Metal Surface Defect Detection Algorithm Based on Improved YOLOv5

Abstract

Aiming at the problem of model misdetection and missed detection caused by the small defect and unclear features of industrial metal surfaces, this paper studies a large number of metal surface defects, and proposes a metal surface micro defect detection algorithm based on improved YOLOv5. First, this paper uses the FenceMask data enhancement method for regularization to solve the problem of few sample images. Then an enhanced multi-scale feature fusion pyramid network DS-FPN is proposed by introducing depthwise separable convolution, dilated convolution and spatial attention mechanism, so that the model can improve the ability to extract key information of images without adding additional parameters and calculations. An adaptive channel spatial attention mechanism SCBAM is also proposed, which adds non-local information to the original interaction with only local information, improving the feature expression ability of the model. Finally, through experimental verification, the detection accuracy of the model in this paper on the public data set GC10-DET has reached 74.9%, which is 4.7% higher than the original YOLOv5 model.