5 April 2000 Modeling visual perception using similarity representation
Author Affiliations +
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.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wilbur S. Peng, Nick DeClaris, "Modeling visual perception using similarity representation", Proc. SPIE 4056, Wavelet Applications VII, (5 April 2000); doi: 10.1117/12.381713; https://doi.org/10.1117/12.381713
PROCEEDINGS
15 PAGES


SHARE
Back to Top