Abstract
Surface defect detection for printed circuit board (PCB) is indispensable for managing PCB production quality. However, automatic detection of PCB surface defects is still a challenging task because, even within the same category of surface defect, defects present great differences in morphology and pattern. Although many computer vision-based detectors have been established to handle these problems, current detectors struggle to achieve high detection accuracy, fast detection speed and low memory consumption simultaneously. To address those issues, we propose a cost-effective deep learning (DL)-based detector based on the cutting-edge YOLOv4 to detect PCB surface defect quickly and efficiently. The YOLOv4 is improved upon with respect to its backbone network and the activation function in its neck/prediction network. The improved YOLOv4 is evaluated with a customized dataset, collected from a PCB factory. The experimental results show that the improved detector achieved a high performance, scoring 98.64% on mean average precision (mAP) at 56.98 frames per second (FPS), outperforming the other compared SOTA detectors. Furthermore, the improved YOLOv4 reduced the parameter space of YOLOv4 from 63.96 M to 39.59 M and the number of multiply-accumulate operations (Madds) from 59.75 G to 26.15 G.
Highlights
Surface defect detection is indispensable in managing Printed circuit board (PCB) production quality
To solve the above-mentioned problems, this study proposes a cost-effective DLbased detector called as YOLOv4-MN3 based on cutting-edge YOLOv4 and MobileNetV3 lightweight network
YOLOv4-MN3 canconfidence, adapt to given different in Figures 13 and 14, indicate that the proposed YOLOv4-MN3 can adapt to different categories of surface defect, and it can handle the difficult problem of a diversity of defect categories of surface defect, and it can handle the difficult problem of a diversity of defect morphologies
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. Used the mathematical morphology method to obtain standard images, and an image aberration detection algorithm was introduced to detect PCB defects These traditional detectors highly rely on prior knowledge to determine previously seen features, or to store a large number of standard images and precisely align testing images to them for element matching. A DL-based detector utilizes a convolutional neural network (CNN) to extract and defect features and learn inherent patterns of defects, automatically, without standard images or manual design rules [8,9], which greatly improves detection accuracy, efficiency and model generalization. Hu et al [18] improved the two-stage Faster RCNN for PCB defect detection They replaced the backbone and neck network of Faster RCNN with ResNet and feature pyramid networks (FPN) respectively.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
