{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:50:25Z","timestamp":1792788625938,"version":"4.5.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"3","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Nature Science Foundation of China","doi-asserted-by":"crossref","award":["62205168"],"award-info":[{"award-number":["62205168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Fujian Province of China","award":["2024J01887"],"award-info":[{"award-number":["2024J01887"]}]},{"name":"Advanced Equipment Manufacturing Project of Putian City of China","award":["2023GJGZ002"],"award-info":[{"award-number":["2023GJGZ002"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>To address the challenges of inadequate feature representation for small objects and slow model convergence in printed circuit board (PCB) defect detection, this paper proposes an improved YOLOv10 algorithm and develops a real-time detection system with a co-optimized hardware and software architecture. The efficient channel attention (ECA) mechanism is used to enhance the ability of the model to extract key channel features; the dynamic snake convolution (DSConv) in the backbone strengthens the model\u2019s capacity to recognize the geometric structures of small targets through deformable kernels and multi-directional feature fusion; the Focaler-CIoU loss emphasizes samples with low intersection over union (IoU) values to boost hard sample learning and improve convergence efficiency. To simulate real-world industrial environments, multiple data augmentation strategies are utilized to expand the PKU-Market-PCB dataset, thereby enhancing the model\u2019s generalization and robustness in complex scenarios. Experimental results demonstrate that the proposed EDF-YOLOv10 achieves mAP@0.50 of 90.6% and mAP@0.50:0.95 of 48.4% on the experimental dataset, representing improvements of 3.0 and 1.6 percentage points over the baseline, respectively. Furthermore, We also develope a real-time interactive detection system for identifying PCB defects. This system utilizes industrial cameras, a controllable light source, and a graphical user interface developed with the PyQt5 framework, employing the EDF-YOLOv10 model. Our approach serves as a methodological reference for detecting PCB defects in complex industrial environments.<\/jats:p>","DOI":"10.1371\/journal.pone.0343130","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:29:30Z","timestamp":1772821770000},"page":"e0343130","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":3,"title":["Defect detection method of printed circuit boards based on EDF-YOLOv10"],"prefix":"10.1371","volume":"21","author":[{"given":"Zhijuan","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonger","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0955-0442","authenticated-orcid":true,"given":"Yiqing","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijun","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"issue":"7","key":"pone.0343130.ref001","doi-asserted-by":"crossref","first-page":"5963","DOI":"10.3390\/su15075963","article-title":"PCB-YOLO: An improved detection algorithm of PCB surface defects based on YOLOv5","volume":"15","author":"JL Tang","year":"2023","journal-title":"Sustainability"},{"issue":"11","key":"pone.0343130.ref002","doi-asserted-by":"crossref","first-page":"12207","DOI":"10.1109\/TPEL.2020.2984055","article-title":"A review of traditional helical to recent miniaturized printed circuit board rogowski coils for power-electronic applications","volume":"35","author":"Y Shi","year":"2020","journal-title":"IEEE Trans Power Electron"},{"issue":"4","key":"pone.0343130.ref003","first-page":"901","article-title":"Review of PCB defect detection algorithm based on machine vision","volume":"19","author":"SN Yang","year":"2025","journal-title":"Journal of Frontiers of Computer Science and Technology"},{"issue":"8","key":"pone.0343130.ref004","first-page":"1","article-title":"Research status and the prospect of PCB defect detection algorithm based on machine vision","volume":"43","author":"YQ Wu","year":"2022","journal-title":"Chinese Journal of Scientific Instruments"},{"issue":"3","key":"pone.0343130.ref005","first-page":"65","article-title":"A DRM-YOLOv8n algorithm for PCB defect detection","volume":"46","author":"J Zhou","year":"2025","journal-title":"Laser Journal"},{"key":"pone.0343130.ref006","doi-asserted-by":"crossref","first-page":"139017","DOI":"10.1109\/ACCESS.2023.3339561","article-title":"A comprehensive review of deep learning-based PCB defect detection","volume":"11","author":"X Chen","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0343130.ref007","doi-asserted-by":"crossref","first-page":"557","DOI":"10.1016\/j.jmsy.2023.08.019","article-title":"Review of vision-based defect detection research and its perspectives for printed circuit board","volume":"70","author":"Y Zhou","year":"2023","journal-title":"Journal of Manufacturing Systems"},{"issue":"3","key":"pone.0343130.ref008","doi-asserted-by":"crossref","first-page":"775","DOI":"10.3390\/pr11030775","article-title":"PCB defect detection based on deep learning algorithm","volume":"11","author":"I-C Chen","year":"2023","journal-title":"Processes"},{"issue":"1","key":"pone.0343130.ref009","doi-asserted-by":"crossref","first-page":"015434","DOI":"10.1088\/1361-6501\/ad9ca3","article-title":"Process planning of repairing and grinding for cylindrical parts based on surface defect detection","volume":"36","author":"Z Yu","year":"2024","journal-title":"Meas Sci Technol"},{"key":"pone.0343130.ref010","doi-asserted-by":"crossref","first-page":"113201","DOI":"10.1016\/j.ymssp.2025.113201","article-title":"Improved mode decomposition method for vibration signal denoising of aero-engine shaft bearing","volume":"238","author":"H Sun","year":"2025","journal-title":"Mechanical Systems and Signal Processing"},{"issue":"12","key":"pone.0343130.ref011","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1080\/0305215X.2024.2308555","article-title":"Topology optimization for cold plate using neural networks as proxy models","volume":"56","author":"Z Song","year":"2024","journal-title":"Engineering Optimization"},{"key":"pone.0343130.ref012","doi-asserted-by":"crossref","first-page":"103807","DOI":"10.1016\/j.micpro.2020.103807","article-title":"Machine vision based online detection of PCB defect","volume":"82","author":"Z Liu","year":"2021","journal-title":"Microprocessors and Microsystems"},{"issue":"6","key":"pone.0343130.ref013","doi-asserted-by":"crossref","first-page":"16363","DOI":"10.1007\/s11042-023-16218-8","article-title":"Printed circuit board inspection using computer vision","volume":"83","author":"A Rajesh","year":"2023","journal-title":"Multimed Tools Appl"},{"key":"pone.0343130.ref014","doi-asserted-by":"crossref","first-page":"108335","DOI":"10.1109\/ACCESS.2020.3001349","article-title":"Detection of PCB surface defects with improved faster-RCNN and feature pyramid network","volume":"8","author":"B Hu","year":"2020","journal-title":"IEEE Access"},{"issue":"15","key":"pone.0343130.ref015","doi-asserted-by":"crossref","first-page":"4968","DOI":"10.3390\/s21154968","article-title":"Printed circuit board defect detection using deep learning via a skip-connected convolutional autoencoder","volume":"21","author":"J Kim","year":"2021","journal-title":"Sensors (Basel)"},{"key":"pone.0343130.ref016","doi-asserted-by":"crossref","first-page":"100968","DOI":"10.1016\/j.rineng.2023.100968","article-title":"A deep context learning based PCB defect detection model with anomalous trend alarming system","volume":"17","author":"J Lim","year":"2023","journal-title":"Results in Engineering"},{"issue":"1","key":"pone.0343130.ref017","doi-asserted-by":"crossref","first-page":"7351","DOI":"10.1038\/s41598-024-57491-3","article-title":"PCB defect detection algorithm based on CDI-YOLO","volume":"14","author":"G Xiao","year":"2024","journal-title":"Sci Rep"},{"issue":"10","key":"pone.0343130.ref018","first-page":"171","article-title":"A defect detection method for PCB based on the improved YOLOv4","volume":"42","author":"JG Wu","year":"2021","journal-title":"Chinese Journal of Scientific Instrument"},{"issue":"10","key":"pone.0343130.ref019","first-page":"141","article-title":"Multi-Scale fusion optimization algorithm for printed circuit board defect detection","volume":"62","author":"K Mao","year":"2025","journal-title":"Laser and Optoelectronics Progress"},{"issue":"8","key":"pone.0343130.ref020","first-page":"1","article-title":"A PCB dataset for defects detection and classification","volume":"14","author":"WB Huang","year":"2018","journal-title":"Journal of Latex Class Files"},{"key":"pone.0343130.ref021","first-page":"107984","article-title":"YOLOv10: Real-time end-to-end object detection","author":"H Chen","year":"2024"},{"issue":"2","key":"pone.0343130.ref022","doi-asserted-by":"crossref","DOI":"10.1007\/s11554-025-01664-4","article-title":"FDDC-YOLO: an efficient detection algorithm for dense small-target solder joint defects in PCB inspection","volume":"22","author":"H Zheng","year":"2025","journal-title":"J Real-Time Image Proc"},{"key":"pone.0343130.ref023","doi-asserted-by":"crossref","first-page":"112776","DOI":"10.1016\/j.measurement.2023.112776","article-title":"RDD-YOLO: A modified YOLO for detection of steel surface defects","volume":"214","author":"C Zhao","year":"2023","journal-title":"Measurement"},{"key":"pone.0343130.ref024","doi-asserted-by":"crossref","unstructured":"Wang QL, Wu BG, Zhu PF, Li PH, Zuo WM, Hu QH. ECA-Net: Efficient channel attention for deep convolutional neural networks. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 2020. 11534\u201342.","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"pone.0343130.ref025","doi-asserted-by":"crossref","unstructured":"Qi YL, He YT, Qi XM, Zhang Y, Yang GY. Dynamic snake convolution based on topological geometric constraints for tubular structure segmentation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2023. 6070\u20139.","DOI":"10.1109\/ICCV51070.2023.00558"},{"issue":"8","key":"pone.0343130.ref026","doi-asserted-by":"crossref","first-page":"8574","DOI":"10.1109\/TCYB.2021.3095305","article-title":"Enhancing geometric factors in model learning and inference for object detection and instance segmentation","volume":"52","author":"Z Zheng","year":"2022","journal-title":"IEEE Trans Cybern"},{"key":"pone.0343130.ref027","unstructured":"Zhang H, Zhang SJ. Focaler-iou: More focused intersection over union loss. 2024. https:\/\/doi.org\/10.2401\/10525"},{"key":"pone.0343130.ref028","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1016\/j.neucom.2022.07.042","article-title":"Focal and efficient IOU loss for accurate bounding box regression","volume":"506","author":"Y-F Zhang","year":"2022","journal-title":"Neurocomputing"},{"key":"pone.0343130.ref029","unstructured":"Gevorgyan Z. SIoU loss: More powerful learning for bounding box regression. 2022. 12740."},{"key":"pone.0343130.ref030","unstructured":"Zhang H, Zhang SJ. Shape-IoU: more accurate metric considering bounding box shape and scale. 2023. 17663."},{"key":"pone.0343130.ref031","unstructured":"Tang SL, He F.; Huang XL, Yang J. Online PCB defect detector on a new PCB defect dataset. 2019."},{"key":"pone.0343130.ref032","author":"J Redmon","year":"2018"},{"key":"pone.0343130.ref033","unstructured":"Li CY, Li LL, Jiang HL, Weng KH, Geng YF, Li L, et al. YOLOv6: a single-stage object detection framework for industrial applications. 2022. 02976."},{"key":"pone.0343130.ref034","first-page":"7464","article-title":"YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors","author":"C-Y Wang","year":"2023"},{"key":"pone.0343130.ref035","author":"Z Ge","year":"2021"},{"key":"pone.0343130.ref036","unstructured":"Zhu XZ, Su WJ, Lu LW, Li B, Wang XG, Dai JF. Deformable detr: Deformable transformers for end-to-end object detection. 2020. https:\/\/arxiv.org\/abs\/2010.04159"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:29:36Z","timestamp":1772821776000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0343130"}},"subtitle":[],"editor":[{"given":"Muhammad E. S.","family":"Elrabaa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":36,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0343130","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]}}}