Title :
ICA-based multi-colour space texture classification system
Author :
Chindaro, S. ; Sirlantzis, Konstantinos ; Fairhurst, Michael C.
Author_Institution :
Dept. of Electron., Univ. of Kent, Canterbury
Abstract :
Presented is a novel method which uses independent component analysis (ICA) for systematically partitioning and combining textural features extracted from different colour spaces, in a multiple classifier based system, for colour texture classification. Results obtained illustrate that the proposed ICA-based feature-partitioning and classifier combination system produces more accurate results compared to a system that combines classifiers applied to features extracted from individual colour spaces
Keywords :
feature extraction; image classification; image colour analysis; image texture; independent component analysis; independent component analysis; multicolour space texture classification system; multiple classifier based system; textural feature combining; textural feature partitioning;
Journal_Title :
Electronics Letters
