Regional Feature Analysis for Automated Welding Defect Classification: Statistical Decomposition Approaches

Regional Feature Analysis for Automated Welding Defect Classification: Statistical Decomposition Approaches | 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 Regional Feature Analysis for Automated Welding Defect Classification: Statistical Decomposition Approaches Mingming Zhang, Jan Polzer, Shi Cheng, Qunfeng Liu, Xun Xu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9307161/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 10 You are reading this latest preprint version Abstract Automated welding defect detection is a critical challenge in manufacturing, where traditional image analysis fails to capture the spatially-dependent nature of defects. This study addresses this limitation by proposing and systematically evaluating a toolkit of five regional feature extraction methodologies. The proposed methods capture defect signatures across distinct regions: Cumulative Projection Profiling (CPP) for high-dimensional spatial analysis (6184 features); Multi-Scale Spatial Grid Feature Extraction (MSSGFE) for hierarchical statistics (336 features); Regional Edge Direction Analysis (REDA) for edge orientations (64 features); FFT Grid Feature Extraction (FFTGFE) for frequency-domain patterns (64 features); and LBP Directional Strip Analysis (LBPDSA) for textural characteristics (32 features).A standardized preprocessing pipeline and a consistent deep learning framework were used to ensure a rigorous comparative evaluation. Experimental results show a clear performance trade-off between computational efficiency and data footprint. The CPP, MSSGFE, and FFTGFE methods demonstrated suitability for high-throughput systems, achieving classification accuracies above 99% at processing speeds exceeding 95 FPS. In contrast, the REDA and LBPDSA methods produced extremely compact feature vectors ( \((<)\) 260 bytes), making them ideal for deployment on resource-constrained embedded devices. The findings establish a practical framework for implementing automated inspection systems, enabling engineers to select an optimal methodology based on specific hardware constraints and application requirements in Industry 4.0 environments. Welding defect detection Automated quality inspection Machine learning Computer vision Feature extraction Image processing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 15 Apr, 2026 Reviews received at journal 09 Apr, 2026 Reviews received at journal 08 Apr, 2026 Reviewers agreed at journal 07 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers agreed at journal 06 Apr, 2026 Reviewers invited by journal 06 Apr, 2026 Editor assigned by journal 05 Apr, 2026 Submission checks completed at journal 04 Apr, 2026 First submitted to journal 02 Apr, 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-9307161","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":620057687,"identity":"f4f6f0f9-6f60-47ea-9b2f-5872c7cc321f","order_by":0,"name":"Mingming Zhang","email":"data:image/png;base64,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","orcid":"","institution":"University of Auckland","correspondingAuthor":true,"prefix":"","firstName":"Mingming","middleName":"","lastName":"Zhang","suffix":""},{"id":620057688,"identity":"e7ac1d66-fac9-4485-88b7-397b1eed0642","order_by":1,"name":"Jan Polzer","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Jan","middleName":"","lastName":"Polzer","suffix":""},{"id":620057689,"identity":"a4f4a42c-2de2-47b0-8da4-d2e5906a59a3","order_by":2,"name":"Shi Cheng","email":"","orcid":"","institution":"Shaanxi Normal University","correspondingAuthor":false,"prefix":"","firstName":"Shi","middleName":"","lastName":"Cheng","suffix":""},{"id":620057690,"identity":"5ed91902-aa31-4a3a-abcb-0dbc6267d78c","order_by":3,"name":"Qunfeng Liu","email":"","orcid":"","institution":"Dongguan University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Qunfeng","middleName":"","lastName":"Liu","suffix":""},{"id":620057691,"identity":"78eaeb82-9ca5-4ac2-9742-5aad9d583238","order_by":4,"name":"Xun Xu","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Xun","middleName":"","lastName":"Xu","suffix":""}],"badges":[],"createdAt":"2026-04-02 22:53:13","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9307161/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9307161/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106960693,"identity":"3bf37ed8-6983-49d8-9483-25069886bf6f","added_by":"auto","created_at":"2026-04-15 09:22:41","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":8402398,"visible":true,"origin":"","legend":"","description":"","filename":"regionalspringer2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9307161/v1_covered_0bff444d-525e-4c8c-bf90-a075f0b6912d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Regional Feature Analysis for Automated Welding Defect Classification: Statistical Decomposition Approaches","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":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Welding defect detection, Automated quality inspection, Machine learning, Computer vision, Feature extraction, Image processing","lastPublishedDoi":"10.21203/rs.3.rs-9307161/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9307161/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomated welding defect detection is a critical challenge in manufacturing, where traditional image analysis fails to capture the spatially-dependent nature of defects. This study addresses this limitation by proposing and systematically evaluating a toolkit of five regional feature extraction methodologies. The proposed methods capture defect signatures across distinct regions: Cumulative Projection Profiling (CPP) for high-dimensional spatial analysis (6184 features); Multi-Scale Spatial Grid Feature Extraction (MSSGFE) for hierarchical statistics (336 features); Regional Edge Direction Analysis (REDA) for edge orientations (64 features); FFT Grid Feature Extraction (FFTGFE) for frequency-domain patterns (64 features); and LBP Directional Strip Analysis (LBPDSA) for textural characteristics (32 features).A standardized preprocessing pipeline and a consistent deep learning framework were used to ensure a rigorous comparative evaluation. Experimental results show a clear performance trade-off between computational efficiency and data footprint. The CPP, MSSGFE, and FFTGFE methods demonstrated suitability for high-throughput systems, achieving classification accuracies above 99% at processing speeds exceeding 95 FPS. In contrast, the REDA and LBPDSA methods produced extremely compact feature vectors (\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\((\u0026lt;)\\)\u003c/span\u003e\u003c/span\u003e260 bytes), making them ideal for deployment on resource-constrained embedded devices. The findings establish a practical framework for implementing automated inspection systems, enabling engineers to select an optimal methodology based on specific hardware constraints and application requirements in Industry 4.0 environments.\u003c/p\u003e","manuscriptTitle":"Regional Feature Analysis for Automated Welding Defect Classification: Statistical Decomposition Approaches","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-13 02:14:28","doi":"10.21203/rs.3.rs-9307161/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2026-04-15T15:02:53+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-09T05:53:49+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-09T00:56:00+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"136976779418937234773166131507522661442","date":"2026-04-07T16:08:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307138929512543830620599156838645352513","date":"2026-04-07T02:23:13+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"240831166584449083986950083899282607721","date":"2026-04-07T02:05:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-07T02:01:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-06T02:41:11+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-04T10:38:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Machine Learning and Cybernetics","date":"2026-04-02T22:40:46+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-machine-learning-and-cybernetics","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jmlc","sideBox":"Learn more about [International Journal of Machine Learning and Cybernetics](http://actavetscand.biomedcentral.com/)","snPcode":"13042","submissionUrl":"https://submission.nature.com/new-submission/13042/3","title":"International Journal of Machine Learning and Cybernetics","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"f3d443f5-5357-4ca6-b0c4-d20d449fcea5","owner":[],"postedDate":"April 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-13T02:14:28+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-13 02:14:28","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9307161","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9307161","identity":"rs-9307161","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}