Accession Number : ADA183807

Title :   Probabilistic Solution of Ill-Posed Problems in Computational Vision.

Descriptive Note : Memorandum rept.,

Corporate Author : MASSACHUSETTS INST OF TECH CAMBRIDGE ARTIFICIAL INTELLIGENCE LAB

Personal Author(s) : Marroquin,J ; Mitter,S ; Poggio,Tomaso

PDF Url : ADA183807

Report Date : Mar 1987

Pagination or Media Count : 41

Abstract : Computational vision is a set of inverse problems. The authors review standard regularization theory, discuss its limitations, and present new stochastic (in particular, Bayesian) methods for their solution. They derive efficient algorithms and describe parallel implementations on digital parallel SIMD architectures, as well as a new class of parallel hybrid computers. Keywords: Stochastic methods; Artificial intelligence; Problem solving; Probablistic approach. (Author)

Descriptors :   *ARTIFICIAL INTELLIGENCE, *VISION, *COMPUTER APPLICATIONS, ALGORITHMS, EFFICIENCY, PROBABILITY, SOLUTIONS(GENERAL), INVERSION, COMPUTATIONS, HYBRID COMPUTERS, PARALLEL ORIENTATION, PROBLEM SOLVING, STOCHASTIC PROCESSES

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE