Emotion-Aware ResNet50V2: Enhancing Mental Health Detection through Facial Expression Analysis

Emotion-Aware ResNet50V2: Enhancing Mental Health Detection through Facial Expression Analysis | 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 Emotion-Aware ResNet50V2: Enhancing Mental Health Detection through Facial Expression Analysis Puspen Lahiri, Rohit Dey, Tithi Jana, Hiranmoy Roy, Debotosh Bhattacharjee This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7236314/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 Mental health conditions, such as anxiety, depression, and stress, significantly impact individuals across diverse demographics. Despite advances in awareness, many cases remain undiagnosed or untreated. This study introduces Emo-Res50V2, a customized ResNet50V2 architecture, to detect facial emotions accurately using the FER2013 dataset. By incorporating an emotion-aware classifier, our model achieves 90.03% accuracy. We correlate detected emotions with mental health conditions through survey data, providing a comprehensive tool for emotional and psychological assessment. Our approach demonstrates robustness against noisy data, outperforming state-of-the-art techniques. This research highlights the potential of deep learning in advancing mental health detection, facilitating early diagnosis, and personalized treatment planning. The code is available at https://github.com/Myself-Rohit-Dey/Emo-Res50V2 Residual Learning ResNet50V2 Emotion-Aware Network Mental Health Detection Noise Robust 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-7236314","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":506228844,"identity":"492818b3-0635-4ecb-8989-29226f38d7e1","order_by":0,"name":"Puspen Lahiri","email":"","orcid":"","institution":"MCKV Institute of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Puspen","middleName":"","lastName":"Lahiri","suffix":""},{"id":506228845,"identity":"336229e5-2483-4137-8e86-24054be689ad","order_by":1,"name":"Rohit Dey","email":"","orcid":"","institution":"MCKV Institute of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Rohit","middleName":"","lastName":"Dey","suffix":""},{"id":506228846,"identity":"39a32c06-c21c-4e8d-b4cf-de36191c0d73","order_by":2,"name":"Tithi Jana","email":"","orcid":"","institution":"MCKV Institute of Engineering","correspondingAuthor":false,"prefix":"","firstName":"Tithi","middleName":"","lastName":"Jana","suffix":""},{"id":506228847,"identity":"52aa3716-ba05-4e26-a85b-71ec50ee2464","order_by":3,"name":"Hiranmoy Roy","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvklEQVRIiWNgGAWjYBACA2Yogx9EJBSQokWyAaTFgBgtcMYBFC4eYM7O+0yCcY9N4ubzqxM/PDBgkOcXO4Bfi2Uzu5kEw7O0xG033m6WADrMcObsBAIOO8zGJsFw4DBQy9kNIC0JBreJ1bJ5xtnNP0jTsoG/dxvRtjBbJBxIM55xg3ebRYKBBBF+OX+M8caHAzay/f1nN9/8UWEjzy9NQAsYANU4NkiAVUoQoRwK7Bn4DxCvehSMglEwCkYWAACdBEJGELoUngAAAABJRU5ErkJggg==","orcid":"","institution":"RCC Institute of Information Technology","correspondingAuthor":true,"prefix":"","firstName":"Hiranmoy","middleName":"","lastName":"Roy","suffix":""},{"id":506228848,"identity":"fbf0bd2d-d536-4b0b-bc8d-b0d40a3523f8","order_by":4,"name":"Debotosh Bhattacharjee","email":"","orcid":"","institution":"RCC Institute of Information Technology","correspondingAuthor":false,"prefix":"","firstName":"Debotosh","middleName":"","lastName":"Bhattacharjee","suffix":""}],"badges":[],"createdAt":"2025-07-28 17:38:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7236314/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7236314/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":98778833,"identity":"16dfe38a-4a87-4aaf-a107-aa07c449afd9","added_by":"auto","created_at":"2025-12-22 12:29:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2887212,"visible":true,"origin":"","legend":"","description":"","filename":"PLRDTJHRDBEmotionAwareResnet50v2SpringerVC.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7236314/v1_covered_a54b2da0-30a1-4a13-96f7-0e423c2dc25e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Emotion-Aware ResNet50V2: Enhancing Mental Health Detection through Facial Expression Analysis","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":"Residual Learning, ResNet50V2, Emotion-Aware Network, Mental Health Detection, Noise Robust","lastPublishedDoi":"10.21203/rs.3.rs-7236314/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7236314/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMental health conditions, such as anxiety, depression, and stress, significantly impact individuals across diverse demographics. Despite advances in awareness, many cases remain undiagnosed or untreated. This study introduces Emo-Res50V2, a customized ResNet50V2 architecture, to detect facial emotions accurately using the FER2013 dataset. By incorporating an emotion-aware classifier, our model achieves 90.03% accuracy. We correlate detected emotions with mental health conditions through survey data, providing a comprehensive tool for emotional and psychological assessment. Our approach demonstrates robustness against noisy data, outperforming state-of-the-art techniques. This research highlights the potential of deep learning in advancing mental health detection, facilitating early diagnosis, and personalized treatment planning. The code is available at https://github.com/Myself-Rohit-Dey/Emo-Res50V2\u003c/p\u003e","manuscriptTitle":"Emotion-Aware ResNet50V2: Enhancing Mental Health Detection through Facial Expression Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-09-01 03:14:05","doi":"10.21203/rs.3.rs-7236314/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":"ee74efe8-2315-4dfd-afd1-88f75e83faae","owner":[],"postedDate":"September 1st, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-12-22T04:54:09+00:00","versionOfRecord":[],"versionCreatedAt":"2025-09-01 03:14:05","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7236314","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7236314","identity":"rs-7236314","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}