Defect Detection on PCB Based on Improved YOLOv8

doi:10.12068/j.issn.1005-3026.2025.20240038

Abstract

Abstract:

Due to the high integration， complex circuits， and increasing parameters of printed circuit boards （PCBs）， defects in PCBs directly affect production efficiency， making computer vision-based defect detection crucial for PCB manufacturing. A self-attention-based PCB defect detection algorithm was proposed based on the YOLO object detection algorithm. First， a polarized self-attention （PSA） mechanism was introduced in the feature extraction stage to separately extract spatial and semantic features of PCBs， which were combined with input raw features to enhance the network’s feature representation capability. Then， a small-object detection head was added in the decoding stage， which fully utilized low-resolution features from the YOLO network Backbone module to enable the network to focus on local details of PCBs and improve defect positioning accuracy. Experiments show that the proposed method achieves 95.5% accuracy on the PCB dataset， 4% higher than the original YOLOv8 method， with the mAP0.5∶0.95 metric increased by 2.8%.

Key words: YOLOv8, small-object detection head, polarized self-attention mechanism, defect detection, object detection

CLC Number:

TP 391.41

Zhen-zhen LYU, Li-jin FANG, Qian-kun ZHAO, Ying-cai WAN. Defect Detection on PCB Based on Improved YOLOv8[J]. Journal of Northeastern University(Natural Science), 2025, 46(10): 1-9.

Figures/Tables 11

References 16

[1]	Zheng X Q， Zheng S， Kong Y G， et al. Recent advances in surface defect inspection of industrial products using deep learning techniques［J］. The International Journal of Advanced Manufacturing Technology， 2021， 113（1）： 35-58.
[2]	Anitha D B， Rao M. A survey on defect detection in bare PCB and assembled PCB using image processing techniques［C］// International Conference on Wireless Communications， Signal Processing and Networking （WiSPNET）. Chennai， 2017： 39-43.
[3]	Ma J J. Defect detection and recognition of bare PCB based on computer vision［C］// 36th Chinese Control Conference （CCC）. Dalian， 2017： 11023-11028.
[4]	邹华东.基于机器学习的PCB孔位信息在线光学检测［J］.辽宁工程技术大学学报（自然科学版），2012，31（1）：93-97.
	Zou Hua-dong. Online optical inspection of PCB hole position information based on machine learning［J］. Journal of Liaoning Technical University （Natural Science Edition）， 2012， 31（1）： 93-97.
[5]	Zhang Z Q， Wang X D， Liu S， et al. An automatic recognition method for PCB visual defects［C］// 2018 International Conference on Sensing， Diagnostics， Prognostics， and Control （SDPC）. Xi’an， 2018： 138-142.
[6]	Wang N， Wang B， Huang J M， et al. PCB characteristic impedance prediction based on an error compensated random forest regression model［C］// 34th Chinese Control and Decision Conference （CCDC）. Hefei， 2022： 3999-4004.
[7]	Chang Q T， Zhang Y， Sun Z. Research on surface defect detection algorithm of ice-cream bars based on clustering［C］// IEEE 3rd Information Technology， Networking， Electronic and Automation Control Conference （ITNEC）. Chengdu， 2019： 537-541.
[8]	Hu B， Wang J H. Detection of PCB surface defects with improved faster-RCNN and feature pyramid network［J］. IEEE Access， 2020， 8： 108335-108345.
[9]	刘伟森，方亦建. 基于多尺度轻量级卷积网络的 PCB 裸板缺陷识别算法［J］.自动化与信息工程， 2020，41（5）：20-25.
	Liu Wei-sen， Fang Yi-jian. PCB bare board defect recognition algorithm based on multi-scale lightweight convolutional network［J］. Automation & Information Engineering， 2020，41（5）： 20-25.
[10]	Han W， Ren H W， Zhu X J， et al. Research and implementation of PCB defect detection based on improved YOLOv5 algorithm［C］// IEEE 3rd International Conference on Information Technology， Big Data and Artificial Intelligence （ICIBA）. Chongqing， 2023： 1475-1478.
[11]	Li Y T， Huang H S， Xie Q S， et al. Research on a surface defect detection algorithm based on MobileNet-SSD［J］. Applied Sciences， 2018， 8（9）： 1678.
[12]	An K， Zhang Y P. LPViT： a transformer based model for PCB image classification and defect detection［J］. IEEE Access， 2022， 10（5）： 42-53.
[13]	王永利，曹江涛，姬晓飞.基于卷积神经网络的 PCB缺陷检测与识别算法［J］.电子测量与仪器学报，2019， 33（8）： 78-84.
	Wang Yong-li， Cao Jiang-tao， Ji Xiao-fei. PCB defect detection and recognition algorithm based on convolutional neural network ［J］. Journal of Electronic Measurement and Instrumentation， 2019， 33（8）： 78-84.
[14]	许思昂，李艺杰，梁桥康，等. 基于改进YOLOv5算法的 PCB裸板缺陷检测［J］.包装工程， 2022， 43（15）： 33-41.
	Xu Si-ang， Li Yi-jie， Liang Qiao-kang， et al. PCB bare board defect detection based on improved YOLOv5 algorithm ［J］. Packaging Engineering， 2022， 43（15）： 33-41.
[15]	Susa J A B， Mariquina E， Tria M L， et al. Cap-Eye-citor： a machine vision inference approach of capacitor detection for PCB automatic optical inspection［C］// IEEE 7th International Conference on Engineering Technologies and Applied Sciences （ICETAS）. Kuala Lumpur， 2020：1-5.
[16]	Xu S Y， Chen X L， Huang Y R， et al. Defect detection of substation instrumentation equipment based on improved YOLOv4 algorithm［C］// 2023 China Automation Congress （CAC）. Chongqing， 2023： 9091-9096.

模型	精度	召回率	mAP0.5∶0.95	参数量
YOLOv6	0.942	0.770	0.471	4 234 338
YOLOv8	0.915	0.829	0.481	3 006 818
YOLOv8_p2	0.926	0.839	0.498	2 921 832
YOLOv8_psa	0.935	0.867	0.491	3 181 317
YOLOv8_p2_psa	0.955	0.812	0.509	3 098 556

模型	精度	召回率	mAP0.5∶0.95	参数量
YOLOv6	0.942	0.770	0.471	4 234 338
YOLOv8	0.915	0.829	0.481	3 006 818
YOLOv8_p2	0.926	0.839	0.498	2 921 832
YOLOv8_psa	0.935	0.867	0.491	3 181 317
YOLOv8_p2_psa	0.955	0.812	0.509	3 098 556

瑕疵类别	YOLOv6	YOLOv8	YOLOv8_p2	YOLOv8_psa	YOLOv8_p2_psa
漏孔	0.667	0.626	0.661	0.657	0.667
鼠咬	0.406	0.464	0.422	0.448	0.464
开路	0.491	0.490	0.512	0.493	0.508
短路	0.467	0.507	0.511	0.520	0.529
杂散	0.376	0.386	0.442	0.379	0.439
杂铜	0.421	0.414	0.440	0.448	0.449

瑕疵类别	YOLOv6	YOLOv8	YOLOv8_p2	YOLOv8_psa	YOLOv8_p2_psa
漏孔	0.667	0.626	0.661	0.657	0.667
鼠咬	0.406	0.464	0.422	0.448	0.464
开路	0.491	0.490	0.512	0.493	0.508
短路	0.467	0.507	0.511	0.520	0.529
杂散	0.376	0.386	0.442	0.379	0.439
杂铜	0.421	0.414	0.440	0.448	0.449