{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,14]],"date-time":"2025-06-14T04:07:19Z","timestamp":1749874039006,"version":"3.41.0"},"reference-count":30,"publisher":"Public Library of Science (PLoS)","issue":"6","license":[{"start":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T00:00:00Z","timestamp":1749772800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52074064"],"award-info":[{"award-number":["52074064"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","award":["N2404013"],"award-info":[{"award-number":["N2404013"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities of China","doi-asserted-by":"crossref","award":["N2404015"],"award-info":[{"award-number":["N2404015"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Natural Science Foundation of Science and Technology Department of Liaoning Province","award":["2024-MSLH-524"],"award-info":[{"award-number":["2024-MSLH-524"]}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Due to the complex factory environment, zinc flower defects and galvanized sheet background are difficult to distinguish, and the production line running speed is fast, the existing detection methods are difficult to meet the needs of real-time detection in terms of accuracy and speed. We propose ZFD-Net, a zinc flower defect detection model on the surface of galvanized sheet based on improved you only look once (YOLO)v5. Firstly, the model combined the YOLOV5 model with our proposed cross stage partial transformer (CSTR) module in this paper to increase the model receptive field and improve the global feature extraction (FE) capability. Secondly, we use bi-directional feature pyramid network (Bi-FPN) weighted bidirectional feature pyramid network to fuse defect details of different levels and scales to improve them. Then we propose a cross resnet simam fasternet (CRSFN) module to improve the reasoning speed of ZFD-Net and ensure the detection effect of zinc flower defects. Finally, we construct a high-quality dataset of zinc flower defect (ZFD) detection on galvanized sheet surface, which solves the problem that no public dataset is available at present. ZFD-Net is compared with state-of-the-art (SOTA) methods on the self-built data set, and its performance indicators are better than all methods.<\/jats:p>","DOI":"10.1371\/journal.pone.0325507","type":"journal-article","created":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T17:47:08Z","timestamp":1749836828000},"page":"e0325507","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["ZFD-Net: Zinc flower defect detection model of galvanized steel surface based on improved YOLOV5"],"prefix":"10.1371","volume":"20","author":[{"given":"Yang","family":"Gao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanquan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lifu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feitong","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0401-6654","authenticated-orcid":true,"given":"Dong","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,6,13]]},"reference":[{"issue":"22","key":"pone.0325507.ref001","doi-asserted-by":"crossref","first-page":"19613","DOI":"10.1021\/acsomega.3c01119","article-title":"Molybdate and Phosphate Cross-Linked Chitosan Films for Corrosion Protection of Hot-Dip Galvanized Steel","volume":"8","author":"C Fern\u00e1ndez-Solis","year":"2023","journal-title":"ACS Omega"},{"key":"pone.0325507.ref002","doi-asserted-by":"crossref","first-page":"8450","DOI":"10.23919\/ChiCC.2019.8865922","article-title":"Detection and Positioning of Surface Defects on Galvanized Sheet Based on Improved MobileNet v2","volume-title":"2019 Chinese Control Conference (CCC)","author":"Y Shen","year":"2019"},{"key":"pone.0325507.ref003","doi-asserted-by":"crossref","first-page":"157496","DOI":"10.1109\/ACCESS.2024.3486110","article-title":"YOLOv5-ACCOF Steel Surface Defect Detection Algorithm","volume":"12","author":"H Xin","year":"2024","journal-title":"IEEE Access"},{"issue":"1","key":"pone.0325507.ref004","doi-asserted-by":"crossref","first-page":"950","DOI":"10.1109\/TII.2024.3470895","article-title":"SRPCNet: Self-Reinforcing Perception Coordination Network for Seamless Steel Pipes Internal Surface Defect Detection","volume":"21","author":"H Chen","year":"2025","journal-title":"IEEE Trans Ind Inf"},{"issue":"12","key":"pone.0325507.ref005","doi-asserted-by":"crossref","first-page":"7448","DOI":"10.1109\/TII.2019.2958826","article-title":"PGA-Net: Pyramid Feature Fusion and Global Context Attention Network for Automated Surface Defect Detection","volume":"16","author":"H Dong","year":"2020","journal-title":"IEEE Trans Ind Inf"},{"issue":"10","key":"pone.0325507.ref006","article-title":"Bearing defect detection based on the improved YOLOv5 algorithm","volume":"19","author":"K Li","year":"2024","journal-title":"PLoS One"},{"issue":"5","key":"pone.0325507.ref007","doi-asserted-by":"crossref","first-page":"4392","DOI":"10.1109\/TIE.2017.2764844","article-title":"NB-CNN: Deep Learning-Based Crack Detection Using Convolutional Neural Network and Na\u00efve Bayes Data Fusion","volume":"65","author":"F-C Chen","year":"2018","journal-title":"IEEE Trans Ind Electron"},{"issue":"12","key":"pone.0325507.ref008","article-title":"PCB defect detection based on pseudo-inverse transformation and YOLOv5","volume":"19","author":"X Wang","year":"2024","journal-title":"PLoS One"},{"issue":"12","key":"pone.0325507.ref009","article-title":"Detection method of small size defects on pipeline weld surface based on improved YOLOv7","volume":"19","author":"X Xu","year":"2024","journal-title":"PLoS One"},{"key":"pone.0325507.ref010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN60899.2024.10651516","article-title":"CEC-YOLO: An Improved Steel Defect Detection Algorithm Based on YOLOv5","volume-title":"2024 International Joint Conference on Neural Networks (IJCNN)","author":"Z Chen","year":"2024"},{"key":"pone.0325507.ref011","doi-asserted-by":"crossref","unstructured":"Liu X, Zhou Y. Surface Defect Detection on Steel Plates Based on Improved Unet Network. 2024 36th Chinese Control and Decision Conference (CCDC). Xi\u2019an, China. 2024. p. 6268\u201373. doi: 10.1109\/CCDC62350.2024.10587873","DOI":"10.1109\/CCDC62350.2024.10587873"},{"key":"pone.0325507.ref012","doi-asserted-by":"crossref","unstructured":"Zhao WD, Chen F, Huang HC, Li D, Cheng W. A new steel defect detection algorithm based on deep learning. Computational Intelligence and Neuroscience. 2021:1\u201313.","DOI":"10.1155\/2021\/5592878"},{"key":"pone.0325507.ref013","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TIM.2024.3488136","article-title":"SSA-YOLO: An Improved YOLO for Hot-Rolled Strip Steel Surface Defect Detection","volume":"73","author":"X Huang","year":"2024","journal-title":"IEEE Trans Instrum Meas"},{"issue":"04","key":"pone.0325507.ref014","first-page":"445","article-title":"Surface defect detection of continuous casting billet based on deep learning","volume":"25","author":"J Hu","year":"2019","journal-title":"Journal of Shanghai University (Natural Science)"},{"key":"pone.0325507.ref015","doi-asserted-by":"crossref","first-page":"148817","DOI":"10.1109\/ACCESS.2024.3476908","article-title":"GDM-YOLO: A Model for Steel Surface Defect Detection Based on YOLOv8s","volume":"12","author":"T Zhang","year":"2024","journal-title":"IEEE Access"},{"key":"pone.0325507.ref016","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/AIPMV62663.2024.10692098","article-title":"Detection of Steel Surface Defects Based on Improved YOLOv8n Algorithm","volume-title":"2024 2nd International Conference on Algorithm, Image Processing and Machine Vision (AIPMV)","author":"J Meng","year":"2024"},{"issue":"06","key":"pone.0325507.ref017","first-page":"19","article-title":"Application of object detection algorithm based on deep learning in surface defect detection of cold rolling","volume":"43","author":"J Gu","year":"2019","journal-title":"Metallurgical Automation"},{"issue":"16","key":"pone.0325507.ref018","first-page":"265","article-title":"Research on surface defect detection of steel plate by improved YOLOv3 network","volume":"56","author":"Q Xu","year":"2020","journal-title":"Computer Engineering and Applications"},{"key":"pone.0325507.ref019","doi-asserted-by":"crossref","first-page":"1231","DOI":"10.1109\/ITOEC53115.2022.9734631","article-title":"Research on edge detection algorithm of work piece defect in machine vision detection system","volume-title":"2022 IEEE 6th Information Technology and Mechatronics Engineering Conference (ITOEC)","author":"S Luo","year":"2022"},{"key":"pone.0325507.ref020","doi-asserted-by":"crossref","first-page":"8594","DOI":"10.23919\/CCC58697.2023.10240342","article-title":"EEDN: An Efficient Edge Detection Network for Aeroengine Blade Defect Segmentation","volume-title":"2023 42nd Chinese Control Conference (CCC)","author":"C Wang","year":"2023"},{"key":"pone.0325507.ref021","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1109\/ICEPE-ST51904.2022.9757088","article-title":"Detection of Mechanical Defects of High Voltage Circuit Breaker based on Improved Edge Detection and Deep Learning Algorithms","volume-title":"2022 6th International Conference on Electric Power Equipment - Switching Technology (ICEPE-ST)","author":"S Lei","year":"2022"},{"key":"pone.0325507.ref022","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1109\/CISCE.2019.00065","article-title":"Defect Detection Based on Edge Detection and Connected Region Filtering Algorithm","volume-title":"2019 International Conference on Communications, Information System and Computer Engineering (CISCE)","author":"Y Pan","year":"2019"},{"key":"pone.0325507.ref023","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1109\/ICETIS61828.2024.10593784","article-title":"Automatic Edge Detection Method of Power Chip Packaging Defect Image Based on Improved Canny Algorithm","volume-title":"2024 9th International Conference on Electronic Technology and Information Science (ICETIS)","author":"Y He","year":"2024"},{"key":"pone.0325507.ref024","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/NNICE58320.2023.10105772","article-title":"An adaptive edge detection method for extracting images of defect steel plates under complex background","volume-title":"2023 3rd International Conference on Neural Networks, Information and Communication Engineering (NNICE)","author":"F Chen","year":"2023"},{"issue":"3","key":"pone.0325507.ref025","doi-asserted-by":"crossref","first-page":"413","DOI":"10.2307\/2981007","article-title":"The Extrapolation, Interpolation and Smoothing of Stationary Time Series, with Engineering Applications","volume":"113","author":"PA M.","year":"1950","journal-title":"Journal of the Royal Statistical Society Series A (General)"},{"key":"pone.0325507.ref026","doi-asserted-by":"crossref","first-page":"474","DOI":"10.1016\/B978-0-12-336156-1.50061-6","article-title":"Contrast limited adaptive histogram equalization ScienceDirect","author":"K Zuiderveld","year":"1994","journal-title":"Graphics Gems"},{"issue":"6","key":"pone.0325507.ref027","first-page":"84","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"A Krizhevsky","year":"2012","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0325507.ref028","first-page":"10778","article-title":"Efficientdet: Scalable and efficient object detection","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"M Tan","year":"2020"},{"key":"pone.0325507.ref029","doi-asserted-by":"crossref","unstructured":"Chen J, Kao S, He H, Zhuo W, Wen S, Lee C. Run, don\u2019t walk: chasing higher flops for faster neural networks. 2023.","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"pone.0325507.ref030","first-page":"21","article-title":"SSD: Single Shot MultiBox Detector","volume-title":"European Conference on Computer Vision","author":"W Liu","year":"2016"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,13]],"date-time":"2025-06-13T17:47:23Z","timestamp":1749836843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0325507"}},"subtitle":[],"editor":[{"given":"Din","family":"Bandhu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,6,13]]},"references-count":30,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,6,13]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0325507","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,13]]}}}