Title :
Performance enhancement for fuzzy adaptive resonance theory (ART) neural networks
Author :
Naghdy, G. ; Wang, J. ; Ogunbona, P.
Author_Institution :
Dept. of Electr. & Comput. Eng., Wollongong Univ., NSW, Australia
fDate :
11/7/1996 12:00:00 AM
Abstract :
A modified fuzzy adaptive resonance theory neural network (ART) is used as a classifier for a texture recognition system. The system consists of a wavelet based low level feature detector and a high level ART classifier. The performance improvement is measured in terms of identification accuracy and computational burden
Keywords :
ART neural nets; fuzzy neural nets; identification; image classification; image texture; pattern classification; wavelet transforms; adaptive resonance theory; computational burden; fuzzy ART neural networks; high level ART classifier; identification accuracy; neural classifier; performance enhancement; texture recognition system; wavelet based low level feature detector;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19961433
