Yoruba Sign Language Digit Recognition System using Deep Convolution Neural Network and Machine Learning

Yoruba Sign Language Digit Recognition System using Deep Convolution Neural Network and Machine Learning | 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 Yoruba Sign Language Digit Recognition System using Deep Convolution Neural Network and Machine Learning Kuditat O. Jimoh, Anuoluwapo O. Ajayi, Olumide A. Ajayi, Abiodun A. Ajasa, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8007915/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 Tools to support communication in the Yor̀ubá language between the hearing-impaired and unimpaired individuals are limited. Thus, this study implements and evaluates a real-time sign language recognition system for Yor̀ubá sign language and determines specific features responsible for recognizing the numeral gestures. A sample of 1000 hand gestures containing ten gestures (each for numeral 1–10) was collected from a deaf school in Nigeria and pre-processed using the augmented techniques to generate 11000 variations of the sign digit images. The processed digits were recognized using Convolution Neural Networks (CNN). The developed model was compared with pre-trained models and three other prevalent machine learning techniques: Artificial Neural Networks, Support Vector Machines, and K-nearest neighbor, using precision, recall, F1-scores, and accuracy as performance metrics. The performance results showed that the CNN model outperformed other models with an average precision (99.52%), recall rate (99.50%), F1-score (99.49%), and accuracy (99.50%). Thus, the developed CNN model successfully recognized Yor̀ubá hand gestures and would thus assist in bridging the gap between hearing-impaired and unimpaired individuals. Yor̀uba Sign Language Convolutional neural networks Data augmentation Feature extraction Pinky-led structure Index-led structure 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-8007915","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":557576191,"identity":"02e561de-317c-47be-9c4c-b239bbf29bfe","order_by":0,"name":"Kuditat O. Jimoh","email":"data:image/png;base64,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","orcid":"","institution":"Osun State University","correspondingAuthor":true,"prefix":"","firstName":"Kuditat","middleName":"O.","lastName":"Jimoh","suffix":""},{"id":557576192,"identity":"b2463728-25b4-4b26-835c-1e8637efd2d8","order_by":1,"name":"Anuoluwapo O. Ajayi","email":"","orcid":"","institution":"University of West of England","correspondingAuthor":false,"prefix":"","firstName":"Anuoluwapo","middleName":"O.","lastName":"Ajayi","suffix":""},{"id":557576193,"identity":"22258b5a-79fe-495f-a278-8ecc7a2837aa","order_by":2,"name":"Olumide A. Ajayi","email":"","orcid":"","institution":"Adeleke University","correspondingAuthor":false,"prefix":"","firstName":"Olumide","middleName":"A.","lastName":"Ajayi","suffix":""},{"id":557576194,"identity":"f95d6645-8a4a-41b1-8f3a-8148e58ba08a","order_by":3,"name":"Abiodun A. Ajasa","email":"","orcid":"","institution":"Lagos State University","correspondingAuthor":false,"prefix":"","firstName":"Abiodun","middleName":"A.","lastName":"Ajasa","suffix":""},{"id":557576197,"identity":"bc899574-3d02-4abd-957b-3cd662288428","order_by":4,"name":"Mutmahinah O. Jimoh-Ademola","email":"","orcid":"","institution":"Lagos State University","correspondingAuthor":false,"prefix":"","firstName":"Mutmahinah","middleName":"O.","lastName":"Jimoh-Ademola","suffix":""}],"badges":[],"createdAt":"2025-11-01 21:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8007915/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8007915/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98007259,"identity":"556a15cc-b68a-4242-a9d5-95064c8b1525","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2643412,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptYSL.docx","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/c8c8a066b41a92e9523592f0.docx"},{"id":98007251,"identity":"a18188e0-a5a5-460c-9fd0-007eee7a0c1d","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6513,"visible":true,"origin":"","legend":"","description":"","filename":"e2da892b30124f71824c6bfceb8a31fc.json","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/310ffe1445e128fe1092d754.json"},{"id":98007256,"identity":"00ce374b-fa78-4f15-af80-c27a8f747c10","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":167939,"visible":true,"origin":"","legend":"","description":"","filename":"e2da892b30124f71824c6bfceb8a31fc1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/1c887b61afd79a344e9b2272.xml"},{"id":98007248,"identity":"5cbe1803-2731-4c1b-b312-9715c26afa35","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"jpeg","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":178905,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/63ab224bc90523ad8f6c7a30.jpeg"},{"id":98426481,"identity":"1c66a77a-faba-4ee1-b1ee-300bba9b5101","added_by":"auto","created_at":"2025-12-17 16:36:30","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":172498,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/88991e9a2eb8114ecc7805c1.png"},{"id":98424603,"identity":"b44adced-dfab-4016-9a43-6565a4fa03de","added_by":"auto","created_at":"2025-12-17 16:33:32","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":675984,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/39820ccac35fdc719d4ce923.png"},{"id":98426123,"identity":"c213a5c7-530c-426f-8e0e-5a469f65fade","added_by":"auto","created_at":"2025-12-17 16:35:43","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":344660,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/0bb2e69d5a2a8629276f6bb4.jpeg"},{"id":98425513,"identity":"9445daa0-d7fd-4323-8cfd-54ccb9b7bcdf","added_by":"auto","created_at":"2025-12-17 16:34:52","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":78831,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/ee53ebc99753aa02d30082d4.png"},{"id":98425899,"identity":"bf7110f3-c42f-410a-a624-621016016fe9","added_by":"auto","created_at":"2025-12-17 16:35:20","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":341091,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/0d08c8e3ccf614aad2023880.jpeg"},{"id":98425553,"identity":"e660f309-6152-4fa4-9a08-131fbca16403","added_by":"auto","created_at":"2025-12-17 16:34:56","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64910,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/214fafb4767d80438d0b7667.png"},{"id":98424900,"identity":"087dd358-b150-4de1-8458-8aa8f84b8c16","added_by":"auto","created_at":"2025-12-17 16:34:02","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":330529,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/e3b8874f99cd221867427687.png"},{"id":98425642,"identity":"18cf597f-70c5-4873-8ccd-4930448cecdf","added_by":"auto","created_at":"2025-12-17 16:35:00","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":705783,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/87a1f594254de6187c653f57.png"},{"id":98424606,"identity":"9cc60d44-b265-4f99-b8e5-f55317879d85","added_by":"auto","created_at":"2025-12-17 16:33:32","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":139175,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/84b37685de051348e332f7a6.png"},{"id":98426498,"identity":"9633b221-cf84-4e2f-9b60-d36a434aea94","added_by":"auto","created_at":"2025-12-17 16:36:32","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23081,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/2225f9ccf4062e99a5d2c229.png"},{"id":98425963,"identity":"6a55f653-6ac9-4c7e-a4b6-2724046e888a","added_by":"auto","created_at":"2025-12-17 16:35:25","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":98109,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/510e7279bd179a74ba71fb86.png"},{"id":98007260,"identity":"82aef3e3-03a3-4dc2-829a-83b514504779","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":427955,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/5be069eb1367ccd56f503291.png"},{"id":98425571,"identity":"4482c53b-4900-444a-9119-42632123acce","added_by":"auto","created_at":"2025-12-17 16:34:57","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18199,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/7926d4754ff5e11aa6ca5bd5.png"},{"id":98425348,"identity":"9d056890-a7d5-4b3f-8357-db16328dbaa2","added_by":"auto","created_at":"2025-12-17 16:34:40","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67908,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/a662b16101529d939e304f9f.png"},{"id":98426136,"identity":"0f5ee5f7-f69a-4929-ac94-e4e954ecf3bf","added_by":"auto","created_at":"2025-12-17 16:35:45","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18945,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/5507240ae5ae4bc1b70aa437.png"},{"id":98425936,"identity":"1f467c32-cc29-430c-8839-3585762c399f","added_by":"auto","created_at":"2025-12-17 16:35:23","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":62334,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/96d67e4af9818a8fb6a3e674.png"},{"id":98007264,"identity":"411e36e1-b746-4a40-a203-e334faf74806","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89999,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/4b3d0a8e7058475c5ec468bc.png"},{"id":98007268,"identity":"6a9265c3-1dbf-4f7e-853b-717e7a190350","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"xml","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":168790,"visible":true,"origin":"","legend":"","description":"","filename":"e2da892b30124f71824c6bfceb8a31fc1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/55e5d5673e845046407a0b22.xml"},{"id":98007269,"identity":"6e8f2967-120a-4e80-98ed-58a3c9fd17d7","added_by":"auto","created_at":"2025-12-11 17:18:00","extension":"html","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":186327,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1/86b8dc116c4e598e35a459fd.html"},{"id":100104279,"identity":"d647b9c4-6d1a-46a2-8ae5-75456e01a863","added_by":"auto","created_at":"2026-01-13 04:24:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1080368,"visible":true,"origin":"","legend":"","description":"","filename":"ManuscriptYSL.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8007915/v1_covered_de355feb-44ac-4ef3-ab46-6d078511e504.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Yoruba Sign Language Digit Recognition System using Deep Convolution Neural Network and Machine Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Yor̀uba Sign Language, Convolutional neural networks, Data augmentation, Feature extraction, Pinky-led structure, Index-led structure","lastPublishedDoi":"10.21203/rs.3.rs-8007915/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8007915/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTools to support communication in the Yor̀ub\u0026aacute; language between the hearing-impaired and unimpaired individuals are limited. Thus, this study implements and evaluates a real-time sign language recognition system for Yor̀ub\u0026aacute; sign language and determines specific features responsible for recognizing the numeral gestures. A sample of 1000 hand gestures containing ten gestures (each for numeral 1\u0026ndash;10) was collected from a deaf school in Nigeria and pre-processed using the augmented techniques to generate 11000 variations of the sign digit images. The processed digits were recognized using Convolution Neural Networks (CNN). The developed model was compared with pre-trained models and three other prevalent machine learning techniques: Artificial Neural Networks, Support Vector Machines, and K-nearest neighbor, using precision, recall, F1-scores, and accuracy as performance metrics. The performance results showed that the CNN model outperformed other models with an average precision (99.52%), recall rate (99.50%), F1-score (99.49%), and accuracy (99.50%). Thus, the developed CNN model successfully recognized Yor̀ub\u0026aacute; hand gestures and would thus assist in bridging the gap between hearing-impaired and unimpaired individuals.\u003c/p\u003e","manuscriptTitle":"Yoruba Sign Language Digit Recognition System using Deep Convolution Neural Network and Machine Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-11 17:17:51","doi":"10.21203/rs.3.rs-8007915/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":"087dc557-20e8-417e-a4f3-8d453a7be950","owner":[],"postedDate":"December 11th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-13T04:23:50+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-11 17:17:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8007915","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8007915","identity":"rs-8007915","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}