A Hybrid YOLOv11–Faster R-CNN Approach for PCB Defect Detection

Abstract

Printed circuit board (PCB) defect detection is critical for ensuring the performance and reliability of electronic products. However, traditional inspection methods suffer from low efficiency and poor stability. In recent years, the development of deep learning models has proceeded at a rapid pace. But existing deep learning models still face challenges in detecting small defects and distinguishing visually similar categories. To address these issues, this paper proposes a hybrid detection method combining You Only Look Once (YOLOv11) and Region-based Convolutional Neural Network (Faster R-CNN). A fusion head is designed to jointly evaluate candidate bounding boxes from both models, improving detection accuracy and stability. Experimental results show that the proposed model achieves mAP@0.5 of 0.974 and F1-score of approximately 0.95, outperforming YOLOv11 (0.921, 0.90) and Faster R-CNN (0.965, 0.94). These results demonstrate that the proposed method can effectively reduce false detections and missed detections, showing strong potential for industrial PCB defect inspection.