Texture Classification by Using Co-occurrences of Local Binary Patterns
کلمات کلیدی:
local binary pattern; rotation invariance; textureclassification
چکیده:
This paper proposes an efficient method for increasingthe performance of Local Binary Patterns (LBPs). Althoughhistogram of LBPs provides sufficient information of localpattern occurrences, it discards global interaction of these localpatterns. We replace histogram of LBPs by making a LocalPattern Co-occurrence Matrix (LPCM) for the purpose ofrotation and illumination invariant texture classification. Experimental results show significant improvement in terms ofclassification accuracy in comparison with conventionalhistogram based feature extraction method