Extending GLCM to include Color Information for Texture Recognition

Аннотация

This paper proposes an automated system for texture recognition using an extended form of Grey Level Co-occurrence Matrix (GLCM). GLCM provides a popular statistical method for texture recognition, however its basic limitation is that it can only capture information from grey-scale images. To improve recognition accuracies this paper studies the possibilities of including color information from color texture images. Color information is captured by applying GLCM to each of the color channels r, g, b, both individually and in pairs providing 9 Color GLCM (C-GLCM) combinations i.e. rr, gg, bb, rg, rb, gr, gb, br, bg.Symmetrical normalized C-GLCMs computed along four directions 0º, 45º, 90º and 135º, from each of the 9 combinations are used to compute two features viz. GLCM Contrast and GLCM Mean, which are used for texture recognition. Experimental results indicate that C-GLCMs provide better recognition accuracies as compared to standard GLCMs on greyscale images