Surface Defect Detection Algorithm for PCB Based on Improved YOLOv8

With the rapid development of the electronics industry, printed circuit boards (PCBs) play a crucial role in electronic products. However, traditional methods for PCB defect detection suffer from low efficiency and insufficient accuracy. To address this issue, this paper proposes an improved YOLO algorithm for PCB defect detection. In the field of PCB defect detection, due to the dense components and complex wiring on PCBs, traditional detection methods struggle to accurately and quickly identify various types of defects. This study aims to improve upon the traditional YOLO algorithm by introducing a new dual-layer routing attention mechanism and a feature extraction module, which enhances the ability to extract features of PCB defects. Additionally, the algorithm’s loss function, Shape-IoU, has been optimized to better accommodate the shape characteristics of PCB defects, thereby improving both detection accuracy and recall rate. Experimental results demonstrate that the improved YOLO algorithm exhibits higher performance in PCB defect detection. Compared to traditional methods, the detection accuracy has increased by $2 \%$, and the detection speed has improved by $3 \%$, providing a more effective technical means for quality control in the PCB production process.