Leveraging Handwriting Recognition System for Identifying Learning Challenges and Adaptive Education Pathways

Leveraging Handwriting Recognition System for Identifying Learning Challenges and Adaptive Education Pathways | 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 Leveraging Handwriting Recognition System for Identifying Learning Challenges and Adaptive Education Pathways Aishwarya Waghmare, Avinash Golande This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9335896/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 The idea of handwriting is not something new and it was believed that the analysis of handwrit- ing can be one of the possible predictors of individual mental and behavioral patterns, especially in the school environment where the written expression is an essential factor. Nevertheless, the conventional methods of handwriting recognition are usually subjective and cannot be scaled. The paper introduces a new hybrid architecture combining deep-learning and manual feature- extraction to objectively and automatically test handwriting to make a prediction of the learning behaviors and academic measures of performance of students. The suggested system utilizes an elaborate preprocessing chain that does not distort the inherent properties of like stroke orienta- tion, spacing, curvature and structural patterns. The architecture of Hybrid CNN-Transformer is used to learn hierarchical visual representations based on handwritten images and is able to learn local stroke-level details as well as global writing styles. Simultaneously, a series of handcrafted characteristics, including slant angle, baseline alignment, word spacing, and densities of strokes, contour structure, and pressure approximation are obtained to offer readable information about writing habits. The two streams are merged into a single architecture to improve on classification accuracy and strength. The framework also has a behavioral analytics module, which uses ex- tracted features to educational indicators, such as legibility, consistency, motor control, attention to detail, presentation quality, and engagement patterns. On this understanding, the system will produce personalized feedback and visual dashboards to help the educators to pinpoint the pros and cons of the students. The results of experimental assessment prove the superiority of the hy- brid methodology over the standalone models because it is able to combine data-driven learning with domain-specific feature representation. The proposed system will consist of a flexible and expressive system to profiling the students based on hand writing that would translate into in- telligent educational systems and learning support. Future research directions include expansion of the model to implement it to transformer based architecture, longitudinal analysis of the data on student progress itself to trace the student progress with the long-term scope. Handwriting Analysis Feature Fusion Graphology-Inspired Analytics Student Behavior Analysis HOG Stroke Analysis Learning Analytics Personalized Education Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 05 May, 2026 Reviewers agreed at journal 04 May, 2026 Reviewers agreed at journal 29 Apr, 2026 Reviewers invited by journal 16 Apr, 2026 Editor assigned by journal 13 Apr, 2026 Submission checks completed at journal 06 Apr, 2026 First submitted to journal 06 Apr, 2026 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-9335896","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":627913080,"identity":"8ddefafe-da24-4874-b149-656e73b68a0e","order_by":0,"name":"Aishwarya Waghmare","email":"data:image/png;base64,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","orcid":"","institution":"Pimpri Chinchwad University","correspondingAuthor":true,"prefix":"","firstName":"Aishwarya","middleName":"","lastName":"Waghmare","suffix":""},{"id":627913081,"identity":"140908ca-aba4-4caa-b256-41e65268e85b","order_by":1,"name":"Avinash Golande","email":"","orcid":"","institution":"Pimpri Chinchwad University","correspondingAuthor":false,"prefix":"","firstName":"Avinash","middleName":"","lastName":"Golande","suffix":""}],"badges":[],"createdAt":"2026-04-06 16:38:36","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9335896/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9335896/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":107688181,"identity":"1f1f30f8-6c32-49a3-98f3-5385f308c01b","added_by":"auto","created_at":"2026-04-24 05:06:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":640883,"visible":true,"origin":"","legend":"","description":"","filename":"LeaveragingHandwritingResearchPaper.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9335896/v1_covered_ee958b6c-9523-4674-a670-4b45931dd8a1.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Leveraging Handwriting Recognition System for Identifying Learning Challenges and Adaptive Education Pathways","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":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Handwriting Analysis, Feature Fusion, Graphology-Inspired Analytics, Student Behavior Analysis, HOG, Stroke Analysis, Learning Analytics, Personalized Education","lastPublishedDoi":"10.21203/rs.3.rs-9335896/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9335896/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe idea of handwriting is not something new and it was believed that the analysis of handwrit- ing can be one of the possible predictors of individual mental and behavioral patterns, especially in the school environment where the written expression is an essential factor. Nevertheless, the conventional methods of handwriting recognition are usually subjective and cannot be scaled. The paper introduces a new hybrid architecture combining deep-learning and manual feature- extraction to objectively and automatically test handwriting to make a prediction of the learning behaviors and academic measures of performance of students. The suggested system utilizes an elaborate preprocessing chain that does not distort the inherent properties of like stroke orienta- tion, spacing, curvature and structural patterns. The architecture of Hybrid CNN-Transformer is used to learn hierarchical visual representations based on handwritten images and is able to learn local stroke-level details as well as global writing styles. Simultaneously, a series of handcrafted characteristics, including slant angle, baseline alignment, word spacing, and densities of strokes, contour structure, and pressure approximation are obtained to offer readable information about writing habits. The two streams are merged into a single architecture to improve on classification accuracy and strength. The framework also has a behavioral analytics module, which uses ex- tracted features to educational indicators, such as legibility, consistency, motor control, attention to detail, presentation quality, and engagement patterns. On this understanding, the system will produce personalized feedback and visual dashboards to help the educators to pinpoint the pros and cons of the students. The results of experimental assessment prove the superiority of the hy- brid methodology over the standalone models because it is able to combine data-driven learning with domain-specific feature representation. The proposed system will consist of a flexible and expressive system to profiling the students based on hand writing that would translate into in- telligent educational systems and learning support. Future research directions include expansion of the model to implement it to transformer based architecture, longitudinal analysis of the data on student progress itself to trace the student progress with the long-term scope.\u003c/p\u003e","manuscriptTitle":"Leveraging Handwriting Recognition System for Identifying Learning Challenges and Adaptive Education Pathways","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-24 05:06:35","doi":"10.21203/rs.3.rs-9335896/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"108825413127956712156392181379090888075","date":"2026-05-05T07:28:02+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"244891503822719102633966966578596218471","date":"2026-05-04T12:12:17+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"107558421576589684080218165926343654222","date":"2026-04-29T12:10:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-16T09:16:37+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-13T14:07:19+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-04-07T02:48:03+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal on Document Analysis and Recognition (IJDAR)","date":"2026-04-06T16:33:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-on-document-analysis-and-recognition-ijdar","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"ijda","sideBox":"Learn more about [International Journal on Document Analysis and Recognition (IJDAR)](http://link.springer.com/journal/10032)","snPcode":"10032","submissionUrl":"https://submission.nature.com/new-submission/10032/3","title":"International Journal on Document Analysis and Recognition (IJDAR)","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"1c9ba7bc-0c84-40ae-baf0-6f0f859989de","owner":[],"postedDate":"April 24th, 2026","published":true,"recentEditorialEvents":[{"type":"reviewerAgreed","content":"108825413127956712156392181379090888075","date":"2026-05-05T07:28:02+00:00","index":24,"fulltext":""},{"type":"reviewerAgreed","content":"244891503822719102633966966578596218471","date":"2026-05-04T12:12:17+00:00","index":19,"fulltext":""},{"type":"reviewerAgreed","content":"107558421576589684080218165926343654222","date":"2026-04-29T12:10:35+00:00","index":18,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-24T05:06:35+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-24 05:06:35","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9335896","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9335896","identity":"rs-9335896","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}