Research on Small Object Defect DetectionAlgorithms Based on Deep Learning

Research on Small Object Defect DetectionAlgorithms Based on 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 Small Object Defect DetectionAlgorithms Based on Deep Learning Jing Li, Yabiao Lu, Muzi Li, Peijuan Li, Rongdi Wang, Jiantao Qi, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4342862/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 In order to improve the accuracy of industrial defect detection based on deep learning, the special defect data set IDEF (Industrial defect data set, IDEF) is constructed, and the defect data is enhanced by digital image processing and deep learning. After data enhancement, the accuracy of defect detection is improved by 0.55 percentage points. Aiming at the phenomenon that small target defects are easy to be missed by the model, a method of adding grid intersection points to the regression strategy of target detection network is proposed to increase the predicted defect benchmark. The experiment shows that this method improves the defect detection accuracy map (mean average precision) by 1.96%. Aiming at the problem of poor representation ability of small target defects, a scale weight loss function is proposed, which makes the model more sensitive to defects with smaller size and more thorough learning of small target defects. It is found that this method improves the accuracy of defect detection by 2.23%. Finally, based on the fcosv2 basic model, two small target defect detection strategies are used at the same time to improve the defect detection accuracy by 3.35%. Defect detection Defect data set Small target detection Regression strategy loss function 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-4342862","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":298797850,"identity":"0cf750e9-de84-40e8-acec-dba78129f794","order_by":0,"name":"Jing Li","email":"","orcid":"","institution":"Henan Boiler and Pressure Vessel Inspection Technology Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Li","suffix":""},{"id":298797853,"identity":"3a15494d-5414-4367-b204-bb39dde1094f","order_by":1,"name":"Yabiao Lu","email":"","orcid":"","institution":"China Shipbuilding Group Corporation 750 Testing Ground","correspondingAuthor":false,"prefix":"","firstName":"Yabiao","middleName":"","lastName":"Lu","suffix":""},{"id":298797855,"identity":"247d9b36-626c-41f6-85f6-42fde7eb122f","order_by":2,"name":"Muzi Li","email":"","orcid":"","institution":"College of New Energy, China University of Petroleum (East China","correspondingAuthor":false,"prefix":"","firstName":"Muzi","middleName":"","lastName":"Li","suffix":""},{"id":298797856,"identity":"797934c5-9f26-45ec-9fc8-7735e00df4c8","order_by":3,"name":"Peijuan Li","email":"","orcid":"","institution":"Henan Boiler and Pressure Vessel Inspection Technology Research Institute","correspondingAuthor":false,"prefix":"","firstName":"Peijuan","middleName":"","lastName":"Li","suffix":""},{"id":298797858,"identity":"44bac406-1e41-4f07-83ae-ce4ba685fd18","order_by":4,"name":"Rongdi Wang","email":"","orcid":"","institution":"College of New Energy, China University of Petroleum (East China","correspondingAuthor":false,"prefix":"","firstName":"Rongdi","middleName":"","lastName":"Wang","suffix":""},{"id":298797860,"identity":"52c16ae5-b891-4e06-bb38-5fc6b3cb24fe","order_by":5,"name":"Jiantao Qi","email":"","orcid":"","institution":"College of New Energy, China University of Petroleum (East China","correspondingAuthor":false,"prefix":"","firstName":"Jiantao","middleName":"","lastName":"Qi","suffix":""},{"id":298797862,"identity":"423cf2b1-a6aa-4e67-a6c7-f06ccf09971e","order_by":6,"name":"Haiqiang Zuo","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAuklEQVRIiWNgGAWjYDACCTBpA+HwkKAljXQth0nQIj+7eZt0Qc35xO3sBxgfvG1jkDcnpIVxzrEy6RnHbifu7ElgNpzbxmC4s4GAFmaJHDNp3obbiRtuMLBJ87YxJBgcIKCFDaLlHEgL+2+itPBAtBwA28JMlBYJibRi6xnHko139iQ2S845J2G4gZAW+RnJG28X1NjJbmc/fPDDmzIbeYK2AIEBM5hkYGxggEUTsVpGwSgYBaNgFOAAAPQGOhR5n89aAAAAAElFTkSuQmCC","orcid":"","institution":"College of New Energy, China University of Petroleum (East China","correspondingAuthor":true,"prefix":"","firstName":"Haiqiang","middleName":"","lastName":"Zuo","suffix":""}],"badges":[],"createdAt":"2024-04-29 12:29:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4342862/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4342862/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":57308749,"identity":"68eb6e17-5051-43a4-91b2-bea2eb6e51ea","added_by":"auto","created_at":"2024-05-29 02:37:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":471827,"visible":true,"origin":"","legend":"","description":"","filename":"ResearchonSmallObjectDefectDetectionAlgorithmsBasedonDeepLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4342862/v1_covered_68f2ac87-6a86-46fc-b2fa-066bce7b8b1e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Research on Small Object Defect DetectionAlgorithms Based on 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":"Defect detection, Defect data set, Small target detection, Regression strategy, loss function","lastPublishedDoi":"10.21203/rs.3.rs-4342862/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4342862/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn order to improve the accuracy of industrial defect detection based on deep learning, the special defect data set IDEF (Industrial defect data set, IDEF) is constructed, and the defect data is enhanced by digital image processing and deep learning. After data enhancement, the accuracy of defect detection is improved by 0.55 percentage points. Aiming at the phenomenon that small target defects are easy to be missed by the model, a method of adding grid intersection points to the regression strategy of target detection network is proposed to increase the predicted defect benchmark. The experiment shows that this method improves the defect detection accuracy map (mean average precision) by 1.96%. Aiming at the problem of poor representation ability of small target defects, a scale weight loss function is proposed, which makes the model more sensitive to defects with smaller size and more thorough learning of small target defects. It is found that this method improves the accuracy of defect detection by 2.23%. Finally, based on the fcosv2 basic model, two small target defect detection strategies are used at the same time to improve the defect detection accuracy by 3.35%.\u003c/p\u003e","manuscriptTitle":"Research on Small Object Defect DetectionAlgorithms Based on Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-06 02:15:46","doi":"10.21203/rs.3.rs-4342862/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":"4fbdd64f-399f-4959-8c2c-0a26823f2e6a","owner":[],"postedDate":"May 6th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-07-11T03:15:23+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-06 02:15:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4342862","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4342862","identity":"rs-4342862","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}