Subtle Defect Detection Network: More accurately detect subtle defects on the Printed Circuit Board surface

Abstract

Printed circuit boards (PCBs) are the hardware foundation of large-scale integrated circuits, where surface quality inspection plays a critical role in manufacturing reliability. We proposed a subtle defect detection network (SDD-Net) to solve the detection problems in PCB surface defects, such as complex background, difficulty in distinguishing between foreground and background, random defect shape, area, and position. We propose a lightweight receptive field augmentation network (LRFA-Net) as the backbone effectively augments the receptive field, reduces parameters, and enhances feature extraction capabilities. A more lightweight multi-scale feature and coordinate information interaction mechanism was designed to enhance the capacity of the network to discern small targets in complex backgrounds. The combination of Varifocal Loss and Complete Intersection over Union Loss (CIoU) addresses the issue of distinguishing between the foreground and background, as well as adapting to PCB surface defects with variable shapes and positions. A lightweight Omni-dimensional dynamic convolutional prediction head (OD-Head) is designed to introduce multi-dimensional attention to effectively perceive small defects on the PCB surface. Compared with other algorithms, SDD-Net has a mean average precision (mAP_0.5) of 99.6 % on the PCB Defect Augmented dataset, and the detection speed reaches 53 frames per second, which achieves a balance between accuracy and speed, and the effect is better than other algorithms. At the same time, SDD-Net is also experimentally verified on the real PCB surface welding defect data set, and the results show that SDD-Net also has the best detection effect.