ISGD : A Dataset for Demographically-Aware Facial Analysis and Privacy-First Skincare Recommendation

ISGD : A Dataset for Demographically-Aware Facial Analysis and Privacy-First Skincare Recommendation | 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 ISGD : A Dataset for Demographically-Aware Facial Analysis and Privacy-First Skincare Recommendation Shreyansh Mishra, Himal Rana, Ankit Yadav, Chirag Bhut, Tanmoy Hazra This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9016523/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Facial attribute recognition plays a crucial role in applications ranging from human-computer interaction to personalised digital health. However, the effectiveness of existing systems is often limited by demographic bias in training data and the absence of domain-specific annotations, particularly for nuanced tasks such as skincare and grooming analysis. Large-scale datasets like CelebA are predominantly Western-centric and lack critical attributes including Oily Skin, Wrinkles, and grooming-related characteristics. To address these limitations, we introduce the Indian Skincare and Grooming Dataset (ISGD), a manually curated dataset comprising 30,141 facial images from the Indian subcontinent, annotated across 33 fine-grained binary attributes specifically designed for skincare and grooming analysis. Building upon ISGD, we propose AKRTI, a privacy-first inference pipeline that decouples visual processing from report generation. The system employs a ConvNeXt-Tiny backbone for multi-label facial attribute prediction. Importantly, only the predicted binary attribute vector—never the raw facial image—is passed to a large language model (LLM) to generate a personalised, human-readable skincare and grooming report, thereby preserving user privacy. Experimental results demonstrate that models trained on ISGD significantly outperform those trained on a size-matched subset of CelebA, achieving 94.26% overall accuracy and an F1-score of 0.8851. Furthermore, per-attribute evaluation indicates more consistent and reliable predictions for skincare-critical features such as beard presence, skin condition, and wrinkles. By introducing a demographically representative dataset alongside a privacy-aware framework, this work establishes a robust foundation for equitable and practical AI-driven facial analysis systems in personalised healthcare and wellness. The source code for all experiments and implementations is publicly available at our GitHub repository: https://github.com/HimalRana2610/ISGD. Archived at Zenodo (DOI: https://doi.org/10.5281/zenodo.18837811). Facial Attribute Recognition Image based dataset ISGD Skincare and Grooming Dataset Computer Vision Privacy-Aware Systems Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 19 Mar, 2026 Reviews received at journal 18 Mar, 2026 Reviewers agreed at journal 13 Mar, 2026 Reviewers invited by journal 11 Mar, 2026 Editor assigned by journal 03 Mar, 2026 Submission checks completed at journal 03 Mar, 2026 First submitted to journal 03 Mar, 2026 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-9016523","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":604211282,"identity":"8054525a-244a-4625-94f2-d76581547eff","order_by":0,"name":"Shreyansh Mishra","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDElEQVRIie2PsWrDMBCGLwic5RqvMjV5hisGpYVAXkWm4GfwEIyh4Cx9gA55j9JNQuAugq7t1Hrq4iGjoZTWTiBDidyOHfQNJ8T9H/oF4PH8R6YbBZICDIcLDoMdFuhU0EqQ+SyOyqPCflG4JAA7X5I6xth4L1Iy3TWVwOTR6LcWivR+Giro1hAvnIo2PK0yFDa7vtiCSR9uGExua8Cr0qHoUvZKjeIZxTmCSsj0xc5KwH3VU4qBpEurL0zucPGBUOyVyeeYUoPg0gZIHAVDYPNBYWOvRBazS5kHyPu/RFsyg0ImrrlTmb2+m5eOglW4MXrX5gXSk26adr1cuZSfPQ9HH+Z/yns8Ho/nNN++slMkV2nRXgAAAABJRU5ErkJggg==","orcid":"","institution":"Sardar Vallabhbhai National Institute of Technology Surat","correspondingAuthor":true,"prefix":"","firstName":"Shreyansh","middleName":"","lastName":"Mishra","suffix":""},{"id":604211283,"identity":"99d111b6-df26-49d2-b6e3-986c36c637b9","order_by":1,"name":"Himal Rana","email":"","orcid":"","institution":"Sardar Vallabhbhai National Institute of Technology Surat","correspondingAuthor":false,"prefix":"","firstName":"Himal","middleName":"","lastName":"Rana","suffix":""},{"id":604211284,"identity":"68b6face-dd39-4635-bd05-dd67d1a533f7","order_by":2,"name":"Ankit Yadav","email":"","orcid":"","institution":"Sardar Vallabhbhai National Institute of Technology Surat","correspondingAuthor":false,"prefix":"","firstName":"Ankit","middleName":"","lastName":"Yadav","suffix":""},{"id":604211285,"identity":"12e6b6c3-a3fa-47e9-b9d2-49759b3a75ed","order_by":3,"name":"Chirag Bhut","email":"","orcid":"","institution":"Sardar Vallabhbhai National Institute of Technology Surat","correspondingAuthor":false,"prefix":"","firstName":"Chirag","middleName":"","lastName":"Bhut","suffix":""},{"id":604211286,"identity":"bda476e0-1398-4a93-ac78-d927a034f70a","order_by":4,"name":"Tanmoy Hazra","email":"","orcid":"","institution":"Sardar Vallabhbhai National Institute of Technology Surat","correspondingAuthor":false,"prefix":"","firstName":"Tanmoy","middleName":"","lastName":"Hazra","suffix":""}],"badges":[],"createdAt":"2026-03-03 06:23:10","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9016523/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9016523/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104781189,"identity":"31155ff1-6a49-4344-95c4-e983a4b19b17","added_by":"auto","created_at":"2026-03-17 07:55:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":812670,"visible":true,"origin":"","legend":"","description":"","filename":"Skincareandgroomingrecommendationsystem1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9016523/v1_covered_be496cf0-1bd6-48d2-9a5a-39b4a0331363.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ISGD : A Dataset for Demographically-Aware Facial Analysis and Privacy-First Skincare Recommendation","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Facial Attribute Recognition, Image based dataset, ISGD, Skincare and Grooming Dataset, Computer Vision, Privacy-Aware Systems","lastPublishedDoi":"10.21203/rs.3.rs-9016523/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9016523/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFacial attribute recognition plays a crucial role in applications ranging from human-computer interaction to personalised digital health. However, the effectiveness of existing systems is often limited by demographic bias in training data and the absence of domain-specific annotations, particularly for nuanced tasks such as skincare and grooming analysis. Large-scale datasets like CelebA are predominantly Western-centric and lack critical attributes including Oily Skin, Wrinkles, and grooming-related characteristics.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eTo address these limitations, we introduce the Indian Skincare and Grooming Dataset (ISGD), a manually curated dataset comprising 30,141 facial images from the Indian subcontinent, annotated across 33 fine-grained binary attributes specifically designed for skincare and grooming analysis. Building upon ISGD, we propose AKRTI, a privacy-first inference pipeline that decouples visual processing from report generation. The system employs a ConvNeXt-Tiny backbone for multi-label facial attribute prediction. Importantly, only the predicted binary attribute vector—never the raw facial image—is passed to a large language model (LLM) to generate a personalised, human-readable skincare and grooming report, thereby preserving user privacy.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eExperimental results demonstrate that models trained on ISGD significantly outperform those trained on a size-matched subset of CelebA, achieving 94.26% overall accuracy and an F1-score of 0.8851. Furthermore, per-attribute evaluation indicates more consistent and reliable predictions for skincare-critical features such as beard presence, skin condition, and wrinkles. By introducing a demographically representative dataset alongside a privacy-aware framework, this work establishes a robust foundation for equitable and practical AI-driven facial analysis systems in personalised healthcare and wellness. The source code for all experiments and implementations is publicly available at our GitHub repository: https://github.com/HimalRana2610/ISGD. Archived at Zenodo (DOI:\u0026nbsp; https://doi.org/10.5281/zenodo.18837811).\u003c/p\u003e","manuscriptTitle":"ISGD : A Dataset for Demographically-Aware Facial Analysis and Privacy-First Skincare Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-13 05:05:15","doi":"10.21203/rs.3.rs-9016523/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"132775850573896896858380174363020538938","date":"2026-03-19T04:26:17+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-03-18T13:33:03+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"105058756423063427420988519220527106207","date":"2026-03-13T05:43:49+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-11T05:17:47+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-03T12:06:49+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-03T10:53:37+00:00","index":"","fulltext":""},{"type":"submitted","content":"The Visual Computer","date":"2026-03-03T06:07:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"the-visual-computer","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"tvcj","sideBox":"Learn more about [The Visual Computer](http://link.springer.com/journal/371)","snPcode":"371","submissionUrl":"https://submission.nature.com/new-submission/371/3","title":"The Visual Computer","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"31160266-9454-4c87-b7ef-e9eb893037ba","owner":[],"postedDate":"March 13th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-13T05:05:15+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-13 05:05:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9016523","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9016523","identity":"rs-9016523","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}