Arabic Sign Language (ARSL) Recognition and Translation into Text

Arabic Sign Language (ARSL) Recognition and Translation into Text | 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 Arabic Sign Language (ARSL) Recognition and Translation into Text Lakehal Maya Amani, Haddouche Milissa, Kaddouri Nassim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7632857/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 Millions of deaf and hard-of-hearing individuals around the Arab world rely on sign language, yet interpreter access remains limited especially given the diversity among Arabic Sign Language (ArSL) dialects. Leveraging recent strides in deep learning, our study explores scalable, real-time recognition methods to bridge this communication gap. We trained and evaluated two models MobileNetV2 with GRU and Inflated 3D ConvNet (I3D) on the publicly available “Arabic Sign Language Dataset”. This dataset, sourced from Kaggle, includes over 8,400 labeled video clips across 20 isolated ArSL classes, contributed by 72 participants. We partitioned it into training (6,749 clips), validation (844), and test (844) sets in an 80/10/10 split. The MobileNetV2+GRU model outperformed with 96% validation accuracy and 97\% test accuracy, alongside over 95% in both precision and recall. These results demonstrate that lightweight, mobile-friendly architectures can deliver near–state-of-the-art performance, offering a promising step toward making ArSL universally accessible. Artificial Intelligence and Machine Learning Linguistics Sign language ArSL Real-time gesture recognition MobileNetV2 GRU I3D 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-7632857","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":516090455,"identity":"45843841-72c3-4e76-b0a8-df0e5d985518","order_by":0,"name":"Lakehal Maya Amani","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5klEQVRIiWNgGAWjYBACPgY2CIOfvfkAkJKQIaiFDaZFsudYAkgLD/FaDG7kGIBoIrSwH0tgulFzWJ7hQM7nVzdqLHgY2A8f3YBXC0/aAeacY4cNGxvObrPOOQZ0GE9a2g38DktvYM5hO8zYzNi7zTiHDahFgscMvxb+50At/w7btzHzPDPO+UeMFgmgw3LbDif2sPEwP85tI0rLs4TDuX3pyTN42MyYc/skeNgI+YWfP83wcc43a9v99x8//pzzrU6On/3wMbxaQOAAA0MzxEYwSUg5FNSBCOYPRKoeBaNgFIyCEQYAR09E8BaV3bgAAAAASUVORK5CYII=","orcid":"","institution":"Numidia Institute of Technology","correspondingAuthor":true,"prefix":"","firstName":"Lakehal","middleName":"Maya","lastName":"Amani","suffix":""},{"id":516090456,"identity":"e36b755f-2ac8-4dff-8d0e-fc9de1274a4a","order_by":1,"name":"Haddouche Milissa","email":"","orcid":"","institution":"Numidia Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Haddouche","middleName":"","lastName":"Milissa","suffix":""},{"id":516090457,"identity":"a959bf8b-87d4-44a4-8078-67d7c7b36f08","order_by":2,"name":"Kaddouri Nassim","email":"","orcid":"","institution":"Research in Intelligent Informatics Mathematics and Applications (RIIMA)","correspondingAuthor":false,"prefix":"","firstName":"Kaddouri","middleName":"","lastName":"Nassim","suffix":""}],"badges":[],"createdAt":"2025-09-16 17:20:15","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-7632857/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7632857/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":91506332,"identity":"be718eb8-617c-472c-b82a-99c7bbea1953","added_by":"auto","created_at":"2025-09-17 08:23:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":693097,"visible":true,"origin":"","legend":"","description":"","filename":"article.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7632857/v1_covered_207a0a29-8e9d-46f6-8d85-759e081aeceb.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eArabic Sign Language (ARSL) Recognition and Translation into Text\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Numidia Institute of Technology","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":"Sign language, ArSL, Real-time gesture recognition, MobileNetV2, GRU, I3D","lastPublishedDoi":"10.21203/rs.3.rs-7632857/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7632857/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMillions of deaf and hard-of-hearing individuals around the Arab world rely on sign language, yet interpreter access remains limited especially given the diversity among Arabic Sign Language (ArSL) dialects. Leveraging recent strides in deep learning, our study explores scalable, real-time recognition methods to bridge this communication gap. We trained and evaluated two models MobileNetV2 with GRU and Inflated 3D ConvNet (I3D) on the publicly available “Arabic Sign Language Dataset”. This dataset, sourced from Kaggle, includes over 8,400 labeled video clips across 20 isolated ArSL classes, contributed by 72 participants. We partitioned it into training (6,749 clips), validation (844), and test (844) sets in an 80/10/10 split. The MobileNetV2+GRU model outperformed with 96% validation accuracy and 97\\% test accuracy, alongside over 95% in both precision and recall. These results demonstrate that lightweight, mobile-friendly architectures can deliver near–state-of-the-art performance, offering a promising step toward making ArSL universally accessible.\u003c/p\u003e","manuscriptTitle":"Arabic Sign Language (ARSL) Recognition and Translation into Text","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-17 08:15:32","doi":"10.21203/rs.3.rs-7632857/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":"f2ecae5b-dab3-4145-882d-389b87461272","owner":[],"postedDate":"September 17th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":54860241,"name":"Artificial Intelligence and Machine Learning"},{"id":54860242,"name":"Linguistics"}],"tags":[],"updatedAt":"2025-09-17T08:15:32+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-17 08:15:32","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7632857","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7632857","identity":"rs-7632857","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}