CRB-GAN: Generating Diverse Samples for Single-sample Character Classes in Handwritten Historical Documents

CRB-GAN: Generating Diverse Samples for Single-sample Character Classes in Handwritten Historical Documents | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || '';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Cite Share Download PDF Article CRB-GAN: Generating Diverse Samples for Single-sample Character Classes in Handwritten Historical Documents Leer Mao, Weilan Wang, Qiaoqiao Li, Xun Bao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6426206/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Enhancing sample diversity of minority classes within an extremely imbalanced handwritten character dataset poses a formidable challenge for GAN-based frameworks. This paper proposes Character Rebalance GAN (CRB-GAN), a novel deep generative model designed to address extreme class imbalance in historical handwritten recognition, especially for scripts like Chinese and Tibetan with many single-sample characters. Unlike prior approaches, CRB-GAN introduces a latent variable initialization method that aligns the mean and covariance of machine-printed and handwritten character embeddings, enabling diversity even before adversarial training. It further incorporates a class-aware loss strategy to balance fidelity and diversity. Experimental result shows that our method not only surpasses others in terms of sample quality and diversity but also demonstrates notable improvements in classification accuracy. Specifically, accuracy sees an impressive rise from 89.26% to 93.83% for Tibetan, and 95.36% to 97.53% for Chinese. CRB-GAN requires no language-specific morphological features, offering a universal, scalable solution for augmenting rare handwritten character classes. Physical sciences/Mathematics and computing/Information technology Physical sciences/Mathematics and computing/Software Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviews received at journal 12 Nov, 2025 Reviewers agreed at journal 05 Nov, 2025 Reviewers invited by journal 04 Nov, 2025 Editor assigned by journal 03 Jun, 2025 Editor invited by journal 14 Apr, 2025 Submission checks completed at journal 11 Apr, 2025 First submitted to journal 11 Apr, 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-6426206","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":540207707,"identity":"0dc44d68-e3af-48d5-9efe-2b7e71e2218b","order_by":0,"name":"Leer Mao","email":"","orcid":"","institution":"Northwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Leer","middleName":"","lastName":"Mao","suffix":""},{"id":540207708,"identity":"5845e523-0f30-4a9a-afc8-1b9fe2c23cb7","order_by":1,"name":"Weilan Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA70lEQVRIiWNgGAWjYPACCRkGBuYDzBBOAnFaeBgY2BJI0sIA1MJjQJwWg+NnD7/mqbDg4Z/d8026MOcwAz97jgHDzx14tJzJS7PmOSPBI3Hn7GbjmdsOM0j2vDFg7D2DW4vZgRwz49w2oF9u5G58zAvUYnAjx4CZsQ2PlvNvgFr+SfDI38h5cBikxZ6glhs5xo9zGyR4gIYzQmyRIKDF/sYbM+Y/xyR4DG+kGQP9ks4jceZZwcFePFok+3OMP86oqZOTu5H8TLpwm7Ucf3vyxgc/8WgBAjYJZB4PiDiAVwMwoXwgoGAUjIJRMApGOgAA7WZOz0Z5yqEAAAAASUVORK5CYII=","orcid":"","institution":"Northwest Minzu University","correspondingAuthor":true,"prefix":"","firstName":"Weilan","middleName":"","lastName":"Wang","suffix":""},{"id":540207709,"identity":"3cc52115-91bf-4294-9289-e2d55402fc2e","order_by":2,"name":"Qiaoqiao Li","email":"","orcid":"","institution":"Northwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Qiaoqiao","middleName":"","lastName":"Li","suffix":""},{"id":540207710,"identity":"9d0229f1-b024-45b2-b5cc-3b48ea55d5ce","order_by":3,"name":"Xun Bao","email":"","orcid":"","institution":"Northwest Minzu University","correspondingAuthor":false,"prefix":"","firstName":"Xun","middleName":"","lastName":"Bao","suffix":""}],"badges":[],"createdAt":"2025-04-11 08:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6426206/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6426206/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95228068,"identity":"b3335dd0-b074-4dde-93a0-daca67c28bec","added_by":"auto","created_at":"2025-11-05 16:33:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1161365,"visible":true,"origin":"","legend":"","description":"","filename":"TemplateforsubmissionstoScientificReports2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6426206/v1_covered_1965790f-f1d3-4a71-9902-4a57ab9e35df.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"CRB-GAN: Generating Diverse Samples for Single-sample Character Classes in Handwritten Historical Documents","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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-6426206/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6426206/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Enhancing sample diversity of minority classes within an extremely imbalanced handwritten character dataset poses a formidable challenge for GAN-based frameworks. This paper proposes Character Rebalance GAN (CRB-GAN), a novel deep generative model designed to address extreme class imbalance in historical handwritten recognition, especially for scripts like Chinese and Tibetan with many single-sample characters. Unlike prior approaches, CRB-GAN introduces a latent variable initialization method that aligns the mean and covariance of machine-printed and handwritten character embeddings, enabling diversity even before adversarial training. It further incorporates a class-aware loss strategy to balance fidelity and diversity. Experimental result shows that our method not only surpasses others in terms of sample quality and diversity but also demonstrates notable improvements in classification accuracy. Specifically, accuracy sees an impressive rise from 89.26% to 93.83% for Tibetan, and 95.36% to 97.53% for Chinese. CRB-GAN requires no language-specific morphological features, offering a universal, scalable solution for augmenting rare handwritten character classes.","manuscriptTitle":"CRB-GAN: Generating Diverse Samples for Single-sample Character Classes in Handwritten Historical Documents","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-05 13:07:51","doi":"10.21203/rs.3.rs-6426206/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"editorInvitedReview","content":"","date":"2025-11-12T14:22:34+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"99452062422272051935710822181577234887","date":"2025-11-05T06:52:52+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-11-04T10:21:38+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-06-03T04:52:43+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-04-14T17:39:39+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-04-11T09:09:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-04-11T07:52:30+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"d46a2f3e-53a7-4092-a48f-98458b1773d8","owner":[],"postedDate":"November 5th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":57460551,"name":"Physical sciences/Mathematics and computing/Information technology"},{"id":57460552,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-11-05T13:07:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-05 13:07:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6426206","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6426206","identity":"rs-6426206","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}