Research on luminaire paint defect detection model based on improved YOLOv10

Research on luminaire paint defect detection model based on improved YOLOv10 | 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 Research on luminaire paint defect detection model based on improved YOLOv10 Dengtao Wu, Likang Yang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5654333/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 Aiming at the problems of low detection accuracy, low computational efficiency and poor detection ability of multi-scale targets in existing detection methods, an improved YOLOv10 algorithm was proposed to improve the accuracy and efficiency of multi-scale defect detection of luminaire paint. By introducing the LSKA attention mechanism to the SPPF module on the YOLOv10 feature extraction backbone network, the recognition ability of the complex form of paint defects of lamps is improved. At the same time, the lightweight design of C2f and detection head module makes the algorithm more suitable for real-time application scenarios. In terms of evaluation indexes, after ablation experiments, the improved algorithm has improved 2.6% compared with the original YOLOv10 in main performance indexes [email protected] . In addition, the lightweight design of the improved algorithm significantly reduces the number of parameters and the amount of computation required. Compared with the original YOLOv10, the number of parameters is reduced by 0.22×10 6 and the amount of computation is reduced by 1.4GFLOPS, making it more suitable for deployment in resource-constrained environments. The improved YOLOv10 algorithm proposed in this paper achieves a balance of high accuracy and high efficiency in the multi-scale defect detection of luminaire paint surface, providing a reliable machine learning technical means for industrial production, and helping industrial equipment to carry out efficient monitoring and diagnosis under unattended conditions. Physical sciences/Mathematics and computing Physical sciences/Mathematics and computing/Computer science Lighting paint defects Object detection Lightweight Multi-scale 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-5654333","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":394275335,"identity":"a7a97546-1fa0-48d7-b097-209bb380b9f2","order_by":0,"name":"Dengtao Wu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA1ElEQVRIiWNgGAWjYBACNvnDBw58qPgnx8/ffIA4LXwSbIkHZ5w5YCw541gCcVrkJHiMD/O2HEjccCDHgEiHSbclHOZtuAPUcubjjTcMdnK6DYS0yBw+cHDujmfGMw/3bracw5BsbHaAkBaGtIQDb88wy/YdOLtNmofhQOI2wlpyDA7wtjEzNhzIeUakFokcg4O8bYcVJxzIYSNSC8+xBGAgp4EC2dhyjgERfpFvbz784UOFDSgqH954U2EnR1ALCpDgITJqkLWQqmMUjIJRMApGBAAAtpxOJQrOerUAAAAASUVORK5CYII=","orcid":"","institution":"Zhejiang University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Dengtao","middleName":"","lastName":"Wu","suffix":""},{"id":394275336,"identity":"dfcd28e5-c04f-40bd-b8dc-00aad46ca378","order_by":1,"name":"Likang Yang","email":"","orcid":"","institution":"Zhejiang University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Likang","middleName":"","lastName":"Yang","suffix":""}],"badges":[],"createdAt":"2024-12-16 13:38:39","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5654333/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5654333/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":80025665,"identity":"46ed4c45-7330-426c-94a5-636a03815b37","added_by":"auto","created_at":"2025-04-07 06:17:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":683504,"visible":true,"origin":"","legend":"","description":"","filename":"paper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5654333/v1_covered_a1c46cd1-2480-4a1e-a4ed-54587e9883a0.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eResearch on luminaire paint defect detection model based on improved YOLOv10\u003c/p\u003e","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":"Lighting paint defects, Object detection, Lightweight, Multi-scale","lastPublishedDoi":"10.21203/rs.3.rs-5654333/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5654333/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAiming at the problems of low detection accuracy, low computational efficiency and poor detection ability of multi-scale targets in existing detection methods, an improved YOLOv10 algorithm was proposed to improve the accuracy and efficiency of multi-scale defect detection of luminaire paint. By introducing the LSKA attention mechanism to the SPPF module on the YOLOv10 feature extraction backbone network, the recognition ability of the complex form of paint defects of lamps is improved. At the same time, the lightweight design of C2f and detection head module makes the algorithm more suitable for real-time application scenarios. In terms of evaluation indexes, after ablation experiments, the improved algorithm has improved 2.6% compared with the original YOLOv10 in main performance indexes [email protected]. In addition, the lightweight design of the improved algorithm significantly reduces the number of parameters and the amount of computation required. Compared with the original YOLOv10, the number of parameters is reduced by 0.22\u0026times;10\u003csup\u003e6\u003c/sup\u003e and the amount of computation is reduced by 1.4GFLOPS, making it more suitable for deployment in resource-constrained environments. The improved YOLOv10 algorithm proposed in this paper achieves a balance of high accuracy and high efficiency in the multi-scale defect detection of luminaire paint surface, providing a reliable machine learning technical means for industrial production, and helping industrial equipment to carry out efficient monitoring and diagnosis under unattended conditions.\u003c/p\u003e","manuscriptTitle":"Research on luminaire paint defect detection model based on improved YOLOv10","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-26 08:19:49","doi":"10.21203/rs.3.rs-5654333/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":"f9a07413-6b8d-41b2-aa9c-618fe9991658","owner":[],"postedDate":"December 26th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":42046784,"name":"Physical sciences/Mathematics and computing"},{"id":42046785,"name":"Physical sciences/Mathematics and computing/Computer science"}],"tags":[],"updatedAt":"2025-04-07T06:08:43+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-26 08:19:49","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5654333","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5654333","identity":"rs-5654333","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}