Steel Surface Defect Recognition: A Survey

Steel surface defect recognition is an important part of industrial product detection, which has attracted more and attention in recent years. In the development steel technology, there been a process from manual detection to automatic based on traditional machine learning algorithm, subsequently deep algorithm. this paper, we discuss key hardware systems offer suggestions for related options; second, present literature review algorithms recognition, includes texture features shape as well supervised, unsupervised, weakly supervised (Incomplete supervision, inexact imprecise supervision). addition, some common datasets algorithm performance evaluation metrics field are summarized. Finally, challenges current corresponding solutions, our future work focus explained.