{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T16:46:55Z","timestamp":1793724415301,"version":"4.6.1"},"reference-count":37,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T00:00:00Z","timestamp":1706140800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100013254","name":"National College Students Innovation and Entrepreneurship Training Program","doi-asserted-by":"publisher","award":["202211528034"],"award-info":[{"award-number":["202211528034"]}],"id":[{"id":"10.13039\/501100013254","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>An essential industrial application is the examination of surface flaws in hot-rolled steel strips. While automatic visual inspection tools must meet strict real-time performance criteria for inspecting hot-rolled steel strips, their capabilities are constrained by the accuracy and processing speed of the algorithm used to identify defects. To solve the problems of poor detection accuracy, low detection efficiency, and unsuitability of low computing power platforms of the hot-rolled strip surface defect detection algorithm The Swin-Transformer-YOLOv5 model based on the improved one-stage detector is proposed. By employing GhostNet, the model\u2019s lightweight design, and guaranteed detection accuracy are both achieved. The C3 module introduces Swin-Transformer to address the issues of cluttered backdrops of defect photos and easily confused defect categories. With the addition of the CoordAttention module, the model\u2019s capacity to extract defective features is improved, and its performance keeps getting better. The issue of huge differences in different scales and poor detection of small flaws is resolved by employing BiFPN for feature fusion, and the detector\u2019s capacity to adapt to targets of different scales is improved. The experimental results demonstrate that the improved Swin-Transformer-Yolov5 model significantly outperforms the industry-standard target detection algorithms, and the model\u2019s mAP value still improves by 8.39% over the original model while reducing the number of parameters, GFLOPs, and weight by 36.6%, 40.0%, and 34.7%, respectively. The model is better suited for use on low-arithmetic platforms as a result.<\/jats:p>","DOI":"10.1371\/journal.pone.0292082","type":"journal-article","created":{"date-parts":[[2024,1,25]],"date-time":"2024-01-25T13:27:05Z","timestamp":1706189225000},"page":"e0292082","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":17,"title":["Swin-Transformer -YOLOv5 for lightweight hot-rolled steel strips surface defect detection algorithm"],"prefix":"10.1371","volume":"19","author":[{"given":"Qiuyan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6730-8367","authenticated-orcid":true,"given":"Haibing","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haoyue","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,1,25]]},"reference":[{"key":"pone.0292082.ref001","first-page":"1478","article-title":"Intelligent detection of steel defects based on improved split attention networks","volume":"9","author":"Z Hao","year":"2022","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"pone.0292082.ref002","doi-asserted-by":"crossref","first-page":"17","DOI":"10.3390\/coatings13010017","article-title":"Steel surface defect recognition: A survey","volume":"13","author":"X Wen","year":"2023","journal-title":"Coatings"},{"key":"pone.0292082.ref003","doi-asserted-by":"crossref","first-page":"1468","DOI":"10.1111\/mice.12792","article-title":"Dual attention deep learning network for automatic steel surface defect segmentation","volume":"37","author":"Y Pan","year":"2022","journal-title":"Computer\u2010Aided Civil and Infrastructure Engineering"},{"key":"pone.0292082.ref004","doi-asserted-by":"crossref","first-page":"110364","DOI":"10.1016\/j.measurement.2021.110364","article-title":"Surface damage detection of steel plate with different depths based on Lamb wave","volume":"187","author":"M Hu","year":"2022","journal-title":"Measurement"},{"key":"pone.0292082.ref005","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1109\/TIM.2018.2852918","article-title":"Generalized completed local binary patterns for time-efficient steel surface defect classification","volume":"68","author":"Q Luo","year":"2018","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"pone.0292082.ref006","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.optlaseng.2019.01.011","article-title":"Surface defect classification of steels with a new semi-supervised learning method","volume":"117","author":"H Di","year":"2019","journal-title":"Optics and Lasers in Engineering"},{"key":"pone.0292082.ref007","doi-asserted-by":"crossref","unstructured":"Usamentiaga R, Garcia D F, Molleda J, Bulnes F G, Bonet G. Vibrations in steel strips: Effects on flatness measurement and filtering. In Proceedings of the 2013 IEEE Industry Applications Society Annual Meeting, Lake Buena Vista, FL, USA, 6\u201311 October 2013; pp. 1\u201310.","DOI":"10.1109\/IAS.2013.6682561"},{"key":"pone.0292082.ref008","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.rcim.2015.09.008","article-title":"A cost-effective and automatic surface defect inspection system for hot-rolled flat steel. Robot","volume":"38","author":"Q Luo","year":"2016","journal-title":"Robotics and Computer-Integrated Manufacturing"},{"key":"pone.0292082.ref009","doi-asserted-by":"crossref","unstructured":"Wu G, Zhang H, Sun X, Xu J, Xu K., et al. A bran-new feature extraction method and its application to surface defect recognition of hot rolled strips[C]\/\/2007 IEEE International Conference on Automation and Logistics. IEEE, 2007: 2069\u20132074.","DOI":"10.1109\/ICAL.2007.4338916"},{"issue":"1","key":"pone.0292082.ref010","doi-asserted-by":"crossref","first-page":"348","DOI":"10.1109\/TIE.1930.896476","article-title":"Computer-vision-based fabric defect detection: A survey","volume":"55","author":"A. Kumar","year":"2008","journal-title":"IEEE transactions on industrial electronics"},{"issue":"1","key":"pone.0292082.ref011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1687-5281-2014-50","article-title":"Review of vision-based steel surface inspection systems","volume":"2014","author":"N Neogi","year":"2014","journal-title":"EURASIP Journal on Image and Video Processing"},{"issue":"2","key":"pone.0292082.ref012","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1109\/TSM.2010.2096437","article-title":"Fifty years of Moore\u2019s law","volume":"24","author":"C A. Mack","year":"2011","journal-title":"IEEE Transactions on semiconductor manufacturing"},{"key":"pone.0292082.ref013","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TIM.2012.2218677","article-title":"Automatic defect detection on hot-rolled flat steel products","volume":"62","author":"S Ghorai","year":"2012","journal-title":"IEEE Transactions on Instrumentation and Measurement"},{"key":"pone.0292082.ref014","doi-asserted-by":"crossref","unstructured":"Kang G W, Liu H B. Surface defects inspection of cold rolled strips based on neural network. In Proceedings of the 2005 International Conference on Machine Learning and Cybernetics, IEEE, Guangzhou, China, 18\u201321 August 2005; Volume 8, pp. 5034\u20135037.","DOI":"10.1109\/ICMLC.2005.1527830"},{"issue":"2","key":"pone.0292082.ref015","article-title":"CNN Based Automated Weed Detection System Using UAV Imagery","volume":"42","author":"A. Haq M","year":"2022","journal-title":"Computer Systems Science & Engineering"},{"key":"pone.0292082.ref016","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1111\/mice.12263","article-title":"Deep learning\u2010based crack damage detection using convolutional neural networks","volume":"32","author":"Y J Cha","year":"2017","journal-title":"Computer\u2010Aided Civil and Infrastructure Engineering"},{"key":"pone.0292082.ref017","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1111\/mice.12334","article-title":"Autonomous structural visual inspection using region\u2010based deep learning for detecting multiple damage types","volume":"33","author":"J Cha Y","year":"2018","journal-title":"Computer\u2010Aided Civil and Infrastructure Engineering"},{"issue":"1","key":"pone.0292082.ref018","article-title":"Development of PCCNN-Based Network Intrusion Detection System for EDGE Computing","volume":"71","author":"A Haq M","year":"2022","journal-title":"Computers, Materials & Continua"},{"issue":"9","key":"pone.0292082.ref019","doi-asserted-by":"crossref","first-page":"1678","DOI":"10.3390\/app8091678","article-title":"Research on a surface defect detection algorithm based on MobileNet-SSD","volume":"8","author":"Y Li","year":"2018","journal-title":"Applied Sciences"},{"issue":"15","key":"pone.0292082.ref020","doi-asserted-by":"crossref","first-page":"2343","DOI":"10.3390\/electronics11152343","article-title":"Target object detection from Unmanned Aerial Vehicle (UAV) images based on improved YOLO algorithm","volume":"11","author":"A Jawaharlalnehru","year":"2022","journal-title":"Electronics"},{"issue":"21","key":"pone.0292082.ref021","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1016\/j.ifacol.2018.09.412","article-title":"Real-time detection of steel strip surface defects based on improved yolo detection network","volume":"51","author":"J Li","year":"2018","journal-title":"IFAC-PapersOnLine"},{"key":"pone.0292082.ref022","first-page":"182","article-title":"Development of a YOLO-V3-based model for detecting defects on steel strip surface","author":"X Kou","year":"2021","journal-title":"Measurement"},{"key":"pone.0292082.ref023","doi-asserted-by":"crossref","first-page":"108208","DOI":"10.1016\/j.compeleceng.2022.108208","article-title":"Surface defect detection of steel strips based on improved YOLOv4","volume":"102","author":"M Li","year":"2022","journal-title":"Computers and Electrical Engineering"},{"key":"pone.0292082.ref024","article-title":"N. Attention is all you need","volume":"30","author":"A Vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"pone.0292082.ref025","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"T Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"pone.0292082.ref026","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"J Devlin","year":"2018","journal-title":"arXiv preprint arXiv:1810.04805"},{"key":"pone.0292082.ref027","first-page":"1","article-title":"Vitaev2: Vision transformer advanced by exploring inductive bias for image recognition and beyond","author":"Q Zhang","year":"2023","journal-title":"International Journal of Computer Vision"},{"key":"pone.0292082.ref028","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z. Swin transformer: Hierarchical vision transformer using shifted windows[C]\/\/Proceedings of the IEEE\/CVF international conference on computer vision. 2021: 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0292082.ref029","first-page":"2761","article-title":"Weapons detection for security and video surveillance using cnn and YOLO-v5s","volume":"70","author":"H Ashraf A","year":"2022","journal-title":"CMC-Comput. Mater. Contin"},{"key":"pone.0292082.ref030","first-page":"109","article-title":"Research on early fire detection of Yolo V5 based on multiple transfer learning","volume":"40","author":"J Wen-ping","year":"2021","journal-title":"Fire Science and Technology"},{"key":"pone.0292082.ref031","doi-asserted-by":"crossref","unstructured":"Han K, Wang Y, Tian Q, Guo J, Xu C, Xu C. Ghostnet: More features from cheap operations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13\u201319 June 2020; pp. 1580\u20131589.","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"pone.0292082.ref032","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, Hu H, Wei Y, Zhang Z, et al. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada, 11\u201317 October 2021.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"pone.0292082.ref033","doi-asserted-by":"crossref","first-page":"2552","DOI":"10.3390\/rs14112552","article-title":"L-Unet: A Landslide Extraction Model Using Multi-Scale Feature Fusion and Attention Mechanism","volume":"14","author":"Z Dong","year":"2022","journal-title":"Remote Sensing"},{"key":"pone.0292082.ref034","doi-asserted-by":"crossref","unstructured":"Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA, 20\u201325 June 2021; pp. 13713\u201313722.","DOI":"10.1109\/CVPR46437.2021.01350"},{"key":"pone.0292082.ref035","doi-asserted-by":"crossref","unstructured":"Tan M, Pang R, Le Q V. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13\u201319 June 2020; pp. 10781\u201310790.","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"pone.0292082.ref036","doi-asserted-by":"crossref","first-page":"83138","DOI":"10.1109\/ACCESS.2022.3197146","article-title":"AB-DLM: An Improved Deep Learning Model Based on Attention Mechanism and BiFPN for Driver Distraction Behavior Detection","volume":"10","author":"T Li","year":"2022","journal-title":"IEEE Access"},{"key":"pone.0292082.ref037","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.optlaseng.2019.06.020","article-title":"Semi-supervised defect classification of steel surface based on multi-training and generative adversarial network","volume":"122","author":"Y He","year":"2019","journal-title":"Optics and Lasers in Engineering"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0292082","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,9]],"date-time":"2024-11-09T00:37:08Z","timestamp":1731112628000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0292082"}},"subtitle":[],"editor":[{"given":"Ahmed Mancy","family":"Mosa","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,1,25]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,1,25]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0292082","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,25]]}}}