Local self-Similarity based texture classification
Hongbo Yang, Xia Hou · 2012
Aim of this paper is to develop a texture classification system for browsing and retrieval of image data. In this paper a novel local self-similarity texture descriptor is presented to describe the local texture pattern. And then, the classifier can be obtained by training local self-similarity texture descriptors captured from different textures. In this paper, the experiments are performed on the Brodatz texture database. And the results demonstrate that the proposed method is very efficient and can achieve high correct classification rate.