Share Email Print
cover

Proceedings Paper

Multicolor neural network using cascaded color LCTVs
Author(s): Kenji Matsushita; Chii-Maw Uang; Xiangyang Yang; Reeser Wade; Francis T. S. Yu
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

One of the important aspects of a neural network is the exploration of the spatial content of the object under observation in this connection. We shall present a color optical neural network using inexpensive package-size liquid crystal televisions (LCTVs). By introducing a color encoding technique in conjunction with a conventional white light source, a multicolor neural net is synthesized. We have shown that by exploiting the spectral component of the LCTVs storage capacity of the neural net can be improved. Simulations as well as experimental results obtained from the proposed LCTV color neural net are provided, in which the effects due to noise and due to color crosstalk are addressed.

Paper Details

Date Published: 30 October 1992
PDF: 7 pages
Proc. SPIE 1812, Optical Computing and Neural Networks, (30 October 1992); doi: 10.1117/12.131193
Show Author Affiliations
Kenji Matsushita, The Pennsylvania State Univ. (Japan)
Chii-Maw Uang, The Pennsylvania State Univ. (Taiwan)
Xiangyang Yang, The Pennsylvania State Univ. (United States)
Reeser Wade, The Pennsylvania State Univ. (United States)
Francis T. S. Yu, The Pennsylvania State Univ. (United States)


Published in SPIE Proceedings Vol. 1812:
Optical Computing and Neural Networks
Ken Yuh Hsu; Hua-Kuang Liu, Editor(s)

© SPIE. Terms of Use
Back to Top