
Biomedical imaging Color image processing
Authors are invited to submit four copies of an
extended summary of at least 1000 words to :
Technical Program Chairman, ICIP'89
c/o Meeting Planners Pte Ltd
100 Beach Road, #33-01
Shaw Towers, Singapore 0718
Republic of Singapore
Telex : RS40125 MEPLAN
Fax : (65) 2962670
E-mail : OSH@NUSEEV.BITNET
The summary should contain sufficient detail, including
a clear description of the salient concepts and novel
features of the work. The summary should include the
authors' names, addresses, affiliations, and telephone,
telex and fax numbers. The authors should also indicate one
or more of the above topics that best describe the contents
of the paper.
Proposals for tutorials and special sessions are also
welcome and should be addressed to the Technical Program
Chairman before 16 January 1989.
AUTHORS' SCHEDULE
Submission of summary 1 February 1989
Notification of acceptance 31 March 1989
Submission of final manuscripts 1 June 1989
------------------------------
End of VISION-LIST
********************
