A Novel Approach for Text Extraction and Word Segmentation from Handwritten Document Images Using CNN-RNN Technique

A Novel Approach for Text Extraction and Word Segmentation from Handwritten Document Images Using CNN-RNN Technique | 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 A Novel Approach for Text Extraction and Word Segmentation from Handwritten Document Images Using CNN-RNN Technique Dimpy Singh, Shalini Puri This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7305332/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Optical Character Recognition is a technology that takes an optical image of a character as input and generates the corresponding character as output. Its applications span a wide array, encompassing fields such as traffic surveillance, robotics, and the digitization of printed material. Implementation of Optical Character Recognition often involves Convolutional Neural Networks, a widely adopted architecture within the realm of deep learning. Traditional Convolutional Neural Network classifiers excel in learning crucial 2D features within images and subsequently classifying them. This classification process is typically carried out utilizing a SoftMax layer. In this paper, the authors described the optical character recognition by using refined versions of Convolutional Neural Networks and a Recurrent Neural Network classifier. The quality of text recognition was assessed using Character Error Rate and Word Error Rate. Two datasets, IAM and RIMES, were utilized, each divided into training and testing subsets. Accuracy, precision, and recall were calculated based on these divisions. The experimental findings revealed that the Convolutional Neural Networks method achieved notably higher accuracy rates across both datasets, reaching 89.3% and 86%, respectively. Physical sciences/Engineering Physical sciences/Mathematics and computing CNN (Convolutional Neural Network) Feature Extraction Optical Character Recognition (OCR) RNN Text Extraction Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 23 Dec, 2025 Reviews received at journal 10 Dec, 2025 Reviewers agreed at journal 28 Nov, 2025 Reviews received at journal 08 Oct, 2025 Reviewers agreed at journal 25 Sep, 2025 Reviewers agreed at journal 11 Sep, 2025 Reviewers invited by journal 05 Sep, 2025 Editor assigned by journal 05 Sep, 2025 Editor invited by journal 19 Aug, 2025 Submission checks completed at journal 12 Aug, 2025 First submitted to journal 12 Aug, 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-7305332","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":510721581,"identity":"8e2d741a-b420-4694-89f2-ea0ed740e9c9","order_by":0,"name":"Dimpy Singh","email":"","orcid":"","institution":"manipal university jaipur","correspondingAuthor":false,"prefix":"","firstName":"Dimpy","middleName":"","lastName":"Singh","suffix":""},{"id":510721582,"identity":"12569847-9d79-41e7-86ed-593fc6a95a5d","order_by":1,"name":"Shalini Puri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABJUlEQVRIie2RMUvDQBSAXzxolyeuGYL9C7elRbF/paXQLBdw6qLogZApOAf8FW6OCQd1kbpm6JAgdM4k7aD4Lia1NekueN8QPnJ8vHccgMHwF7HBikf01cQFAtYHJEwCdNoS2CZJtJ9Yh5PaGe6ftSe9h7sszp/64Np+rs6dC4ckO0qvl47bTSQUM/U74cs5j8cvNgwijyuBE9TCxHyFg3AsrWjRTOwRJYENPJ0CJQy1MNFRSP8lOw4aSS/yip+kj7dV8knJay7ZRzOBVOxMAVTfiR9ooSlWM+GpuNQJbb6CJMTnUpR/r+hSuUzChdey2GO+CW5O3e6UFZvwakhivYl3NXRPJkm2np01FqtAXj5ESHOheqmtHKJMYF0L7IjBYDD8d74A/JxyUXK28WQAAAAASUVORK5CYII=","orcid":"","institution":"manipal university jaipur","correspondingAuthor":true,"prefix":"","firstName":"Shalini","middleName":"","lastName":"Puri","suffix":""}],"badges":[],"createdAt":"2025-08-06 03:53:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7305332/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7305332/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91149328,"identity":"61013e9b-3123-4d4e-a708-2d0d0fbeabfd","added_by":"auto","created_at":"2025-09-12 06:48:49","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":840599,"visible":true,"origin":"","legend":"","description":"","filename":"DimpySinghFinalpaperrevs.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7305332/v1_covered_d8329636-b8c3-4bc9-8018-bbd3bdd1511a.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Novel Approach for Text Extraction and Word Segmentation from Handwritten Document Images Using CNN-RNN Technique","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":"CNN (Convolutional Neural Network), Feature Extraction, Optical Character Recognition (OCR), RNN, Text Extraction","lastPublishedDoi":"10.21203/rs.3.rs-7305332/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7305332/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eOptical Character Recognition is a technology that takes an optical image of a character as input and generates the corresponding character as output. Its applications span a wide array, encompassing fields such as traffic surveillance, robotics, and the digitization of printed material. Implementation of Optical Character Recognition often involves Convolutional Neural Networks, a widely adopted architecture within the realm of deep learning. Traditional Convolutional Neural Network classifiers excel in learning crucial 2D features within images and subsequently classifying them. This classification process is typically carried out utilizing a SoftMax layer. In this paper, the authors described the optical character recognition by using refined versions of Convolutional Neural Networks and a Recurrent Neural Network classifier. The quality of text recognition was assessed using Character Error Rate and Word Error Rate. Two datasets, IAM and RIMES, were utilized, each divided into training and testing subsets. Accuracy, precision, and recall were calculated based on these divisions. The experimental findings revealed that the Convolutional Neural Networks method achieved notably higher accuracy rates across both datasets, reaching 89.3% and 86%, respectively.\u003c/p\u003e","manuscriptTitle":"A Novel Approach for Text Extraction and Word Segmentation from Handwritten Document Images Using CNN-RNN Technique","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-11 16:10:25","doi":"10.21203/rs.3.rs-7305332/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2025-12-23T07:29:47+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-12-10T07:30:11+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19581665526592865087260044748367309544","date":"2025-11-29T03:51:37+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2025-10-08T09:29:23+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"218397334707430350019940726431867321754","date":"2025-09-25T10:52:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"286062265576648118694244009605080550492","date":"2025-09-11T05:08:43+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-05T10:09:04+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-09-05T10:07:44+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2025-08-19T07:42:48+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-12T15:49:15+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2025-08-12T15:45:46+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":"249e1971-dfae-42f0-ab31-6dd355ef27ff","owner":[],"postedDate":"September 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[{"id":54252768,"name":"Physical sciences/Engineering"},{"id":54252769,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-22T06:08:25+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-11 16:10:25","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7305332","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7305332","identity":"rs-7305332","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}