HOME    »    PROGRAMS/ACTIVITIES    »    Annual Thematic Program
Fall 2000
IMA Workshop
Image Analysis and High Level Vision
November 13-17, 2000


with partial support by The Office of Naval Research

Organizers:

Peter Olver
School of Mathematics
University of Minnesota

olver@math.umn.edu

Allen Tannenbaum
Department of Computer and Electrical Engineering
University of Minnesota
tannenba@ee.umn.edu

Donald Geman
Department of Mathematics and Statistics
University of Massachusetts at Amherst

geman@math.umass.edu

Yali Amit
Department of Statistics
The University of Chicago
amit@galton.uchicago.edu

Steven Zucker
Computer Science and Electrical Engineering
Yale University
steven.zucker@yale.edu

 

 

This workshop will concentrate on mathematical and practical issues arising in the higher level processes in image analysis. These include object recognition, optical character and handwriting recognizers, printed-circuit board inspection systems, and quality control devices, motion detection, robotic control by visual feedback, theory of shape, reconstruction of objects from stereoscopic view and/or motion, and many others. Shape theory is of fundamental importance since it is the bottleneck between high and low level vision, and forms the bridge between the two workshops on vision. The recent geometric partial differential equation methods have been essential in throwing new light on this very difficult problem area. There are two classical approaches to approximating the shape of objects. The first is based on diffusion and often leads to the (Gaussian) smoothing of contour information. The resulting scale-space may often be viewed as generated by parabolic operators which progressively and globally smooth shapes. The second approach is based on morphological morphology operations that represent the interior of shapes as sets, e.g., a collection of disks. The resulting morphological space can be viewed as being defined via a hyperbolic operator whose weak or viscosity solutions progressively smooth shapes in a local manner. The geometric PDE approach based on abstract conservation principles, Hamilton-Jacobi theory, and curvature driven flows leads to a computational theory of shape that naturally characterizes its computational elements including protrusions, parts, bends, and seeds (which show where to place the components of a shape). Stochastic processes, including Markov random fields, have been used in a Bayesian framework to incorporate prior constraints on a smoothness and the regularities of discontinuities into algorithms for image restoration and reconstruction. Sequential decision theory has been used to develop algorithms for efficient identification of objects in a scene, including handwritten characters, roads in satellite imagery, and faces. Deformable templates have been used to automate the identification of structures, both normal and pathological, in medical imagery. Since human vision relies on a variety of symmetry transformations, including Euclidean, affine and projective invariance, the incorporation of group theory and invariants into the image processing equations has been of great importance in the design of algorithms, both continuous and numerical.

A primary goal of this workshop is to educate and interest mathematicians in the mathematical and scientific problems that arise in the study of computer and natural vision. There will be a mix of tutorials in natural and artificial vision and mathematical talks on the theoretical foundations of existing and proposed vision systems. An additional goal is to bring together researchers working in these areas to compare results and to collaborate on ways to integrate these approaches into a powerful overall mathematical approach to vision. Unlike numerical analysis, the computer vision community has yet to establish "benchmark" tests for comparison of the various visual processing systems that are available, making direct and rigorous comparisons difficult. In this workshop we propose to initiate the development of a set of benchmark visual images that can be used for overall comparison purposes.

WORKSHOP SCHEDULE

Monday Tuesday
MONDAY, NOVEMBER 13
All talks are in Lecture Hall EE/CS 3-180 unless otherwise noted.
8:30 am Coffee and Registration

Reception Room EE/CS 3-176

9:10 am Willard Miller, Fred Dulles, and Peter Olver Introduction
9:30 am Donald Geman
University of Massachusetts at Amherst

Coarse-to-Fine Object Detection

Talk   slides

10:30 am Break Reception Room EE/CS 3-176

11:00 am-
12:00 pm

Pietro Perona
Caltech
Unsupervised Learning of Models for Object Recognition
2:00-3:00 pm Alan L. Yuille
The Smith-Kettlewell Eye Research Institute

Order Parameters for Detecting Target Curves in Images: When Does High Level Knowledge Help?

Talk    pdf    postscript

4:00 pm IMA Tea
A variety of appetizers and beverages will be served.
IMA East, 400 Lind Hall
TUESDAY, NOVEMBER 14
All talks are in Lecture Hall EE/CS 3-180 unless otherwise noted.
9:15 am Coffee Reception Room EE/CS 3-176
9:30 am Steven Zucker
Yale University
How Folds Cut a Scene
10:30 am Break Reception Room EE/CS 3-176
11:00 am-
12:00 pm
Irving Biederman
University of Southern California
Neural and Psychophysical Aspects of Visual Shape Recognition
1:15 pm Tai Sing Lee
Carnegie Mellon University
The Influence of High Level Vision on Early Visual Processing in the Brain
2:00 pm Yali Amit
The University of Chicago

A Neural Architecture for Learning, Detecting and Recognizing Objects

Talk   pdf    postscript

3:00 pm Break Reception Room EE/CS 3-176
3:30 pm Panel Discussion:
Irving Biederman (University of Southern California), Donald Geman, (University of Massachusetts at Amherst), and Pietro Perona (Caltech)
TBA
WEDNESDAY, NOVEMBER 15
All talks are in Lecture Hall EE/CS 3-180 unless otherwise noted.
9:15 am Coffee Reception Room EE/CS 3-176
9:30 am Ian L. Dryden
University of Nottingham

Statistical Shape Analysis in High-Level Vision

Talk  pdf   postscript

10:30 am Break Reception Room EE/CS 3-176
11:00 am-
12:00 pm
Jayant M. Shah
Northeastern University

Local Symmetries and Segmentaton of Shapes

Talk  slides

2:00 pm Peter N. Belhumeur
Yale University
Shedding Light on Illumination
3:00 pm Break Reception Room EE/CS 3-176
3:30 pm David Mumford
Brown University
What is the Space of Shapes and What Can We Do With It?
4:15-5:00 pm Song-Chun Zhu
Ohio State University

Tackling Visual Complexity by Statistical Learning and Stochastic Computing

Talk    pdf

THURSDAY, NOVEMBER 16
All talks are in Lecture Hall EE/CS 3-180 unless otherwise noted.
9:15 am Coffee Reception Room EE/CS 3-176
9:30 am Davi Geiger
Courant Institute, NYU
Measuring the Convexity of Shapes
10:30 am Break Reception Room EE/CS 3-176
11:00 am-
12:00 pm
Laurent Younes
CNRS
Metrics, Shapes and Deformations
2:00 pm Benjamin B. Kimia
Brown University
Symmetry Maps and Transforms for Perceptual Organization and Object Recognition
3:00 pm Break Reception Room EE/CS 3-176
3:30-4:30 pm Ernst D. Dickmanns
Universität der Bundeswehr München

Expectation-based, Multi-focal, Saccadic (EMS-) Vision. (A System for Understanding Dynamic Scenes Observed from a Moving Platform)

Talk    pdf

6:00 pm Workshop Dinner Shuang Chen Restaurant
FRIDAY, NOVEMBER 17
All talks are in Lecture Hall EE/CS 3-180 unless otherwise noted.
9:15 am Coffee Reception Room EE/CS 3-176
9:30 am John Oliensis
NEC Research Institute Inc.
From Movies to Geometric 3D Models: the Structure-from-Motion Problem
10:30 am Break Reception Room EE/CS 3-176
11:00 am-
12:00 pm
Rama Chellappa
University of Maryland
Face Recognition and Verification in Still and Video Images
Contributed Talks
The afternoon talks are in Lind Hall 409 unless otherwise noted.
2:00 pm Xavier Pennec
INRIA Sophia - Project Epidaure

Probabilities and Statistics on Riemannian Manifolds: Basic Tools for Geometric Measurements

Talk   pdf

2:30 pm Mohamed Ben Hadj Rhouma
Georgia Institute of Technology
Image Segmentation Using Integrate-and-Fire Oscillators
3:00-3:30 pm Jason Miller
Truman State University
Relative Critical Sets and Ridges Sets of Functions
Monday Tuesday

LIST OF CONFIRMED PARTICIPANTS

as of 11/14/2000
Name Department Affiliation
Yali Amit Statistics The University of Chicago
Peter Belhumeur Electrical Engineering and Computer Science Yale University
Mohamed Ben Rhouma Center for Dynamical Systems and Nonlinear Studies Georgia Institute of Technology
Santiago Betelu   Institute for Mathematics and its Applications
Irving Biederman Neuroscience Prog. and Dept.'s of Psych. and CSci University of Southern California
Mireille Boutin Mathematics University of Minnesota
Michele Carriero Mathematics University of Lecce
Jamylle Carter   Institute for Mathematics and its Applications
Vicent Caselles Tecnologia Universitat Pompeu-Fabra
Rama Chellappa Center for Automation Research University of Maryland
Li-Tien Cheng   Institute for Mathematics and its Applications
Alessandro Chiuso Electronics and Informatics University of Padova
Fabio Cuzzolin   UCLA
Ernst Dickmanns Institut für Systemdynamik und Flugmechanik Universität der Bundeswehr München
Ian Dryden Mathematical Sciences University of Nottingham
Fred Dulles   Institute for Mathematics & its Applications
Selim Esedoglu   Institute for Mathematics and its Applications
Francois Fleuret Projet Imedia INRIA-Rocquencourt
Davi Geiger Computer Science and Neural Science Courant Institute, NYU
Donald Geman Mathematics and Statistics University of Massachusetts at Amherst
Jack Goldfeather Mathematics and Computer Science Carleton College
Fernando Carvalho Gomes SITE University of Ottawa
Robert Gulliver Mathematics University of Minnesota
Dirk Horstmann Mathematisches Institut Universitat zu Koeln
Dan Kersten Psychology University of Minnesota
Benjamin B. Kimia Engineering Brown University
Samuel Krempp   Un. of Massachussetts
Christopher Lang   Indiana University Southeast
Antonio Leaci Mathematics University of Lecce
Tai-Sing Lee Comp. Sci & Cnbc Carnegie Mellon University
Andrey Litvin Electrical and Computer Engineering Boston University
Darek Madej Advanced Development Symbol Technologies
Andres Sole Martinez   Universitat Pompeu Fabra
Massimo Mascaro Statistics University of Chicago
Donald E. McClure Applied Mathematics Brown University
Peter McCoy Mathematics U.S. Naval Academy
Jason Miller Mathematics & Computer Science Truman State University
Ronald Miller Ford Research Laboratory Ford
Willard Miller   Institute for Mathematics & its Applications
David Mumford Applied Mathematics Brown University
John Oliensis   NEC Research Institute Inc.
Peter Olver Mathematics University of Minnesota
Victor Patrangenaru Mathematics and Statistics Georgia State University
Xavier Pennec Unite de Recherche INRIA Epidaure
Pietro Perona Electrical Engineering Caltech
Mary Pugh Mathematics University of Pennsylvania
Anand Rangarajan Diagnostic Radiology & Elec. Eng. Yale University School of Medicine
Christopher S. Raphael Mathematics & Statistics University of Massachusetts, Amherst
Erik Schlicht Psychology University of Minnesota
Kevin Schweiker Engineering Freestyle Technologies, Inc.
Jayant M. Shah Mathematics Northeastern University
Shuli Cohen Shwartz U.C.G. Technologies Ltd. The Technion Enterpreneurial Incubator Co.
Stefano Soatto Electrical Engineering Washington University
Allen Tannenbaum Electrical & Computer Engineering Georgia Institute of Technology
Franco Tomarelli Matematica Politecnico di Milano
Laurent Younes Le Centre de Mathématiques et de Leurs App. CNRS
Alan Yuille   The Smith-Kettlewell Eye Research Institute
Song Chun Zhu Computer & Information Sciences Ohio State University
Steven Zucker Computer Science and Electrical Engineering Yale University


Talk Abstracts

2000-2001 Program: Mathematics in Multimedia

Back to top of page

Connect With Us:
Go