Defect detection of light guide plate based on improved YOLOv5 Networks

Abstract:

Light guide plate (LGP) is a kind of material used in backlight module. How to improve the quality control of LGP has become the focus of research in the industry. To address issues such as low gray contrast and large proportion of small target defects in LGP images, an improved YOLOv5 neural network based on multi-scale dilation convolution and a novel loss function is proposed. First, the LGP image is preprocessed, and then the Context Amplification Module (CAM) is integrated in the feature fusion part of the detection algorithm to fuse multi-scale expansion convolution features to obtain rich context information. XIoU Loss function is selected as the location regression Loss function. The result shows that this method can effectively improve the detection accuracy and positioning accuracy. Compared with YOLOv5, the average accuracy is increased by 4.7%, and the recall rate is increased by 27%. It can achieve accurate detection of defects such as white/bright spots, black spots,line scratches,and surface foreign objects in LGP.

Key words:Defect detection; YOLOv5; Multi-scale feature fusion; Attention mechanism; Loss function