Duality theory of cellular neural networks for image compression and regeneration

Author

Tanaka, Mamoru ; Nakamura, Yoshinori ; Ikegami, Munemitsu ; Chigusa, Yasutami ; Mizutani, Hikaru

Author_Institution

Sophia Univ., Tokyo, Japan

Volume

1

fYear

1992

fDate

10-13 May 1992

Firstpage

367

Abstract

Image compression and regeneration by nonlinear associative cellular neural networks (CNNs) that can be used as retina chips are addressed. One is a sparse Hopfield-type neural network that is called an H-type CNN and the other is its dual network and is called a DH-type CNN. Their input information sequences are given by nodes and links as voltages and currents, respectively. Their error correcting capacity (minimum basins of attraction) is decided by the minimum numbers of links of cutset and loop, respectively. Simulation results showing the performance of both types of network are reported

Keywords

Hopfield neural nets; data compression; image coding; image reconstruction; DH-type CNN; H-type CNN; cellular neural networks; cutset; dual network; duality theory; error correcting capacity; image compression; image regeneration; input information sequences; loop; minimum basins; nonlinear associative networks; retina chips; sparse Hopfield-type neural network; Artificial neural networks; Cellular neural networks; DH-HEMTs; Error correction; Hopfield neural networks; Image coding; Neural networks; Quantization; Retina; Voltage;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1992. ISCAS '92. Proceedings., 1992 IEEE International Symposium on

Conference_Location

San Diego, CA

Print_ISBN

0-7803-0593-0

Type

conf

DOI

10.1109/ISCAS.1992.229937

Filename

229937