Real-Time Textile Defect Inspection: A Lightweight Super-Resolution Augmented Detection Pipeline

Real-Time Textile Defect Inspection: A Lightweight Super-Resolution Augmented Detection Pipeline | 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 Real-Time Textile Defect Inspection: A Lightweight Super-Resolution Augmented Detection Pipeline Ahmet Metin, Haydar Ozkan This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9227332/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 4 You are reading this latest preprint version Abstract The textile industry’s pursuit of defect-free production has driven the demand for efficient automated inspection systems, yet low-resolution imaging and subtle defect visibility remain critical challenges. Traditional manual inspection is limited by high labor costs, low repeatability, and subjective judgments, while high-resolution camera systems impose significant hardware constraints. This study proposes a cost-efficient pipeline that integrates lightweight super-resolution (SR) enhancement and real-time defect detection to narrow the performance gap with native high-resolution imaging. The SR module, derived from ESRGAN, is optimized via two complementary modifications: reducing block depth and channel width in residual-in-residual dense blocks (RRDB) and replacing standard convolutions with depthwise-separable convolutions (SRRDB), achieving a 24–44% reduction in per-patch latency and a 4–5× decrease in model size. Enhanced images are partitioned into 4×4 non-overlapping tiles, enabling precise defect localization and segmentation via single-stage detectors. Here we show that the pipeline delivers real-time throughput of 28.4 FPS on a high-performance computing (HPC) environment, with YOLOv8 variants achieving balanced accuracy—particularly for hole, oil stain, and object defects—with mAP50 values exceeding 0.84 on the TILDA dataset. For edge deployment on Raspberry Pi 4B/5, the lightweight SRRDB configuration reduces SR latency by 29% compared to baseline RRDB. This work demonstrates that low-cost cameras, augmented by optimized SR and tiled detection, can provide a practical alternative to high-resolution imaging systems, advancing industrial quality control in textile production while balancing computational efficiency and detection performance. The relevant code is available at https://github.com/ahmet-metin/textile-defect-sr-pipeline. Fabric defect detection YOLO ESRGAN Super-Resolution Real-Time defect detection Industrial quality control Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 27 Mar, 2026 Editor assigned by journal 27 Mar, 2026 Submission checks completed at journal 27 Mar, 2026 First submitted to journal 25 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-9227332","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":613366185,"identity":"20128562-b2a1-4aee-b386-dece4c19c96a","order_by":0,"name":"Ahmet Metin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA60lEQVRIiWNgGAWjYDACCRiDmYHxMYSVQISWA0DMw8zAbAxRnQARIayFgYFNmigt/LO7Ex9/YNgmZ8/Oe6y68MdhBn72HAPmj3vwWHLn7GaDAwy3jXmY+dJuz0g4zCDZ88aA4cAzPNbcyN0mAdSS2MPMY3abB6jF4EYOUAsel8nfyN3+A6ilHqSlGKTFnpAWA6AtQM/eTuABamEG2yJBQIvhjdzNEmcMbhv2HOYxlp6Rls4jceZZwYEzeLTI3cjd+KGi4rY8e/8Zw88FNtZy/O3JGx9U4NECdR6CyQMiCGoYBaNgFIyCUYAfAACfZFHhBqqxTAAAAABJRU5ErkJggg==","orcid":"","institution":"Bursa Technical University","correspondingAuthor":true,"prefix":"","firstName":"Ahmet","middleName":"","lastName":"Metin","suffix":""},{"id":613366186,"identity":"8abad42d-3ef6-41bb-965d-c3ae8ed5e3ed","order_by":1,"name":"Haydar Ozkan","email":"","orcid":"","institution":"Bursa Technical University","correspondingAuthor":false,"prefix":"","firstName":"Haydar","middleName":"","lastName":"Ozkan","suffix":""}],"badges":[],"createdAt":"2026-03-25 22:23:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9227332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9227332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107488297,"identity":"998ca1a1-f337-401b-9acd-790eda2a9430","added_by":"auto","created_at":"2026-04-22 02:44:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":16892322,"visible":true,"origin":"","legend":"","description":"","filename":"RealTimeTextileDefectInspectionALightweightSuperResolutionAugmentedDetectionPipeline.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9227332/v1_covered_17c80c9a-da1b-4de4-ae8e-3a4737b2d50e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Real-Time Textile Defect Inspection: A Lightweight Super-Resolution Augmented Detection Pipeline","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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Fabric defect detection, YOLO, ESRGAN, Super-Resolution, Real-Time defect detection, Industrial quality control","lastPublishedDoi":"10.21203/rs.3.rs-9227332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9227332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe textile industry\u0026rsquo;s pursuit of defect-free production has driven the demand for efficient automated inspection systems, yet low-resolution imaging and subtle defect visibility remain critical challenges. Traditional manual inspection is limited by high labor costs, low repeatability, and subjective judgments, while high-resolution camera systems impose significant hardware constraints. This study proposes a cost-efficient pipeline that integrates lightweight super-resolution (SR) enhancement and real-time defect detection to narrow the performance gap with native high-resolution imaging. The SR module, derived from ESRGAN, is optimized via two complementary modifications: reducing block depth and channel width in residual-in-residual dense blocks (RRDB) and replacing standard convolutions with depthwise-separable convolutions (SRRDB), achieving a 24\u0026ndash;44% reduction in per-patch latency and a 4\u0026ndash;5\u0026times; decrease in model size. Enhanced images are partitioned into 4\u0026times;4 non-overlapping tiles, enabling precise defect localization and segmentation via single-stage detectors. Here we show that the pipeline delivers real-time throughput of 28.4 FPS on a high-performance computing (HPC) environment, with YOLOv8 variants achieving balanced accuracy\u0026mdash;particularly for hole, oil stain, and object defects\u0026mdash;with mAP50 values exceeding 0.84 on the TILDA dataset. For edge deployment on Raspberry Pi 4B/5, the lightweight SRRDB configuration reduces SR latency by 29% compared to baseline RRDB. This work demonstrates that low-cost cameras, augmented by optimized SR and tiled detection, can provide a practical alternative to high-resolution imaging systems, advancing industrial quality control in textile production while balancing computational efficiency and detection performance. The relevant code is available at https://github.com/ahmet-metin/textile-defect-sr-pipeline.\u003c/p\u003e","manuscriptTitle":"Real-Time Textile Defect Inspection: A Lightweight Super-Resolution Augmented Detection Pipeline","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:52:06","doi":"10.21203/rs.3.rs-9227332/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-03-27T13:00:01+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-27T12:36:57+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-27T06:27:50+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2026-03-25T22:15:54+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8adc385c-a7e1-435d-9dcc-20d63e047dd3","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-05-07T07:39:34+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:52:06","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9227332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9227332","identity":"rs-9227332","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}