A Dual-Architecture Deep Learning Pipeline for Real-Time High-Accuracy Arabic Sign Language Recognition

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract This research presents a deep learning-based pipeline for Arabic Sign Language (ArSL) recognition to bridge the communication gap for the Deaf and Hard of Hearing community. We propose a robust system that processes both static images and live video streams, translating isolated gestures into corresponding alphabet letters. Our methodology integrates advanced image preprocessing using Google's MediaPipe for hand landmark detection, along with data augmentation. Two classification approaches are developed: a fine-tuned ResNet18 model achieving 98% test accuracy, and an enhanced architecture employing EfficientNet-B2 as a feature extractor combined with a Random Forest classifier, which achieves 99% accuracy on a diverse, participant-rich dataset of 7,856 labelled RGB images. The superior performance of the latter model demonstrates effective feature extraction and generalization. A functional real-time application validates the system's practical utility, offering an accurate and efficient tool for ArSL recognition.
Full text 12,894 characters · extracted from preprint-html · click to expand
A Dual-Architecture Deep Learning Pipeline for Real-Time High-Accuracy Arabic Sign Language Recognition | 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 A Dual-Architecture Deep Learning Pipeline for Real-Time High-Accuracy Arabic Sign Language Recognition Asmaa Youssef, Amira Gaber, Shereen M. El-Metwally This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8605046/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 17 You are reading this latest preprint version Abstract This research presents a deep learning-based pipeline for Arabic Sign Language (ArSL) recognition to bridge the communication gap for the Deaf and Hard of Hearing community. We propose a robust system that processes both static images and live video streams, translating isolated gestures into corresponding alphabet letters. Our methodology integrates advanced image preprocessing using Google's MediaPipe for hand landmark detection, along with data augmentation. Two classification approaches are developed: a fine-tuned ResNet18 model achieving 98% test accuracy, and an enhanced architecture employing EfficientNet-B2 as a feature extractor combined with a Random Forest classifier, which achieves 99% accuracy on a diverse, participant-rich dataset of 7,856 labelled RGB images. The superior performance of the latter model demonstrates effective feature extraction and generalization. A functional real-time application validates the system's practical utility, offering an accurate and efficient tool for ArSL recognition. Arabic Sign Language Recognition Deep Learning Computer Vision EfficientNet MediaPipe Assistive Technology Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 24 Feb, 2026 Reviews received at journal 24 Feb, 2026 Reviews received at journal 10 Feb, 2026 Reviewers agreed at journal 10 Feb, 2026 Reviews received at journal 09 Feb, 2026 Reviews received at journal 09 Feb, 2026 Reviewers agreed at journal 09 Feb, 2026 Reviews received at journal 08 Feb, 2026 Reviewers agreed at journal 07 Feb, 2026 Reviewers agreed at journal 06 Feb, 2026 Reviewers agreed at journal 02 Feb, 2026 Reviewers agreed at journal 02 Feb, 2026 Reviewers invited by journal 02 Feb, 2026 Editor invited by journal 23 Jan, 2026 Editor assigned by journal 16 Jan, 2026 Submission checks completed at journal 16 Jan, 2026 First submitted to journal 14 Jan, 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-8605046","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":585024712,"identity":"c5888a4b-6dca-4463-a0e4-c490d1f8ac2c","order_by":0,"name":"Asmaa Youssef","email":"data:image/png;base64,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","orcid":"","institution":"Cairo University","correspondingAuthor":true,"prefix":"","firstName":"Asmaa","middleName":"","lastName":"Youssef","suffix":""},{"id":585024714,"identity":"92db1543-0a92-4557-8530-22413362985a","order_by":1,"name":"Amira Gaber","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Amira","middleName":"","lastName":"Gaber","suffix":""},{"id":585024717,"identity":"fae26b73-6f2b-4ebb-a9d6-e0fed4a80042","order_by":2,"name":"Shereen M. El-Metwally","email":"","orcid":"","institution":"Cairo University","correspondingAuthor":false,"prefix":"","firstName":"Shereen","middleName":"M.","lastName":"El-Metwally","suffix":""}],"badges":[],"createdAt":"2026-01-14 20:53:26","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8605046/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8605046/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":101881764,"identity":"3c4b1106-ff6f-44e3-8c3c-e79fb8596322","added_by":"auto","created_at":"2026-02-04 15:16:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":967655,"visible":true,"origin":"","legend":"","description":"","filename":"ADualArchitectureDeepLearning.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8605046/v1_covered_333809d7-e7f4-4d9c-9490-d691d29d6317.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Dual-Architecture Deep Learning Pipeline for Real-Time High-Accuracy Arabic Sign Language Recognition","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":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Arabic Sign Language Recognition, Deep Learning, Computer Vision, EfficientNet, MediaPipe, Assistive Technology","lastPublishedDoi":"10.21203/rs.3.rs-8605046/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8605046/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis research presents a deep learning-based pipeline for Arabic Sign Language (ArSL) recognition to bridge the communication gap for the Deaf and Hard of Hearing community. We propose a robust system that processes both static images and live video streams, translating isolated gestures into corresponding alphabet letters. Our methodology integrates advanced image preprocessing using Google's MediaPipe for hand landmark detection, along with data augmentation. Two classification approaches are developed: a fine-tuned ResNet18 model achieving 98% test accuracy, and an enhanced architecture employing EfficientNet-B2 as a feature extractor combined with a Random Forest classifier, which achieves 99% accuracy on a diverse, participant-rich dataset of 7,856 labelled RGB images. The superior performance of the latter model demonstrates effective feature extraction and generalization. A functional real-time application validates the system's practical utility, offering an accurate and efficient tool for ArSL recognition.\u003c/p\u003e","manuscriptTitle":"A Dual-Architecture Deep Learning Pipeline for Real-Time High-Accuracy Arabic Sign Language Recognition","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-04 12:13:58","doi":"10.21203/rs.3.rs-8605046/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-25T04:27:41+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-24T07:22:40+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-10T22:44:50+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"270340777715574390106410468200090724299","date":"2026-02-10T11:49:24+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-10T01:58:47+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-09T10:49:20+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"18827630716781496230080641537059327191","date":"2026-02-09T10:14:12+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-09T04:41:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"169427386756273395691880645916678974814","date":"2026-02-07T11:18:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"19581665526592865087260044748367309544","date":"2026-02-06T11:36:04+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"290870774068210976665537897066291523121","date":"2026-02-02T14:30:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"101934192878012919000242992797690874797","date":"2026-02-02T11:33:20+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-02-02T10:21:43+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-01-23T08:34:23+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-01-16T10:42:28+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-16T10:37:38+00:00","index":"","fulltext":""},{"type":"submitted","content":"Discover Artificial Intelligence","date":"2026-01-14T20:45:31+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"discover-artificial-intelligence","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"diai","sideBox":"Learn more about [Discover Artificial Intelligence](https://www.springer.com/44163)","snPcode":"","submissionUrl":"","title":"Discover Artificial Intelligence","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Discover Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"09dddca5-6e5e-43da-81f5-95aaf447161e","owner":[],"postedDate":"February 4th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-05-15T13:08:30+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-04 12:13:58","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8605046","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8605046","identity":"rs-8605046","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-27T02:00:06.600101+00:00
License: CC-BY-4.0