Neural network for image Fourier transform classification

Author

Levchenko, E.B. ; Myl´nikov, G.D. ; Timashev, A.N. ; Turygin, A. Yu

Author_Institution

TRINITI, Moscow Region, Russia

fYear

1992

Firstpage

196

Abstract

Considers the performance of a neural-network (NN)-based visual control system with NNs of different types (multilayered perceptrons and Hamming nets). They discuss the possible compensation of disturbances arising in a coherent-optical processor by NN learning. Simulation shows that different NNs have different behaviors for two types of input distorted data: the perceptron NN is more suitable for compensation of optical tract errors while the winner-takes-all NN performs better for noise damaged input patterns

Keywords

Fourier transform optics; computer vision; neural nets; Hamming nets; coherent-optical processor; disturbance compensation; image Fourier transform classification; input distorted data; learning; multilayered perceptrons; neural-network; noise damaged input patterns; optical tract errors; simulation; visual control system; winner takes all network; Fourier transforms; Image processing; Image recognition; Neural networks; Nonlinear optical devices; Nonlinear optics; Optical computing; Optical devices; Optical fiber networks; Optoelectronic devices;

fLanguage

English

Publisher

ieee

Conference_Titel

Neuroinformatics and Neurocomputers, 1992., RNNS/IEEE Symposium on

Conference_Location

Rostov-on-Don

Print_ISBN

0-7803-0809-3

Type

conf

DOI

10.1109/RNNS.1992.268593

Filename

268593