BLOCK TRUNCATION CODING USING HOPFIELD NEURAL NETWORK

被引:8
作者
MITCHELL, HB
DORFAN, M
机构
[1] Signal Processing & Computing Department, Elta Electronics Industries Ltd., Ashdod
关键词
BLOCK TRUNCATION CODING; IMAGE CODING; NEURAL NETWORKS;
D O I
10.1049/el:19921376
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
The authors extend the analysis of the block truncation coding (BTC) algorithm using a Hopfield neural network (HNN). They show that its performance is suboptimum (in the mean square error sense) and that alternative (non-neural network) BTC algorithms are available with virtually the same performance.
引用
收藏
页码:2144 / 2145
页数:2
相关论文
共 6 条
[1]  
Efrati N., 1991, Signal Processing: Image Communication, V3, P275, DOI 10.1016/0923-5965(91)90015-T
[2]  
QUI G, 1991, ELECTRON LETT, V27, P1924
[3]  
RIDLER TW, 1978, IEEE T SYST MAN CYB, V8, P629
[4]  
TRUSSELL HJ, 1978, IEEE T SMC, V9, P311
[5]  
UDPIKAR VR, 1985, ELECTRON LETT, V21, P901
[6]  
WALACH E, 1983, SIGNAL PROCESSING, V2