Exploring Deep Fully-convolutional Neural Networks for Surface Defect Detection in Complex Geometries

Exploring Deep Fully-convolutional Neural Networks for Surface Defect Detection in Complex Geometries | 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 Exploring Deep Fully-convolutional Neural Networks for Surface Defect Detection in Complex Geometries Daniel García, Diego García, Ignacio Díaz, Jorge Marina This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3929007/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 16 Jul, 2024 Read the published version in The International Journal of Advanced Manufacturing Technology → Version 1 posted 5 You are reading this latest preprint version Abstract In this paper, we propose a machine learning approach for detecting superficial defects in metal surfaces using point cloud data. We compare the performance of two popular deep learning architectures, Multilayer Perceptron Networks (MLPs) and Fully Convolutional Networks (FCNs), with varying feature sets. Our results show that FCNs outperformed MLPs in terms of precision, recall, and f1-score. We found that transfer learning with pre-trained models can improve performance when the amount of available data is limited. Our study highlights the importance of considering the amount and quality of training data in developing machine learning models for defect detection in industrial settings with 3D images. Image segmentation defect detection Convolutional Neural Networks Deep Learning Machine Learning 3D images Fully Convolutional Networks Transfer Learning Full Text Cite Share Download PDF Status: Published Journal Publication published 16 Jul, 2024 Read the published version in The International Journal of Advanced Manufacturing Technology → Version 1 posted Editorial decision: Minor Revisions Needed 21 May, 2024 Reviewers agreed at journal 04 Mar, 2024 Reviewers invited by journal 14 Feb, 2024 Editor assigned by journal 07 Feb, 2024 First submitted to journal 07 Feb, 2024 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-3929007","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":273113472,"identity":"1a10d60a-bbbd-47e7-bf24-b193b48c8ddd","order_by":0,"name":"Daniel García","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA90lEQVRIiWNgGAWjYDCCA2DEwMAGIj6AGOykaGGcAWIwE6EFDph5wCQBHXzHzx48+KXmnjwf+9mDj21+bZPnY2Zg/PAxB7cWyTN5CYdljhUbtvHkJRvn9t02bGNmYJacuQ23FoMDOQaHJdgSEtgYcsykc3tuMwK1sDHz4tNy/g1Qyz+gFv435r8te27bE9ZyI8fg4Mc2oBaJHDNmhh+3EwlqkbwBtIWxL8GwTeJdsmRvw+3kNmbGZrx+4TufY/zxx7cEefn+3IMffvy5bTu/vfngh494tIAAJDoYgCRjG4jB2IBfPUjJD5gWhj8EFY+CUTAKRsEIBAACqVM4q2Br8wAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0002-1456-4785","institution":"Universidad de Oviedo","correspondingAuthor":true,"prefix":"","firstName":"Daniel","middleName":"","lastName":"García","suffix":""},{"id":273113473,"identity":"d06fff07-7eb1-41ad-9fe0-e5b42e81818b","order_by":1,"name":"Diego García","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Diego","middleName":"","lastName":"García","suffix":""},{"id":273113474,"identity":"54830909-c8ff-4288-9e91-7d146aea730a","order_by":2,"name":"Ignacio Díaz","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ignacio","middleName":"","lastName":"Díaz","suffix":""},{"id":273113475,"identity":"c1d51e00-cb6f-4c9e-89b3-7dddd58e0055","order_by":3,"name":"Jorge Marina","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Jorge","middleName":"","lastName":"Marina","suffix":""}],"badges":[],"createdAt":"2024-02-04 22:28:19","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3929007/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3929007/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s00170-024-14069-7","type":"published","date":"2024-07-16T16:13:23+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":61595357,"identity":"658be965-1e39-4d13-9c6b-cba7d3b82e70","added_by":"auto","created_at":"2024-08-01 17:22:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":821688,"visible":true,"origin":"","legend":"","description":"","filename":"JAMTD2400669.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3929007/v1_covered_6bd0a27f-6a8c-4ba6-9f89-2bf6f5e0c3b0.pdf"}],"financialInterests":"","formattedTitle":"Exploring Deep Fully-convolutional Neural Networks for Surface Defect Detection in Complex Geometries","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":true,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"the-international-journal-of-advanced-manufacturing-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jamt","sideBox":"Learn more about [The International Journal of Advanced Manufacturing Technology](https://www.springer.com/journal/170)","snPcode":"170","submissionUrl":"https://submission.nature.com/new-submission/170/3","title":"The International Journal of Advanced Manufacturing Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Image segmentation, defect detection, Convolutional Neural Networks, Deep Learning, Machine Learning, 3D images, Fully Convolutional Networks, Transfer Learning","lastPublishedDoi":"10.21203/rs.3.rs-3929007/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3929007/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eIn this paper, we propose a machine learning approach for detecting superficial defects in metal surfaces using point cloud data. We compare the performance of two popular deep learning architectures, Multilayer Perceptron Networks (MLPs) and Fully Convolutional Networks (FCNs), with varying feature sets. Our results show that FCNs outperformed MLPs in terms of precision, recall, and f1-score. We found that transfer learning with pre-trained models can improve performance when the amount of available data is limited. Our study highlights the importance of considering the amount and quality of training data in developing machine learning models for defect detection in industrial settings with 3D images.\u003c/p\u003e","manuscriptTitle":"Exploring Deep Fully-convolutional Neural Networks for Surface Defect Detection in Complex Geometries","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-19 15:51:59","doi":"10.21203/rs.3.rs-3929007/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Minor Revisions Needed","date":"2024-05-21T14:30:26+00:00","index":"","fulltext":""},{"type":"reviewerAgreed","content":"","date":"2024-03-04T06:34:02+00:00","index":0,"fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-02-14T22:19:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-02-07T23:37:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"The International Journal of Advanced Manufacturing Technology","date":"2024-02-07T11:44:42+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-international-journal-of-advanced-manufacturing-technology","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jamt","sideBox":"Learn more about [The International Journal of Advanced Manufacturing Technology](https://www.springer.com/journal/170)","snPcode":"170","submissionUrl":"https://submission.nature.com/new-submission/170/3","title":"The International Journal of Advanced Manufacturing Technology","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"85d16b42-8f6b-40be-9a8b-c55993cfc95b","owner":[],"postedDate":"February 19th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-08-01T16:21:04+00:00","versionOfRecord":{"articleIdentity":"rs-3929007","link":"https://doi.org/10.1007/s00170-024-14069-7","journal":{"identity":"the-international-journal-of-advanced-manufacturing-technology","isVorOnly":false,"title":"The International Journal of Advanced Manufacturing Technology"},"publishedOn":"2024-07-16 16:13:23","publishedOnDateReadable":"July 16th, 2024"},"versionCreatedAt":"2024-02-19 15:51:59","video":"","vorDoi":"10.1007/s00170-024-14069-7","vorDoiUrl":"https://doi.org/10.1007/s00170-024-14069-7","workflowStages":[]},"version":"v1","identity":"rs-3929007","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3929007","identity":"rs-3929007","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}