Defect detection of Printed circuit board Surface based on an improved YOLOv8 with FasterNet backbone algorithms

Defect detection of Printed circuit board Surface based on an improved YOLOv8 with FasterNet backbone algorithms | 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 Defect detection of Printed circuit board Surface based on an improved YOLOv8 with FasterNet backbone algorithms Li-Juan Liu, Yu Zhang, Hamid Reza Karimic This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4823049/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 07 Dec, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted 7 You are reading this latest preprint version Abstract Printed circuit board (PCB) constitutes a crucial element of electronic equipment, and its surface defects can seriously affect the performance and reliability of the product. To promptly and accurately detect and identify these surface defects, this paper proposes a method for defect detection of printed circuit board surface based on an improved YOLOv8 with FasterNet backbone algorithms. Firstly, FasterNet is employed as the backbone network structure to minimize unnecessary computational overhead and memory accesses, enabling a more streamlined and effective extraction of spatial characteristics. Then, in the Neck layer, the C2f module is exchanged for the C2f_NAM attention mechanism. This allows for a more precise focus on important weights, thereby reducing unnecessary computations and parameters. Finally, the loss function of YOLOv8 is substituted with WIoU, which comprehensively considers the surrounding area information and flexibly adjusts the weights. The effectiveness of the method is demonstrated by experimental results on two publicly available PCB datasets. The mAP50 reaches 91.1% with a P of 88.6%, and the mAP50-95 stands at 46.9% on the PCB-AoI Public dataset. On the HRIPCB dataset, the method attains a mAP50 of 94.4%, a P of 96.1%, and a mAP50-95 of 58.3%. Compared to existing methods, this method shows a comprehensive performance advantage. YOLOv8 Fasternet C2f NAM attention Printed circuit board Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 07 Dec, 2024 Read the published version in Signal, Image and Video Processing → Version 1 posted Editorial decision: Revision requested 27 Aug, 2024 Reviews received at journal 27 Aug, 2024 Reviewers agreed at journal 07 Aug, 2024 Reviewers invited by journal 06 Aug, 2024 Editor assigned by journal 30 Jul, 2024 Submission checks completed at journal 30 Jul, 2024 First submitted to journal 29 Jul, 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-4823049","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":346018501,"identity":"b1851d56-5788-499a-9c8e-6d4f8fdcdfdf","order_by":0,"name":"Li-Juan Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwElEQVRIiWNgGAWjYBACPmYGxgMSFczMYB4PMVrYgGoPSJxhZuYhXgsQH2BsY2YgQQs7j8EBy3nW7PYSCYwP3rYxyJsTdhhQi+S2dGYeiQRmw7ltDIY7G4jTchikhU2at40hweAAUVrmgLWw/yZBSwPEFmYitbAVHJA4BvTLmYfNknPOSRhuIKSFn//wxscSNdbJ7O3JBz+8KbORJ2gLCDBLMDAkMzAwNgDZEkSoBwLGDwwMdsQpHQWjYBSMghEJAO0DMsiqN1ntAAAAAElFTkSuQmCC","orcid":"","institution":"Dalian Jiaotong University","correspondingAuthor":true,"prefix":"","firstName":"Li-Juan","middleName":"","lastName":"Liu","suffix":""},{"id":346018502,"identity":"235b8285-6f47-4058-b1a1-5ee63064e668","order_by":1,"name":"Yu Zhang","email":"","orcid":"","institution":"Dalian Jiaotong University","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Zhang","suffix":""},{"id":346018503,"identity":"5c543f82-d9c3-4853-b050-48319d9728cf","order_by":2,"name":"Hamid Reza Karimic","email":"","orcid":"","institution":"Politecnico di Milano","correspondingAuthor":false,"prefix":"","firstName":"Hamid","middleName":"Reza","lastName":"Karimic","suffix":""}],"badges":[],"createdAt":"2024-07-29 15:14:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4823049/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4823049/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s11760-024-03646-8","type":"published","date":"2024-12-07T15:58:07+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":70964974,"identity":"6f4cae0a-7a75-4f74-8e3a-c041e246d64d","added_by":"auto","created_at":"2024-12-09 16:17:35","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2821384,"visible":true,"origin":"","legend":"","description":"","filename":"DefectdetectionofPrintedcircuitboardSurfacebasedonanimprovedYOLOv8withFasterNetbackbonealgorithms.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4823049/v1_covered_0175659d-1c0c-4911-a253-d5a91de357f8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Defect detection of Printed circuit board Surface based on an improved YOLOv8 with FasterNet backbone algorithms","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":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"YOLOv8, Fasternet, C2f NAM attention, Printed circuit board","lastPublishedDoi":"10.21203/rs.3.rs-4823049/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4823049/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Printed circuit board (PCB) constitutes a crucial element of electronic equipment, and its surface defects can seriously affect the performance and reliability of the product. To promptly and accurately detect and identify these surface defects, this paper proposes a method for defect detection of printed circuit board surface based on an improved YOLOv8 with FasterNet backbone algorithms. Firstly, FasterNet is employed as the backbone network structure to minimize unnecessary computational overhead and memory accesses, enabling a more streamlined and effective extraction of spatial characteristics. Then, in the Neck layer, the C2f module is exchanged for the C2f_NAM attention mechanism. This allows for a more precise focus on important weights, thereby reducing unnecessary computations and parameters. Finally, the loss function of YOLOv8 is substituted with WIoU, which comprehensively considers the surrounding area information and flexibly adjusts the weights. The effectiveness of the method is demonstrated by experimental results on two publicly available PCB datasets. The mAP50 reaches 91.1% with a P of 88.6%, and the mAP50-95 stands at 46.9% on the PCB-AoI Public dataset. On the HRIPCB dataset, the method attains a mAP50 of 94.4%, a P of 96.1%, and a mAP50-95 of 58.3%. Compared to existing methods, this method shows a comprehensive performance advantage.","manuscriptTitle":"Defect detection of Printed circuit board Surface based on an improved YOLOv8 with FasterNet backbone algorithms","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-30 05:07:09","doi":"10.21203/rs.3.rs-4823049/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-08-28T01:53:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-27T10:08:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"23917136233730460210199259264459799760","date":"2024-08-07T11:03:56+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-07T01:36:02+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-07-30T09:33:04+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-30T09:31:42+00:00","index":"","fulltext":""},{"type":"submitted","content":"Signal, Image and Video Processing","date":"2024-07-29T15:12:51+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"signal-image-and-video-processing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"sivp","sideBox":"Learn more about [Signal, Image and Video Processing](http://link.springer.com/journal/11760)","snPcode":"11760","submissionUrl":"https://submission.nature.com/new-submission/11760/3","title":"Signal, Image and Video Processing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"161f7fd0-e295-4e7c-a19a-d19ae274f2ce","owner":[],"postedDate":"August 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-12-09T16:07:40+00:00","versionOfRecord":{"articleIdentity":"rs-4823049","link":"https://doi.org/10.1007/s11760-024-03646-8","journal":{"identity":"signal-image-and-video-processing","isVorOnly":false,"title":"Signal, Image and Video Processing"},"publishedOn":"2024-12-07 15:58:07","publishedOnDateReadable":"December 7th, 2024"},"versionCreatedAt":"2024-08-30 05:07:09","video":"","vorDoi":"10.1007/s11760-024-03646-8","vorDoiUrl":"https://doi.org/10.1007/s11760-024-03646-8","workflowStages":[]},"version":"v1","identity":"rs-4823049","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4823049","identity":"rs-4823049","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}