🤖 AI Summary
In PCB defect detection, YOLO models suffer from poor generalization and robustness due to sensitivity to viewpoint variations, object orientation, and image quality. To address this, we propose VR-YOLO—a viewpoint-robust variant of YOLOv8. Our method integrates multi-angle data augmentation, a key-object focusing mechanism, an angle-aware loss function, and a lightweight attention module to enhance small-object feature representation. Experiments demonstrate that VR-YOLO achieves 98.9% mAP on standard benchmarks and maintains 94.7% mAP under significant viewpoint shifts—substantially outperforming baseline models—while incurring negligible computational overhead, enabling practical industrial deployment. The core contribution lies in systematically enhancing YOLO’s viewpoint invariance and fine-grained defect detection capability in complex industrial environments.
📝 Abstract
The integration of large-scale circuits and systems emphasizes the importance of automated defect detection of electronic components. The YOLO image detection model has been used to detect PCB defects and it has become a typical AI-assisted case of traditional industrial production. However, conventional detection algorithms have stringent requirements for the angle, orientation, and clarity of target images. In this paper, we propose an enhanced PCB defect detection algorithm, named VR-YOLO, based on the YOLOv8 model. This algorithm aims to improve the model's generalization performance and enhance viewpoint robustness in practical application scenarios. We first propose a diversified scene enhancement (DSE) method by expanding the PCB defect dataset by incorporating diverse scenarios and segmenting samples to improve target diversity. A novel key object focus (KOF) scheme is then presented by considering angular loss and introducing an additional attention mechanism to enhance fine-grained learning of small target features. Experimental results demonstrate that our improved PCB defect detection approach achieves a mean average precision (mAP) of 98.9% for the original test images, and 94.7% for the test images with viewpoint shifts (horizontal and vertical shear coefficients of $pm 0.06$ and rotation angle of $pm 10$ degrees), showing significant improvements compared to the baseline YOLO model with negligible additional computational cost.