Synergizing CNNs and Transformers for Accurate Face Age Estimation

Synergizing CNNs and Transformers for Accurate Face Age Estimation | 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 Synergizing CNNs and Transformers for Accurate Face Age Estimation Ahmed Chaouki Chami, Riadh Ajgou, Abdelmalik Taleb-Ahmed This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5427570/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 Estimating the actual and perceived age of human faces has garnered significant interest for its wide-ranging practical applications. Various intelligent scenarios stand to gain from these computational systems capable of accurately predicting individuals’ ages. Automated age estimation systems are particularly valuable in fields such as medical diagnostics, facial product development, casting for films, assessing the impact of cosmetic procedures, and anti-aging treatments. In the realm where deep networks have demonstrated their supremacy as the fron-trunners among machine learning tools, Our approach integrates Convolutional Neural Networks (CNN) with Transformers. This novel system enhances information extraction by utilizing transformer attention mechanisms, rather than solely depending on features extracted from convolutional neural networks for estimating age. Based on the experiments conducted, the system effectively captures the sequential progression and continuous nature of the aging process. Furthermore, the proposed model surpasses the cutting-edge model by delivering exceptional results, achieving the lowest mean absolute errors of 2.31 for MORPH II, 5.35 for CACD, and 2.91 for AFAD. Age estimation deep learning vision transformers hybrid model 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-5427570","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":377908822,"identity":"bd567449-f64b-4046-8b3f-c0acab4aab51","order_by":0,"name":"Ahmed Chaouki Chami","email":"data:image/png;base64,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","orcid":"","institution":"Faculty of Technology, University of El Oued","correspondingAuthor":true,"prefix":"","firstName":"Ahmed","middleName":"Chaouki","lastName":"Chami","suffix":""},{"id":377908823,"identity":"51813a83-a92b-4bf7-83d7-96c70559e998","order_by":1,"name":"Riadh Ajgou","email":"","orcid":"","institution":"Faculty of Technology, University of El Oued","correspondingAuthor":false,"prefix":"","firstName":"Riadh","middleName":"","lastName":"Ajgou","suffix":""},{"id":377908824,"identity":"2a7075e5-b07a-4e53-972b-0571536a2421","order_by":2,"name":"Abdelmalik Taleb-Ahmed","email":"","orcid":"","institution":"EMN DOAE UMR CNRS 8520 Laboratory, Polytechnic University of Hauts-de-France","correspondingAuthor":false,"prefix":"","firstName":"Abdelmalik","middleName":"","lastName":"Taleb-Ahmed","suffix":""}],"badges":[],"createdAt":"2024-11-10 20:38:07","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5427570/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5427570/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":71411481,"identity":"de24669b-da58-40e8-9e26-6ee8e33b1efc","added_by":"auto","created_at":"2024-12-14 13:32:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":608606,"visible":true,"origin":"","legend":"","description":"","filename":"SynergizingCNNsandTransformersforAccurateFaceAgeEstimation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5427570/v1_covered_f3b5c356-28ca-49f5-85e3-8d0ae426a340.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Synergizing CNNs and Transformers for Accurate Face Age Estimation","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":"Age estimation, deep learning, vision transformers, hybrid model","lastPublishedDoi":"10.21203/rs.3.rs-5427570/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5427570/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEstimating the actual and perceived age of human faces has garnered significant interest for its wide-ranging practical applications. Various intelligent scenarios stand to gain from these computational systems capable of accurately predicting individuals’ ages. Automated age estimation systems are particularly valuable in fields such as medical diagnostics, facial product development, casting for films, assessing the impact of cosmetic procedures, and anti-aging treatments. In the realm where deep networks have demonstrated their supremacy as the fron-trunners among machine learning tools, Our approach integrates Convolutional Neural Networks (CNN) with Transformers. This novel system enhances information extraction by utilizing transformer attention mechanisms, rather than solely depending on features extracted from convolutional neural networks for estimating age. Based on the experiments conducted, the system effectively captures the sequential progression and continuous nature of the aging process. Furthermore, the proposed model surpasses the cutting-edge model by delivering exceptional results, achieving the lowest mean absolute errors of 2.31 for MORPH II, 5.35 for CACD, and 2.91 for AFAD.\u003c/p\u003e","manuscriptTitle":"Synergizing CNNs and Transformers for Accurate Face Age Estimation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-12-02 01:49:56","doi":"10.21203/rs.3.rs-5427570/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":"8f43b4ac-aa50-4479-8107-0c84e91c4113","owner":[],"postedDate":"December 2nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-12-14T13:23:55+00:00","versionOfRecord":[],"versionCreatedAt":"2024-12-02 01:49:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5427570","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5427570","identity":"rs-5427570","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}