Silicon retina: image compression by associative neural network based on code and graph theories

Author

Tanaka, Mamoru

Author_Institution

Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan

fYear

1990

fDate

1-3 May 1990

Firstpage

1871

Abstract

An associative neural network (NN) is constructed on the basis of code and graph theories to realize a silicon retina. Each neuron is an EXCLUSIVE-OR unit in the digital NN (DNN) based on finite field GF(2). Each neuron is an adder unit in the analog NN (ANN) based on real field R^b. The network has the following features: no multiplier, sparsity, cellular structure, high concurrency, and high speed. The DNN and the ANN can be applied to data compression for binary and analog images, respectively. The S/N rate in the reproduction image depends on the network structure. Secret image communication and image recognition are possible

Keywords

analogue computer circuits; computerised pattern recognition; computerised picture processing; content-addressable storage; data compression; digital circuits; learning systems; neural nets; parallel architectures; EXCLUSIVE-OR unit; S/N rate; SANNET; Sophia neural net; adder unit; analog images; analogue neural network; associative neural network; binary images; cellular structure; code theory; data compression; digital neural network; graph theories; high concurrency; high speed; image compression; image recognition; secret image communication; silicon retina; Adders; Artificial neural networks; Cellular networks; Galois fields; Graph theory; Image coding; Neural networks; Neurons; Retina; Silicon;

fLanguage

English

Publisher

ieee

Conference_Titel

Circuits and Systems, 1990., IEEE International Symposium on

Conference_Location

New Orleans, LA

Type

conf

DOI

10.1109/ISCAS.1990.112037

Filename

112037