Rotation Invariant Texture Classification using Fuzzy Logic

In this paper, we develop a scale invariant texture classification method based on Fuzzy logic. It is applied for the classification of texture images. Texture is a common property of any surface having uncertainty. Two types of texture features are extracted one using Discrete Wavelet Transform (DWT) and other using Co-occurrence matrix. Co-occurrence features are obtained using DWT coefficients. Two features are obtained from each sub-band of DWT coefficients upto fifth level of decomposition and eight features are extracted from co-occurrence matrix of whole image and each sub-band of first level DWT decomposition. The fuzzy classification is achieved in two steps, fuzzification step, and rule generation step. The performance is measured in terms of Success Rate. This study showed that the proposed method offers excellent scale invariant texture classification Success Rate. Also wavelet features like standard deviation, combination of energy and standard deviation along with some proposed hybrid feature sets outperform the other feature sets. This success rate is comparatively high when compared with results published earlier.