Accession Number : ADA190384

Title :   Energy Functions for Early Vision and Analog Networks.

Descriptive Note : Memorandum rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Yuille, Alan

PDF Url : ADA190384

Report Date : Nov 1987

Pagination or Media Count : 54

Abstract : Abstract. This paper describes attempts to model the modules of early vision in terms of minimizing energy functions, in particular energy functions allowing discontinuities in the solution. It examines the success of using Hopfield-style analog networks for solving such problems. Finally it discusses the limitations of the energy function approach. Keywords: Surface interpolation; Motion smoothing; Segmentation.

Descriptors :   *VISION, *IMAGE PROCESSING, *ARTIFICIAL INTELLIGENCE, ANALOG SYSTEMS, ENERGY, INTERPOLATION, NETWORKS, SEGMENTED, SURFACES

Subject Categories : Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE