Periodic defects in steel strips: Detection through a vision-based technique

This article proposes a technique to detect the defects caused by defective work roll. This system inspects the surface (top and bottom) of each strip. The images captured by the cameras are then processed. It includes a way to store the information necessary for detection as well as a flexible algorithm that uses this information efficiently. To train the algorithm to obtain the best possible outcome for a set of test strips, a way to quantify each solution is also proposed. Finally, the results obtained are compared with those obtained by a commercial tool, and the improvement achieved using the new technique is discussed.