Review of PCB Defect Detection Algorithm Based on Machine Vision

doi:10.3778/j.issn.1673-9418.2409061

Abstract

Abstract: Printed circuit board (PCB) as a core component of electronic products, its quality directly affects the reliability of the product. As electronic products move toward lighter, thinner, and more sophisticated, machine vision-based PCB defect detection faces challenges such as the difficulty of detecting tiny defects. In order to further study the PCB defect detection technology, the algorithms of each stage are discussed in detail according to the development history. Firstly, the main challenges in the field are pointed out, and traditional PCB defect detection methods and their limitations are introduced. Then, from the perspective of traditional machine learning and deep learning, this paper systematically reviews the PCB defect detection methods and their advantages and disadvantages in recent years. Next, this paper summarizes the commonly used evaluation indicators and mainstream datasets of PCB defect detection algorithms, compares the performance of the latest research methods on PCB-Defect, DeeP-PCB and HRIPCB datasets in the past three years, and analyzes the reasons for the differences. Finally, based on the current situation and the problems to be solved, the future development trend is prospected.

Key words: printed circuit board (PCB), defect detection, machine vision, machine learning, deep learning

摘要： 印刷电路板（PCB）作为电子产品的核心组成部分，其质量直接影响产品的可靠性。随着电子产品朝着更轻、更薄、更精密的方向发展，基于机器视觉的PCB缺陷检测面临诸如微小缺陷难以检测等挑战。为深入研究PCB缺陷检测技术，根据其发展历程对各阶段的算法进行了详细探讨。指出了该领域面临的主要挑战，并介绍了传统PCB缺陷检测方法及其局限性。从传统机器学习和深度学习两个角度系统回顾了近几年PCB缺陷检测所采用的方法及其优缺点。对PCB缺陷检测算法常用的评价指标和主流数据集进行了归纳，并对近三年在PCB-Defect、DeeP-PCB和HRIPCB三个数据集上的最新研究方法进行了性能比较，分析了产生差异化的原因。基于当前现状和亟待解决的问题，对未来的发展趋势进行了展望。

关键词: 印刷电路板（PCB）, 缺陷检测, 机器视觉, 机器学习, 深度学习

YANG Sinian, CAO Lijia, YANG Yang, GUO Chuandong. Review of PCB Defect Detection Algorithm Based on Machine Vision[J]. Journal of Frontiers of Computer Science and Technology, 2025, 19(4): 901-915.

杨思念, 曹立佳, 杨洋, 郭川东. 基于机器视觉的PCB缺陷检测算法研究综述[J]. 计算机科学与探索, 2025, 19(4): 901-915.

References

[1] PARK J H, KIM Y S, SEO H, et al. Analysis of training deep learning models for PCB defect detection[J]. Sensors, 2023, 23(5): 2766.
[2] LING Q, ISA N A M. Printed circuit board defect detection methods based on image processing, machine learning and deep learning: a survey[J]. IEEE Access, 2023, 11: 15921-15944.
[3] CHEN X, WU Y L, HE X Y, et al. A comprehensive review of deep learning-based PCB defect detection[J]. IEEE Access, 2023, 11: 139017-139038.
[4] SANKAR V U, LAKSHMI G, SANKAR Y S. A review of various defects in PCB[J]. Journal of Electronic Testing, 2022, 38(5): 481-491.
[5] 吴一全, 赵朗月, 苑玉彬, 等. 基于机器视觉的PCB缺陷检测算法研究现状及展望[J]. 仪器仪表学报, 2022, 43(8): 1-17.
WU Y Q, ZHAO L Y, YUAN Y B, et al. Research status and the prospect of PCB defect detection algorithm based on machine vision[J]. Chinese Journal of Scientific Instrument, 2022, 43(8): 1-17.
[6] CHEN I C, HWANG R, HUANG H C. PCB defect detection based on deep learning algorithm[J]. Processes, 2023, 11(3): 775.
[7] ZHOU Y B, YUAN M H, ZHANG J, et al. Review of vision-based defect detection research and its perspectives for printed circuit board[J]. Journal of Manufacturing Systems, 2023, 70: 557-578.
[8] TULBURE A A, TULBURE A A, DULF E H. A review on modern defect detection models using DCNNs-deep convolutional neural networks[J]. Journal of Advanced Research, 2022, 35: 33-48.
[9] LAKSHMI G, SANKAR V U, SANKAR Y S. A survey of PCB defect detection algorithms[J]. Journal of Electronic Testing, 2023, 39(5): 541-554.
[10] ZHANG F, QIAO N S, LI J F. A PCB photoelectric image edge information detection method[J]. Optik, 2017, 144: 642-646.
[11] 温悦欣. 基于机器视觉的PCB表面缺陷检测方法研究与系统实现[D]. 成都: 电子科技大学, 2020: 84.
WEN Y X. Research and system implementation of PCB surface defect detection method based on machine vision[D]. Chengdu: University of Electronic Science and Technology of China, 2020: 84.
[12] 廖鑫婷, 张洁, 吕盛坪. 融合浅层特征和注意力机制的PCB缺陷检测方法[J]. 计算机集成制造系统, 2024, 30(3): 1092-1104.
LIAO X T, ZHANG J, LYU S P. Defect detection for PCB by combining shallow features and attention mechanism[J]. Computer Integrated Manufacturing Systems, 2024, 30(3): 1092-1104.
[13] LI Y F, LI S Y. Defect detection of bare printed circuit boards based on gradient direction information entropy and uniform local binary patterns[J]. Circuit World, 2017, 43(4): 145-151.
[14] WANG S Y, ZHAO Y, WEN L Y. PCB welding spot detection with image processing method based on automatic threshold image segmentation algorithm and mathematical morphology[J]. Circuit World, 2016, 42(3): 97-103.
[15] FANG K. Threshold segmentation of PCB defect image grid based on finite difference dispersion for providing accuracy in the IoT based data of smart cities[J]. International Journal of System Assurance Engineering and Management, 2022, 13(1): 121-131.
[16] ZHU W B, GU H, SU W M. A fast PCB hole detection method based on geometric features[J]. Measurement Science and Technology, 2020, 31(9): 095402.
[17] RAIHAN F, CE W. PCB defect detection USING OPENCV with image subtraction method[C]//Proceedings of the 2017 International Conference on Information Management and Technology. Piscataway: IEEE, 2017: 204-209.
[18] ANNABY M H, FOUDA Y M, RUSHDI M A. Improved normalized cross-correlation for defect detection in printed-circuit boards[J]. IEEE Transactions on Semiconductor Manu-facturing, 2019, 32(2): 199-211.
[19] REN Z H, FANG F Z, YAN N, et al. State of the art in defect detection based on machine vision[J]. International Journal of Precision Engineering and Manufacturing-Green Technology, 2022, 9(2): 661-691.
[20] WU H. Solder joint defect classification based on ensemble learning[J]. Soldering & Surface Mount Technology, 2017, 29(3): 164-170.
[21] BANSAL M, GOYAL A, CHOUDHARY A. A comparative analysis of K-nearest neighbor, genetic, support vector machine, decision tree, and long short term memory algorithms in machine learning[J]. Decision Analytics Journal, 2022, 3: 100071.
[22] LIAO C T, LEE W H, LAI S H. A flexible PCB inspection system based on statistical learning[J]. Journal of Signal Processing Systems, 2012, 67(3): 279-290.
[23] YUK E H, PARK S H, PARK C S, et al. Feature-learning-based printed circuit board inspection via speeded-up robust features and random forest[J]. Applied Sciences, 2018, 8(6): 932.
[24] UR REHMAN S, THANG K F, LAI N S. Automated PCB identification and defect-detection system (APIDS)[J]. International Journal of Electrical and Computer Engineering, 2019, 9(1): 297.
[25] SONG J D, KIM Y G, PARK T H. SMT defect classification by feature extraction region optimization and machine learning[J]. The International Journal of Advanced Manufacturing Technology, 2019, 101(5): 1303-1313.
[26] CAI N, ZHOU Y, YE Q, et al. IC solder joint inspection via robust principle component analysis[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2017, 7(2): 300-309.
[27] EL BELGHITI ALAOUI N, CASSOU A, TOUNSI P, et al. Using infrared thermal responses for PCBA production tests: feasibility study[J]. Microelectronics Reliability, 2019, 100: 113354.
[28] SARKER I H. Deep learning: a comprehensive overview on techniques, taxonomy, applications and research directions[J]. SN Computer Science, 2021, 2(6): 420.
[29] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[30] YOU S Y. PCB defect detection based on generative adversarial network[C]//Proceedings of the 2022 2nd International Conference on Consumer Electronics and Computer Engineering. Piscataway: IEEE, 2022: 557-560.
[31] TSAI A C, TSOU C H, WANG J F. EESRGAN: efficient & effective super-resolution generative adversarial network[J]. IETE Technical Review, 2024, 41(2): 200-211.
[32] LIU Z H, HE P F, WANG F. PCB defect images super-resolution reconstruction based on improved SRGAN[J]. Applied Sciences, 2023, 13(11): 6786.
[33] LEDIG C, THEIS L, HUSZáR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2017: 105-114.
[34] LU Z W, WU C D, CHEN D Y, et al. Overview on image super resolution reconstruction[C]//Proceedings of the 26th Chinese Control and Decision Conference. Piscataway: IEEE, 2014: 2009-2014.
[35] AN K, ZHANG Y P. LPViT: a transformer based model for PCB image classification and defect detection[J]. IEEE Access, 2022, 10: 42542-42553.
[36] HAN X X, LI R P, WANG B Q, et al. Defect identification of bare printed circuit boards based on Bayesian fusion of multi-scale features[J]. PeerJ Computer Science, 2024, 10: e1900.
[37] YU X Y, LI H X, YANG H D. PCB defect detection model based on intrinsic feature decomposition and multilevel fusion against image uncertainty[J]. IEEE Sensors Journal, 2024, 24(12): 19497-19505.
[38] LI Y T, GUO J. A VGG-16 based faster RCNN model for PCB error inspection in industrial AOI applications[C]//Proceedings of the 2018 IEEE International Conference on Consumer Electronics. Piscataway: IEEE, 2018: 1-2.
[39] CHEN W, HUANG Z T, MU Q, et al. PCB defect detection method based on transformer-YOLO[J]. IEEE Access, 2022, 10: 129480-129489.
[40] LIU Z, HU H, LIN Y T, et al. Swin transformer V2: scaling up capacity and resolution[C]//Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE, 2022: 11999-12009.
[41] 庹冰, 黄丽雯, 唐鑫, 等. 基于YOLOX-WSC的PCB缺陷检测算法研究[J]. 计算机工程与应用, 2023, 59(10): 236-243.
TUO B, HUANG L W, TANG X, et al. Research on PCB defect detection algorithm based on YOLOX-WSC[J]. Com-puter Engineering and Applications, 2023, 59(10): 236-243.
[42] 苏佳, 贾泽, 秦一畅, 等. 面向工业表面缺陷检测的改进YOLOv8算法[J]. 计算机工程与应用, 2024, 60(14): 187-196.
SU J, JIA Z, QIN Y C, et al. Improved YOLOv8 algorithm for industrial surface defect detection[J]. Computer Engineering and Applications, 2024, 60(14): 187-196.
[43] YU J B, ZHAO L X, WANG Y S, et al. Defect detection of printed circuit board based on adaptive key-points localization network[J]. Computers & Industrial Engineering, 2024, 193: 110258.
[44] ZHANG Y, XIE F, HUANG L, et al. A lightweight one-stage defect detection network for small object based on dual attention mechanism and PAFPN[J]. Frontiers in Physics, 2021, 9:708097.
[45] LI J, LI W Y, CHEN Y Q, et al. Research on object detection of PCB assembly scene based on effective receptive field anchor allocation[J]. Computational Intelligence and Neuroscience, 2022(1): 7536711.
[46] WANG X, GAO J S, HOU B J, et al. A lightweight modified YOLOX network using coordinate attention mechanism for PCB surface defect detection[J]. IEEE Sensors Journal, 2022, 22(21): 20910-20920.
[47] 杨永跃, 夏远超. PCB缺陷检测深度学习算法的精度改进[J]. 电子测量与仪器学报, 2023, 37(5): 11-19.
YANG Y Y, XIA Y C. Accuracy improvement of deep learning algorithm for PCB defect detection[J]. Journal of Electronic Measurement and Instrumentation, 2023, 37(5): 11-19.
[48] LIU T H, CAO G Z, HE Z S, et al. Refined defect detector with deformable transformer and pyramid feature fusion for PCB detection[J]. IEEE Transactions on Instrumentation and Measurement, 2023, 73: 5001111.
[49] CHENG G, HAN J W. A survey on object detection in optical remote sensing images[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 117: 11-28.
[50] BAI J, REN J J, YANG Y J, et al. Object detection in large-scale remote-sensing images based on time-frequency analysis and feature optimization[J]. IEEE Transactions on Geoscience and Remote Sensing, 2021, 60: 5405316.
[51] LIN T Y, MAIRE M, BELONGIE S, et al. Microsoft COCO: common objects in context[C]//Proceedings of the 13th European Conference on Computer Vision. Cham: Springer, 2014: 740-755.
[52] BOCHKOVSKIY A, WANG C Y, LIAO H M. YOLOv4: optimal speed and accuracy of object detection[EB/OL]. [2024-06-14]. https://arxiv.org/abs/2004.10934.
[53] LU H W, MEHTA D, PARADIS O P, et al. FICS-PCB: a multi-modal image dataset for automated printed circuit board visual inspection[J]. IACR Cryptology ePrint Archive, 2020: 366.
[54] PRAMERDORFER C, KAMPEL M. A dataset for computer-vision-based PCB analysis[C]//Proceedings of the 2015 14th IAPR International Conference on Machine Vision Applications. Piscataway: IEEE, 2015: 378-381.
[55] MAHALINGAM G, GAY K M, RICANEK K. PCB-METAL: a PCB image dataset for advanced computer vision machine learning component analysis[C]//Proceedings of the 2019 16th International Conference on Machine Vision Applications. Piscataway: IEEE, 2019: 1-5.
[56] TANG S L, HE F, HUANG X L, et al. Online PCB defect detector on a new PCB defect dataset[EB/OL]. [2024-06-14]. https://arxiv.org/abs/1902.06197.
[57] HUANG W B, WEI P, ZHANG M H, et al. HRIPCB: a challenging dataset for PCB defects detection and classification[J]. The Journal of Engineering, 2020(13): 303-309.
[58] HUANG W B, WEI P. A PCB dataset for defects detection and classification[EB/OL]. [2024-06-14]. https://arxiv.org/abs/1901.08204.
[59] YU X Y, LYU W T, ZHOU D, et al. ES-Net: efficient scale-aware network for tiny defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 3511314.
[60] ZHOU G A, YU L J, SU Y X, et al. Lightweight PCB defect detection algorithm based on MSD-YOLO[J]. Cluster Computing, 2024, 27(3): 3559-3573.
[61] WANG H D, XIE J, XU X Y, et al. Few-shot PCB surface defect detection based on feature enhancement and multi-scale fusion[J]. IEEE Access, 2022, 10: 129911-129924.
[62] ZHANG L X, CHEN J S, CHEN J G, et al. LDD-Net: lightweight printed circuit board defect detection network fusing multi-scale features[J]. Engineering Applications of Artificial Intelligence, 2024, 129: 107628.
[63] LI C J, QU Z, WANG S Y, et al. A method of defect detection for focal hard samples PCB based on extended FPN model[J]. IEEE Transactions on Components, Packaging and Manufacturing Technology, 2022, 12(2): 217-227.
[64] LIU Q, LIU M, JONATHAN Q M, et al. A real-time anchor-free defect detector with global and local feature enhancement for surface defect detection[J]. Expert Systems with Applications, 2024, 246: 123199.
[65] 朱红艳, 李泽平, 赵勇, 等. 基于多尺度融合和可变形卷积PCB缺陷检测算法[J]. 计算机工程与设计, 2022, 43(8): 2188-2196.
ZHU H Y, LI Z P, ZHAO Y, et al. PCB defect detection algorithm based on multi-scale fusion and deformable convolution[J]. Computer Engineering and Design, 2022, 43(8): 2188-2196.
[66] XIA K W, LV Z L, LIU K, et al. Global contextual attention augmented YOLO with ConvMixer prediction heads for PCB surface defect detection[J]. Scientific Reports, 2023, 13(1): 9805.
[67] CHEN G D, XU F, LIU G H, et al. ESDDNet: efficient small defect detection network of workpiece surface[J]. Measurement Science and Technology, 2022, 33(10): 105007.
[68] YE M, WANG H, XIAO H. Light-YOLOv5: a lightweight algorithm for improved YOLOv5 in PCB defect detection[C]//Proceedings of the 2023 IEEE 2nd International Conference on Electrical Engineering, Big Data and Algorithms. Piscataway: IEEE, 2023: 523-528.
[69] ZHU P K, CAI Y W, LI F, et al. A deep learning method for PCB defect detection based on improved Yolov8[C]//Proceedings of the 2024 International Conference on Computer Vision and Deep Learning. New York: ACM, 2024: 1-7.
[70] LI G Y, LIAO X F, SU X C, et al. PCB defect detection based on improved YOLOX algorithm[C]//Proceedings of the 2023 5th International Conference on Electrical Engineering and Control Technologies. Piscataway: IEEE, 2023: 380-384.
[71] SHAO R, ZHOU M L, LI M, et al. TD-Net: tiny defect detection network for industrial products[J]. Complex & Intelligent Systems, 2024, 10(3): 3943-3954.
[72] XU Y H, HUO H. DSASPP: depthwise separable atrous spatial pyramid pooling for PCB surface defect detection[J]. Electronics, 2024, 13(8): 1490.
[73] WU Y X, ZHENG L M, CHEN E Z. EEMNet: an end-to-end efficient model for PCB surface tiny defect detection[J]. International Journal of Machine Learning and Cybernetics, 2024, 15(12): 5579-5594.
[74] 陈俊英, 李朝阳, 席月芸, 等. ViT和注意力融合的类别不均衡PCB缺陷检测方法[J]. 仪器仪表学报, 2024, 45(4): 294-306.
CHEN J Y, LI Z Y, XI Y Y, et al. ViT and attention fusion for class-imbalanced PCB defect detection[J]. Chinese Journal of Scientific Instrument, 2024, 45(4): 294-306.
[75] ZHOU W, LI C Y, YE Z W, et al. An efficient tiny defect detection method for PCB with improved YOLO through a compression training strategy[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 2003514.
[76] XIAO G S, HOU S L, ZHOU H Y. PCB defect detection algorithm based on CDI-YOLO[J]. Scientific Reports, 2024, 14(1): 7351.
[77] TANG J L, LIU S B, ZHAO D X, et al. PCB-YOLO: an improved detection algorithm of PCB surface defects based on YOLOv5[J]. Sustainability, 2023, 15(7): 5963.
[78] YUAN Z H, TANG X Y, NING H, et al. LW-YOLO: lightweight deep learning model for fast and precise defect detection in printed circuit boards[J]. Symmetry, 2024, 16(4): 418.
[79] YU Z L, WU Y X, WEI B Q, et al. A lightweight and efficient model for surface tiny defect detection[J]. Applied Intelligence, 2023, 53(6): 6344-6353.
[80] WAN Y S, GAO L, LI X Y, et al. Semi-supervised defect detection method with data-expanding strategy for PCB quality inspection[J]. Sensors, 2022, 22(20): 7971.
[81] DU B W, WAN F, LEI G B, et al. YOLO-MBBi: PCB surface defect detection method based on enhanced YOLOv5[J]. Electronics, 2023, 12(13): 2821.
[82] FENG B X, CAI J P. PCB defect detection via local detail and global dependency information[J]. Sensors, 2023, 23(18): 7755.
[83] XIE Y F, HU W T, XIE S W, et al. Surface defect detection algorithm based on feature-enhanced YOLO[J]. Cognitive Computation, 2023, 15(2): 565-579.
[84] YU H Z, LIN Q S, LIU C L. Design and implementation of embedded PCB defect detection system based on FPGA[C]//Proceedings of the 2023 IEEE 7th Information Technology and Mechatronics Engineering Conference. Piscataway: IEEE, 2023: 530-535.
[85] CHEN C L, WU Q M, ZHANG J, et al. U2D2PCB: uncertainty-aware unsupervised defect detection on PCB images using reconstructive and discriminative models[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 5017710.
[86] 张莹, 邓华宣, 王耀南, 等. 基于多通道特征融合学习的印制电路板小目标缺陷检测[J]. 仪器仪表学报, 2024, 45(5): 10-19.
ZHANG Y, DENG H X, WANG Y N, et al. Small defects detection of PCB based on multi-channel feature fusion learning[J]. Chinese Journal of Scientific Instrument, 2024, 45(5): 10-19.
[87] 王健, 肖迪, 冯李航, 等. 基于改进YOLOv8s的PCB小目标缺陷检测模型[J/OL]. 计算机工程与应用(2024-08-20)[2024-09-27]. http://kns.cnki.net/kcms/detail/11.2127.tp.20240819. 1152.016.html.
WANG J, XIAO D, FENG L H, et al. PCB small target defect detection model based on improved YOLOv8s[J/OL]. Computer Engineering and Applications (2024-08-20)[2024-09-27]. http://kns.cnki.net/kcms/detail/11.2127.tp.20240819. 1152.016.html.
[88] BHATTACHARYA A, CLOUTIER S G. End-to-end deep learning framework for printed circuit board manufacturing defect classification[J]. Scientific Reports, 2022, 12(1): 12559.
[89] LEI L, LI H X, YANG H D. Multiscale convolution-based probabilistic classification for detecting bare PCB defects[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 72: 3503108.
[90] LIM J, LIM J, BASKARAN V M, et al. A deep context learning based PCB defect detection model with anomalous trend alarming system[J]. Results in Engineering, 2023, 17: 100968.
[91] CHEN W X, MENG S M, WANG X P. Local and global context-enhanced lightweight CenterNet for PCB surface defect detection[J]. Sensors, 2024, 24(14): 4729.
[92] VAKILI E, KARIMIAN G, SHOARAN M, et al. Valid-IoU: an improved IoU-based loss function and its application to detection of defects on printed circuit boards[J]. Multimedia Tools and Applications, 2024. DOI: 10.1007/s11042-024-19482-4.
[93] LIU L J, ZHANG Y, KARIMIC H R. Defect detection of printed circuit board surface based on an improved YOLOv8 with FasterNet backbone algorithms[EB/OL]. (2024-08-30)[2024-09-14]. https://www.researchsquare.com/article/rs-4823049/v1.
[94] LI Z Y, LI A M, ZHANG Y C, et al. BEW-YOLO: an improved method for PCB defect detection based on YOLOv7[C]//Proceedings of the 2023 IEEE 29th International Conference on Parallel and Distributed Systems. Piscataway: IEEE, 2023: 268-274.
[95] LING Q, ISA N A M. TD-YOLO: a lightweight detection algorithm for tiny defects in high-resolution PCBs[J]. Advanced Theory and Simulations, 2024, 7(4): 2300971.
[96] YUAN M H, ZHOU Y B, REN X Y, et al. YOLO-HMC: an improved method for PCB surface defect detection[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 2001611.