Feature extraction through contourlet subband clustering for texture classification

Feature extraction is an important processing procedure in texture classification. For feature extraction in the wavelet domain, the energies of subbands are usually extracted for texture classification. However, the energy of one subband is just a specific feature. In this paper, we propose an efficient feature extraction method for texture classification. In particular, feature vectors are obtained by c-means clustering on the contourlet domain as well as using two conventionally extracted features that represent the dispersion degree of contourlet subband coefficients. The c-means clustering algorithm is initialized via a nonrandom initialization scheme. By investigating these feature vectors, we employ a weighted L1-distance for comparing any two feature vectors that represent the corresponding subbands of two images and define a new distance between two images. According to the new distance, a k-Nearest Neighbor (kNN) classifier is utilized to perform texture classification, and experimental results show that our proposed approach outperforms five current state-of-the-art texture classification approaches. ? 2013 Elsevier B.V.EI157-16411