Share Email Print

Proceedings Paper

Modeling visual perception using similarity representation
Author(s): Wilbur S. Peng; Nick DeClaris
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

We present a model of 3D visual perception which uses a notion of similarity that preserves meaningful neighborhood relationships between different visual stimuli. The notion involves a similarity graph-based representation that seeks to capture local connectivity in the similarity domain. An end-to-end computational implementation using wavelet features and a multilayer neural network architecture is presented. The usefulness of the similarity representation for visual reasoning is explored.

Paper Details

Date Published: 5 April 2000
PDF: 15 pages
Proc. SPIE 4056, Wavelet Applications VII, (5 April 2000); doi: 10.1117/12.381713
Show Author Affiliations
Wilbur S. Peng, Univ. of Maryland/College Park (United States)
Nick DeClaris, Univ. of Maryland/Baltimore (United States)

Published in SPIE Proceedings Vol. 4056:
Wavelet Applications VII
Harold H. Szu; Martin Vetterli; William J. Campbell; James R. Buss, Editor(s)

© SPIE. Terms of Use
Back to Top