A Robust method for detecting image features with applications to face recognition and motion correspondence

B. S. Manjunath*, Chandra Shekhar**, R. Chellappa*** and C. von der Malsburg****

* Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA 93106 USA

** Electrical Engineering-Systems
University of Southern California
Los Angeles, CA 90089-2564

*** Department of Electrical and Engineering
University of Maryland
College Park, MD 20742

**** Ruhr-Universitat Bochum
Institut fur Neuroinformatik
Federal Republic of Germany

Abstract

Feature detection is a fundamental issue in many intermediate level vision problems such as stereo, motion correspondence, image registration, etc. In this paper a new approach to feature detection is presented. It is based on a scale-interaction model of the end- inhibition property exhibited by certain cells in the visual cortex of mammals. These feature detector cells are responsive to short lines, line endings, corners and other such sharp changes in curvature. In addition, this method also provides a compact representation of feature information which is useful in shape recognition problems. Application to face recognition and motion correspondence are illustrated.
[PDF] [BibTex]
B. S. Manjunath, Chandra Shekhar, R. Chellappa and C. von der Malsburg,
11th IAPR International Conference on Pattern Recognition, pp. 208-212, The Hague, Netherlands, Aug. 1992.
Node ID: 212 , DB ID: 6 , VRLID: 12 , Lab: VRL , Target: Proceedings
Subject: [Managing Multimedia Databases] « Look up more