Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!ucsd!ucbvax!ADS.COM!Vision-List-Request From: Vision-List-Request@ADS.COM (Vision-List moderator Phil Kahn) Newsgroups: comp.ai.vision Subject: Vision-List digest delayed redistribution Message-ID: <9011280500.AA16532@deimos.ads.com> Date: 27 Nov 90 20:28:14 GMT Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: Vision-List@ADS.COM Distribution: inet Organization: The Internet Lines: 587 Approved: vision-list@ads.com Vision-List Digest Tue Nov 27 12:28:14 PDT 90 - Send submissions to Vision-List@ADS.COM - Send requests for list membership to Vision-List-Request@ADS.COM Today's Topics: PD Range Image Archive RE: Optical Flow in Realtime Public domain image processing / vision software CVNet- Several Postdoctoral Positions Job opening: Assistant Professor, Cognitive Psychology, Yale Job opening: Chair of Computer Science at Birmingham University, UK Call for Papers: Neural Networks in System, Control, Vision and Genetics CVNet- Neural Net Conference Announcement ---------------------------------------------------------------------- Date: Mon, 26 Nov 90 14:38:09 EST From: flynn@shillelagh.cse.nd.edu (Patrick J. Flynn) Subject: PD Range Image Archive Back in February, I made 44 range images available for anonymous ftp from my workstation at Michigan State University, and said: >> I will try to keep these images available [...] >> until I leave MSU this summer. >> If my next job has machines with internet access and some disk space, >> I'll put them there. The archive has been expanded (over 200 images, including 100 synthetic images generated from CAD models) and moved from Michigan State to my Sun here at Notre Dame. The machine name and IP address is: shillelagh.cse.nd.edu (129.74.9.7) The images are in the pub/range-images directory. The README file from that directory appears below. Please remember to use binary mode when transferring files, and perform ftp transfers AFTER `normal' business hours (i.e. do it between 1700 EST and 0800 EST). I reserve the right to disable ftp activity during the day if it significantly impacts my ability to use shillelagh for my work. Direct *specific* questions about the images to me (flynn@cse.nd.edu). General questions about range sensing are best answered by reading the surveys by Jarvis (PAMI '83), Nitzan (PAMI '88), or Besl (in the `Advances in Machine Vision' book by J. Sanz, pub. by Springer, or in the `Machine Vision and Applications' journal, volume 1). A European version of the archive is in the works (courtesy of Adrian Clark). I will post details to vision-list when we get it set up. Here is the text of the README file in the pub/range-images directory. This directory contains a bunch of range images produced by - the MSU Pattern Recognition and Image Processing Lab's Technical Arts 100X scanner (aka `White scanner'), OR - scan-conversion software that I adapted from a program originally written by Paul Besl many years ago. You are free to use these images to test your algorithms. If the images are to appear in a published article, please acknowledge the MSU PRIP Lab as the source of the images (you don't have to mention my name, though). File format: rather than deal with all the goofy standards out there for images (and to preserve the floating-point representation), these images are compressed ASCII text files. Beware: they expand by about 10x when uncompressed. I recommend that you keep them compressed to save disk space. Many of you will probably convert these files to your own `local' image format anyway. Each image file has a three-line header giving the number of rows and columns. This is followed by four images. The first is the so-called 'flag' image, where a pixel value of 1 means the corresponding (x,y,z) values at that pixel are valid. If the flag value is zero, you should ignore the (x,y,z) components for that pixel. Following the flag image is the image of X-coordinates, the image of Y-coordinates, and the image of Z-coordinates. All are floating-point images. MSU's White scanner is configured so that each stripe of range values occupies one column in the image. The object is swept under the stripe with an XY table to get an image. So the X coordinate image is a linear ramp; the X value is taken from the absolute position of the X stage in the XY table. The Y value depends on the column number of the pixel, and the Z value is the measured range (the height above a table). You can use the 3D coordinates of each range pixel, or you can throw away the X and Y images, and concern yourself with the Z-value alone. Note that the `aspect ratio' of the image doesn't have to be 1, although I try to keep it in the neighborhood of 1. Remember to use binary mode when you transfer the images. Contents: In this directory, there are 4 subdirectories: NAME SIZE CONTENTS cluttered 1302KB 10 White Scanner images of pairs of objects isolated 9270KB 100 White Scanner images; 5 images of each of 20 objects misc 6008KB 47 `miscellaneous' images of various objects The files labeled `foot1' and `foot2' are images of a human foot (belonging to Dr. Rick Hallgren). Most of the others are blocky, industrial-ish parts. synth 22027KB 100 synthetic images; 5 images of each of 20 objects (the same 20 objects as in the `isolated' directory). ------------------------------ Date: Mon, 19 Nov 90 11:11:54 GMT From: Massimo Tistarelli Subject: RE: Optical Flow in Realtime I have developed a system for the computation of the optical flow in real-time using the Connection Machine. It is capable of computing a dense optic flow from image sequences at near real time, allowing the computation of one velocity field at a rate of 20 frames per second. The program is Public Domain, I can send it directly to you or you can ask Thinking Machines Co. in Cambridge (MA), together with related documentation. Also the time-to-impact can be computed at almost no "extra cost" in terms of processing time. As the algorithm is devised, it will be possible to realize an implementation of the system on other parallel machines. I' m currently working on it! Regards, Massimo Tistarelli (tista@dist.unige.it) ------------------------------ Date: Wed, 21 Nov 90 11:40:08 CST From: honavar@iastate.edu Subject: public domain image processing / vision software Thanks to all those who volunteered information on public domain image processing packages. Here is a summary. Vasant Honavar honavar@iastate.edu ************************************************************* From: Stephen M. Pizer I write in response to your news item requesting info on public domain image processing packages using X. UNC's /usr/image image processing package is Unix and X based. It is in the public domain and is licensed and distributed by softlab@cs.unc.edu for a copying cost of $300. It is installed in around 40 sites worldwide, most of which are involved in medical image processing. It consists of a collection of image access modules, numerous X-based display modules, including 2D, 3D, and cinematic display, and a wide range of around 75 image processing, analysis, and utility programs. Maintenance is not provided. Further information can be obtained from gash@cs.unc.edu. ************************************************************** From: yangchen%iris.usc.edu@usc.edu (Yang Chen) Well, we have an OBVIUS system from MIT available from whitechapel.media.mit.edu. It provides some basics for doing image processing using LISP. It runs under either SunView or X-window. ************************************************************** From: rasure@snidley.unm.edu (John Rasure) The Vision Lab at the University of New Mexico announces the open distribution of the Khoros system (Beta release)! INTRODUCTION Khoros is an integrated software development environ- ment for information processing and visualization, based on X11R4. Khoros components include a visual programming language, code generators for extending the visual language and adding new application packages to the system, an interactive user interface editor, an interactive image display package, an extensive library of image and signal processing routines, and 2D/3D plotting packages. SYSTEM COMPONENTS X Windows Applications Cantata - Extensible Visual Programming Language Editimage - Interactive Image Display & Manipulation Program Animate - Interactive Image Sequence Display Tool Xprism2 and xprism3 - Comprehensive 2D and 3D Plotting Packages Image & Signal Processing Algorithms The library of algorithms contains over 220 programs, in the following categories: arithmetic, classifica- tion, color conversion, data conversion, file format conversion, feature extraction, frequency filtering, spatial filtering, morphology filtering, geometric manipulation, histogram manipulation, statistics, sig- nal generation, linear operations, segmentation, spec- tral estimation, subregion, and transforms. User Interface Tools Preview - Graphical User Interface Display Tool Composer - Interactive Graphical User Interface Editor Conductor - Code Generation Tool for a Graphical User Interface Ghostwriter - Code Generation Tool for a Command Line User Interface Source Configuration & Management Tools KHOROS DISTRIBUTION METHODS 1) Anonymous FTP Khoros is available via anonymous ftp from pprg.unm.edu (129.24.13.10). Use your e-mail address as the password (for example, herman@football.wmu.edu). Once you have logged in, cd to the "pub/khoros" directory and get the ascii file RELEASE_NOTES.ftp. This file will give you com- plete instructions on how to get Khoros and install it on your system. To get this file, execute the following com- a. Use ftp to connect to pprg.unm.edu. % ftp pprg.unm.edu -or- % ftp 129.24.13.10 b. Use "anonymous" or "ftp" as the user name. Name (pprg.unm.edu:login): anonymous -or- Name (pprg.unm.edu:login): ftp c. Use your e-mail address as the password; please care- fully use a valid e-mail address, as this version site logs all anonymous ftp's. Password (pprg.unm.edu:user): {your valid email address} 331 Anonymous login ok, use your E-MAIL address as the password. 230 Guest login ok, access restrictions apply. d. Get the release notes for acquiring Khoros via anonymous ftp (note that "RELEASE_NOTES.ftp" is the plain text file - both ".ms" and ".ps" files are avail- able for those who would like them). ftp> cd /pub/khoros ftp> get RELEASE_NOTES.ftp 2) UPS Delivery If you would like to have a tape and printed documenta- tion sent to you, send the order form below (last page) along with a $1000.00 check or purchase order (payable to UNM EECE Dept., in U.S. funds) to: KHOROS Room 110 Department of EECE University of New Mexico Albuquerque, NM 87131 We will begin shipping tapes (source, binaries and printed documentation) no earlier than November 1st. Please remember, this is a BETA release; the final release will be complete in January 1991. There will be no support or updates provided for the beta release. KHOROS REQUIREMENTS AND LIMITATIONS To run Khoros, you must have a UNIX platform running the X11R3, X11R4, or OpenWindows servers. The Khoros system consists of ~350,000 lines of C code; it requires ~100 Meg for storage for source, documentation and binaries. To com- pile Khoros, the system requires X11R4 from MIT (patch lev- els 1-18), and an additional ~30 Meg of storage. If you have questions or problems, mail rasure@bullwinkle.unm.edu. Once you have the system and want to report bugs or comments, mail khoros-bugs@bullwinkle.unm.edu. UNIX is a trademark of AT&T Bell Laboratories. The X Window System is a trademark of Massachusetts Insti- tute of Technology. SunOS is a trademark for Sun Microsystems. Ultrix is a trademark of Digital Equipment Corporation. ------------------------------ Date: Mon, 19 Nov 90 09:35:55 EST From: Color and Vision Network Subject: CVNet- Several Postdoctoral Positions Postdoctoral Positions CENTER FOR VISUAL SCIENCE University of Rochester The Center for Visual Science has postdoctoral positions available in several areas of visual science, including, but not restricted to, psychophysical, computational and physiological aspects of spatial vision, color vision, eye-movements, and motion perception. Through its provision of shared resources the Center for Visual Science brings together faculty and students from different parts of the University, including the College of Arts and Science, and the Medical School. The Center encourages collaborative research, and post-doctoral fellows have substantial freedom to pursue projects that involve several members of the faculty. Faculty include: Joanne Albano, Richard Aslin, Dana Ballard, Robert Chapman, Robert Emerson, Mary Hayhoe, Michael King, Kyunghee Koh, Peter Lennie, Walter Makous, John Maunsell, William Merigan, Gary Paige, Tatiana Pasternak, David Williams. For general information about the Center and about postdoctoral opportunities, contact Peter Lennie (lennie@cvs.rochester.edu, phone: 716-275-2450). Prospective postdoctoral fellows interested in working with particular members of faculty should contact those members directly. Any member of the Center can be reached by email using his or her surname as a username (e.g., albano@cvs.rochester.edu). ------------------------------ Date: Wed, 21 Nov 90 11:05:36 EST From: michael tarr Subject: Job opening: Assistant Professor, Cognitive Psychology, Yale Assistant Professor, Cognitive Psychology: The Department of Psychology at Yale University expects to make an appointment at the rank of Assistant Professor in the area of cognitive psychology effective July 1, 1991. Outstanding candidates in any subspeciality of this area are encouraged to apply. All applicants are expected to provide high- quality teaching at the undergraduate level and in a graduate cognitive psychology program, and to have exhibited (or shown very clear promise of) excellence in research. Applicants should send a letter of application, a resume, and papers or reprints, and should arrange for three letters of recommendation to be sent to: Chair, Cognitive Psychology Search Committee, Department of Psychology, Yale University, Box 11A Yale Station, New Haven, CT 06520-7447. Deadline for completed applications: February 1, 1991. Yale is an Equal Opportunity/ Affirmative Action employer, and applications from women and minority group members are especially encouraged. ------------------------------ Date: Mon, 26 Nov 90 09:06:58 -0500 From: fpst@hubcap.clemson.edu (Steve Stevenson) Subject: Job opening: Chair of Computer Science at Birmingham University, UK Birmingham University (which I shall be joining from 1st August 1991) wishes to appoint another professor in the School of Computer Science. Only candidates with an established research and publications record and potential for attracting research students will be considered. Applicants from any area of Computer Science will be considered, and the primary requirement is academic distinction, though because there is already one professor with interests in AI/cognitive science, applicants from other fields will have preference, other things being equal. The post will be on the professorial scale (minimum 27013 pounds p.a.) Full details are available from Mr. P.J.F. Scott, Director of Staffing Services University of Birmingham Edgbaston Birmingham B15 2TT England Phone +44 (0)21-414-3841 FAX +44 (0)21-414-4802 Applications (ten copies for UK applicants, one copy for overseas applicants) should be in by 14 December, though late applications will be considered. It is hoped that short-listed candidates will be interviewed on 19th March. Further enquiries about the nature of the job to Prof Peter Jarratt School of Computer Science University of Birmingham Edgbaston Birmingham B15 2TT England Phone +44 (0)21-414 3711 Email P.JARRATT@BIRMINGHAM.AC.UK The university is located on a large park south of the centre of Birmingham, with academic buildings at one end, student halls at the other and a lake in between. Substantial resources have recently been made available for developing computer science and cognitive science. ------------------------------ Date: Wed, 21 Nov 90 19:00:49 GMT From: rswiniar%ania@ucselx.sdsu.edu (Dr. Roman Swiniarski) Subject: Call for Papers: Neural Networks in System, Control, Vision & Genetics Organization: San Diego State University, Computer Science Call for Papers The First International Conference on ``NEURAL NETWORKS IN SYSTEM, CONTROL, VISION AND GENETICS'' Methodologies and Applications May 29-31, 1991, San Diego, U.S.A. The conference will be organized under the auspice of International Organization ``Association Pour Promotion Des Techniques de Modelisation at de Simulation dans L'Enterprise with the participation of San Diego State University. The conference will be an international forum for presenting and discussing the issues in neural networks and their applications in: system, control, robotics, computer vision, and genetic engineering. TOPICS 1. Neural Network Architectures and Learning Algorithms. Static Neural Networks. Dynamic and Recurrent Neural Networks. Fuzzy Neural Networks. Probabilistic Neural Networks. Fractal and Cellular Neural Networks. Oscillating Neural Networks. Hybrid Neural Networks. Ensembles of Neural Networks. Genetic and Parallel Training Algorithms. Fast and Adaptive Learning Algorithms. Adaptive Critic and Reinforcement Learning. Unsupervised Learning. Generalization. Learnability. Stability and Informational Capacity of Neural Networks. 2. Applications of Neural Networks. 2.1. Signals and Systems: Temporal Pattern Recognition. Modeling. Nonlinear Systems. Adaptive Signal Processing. Identification. Estimation and Filtering. Temporal Data Compression. Combinatorial Optimization. 2.2. Control and Robotics: Stability Analysis and Robust Control. Optimal Control. Adaptive Control. Self-Tuning Control. Variable Structure Control. Sequential Control. Predictive Control. Adaptive Control of Robot. Autonomous Robots. Target Recognition and Tracking. Robot Grasping. Trajectory Planning. Multisensor Fusion. 2.3. Diagnostic and Inspection: Failure Detection in Control Systems. Sensor Failure Detection. Diagnostic of Dynamic Systems. Feature Extraction from Temporal Signals. 2.4. Computer Vision: Image Modelling and Estimation. Image Compression. Feature Extraction. Image Filtering and Enhancing. Segmentation. Motion Detection. 2.5. Genetics: Retrieving Information from Large Genome Data Banks. Genome Sequence Matching. Genome Sequence Alignments Hard Combinatorial Optimization. in Phylogenetic Analysis. 2.6. Text Processing and Pattern Recognition: Hand Written Recognition. Printed Text Recognition. Text Compression. Paper Submission Authors are cordially invited to submit papers describing relevant research and experience. Authors should send two copies of a ``One page summary'' on a standard sheet of paper (A4 21x29.7 cm). Summaries including full names, affiliations, addresses, and FAX or e-mail of authors, should be mailed to the General Chairman of the Conference. Deadline for submission of a summary: February 28, 1991.\\ Summaries of proposed papers, will be reviewed by the International Program Committee. Full texts of accepted papers may be provided up to the Conference. Initiatives in organizing sessions are invited.\\ The selected papers presented at the Conference will be published in the Conference Proceedings. Selected papers will be additionally published in a special monograph. Conference Committee. General Chair G. Masnard President of ``Association Pour Promotion Des Techniques de Modelisation at de Simulation dans L'Enterprise '' 16 avenue de Grange-Blanche, 69160 TASSIN-LA-DEMI-LUNE, France FAX 011-33-78345417 (from USA). Chair of International Program Committee Roman Swiniarski Department of Mathematical Sciences San Diego State University San Diego , CA 92182-0314, USA e-mail: rswiniar@ania.sdsu.edu Tel: (619) 594-5538 Fax: 619-594-5642 The venue of conference and other details will be provided in a later announcement. ------------------------------ Date: Wed, 21 Nov 90 17:03:11 EST From: Color and Vision Network Subject: CVNet- Neural Net Conference Announcement NEURAL NETWORKS COURSE AND CONFERENCE AT BOSTON UNIVERSITY NEURAL NETWORKS: FROM FOUNDATIONS TO APPLICATIONS May 5-10, 1991 This self-contained 5-day course is sponsored by the Boston University Wang Institute, Center for Adaptive Systems, and Graduate Program in Cognitive and Neural Systems. The course provides a systematic interdisciplinary introduction to the biology, computation, mathematics, and technology of neural networks. Boston University tutors are Stephen Grossberg, Gail Carpenter, Ennio Mingolla, Michael Cohen, Dan Bullock, and John Merrill. Guest tutors are Federico Faggin, Robert Hecht-Nielsen, Michael Jordan, Andy Barto, and Alex Waibel. Registration fee: $985 (professional) and $275 (student). NEURAL NETWORKS FOR VISION AND IMAGE PROCESSING May 10-12, 1991 This research conference at the Wang Institute will present invited lectures and contributed posters, herewith solicited, ranging from visual neurobiology and psychophysics through computational modelling to technological applications. Invited speakers include: Jacob Beck, Gail A. Carpenter, David Casasent, John Daugman, Robert Desimone, Stephen Grossberg, Robert Hecht-Nielsen, Ralph Linsker, Ennio Mingolla, Alex Pentland, V.S. Ramachandran, Eric Schwartz, George Sperling, James Todd, and Alex Waxman. A featured Poster Session will be held on May 11. To present a poster, submit 3 copies of an abstract (1 single-spaced page), postmarked by March 1, 1991, for refereeing. Include with the abstract the author's name, address, and telephone number. Mail to VIP Poster Session, Neural Networks Conference, Wang Institute of Boston University, 72 Tyng Road, Tyngsboro, MA 01879. Authors will be informed of abstract acceptance by March 31, 1991. Registration fee: $95 (professionals) and $75 (student). Fee includes lectures and poster session, reception, meals, and coffee services. TO REGISTER: For one or both events by phone, call (508) 649-9731 with VISA or MasterCard between 9 a.m. - 5 p.m. (EST). For a meeting brochure, call as above or write: Neural Networks, Wang Institute of Boston University, 72 Tyng Road, Tyngsboro, MA 01879. ------------------------------ End of VISION-LIST ********************