A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM

This paper describes the designing and testing process of a vision system for strongly reflected metal’s surface defects detection. In the authors’ view, an automatic inspection system has the following stages: image acquisition, image pre-processing, feature extraction and classification. Thus, the system including four subsystems is designed, and image processing method and pattern recognition algorithm that perform specific functions are outlined. First, the study uses wavelet smoothing method to eliminate noise from the images. Then, the images are segmented by Otsu threshold. At last, five characteristics based on spectral measure of the binary images are collected and input into a support vector machine (SVM). Furthermore, kernel function selection and parameters settings which are used for SVM method are evaluated and discussed. Also, a very difficult detection case for the surface defects of strongly reflected metal is depicted in details. The classification results demonstrate that the proposed method can identify seven classes of metal surface defects effectively, and the results are summarized and interpreted.