Wafer surface defect detection holds significant importance in semiconductor chip manufacturing.However,during the inspection process,false detection and missed detection of defects often occur due to the complexity and diversity of wafer surface defect types and manifestations.To balance real time and ac-curacy requirements,a wafer surface defect detection method based on the improved YOLOv5 algorithm is proposed.This method uses the lightweight network GhostNet as the backbone extraction network to re-duce model complexity and improve detection speed.Additionally,an efficient channel attention mecha-nism is introduced to enhance the model's feature extraction ability and detection accuracy.The original Si-LU function is replaced with the FReLU activation function to improve the model's sensitivity to space and detection accuracy.The improved model is validated using a real wafer defect dataset.The experimental re-sults show that the improved YOLOv5 network model achieves 30.02％parameter compression compared with the original model.The target accuracy reaches 78.6％,which is 4.4％higher than YOLOv5s.The mAP value is increased by 5.5％,and the detection speed is increased by 1.3 ms.
关键词
深度学习/晶圆表面缺陷/缺陷检测/YOLOv5/GhostNet
Key words
deep learning/wafer surface defects/defect detection/YOLOv5/GhostNet
维普
万方数据