Accession Number : ADA299588

Title :   Automated Acquisition of Object Recognition Strategies for Image Exploitation.

Descriptive Note : Final technical rept. Jul 91-Aug 94,

Corporate Author : MASSACHUSETTS UNIV AMHERST DEPT OF COMPUTER AND INFORMATION SCIENCE

Personal Author(s) : Draper, Bruce A. ; Hanson, Allen R. ; Riseman, Edward M.

PDF Url : ADA299588

Report Date : AUG 1995

Pagination or Media Count : 63

Abstract : This effort attempts to solve a crucial problem of knowledge-based scene interpretation by building proper, more efficient, recognition strategies. The proposed system will automatically learn object recognition strategies with the goal of learning how to recognize objects from a combination of training images and a library of visual sources. This project will incorporate two types of learning techniques, Hypothesis Generation Learning, and Hypothesis Verification. Recognition graphs will represent three control strategies: an exhaustive exploration algorithm, a DNF generalization algorithm, and a graph optimization algorithm.

Descriptors :   *IMAGE PROCESSING, *LEARNING MACHINES, *PATTERN RECOGNITION, *KNOWLEDGE BASED SYSTEMS, MATHEMATICAL MODELS, ALGORITHMS, SCENARIOS, OPTIMIZATION, AUTOMATION, DATA MANAGEMENT, SKILLS, STRATEGIC ANALYSIS, VERIFICATION, TARGET RECOGNITION, CONCURRENT ENGINEERING, IDENTIFICATION, RELIABILITY, DECISION THEORY, DATA ACQUISITION, COMPUTER VISION, HYPOTHESES, VISUAL TARGETS, EXECUTIVE ROUTINES, CONTROL SEQUENCES.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE