YOLO-HCS: A YOLO-Based Framework for Small Defect Detection in Industrial Automated Optical Inspection

YOLO-HCS: A YOLO-Based Framework for Small Defect Detection in Industrial Automated Optical Inspection | 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 YOLO-HCS: A YOLO-Based Framework for Small Defect Detection in Industrial Automated Optical Inspection Chun-Cheng Lin, Hsiang-En Weng, Shin-Hang Lu, Heng-Yih Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9130149/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 13 You are reading this latest preprint version Abstract Connectors are used in electronic and industrial systems to establish electrical connections between components, with terminal surfaces playing a role in ensuring current transmission. Accurate defect detection on these terminals is vital for maintaining product reliability and quality. However, detecting small, irregular, and scale-varying defects remains a challenge for automated visual inspection systems. To tackle this challenge, this work presents You Only Look Once with Hierarchical Coordinate Sampling (YOLO-HCS), a defect detection framework that integrates hierarchical positive sample selection (HPSS) to improve training stability, coordinate attention (CA) to enhance spatial localization of small targets, and scylla-Intersection over Union (SIoU) loss to refine bounding box regression through geometric constraints. We validate the approach on two datasets collected using automated optical inspection (AOI) systems. The proposed YOLO-HCS framework integrates hierarchical positive sample selection, coordinate attention, and SIoU loss to improve the detection of small and irregular defects in industrial AOI environments. Experimental results on two real-world AOI datasets demonstrate that the YOLO- HCS model achieves higher mean average precision (mAP), outperforming YOLOv7 and other state-of-the-art detectors. Beyond accuracy gains, the proposed method improves production line reliability, reduces reliance on manual inspection, and satisfies the real-time speed requirements of high-throughput manufacturing. Its lightweight design enables efficient deployment in industrial AOI systems while maintaining real-time inspection capability. While validated on connector terminals, the approach is broadly transferable to semiconductor packaging, printed circuit board (PCB) inspection, and precision component manufacturing, offering a practical pathway to strengthen industrial quality control and reduce operational costs. Connector terminal inspection automated optical inspection small defect detection deep learning for manufacturing You Only Look Once object detection Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 18 May, 2026 Reviews received at journal 18 May, 2026 Reviews received at journal 03 May, 2026 Reviews received at journal 01 May, 2026 Reviews received at journal 26 Apr, 2026 Reviewers agreed at journal 19 Apr, 2026 Reviewers agreed at journal 15 Apr, 2026 Reviewers agreed at journal 14 Apr, 2026 Reviewers agreed at journal 13 Apr, 2026 Reviewers invited by journal 13 Apr, 2026 Editor assigned by journal 16 Mar, 2026 Submission checks completed at journal 16 Mar, 2026 First submitted to journal 15 Mar, 2026 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-9130149","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":625867601,"identity":"6d389940-b4a8-4a94-ba48-3010050bf826","order_by":0,"name":"Chun-Cheng Lin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYFAC5oYDDD9sePihXMYGwloYGw4w9qTJSDbAtTAT1sLAwHbYxuAAsVr42w82Hi7gYeYxvt1j+JmHwUZ2wwH+YxL4tEicSWw4PMOCjcfszhljaR6GNOMNB5jZ8GoxkGBsOMwDBGY3csyYeRgOJ4K03CCshU2Cx3gGWMt/orUY8BhIgLUcIKwF7BfengQeiRtpxZJzDJKNZx5mNv+BTwt/++HDn3l+/Lfnn5G88cObCjvZvuONjw3waUECHECFILUEYxIB2B8Qr3YUjIJRMApGFAAAh5dFZuty5/gAAAAASUVORK5CYII=","orcid":"","institution":"National Yang Ming Chiao Tung University","correspondingAuthor":true,"prefix":"","firstName":"Chun-Cheng","middleName":"","lastName":"Lin","suffix":""},{"id":625867606,"identity":"08ffb499-ca71-4eba-a5f8-48decd31eb1e","order_by":1,"name":"Hsiang-En Weng","email":"","orcid":"","institution":"National Yang Ming Chiao Tung University","correspondingAuthor":false,"prefix":"","firstName":"Hsiang-En","middleName":"","lastName":"Weng","suffix":""},{"id":625867607,"identity":"b5825bb2-858a-479b-a7b5-f9dea9b1bb4c","order_by":2,"name":"Shin-Hang Lu","email":"","orcid":"","institution":"Yuan Ze University","correspondingAuthor":false,"prefix":"","firstName":"Shin-Hang","middleName":"","lastName":"Lu","suffix":""},{"id":625867609,"identity":"e19a905d-0bf0-4753-bc56-ff4d027c1151","order_by":3,"name":"Heng-Yih Liu","email":"","orcid":"","institution":"Yuan Ze University","correspondingAuthor":false,"prefix":"","firstName":"Heng-Yih","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2026-03-15 16:53:33","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9130149/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9130149/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107432908,"identity":"3a04bda2-d5db-47d2-8527-6fe39abf293e","added_by":"auto","created_at":"2026-04-21 12:41:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":760216,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9130149/v1_covered_315676d9-6dbd-4c15-8ae3-12b7bf7d5da8.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"YOLO-HCS: A YOLO-Based Framework for Small Defect Detection in Industrial Automated Optical Inspection","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Connector terminal inspection, automated optical inspection, small defect detection, deep learning for manufacturing, You Only Look Once object detection","lastPublishedDoi":"10.21203/rs.3.rs-9130149/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9130149/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eConnectors are used in electronic and industrial systems to establish electrical connections between components, with terminal surfaces playing a role in ensuring current transmission. Accurate defect detection on these terminals is vital for maintaining product reliability and quality. However, detecting small, irregular, and scale-varying defects remains a challenge for automated visual inspection systems. To tackle this challenge, this work presents You Only Look Once with Hierarchical Coordinate Sampling (YOLO-HCS), a defect detection framework that integrates hierarchical positive sample selection (HPSS) to improve training stability, coordinate attention (CA) to enhance spatial localization of small targets, and scylla-Intersection over Union (SIoU) loss to refine bounding box regression through geometric constraints. We validate the approach on two datasets collected using automated optical inspection (AOI) systems. The proposed YOLO-HCS framework integrates hierarchical positive sample selection, coordinate attention, and SIoU loss to improve the detection of small and irregular defects in industrial AOI environments. Experimental results on two real-world AOI datasets demonstrate that the YOLO- HCS model achieves higher mean average precision (mAP), outperforming YOLOv7 and other state-of-the-art detectors. Beyond accuracy gains, the proposed method improves production line reliability, reduces reliance on manual inspection, and satisfies the real-time speed requirements of high-throughput manufacturing. Its lightweight design enables efficient deployment in industrial AOI systems while maintaining real-time inspection capability. While validated on connector terminals, the approach is broadly transferable to semiconductor packaging, printed circuit board (PCB) inspection, and precision component manufacturing, offering a practical pathway to strengthen industrial quality control and reduce operational costs.\u003c/p\u003e","manuscriptTitle":"YOLO-HCS: A YOLO-Based Framework for Small Defect Detection in Industrial Automated Optical Inspection","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 12:40:55","doi":"10.21203/rs.3.rs-9130149/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-05-18T12:49:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-18T11:28:55+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T17:30:23+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T07:20:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-26T09:41:15+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"273887375945440272717098605743350917865","date":"2026-04-20T00:12:09+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"73686394458769416587100594402066655002","date":"2026-04-15T16:09:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"45243526016047603626106205908964648755","date":"2026-04-15T02:52:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"247014633705761899218762081697816275412","date":"2026-04-13T16:33:13+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-13T16:05:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-16T05:24:16+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-16T05:24:10+00:00","index":"","fulltext":""},{"type":"submitted","content":"Machine Vision and Applications","date":"2026-03-15T16:45:56+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"machine-vision-and-applications","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"mvap","sideBox":"Learn more about [Machine Vision and Applications](https://www.springer.com/journal/138)","snPcode":"138","submissionUrl":"https://submission.springernature.com/new-submission/138/3","title":"Machine Vision and Applications","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"2c8023c2-34f5-4b34-8e98-f666f8f5893f","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Revision requested","date":"2026-05-18T12:49:27+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-18T11:28:55+00:00","index":23,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-03T17:30:23+00:00","index":22,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T07:20:24+00:00","index":21,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-18T12:54:57+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 12:40:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9130149","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9130149","identity":"rs-9130149","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}