Texture Image Classification Using Non-subsampled Contourlet Transform and Support Vector Machines

This paper proposes a new approach to characterize texture image at multiresolution using the non-subsampled contourlet transform, a new geometrical multiresolution transform. The support vector machines (SVMs), which have demonstrated excellent performance in a variety of pattern recognition problems, are used as classifiers. The Classification experiments with 20 Brodatz textures indicate that the NSCT and SVM approach is superior to standard wavelet transform method.