GujaratiHCR: A Hybrid Deep Learning Approach to Handwritten Character Recognition of Gujarati Language

GujaratiHCR: A Hybrid Deep Learning Approach to Handwritten Character Recognition of Gujarati Language | 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 GujaratiHCR: A Hybrid Deep Learning Approach to Handwritten Character Recognition of Gujarati Language Mehulkumar Dalwadi, Abhishek Mehta This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7338523/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 Handwritten Character Recognition (HCR) for low-resource languages such as Gujarati is still a cumbersome task because of the intricate nature and differential writing styles. This work presents GujaratiHCR, a deep learning hybrid model that tries to recognize handwritten Gujarati text both accurately and linguistically complete. The system initiated here starts off with a good preprocessing phase where grayscale conversion is done, then Adaptive Histogram Equalization (AHE) to enhance contrast, Non-Local Means (NLM) filter for noise filtering, and also morphological cleanup to eliminate the artifacts. This is followed by a refined text segmentation and line detection module based on Canny edge detection with contour-based approaches, and accurate character segmentation through a new combination of the Watershed Transform and a U-Net-based deep learning model. The core of recognition module employs a character-level CNN-LSTM-Transformer hybrid network complemented by n-gram feature extraction and linguistic correction using BERT-based mechanism to improve the coherence of the text. Subsequent to recognition, the system normalizes output by converting to Unicode and performs fine-grained tokenization in syllables and words. Additional linguistic processing involves Part-of-Speech (POS) tagging and Named Entity Recognition (NER) to determine grammatical structure and significant entities for downstream tasks such as speech synthesis. Experimental findings on various measures like accuracy, F-measure, PSNR, SSIM, and BLEU score illustrate that GujaratiHCR remarkably surpasses the performance of other available models like CNN, DCNN, CNN-LSTM, and CapsNet-LSTM with a holistic solution for precise and context-aware Gujarati handwritten text recognition. Gujarati Handwritten Character Recognition Deep Learning Text Segmentation Watershed Transform BERT Tokenization POS Tagging Named Entity Recognition 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-7338523","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":501531600,"identity":"4ae4d691-d021-4f09-8533-89017ce5ef19","order_by":0,"name":"Mehulkumar Dalwadi","email":"data:image/png;base64,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","orcid":"","institution":"Parul University","correspondingAuthor":true,"prefix":"","firstName":"Mehulkumar","middleName":"","lastName":"Dalwadi","suffix":""},{"id":501531601,"identity":"b5915c98-ec73-4880-ae15-bbb1d6e471bd","order_by":1,"name":"Abhishek Mehta","email":"","orcid":"","institution":"Parul University","correspondingAuthor":false,"prefix":"","firstName":"Abhishek","middleName":"","lastName":"Mehta","suffix":""}],"badges":[],"createdAt":"2025-08-10 11:23:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7338523/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7338523/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":89884505,"identity":"187620c8-7d59-4e63-a42a-3342fe210c19","added_by":"auto","created_at":"2025-08-26 06:17:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1175226,"visible":true,"origin":"","legend":"","description":"","filename":"MehulkumarDalwadiMenuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7338523/v1_covered_0b9ecf92-6b6d-48ee-b96e-0e2fc28e1541.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"GujaratiHCR: A Hybrid Deep Learning Approach to Handwritten Character Recognition of Gujarati Language","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":"Gujarati Handwritten Character Recognition, Deep Learning, Text Segmentation, Watershed Transform, BERT, Tokenization, POS Tagging, Named Entity Recognition","lastPublishedDoi":"10.21203/rs.3.rs-7338523/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7338523/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eHandwritten Character Recognition (HCR) for low-resource languages such as Gujarati is still a cumbersome task because of the intricate nature and differential writing styles. This work presents GujaratiHCR, a deep learning hybrid model that tries to recognize handwritten Gujarati text both accurately and linguistically complete. The system initiated here starts off with a good preprocessing phase where grayscale conversion is done, then Adaptive Histogram Equalization (AHE) to enhance contrast, Non-Local Means (NLM) filter for noise filtering, and also morphological cleanup to eliminate the artifacts. This is followed by a refined text segmentation and line detection module based on Canny edge detection with contour-based approaches, and accurate character segmentation through a new combination of the Watershed Transform and a U-Net-based deep learning model. The core of recognition module employs a character-level CNN-LSTM-Transformer hybrid network complemented by n-gram feature extraction and linguistic correction using BERT-based mechanism to improve the coherence of the text. Subsequent to recognition, the system normalizes output by converting to Unicode and performs fine-grained tokenization in syllables and words. Additional linguistic processing involves Part-of-Speech (POS) tagging and Named Entity Recognition (NER) to determine grammatical structure and significant entities for downstream tasks such as speech synthesis. Experimental findings on various measures like accuracy, F-measure, PSNR, SSIM, and BLEU score illustrate that GujaratiHCR remarkably surpasses the performance of other available models like CNN, DCNN, CNN-LSTM, and CapsNet-LSTM with a holistic solution for precise and context-aware Gujarati handwritten text recognition.\u003c/p\u003e","manuscriptTitle":"GujaratiHCR: A Hybrid Deep Learning Approach to Handwritten Character Recognition of Gujarati Language","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-08-20 03:37:53","doi":"10.21203/rs.3.rs-7338523/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":"23c966ce-130f-42bc-a1aa-fa6e4a832d54","owner":[],"postedDate":"August 20th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-08-26T06:09:14+00:00","versionOfRecord":[],"versionCreatedAt":"2025-08-20 03:37:53","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7338523","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7338523","identity":"rs-7338523","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}