Classification of colour textures using shearlets

This paper proposes an efficient approach for the classification of colour textures using shearlets. The principal features of each texture are extracted from the directional components of shearlet decomposed image. In order to increase the efficiency and reduce the computation time, mean of directional components are used as principal feature for classification. The given unknown texture image is classified into known texture by nearest neighbor classifier with the help of features extracted. Experimental results show the usefulness of the proposed approach and 97.5% classification accuracy is achieved.