YOLOv5s‐GC‐Based Surface Defect Detection Method of Strip Steel

Detecting surface defects in strip steel is significantly important for improving production efficiency and product quality. Herein, a novel surface defect detection of strip steel method based on You Only Look Once (YOLO)v5s‐GC is proposed. First, a ResNet‐Mini is developed to preclassify the original dataset to reduce the number of calculations. Subsequently, image preprocessing is conducted to enhance the defect features, which consists of two steps: the first is combining the ResNet‐Mini network weights with Grad‐CAM to crop defective areas and remove background interference and the second is applying the OTSU and normal distribution enhancement algorithm to extract the feature grayscale. Furthermore, a size enhancement strategy is adopted to obtain larger data sizes that could simulate an actual application scenario with a large‐area saccade of strip steel. Finally, the cross‐stage partial module of YOLOv5s is replaced with GhostBottleneck, and the convolutional block attention module is added to the detection neck. The average accuracy of YOLOv5s‐GC for detecting six types of strip steel is 82.4%, marking an increase of 7.0% over YOLOv5s. In addition, the calculation amount of YOLOv5s‐GC is reduced by 48%, and the inference speed is increased by 24%. To balance the speed and accuracy in strip surface defect detection, a novel You Only Look Once v5s‐GC method is proposed based on convolutional block attention module, GhostBottleneck, and YOLOv5s. It incorporates residual network mini for preclassification and introduces OTSU and normal distribution enhancement algorithm for image preprocessing. The network achieves an average accuracy of 82.4% with 24% inference speed increase.