SYNOPSIS ON TEXTURE CLASSIFICATION BY USING ADVANCED LOCAL BINARY PATTERNS AND SPATIAL DISTRIBUTION OF DOMINANT PATTERNS

SYNOPSIS

            In this paper, we propose a new feature extraction method, which is robust against rotation and histogram equalization for texture classification. To this end, we introduce the concept of Advanced Local Binary Patterns (ALBP), which reflects the local dominant structural characteristics of different kinds of textures. In addition, to extract the global spatial distribution feature of the ALBP patterns, we incooperate ALBP with the Auro Matrix measure as the second layer to analyze texture images. The proposed  method has three novel contribution. (a) The proposed ALBP approach captures the most essential local structure characteristics of textures the most essential local structure characteristics  of texture images (i.e. edges, corners). (b) The proposed method extracts global information by using Auro Matrix measure based on the spatial distribution information of the dominant patterns produced by ALBP. (c) The proposed method is robust to rotation and histogram equalization.