Gabor-like Eigenfilters for Texture Segmentation

Classification, segmentation and discrimination of textures are some of the most fundamental tasks in many image understanding, pattern recognition and machine vision applications. In the past two decades or so, these topics have been actively studied by many researchers and different approaches to the problem have been proposed. Earlier approaches to texture segmentation include co-occurrence matrices [ 11, Gauss-Markov random fields [ 2 ] , second-order statistics [ 3 ] and local linear transforms [4]. These approaches normally operates on a relatively small neighbourhood and therefore are most effective in segmenting the class of so called microtextures [5]. Microstructure texture feature extraction method based on a principal component transformation of a texture sample has also been studied [ 151.