Research on textile Defect detection Algorithm for Deep Learning

Research on textile Defect detection Algorithm for Deep Learning | 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 Research Article Research on textile Defect detection Algorithm for Deep Learning Yachao Si, Jiajie Gao, Xingxuan Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4179693/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Textile defect detection is a crucial aspect of the textile industry. However, the detection accuracy is often low due to the small size of textile defects and the influence of fabric texture background. To address these issues, we propose a textile defect detection algorithm based on YOLOv8.The reparameterized structure was introduced to the original YOLOv8 to achieve hardware efficiency with the RepGhost module. The head section incorporates a new GD Mechanism and includes the Wasserstein Distance loss function.This method accurately identifies the location and type of defects in textiles with high precision under complex backgrounds, meeting the needs of industrial textile production. We conducted training and comparison experiments on different models using the AITEX public dataset and Roboflow open source dataset. We also designed ablation experiments to verify the considerable improvement of each enhancement on the evaluation index. The experimental results indicate that the detection accuracy of the enhanced YOLOv8 model in the task of detecting textile defects has increased by 18.9% to 93.8% on the public dataset. The number of parameters has increased by 10.94MB, and the FLOPs have increased from 8.2G to 11.3G. The improved algorithm has significantly enhanced the accuracy. It can effectively handle large amounts of data and recognize defects even under complex backgrounds, meeting the fast, complex, and high-precision requirements of the textile industry. YOLOv8 RepGhost Wasserstein Distance AITEX Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-4179693","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":285947999,"identity":"e90ed84e-a428-4fa8-ad7a-bf968dab455d","order_by":0,"name":"Yachao Si","email":"","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":false,"prefix":"","firstName":"Yachao","middleName":"","lastName":"Si","suffix":""},{"id":285948000,"identity":"43ae6901-38c5-461e-80ae-43e4c4de64c5","order_by":1,"name":"Jiajie Gao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA40lEQVRIiWNgGAWjYBACNvnzjx98+MFmx8/e2PggoaKGsBY+CR42w5k9fMmSPYcPGzw4c4ywFjkJHgZpHjY5xg033NIkH7YwE+Ew6d4DBjw8ZswGN3jMKhIb2Bj427sT8GuROZfwQMIijU/ydo/ZjcQdMgwSZ85uwK+FIcHAwIDnGDPfnTNALWfYGAwkcglrkUhg+8/YcCPHrCCxjZkILRI5BhIH2NgYJ9xIS2MgTgvPsTTDxh42cCBLJJw5xkPQL/LtzYcf/4FG5ccfFTVy/O29+LVgAB7SlI+CUTAKRsEowAoAuIdLBglXKc0AAAAASUVORK5CYII=","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":true,"prefix":"","firstName":"Jiajie","middleName":"","lastName":"Gao","suffix":""},{"id":285948002,"identity":"319a5896-c6ac-4f17-8ae7-4c9608414147","order_by":2,"name":"Xingxuan Zhao","email":"","orcid":"","institution":"Hebei University of Architecture","correspondingAuthor":false,"prefix":"","firstName":"Xingxuan","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2024-03-28 05:23:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4179693/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4179693/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":54193061,"identity":"77043072-6c77-48f6-99dc-d2b9d3c01ec4","added_by":"auto","created_at":"2024-04-05 21:22:48","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4010481,"visible":true,"origin":"","legend":"","description":"","filename":"ArticleTitle71.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4179693/v1_covered_84985de9-98c5-4d6b-a6d3-170f17b92c6d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on textile Defect detection Algorithm for Deep Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"YOLOv8, RepGhost, Wasserstein Distance, AITEX","lastPublishedDoi":"10.21203/rs.3.rs-4179693/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4179693/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Textile defect detection is a crucial aspect of the textile industry. However, the detection accuracy is often low due to the small size of textile defects and the influence of fabric texture background. To address these issues, we propose a textile defect detection algorithm based on YOLOv8.The reparameterized structure was introduced to the original YOLOv8 to achieve hardware efficiency with the RepGhost module. The head section incorporates a new GD Mechanism and includes the Wasserstein Distance loss function.This method accurately identifies the location and type of defects in textiles with high precision under complex backgrounds, meeting the needs of industrial textile production. We conducted training and comparison experiments on different models using the AITEX public dataset and Roboflow open source dataset. We also designed ablation experiments to verify the considerable improvement of each enhancement on the evaluation index. The experimental results indicate that the detection accuracy of the enhanced YOLOv8 model in the task of detecting textile defects has increased by 18.9\\% to 93.8\\% on the public dataset. The number of parameters has increased by 10.94MB, and the FLOPs have increased from 8.2G to 11.3G. The improved algorithm has significantly enhanced the accuracy. It can effectively handle large amounts of data and recognize defects even under complex backgrounds, meeting the fast, complex, and high-precision requirements of the textile industry.","manuscriptTitle":"Research on textile Defect detection Algorithm for Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-02 05:27:54","doi":"10.21203/rs.3.rs-4179693/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"94a084e0-c99d-4055-9074-dd2f830c3cae","owner":[],"postedDate":"April 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-04-05T21:14:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-02 05:27:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4179693","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4179693","identity":"rs-4179693","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}