DocumentCode
2973333
Title
Optical neural network having a function of relative feature extraction without inhibitory connections
Author
Kuratomi, Yasunori ; Takimoto, Akio ; Ogawa, Hisahito
Author_Institution
Central Res. Labs., Matsushita Electr. Ind. Co. Ltd., Osaka, Japan
Volume
3
fYear
1993
fDate
25-29 Oct. 1993
Firstpage
3023
Abstract
An optical neural network (ONN) model having a function of feature extraction without any inhibitory synaptic connections has been proposed. The model called relative feature extracting ONN (R-FEONN) can recognize handwritten alphabet and numerical letters by extracting relative features which are hardly affected by changes in size or shifts in position of the input pattern. The optical system realizing the feature extraction is described.
Keywords
feature extraction; optical character recognition; optical neural nets; alphabet letters; elative feature extracting ONN; numerical letters; optical neural network; relative feature extraction; Feature extraction; Laboratories; Multi-layer neural network; Neural networks; Neurons; Optical computing; Optical devices; Optical fiber networks; Optical interconnections; Pattern recognition;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN
0-7803-1421-2
Type
conf
DOI
10.1109/IJCNN.1993.714357
Filename
714357
Link To Document