Title :
Structural pattern compression and recognition by linear CNN
Author :
Cheng, Gui-Xin ; Tanaka, Mamoru
Author_Institution :
Dept. of Electr. & Electron. Eng., Sophia Univ., Tokyo, Japan
fDate :
30 May-2 Jun 1994
Abstract :
In this paper, a multi-layer pattern structural compression method, a method memorizing this pattern in a multi-layer weighted resister network and a method associating the memorized pattern are proposed. Simulation results show the efficiency of these methods
Keywords :
cellular neural nets; data compression; pattern recognition; association; linear CNN; multi-layer weighted resister network; pattern memorization; simulation; structural pattern compression; structural pattern recognition; Cellular neural networks; Current distribution; Decoding; Filters; Image coding; Image reconstruction; Neural networks; Pattern recognition; Resistors; Very large scale integration;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409613
