Characterization of the texture characteristics of the machined surface image based on RULBP and GLCM

The texture characteristics of the workpiece surface after machining with different tool conditions are different, and the machined surface image contains a lot of information about the tool condition. In order to extract the texture features of workpiece surface which reflect the tool condition effectively and efficiently, a texture feature extraction method combining rotation-invariant uniform local binary pattern (RULBP) and gray-level co-occurrence matrix (GLCM) is proposed. This method utilizes the calculation principle of RULBP and GLCM to extract the micro and macro structure features of the workpiece surface texture respectively, so as to achieve the purpose of comprehensively extracting the "micro and macro" texture features. Experimental results show that the proposed method can significantly improve the characterization level of the texture features compared with the commonly used texture feature extraction methods.