Abstract:

A simple and effective texture classification of invariant scale and rotation was proposed．In this classifica-tion‚firstly‚the texture images to be classified are translated into Log-polar images via Log-polar transformation．Then‚the feature vectors of texture images are constituted with the normalized row project datum vector of the translated images. Finally‚the support vector machines are used to the texture classification of invariant scale and rotation．Experimental results show that the proposed method is of an accuracy of more than90％ when it is used to the texture classification of invariant scale and rotation．

Key words: texture classification, support vector machine, scale invariability, rotation invariability, Log-polar transformation