EEDD: Edge-Guided Energy-Based PCB Defect Detection

Abstract

Printed circuit board (PCB) defect detection is critical for ensuring the safety of electronic devices, especially in the space industry. Non-reference-based methods, typically the deep learning methods, suffer from a large amount of annotated data requirements and poor interpretability. In contrast, conventional reference-based methods achieve higher detection accuracy by comparing with a template image but rely on precise image alignment and face the challenge of fine defects detection. To solve the problem, we propose a novel Edge-guided Energy-based PCB Defect Detection method (EEDD). We focus on the salient edge characteristic of PCB images and regard the functional defects as contour differences and then propose a novel energy measurement method for PCB contour anomaly detection. We introduce the energy transformation using the edge information of the template and test image, then Speeded-Up Robust Features method (SURF) is used for image alignment, and finally achieve defect detection by measuring the energy anomaly score pixel by pixel with the proposed energy-based defect localization and contour flood fill methods. Our method excels in detecting multi-scale defects, particularly tiny defects, and is robust against interferences such as non-finely aligned images and edge spurs. Experiments on the DeepPCB-A dataset and our high-resolution PCB dataset (HDPCB) show that the proposed method outperforms state-of-the-art methods in PCB defect-detection tasks.

Printed circuit board and printed circuit board assembly methods for testing and visual inspection: a review

“…Deng et al [43] propose a new method for PCB defect detection based on finding the contour unconformity (anomaly) and energy transformation (edge-guided energy-based PCB defect detection (EEDD)). Its advantages lead to possibility for tiny defects detection and flexible definition of defect criteria taking into account the requirements of a given production.…”

CGS-YOLOv5: a defect detection algorithm for PCB board based on YOLOv5 algorithm

“…As one of the core components of electronic equipment, the quality and reliability of the PCB board directly affect whether the whole equipment can operate normally, so defect detection on the PCB board is an indispensable link 1,2 .In earlier times, human eye inspection and in-line inspection were the main methods to check whether the PCB is in good condition 3,4 . However, due to the increase of the complexity of PCB board and the expansion of production scale, it is difficult for the traditional manual detection accuracy and speed to meet the demand, while online testing detects defects through electrical performance, with high cost and slow detection speed 5,6 .…”