Vertical scratch detection algorithm for high-speed scale-covered steel BIC(Bar in Coil)

Abstract

Recently, vision-based inspection systems have been widely investigated for the defect inspection in various industrial products. This paper proposes a vision-based method for detection of scratches in the surfaces of scale-covered steel wire rods. Scales are formed on the surface of wire rods owing to the deposition of oxidized substances that are produces during manufacturing. Because of the variety in the types of steel, presence of scales, and manufacturing conditions, the features of wire rod surface images are not uniform. Moreover, the similarities in the gray-level and shape of the defect and defect-free regions make it very difficult to accurately detect defects. In order to solve the abovementioned problems and to detect defects more effectively, we propose a new defect detection algorithm, which is based on edge pair detection, binarization with double threshold, morphological operation, and SVM(Support Vector Machine). Finally, the experimental results conducted on steel wire rod images obtained from actual steel production lines show that the proposed algorithm is effective for defect detection of scale-covered steel wire rods.