SinFUND and SinOCR: Benchmarks for Sinhala Handwritten OCR and Template-Free Form Understanding

SinFUND and SinOCR: Benchmarks for Sinhala Handwritten OCR and Template-Free Form Understanding | 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 SinFUND and SinOCR: Benchmarks for Sinhala Handwritten OCR and Template-Free Form Understanding Kavishka Gunathilaka, Danusha Hewagama, Supul Pushpakumara, Thanuja D. Ambegoda This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6976719/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 9 You are reading this latest preprint version Abstract We introduce SinFUND and SinOCR, two novel datasets with benchmarks designed to enhance Optical Character Recognition (OCR) and template-free form understanding for Sinhala, a low-resource language spoken by approximately 16 million people in Sri Lanka. SinFUND is the first fully annotated dataset of 100 diverse, manually filled Sinhala forms, marking a significant advancement in form understanding research for Sinhala. SinOCR is the most extensive dataset for Sinhala OCR available to date, consisting of 100,000 images including 1,135 handwritten texts and texts printed in 200 different Sinhala fonts, representing a broad range of writing styles.This study outlines the development and annotation processes that ensure the high quality and practical applicability of these datasets in OCR and form understanding tasks. We also introduce novel baseline models optimized for these datasets, that demonstrate state-of-the-art performance in recognizing and interpreting Sinhala text, whether printed or handwritten. These models utilize a language-independent document understanding framework coupled with a multilingual language model, enhancing the efficiency and accuracy of processing multilingual forms.The benchmarks and datasets presented hold the potential to significantly support digital transformation in Sri Lanka by improving administrative efficiency and document accessibility in various sectors. Furthermore, our framework is scalable and adaptable, offering potential applications for similar OCR and form understanding tasks in other low-resource languages. Optical Character Recognition (OCR) form understanding Low-resource Languages Document Digitization Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 20 May, 2026 Reviews received at journal 30 Apr, 2026 Reviewers agreed at journal 04 Apr, 2026 Reviewers agreed at journal 01 Sep, 2025 Reviewers agreed at journal 30 Aug, 2025 Reviewers invited by journal 28 Aug, 2025 Editor assigned by journal 26 Jun, 2025 Submission checks completed at journal 26 Jun, 2025 First submitted to journal 25 Jun, 2025 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-6976719","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":508231442,"identity":"2dc47796-09dd-46c5-a9e7-b517325cadce","order_by":0,"name":"Kavishka Gunathilaka","email":"","orcid":"","institution":"University of Moratuwa","correspondingAuthor":false,"prefix":"","firstName":"Kavishka","middleName":"","lastName":"Gunathilaka","suffix":""},{"id":508231443,"identity":"68112001-9855-4019-b93a-58143e5a68e1","order_by":1,"name":"Danusha Hewagama","email":"","orcid":"","institution":"University of Moratuwa","correspondingAuthor":false,"prefix":"","firstName":"Danusha","middleName":"","lastName":"Hewagama","suffix":""},{"id":508231444,"identity":"76bacbf5-a8d8-45ab-a6f1-03d02d8dcd47","order_by":2,"name":"Supul Pushpakumara","email":"","orcid":"","institution":"University of Moratuwa","correspondingAuthor":false,"prefix":"","firstName":"Supul","middleName":"","lastName":"Pushpakumara","suffix":""},{"id":508231445,"identity":"73493665-8060-403a-b4e3-cc511e0f4a3b","order_by":3,"name":"Thanuja D. Ambegoda","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA6UlEQVRIiWNgGAWjYDACCRDBwyCHLMZ4sAGPDh6oFmMo3wBMEqGFgSGxgWgt9tLNzx7zyNil9/cfPsB0c88fBv72AwwHZ+CzReaYuTEPT3LujBtpCcw5zwwYJM4kMBzcgNdhCWbSPDzMuRskeAyYcw4AHXYD6LAHeLWkfwNqqU834D//AaxFnrCWHJAthxMMGHIYwFoMQFrwOuxGTpnkHJ7jhkC/GBzOOWDMY3gmsQGv99lnpG+TeNtTLc/ff/jh45wDcnJyxw8ffNiDRwsYMEJVHABZC+Q2ENIABD+IUDMKRsEoGAUjFwAAhF9JM6uyOmAAAAAASUVORK5CYII=","orcid":"","institution":"University of Moratuwa","correspondingAuthor":true,"prefix":"","firstName":"Thanuja","middleName":"D.","lastName":"Ambegoda","suffix":""}],"badges":[],"createdAt":"2025-06-25 16:38:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6976719/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6976719/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":90551793,"identity":"d7d60c71-be73-4148-ad43-47be72e94fdd","added_by":"auto","created_at":"2025-09-04 03:21:08","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2556936,"visible":true,"origin":"","legend":"","description":"","filename":"SinFUNDSinOCRIJDAR.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6976719/v1_covered_97ef5537-b686-476a-a23a-4d22cce64031.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"SinFUND and SinOCR: Benchmarks for Sinhala Handwritten OCR and Template-Free Form Understanding","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-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Optical Character Recognition (OCR), form understanding, Low-resource Languages, Document Digitization","lastPublishedDoi":"10.21203/rs.3.rs-6976719/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6976719/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"We introduce SinFUND and SinOCR, two novel datasets with benchmarks designed to enhance Optical Character Recognition (OCR) and template-free form understanding for Sinhala, a low-resource language spoken by approximately 16 million people in Sri Lanka. SinFUND is the first fully annotated dataset of 100 diverse, manually filled Sinhala forms, marking a significant advancement in form understanding research for Sinhala. SinOCR is the most extensive dataset for Sinhala OCR available to date, consisting of 100,000 images including 1,135 handwritten texts and texts printed in 200 different Sinhala fonts, representing a broad range of writing styles.This study outlines the development and annotation processes that ensure the high quality and practical applicability of these datasets in OCR and form understanding tasks. We also introduce novel baseline models optimized for these datasets, that demonstrate state-of-the-art performance in recognizing and interpreting Sinhala text, whether printed or handwritten. These models utilize a language-independent document understanding framework coupled with a multilingual language model, enhancing the efficiency and accuracy of processing multilingual forms.The benchmarks and datasets presented hold the potential to significantly support digital transformation in Sri Lanka by improving administrative efficiency and document accessibility in various sectors. Furthermore, our framework is scalable and adaptable, offering potential applications for similar OCR and form understanding tasks in other low-resource languages.","manuscriptTitle":"SinFUND and SinOCR: Benchmarks for Sinhala Handwritten OCR and Template-Free Form Understanding","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-04 03:13:02","doi":"10.21203/rs.3.rs-6976719/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"301048777159341458507347963286412646626","date":"2026-05-21T03:16:07+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-30T10:13:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"307803655272456578481882771211479598183","date":"2026-04-05T02:19:58+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"67176540729320995104989149006024880079","date":"2025-09-01T04:09:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"215890847867893831143365744053260616222","date":"2025-08-30T05:45:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-08-28T04:40:58+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-27T03:12:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-06-26T10:42:59+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal on Document Analysis and Recognition (IJDAR)","date":"2025-06-25T16:35:38+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"bb094c92-f90f-4bf9-8fc4-3b407797999a","owner":[],"postedDate":"September 4th, 2025","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"301048777159341458507347963286412646626","date":"2026-05-21T03:16:07+00:00","index":19,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-10-23T19:45:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-04 03:13:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6976719","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6976719","identity":"rs-6976719","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}