1 November 1991 Neural networks and model-based approaches to object identification
Author Affiliations +
Proceedings Volume 1606, Visual Communications and Image Processing '91: Image Processing; (1991); doi: 10.1117/12.50333
Event: Visual Communications, '91, 1991, Boston, MA, United States
Abstract
This paper describes an adaptive (self-learning) approach to object identification developed during the last two years. This approach combines an adaptive neural network with a model- based approach to object identification. It is based on the Maximum Likelihood Adaptive Neural System (MLANS), which has a capability for self-learning invariant features and symbolic patterns.
© (1991) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Leonid I. Perlovsky, "Neural networks and model-based approaches to object identification", Proc. SPIE 1606, Visual Communications and Image Processing '91: Image Processing, (1 November 1991); doi: 10.1117/12.50333; https://doi.org/10.1117/12.50333
PROCEEDINGS
6 PAGES


SHARE
KEYWORDS
Neural networks

Image classification

Image processing

Visual process modeling

Evolutionary algorithms

Pattern recognition

Statistical modeling

Back to Top