A Lightweight Algorithm for Steel Surface Defect Detection Using Improved YOLOv8

A Lightweight Algorithm for Steel Surface Defect Detection Using Improved YOLOv8 | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Article A Lightweight Algorithm for Steel Surface Defect Detection Using Improved YOLOv8 Shuangbao Ma, Xin Zhao, Li Wan, Yapeng Zhang, Hongliang Gao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5933201/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 15 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted 10 You are reading this latest preprint version Abstract In response to the issues of low precision, a large number of parameters and high model complexity in steel surface defect detection, a lightweight algorithm using improved YOLOv8 is proposed. Firstly, GhostNet is utilized as the backbone network in order to reduce the number of model parameters and computational complexity. Secondly, the MPCA((MultiPath Coordinate Attention, MPCA) attention mechanism is integrated to enhance feature extraction capabilities. Finally, the SIoU (Simplified IoU, SIoU) is used to replace the traditional CIoU loss function, which can make the anchor frame more fast and accurate in the regression process, to improve the stability and the robustness of detection. The experimental results indicate that these enhancements have led to a reduction of 37% in calculation amount for the improved YOLOv8n algorithm, a decrease of 32% in parameter count, and an increase in average detection accuracy (mAP) by 1.2%. This model achieves a balance between lightweighting and detection accuracy while providing a viable solution for deployment in computationally resource-constrained edge computing environments such as embedded systems and mobile devices. Physical sciences/Engineering Physical sciences/Physics YOLOv8 Lightweight Defect Detection GhostNet Attention Mechanisms SIoU Full Text Additional Declarations No competing interests reported. Supplementary Files data.rar yolov8.rar Cite Share Download PDF Status: Published Journal Publication published 15 Mar, 2025 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 14 Feb, 2025 Reviews received at journal 14 Feb, 2025 Reviews received at journal 07 Feb, 2025 Reviewers agreed at journal 05 Feb, 2025 Reviewers agreed at journal 05 Feb, 2025 Reviewers invited by journal 05 Feb, 2025 Editor assigned by journal 05 Feb, 2025 Editor invited by journal 03 Feb, 2025 Submission checks completed at journal 31 Jan, 2025 First submitted to journal 30 Jan, 2025 You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-5933201","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":409563798,"identity":"5c464890-775a-48e4-a191-a8494ea0fe9d","order_by":0,"name":"Shuangbao Ma","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Shuangbao","middleName":"","lastName":"Ma","suffix":""},{"id":409563799,"identity":"3b13cd37-be48-4361-8afd-ff806e532c5e","order_by":1,"name":"Xin Zhao","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Zhao","suffix":""},{"id":409563800,"identity":"e9aeda5c-e03f-4de5-9043-e035d74a3a8a","order_by":2,"name":"Li Wan","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Wan","suffix":""},{"id":409563801,"identity":"5e2b241b-14a7-4cee-b52c-345d77c2c009","order_by":3,"name":"Yapeng Zhang","email":"","orcid":"","institution":"Wuhan Textile University","correspondingAuthor":false,"prefix":"","firstName":"Yapeng","middleName":"","lastName":"Zhang","suffix":""},{"id":409563803,"identity":"af15677b-13f6-4df6-9af3-6376b3337343","order_by":4,"name":"Hongliang Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYHACNoYHFRI8/Ow9bBD+AWK0JJyxkZHsOUOKlsS2NBuDGTlEapF3P3zsQQLbYR4DybfHHhe2Mcjx3Uhg/FyAR4vhmbR0gwSewzzm0nnpxjPbGIwlbyQwS8/Ap6Uhx0wiQeIwj+XsHDNp3jaGxA03EtiYefBp6X8D1GIAdNjNM2At9QS1yEuAbElI4zG4wQPWkmBASIuBxLM0iYQDNjySPTnmxjznJAxnnnnYLI3Xlv7kYxIf/0nY87OfMXvMU2Yjz3c8+eBnvLYcQOVLADFjAx4NQFvwS4+CUTAKRsEoAAIAPeNHSGm5vXcAAAAASUVORK5CYII=","orcid":"","institution":"Hubei Normal University","correspondingAuthor":true,"prefix":"","firstName":"Hongliang","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2025-01-31 02:08:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5933201/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5933201/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1038/s41598-025-93469-5","type":"published","date":"2025-03-15T15:58:08+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":78689026,"identity":"0a4e34a9-9ea2-4b12-9dc6-1743e8f0c84e","added_by":"auto","created_at":"2025-03-17 16:10:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":523575,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript0131.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5933201/v1_covered_45b94946-d4a2-47e9-bf0f-487ff84981c9.pdf"},{"id":75938567,"identity":"8d6ba18c-4df4-4722-83dd-ea456d180956","added_by":"auto","created_at":"2025-02-10 17:44:48","extension":"rar","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":27145166,"visible":true,"origin":"","legend":"","description":"","filename":"data.rar","url":"https://assets-eu.researchsquare.com/files/rs-5933201/v1/2a0209754f523c5afcf32069.rar"},{"id":75938568,"identity":"40ac5835-f99f-4c04-a035-5e22cc7fde35","added_by":"auto","created_at":"2025-02-10 17:45:01","extension":"rar","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":226101574,"visible":true,"origin":"","legend":"","description":"","filename":"yolov8.rar","url":"https://assets-eu.researchsquare.com/files/rs-5933201/v1/c6c7056a4209d17f943b257d.rar"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Lightweight Algorithm for Steel Surface Defect Detection Using Improved YOLOv8","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"YOLOv8, Lightweight, Defect Detection, GhostNet, Attention Mechanisms, SIoU","lastPublishedDoi":"10.21203/rs.3.rs-5933201/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5933201/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"In response to the issues of low precision, a large number of parameters and high model complexity in steel surface defect detection, a lightweight algorithm using improved YOLOv8 is proposed. Firstly, GhostNet is utilized as the backbone network in order to reduce the number of model parameters and computational complexity. Secondly, the MPCA((MultiPath Coordinate Attention, MPCA) attention mechanism is integrated to enhance feature extraction capabilities. Finally, the SIoU (Simplified IoU, SIoU) is used to replace the traditional CIoU loss function, which can make the anchor frame more fast and accurate in the regression process, to improve the stability and the robustness of detection. The experimental results indicate that these enhancements have led to a reduction of 37% in calculation amount for the improved YOLOv8n algorithm, a decrease of 32% in parameter count, and an increase in average detection accuracy (mAP) by 1.2%. This model achieves a balance between lightweighting and detection accuracy while providing a viable solution for deployment in computationally resource-constrained edge computing environments such as embedded systems and mobile devices.","manuscriptTitle":"A Lightweight Algorithm for Steel Surface Defect Detection Using Improved YOLOv8","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-02-10 17:44:42","doi":"10.21203/rs.3.rs-5933201/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-02-14T17:52:21+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-14T05:42:33+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-02-07T10:55:25+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"315534511364987215351743280593736701535","date":"2025-02-06T02:31:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"51706382384739021314869708238739130559","date":"2025-02-06T02:07:00+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-02-06T02:02:24+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-02-06T01:59:24+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-02-03T15:10:03+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-01-31T13:13:54+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-01-31T01:52:12+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e92ad9f1-c191-4cb9-9b46-f1c92afbf051","owner":[],"postedDate":"February 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[{"id":43674751,"name":"Physical sciences/Engineering"},{"id":43674752,"name":"Physical sciences/Physics"}],"tags":[],"updatedAt":"2025-03-17T16:03:37+00:00","versionOfRecord":{"articleIdentity":"rs-5933201","link":"https://doi.org/10.1038/s41598-025-93469-5","journal":{"identity":"scientific-reports","isVorOnly":false,"title":"Scientific Reports"},"publishedOn":"2025-03-15 15:58:08","publishedOnDateReadable":"March 15th, 2025"},"versionCreatedAt":"2025-02-10 17:44:42","video":"","vorDoi":"10.1038/s41598-025-93469-5","vorDoiUrl":"https://doi.org/10.1038/s41598-025-93469-5","workflowStages":[]},"version":"v1","identity":"rs-5933201","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5933201","identity":"rs-5933201","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}