Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network

Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network | 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 Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network Zhuguo Zhou, Yujun Lu, Liye Lv This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4699134/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 3 You are reading this latest preprint version Abstract An enhanced clustering technique integrated with the YOLOv5s model addresses the challenges of detecting small defect targets on Printed Circuit Boards (PCBs), which are often difficult to locate and prone to high false detection rates. Initially, the method improves the original K-means algorithm by employing a self-developed Hierarchical Density-Based K-means (HDBK-means) algorithm to re-cluster and generate anchor boxes better suited to PCB fault characteristics. Secondly, it replaces the Concentrated-Comprehensive Convolution (C3) module with a novel combination of the Reparameterized Normalized Cross-Stage Partial Efficient Layer Aggregation Network (RepNCSPELAN) module and Spatial and Channel Reconstruction Convolution (SCConv), reducing the model's computational cost without compromising accuracy. Furthermore, the network is enhanced with an adaptive feature selection module to boost its performance in recognizing small targets. Lastly, the GDFPN (Generalized Dynamic Feature Pyramid Network) is used to achieve information interaction across different scales. further enhancing the network's detection accuracy. Comparative studies were conducted on a public PCB dataset. The experimental results demonstrate that the proposed algorithm achieves a mAP (mean Average Precision) of 98.6%, an accuracy of 99.2%, a model size of 10.9M, and an FPS (Frames Per Second) of 138.1. Compared to the original model, the proposed algorithm improves the mAP by 3.8% and the Precision (P) by 2.9%, while reducing the model size by 20.4%, thus fulfilling the requirements for easy deployment. Printed circuit boards YOLOv5s Clustering algorithms Feature selection module Feature fusion Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editor assigned by journal 09 Jul, 2024 Submission checks completed at journal 08 Jul, 2024 First submitted to journal 07 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-4699134","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":324700809,"identity":"69d149c6-1aa2-44d8-88d5-1a9125ad6326","order_by":0,"name":"Zhuguo Zhou","email":"","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Zhuguo","middleName":"","lastName":"Zhou","suffix":""},{"id":324700810,"identity":"36d44e76-e209-4b28-b42a-df77c0920d5b","order_by":1,"name":"Yujun Lu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA2klEQVRIiWNgGAWjYBACPjBZwMDMDxVgbCCkhQ2syICBWbIBopp4LQwGB4jWIpF8/AGDwWF24/PHnz/mYbCR3XCA+dkD/FrSEoG2HGY2O3DGsJmHIc14wwE2cwP8WnIMIVoO9jACtRxO3HCAh00Cv5b8j2Atxs3sD4Fa/hOjJYcRrMWAjQHksANEaOF5ZjiDwSCdWeIMj+HMOQbJxjMPs5nh1cLPnvzgA0OFdTJ///EHH95U2Mn2HW9+hlcLCDD/YWhOhjBBQcVMSD0E1NkRp24UjIJRMApGJAAAUEVBqfsvyaEAAAAASUVORK5CYII=","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":true,"prefix":"","firstName":"Yujun","middleName":"","lastName":"Lu","suffix":""},{"id":324700811,"identity":"7d3ae119-08df-4d98-8a27-398c8fbbb817","order_by":2,"name":"Liye Lv","email":"","orcid":"","institution":"Zhejiang Sci-Tech University","correspondingAuthor":false,"prefix":"","firstName":"Liye","middleName":"","lastName":"Lv","suffix":""}],"badges":[],"createdAt":"2024-07-07 07:21:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4699134/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4699134/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":61579032,"identity":"de462c08-c5fb-4d1d-91e1-59d522befb9a","added_by":"auto","created_at":"2024-08-01 13:00:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1658166,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4699134/v1_covered_da190d8a-255b-4dd7-aa17-84253a2e5948.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network","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":"computer-supported-cooperative-work-cscw","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cosu","sideBox":"Learn more about [Computer Supported Cooperative Work (CSCW)](http://link.springer.com/journal/10606)","snPcode":"10606","submissionUrl":"https://submission.nature.com/new-submission/10606/3","title":"Computer Supported Cooperative Work (CSCW)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Printed circuit boards, YOLOv5s, Clustering algorithms, Feature selection module, Feature fusion","lastPublishedDoi":"10.21203/rs.3.rs-4699134/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4699134/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAn enhanced clustering technique integrated with the YOLOv5s model addresses the challenges of detecting small defect targets on Printed Circuit Boards (PCBs), which are often difficult to locate and prone to high false detection rates. Initially, the method improves the original K-means algorithm by employing a self-developed Hierarchical Density-Based K-means (HDBK-means) algorithm to re-cluster and generate anchor boxes better suited to PCB fault characteristics. Secondly, it replaces the Concentrated-Comprehensive Convolution (C3) module with a novel combination of the Reparameterized Normalized Cross-Stage Partial Efficient Layer Aggregation Network (RepNCSPELAN) module and Spatial and Channel Reconstruction Convolution (SCConv), reducing the model's computational cost without compromising accuracy. Furthermore, the network is enhanced with an adaptive feature selection module to boost its performance in recognizing small targets. Lastly, the GDFPN (Generalized Dynamic Feature Pyramid Network) is used to achieve information interaction across different scales. further enhancing the network's detection accuracy. Comparative studies were conducted on a public PCB dataset. The experimental results demonstrate that the proposed algorithm achieves a mAP (mean Average Precision) of 98.6%, an accuracy of 99.2%, a model size of 10.9M, and an FPS (Frames Per Second) of 138.1. Compared to the original model, the proposed algorithm improves the mAP by 3.8% and the Precision (P) by 2.9%, while reducing the model size by 20.4%, thus fulfilling the requirements for easy deployment.\u003c/p\u003e","manuscriptTitle":"Enhanced Small Defect Detection on PCBs Using Lightweight YOLOv5s with Hierarchical Clustering and Dynamic Feature Pyramid Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-01 12:52:46","doi":"10.21203/rs.3.rs-4699134/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorAssigned","content":"","date":"2024-07-09T11:59:20+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-07-09T03:41:18+00:00","index":"","fulltext":""},{"type":"submitted","content":"Computer Supported Cooperative Work (CSCW)","date":"2024-07-07T07:18:26+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"computer-supported-cooperative-work-cscw","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"cosu","sideBox":"Learn more about [Computer Supported Cooperative Work (CSCW)](http://link.springer.com/journal/10606)","snPcode":"10606","submissionUrl":"https://submission.nature.com/new-submission/10606/3","title":"Computer Supported Cooperative Work (CSCW)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"9754b25a-ced5-482f-8fcb-cddce4adf6b6","owner":[],"postedDate":"August 1st, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-08-01T12:52:46+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-01 12:52:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4699134","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4699134","identity":"rs-4699134","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}