An improved surface roughness measurement method for micro-heterogeneous texture in deep hole based on gray-level co-occurrence matrix and support vector machine

Microscopic vision system has been employed to measure the surface roughness of micro-heterogeneous texture in deep hole, by virtue of frequency domain features of microscopic image and back-propagation artificial neural network optimized by genetic algorithm. However, the measurement accuracy needs to be improved for engineering application. In this paper, we propose an improved method based on microscopic vision to detect the surface roughness of R-surface in the valve. Firstly, the measurement system for the roughness of R-surface in deep hole is described. Thereafter, the surface topography images of R-surface are analyzed by the gray-level co-occurrence matrix (GLCM) method, and several features of microscopic image, which are nearly monotonic with the surface roughness, are extracted to fabricate the prediction model of the roughness of R-surface accurately. Moreover, a support vector machine (SVM) model is presented to describe the relationship of GLCM features and the actual surface roughness. Finally, experiments on measuring the surface roughness are conducted, and the experimental results indicate that the GLCM-SVM model exhibits higher accuracy and generalization ability for evaluating the microcosmic surface roughness of micro-heterogeneous texture in deep hole.