Title :
Recursive least squares approach to combining principal and minor component analyses
Author :
Wong, Arnold-Shu-Yan ; Wong, Kwok-Wo ; Leung, Chi-sing
Author_Institution :
Dept. of Electron. Eng., City Polytech. of Hong Kong, Kowloon, Hong Kong
fDate :
5/28/1998 12:00:00 AM
Abstract :
A novel approach for high-performance data compression using neural networks is proposed. After the principal components of the input vectors are extracted, the error covariance matrix obtained in the recursive least square training process is used to perform minor components pruning so that a higher compression ratio is achieved. Simulation results show that our method effectively combines principal and minor component analyses
Keywords :
covariance matrices; data compression; image coding; image reconstruction; least squares approximations; neural nets; compression ratio; data compression; error covariance matrix; input vectors; minor component analyses; minor components pruning; neural networks; principal component analyses; recursive least squares approach; training process;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19980765
