Accession Number : ADA316134

Title :   Logical/Linear Operators in Early Vision.

Descriptive Note : Annual progress rept. 15 Jun 93-14 Jun 96,

Corporate Author : MCGILL UNIV MONTREAL (QUEBEC)

Personal Author(s) : Zucker, Steven W.

PDF Url : ADA316134

Report Date : 14 JUN 1996

Pagination or Media Count : 23

Abstract : We propose a research program to investigate new techniques for computing image descriptions in early vision. The program will incorporate computational, physiological and psychophysical aspects. Research will be focused on the certain non-linearities that we have discovered can play an important role in improving the robustness of edge, line, and curve detection. These non-linearities are totally different from those previously studied in early vision. We embody them in what we call logical/linear operators, because these operators exhibit both logical (i.e., they form an appropriate Boolean algebra) and linear properties. We submit that these operators can lead to both more robust computer vision, and to new insights into biological vision.

Descriptors :   *IMAGE PROCESSING, *COMPUTER VISION, ALGORITHMS, SOFTWARE ENGINEERING, TARGET DISCRIMINATION, FLOW FIELDS, NONLINEAR SYSTEMS, IMAGE INTENSIFICATION, COMPUTER GRAPHICS, PATTERN RECOGNITION, SYSTEMS ANALYSIS, VISUAL PERCEPTION, BOOLEAN ALGEBRA, PSYCHOPHYSIOLOGY.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE