Contrastive Self-Supervised Learning with Domain-Specific Augmentation for Script Classification of Chinese Ancient Manuscripts

Contrastive Self-Supervised Learning with Domain-Specific Augmentation for Script Classification of Chinese Ancient Manuscripts | 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 Contrastive Self-Supervised Learning with Domain-Specific Augmentation for Script Classification of Chinese Ancient Manuscripts Haoran Xu, Yixin Xia, Yuxin Deng, Zhixin Liu This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6539019/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 Classification of Chinese ancient manuscripts is crucial for historical and cultural preservation but faces significant challenges due to complex script variability, material degradation, and limited annotated datasets. This study proposes a novel framework leveraging contrastive self-supervised learning for accurate identification and classification of Chinese ancient manuscript scripts, including Seal, Clerical, Cursive, Regular, and Running scripts. Utilizing publicly accessible datasets, particularly the CASIA Ancient Chinese Handwritten Character Database, the HCL2000 Historical Chinese Literature Dataset, and the HUSAM-SinoCDCS Collection, our method integrates domain-specific augmentations that reflect realistic manuscript conditions such as faded ink, fragmentation, and surface damage. Experimental results demonstrate that the proposed framework consistently outperforms traditional supervised learning baselines, achieving higher accuracy and robustness even under low-resource labeled scenarios. The outcomes of this research contribute to advancing computational methods for ancient document analysis and offer valuable tools for digital humanities efforts focused on preserving Chinese cultural heritage. Information Theory Theoretical Computer Science Computer Architecture and Engineering Chinese Ancient Manuscripts Contrastive Self-Supervised Learning Ancient Document Analysis 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-6539019","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":448556477,"identity":"09e314c4-78fa-4ea7-bf73-db1f92e2f4cc","order_by":0,"name":"Haoran Xu","email":"","orcid":"","institution":"University of Nottingham Ningbo China","correspondingAuthor":false,"prefix":"","firstName":"Haoran","middleName":"","lastName":"Xu","suffix":""},{"id":448556531,"identity":"bc6b8d59-e070-4a06-87c6-45d7af88dcf4","order_by":1,"name":"Yixin Xia","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYFACxgYGhgP/6vtB7IQC4rUcYJzZANJiQLRNQC0bDoAYxGgxn5Hc+LnizB1m4/OrEz88MGCQ5xc7gF+LzI3EZskzN56xmd14u1kC6DDDmbMT8GuRkEhskGz4wMxjduPsBpCWBIPbhLU0/wRqkTCecXbzD2K1tEk23DhsYMDfu41IW3getlk2nElLkLjBu80iwUCCCL+wpz++2XDMJoG//+zmmz8qbOT5pQloQdIMVilBrHIQ4D9AiupRMApGwSgYSQAAaMtJq9DgznIAAAAASUVORK5CYII=","orcid":"","institution":"University of Nottingham Ningbo China","correspondingAuthor":true,"prefix":"","firstName":"Yixin","middleName":"","lastName":"Xia","suffix":""},{"id":448556609,"identity":"cea3d6bf-a0ae-45d4-8066-529fb70834fc","order_by":2,"name":"Yuxin Deng","email":"","orcid":"","institution":"University of Nottingham Ningbo China","correspondingAuthor":false,"prefix":"","firstName":"Yuxin","middleName":"","lastName":"Deng","suffix":""},{"id":448556610,"identity":"823538a6-bd50-4766-8d55-fbc51e0e33fe","order_by":3,"name":"Zhixin Liu","email":"","orcid":"","institution":"University of Nottingham Ningbo China","correspondingAuthor":false,"prefix":"","firstName":"Zhixin","middleName":"","lastName":"Liu","suffix":""}],"badges":[],"createdAt":"2025-04-27 08:15:28","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-6539019/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6539019/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":81602311,"identity":"1c3060a2-ff61-404b-8a08-130f11e24af5","added_by":"auto","created_at":"2025-04-29 04:36:06","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":756965,"visible":true,"origin":"","legend":"","description":"","filename":"Paper3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6539019/v1_covered_ca86d1ed-9ec9-49a8-a0d0-ecde6b0e7d0f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eContrastive Self-Supervised Learning with Domain-Specific Augmentation for Script Classification of Chinese Ancient Manuscripts\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of Nottingham Ningbo China","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":"Chinese Ancient Manuscripts, Contrastive Self-Supervised Learning, Ancient Document Analysis","lastPublishedDoi":"10.21203/rs.3.rs-6539019/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6539019/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eClassification of Chinese ancient manuscripts is crucial for historical and cultural preservation but faces significant challenges due to complex script variability, material degradation, and limited annotated datasets. This study proposes a novel framework leveraging contrastive self-supervised learning for accurate identification and classification of Chinese ancient manuscript scripts, including Seal, Clerical, Cursive, Regular, and Running scripts. Utilizing publicly accessible datasets, particularly the CASIA Ancient Chinese Handwritten Character Database, the HCL2000 Historical Chinese Literature Dataset, and the HUSAM-SinoCDCS Collection, our method integrates domain-specific augmentations that reflect realistic manuscript conditions such as faded ink, fragmentation, and surface damage. Experimental results demonstrate that the proposed framework consistently outperforms traditional supervised learning baselines, achieving higher accuracy and robustness even under low-resource labeled scenarios. The outcomes of this research contribute to advancing computational methods for ancient document analysis and offer valuable tools for digital humanities efforts focused on preserving Chinese cultural heritage.\u003c/p\u003e","manuscriptTitle":"Contrastive Self-Supervised Learning with Domain-Specific Augmentation for Script Classification of Chinese Ancient Manuscripts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-04-29 04:27:59","doi":"10.21203/rs.3.rs-6539019/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":"c19f99f2-7d83-4846-9616-8d05a4aa15d1","owner":[],"postedDate":"April 29th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":47736370,"name":"Information Theory"},{"id":47736371,"name":"Theoretical Computer Science"},{"id":47736372,"name":"Computer Architecture and Engineering"}],"tags":[],"updatedAt":"2025-04-29T04:27:59+00:00","versionOfRecord":[],"versionCreatedAt":"2025-04-29 04:27:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6539019","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6539019","identity":"rs-6539019","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}