Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs

Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which...

Full description

Saved in:
Bibliographic Details
Main Authors: Liying Zhu, Sen Wang, Mingfang Chen, Aiping Shen, Xuangang Li
Format: Article
Language:English
Published: Springer 2024-07-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01554-5
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850181831441252352
author Liying Zhu
Sen Wang
Mingfang Chen
Aiping Shen
Xuangang Li
author_facet Liying Zhu
Sen Wang
Mingfang Chen
Aiping Shen
Xuangang Li
author_sort Liying Zhu
collection DOAJ
description Abstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP@0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS).
format Article
id doaj-art-75e9a19c662c4c5f90db5d10979da754
institution OA Journals
issn 2199-4536
2198-6053
language English
publishDate 2024-07-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-75e9a19c662c4c5f90db5d10979da7542025-08-20T02:17:49ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-07-011067591760410.1007/s40747-024-01554-5Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBsLiying Zhu0Sen Wang1Mingfang Chen2Aiping Shen3Xuangang Li4Faculty of Mechanical and Electrical Engineering, Kunming University of Science and TechnologyFaculty of Mechanical and Electrical Engineering, Kunming University of Science and TechnologyFaculty of Mechanical and Electrical Engineering, Kunming University of Science and TechnologyFaculty of Mechanical and Electrical Engineering, Kunming University of Science and TechnologyFaculty of Mechanical and Electrical Engineering, Kunming University of Science and TechnologyAbstract High-quality printed circuit boards (PCBs) are essential components in modern electronic circuits. Nevertheless, most of the existing methods for PCB surface defect detection neglect the fact that PCB surface defects in complex backgrounds are prone to long-tailed data distributions, which in turn affects the effectiveness of defect detection. Additionally, most of the existing methods ignore the intra-scale features of defects and do not utilize auxiliary supervision strategies to improve the detection performance of the network. To tackle these issues, we propose a lightweight long-tailed data mining network (LLM-Net) for identifying PCB surface defects. Firstly, the proposed Efficient Feature Fusion Network (EFFNet) is applied to embed intra-scale feature associations and multi-scale features of defects into LLM-Net. Next, an auxiliary supervision method with a soft label assignment strategy is designed to help LLM-Net learn more accurate defect features. Finally, the issue of inadequate tail data detection is addressed by employing the devised Binary Cross-Entropy Loss Rank Mining method (BCE-LRM) to identify challenging samples. The performance of LLM-Net was evaluated on a homemade dataset of PCB surface soldering defects, and the results show that LLM-Net achieves the best accuracy of mAP@0.5 for the evaluation metric of the COCO dataset, and it has a real-time inference speed of 188 frames per second (FPS).https://doi.org/10.1007/s40747-024-01554-5PCB defect detectionObject detectionEFFNetAuxiliary supervisionBCE-LRM
spellingShingle Liying Zhu
Sen Wang
Mingfang Chen
Aiping Shen
Xuangang Li
Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
Complex & Intelligent Systems
PCB defect detection
Object detection
EFFNet
Auxiliary supervision
BCE-LRM
title Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
title_full Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
title_fullStr Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
title_full_unstemmed Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
title_short Incorporating long-tail data in complex backgrounds for visual surface defect detection in PCBs
title_sort incorporating long tail data in complex backgrounds for visual surface defect detection in pcbs
topic PCB defect detection
Object detection
EFFNet
Auxiliary supervision
BCE-LRM
url https://doi.org/10.1007/s40747-024-01554-5
work_keys_str_mv AT liyingzhu incorporatinglongtaildataincomplexbackgroundsforvisualsurfacedefectdetectioninpcbs
AT senwang incorporatinglongtaildataincomplexbackgroundsforvisualsurfacedefectdetectioninpcbs
AT mingfangchen incorporatinglongtaildataincomplexbackgroundsforvisualsurfacedefectdetectioninpcbs
AT aipingshen incorporatinglongtaildataincomplexbackgroundsforvisualsurfacedefectdetectioninpcbs
AT xuangangli incorporatinglongtaildataincomplexbackgroundsforvisualsurfacedefectdetectioninpcbs