Tablecert: YOLO and TATR Enhanced Models to Boost Table Detection and Recognition in Legacy Documents

Tablecert: YOLO and TATR Enhanced Models to Boost Table Detection and Recognition in Legacy Documents | 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 Tablecert: YOLO and TATR Enhanced Models to Boost Table Detection and Recognition in Legacy Documents Patrick Ferreira Barroso, Wilson de Souza Melo Junior, Rodrigo Pereira David, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8864429/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 The digital transformation of legacy documents remains challenging, as these documents are often unstructured and contain complex table layouts (e.g., watermarks, spaced headers, closely spaced tables, nested structures, and double borders) that degrade the performance of conventional table detection and recognition systems. We propose a modular, plug-and-play adaptation framework for YOLO-based table detection and Table Transformer (TATR)-based structure recognition, combining parameter-efficient LoRA fine-tuning with lightweight architectural modules (e.g., frequency-domain filtering and structural refinements). We evaluate the framework on a dataset of calibration certificates using a controlled training and evaluation protocol with standard detection and structure metrics. The adapted models outperform their respective baselines, mitigating layout-related challenges, and achieve F1-scores of 0.9999 (YOLO) and 0.9640 (TATR), alongside reduced validation loss. The best YOLO adaptation improves robustness in table detection under challenging visual artifacts, whereas the TATR-V6 yields stronger structural recognition. Finally, we show that the proposed FreqFilter2D module is a promising drop-in component for other computer vision architectures. Artificial Intelligence and Machine Learning Information Retrieval and Management Computer Vision Deep Learning Digital Calibration Certificates Digital Transformation for Metrology Fine-Tuning Low-Rank Adaptation Full Text Additional Declarations The authors declare no competing interests. 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-8864429","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":590501032,"identity":"4dbc7436-b2ef-4efd-b9e2-28088f533fe3","order_by":0,"name":"Patrick Ferreira Barroso","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7UlEQVRIiWNgGAWjYDACCSjNz4wsythAhBbJZhCZQIoWgwPEajGXbn72uaKiTs74OO/RDR9/3JNj4F98TIJxxz2cWiznHDOeeebMYWOzw3xpN2ckFBszSDxLk2A8U4xTi8GNBGPGxrYDidsO85jd5klISGyQOGNswNiWgEdL+meglrrEzc1ALX+I05IDsoU5cQMzUAsDSAt/j+EDfFos55wpZmwA+kUC6LCbPWkJxmwSbIkPEs/g1mIu3b6ZsQEYYvz9Z8xu/LBJkOPnP3zgwMcdeByGIcImkYCIH+K0MPAfwKN+FIyCUTAKRiIAAK9uU7rKx+/xAAAAAElFTkSuQmCC","orcid":"","institution":"National Institute of Metrology, Quality and Technology (INMETRO)","correspondingAuthor":true,"prefix":"","firstName":"Patrick","middleName":"Ferreira","lastName":"Barroso","suffix":""},{"id":590501033,"identity":"e04384da-b0f9-4352-a5d2-4b3ca05205e3","order_by":1,"name":"Wilson de Souza Melo Junior","email":"","orcid":"","institution":"National Institute of Metrology, Quality and Technology (INMETRO)","correspondingAuthor":false,"prefix":"","firstName":"Wilson","middleName":"de Souza Melo","lastName":"Junior","suffix":""},{"id":590501034,"identity":"49dab587-565a-4d03-b71f-fd35579a6ffb","order_by":2,"name":"Rodrigo Pereira David","email":"","orcid":"","institution":"National Institute of Metrology, Quality and Technology (INMETRO)","correspondingAuthor":false,"prefix":"","firstName":"Rodrigo","middleName":"Pereira","lastName":"David","suffix":""},{"id":590501035,"identity":"2ba1bf7d-8c00-44fb-83ff-d2182dfcea60","order_by":3,"name":"Luiz Fernando Rust da Costa Carmo","email":"","orcid":"","institution":"National Institute of Metrology, Quality and Technology (INMETRO)","correspondingAuthor":false,"prefix":"","firstName":"Luiz","middleName":"Fernando Rust da Costa","lastName":"Carmo","suffix":""}],"badges":[],"createdAt":"2026-02-12 17:00:09","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8864429/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8864429/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102749414,"identity":"b1a8a177-9a3b-49f6-91a7-eeb238623a23","added_by":"auto","created_at":"2026-02-16 09:12:36","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1692950,"visible":true,"origin":"","legend":"","description":"","filename":"TABLECERTV4.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8864429/v1_covered_143fd86c-276f-4bbd-855d-7f5c7638bf9a.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eTablecert: YOLO and TATR Enhanced Models to Boost Table Detection and Recognition in Legacy Documents\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Instituto Nacional de Metrologia, Qualidade e Tecnologia","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":"Computer Vision, Deep Learning, Digital Calibration Certificates, Digital Transformation for Metrology, Fine-Tuning, Low-Rank Adaptation","lastPublishedDoi":"10.21203/rs.3.rs-8864429/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8864429/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe digital transformation of legacy \u0026nbsp;documents remains challenging, as these documents are often unstructured and contain complex table layouts (e.g., watermarks, spaced headers, closely spaced tables, nested structures, and double borders) that degrade the performance of conventional table detection and recognition systems. We propose a modular, plug-and-play adaptation framework for YOLO-based table detection and Table Transformer (TATR)-based structure recognition, combining parameter-efficient LoRA fine-tuning with lightweight architectural modules (e.g., frequency-domain filtering and structural refinements). We evaluate the framework on a dataset of calibration certificates using a controlled training and evaluation protocol with standard detection and structure metrics. The adapted models outperform their respective baselines, mitigating layout-related challenges, and achieve F1-scores of 0.9999 (YOLO) and 0.9640 (TATR), alongside reduced validation loss. The best YOLO adaptation improves robustness in table detection under challenging visual artifacts, whereas the TATR-V6 yields stronger structural recognition. Finally, we show that the proposed FreqFilter2D module is a promising drop-in component for other computer vision architectures.\u003c/p\u003e","manuscriptTitle":"Tablecert: YOLO and TATR Enhanced Models to Boost Table Detection and Recognition in Legacy Documents","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-16 06:24:59","doi":"10.21203/rs.3.rs-8864429/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":"c06ab0db-a977-47ac-ac21-265e1f7c8da4","owner":[],"postedDate":"February 16th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62839806,"name":"Artificial Intelligence and Machine Learning"},{"id":62839807,"name":"Information Retrieval and Management"}],"tags":[],"updatedAt":"2026-02-16T06:24:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-16 06:24:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8864429","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8864429","identity":"rs-8864429","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}