An Efficient Pedestrian Gender Recognition Method Based on Key Area Feature Extraction and Information Fusion

An Efficient Pedestrian Gender Recognition Method Based on Key Area Feature Extraction and Information Fusion | 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 An Efficient Pedestrian Gender Recognition Method Based on Key Area Feature Extraction and Information Fusion YE ZHANG, WEIDONG YAN, GUOQI LIU, JIN NING, LU HAN This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7746548/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 to address the problems of scale uncertainty, feature extraction difficulty, model training difficulty, poor real-time performance, and sample imbalance in low-resolution images for gender recognition, this study proposes an efficient pedestrian gender recognition model based on key area feature extraction and fusion. First, a discrete cosine transform (DCT) based local super-resolution preprocessing algorithm is developed for facial image gender recognition. Then, a key area feature extraction and information fusion model is designed, using additional appearance features to assist in gender recognition and improve accuracy. The proposed model preprocesses images using the DCT image fusion and super-resolution methods, dividing pedestrian images into three regions: face, hair, and lower body (legs) regions. Features are separately extracted from each of the three image regions. Finally, a multi-region local gender recognition classifier is designed and trained, employing decision-level information fusion. The results of the three local classifiers are fused using a Bayesian computation-based fusion strategy to obtain the final recognition result of a pedestrian's gender. This study uses surveillance video data to create a dataset for experimental comparison. The experimental results show that, compared with the state-of-the-art algorithms, the proposed pedestrian gender recognition model based on multi-region feature extraction and information fusion can improve recognition accuracy, demonstrating high application potential for gender recognition tasks in real-world blurred images. Super-resolution processing key area feature information fusion gender recognition 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-7746548","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":533092658,"identity":"21b43e18-28e4-45d7-92b1-b916f3a63d23","order_by":0,"name":"YE ZHANG","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYBACfvbGhoMfKiTk+NkbiNQi2XO48bDEGRtjyZ4DRGoxuJHefIC3LS1xw40EYm1pSGw4IHHmMOOGm4833mCosYkmqIWf4WDDgYKKw8ySt9OKLRiOpeU2ELSlsRFsCxvf7RwzCcaGw4S1GBxmbAD65TAPw80zxGo5BtaSJiFwg4dILZI9QGXAQDaQ7AH6JYEYv/DLP3/8ERiV9f3shzfe+FBjQ1gLiiMlEkhRDtFCqo5RMApGwSgYGQAA45BJM/CRtrAAAAAASUVORK5CYII=","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":true,"prefix":"","firstName":"YE","middleName":"","lastName":"ZHANG","suffix":""},{"id":533092659,"identity":"3817766f-4e0c-4c37-94ea-fb28baee1a36","order_by":1,"name":"WEIDONG YAN","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"WEIDONG","middleName":"","lastName":"YAN","suffix":""},{"id":533092660,"identity":"a3ac2dfe-3fa4-4af5-bd00-fef6a319743d","order_by":2,"name":"GUOQI LIU","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"GUOQI","middleName":"","lastName":"LIU","suffix":""},{"id":533092661,"identity":"3eba8a5c-2631-4813-aaee-d430073ed2ef","order_by":3,"name":"JIN NING","email":"","orcid":"","institution":"Shenyang Jianzhu University","correspondingAuthor":false,"prefix":"","firstName":"JIN","middleName":"","lastName":"NING","suffix":""},{"id":533092662,"identity":"ee33d5bc-526e-4d36-a3bf-2ca89b5c3573","order_by":4,"name":"LU HAN","email":"","orcid":"","institution":"Liaoning Province Data Centre","correspondingAuthor":false,"prefix":"","firstName":"LU","middleName":"","lastName":"HAN","suffix":""}],"badges":[],"createdAt":"2025-09-30 03:08:27","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7746548/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7746548/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94240769,"identity":"0a882e79-4926-4413-907c-81efd41e7f8b","added_by":"auto","created_at":"2025-10-24 03:48:20","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1090470,"visible":true,"origin":"","legend":"","description":"","filename":"AnEfficientPedestrianGenderRecognitionMethodBasedonKeyAreaFeatureExtractionandInformationFusion.docx","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/74e866ff0678331e3d47d107.docx"},{"id":94240574,"identity":"1b2f08d2-d2b9-4d71-8f72-4265c32a139a","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7391,"visible":true,"origin":"","legend":"","description":"","filename":"02b509f5126c4fa7aec16723f47af594.json","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/bd01aaeff7c0f25c3d99da04.json"},{"id":94240572,"identity":"31a0e1bd-adff-42b8-844c-7b4a15334b8b","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87539,"visible":true,"origin":"","legend":"","description":"","filename":"02b509f5126c4fa7aec16723f47af5941enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/a2e29a5efca583d5178b40c7.xml"},{"id":94240577,"identity":"1866a5eb-4887-48e6-b4e4-5bb311333f86","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"emf","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208596,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.emf","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/5432e8f059415fbeea27da07.emf"},{"id":94240578,"identity":"de9e4c57-147a-4f3a-94e7-674266981892","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"emf","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256696,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.emf","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/4b22cdcf80d51477b2bb3d53.emf"},{"id":94240576,"identity":"d2e9d768-1dac-48ed-a3a8-f24d6f9fddb8","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":94916,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/7c8ed897dce8708341eb25df.png"},{"id":94240768,"identity":"3c4430d2-0314-423c-ad94-e007bc6249c9","added_by":"auto","created_at":"2025-10-24 03:48:20","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16163,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/a8da13bf8e18fbcef9259c92.png"},{"id":94240585,"identity":"e6151619-2b7b-4ca3-8e4d-01b98d7a7431","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"jpeg","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":336531,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/f97db7bcd34396088447949f.jpeg"},{"id":94240579,"identity":"b90b9356-c320-4671-865b-eddfdd7a33ae","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"jpeg","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":115281,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/a2932accf7a43ea85188959d.jpeg"},{"id":94240583,"identity":"715afd30-84a0-4380-beb6-ab91be5ad11d","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":348417,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/b4a492c95474d1ba8aebfbe3.jpeg"},{"id":94240587,"identity":"e875992d-0186-4113-b217-570a32279054","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5630,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/21268137e3f2e989c6a1041b.png"},{"id":94240770,"identity":"4b4cf8e1-40da-4971-831e-34f1c53b3689","added_by":"auto","created_at":"2025-10-24 03:48:20","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6990,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/bc65c2f297930ee191654009.png"},{"id":94240584,"identity":"3c086020-bd87-43de-b35a-cbca9dfdd729","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15962,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/449e9ca4b26bd7e64cc03fac.png"},{"id":94240590,"identity":"6bba84b9-cf9a-4b24-8709-db0c6a2a42b8","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5820,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/4c347e05b1746c667e90e188.png"},{"id":94240772,"identity":"4ff57463-e306-4e64-b75e-4f910a940695","added_by":"auto","created_at":"2025-10-24 03:48:20","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":105716,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/c9a638d1c83799511bf0019c.png"},{"id":94240586,"identity":"4aa4b07f-b674-44c3-b134-3d00f578fc77","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":27429,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/1026778789f0b96ca48428d8.png"},{"id":94240581,"identity":"d3677e9b-82e4-4743-b537-d565acecc075","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":77655,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/0f5ab27702a65c42c77ad1af.png"},{"id":94240588,"identity":"cbf0a05c-ff84-4c43-89e4-1a1450359854","added_by":"auto","created_at":"2025-10-24 03:40:20","extension":"xml","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86383,"visible":true,"origin":"","legend":"","description":"","filename":"02b509f5126c4fa7aec16723f47af5941structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/5f555f3c995ad58cf2bf02fd.xml"},{"id":94241200,"identity":"9ab69f5f-6119-4097-945d-80b7614b9efb","added_by":"auto","created_at":"2025-10-24 03:56:20","extension":"html","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99682,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1/ef896a9d1467159941a07766.html"},{"id":94986205,"identity":"fd50bbf8-e40c-492a-882f-552b3f05fc24","added_by":"auto","created_at":"2025-11-03 07:00:03","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":668812,"visible":true,"origin":"","legend":"","description":"","filename":"AnEfficientPedestrianGenderRecognitionMethodBasedonKeyAreaFeatureExtractionandInformationFusion.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7746548/v1_covered_194cb8f2-3cc8-4fff-a19e-009218b09203.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Efficient Pedestrian Gender Recognition Method Based on Key Area Feature Extraction and Information Fusion","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":"Super-resolution processing, key area feature, information fusion, gender recognition","lastPublishedDoi":"10.21203/rs.3.rs-7746548/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7746548/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAiming to address the problems of scale uncertainty, feature extraction difficulty, model training difficulty, poor real-time performance, and sample imbalance in low-resolution images for gender recognition, this study proposes an efficient pedestrian gender recognition model based on key area feature extraction and fusion. First, a discrete cosine transform (DCT) based local super-resolution preprocessing algorithm is developed for facial image gender recognition. Then, a key area feature extraction and information fusion model is designed, using additional appearance features to assist in gender recognition and improve accuracy. The proposed model preprocesses images using the DCT image fusion and super-resolution methods, dividing pedestrian images into three regions: face, hair, and lower body (legs) regions. Features are separately extracted from each of the three image regions. Finally, a multi-region local gender recognition classifier is designed and trained, employing decision-level information fusion. The results of the three local classifiers are fused using a Bayesian computation-based fusion strategy to obtain the final recognition result of a pedestrian's gender. This study uses surveillance video data to create a dataset for experimental comparison. The experimental results show that, compared with the state-of-the-art algorithms, the proposed pedestrian gender recognition model based on multi-region feature extraction and information fusion can improve recognition accuracy, demonstrating high application potential for gender recognition tasks in real-world blurred images.\u003c/p\u003e","manuscriptTitle":"An Efficient Pedestrian Gender Recognition Method Based on Key Area Feature Extraction and Information Fusion","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-24 03:40:15","doi":"10.21203/rs.3.rs-7746548/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":"bd37710a-9e61-4aca-b055-5bdfb2de570c","owner":[],"postedDate":"October 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-31T16:38:47+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-24 03:40:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7746548","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7746548","identity":"rs-7746548","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}