Thursday, May 7

Invariant Curvature Flows in Computer Vision and Image Processing

9:00 AM-10:00 AM
Chair: John A. Burns, Virginia Polytechnic Institute and State University
Room: Salon D

In this presentation, the speaker will discuss the use of geometric curvature-based flows in image processing and computer vision. Certain of these flows give rise to (nonlinear) geometric diffusion equations that are invariant with respect to a given transformation group action. The smoothing properties of such flows will be discussed. He will also present some results from the theory of curve and surface evolution, and show how these may be used for a number of areas in image processing, such as image enhancement, optical flow, image segmentation, shape theory, and invariant scale-spaces. The speaker will also outline a paradigm for object recognition based on these ideas.

These techniques will be applied to problems in visual tracking.

Allen Tannenbaum
Department of Electrical Engineering, University of Minnesota, Minneapolis

CT98 Homepage | Program Updates| Registration | Hotel Information | Transportation | Program-at-a-Glance | Speaker Index

MMD, 11/25/97