Feature fusion for image texture segmentation
David A. Clausi, Huawu Deng · 2004
A design-based method to fuse Gabor filter and grey level co-occurrence probability (GLCP) features for im-proved texture recognition is presented. Feature space separability and unsupervised image segmentation are used for testing. The fused features are robust with re-spect to the curse of dimensionality and additive noise. Feature reduction methods are typically detrimental to the segmentation performance. Overall, the fused fea-tures are a definite improvement over non-fused features and are advocated in texture analysis applications. 1