Improved MobileNetv3 lightweight dynamic expression recognition algorithm for classroom scenarios

Improved MobileNetv3 lightweight dynamic expression recognition algorithm for classroom scenarios | 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 Improved MobileNetv3 lightweight dynamic expression recognition algorithm for classroom scenarios 梅花 顾, 梦玥 丁, 婧 冯 This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4453655/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 Aiming at the proplem of high difficulty and low real-time in dynamic expressions recognition under classroom scenes, a lightweight dynamic expression recognition algorithm based on improved MobileNetv3 is proposed. Firstly, through embedding a feature extraction module of GRU (Gate Recurrent Unit) in the MobileNetv3 network, the corresponding space vector of each expression image is processed, the temporal feature among expression image sequences is extracted, and the expression characteristics over time are fully explored. Then, a new hybrid loss LMCF (Large Margin Cosine Focal Loss) is proposed to build the hypersphere of facial expression features, and the inter-class distance of expressions is increased by enlarging the cosine distance, while the blurring problem of inter-class feature boundaries caused by unbalanced expression data is alleviated. Finally, a sparsely connected Pointwise Group Convolution is adopted to optimize the depthwise separable convolution in MobileNetv3 network, the model complexity is reduced, and the model speed is improved. The experimental results show that the accuracy and speed of the proposed algorithm are better than those of the other algorithms in the classroom scene test set, the mean average precision (mAP) can be improved by up to 2.88%, and the recognition rate can be improved by up to 12 FPS. classroom scenes MobileNetv3 Dynamic facial expression recognition Lightweight networks Loss function 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-4453655","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":308177097,"identity":"02a5cabf-3fbe-417c-a33c-401c45c132f4","order_by":0,"name":"梅花 顾","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAvklEQVRIiWNgGAWjYHACNoYPBhI8/MzMhx8QrYVxRoWNjGQ7W5oB0VqYec6k2Ric51GQIEq9fER22gPetsM8xod5GAwYamyiCWoxvJG73UASqMXsMO+BBwzH0nIbCGqZkbtNwhCshS/BgLHhMJFaEkEOa+YxkCBKi7wEUMuBM2k8BszEajHgebtNsqHChkfiMDCQE4jxi3x77jbpPwYS9vz9hw8/+FBjQ4QtB5B5CYSUg20haOgoGAWjYBSMAgDmoT1TgPu4rwAAAABJRU5ErkJggg==","orcid":"","institution":"Xi'an Polytechnic University","correspondingAuthor":true,"prefix":"","firstName":"梅花","middleName":"","lastName":"顾","suffix":""},{"id":308177098,"identity":"455cad56-e5ed-4c00-9b6d-3ac01024795f","order_by":1,"name":"梦玥 丁","email":"","orcid":"","institution":"Xi'an Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"梦玥","middleName":"","lastName":"丁","suffix":""},{"id":308177099,"identity":"909baec6-66b1-46c3-b8c0-99c94196022f","order_by":2,"name":"婧 冯","email":"","orcid":"","institution":"Xi'an Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"婧","middleName":"","lastName":"冯","suffix":""}],"badges":[],"createdAt":"2024-05-21 09:18:02","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4453655/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4453655/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":58894197,"identity":"b6ca7ecd-3b93-44b0-a385-399963c7bd98","added_by":"auto","created_at":"2024-06-23 15:45:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":526568,"visible":true,"origin":"","legend":"","description":"","filename":"ImprovedMobileNetv3lightweightdynamicexpressionrecognitionalgorithmforclassroomscenarios.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4453655/v1_covered_21957739-e447-465f-a962-fee5d260f3a7.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Improved MobileNetv3 lightweight dynamic expression recognition algorithm for classroom scenarios","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":"classroom scenes, MobileNetv3, Dynamic facial expression recognition, Lightweight networks, Loss function","lastPublishedDoi":"10.21203/rs.3.rs-4453655/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4453655/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAiming at the proplem of high difficulty and low real-time in dynamic expressions recognition under classroom scenes, a lightweight dynamic expression recognition algorithm based on improved MobileNetv3 is proposed. Firstly, through embedding a feature extraction module of GRU (Gate Recurrent Unit) in the MobileNetv3 network, the corresponding space vector of each expression image is processed, the temporal feature among expression image sequences is extracted, and the expression characteristics over time are fully explored. Then, a new hybrid loss LMCF (Large Margin Cosine Focal Loss) is proposed to build the hypersphere of facial expression features, and the inter-class distance of expressions is increased by enlarging the cosine distance, while the blurring problem of inter-class feature boundaries caused by unbalanced expression data is alleviated. Finally, a sparsely connected Pointwise Group Convolution is adopted to optimize the depthwise separable convolution in MobileNetv3 network, the model complexity is reduced, and the model speed is improved. The experimental results show that the accuracy and speed of the proposed algorithm are better than those of the other algorithms in the classroom scene test set, the mean average precision (mAP) can be improved by up to 2.88%, and the recognition rate can be improved by up to 12 FPS.\u003c/p\u003e","manuscriptTitle":"Improved MobileNetv3 lightweight dynamic expression recognition algorithm for classroom scenarios","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-03 06:24:42","doi":"10.21203/rs.3.rs-4453655/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":"0ce76f18-efc7-4f7a-adde-e4ebf45894ca","owner":[],"postedDate":"June 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-06-23T15:37:11+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-03 06:24:42","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4453655","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4453655","identity":"rs-4453655","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}