Texture classification using orientation-invariant wavelet packet features

This paper proposes an effective orientation-invariant texture feature for the classification of texture images. The feature extraction algorithm performs the tasks of transforming a texture image to its equivalent polar form, decomposing the polar image with a family of real orthonnormal wavelet bases for different levels, computing the wavelet packet coefficients, and computing the energy signatures using the wavelet packet coefficients. Such energy signatures are used as a feature for texture image classification. We employ a Mahalanobis distance classifier to classify a set of twenty distinct natural textures selected from the Brodatz album. Experimental results, based on a large sample data set having different orientations, show that the proposed method outperforms other methods which may perform quite well in the classification of texture images having the same orientation.