Accession Number : ADA316810

Title :   Deformable Topological Templates for Image Analysis.

Descriptive Note : Final rept. Sep 92-Aug 96,

Corporate Author : CHICAGO UNIV IL DEPT OF STATISTICS

Personal Author(s) : Amit, Yali

PDF Url : ADA316810

Report Date : 10 AUG 1996

Pagination or Media Count : 7

Abstract : The main achievements of this proposal has been the introduction of a new family of global but sparse image features consisting of geometric arrangements of local responses. These features can serve as building blocks for template models, allowing for explicit modeling of the variability of the object family, and efficient computation of the template match. These features can also be accessed through decision trees to provide very accurate and efficient shape classifiers.

Descriptors :   *IMAGE PROCESSING, *TOPOLOGY, *TOMOGRAPHY, REPRINTS, COMPUTATIONS, DEFORMATION, TEMPLATES, TARGET CLASSIFICATION.

Subject Categories : Cybernetics

Distribution Statement : APPROVED FOR PUBLIC RELEASE