Khayyam Offline Persian Handwriting Dataset

Khayyam Offline Persian Handwriting Dataset | 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 Khayyam Offline Persian Handwriting Dataset Pourya Jafarzadeh, Padideh Choobdar, Vahid Mohammadi Safarzadeh This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5414436/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 is still an important application in machine learning. A basic requirement for any handwriting recognition application is the availability of comprehensive datasets. Standard labelled datasets play a significant role in training and evaluating learning algorithms. In this paper, we present the Khayyam dataset as another large unconstrained handwriting dataset for elements (words, sentences, letters, digits) of the Persian language. We intentionally concentrated on collecting Persian word samples which are rare in the currently available datasets. Khayyam's dataset contains 44000 words, 60000 letters, and 6000 digits. Moreover, the forms were filled out by 400 native Persian writers. To show the applicability of the dataset, machine learning algorithms are trained on the digits, letters, and word data and results are reported. This dataset is available for research and academic use. Persian/Arabic Handwriting Dataset Machine Learning 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-5414436","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":377743966,"identity":"6e6886e5-5a27-4755-8171-d5b166a4cd83","order_by":0,"name":"Pourya Jafarzadeh","email":"data:image/png;base64,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","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Pourya","middleName":"","lastName":"Jafarzadeh","suffix":""},{"id":377743967,"identity":"6cc2173d-5403-41be-8852-9f4224683d3f","order_by":1,"name":"Padideh Choobdar","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Padideh","middleName":"","lastName":"Choobdar","suffix":""},{"id":377743968,"identity":"fa67d85e-72f8-4103-9e4b-4e1c8f4c5219","order_by":2,"name":"Vahid Mohammadi Safarzadeh","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Vahid","middleName":"Mohammadi","lastName":"Safarzadeh","suffix":""}],"badges":[],"createdAt":"2024-11-08 07:23:21","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5414436/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5414436/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":92430415,"identity":"677b7cb0-9a20-4cd4-9c7f-566125535b4b","added_by":"auto","created_at":"2025-09-29 16:01:50","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":721616,"visible":true,"origin":"","legend":"","description":"","filename":"FinalVMSUplodedArxiv.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5414436/v1_covered_da59620d-caba-4a6e-ab64-d2712ce56c0f.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Khayyam Offline Persian Handwriting Dataset","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":"Persian/Arabic Handwriting Dataset, Machine Learning","lastPublishedDoi":"10.21203/rs.3.rs-5414436/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5414436/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHandwriting analysis is still an important application in machine learning. A basic requirement for any handwriting recognition application is the availability of comprehensive datasets. Standard labelled datasets play a significant role in training and evaluating learning algorithms. In this paper, we present the Khayyam dataset as another large unconstrained handwriting dataset for elements (words, sentences, letters, digits) of the Persian language. We intentionally concentrated on collecting Persian word samples which are rare in the currently available datasets. Khayyam's dataset contains 44000 words, 60000 letters, and 6000 digits. Moreover, the forms were filled out by 400 native Persian writers. To show the applicability of the dataset, machine learning algorithms are trained on the digits, letters, and word data and results are reported. This dataset is available for research and academic use.\u003c/p\u003e","manuscriptTitle":"Khayyam Offline Persian Handwriting Dataset","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-27 09:44:52","doi":"10.21203/rs.3.rs-5414436/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":"bfc5ac90-5996-4325-a36c-acb30f2ecf0f","owner":[],"postedDate":"November 27th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-05T21:08:27+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-27 09:44:52","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5414436","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5414436","identity":"rs-5414436","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}