Improving YOLO Detection Performance for High-Speed Steel Manufacturing via Normalized Statistical Contrast Layers

Improving YOLO Detection Performance for High-Speed Steel Manufacturing via Normalized Statistical Contrast Layers | 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 Improving YOLO Detection Performance for High-Speed Steel Manufacturing via Normalized Statistical Contrast Layers Reza Yazdi, Erfan Hassannayebi, Abdollah Moshiri, Mahsa Nazari, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8741554/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Automated surface defect detection in high-speed steel manufacturing demands robust, real-timecapable models that can reliably identify subtle, low-contrast anomalies under industrial conditions. While YOLO-based detectors offer an attractive speed–accuracy trade-off, their performance on challenging defect types—such as crazing or rolled-in scale—remains limited by insufficient local contrast representation. To address this, we propose MaxSigLayerNormalized, a novel, lightweight, and learnable contrast enhancement module derived from MaxSigLayer, which adaptively amplifies discriminative features using a statistically normalized formulation based on center, median, and mean statistics. Integrated via a plug-and-play block—MaxSigC2f—into both the backbone and neck of YOLOv8 andYOLOv11 architectures, our method improves detection sensitivity with negligible computational overhead (<2% increase in GFLOPs). Extensive experiments on the NEU-DET benchmark demonstrate consistent gains across model scales and splits, with [email protected] improving from 0.726 to 0.744 and [email protected] :0.95 from 0.375 to 0.399. The approach exhibits strong generalizability, robustness under stratified cross-validation, and particular efficacy on low-contrast defect classes. By combining statistical rigor with architectural compatibility, MaxSigLayerNormalized offers a practical, deployable enhancement for industrial vision systems requiring high reliability and real-time performance. YOLO Defect detection Enhanced YOLO Steel defect detection MaxSigLayerNormalized Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted 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-8741554","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":590272005,"identity":"4ad38a0a-8e45-4b4f-9dc9-604c456e2452","order_by":0,"name":"Reza Yazdi","email":"","orcid":"","institution":"Golestan University","correspondingAuthor":false,"prefix":"","firstName":"Reza","middleName":"","lastName":"Yazdi","suffix":""},{"id":590272016,"identity":"1348b63a-194e-4677-aa02-b2e695381292","order_by":1,"name":"Erfan Hassannayebi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABAklEQVRIie3OMWvCQBTA8Xc8SJcUZ5GSfoRz0UorfpVIB5fY0dnpuhjnK/ghMna88IYsabpmECoE7GIhbhYiNDq0OlyasdD7T++O9zsOwGT6g/Gf0QaVgwJAtgKwapJQHgny+gTtA4FfSPciyvLP56XDIz+ku2LpdB8RIJ+QlvRmXqfpx+t2ECcujcW6vSAEJhM94cqz4FIQC1KP03hKTGJDYXmjJ6/v2XYvaBC8bTjdFDSQiID7KpK6vFW+OQxSmxNYNDwSVkk2ndaVoPun+MEN/XI4kHCWjCo+Nsq2H4L68+iF8l1BfdkgttpNbrXku2t1clCapfOcaa01k8lk+o99AW7TYvAeGB62AAAAAElFTkSuQmCC","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":true,"prefix":"","firstName":"Erfan","middleName":"","lastName":"Hassannayebi","suffix":""},{"id":590272025,"identity":"2007aee2-8804-4a75-9594-dab0fffec263","order_by":2,"name":"Abdollah Moshiri","email":"","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Abdollah","middleName":"","lastName":"Moshiri","suffix":""},{"id":590272026,"identity":"2d5701af-7766-4be4-98ea-1c969e6dcf34","order_by":3,"name":"Mahsa Nazari","email":"","orcid":"","institution":"Newcastle University","correspondingAuthor":false,"prefix":"","firstName":"Mahsa","middleName":"","lastName":"Nazari","suffix":""},{"id":590272027,"identity":"f7e40953-0e0e-4944-82ac-c70a4f55194d","order_by":4,"name":"Somayeh Dolatkhah","email":"","orcid":"","institution":"K.N.Toosi University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Somayeh","middleName":"","lastName":"Dolatkhah","suffix":""},{"id":590272028,"identity":"e9fb6c57-c9c9-44d8-a62e-8e2596714b3a","order_by":5,"name":"Zahra Bagheri","email":"","orcid":"","institution":"Sharif University of Technology","correspondingAuthor":false,"prefix":"","firstName":"Zahra","middleName":"","lastName":"Bagheri","suffix":""},{"id":590272029,"identity":"0d7b1682-4041-4bc0-803c-4a34ac82e87a","order_by":6,"name":"Alireza Motadayen","email":"","orcid":"","institution":"Islamic Azad University, Tehran","correspondingAuthor":false,"prefix":"","firstName":"Alireza","middleName":"","lastName":"Motadayen","suffix":""}],"badges":[],"createdAt":"2026-01-30 13:23:08","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8741554/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8741554/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108182572,"identity":"07106b50-d19f-412b-a9f5-20e03873ce35","added_by":"auto","created_at":"2026-04-30 08:59:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1139485,"visible":true,"origin":"","legend":"","description":"","filename":"SIVP.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8741554/v1_covered_c18ebfce-a892-4bb3-a3d9-734a83b340fe.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improving YOLO Detection Performance for High-Speed Steel Manufacturing via Normalized Statistical Contrast Layers","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"YOLO, Defect detection, Enhanced YOLO, Steel defect detection, MaxSigLayerNormalized","lastPublishedDoi":"10.21203/rs.3.rs-8741554/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8741554/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomated surface defect detection in high-speed steel manufacturing demands robust, real-timecapable models that can reliably identify subtle, low-contrast anomalies under industrial conditions. While YOLO-based detectors offer an attractive speed–accuracy trade-off, their performance on challenging defect types—such as crazing or rolled-in scale—remains limited by insufficient local contrast representation. To address this, we propose MaxSigLayerNormalized, a novel, lightweight, and learnable contrast enhancement module derived from MaxSigLayer, which adaptively amplifies discriminative features using a statistically normalized formulation based on center, median, and mean statistics. Integrated via a plug-and-play block—MaxSigC2f—into both the backbone and neck of YOLOv8 andYOLOv11 architectures, our method improves detection sensitivity with negligible computational overhead (\u0026lt;2% increase in GFLOPs). Extensive experiments on the NEU-DET benchmark demonstrate consistent gains across model scales and splits, with [email protected] improving from 0.726 to 0.744 and [email protected] :0.95 from 0.375 to 0.399. The approach exhibits strong generalizability, robustness under stratified cross-validation, and particular efficacy on low-contrast defect classes. By combining statistical rigor with architectural compatibility, MaxSigLayerNormalized offers a practical, deployable enhancement for industrial vision systems requiring high reliability and real-time performance.\u003c/p\u003e","manuscriptTitle":"Improving YOLO Detection Performance for High-Speed Steel Manufacturing via Normalized Statistical Contrast Layers","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-16 04:38:55","doi":"10.21203/rs.3.rs-8741554/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"026b92be-4cd6-4d07-8d32-510295b867f5","owner":[],"postedDate":"February 16th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-04-30T03:10:42+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-30T03:24:49+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-16 04:38:55","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8741554","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8741554","identity":"rs-8741554","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}