A new approach to image feature detection with applications

B. S. Manjunath*, C. Shekhar ** and R. Chellappa**

* Department of Electrical and Computer Engineering
University of California, Santa Barbara, CA 93106-9560
manj [at] ece.ucsb.edu

** Center for Automation Research
University of Maryland, College Park, MD 20742
chella [at] engr.umd.edu

Abstract

Image feature detection is a fundamental issue in many intermediate level vision problems such as stereo, motion correspondence, image registration, and object recognition. In this paper we present an approach to feature detection based on a scale-interaction model. This feature detector is responsive to short lines, line endings, corners and other such sharp changes in curvature. We provide extensive experimental results to demonstrate its potential applications to several image analysis problems.
[PDF] [BibTex]
B. S. Manjunath, C. Shekhar and R. Chellappa,
Pattern Recognition, vol. 29, no. 4, pp. 627-640, Apr. 1996.
Node ID: 250 , DB ID: 44 , VRLID: 33 , Lab: VRL , Target: Journal
Subject: [Image Texture] « Look up more