期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：93
期号：2
出版社：Journal of Theoretical and Applied
摘要：One of the important and crucial tasks of image analysis is to derive significant features of the images. The gray level co-occurrence matrix (GLCM) and its features derived by Haralick are widely known for texture classification. The main disadvantage of GLCM is its high dimensionality when applied on the grey level image. The local features derived from local binary pattern (LBP) have shown significant results in various image and video processing applications. The present paper derived the fundamental rotational invariant local features from LBP in the form of uniform LBP (ULBP) and treated all non-uniform LBP (NULBP) as miscellaneous. After encoding the texture into ULBP coded texture the present paper derived GLCM features and performed texture classification rate, mean absolute error and root mean square error on Brodtaz textures using various machine learning classifiers. The proposed uniform local binary pattern matrix (ULBPM) is compared with GLCM method, cross diagonal texture unit matrix (CDTM) and texture spectrum (TS) methods. The results indicate high performance of the proposed method over the existing methods.
