Automated Yoga Pose Classification Using Deep Learning on Image-Based Datasets

Automated Yoga Pose Classification Using Deep Learning on Image-Based Datasets | 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 Automated Yoga Pose Classification Using Deep Learning on Image-Based Datasets Anish Antony, M.A.H. Farquad, Ashvini Alashetty, Sachin Kumar, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9048026/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 The With the increasing popularity of yoga as a form of physical and mental fitness, the correct recognition of yoga poses is crucial for automated feedback systems, virtual training and health monitoring, and other applications. The main contribution of the present work is to introduce a yoga pose recognition pipeline based on deep learning methods for image-based datasets. The model makes use of MobileNetV2 for posture classification and YOLOv5 for real-time pose detection, which allows the system to perform efficient feature extraction and localize the body joints spatially. The models were trained and tested using a large dataset of multiple poses of different types and backgrounds in yoga. As experimental results, MobileNetV2 also had a good validation accuracy of 72.6%, also being able to effectively classify postures with a high frequency, while YOLOv5 also obtained a fairly good overall accuracy of 70%, being able to robustly detect and classify it at the same time. It can be concluded that in a single frame, where multi-pose detection is required, YOLOv5 is more suited, while for isolated posture recognition MobileNetV2 performs better for isolated posture recognition with MobileNetV2. This framework emphasizes the promise of deep learning for developing yoga intelligent training systems that can give automatic, real-time feedback to attendees, for applications focused on health and rehabilitation purposes. Biological sciences/Computational biology and bioinformatics Physical sciences/Engineering Health sciences/Health care Physical sciences/Mathematics and computing Yolo MobileNetV2 Yoga Deep Learning Classification 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-9048026","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":621700595,"identity":"e2ef94c6-ef70-4886-ad0c-02f5206aaeaa","order_by":0,"name":"Anish Antony","email":"","orcid":"","institution":"School of Advanced Studies S-Vyasa Deemed-To-Be University","correspondingAuthor":false,"prefix":"","firstName":"Anish","middleName":"","lastName":"Antony","suffix":""},{"id":621700596,"identity":"e70fd3cf-f0d0-4353-8dc0-e9278d3b10e9","order_by":1,"name":"M.A.H. Farquad","email":"","orcid":"","institution":"Faculty of Computer Information Systems, Higher Colleges of Technology, Ras Al-Khaimah, United Arab Emirates","correspondingAuthor":false,"prefix":"","firstName":"M.A.H.","middleName":"","lastName":"Farquad","suffix":""},{"id":621700597,"identity":"3e3cad3d-dc84-4bd0-bae3-44e4e9de5101","order_by":2,"name":"Ashvini Alashetty","email":"data:image/png;base64,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","orcid":"","institution":"School of Advanced Studies S-Vyasa Deemed-To-Be University","correspondingAuthor":true,"prefix":"","firstName":"Ashvini","middleName":"","lastName":"Alashetty","suffix":""},{"id":621700598,"identity":"eb0da6cb-5ca5-4591-8c19-79249c70eeaf","order_by":3,"name":"Sachin Kumar","email":"","orcid":"","institution":"Galgotias University","correspondingAuthor":false,"prefix":"","firstName":"Sachin","middleName":"","lastName":"Kumar","suffix":""},{"id":621700599,"identity":"ef774602-71c2-447c-9efc-62de0e79f5ac","order_by":4,"name":"Punitkumar Basavaraj Nayak","email":"","orcid":"","institution":"School of Advanced Studies S-Vyasa Deemed-To-Be University","correspondingAuthor":false,"prefix":"","firstName":"Punitkumar","middleName":"Basavaraj","lastName":"Nayak","suffix":""},{"id":621700600,"identity":"5c55d26c-270f-4576-b143-3be0c38f5b1d","order_by":5,"name":"Dr Geethanjali P P","email":"","orcid":"","institution":"School of Advanced Studies S-Vyasa Deemed-To-Be University","correspondingAuthor":false,"prefix":"Dr","firstName":"Geethanjali","middleName":"P","lastName":"P","suffix":""},{"id":621700601,"identity":"83c03f74-87ef-4f3a-bbe8-83440801f68e","order_by":6,"name":"sachin sharma","email":"","orcid":"","institution":"School of Advanced Studies S-Vyasa Deemed-To-Be University","correspondingAuthor":false,"prefix":"","firstName":"sachin","middleName":"","lastName":"sharma","suffix":""},{"id":621700602,"identity":"f71fbed2-727b-419b-88ae-3e2aef11f544","order_by":7,"name":"Dr. K. Sekhar, ( Kamanuri Sekhar) Sekhar","email":"","orcid":"","institution":"Akmonlink College, Department of Management, Lega Tafo, Sheger City, Addis Ababa.","correspondingAuthor":false,"prefix":"Dr.","firstName":"(","middleName":"Kamanuri Sekhar) Sekhar K.","lastName":"Sekhar","suffix":""}],"badges":[],"createdAt":"2026-03-06 08:25:30","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9048026/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9048026/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109494655,"identity":"717db1c2-efc0-46a8-8cd0-12bf31bab7ba","added_by":"auto","created_at":"2026-05-18 19:10:25","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":564962,"visible":true,"origin":"","legend":"","description":"","filename":"Formatted3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9048026/v1_covered_058ab317-26fd-415f-a6fc-eed4339d958d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Automated Yoga Pose Classification Using Deep Learning on Image-Based Datasets","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":"Yolo, MobileNetV2, Yoga, Deep Learning, Classification","lastPublishedDoi":"10.21203/rs.3.rs-9048026/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9048026/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe With the increasing popularity of yoga as a form of physical and mental fitness, the correct recognition of yoga poses is crucial for automated feedback systems, virtual training and health monitoring, and other applications. The main contribution of the present work is to introduce a yoga pose recognition pipeline based on deep learning methods for image-based datasets. The model makes use of MobileNetV2 for posture classification and YOLOv5 for real-time pose detection, which allows the system to perform efficient feature extraction and localize the body joints spatially. The models were trained and tested using a large dataset of multiple poses of different types and backgrounds in yoga. As experimental results, MobileNetV2 also had a good validation accuracy of 72.6%, also being able to effectively classify postures with a high frequency, while YOLOv5 also obtained a fairly good overall accuracy of 70%, being able to robustly detect and classify it at the same time. It can be concluded that in a single frame, where multi-pose detection is required, YOLOv5 is more suited, while for isolated posture recognition MobileNetV2 performs better for isolated posture recognition with MobileNetV2. This framework emphasizes the promise of deep learning for developing yoga intelligent training systems that can give automatic, real-time feedback to attendees, for applications focused on health and rehabilitation purposes.\u003c/p\u003e","manuscriptTitle":"Automated Yoga Pose Classification Using Deep Learning on Image-Based Datasets","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-14 06:15:01","doi":"10.21203/rs.3.rs-9048026/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":"d3ea2093-1170-47c1-bd9f-12f05954d8cf","owner":[],"postedDate":"April 14th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Rejected","date":"2026-05-18T18:56:19+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-14T03:47:22+00:00","index":212,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-10T21:28:29+00:00","index":211,"fulltext":""},{"type":"reviewerAgreed","content":"185828072838948616385192770816589977964","date":"2026-05-06T05:07:07+00:00","index":207,"fulltext":""},{"type":"reviewerAgreed","content":"69135271332740521538538037664480886767","date":"2026-05-03T16:29:42+00:00","index":200,"fulltext":""},{"type":"reviewerAgreed","content":"53793972025060547818504730480186287713","date":"2026-05-03T15:19:51+00:00","index":196,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66158172,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":66158173,"name":"Physical sciences/Engineering"},{"id":66158174,"name":"Health sciences/Health care"},{"id":66158175,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-18T19:10:17+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-14 06:15:01","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9048026","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9048026","identity":"rs-9048026","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}