NetNews Usenet Archive 1992 #30

home *** CD-ROM | disk | FTP | other *** search

/ NetNews Usenet Archive 1992 #30 / NN_1992_30.iso / spool / comp / ai / vision / 43 next >

Wrap

Internet Message Format | 1992-12-15 | 59.8 KB

Path: sparky!uunet!zaphod.mps.ohio-state.edu!cis.ohio-state.edu!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 11.43 Message-ID: <9212152214.AA20306@deimos.ads.com> Date: 15 Dec 92 21:55:20 GMT Sender: daemon@ucbvax.BERKELEY.EDU Reply-To: Vision-List@ads.com Distribution: inet Organization: The Internet Lines: 1579 Approved: vision-list@ads.com VISION-LIST Digest Tue Dec 15 13:55:20 PDT 92 Volume 11 : Issue 43 - ***** The List is moving sites soon: you will be notified **** - 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: Re: Request for Road Images request for Kanji characters Non-Rigid Recognition Signal to Noise ratio Question Plausible pattern recognition (Info needed) Help! Energy Reduction Algorithm for SP Optical Music Recognition - Bibliography aviable LaboImage 4.0: new X11 version Studentships Doctoral Program in Philosophy-Psychology-Neuroscience Special issue of the machine vision and applications AAAI '93 : Call for Papers CFP: Geometric Methods in Computer Vision Sun Pix (long) References on automatic face recognition (long) Snakes: summary of responses (long) ---------------------------------------------------------------------- Date: Fri, 04 Dec 92 09:20:27 +1100 Subject: Re: Request for Road Images From: stevea@vast.unsw.edu.au >From Vision-List digest 11.42: I am interested to get sequence of road images (24 bits color) taken from a mo ving car. Road sign of any type should be visible along the road. There are several places you can get this sort of imagery. Probably the best site though is cicero.cs.umass.edu, which is the home site of Allen R. Hanson and Edward M. Riseman (of image segmentation fame). They have a great liking for roadside images in their experimental results, and there are many samples there. Please note though, that not all of them have road signs in them. The directories you probably want most are area_road_scenes and amherst_roads. Another site that has a set of images that may be helpful is isy.liu.se, which has a video sequence taken from inside a car. This sequence contains one prominent road sign, and possibly one or two more further away from the camera involving road works. I hope this info is useful for you. cheers -steve Steve Avery | VLSI and Systems Technology Laboratory, (PhD type student person) | School of Computer Science & Engineering, | University of New South Wales, stevea@vast.unsw.edu.au | P.O. Box 1, Kensington, 2033, Australia. "Why have you two eyes and just one mouth?" -Ryuchi Sakamoto Here is the content of the file README.image_files that is located in the home directory at this site: This directory contains the image library of the VISIONS group at UMass/Amherst. Each sub-directory contains a specific sort of image: Typically the name of the directory suggests the sort of images in the directory. There is also an interactive DB of image descriptions available. Telneting in as 'visimgdb' to cicero.cs.umass.edu will place you in an interactive program which will allow you to search a data base of image descriptions. The data base and the program to access are also available for FTP'ing in the directory imdb (the data base is vis-imagedb.ilb* and the program source is in image_db.tar.Z). Most of the image data is in what we call "Universal Plane File Format" - this is a variation of our LLVS plane file format. The directory 'universal_plane_file_format' contains documentation describing this format as well as code to read these files on several different platforms. These plane files always have an extension of '.plane'. Plane files should always be transfered in binary mode. If you have questions or can't find a particular sort of image, let us know by sending E-Mail to me Robert Heller (systems programmer) <heller@cs.umass.edu> or Val Conti (Lab Manager) <conti@cs.umass.edu>. Jan-15-1991 - by popular request, some of the motion data files have been collected into tar files and compressed. Also, all of the files in 'universal_plane_file_format' have also been collected into a tar file and compressed. This has been done to make FTP'ing easier. RPH. ------------------------------ Date: Mon, 14 Dec 92 09:31 JST From: SHARONE%HADASSAH@VMS.HUJI.AC.IL Subject: request for Kanji characters A friend of mine needs for his research in Pattern Recognition a set of contours from KANJI characters. Email or pointers to a FTP site are welcomed. Thanks in Advance. Haim Karger Dept of Nuclear Medecine ------------------------------ From: brian@ai.mit.edu (Brian Subirana) Date: Mon, 14 Dec 92 09:23:35 EST Subject: Non-Rigid Recognition I am interested in collecting references on non-rigid objects for a survey that I am writing. Particularly, but not exclusively, recent ones on the recognition of non-rigid objects. Pointers are most welcomed, Brian Subirana MIT AI Lab Email: brian@ai.mit.edu ------------------------------ Date: Sat, 12 Dec 1992 19:19:51 -0500 From: kwon lim <lim@silver.ucs.indiana.edu> Subject: Signal to Noise ratio Question Could someone tell me if the following phrase make sense ? "A signal to noise ratio of a SAR image is 1 or 2". My question is: Is it possible to assert the signal to noise ratio of a two dimension signal(say grey scale image) without considering some noise model. It seems like there is some way of obtaining the signal to noise ratio as a measure of how good or bad the signal is. In other words, my question boils down to the one of how to separate signal and noise component. Any ideas or references will be appreciated. Thanks in advance. ------------------------------ Date: Fri, 4 Dec 1992 02:44:31 GMT From: yang@dante.cs.uiuc.edu (Der-Shung Yang) Organization: University of Illinois, Dept. of Comp. Sci., Urbana, IL Subject: Plausible pattern recognition (Info needed) Keywords: plausible pattern recognition Hi, I'm doing some research on pattern recognition. The domain I'm working on has a special feature that seems interesting (at least to me:-) in general. I'm looking for any special technique that handles this situation or any opinions on whether this feature exists in any other domains. I'm trying to develop a system to recognize what a user is drawing on a CAD (Computer-Aided Design) screen. This looks like a very general pattern recognition problem. However, in this domain, there's no need for "perfect recognition." That is, my system only needs to suggest a fixed number of objects that look similar to what the user is drawing, possibly ranked by the "similarity" between the suggested object and the user's input, with the most similar one output first. So, a good system should output the target object as soon as possible, but not necessarily get it right at the first place. I call this type of problem "plausible pattern recognition," meaning that the recognition only needs to make plausible suggestions, not the perfect one. To me, this type of problem seems to reduce the difficulty of recognition and is more doable than trying to find a "perfect" system. If you came across something similar to this type of problem or have some opinions on whether "plausible PR" is important theoretically or practically, please let me know. Both emails and followups are welcome. Comments, references, and/or critics are all greatly appreciated. DerShung Yang yang@cs.uiuc.edu Beckman Institute Univ. of Illinois at Urbana-Champaign ------------------------------ Date: Fri, 11 Dec 92 19:30:52 EST From: ge@acsu.buffalo.edu (Wang Ge) Subject: Help! Energy Reduction Algorithm for SP Dear Colleagues, I once heard of the energy reduction algorithm for recovering a signal on an interval from its known values on other intervals. Would you please give me some pointers to recent papers and public software (C is preferred). Thank you very much! Ge ------------------------------ Date: Mon, 14 Dec 1992 13:05:12 GMT From: roth@sitter.ips.id.ethz.ch (Martin Roth) Organization: ETH Zurich (Swiss Federal Institute of Technology) Subject: Optical Music Recognition - Bibliography aviable I compiled a bibliography for Optical Music Recognition (automatic reading a scanned-in page of music, pattern recognition). PostScript and BibTeX files are aviable via ftp from maggia.ethz.ch (129.132.17.1), login ftp, directory /pub/roth/omrbib. If you can't use ftp or can't uncompress *.Z files, drop me a mail. Comments, additions about new publications are welcome! _ Martin Roth Martin Roth ETHZ, ips, RZ F16 |\ /|_) Mail: roth@ips.id.ethz.ch Sandacker 14 ETHZ, ti, IFW B45.2 | \/ | \ Dipl. Eng. Comp. Sci. ETH CH-8154 Oberglatt g 01/256 55 68 (F-)emails welcome! Switzerland p 01/850 32 75 ------------------------------ Date: Wed, 9 Dec 1992 14:39:01 +0100 From: Alain Jacot-Descombes <jacot@cui.unige.ch> Subject: LaboImage 4.0: new X11 version [ A new version of LaboImage was just installed in the Vision List Archive SHAREWARE subdirectory. Thanks to the unige group! phil... ] LABOIMAGE Original notice March 8th, 1989: LaboImage 2.0 (SunView) August 24th, 1990: LaboImage 3.0 (SunView) March 19th, 1991: LaboImage 3.1 (SunView) December 1st, 1992: LaboImage 4.0 (X11 / OSF Motif) Computer Science Center, University of Geneva, Switzerland Thank you for your interest in LaboImage! GENERAL DESCRIPTION Labo Image is a window based software for image processing and analysis. It contains a comprehensive set of operators as well as general utilities. It is designed to be open-ended; new modules can easily be added. The software, written in C, is now based on X11 / OSF Motif. The current version has been developped and tested on a Sun SPARC station, with X11r4 and Motif 1.1. LaboImage has been extensively used by students as well as researchers from various domains: computer science (image analysis), medicine, biology, physics. It is distributed free of charge (source code). STATUS Version 4.0, 1st December 1992: - hosts: Sun SPARC station; - OS: 4.1.1; - window system: X11r4 / Motif 1.1; - language: C; - approx. code size: source 2.5MB (80'000 lines), executable 2.5MB; - documentation: interactive help (english) MEANS OF DISTRIBUTIONS LaboImage source code is available by anonymous ftp at: 1) ftp.ads.com, login name anonymous, in pub/VISION-LIST-ARCHIVE/SHAREWARE. 2) peipa.essex.ac.uk, login name anonymous, in ipa/proc-src. If you have no access to ftp, please contact the author. If you wish to be kept current with update, error reports, ..., please send us a mail with your full name, regular and electronic addresses. DISTRIBUTION POLICY In essence: - this is a non-profit software, but it is our property and the copyright notice must appear; - the reference to cite in case of published results obtained with Labo Image is: "A. Jacot-Descombes, M. Rupp, T. Pun: `LaboImage: A portable window-based environment for research in image processing and analysis', SPIE Symposium on Electronic Imaging Science and Technology, Image Processing: Implementation and Systems, San Jose, California, USA, Feb. 9-14, 1992. - no responsibility is assumed; - not to be used for profit making purposes; - bugs will usually be corrected since we use the software intensively ; - modifications should be communicated to us, with (normally) allowance for redistribution. PAYMENT Athough LaboImage has undergone many upgrades and suffered in the hands of many users, the current version is certainly not bug free. For the time being, we require NO prepayment, return postage or anything. We may however change this policy in the future, and ask for nominal fees to cover material expenditures. HOWEVER, if you are satisfied with the product, why not send us some "souvenir" (post card, drink, etc.)) from your country...??!! CAPABILITIES Labo Image is an interactive software, whose interface is menu, mouse and window based. Its main features are: - input-output: LaboImage format file, SUN raster file; postscript; - display: mono, RGB, dithering, color table editor; - preprocessing: filters (median, high pass, low pass: hamming, gauss, etc), background subtraction, histogram equalization; - processing: thresholding, Fourier transforms, edge extractions: various operators, ridge-riding, zero-crossing; segmentation into regions, binary and gray tone mathematical morphology; - measures: histograms, image statistics, power, region outlining, object counting; - auxiliary: conversions, arithmetic & logical operations, noise addition, image generation, magnification, convolution/correlation with masks, image; padding; - elementary interactive operations: region outlining, statistics and histogram computation, etc.; - special tools: - modify image at pixel level interactively, - one-dimensional gel analysis, - expert system for image segmentation (not implemented in LaboImage 4.0); - macros definitions, save and replay (not implemented in LaboImage 4.0); - on line documentation. IMAGE FORMATS Own format: descriptor file + data file (binary, byte, int, float, complex; mono or RGB). Supports also Sun raster format. Conversions to various other formats. Data structures: - iconic (pixel-based), with each image having its own parameter list; - vectors (histograms, look-up tables); MISCELLANEOUS REMARKS (answers to commonly asked questions) - FILE FORMAT: we decided to go for: 1) a machine independant format; 2) a simple, data (ie. signal) oriented format. At the beginning of the development (summer 1987), we were not aware of any image format used by the whole community. There seems now to be some progress on the matter (TIFF, etc.), but they are still not that widely used in the community. Also, due to development priorities we consider conversion routines a more secondary issue as long as our format is simple. In addition, the menu "ACQUISITION=>free byte format" is fairly versatile. Also, the SUN raster images can now be read into LaboImage and likewise images on system may be stored in SUN raster format. However.. we would welcome any software contribution! - 3D IMAGE PROCESSING: nothing special for such images. - ON LINE HELP: available. ACKNOWLEDGEMENTS More than 10 people have so far participated in this project, and their contribution is gratefully acknowledged. Staff: Pierre-Yves Burgi, Claudia Coiteux-Rosu, Ziping Hu, Alain Jacot- Descombes, Rene Lutz, Christian Pellegrini, Thierry Pun, Marianne Logean- Rupp, Krassimir Todorov. Students: Anne Bobillier, Alain Brunner, Markus Buchi, Christian Girard, Rene Perrier, Vrinda Shukla. Amongst them, A. Jacot-Descombes is responsible for general design issues, and is the keystone for implementation; R. Lutz is responsible for display manipulations (Color Table Editor,etc.); T. Pun is responsible for the original layout and general design issues; V. Shukla is responsible for the upgrade from LaboImage 2.0 to LaboImage 3.0; Marianne Logean-Rupp is responsible for the portability of LaboImage to X11 (LaboImage 4.0). We are particularly grateful to Drs. D. F. Hochstrasser and O. Ratib, Digital Imaging Unit, Computer Center, University Hospital of Geneva, for their extended support. LaboImage 4.0 could not have been without their help. CONTACTS Particular problems will be redirected to relevant persons, but we prefer that all communications be made to the same address: e-mail: "pun@uni2a.unige.ch" or pun@cgeuge51.bitnet (if this fails, "pun@cui.unige.ch"). tel.: +(4122) 705 76 27 (T. Pun), 705 76 30 (A. Jacot-Descombes). fax: +(4122) 320 29 27. postal address: Thierry Pun LaboImage Computing Science Center, University of Geneva 24, rue du General-Dufour CH - 1211 Geneva 4 SWITZERLAND ------------------------------ Date: Fri, 4 Dec 92 14:22:34 GMT From: M.Petrou@ee.surrey.ac.uk Subject: studentships UNIVERSITY OF SURREY Research Studentships - Image Processing/Computer Vision Three research studentships are available from 15 January 1993 to carry out PhD research in the Vision Speech and Signal Processing Research Group of the Department of Electronic and Electrical Engineering with extensive computing resources including SUN sparc stations as well as speciliased image processing facilities. The studentships are in the following areas: - 3D object recognition with emphasis on active vision - Image processing for remote sensing to study contextual multispectral image classification. - Automatic inspection of colour texture surfaces. Succesfull applicants will have a very good degree in Computer Science, Physics, Electrical Engineering or Mathematics with dedication to and apptitude for research. The value of the studentships will be set at or above the SERC rates depending on the circumstances. Further information and application forms may be obtained from Professor J Kittler on +44 483 509294, email: J.Kittler@ee.surrey.ac.uk, or at the Department of Electronic and Electrical Engineering, University of Surrey, Guildford, Surrey GU2 5XH United Kingdom. ------------------------------ Date: Tue, 15 Dec 92 16:43:25 GMT From: Andy Clark <andycl@syma.sussex.ac.uk> Subject: Doctoral Program in Philosophy-Psychology-Neuroscience First Announcement of a New Doctoral Programme in PHILOSOPHY-NEUROSCIENCE-PSYCHOLOGY at Washington University in St. Louis The Philosophy-Neuroscience-Psychology (PNP) program offers a unique opportunity to combine advanced philosophical studies with in-depth work in Neuroscience or Psychology. In addition to meeting the usual requirements for a Doctorate in Philosophy, students will spend one year working in Neuroscience or Psychology. The Neuroscience option will draw on the resources of the Washington University School of Medicine which is an internationally acknowledged center of excellence in neuroscientific research. The initiative will also employ several new PNP related Philosophy faculty and post-doctoral fellows. Students admitted to the PNP program will embark upon a five-year course of study designed to fulfill all the requirements for the Ph.D. in philosophy, including an academic year studying neuroscience at Washington University's School of Medicine or psychology in the Department of Psychology. Finally, each PNP student will write a dissertation jointly directed by a philosopher and a faculty member from either the medical school or the psychology department. THE FACULTY Roger F. Gibson, Ph.D., Missouri, Professor and Chair: Philosophy of Language, Epistemology, Quine Robert B. Barrett, Ph.D., Johns Hopkins, Professor: Pragmatism, Renaissance Science, Philosophy of Social Science, Analytic Philosophy. Andy Clark, Ph.D., Stirling, Visiting Professor (1993-6) and Acting Director of PNP: Philosophy of Cognitive Science, Philosophy of Mind, Philosophy of Language, Connectionism. J. Claude Evans, Ph.D., SUNY-Stony Brook, Associate Pro- fessor: Modern Philosophy, Contemporary Continental Philosophy, Phenomenology, Analytic Philosophy, Social and Political Theory. Marilyn A. Friedman, Ph.D., Western Ontario, Associate Professor: Ethics, Social Philosophy, Feminist Theory. William H. Gass, Ph.D., Cornell, Distinguished University Professor of the Humanities: Philosophy of Literature, Photography, Architecture. Lucian W. Krukowski, Ph.D., Washington University, Pro- fessor: 20th Century Aesthetics, Philosophy of Art, 18th and 19th Century Philosophy, Kant, Hegel, Schopenhauer. Josefa Toribio Mateas, Ph.D., Complutense University, Assistant Professor: Philosophy of Language, Philosophy of Mind. Larry May, Ph.D., New School for Social Research, Pro- fessor: Social and Political Philosophy, Philosophy of Law, Moral and Legal Responsibility. Stanley L. Paulson, Ph.D., Wisconsin, J.D., Harvard, Pro- fessor: Philosophy of Law. Mark Rollins, Ph.D., Columbia, Assistant Professor: Philosophy of Mind, Epistemology, Philosophy of Science, Neuroscience. Jerome P. Schiller, Ph.D., Harvard, Professor: Ancient Philosophy, Plato, Aristotle. Joyce Trebilcot, Ph.D., California at Santa Barbara, Associ- ate Professor: Feminist Philosophy. Joseph S. Ullian, Ph.D., Harvard, Professor: Logic, Philos- ophy of Mathematics, Philosophy of Language. Richard A. Watson, Ph.D., Iowa, Professor: Modern Philoso- phy, Descartes, Historical Sciences. Carl P. Wellman, Ph.D., Harvard, Hortense and Tobias Lewin Professor in the Humanities: Ethics, Philosophy of Law, Legal and Moral Rights. EMERITI Richard H. Popkin, Ph.D., Columbia: History of Ideas, Jewish Intellectual History. Alfred J. Stenner, Ph.D., Michigan State: Philosophy of Science, Epistemology, Philosophy of Language. FINANCIAL SUPPORT Students admitted to the Philosophy-Neuroscience-Psychology (PNP) program are eligible for five years of full financial support at competitive rates in the presence of satisfactory academic progress. APPLICATIONS Application for admission to the Graduate School should be made to: Chair, Graduate Admissions Department of Philosophy Washington University Campus Box 1073 One Brookings Drive St. Louis, MO 63130-4899 Washington University encourages and gives full consideration to all applicants for admission and financial aid without regard to race, color, national origin, handicap, sex, or religious creed. Services for students with hearing, visual, orthopedic, learning, or other disabilities are coordinated through the office of the Assistant Dean for Special Services. ------------------------------ Date: Tue, 15 Dec 1992 17:59:45 GMT From: sethi@usha.cs.wayne.edu (Ishwar K. Sethi) Organization: Wayne State University, Detroit Subject: special issue of the machine vision and applications Keywords: machine vision, neural networks CALL FOR PAPERS Special Issue of the Machine Vision and Applications on Neural Networks for Machine Vision The developments in the artificial neural network technology in recent years have provided machine vision researchers and developers with new tools and techniques to build machine vision algorithms and systems that exhibit human-like visual perception capabilities. The goal of the special issue is to capture these developments in neural network theory and its applications to machine vision and to provide the readers with an overview of the state-of-the-art. To meet this goal, papers are solicited for the special issue which is scheduled to appear in early 1995. Possible topics for the special issue, but not limited to, include the followings: * Learning and Self-Organization for Segmentation, Feature Extraction, and Recognition. * Motion Detection, Tracking, and Characterization using Neural Networks. * Hardware Implementations including Smart Vision Chips. * Neural Networks for Multisensory Processing. * Automated Visual Monitoring and Inspection using Neural Networks. * Reverse Engineering for Machine Vision using Neural Networks. Papers emphasizing technical details and theoretical background of machine vision systems having strong neural network components and currently in use are especially welcome. The papers should be prepared following the Machine Vision and Applications guidelines. All papers will be reviewed according to the guidelines of the Machine Vision and Applications . Please submit four copies of your manuscript to: Professor Ishwar K. Sethi Department of Computer Science Wayne State University Detroit, MI 48202 U.S.A. The deadline for submission is July 31, 1993. For enquiries, send E-mail to sethi@cs.wayne.edu or fax to 313-577-6868. ------------------------------ Date: Mon, 7 Dec 92 14:37:42 -0500 From: carlson@titanic.cs.umass.edu (Adam Carlson) Subject: AAAI '93 : Call for Papers Call for Papers AAAI-93 AAAI-93 is the eleventh national conference. The purpose of the conference is to promote research in artificial intelligence (AI) and scientific interchange among AI researchers and practitioners. Papers may represent significant contributions to all aspects of AI: a) the principles underlying cognition, perception, and action in humans and machines; b) the design, application, and evaluation of AI algorithms and intelligent systems; and c) the analysis of tasks and domains in which intelligent systems perform. In recognition of the wide range of methodologies and research activities legitimately associated with AI, we invite authors to submit papers describing both experimental and theoretical results from all stages of AI research. In particular, we encourage submission of papers that present promising research directions by describing innovative concepts, techniques, perspectives, or observations that are not yet supported by mature results. To be accepted, such submissions must include substantial analysis of the ideas, the technology needed to realize them, and their potential impact. In addition, because of the essential interdisciplinary nature of AI and the need to maintain effective communication across sub-specialties, we encourage authors to position and motivate their work in the larger context of the general AI community. While papers concerned with applications of AI are invited, those that describe working commercial systems should be submitted to the IAAI conference. Requirements for Submission Authors must submit six (6) complete printed copies of their papers to the AAAI office by January 13, 1993. Papers received after that date will be returned unopened. Notification of receipt will be mailed to the first author (or designated author) soon after receipt. All inquiries regarding lost papers must be made by January 27, 1993. Authors are also requested to send their paperUs title page in an electronic mail message to abstract@aaai.org by January 13, 1993. Notification of acceptance or rejection of submitted papers will be mailed to the first author (or designated author) by March 3, 1993. Camera-ready copy of accepted papers will be due about one month later. Paper Format for Review All six (6) copies of a submitted paper must be clearly legible. Neither computer files nor fax submissions are acceptable. Submissions must be printed on 8 1/2" x 11" or A4 paper using 12 point type (10 characters per inch for typewriters). Each page must have a maximum of 38 lines and an average of 75 characters per line (corresponding to the LaTeX article-style, 12 point). Double-sided printing is strongly encouraged. Length The body of submitted papers must be at most 11 pages, including figures, tables, and diagrams, but excluding the title page and bibliography. Papers exceeding the specified length and formatting requirements are subject to rejection without review. Title page Each copy of the paper must have a title page (separate from the body of the paper) containing the title of the paper, the names and addresses of all authors, a short (less than 200 word) abstract, and a descriptive content area or areas. The title page sent via electronic mail to the AAAI office must be in plain ASCII text with each section of the title page preceded by the name of that section as follows: title: <title> author: <name of first author> address: <address of first author> author: <name of last author> address: <address of last author> abstract: <abstract> content areas: <first area>, I, <last area> To facilitate the reviewing process, authors are requested to select appropriate content areas from the list below. Authors are invited to add additional content area descriptors to their title page as needed. Artificial Life, Automated Reasoning, Behavior-Based Control, Belief Revision, Case-Based Reasoning, Cognitive Modeling, Common Sense Reasoning, Communication and Cooperation, Constraint-Based Reasoning, Computer-Aided Education, Connectionist Models, Corpus-Based Language Analysis, Deduction, Diagnosis, Discourse Analysis, Distributed Problem Solving, Expert Systems, Geometrical Reasoning, Information Extraction, Knowledge Acquisition, Knowledge Representation, Knowledge Sharing Technology, Large Scale Knowledge Engineering, Learning/Adaptation, Machine Learning, Machine Translation, Mathematical Foundations, Multi-Agent Planning, Natural Language Processing, Neural Networks, Nonmonotonic Reasoning, Perception, Planning, Probabilistic Reasoning, Qualitative Reasoning, Reasoning about Action, Reasoning about Physical Systems, Reactivity, Robot Navigation, Robotics, Rule- Based Reasoning, Scheduling, Search, Sensor Interpretation, Sensory Fusion/Fission, Simulation, Situated Cognition, Spatial Reasoning, Speech Recognition, System Architectures, Temporal Reasoning, Terminological Reasoning, Theorem Proving, Truth Maintenance, User Interfaces, Virtual Reality, Vision, 3- D Model Acquisition. Submissions to Multiple Conferences Papers that are being submitted to other conferences, whether verbatim or in essence, must state this fact on the title page. If a paper appears at another conference (with the exception of specialized workshops), it must be withdrawn from AAAI-93. Papers that violate these requirements are subject to rejection without review. Review Criteria Each paper will be carefully reviewed by experts specializing in the content areas on the paperUs title page. Questions that will appear on the review form have been reproduced below. Authors are advised to bear these questions in mind while writing their papers: Significance How important is the work reported? Does it attack an important/difficult problem or a peripheral/simple one? Does the approach offered advance the state of the art? Originality Has this or similar work been previously reported? Are the problems and approaches completely new? Is this a novel combination of familiar techniques? Does the paper point out differences from related research? Is it re-inventing the wheel using new terminology? Quality Is the paper technically sound? Does it carefully evaluate the strengths and limitations of its contribution? How are its claims backed up? Clarity Is the paper clearly written? Does it motivate the research? Does it describe the inputs, outputs and basic algorithms employed? Does the paper describe previous work? Are the results described and evaluated? Is the paper organized in a logical fashion? Publication Accepted papers will be allocated six (6) pages in the conference proceedings. Up to two (2) additional pages may be used at a cost to the authors of $250 per page. Papers exceeding eight (8) pages and those violating the instructions to authors will not be included in the proceedings. Copyright Authors will be required to transfer copyright of their paper to AAAI. Please send papers and conference registration inquiries to: AAAI-93 American Association for Artificial Intelligence 445 Burgess Drive Menlo Park, CA 94025-3496 Registration and call clarification inquiries (ONLY) may be sent to the CSNET address: NCAI@aaai.org. Please send program suggestions and inquiries to: Richard Fikes Knowledge Systems Laboratory Stanford University 701 Welch Road, Building C Palo Alto, CA 94304 fikes@ksl.stanford.edu Wendy Lehnert Department of Computer Science University of Massachusetts Amherst, MA 01003 lehnert@cs.umass.edu ------------------------------ Date: Thu, 10 Dec 92 16:51:41 -0500 From: "Baba Vemuri" <vemuri@scuba.cis.ufl.edu> Status: CFP: Geometric Methods in Computer Vision CALL FOR PAPERS Geometric Methods in Computer Vision (Part of SPIE's Annual International Symposium on Optoelectronic Applied Science and Engineering; 12-13th July 1993; San Diego, California, San Diego Convention Center, Marriott Hotel and Marina) Conference Chair: Baba C. Vemuri Dept. of Computer & Information Sciences, CSE326 University of Florida, Gainesville, FL. 32611 Co-chairs: Ruud M. Bolle, IBM T. J. Watson Research Center, Yorktown Heights, NY. Demetri Terzopoulos, Department of Computer Science, Univ. of Toronto, Canada. Richard Szeliski, Cambridge Research Labs, DEC, Cambridge, MA. Gabriel Taubin, IBM T. J. Watson Research Center, Yorktown Heights, NY. Alan Yuille, Division of Applied Sciences, Harvard University, MA. Ramesh C. Jain, Dept. of EECS, Univ. of Michigan, Ann Arbor, MI. Key Note Address: Professor Dr. Jan Koenderink Physics Lab, Department of Medical and Physiological Physics University of Utrecht, Netherlands. The theme of this conference is application of geometric methods in low-level vision tasks, specifically for shape and motion estimation. Over the past few years, there has been increased interest in the use of differential geometry, computational physics and probability theory for various vision tasks. Papers describing novel contributions in all aspects of geometric and probabilistic methods in vision are solicited, with particular emphasis on: Differential Geometric Methods for Shape Representation. Energy-based Methods for Shape Estimation. Probabilistic Techniques for Shape Estimation and Representation. Geometry and Shape Recognition. New Deadlines Abstract Due Date: DECEMBER 28, 1992 Manuscript Due Date: April 19, 1993 (Proceedings will be made available at the conference) Please FAX or airmail FOUR copies, or email ONE copy of your abstract by 14 DECEMBER 1992 to: SPIE, San Diego '93 P.O. Box 10, Bellingham, WA 98227-0010 Shipping Address: 1000 20th Street, Bellingham, WA 98225 Telephone: 206/676-3290 FAX: 206/647-1445 email: abstracts@mom.spie.org (ASCII Files only) CompuServe 71630,2177 Your submission should include the title of your abstract, the authors' names, affiliations, mailing addresses, phone/FAX numbers, and email addresses, as well as the abstract text of approximately 500 words. Please be sure to indicate that your abstract is intended for the conference on Geometric Methods in Computer Vision II (Vemuri). Applicants will be notified of acceptance by March 1993. A manuscript due date of 19 April 1993 must be strictly observed since the Proceedings of this conference will be published before the meeting and available on site. Note: Late abstract submissions may be considered, subject to program time availability and chairs approval. ------------------------------ From: Mark Evans <mre1@it-research-institute.brighton.ac.uk> Date: Tue, 8 Dec 92 18:08:00 GMT Subject: Sun Pix I have summarised some reponses I got about Sun's video pix frame grabber. It might be of interest to others. Regards, Mark # Mark Evans mre1@itri.bton.ac.uk # # itri!mre1 # # ITRI, # # University of Brighton, # # Lewes Road, # # BRIGHTON, # # E. Sussex, # # BN2 4AT. # # Tel: +44 273 642904/642900 # # Fax: +44 273 606653 # >Does anyone have any experience of using the VideoPix card >by Sun ? It allows you to capture images and display them >on a sparc workstation. Does anyone have a recommendation >for a frame grabber for a sparc costing 500-700 pounds ? Thank you for everyone that supplied me with information. Special thanks to MS and EM of Sun Microsystems (both worked on the videopix card project) for all the their help. *** Users Comments *** 1. I have used the videopix here in the USA. It seems to work OK for me. I don't know how high a video quality that you need but the videopix only has 7-bit analogue to digital converters. I don't know of anything else in the same price range but I haven't looked for about 1.5 years. 2. We have three or four VideoPix boards and are very happy with them. They're not full-motion though, so if this is a requirement for you then the VideoPix may not be what you want. The boards can capture and display about 15fps of greyscale video in a small window. As you increase the size of the window (and hence the amount of data which needs to be blitted through the window system) and add color, the capture and display rate drops and eventually bottoms out at about 5fps for a fairly large color window. The board comes with a nice software library and a GUI interface, and seems to be a well thought-out product. We've had no complaints at all. 3. I've used the Sun VideoPix card. When it comes to grabbing single frames (motionless) it's OK. I use the PAL-format, which gives about 720x575 pixels. NTSC gives, I think, 640x480. Also, it stores 7 bits of luminosity per pixel, and 2*7 bits of chrominance per every four pixels. So, the color-information appears a bit slower than the intensity. Maybe this is only natural. The eye might be better at intensity differences than those of color. To grab a movie in realtime is harder. I've managed to grab about 6 frames/s, on a Sparc 2, each frame having a resolution of 320x240 full color. Full frame-rate would be 25-30 frames/s. 4. I have messed around with the videopix card quite a bit, and it seems to be a viable tools for conferencing, image-oriented mail and multimedia, etc, but does not produce the quality required for high-end image processing applications. 5. We have one of these boards here at ANU, but we just got the thing so we don't have much experience with it so far. It can display about a frame a second from live video or TV in color, but the quality isn't as good as I expected. That may be a result of the poor quality signal from the TV though. It can do a few frames a second in black and white. The frame grabs work pretty good, but it is hard to get the exact frame that you want. *** Technical Specification *** 1. Colour (8 and 24 bit) Yes. 2. Greyscale (256 levels) Yes. 3. Monochrome Yes. 1bit per pixel file saves are available. All functions work on 1bit frame buffers, also. 4. A resolution of 512x512 or better Square pixel PAL resolution is what you get from the VFCtool software, but we also have an API that lets you get the full non-square data. So you can customize your software to control VideoPix directly. The API isn't a specific tool per say, but a list of defined driver calls. 5. Video input 2 Composite (NTSC or PAL), 1 S-Video (NTSC or PAL) all software selectable. 6. Continuous Frame Gabbing - (what is the max frames grabbed per sec ?) Ah. This depends on which mode (B&W or Colour) and what display resolution you selected from the software. Basically it's: mode resolution (displayed) FPS Colour Full (640x480 NTSC) 1 Colour Half (320x240 NTSC) ~3.5 Colour Quarter (160x120 NTSC) ~5 B&W Full (640x480 NTSC) ~3.5 B&W Half (320x240 NTSC) ~6.5 B&W Quarter (160x120 NTSC) ~8.5 The fastest library routine that is supplied might be able to grab 15 fields per second, NTSC, in raw YUV format. *** Technical Explanation *** The ADC's are a full 8 bits, But the SAA9051 Multi-Standard Decoder operates only on 7 bits. The output of the decoder is 4:1:1 digital YUV data that is stored in the boards FRAM. There is a full frame of FRAM on the board for either NTSC or PAL. Basicaly the board looks like this: input conn -> SWITCH-AGC-FILTER-ADC -> SAA9051 decoder-> FRAM ->SBUS input conn -| | | input conn -| --------I2C UART ----- What happens along this decode path is this: 1. The video source is supplied via the input connectors. Which input is selected via the software. Commands are send through I2C bus to tell the decoder which input has been requested. 2. Now the video has been selected, the ADC now gain adjusts the video levels and low pass filters the signal to trap out un-wanted noise above 6.5Mhz. Then the video is buffered and sent into the ADC. The ADC digitizes the CVBS signal with 8 bit resolution. The data is then sent to the decoder. 3. Now the data is taken into the SAA9051 decoder. Although the part has an 8bit hardware interface to the input ADC's, the internal resolution that the chip operates at is only 7bits in the (y) luminance path. The color information (c) is decoded and sub-sampled and then outputed with the (y) information to produces a 4:1:1 digital YUV output data stream. 4. The information is now stored in the on-board 1 Meg FRAM (Field RAM) buffer at video speed. FRAM is a memory specially designed for use in video frame store applications. It was first used in televisions that had Picture-In-Picture (PIP) processors. It now can be found in most high end VCR's being used for time base correction applications or in digitizers like VideoPix. FRAM looks like a big FIFO, and is in fact read like a FIFO. But it's storage cell can hold an entire field of PAL (or NTSC) video. Now that this information is held in the FRAM, The application can now access it from the SBUS. This is where the speed bottleneck is. 5. SBUS. Once the data is requested, it is sent in it's raw YUV data form into the host memory via VideoPix's slave interface. The data transfer speeds are fast, but not fast enough for real-time transfers (30FPS). This amount of data is in the order of ~20 MBytes/sec which requires an expensive (at the time) DMA interface. This also swamps SBUS disallowing of transactions to occur from other SBUS cards. Since SBUS is considerd a general purpose I/O bus and not a high speed video bus, it would be wrong for any SBUS card to take more than 50% of the bandwith at anytime. The net results is that we have an upper limit as to how fast we can transfer the data from the card to the host ram. 6. Once the data is in the host, the software does several things to it. The data arrives as 4:1:1 coded YUV non-square (4:3 aspect) pixels. In order to display this on the console, the data is transcoded to RGB and dithered if the framebuffer is only 8bits. It is then sub-sampled to render a square image. This basicaly means dropping every fith pixel. 7. The data is now bit-blited to the display for you to enjoy!. *** My thoughts *** I will be buying one. If your main frame grabber specification is real time frame grabbing you will have to purchase a different, more expensive frame grabber. For the price it seems good value for money. I have two sample jpeg images (90%) grabbed from TV using the videopix card if anyone is interested. Thank you again for everyone that sent info to me. Regards, Mark ------------------------------ Date: Wed, 9 Dec 92 15:28:07 EST From: bedard@robocop.NYU.EDU (Patricia Bedard) Subject: References on automatic face recognition Following my previous request for references on automatic face recognition, many people expressed an interest in the compilation, so I thought it might be useful to post it to the vision list. Here is the list of references that I have compiled. If you notice that some references that you know about are missing, please let me know. Cheers, Patricia Patricia J. Bedard (bedard@robocop.nyu.edu) Courant Institute of Mathematical Sciences New York University 251 Mercer St. New York, NY, 10012 U.S.A. *************** survey (with extensive bibliography): ==================================== Ashok Samal and Prasana A. Iyengar: "Automatic Recognition and Analysis of Human Faces and facial Expressions: A Survey" Pattern Recognition _25(1)_, 65--77, 1992. references: ========== Andrew C. Aitchison and Ian Craw. "Synthetic Images Of Faces - An Approach to Model-Based face recognition" in "BMVC91, Proceedings of the British Machine Vision Conference", 1991, (Peter Mowforth, editor) Springer-Verlag. Shigeru Akamatsu and Tsutomu Sasaki and Hideo Fukamachi and Nobuhiko Masui and Yasuhito Suenaga. "An Accurate and Robust Face Identification Scheme" in ICPR'92, 1992. Shigeru Akamatsu and Tsutomu Sasaki and Hideo Fukamachi and Yasuhito Suenaga. "A robust face identification scheme --- KL expansion of an invariant feature space" in Intelligent Robots and Computer Vision X: Algorithms and Techniques", SPIE #1607, 1991. pp. 71-84. Robert Baron, Mechanisms of human facial recognition International Journal of Man-Machine Studies (1981) 15, 137-178 Alan Bennett and Ian Craw. "Finding Image Features Using Deformable Templates And Detailed Prior Statistical Knowledge" in "BMVC91, Proceedings of the British Machine Vision Conference", 1991, (Peter Mowforth, editor), Springer-Verlag. Brunelli, R. and Poggio, T. "Face Recognition through Geometrical Features" in "Proc. 2nd European Conf. on Computer Vision, Lecture Notes in Computer Science #588" (G. Sandini, editor), Springer Verlag, 1992. pp. 792-800. R. Brunelli and T. Poggio, ``HyperBF networks for gender classification,'' Proc. DARPA IU Workshop, 1992, 311--314. Buhmann, Joachim and Lades, Martin and von der Marlsburg, Christoph. "Size and Distortion Invariant Object Recognition by Hierarchical Graph Matching", IJCNN, 1990, V.2. pp. 411-416. Burt, Peter J. "Smart Sensing within a Pyramid Vision Machine" in "Proceedings of the {IEEE}", 1988, vol 76, no 8, pp. 1006-1015. Craw, Ian and Cameron, Peter. "Face Recognition by Computer" in "Proc. British Machine Vision Conference", 1992, (David Hogg and Roger Boyle, editors), Springer Verlag. Ian Craw and Peter Cameron. "Parameterising Images for Recognition and Reconstruction" in "BMVC91, Proceedings of the British Machine Vision Conference", 1991,(Peter Mowforth, editor), Springer-Verlag. I. Craw, H. Ellis and J.R. Lishman, Automatic extraction of face-features Pattern Recognition Letters, 5, 1987, 183-187 Ian Craw and David Tock and Alan Bennett. "Finding Face Features" in ECCV'92, Lecture Notes in Computer Science #588, Springer Verlag. pp. S. Edelman and D. Reisfeld and Y. Yeshurun. "Learning to recognize faces from examples" in "Proc. 2nd European Conf. on Computer Vision, Lecture Notes in Computer Science #588", (G. Sandini, editor), Springer Verlag, 1992. pp. 787-791. Fleming, Michael K. and Cottrell, Garrison W. ""Categorization of Faces Using Unsupervised Feature Extraction" in IJCNN, 1990, Vol 2, pp. 65-70. R Gallery and T I P Trew. "An Architecture for Face Classification" in "Colloquium: Machine Storage and Recognition of Faces. IEE Digest 017, 1992. Goldstein, A. Jay and Harmon, Leon D. and Lesk, Ann B. "Identification of Human Faces" in "Proceedings of the {IEEE}", 1971, Vol 59, No 5, pp. 748-760. G.G. Gordon, ``Face recognition based on depth and curvature features,'' Proc. IEEE CVPR, 1992, 808--810. Govindaraju, Venu and Srihari, Sargur. N. and Sher, David B. "A Computational Model for Face Location" in ICCV'90, pp. 718-721. Harmon, L. D. and Khan, M. K. and Lasch, Richard and Ramig, P. F. "Machine Identification of Human Faces" in "Pattern Recognition", 1981, Vol 13, No. 2, pp. 97-110. Hong, Zi-Quan. "Algebraic feature extraction of image for recognition" in "Pattern Recognition", Vol 24, March 1991, pp. 211-219. Jia, Xiaoguang and Nixon, Mark S. "On developing an extended feature set for automatic face recognition" in "Colloquium: Machine Storage and Recognition of Faces, IEE Digest 017", 1992. Kanade, Takeo. "Computer Recognition of Human Faces" in volume 47 of "Interdisciplinary Systems Research", Birkhauser, Basel, Stuttgart, 1977. Kaya, Y. and Kobayashi, K. ""A Basic Study on Human Face Recognition" in "Frontiers of Pattern Recognition", 1972, pp. 265-289. Kirby, M. and Sirovich, L. "Application of the Karhunen-Lo\`{e}ve Procedure for the Characterization of Human Faces" in PAMI-12, 1980, V.12, no 1, pp. 103-108. J.C. Lee and E. Milios, ``Matching range images of human faces,'' Proc. ICCV, 1990, 722--726. B.S. Manjunath, R. Chellappa, and C. von der Malsburg, ``A feature based approach to face recognition,'' Proc. IEEE CVPR, 1992, 373--378. Nakamura, Osamu and Mathur, Shailendra and Minami, Toshi. "Identification of Human Faces Based on Isodensity Maps" in "Pattern Recognition", 1991, Vol 24, no 3, pp. 263-272. A. Pentland and S. Sclaroff, ``Closed-form solutions for physically based shape modeling and recognition,'' IEEE PAMI, Vol.\ 13, 1991, 715--729. C.S. Ramsey and K. Sutherland and D. Renshaw and P.B. Denyer. "A Comparison of Vector Quantisation Codebook Generation Algorithms Applied to Automatic Face Recognition" in "Proceedings of BMVC-92", (David Hogg, editor), Springer-Verlag, 1992. Anne-Caroline Schreiber et. al., Facenet: A Connectionist Model of Face Identification in Context European Journal of Cognitive Psychology, 1991, 3 (1), 177-198 Ken Sutherland, D. Rensham, and P.B. Denyer. "A novel automatic face recognition algorithm employing vector quantization" in "Colloquium: Machine Storage and Recognition of Faces, IEE Digest 017", 1992. D. Terzopoulos and K. Waters, ``Analysis of facial images using physical and anatomical models,'' Proc. ICCV, 1990, 727--732. David Tock and Ian Craw and Roly Lishman. "A Knowledge Based System for Measuring Faces" in "BMVC90, Proceedings of the British Machine Vision Conference", 1990. pp. 401-407. M. Turk, "Interactive-Time Vision: Face Recognition as a Visual Behavior", Ph.D. Thesis, MIT Media Lab, August 1991. M. Turk and A. Pentland, ``Eigenfaces for recognition,'' {\sl Journal of Cognitive Neuroscience}, Vol. 3, No. 1, pp. 71-86, 1991. M. Turk and A. Pentland, ``Face Recognition Using Eigenfaces,'' {\sl Proc. CVPR}, Maui, Hawaii, pp. 586-591, 1991. M. Turk and A. Pentland, ``Recognition in face space,'' {\sl Intelligent Robots and Computer Vision IX}, SPIE Vol. 1381, Boston, MA, 1990. (Reprinted in H. Nasr (ed.), {\sl Selected Papers on Automatic Object Recognition}, SPIE Optical Engineering Press, Washington, 1991.) Wong, K. H. and Law, Hudson H. M. and Tsang, P. W. M. "A system for recognising human faces" in "Proceedings of the International Conference on Acoustics, Speech and Signal Processing", 1989, pp.1638-1642. Y. Yacoob and L. Davis, Qualitative Labeling of Human Face Features from Range Data, Technical Report CS-TR-2971, Center for Automation Research, University of Maryland, College Park, MD, Oct. 1992. A.L. Yuille, D.S. Cohen, and P.W. Hallinan, ``Feature extraction from faces using deformable templates,'' Proc. IEEE CVPR, 1989, 104--109. Alan Yuille, Deformable Templates for face recognition Journal of Cognitive Neuroscience, 1991, Vol 3, No. 1, p59-70 papers soon to be released: ========================== work by Martin Lades, C. von der Malsburg (et al.?) to appear in IEEE Trans. on Computers. report on face recognition prepared by Alex Pentland, Terry Sejnowski and others soon to be publicly available. ------------------------------ From: nde@scs.leeds.ac.uk Date: Fri, 11 Dec 92 12:57:10 GMT Subject: Snakes: summary of responses (long) Status: R The response to my request for references on snakes and active contour models was terrific: my thanks go to all who contributed information. I've collated the various contributions into the list below. Nick Efford School of Computer Studies Leeds University, Leeds, UK @inproceedings{amini88:iccv, author = "Amini, A. and Tehrani, S. and Weymouth, T", year = 1988, title = "Using dynamic programming for minimizing the energy of active contours in the presence of hard constraints", booktitle = "Proceedings of the Second International Conference on Computer Vision, Tampa, Florida", pages = "95--99"} @inproceedings{berger90:icpr, author = "Berger, M. O. and Mohr, R.", year = 1990, title = "Towards autonomy in active contour models", booktitle = "Proceedings of the Tenth International Conference on Pattern Recognition"} @article{brzak91:cvgip, author = "Brzakovic, D. and Liakopoulos, A. and Hong, L.", year = 1991, title = "Spline models for boundary detection/description: formulation and performance evaluation", journal = "CVGIP: Graphical Models and Image Processing", volume = 53, number = 4, pages = "392--401"} @incollection{calbom91, author = "Calbom, I. and Terzopoulos, D. and Harris, K. M.", year = 1991, title = "Reconstructing and visualizing models of neuronal dendrites", booktitle = "Scientific Visualization of Physical Phenomena", publisher = "Springer-Verlag", pages = "623--638"} @article{cohen91:cvgip, author = "Cohen, L. D.", year = 1991, title = "Note on active contour models and balloons", journal = "CVGIP: Image Understanding", volume = 53, number = 2, pages = "211-218"} @inproceedings{cohen90:iccv, author = "Cohen, L. and Cohen, I.", year = 1990, title = "A finite element method applied to new active contour models and {3D} reconstructions", booktitle = "Proceedings of the Third International Conference on Computer Vision, Osaka, Japan, December 1990", pages = "587--591"} @article{cohen92:cvgip, author = "Cohen, I. and Cohen, L. D. and Ayache, N.", year = 1992, title = "Using deformable templates to segment {3D} imags and infer differential structures", journal = "CVGIP: Image Understanding", volume = 56, number = 2, pages = "242--263"} @inproceedings{cohen92:cvpr, author = "Cohen, L. D. and Cohen, I.", year = 1992, title = "Deformable models for {3D} medical images using finite elements and balloons", booktitle = "IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Champaign, Illinois, June 1992"} @techreport{davatz92, author = "Davatzikos, C. A. and Prince, J. L.", year = 1992, title = "An active contour algorithm for thick curves", institution = "Johns Hopkins University", number = "JHU/ECE 92-07"} @inproceedings{davatz92:icassp, author = "Davatzikos, C. A. and Prince, J. L.", year = 1992, title = "Segmentation and mapping of highly-convoluted contours with applications to medical images", booktitle = "Proceedings of ICASSP '92, IEEE Conference on Acoustics, Speech and Signal Processing"} @unpublished{davatz93:cvpr, author = "Davatzikos, C. A. and Prince, J. L.", year = 1993, title = "Adaptive active contour algorithms for extracting and mapping thick curves", note = "Submitted to CVPR '93, IEEE Conference on Computer Vision and Pattern Recognition"} @article{kass88:ijcv, author = "Kass, M. and Witkin, A. and Terzopoulos, D.", year = 1988, title = "Snakes: active contour models", journal = "International Journal of Computer Vision", volume = 1, number = 4, pages = "321--331"} @article{leymarie92:pami, author = "Leymarie, F. and Levine, M. D.", year = 1992, title = "Simulating the grassfire transform using an active contour model", journal = "IEEE Transations on Pattern Analysis and Machine Intelligence", volume = 14, number = 1, pages = "56--75"} @unpublished{leymarie93:pami, author = "Leymarie, F. and Levine, M. D.", year = 1993, title = "Tracking deformable objects in the plane using an active contour model", note = "To appear in IEEE Transactions on Pattern Analysis and Machine Intelligence"} @inproceedings{menet90:darpa, author = "Menet, S. and Saint-Marc, P. and Medioni, G.", year = 1990, title = "B-snakes: implementation and application to stereo", booktitle = "Proceedings of the DARPA Image Understanding Workshop, Pittsburgh, Pennsylvania, September 1990"} @article{poggio85, author = "Poggio, T. and Torre, V. and Koch, C.", year = 1985, title = "Computational vision and regularization theory", journal = "Nature", volume = 317, pages = "314--319"} @inproceedings{richens92:ipa, author = "Richens, D. and Rougan, N. and Bloch, I. and Mousseaux, E.", year = 1992, title = "Segmentation by deformable contours of {MRI} sequence of left ventricle for quantitative myocardial analysis", booktitle = "IEE Proceedings of the Fourth International Conference on Image Processing and its Applications, Maastricht, April 1992", pages = "393--396"} @article{rougan91:spie, author = "Rougan, N. and Preteux, F.", year = 1991, title = "Deformable markers: mathematical morphology for active contour model control", journal = "Proceedings of the Society of Photo-Optical Instrumentation Engineers", volume = 1568, pages = "78--89"} @inproceedings{rougan92:embs, author = "Rougan, N. and Preteux, F.", year = 1992, title = "Oriented smoothness constraints for adaptive active contour models", booktitle = "Proceedings of the Fourteenth Conference of the IEEE Engineering in Medicine and Biology Society", pages = "1916--1917"} @article{samad91:spie, author = "Samadani, R.", year = 1991, title = "Adaptive snakes: control of damping and material parameters", journal = "Proceedings of the Society of Photo-Optical Instrumentation Engineers", volume = 1568} @article{sinha92:pami, author = "Sinha, S. S. and Schunk, B. G.", year = 1992, title = "A two-stage algorithm for discontinuity-preserving surface reconstruction", journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence", volume = "PAMI-14", number = 1, pages = "36--55"} @article{snyder91:pami, author = "Snyder, M. A.", year = 1991, title = "On the mathematical foundations of smoothness constraints for the determination of optical flow and for surface reconstruction", journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence", volume = "PAMI-13", number = 11, pages = "1105--1114"} @article{staib92:pami, author = "Staib, L. H. and Duncan, J. S.", year = 1992, title = "Boundary finding with parametrically deformable models", journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence", volume = "PAMI-14", number = 11, pages = "1061--1075"} @article{terzop86:pami, author = "Terzopoulos, D.", year = 1986, title = "Regularization of inverse visual problems involving discontinuities", journal = "IEEE Transactions on Pattern Analysis and Machine Intelligence", volume = "PAMI-8", number = 4, pages = "413--423"} @article{terzop87:cg, author = "Terzopoulos, D. and Platt, J. and Barr, A. and Fleischer, K.", year = 1987, title = "Elastically deformable models", journal = "Computer Graphics", volume = 21, number = 4, pages = "205--214"} @article{terzop88:cga, author = "Terzopoulos, D. and Witkin, A.", year = 1988, title = "Physically-based models with rigid and deformable components", journal = "IEEE Computer Graphics and Applications", month = "November", pages = "41--51"} @article{terzop88:ai, author = "Terzopoulos, D. and Witkin, A.", year = 1988, title = "Constraints on deformable models: recovering shape and non-rigid motion", journal = "Artificial Intelligence", volume = 36, pages = "91--123"} @article{waite90:bttj, author = "Waite, J. B. and Welsh, W. J.", year = 1990, title = "Head boundary location using snakes", journal = "British Telecom Technology Journal", volume = 8, number = 3, pages = "127--136"} @article{will92:cvgip, author = "Williams, D. J. and Shah, M.", year = 1992, title = "A fast algorithm for active contours and curvature information", journal = "CVGIP: Image Understanding", number = 55, volume = 1, pages = "14--26"} @article{yuille92:ijcv, author = "Yuille, A. L. and Hallinan, P. W. and Cohen, D. S.", year = 1992, title = "Feature extraction from faces using deformable templates", journal = "International Journal of Computer Vision", volume = 8, number = 2, pages = "99--111"} ------------------------------ End of VISION-LIST digest 11.43 ************************