Rotation and Scale Invariant Texture Classification Using Gabor and Curvelet Transforms
Selvaraj Arivazhagan, S. Jaya Nirmala · International journal of tomography and simulation · 2015
One of the challenging problems in image processing and computer vision is texture classification. The goal of texture classification is to assign a test sample to one of the set of known classes. s. This paper presents an efficient method for rotation and scale invariant texture classification using multi-resolution transform such as Gabor and Curvelet transform. Gabor transform is a very useful tool for recognizing texture images, because of their optimal localization properties. The features (mean, standard deviation, entropy) are extracted from the Gabor transformed images and used for texture classification. The Curvelet transform is very effective for representing the edges and other singularities along the curves. The features such as mean, standard deviation are derived from curvelet sub bands. This proposed method with combined Gabor and Curvelet transform produces better classification rate.