Texture classification using color local texture features

This Paper proposes a new approach to extract the features of a color texture image for the purpose of texture classification. Four feature sets are involved. Dominant Neighbourhood Structure (DNS) is the new feature set that has been used for color texture image classification. In this feature a global map is generated which represents measured intensity similarity between a given image pixel and its surrounding neighbours within a certain window. Addition to the above generated feature set, features obtained from DWT are added together with DNS to obtain an efficient texture classification. Also the proposed feature sets are compared with that of Gabor wavelet, LBP and DWT. The texture classification process is carried out with the robust SVM classifier. The experimental results on the CUReT database shows that the proposed method is an efficient method whose classification rate is higher when compared with the other methods.