Vision-based automatic detection of steel surface defects in the cold rolling process: considering the influence of industrial liquids and surface textures

In the cold rolling process, automatic surface defect detection could be considered as an important technique to monitor product quality, and so far, substantial kinds of surface defects have been already successfully inspected. However, the interference of industrial liquids and produced surface textures has been rarely studied yet. To address this problem, the vision-based automatic detection method is proposed in this paper containing three main parts: (i) region extraction, (ii) defect detection, and (iii) industrial liquid quantification. Four sets of experiments are designed to verify the feasibility, accuracy, and stability of the proposed method. The results indicate that the proposed method can detect most cracks and scratches with the accuracy of more than 91 %. Also, the proposed method could accurately quantify the industrial liquids including their numbers (with the average accuracy of more than 90 %) and their sizes (with the accuracy of more than 91 %); it is therefore expected to be promising because it could be utilized to track the online running status of the rolling system and provide rolling system maintenance suggestions.