Abstract

A visual pattern recognition network and its training algorithm are proposed. The network constructed of a one-layer morphology network and a two-layer modified Hamming net. This visual network can implement invariant pattern recognition with respect to image translation and size projection. After supervised learning takes place, the visual network extracts image features and classifies patterns much the same as living beings do. Moreover we set up its optoelectronic architecture for real-time pattern recognition.

© 1996 Optical Society of America

Optical implementation of the Hamming net

Xiangyang Yang and Francis T. S. Yu
Appl. Opt. 31(20) 3999-4003 (1992)

Adaptive hierarchical architecture for visual recognition

Fok H. C. Tivive, Abdesselam Bouzerdoum, Son Lam Phung, and Khan M. Iftekharuddin
Appl. Opt. 49(10) B1-B8 (2010)

Neural-network classifiers for automatic real-world aerial image recognition

Shlomo Greenberg and Hugo Guterman
Appl. Opt. 35(23) 4598-4609 (1996)

Improvement of the generalization capability for a pattern-recognition neural network that uses a Gaussian-synapse neuron model

Xin Lin, Masahiko Mori, and Masanobu Watanabe
Appl. Opt. 39(5) 770-775 (2000)

Optoelectronic analogs of self-programming neural nets: architecture and methodologies for implementing fast stochastic learning by simulated annealing

Nabil H. Farhat
Appl. Opt. 26(23) 5093-5103 (1987)