{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T16:47:44Z","timestamp":1791996464673,"version":"4.4.0"},"reference-count":33,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T00:00:00Z","timestamp":1744934400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>Aiming at the problems of low accuracy and large computation in the task of PCB defect detection. This paper proposes a lightweight PCB defect detection algorithm based on YOLO. To address the problem of large numbers of parameters and calculations, GhostNet are used in Backbone to keep the model lightweight. Second, the ordinary convolution of the neck network is improved by depthwise separable convolution, resulting in a reduction of redundant parameters within the neck network. Afterwards, the Swin-Transformer is integrated with the C3 module in the Neck to build the C3STR module, which aims to address the issue of cluttered background in defective images and the confusion caused by simple defect types. Finally, the PANet network structure is replaced with the bidirectional feature pyramid network (BIFPN) structure to enhance the fusion of multi-scale features in the network. The results indicated that when comparing our model with the original model, there was a 47.2% reduction in the model\u2019s parameter count, a 48.5% reduction in GFLOPs, a 42.4% reduction in Weight, a 2.0% reduction in FPS, and a 2.4% rise in mAP. The model is better suited for use on low-arithmetic platforms as a result.<\/jats:p>","DOI":"10.1371\/journal.pone.0320344","type":"journal-article","created":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:25:36Z","timestamp":1744997136000},"page":"e0320344","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":16,"title":["A lightweight detection algorithm of PCB surface defects based on YOLO"],"prefix":"10.1371","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7359-9160","authenticated-orcid":true,"given":"Shiwei","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoqiang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linhua","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jikui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,4,18]]},"reference":[{"issue":"21","key":"pone.0320344.ref001","doi-asserted-by":"crossref","first-page":"20910","DOI":"10.1109\/JSEN.2022.3208580","article-title":"A lightweight modified YOLOX network using coordinate attention mechanism for PCB surface defect detection","volume":"22","author":"W Xuan","year":"2022","journal-title":"IEEE Sensors J"},{"key":"pone.0320344.ref002","doi-asserted-by":"crossref","first-page":"113611","DOI":"10.1016\/j.measurement.2023.113611","article-title":"PCB defect detection with self-supervised learning of local image patches","volume":"222","author":"N Yao","year":"2023","journal-title":"Measurement"},{"key":"pone.0320344.ref003","first-page":"1","article-title":"Collaborative learning classification model for PCBs defect detection against image and label uncertainty","volume":"72","author":"X Yu","year":"2023","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"pone.0320344.ref004","article-title":"Fast PCB defect detection method based on FasterNet backbone network and CBAM attention mechanism integrated with feature fusion module in improved YOLOv7","author":"B Chen","year":"2023","journal-title":"IEEE Access"},{"key":"pone.0320344.ref005","first-page":"1552","article-title":"A new path planning method for flying probe test arms","author":"W Li","journal-title":"2020 Chinese Control And Decision Conference (CCDC)"},{"key":"pone.0320344.ref006","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"},{"key":"pone.0320344.ref007","doi-asserted-by":"crossref","unstructured":"Onshaunjit J, Srinonchat J. Algorithmic Scheme for Concurrent Detection and Classification of Printed Circuit Board Defects[J]. Computers, Materials & Continua. 2022;71(1).","DOI":"10.32604\/cmc.2022.017698"},{"key":"pone.0320344.ref008","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1109\/CCAA.2015.7148363","article-title":"A novel approach of standard data base generation for defect detection in bare PCB","author":"M Kumar","year":"2015","journal-title":"Proceedings of the International Conference on Computing, Communication & Automation"},{"key":"pone.0320344.ref009","doi-asserted-by":"crossref","first-page":"109908","DOI":"10.1109\/ACCESS.2022.3214306","article-title":"Printed circuit boards defect detection method based on improved fully convolutional networks","volume":"10","author":"J Zheng","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0320344.ref010","doi-asserted-by":"crossref","unstructured":"Kuo CW, Ashmore JD, Huggins D, et al. Data-efficient graph embedding learning for PCB component detection[C]\/\/2019 IEEE winter conference on applications of computer vision (WACV). IEEE. 2019;551-60.","DOI":"10.1109\/WACV.2019.00064"},{"key":"pone.0320344.ref011","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1016\/j.wasman.2021.03.017","article-title":"A deep convolutional neural network to simultaneously localize and recognize waste types in images","volume":"126","author":"S Liang","year":"2021","journal-title":"Waste Manag"},{"key":"pone.0320344.ref012","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.wasman.2020.04.041","article-title":"Application of deep learning object classifier to improve e-waste collection planning","volume":"109","author":"P Nowakowski","year":"2020","journal-title":"Waste Manag"},{"key":"pone.0320344.ref013","first-page":"580","article-title":"Rich feature hierarchies for accurate object detection and semantic segmentation","author":"R Girshick","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref014","first-page":"283","article-title":"A PCB defect detection algorithm with improved Faster R-CNN","author":"J Niu","year":"2022","journal-title":"Proceedings of ICBASE"},{"issue":"1","key":"pone.0320344.ref015","first-page":"1","article-title":"A small-sized object detection oriented multi-scale feature fusion approach with application to defect detection","volume":"71","author":"N Zeng","year":"2022","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"pone.0320344.ref016","doi-asserted-by":"crossref","first-page":"115673","DOI":"10.1016\/j.eswa.2021.115673","article-title":"CS-ResNet: Cost-sensitive residual convolutional neural network for PCB cosmetic defect detection","volume":"185","author":"H Zhang","year":"2021","journal-title":"Expert Systems with Applications"},{"key":"pone.0320344.ref017","first-page":"779","article-title":"You only look once: Unified, real-time object detection","author":"J Redmon","year":"2019","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref018","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1007\/978-3-319-46448-0_2","article-title":"Ssd: Single shot multibox detector","author":"W Liu","year":"2016","journal-title":"Computer Vision\u2013ECCV 2016: 14th European Conference"},{"issue":"18","key":"pone.0320344.ref019","doi-asserted-by":"crossref","first-page":"3750","DOI":"10.3390\/app9183750","article-title":"Application Research of Improved YOLO V3 Algorithm in PCB Electronic Component Detection","volume":"9","author":"J Li","year":"2019","journal-title":"Applied Sciences"},{"key":"pone.0320344.ref020","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":"JY Lim","year":"2023","journal-title":"Results in Engineering"},{"key":"pone.0320344.ref021","doi-asserted-by":"crossref","unstructured":"Chen W, Huang Z, Mu Q, et al. PCB defect detection method based on transformer-YOLO[J]. IEEE Access. 2022;10:129480-9.","DOI":"10.1109\/ACCESS.2022.3228206"},{"key":"pone.0320344.ref022","doi-asserted-by":"crossref","first-page":"106359","DOI":"10.1016\/j.engappai.2023.106359","article-title":"PCB defects target detection combining multi-scale and attention mechanism","volume":"123","author":"W Jiang","year":"2023","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"pone.0320344.ref023","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"A Howard","year":"2017","journal-title":"arXiv preprint"},{"key":"pone.0320344.ref024","first-page":"116","article-title":"Shufflenet v2: Practical guidelines for efficient cnn architecture design","author":"N Ma","journal-title":"Proceedings of the European Conference on Computer Vision (ECCV)"},{"key":"pone.0320344.ref025","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1016\/j.neunet.2023.08.053","article-title":"Efficient and accurate compound scaling for convolutional neural networks","volume":"167","author":"C Lin","year":"2023","journal-title":"Neural Netw"},{"key":"pone.0320344.ref026","article-title":"Contextnet: Exploring context and detail for semantic segmentation in real-time","author":"RPK Poudel","year":"2018","journal-title":"arXiv preprint"},{"key":"pone.0320344.ref027","first-page":"392","article-title":"A hierarchical graph network for 3D object detection on point clouds","author":"J Chen","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref028","first-page":"1580","article-title":"Ghostnet: More features from cheap operations","author":"K Han","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref029","first-page":"1251","article-title":"Xception: Deep learning with depthwise separable convolutions","volume":"2017","author":"F Chollet","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref030","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Z Liu","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"pone.0320344.ref031","first-page":"2117","article-title":"Feature pyramid networks for object detection","author":"T Lin","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"pone.0320344.ref032","first-page":"8759","article-title":"Path aggregation network for instance segmentation","author":"S Liu","year":"2018","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"issue":"2","key":"pone.0320344.ref033","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1049\/trit.2019.0019","article-title":"TDD\u2010net: a tiny defect detection network for printed circuit boards","volume":"4","author":"R Ding","year":"2019","journal-title":"CAAI Transactions on Intelligence Technology"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,18]],"date-time":"2025-04-18T17:25:50Z","timestamp":1744997150000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0320344"}},"subtitle":[],"editor":[{"given":"Azim","family":"Uddin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,18]]},"references-count":33,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,18]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0320344","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,18]]}}}