Storming Media: Pentagon Reports and DocumentsPentagon Reports: Fast. Definitive. Complete.     
New Account »
Forgot Password?
Advanced Search »
ComputersCybernetics

Deformable Topological Templates for Image Analysis

Authors: Yali Amit; CHICAGO UNIV IL DEPT OF STATISTICS
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.

Limitations: APPROVED FOR PUBLIC RELEASE
Description: Final rept. Sep 92-Aug 96
Pages: 7
Report Date: 10 AUG 96
Contract Number: DAAL03-92-G-0322
Report Number: A018613
Keywords relating to this report:
COMPUTATIONS
DEFORMATION
IMAGE PROCESSING
REPRINTS
TARGET CLASSIFICATION
TEMPLATES
TOMOGRAPHY
TOPOLOGY
Email This Abstract