Deep learning-based approach for identifying writers' gender using Sinhala handwritten text

Deep learning-based approach for identifying writers' gender using Sinhala handwritten text | 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 Deep learning-based approach for identifying writers' gender using Sinhala handwritten text R.M.P.M. Ramanayake, W.A.C. Weerakoon This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7289914/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 Handwriting analysis plays a significant role in forensic science, psychological profiling, and document authentication due to the unique patterns in each person’s handwriting, influenced by motor skills and habits. Building on this, Artificial Intelligence and machine learning techniques have been widely applied to improve handwriting analysis in popular languages such as English and Arabic. However, similar research on Sinhala is limited due to its complex script, which includes a large number of characters and many combined forms. This study developed a model that accurately predicts a writer’s gender using Sinhala handwritten text. To achieve this, a diverse dataset was collected from individuals aged 15 to 70. Research combines traditional handwriting features such as skew angle, irregularity, and letter size with deep learning methods to improve prediction accuracy. In this study, KNN, SVM, RF, and DNN models were tested, and out of the models, the Deep Neural Network (DNN) was the best performer in classifying gender. This work contributes to forensic science and psychological research. Further, it lays a foundation for future studies on lesser-studied languages. Handwriting analysis Sinhala script Gender prediction Deep learning Full Text Additional Declarations No competing interests reported. Ethics Statement: An ethics review for this study was requested from the Ethics Review Committee of the University of Kelaniya, Sri Lanka, and the work was carried out in alignment with the Committee’s ethical standards and guidelines. Participant Consent Statement: Informed consent was obtained from all participants before data collection via a Google Sheet explaining the research purpose. Participants voluntarily agreed by choosing to participate and could decline freely. This process ensured informed consent before submitting handwriting samples. 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-7289914","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":498248379,"identity":"4b222500-3644-445f-b0e2-e8ff7eff150e","order_by":0,"name":"R.M.P.M. Ramanayake","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYNCCin88/DzMDWA2Hw9RWs4ckJHsYYRoYSNKC2PbARuDM8RqMZ929ujmCrY7PMZnDrY9YKixA2o5gF+LzO28tJtneJ7xmJ1tbDdgOJbMwMbbgF+LhHSO2c0GCWYes/OMbRIMbAcY2PgJOAyixYCZx7gfpOUf0VoSDvMY8Da2SQDDgRiHAf3ScCCNRwLofYnEvmQegt6XkM49drPxn409f0/yMYkP3+zk+HkSCLiMATkaElC5xGgZBaNgFIyCUYANAABe9jwf9LvaFwAAAABJRU5ErkJggg==","orcid":"","institution":"University of Kelaniya","correspondingAuthor":true,"prefix":"","firstName":"R.M.P.M.","middleName":"","lastName":"Ramanayake","suffix":""},{"id":498248380,"identity":"64b81e7c-71f0-4a3a-aa79-bc63712102a7","order_by":1,"name":"W.A.C. Weerakoon","email":"","orcid":"","institution":"University of Kelaniya","correspondingAuthor":false,"prefix":"","firstName":"W.A.C.","middleName":"","lastName":"Weerakoon","suffix":""}],"badges":[],"createdAt":"2025-08-04 10:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7289914/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7289914/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89459963,"identity":"c4518d42-aae4-46db-ab78-9a8b307ff56e","added_by":"auto","created_at":"2025-08-20 07:47:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":706360,"visible":true,"origin":"","legend":"","description":"","filename":"DeeplearningbasedapproachforidentifyingwritersgenderusingSinhalahandwrittentext.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7289914/v1_covered_a460f896-fbe2-4225-8d3d-27aa97819981.pdf"}],"financialInterests":"\u003cp\u003eNo competing interests reported.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics Statement:\u0026nbsp;\u003c/strong\u003eAn ethics review for this study was requested from the Ethics Review Committee of the University of Kelaniya, Sri Lanka, and the work was carried out in alignment with the Committee’s ethical standards and guidelines. Participant Consent Statement: Informed consent was obtained from all participants before data collection via a Google Sheet explaining the research purpose. Participants voluntarily agreed by choosing to participate and could decline freely. This process ensured informed consent before submitting handwriting samples.\u003c/p\u003e","formattedTitle":"Deep learning-based approach for identifying writers' gender using Sinhala handwritten text","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Handwriting analysis, Sinhala script, Gender prediction, Deep learning","lastPublishedDoi":"10.21203/rs.3.rs-7289914/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7289914/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHandwriting analysis plays a significant role in forensic science, psychological profiling, and document authentication due to the unique patterns in each person\u0026rsquo;s handwriting, influenced by motor skills and habits. Building on this, Artificial Intelligence and machine learning techniques have been widely applied to improve handwriting analysis in popular languages such as English and Arabic. However, similar research on Sinhala is limited due to its complex script, which includes a large number of characters and many combined forms. This study developed a model that accurately predicts a writer\u0026rsquo;s gender using Sinhala handwritten text. To achieve this, a diverse dataset was collected from individuals aged 15 to 70. Research combines traditional handwriting features such as skew angle, irregularity, and letter size with deep learning methods to improve prediction accuracy. In this study, KNN, SVM, RF, and DNN models were tested, and out of the models, the Deep Neural Network (DNN) was the best performer in classifying gender. This work contributes to forensic science and psychological research. Further, it lays a foundation for future studies on lesser-studied languages.\u003c/p\u003e","manuscriptTitle":"Deep learning-based approach for identifying writers' gender using Sinhala handwritten text","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-12 04:33:20","doi":"10.21203/rs.3.rs-7289914/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":"1087098c-e4bd-455d-b800-621f6398a788","owner":[],"postedDate":"August 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-20T07:38:55+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-12 04:33:20","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7289914","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7289914","identity":"rs-7289914","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}