{"paper_id":"4d6a49bb-237d-4e21-9e17-3c3907d19646","body_text":"Efficient Unsupervised Clustering of Facial Geometry and Head Orientation Using 2D Landmarks | 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 Efficient Unsupervised Clustering of Facial Geometry and Head Orientation Using 2D Landmarks Vineet Kumar Rakesh, Amitabha Das, Tapas Samanta, Sarbajit Pal, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8719610/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 Facial geometry and head orientation play a crucial role in understanding human expressions and interactions. This study proposes an efficient, interpretable, and real-time framework for unsupervised clustering of facial geometry and head orientation using 2D geometric descriptors derived from dlib’s 68-point landmarks. The pipeline computes handcrafted descriptors, including lip aspect ratio, eye aspect ratio, normalized pupil position, and head pose angle, and leverages KMeans clustering to segment semantic facial states without supervision. Experiments conducted on FER and AffectNet datasets, demonstrate robust clustering performance, achieving Silhouette Scores of up to 0.721 for eye-state clustering and 0.567 for lip-state clustering. Comprehensive evaluation using the Davies–Bouldin Index and Calinski–Harabasz Score confirms the discriminative power of the proposed descriptors, while ablation studies highlight their individual contributions. Cross-dataset comparisons further reveal strong generalizability across modalities. With a lightweight design delivering 52 FPS on a CPU-only system and minimal memory footprint, the framework is well-suited for real-time applications, including fatigue monitoring, viseme synthesis, and human–computer interaction. Unlike prior geometric studies that focus on isolated modalities or deep clustering pipelines, this work presents a unified and interpretable geometry-based clustering paradigm that integrates four facial modalities—lips, eyes, pupils, and head orientation. The framework achieves comparable clustering quality to lightweight deep baselines while remaining fully transparent and CPU-real-time. This makes it well-suited for edge deployment and human–computer interaction scenarios. GitHub: https://vineetkumarrakesh.github.io/2D-Geo-Clustering 2D Facial Landmarks Unsupervised Clustering Geometric Descriptors Head Pose Estimation Real-Time Facial Analysis 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-8719610\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":true,\"archivedVersions\":[],\"articleType\":\"Research Article\",\"associatedPublications\":[],\"authors\":[{\"id\":587594600,\"identity\":\"6c66b315-36e6-4951-9d4c-2a53bb1f2431\",\"order_by\":0,\"name\":\"Vineet Kumar Rakesh\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyUlEQVRIiWNgGAWjYDACZjBpgxBgI05LQhopWsAg4TDxzmIwOM578MHHH+cT+9kPP2D8UnGYgU+6gYCWw3zJhjMSbifO7EkzYJY5c5iBTeYAfi2SzTxm0jwJt40NbvAwMEu2pTGwSSQQ1GL++0/COWN7orXwM/OYMTMkHJAzkOBhYPzYZkOUFmPJnrRkOYkzaQaHGc7Y8BDUwsZ/xvDDDxs7Hv72ww8f/qiQkJOfQUALCjjMw8DAQ4J6IGD8QZr6UTAKRsEoGCEAAG+iNfzfe3syAAAAAElFTkSuQmCC\",\"orcid\":\"\",\"institution\":\"Homi Bhabha National Institute\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Vineet\",\"middleName\":\"Kumar\",\"lastName\":\"Rakesh\",\"suffix\":\"\"},{\"id\":587594602,\"identity\":\"295c9b06-3958-49e0-baa2-1d566490c1bb\",\"order_by\":1,\"name\":\"Amitabha Das\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Jadavpur University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Amitabha\",\"middleName\":\"\",\"lastName\":\"Das\",\"suffix\":\"\"},{\"id\":587594604,\"identity\":\"7751da31-e337-4564-a72c-aa650d480584\",\"order_by\":2,\"name\":\"Tapas Samanta\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Variable Energy Cyclotron Centre\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Tapas\",\"middleName\":\"\",\"lastName\":\"Samanta\",\"suffix\":\"\"},{\"id\":587594608,\"identity\":\"6363c2d3-91e1-4e2f-a4b3-a3820fc1a557\",\"order_by\":3,\"name\":\"Sarbajit Pal\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Mahatma Gandhi University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Sarbajit\",\"middleName\":\"\",\"lastName\":\"Pal\",\"suffix\":\"\"},{\"id\":587594612,\"identity\":\"1bfe26d8-082a-4e7c-83ff-36a0d6f7d1e5\",\"order_by\":4,\"name\":\"Hemendra Kumar Pandey\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Variable Energy Cyclotron Centre\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Hemendra\",\"middleName\":\"Kumar\",\"lastName\":\"Pandey\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2026-01-28 10:54:55\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-8719610/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-8719610/v1\",\"draftVersion\":[],\"editorialEvents\":[],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":109249517,\"identity\":\"398e573d-9e52-419e-a892-64bf0bc76301\",\"added_by\":\"auto\",\"created_at\":\"2026-05-14 08:55:06\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":3877544,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"2DGeoFormatted.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-8719610/v1_covered_433b4450-ee5f-4b91-b847-327b1c2d7dae.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"Efficient Unsupervised Clustering of Facial Geometry and Head Orientation Using 2D Landmarks\",\"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\":\"info@researchsquare.com\",\"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\":\"2D Facial Landmarks, Unsupervised Clustering, Geometric Descriptors, Head Pose Estimation, Real-Time Facial Analysis\",\"lastPublishedDoi\":\"10.21203/rs.3.rs-8719610/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-8719610/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Facial geometry and head orientation play a crucial role in understanding human expressions and interactions. This study proposes an efficient, interpretable, and real-time framework for unsupervised clustering of facial geometry and head orientation using 2D geometric descriptors derived from dlib’s 68-point landmarks. The pipeline computes handcrafted descriptors, including lip aspect ratio, eye aspect ratio, normalized pupil position, and head pose angle, and leverages KMeans clustering to segment semantic facial states without supervision. Experiments conducted on FER and AffectNet datasets, demonstrate robust clustering performance, achieving Silhouette Scores of up to 0.721 for eye-state clustering and 0.567 for lip-state clustering. Comprehensive evaluation using the Davies–Bouldin Index and Calinski–Harabasz Score confirms the discriminative power of the proposed descriptors, while ablation studies highlight their individual contributions. Cross-dataset comparisons further reveal strong generalizability across modalities. With a lightweight design delivering 52 FPS on a CPU-only system and minimal memory footprint, the framework is well-suited for real-time applications, including fatigue monitoring, viseme synthesis, and human–computer interaction. Unlike prior geometric studies that focus on isolated modalities or deep clustering pipelines, this work presents a unified and interpretable geometry-based clustering paradigm that integrates four facial modalities—lips, eyes, pupils, and head orientation. The framework achieves comparable clustering quality to lightweight deep baselines while remaining fully transparent and CPU-real-time. This makes it well-suited for edge deployment and human–computer interaction scenarios. GitHub: https://vineetkumarrakesh.github.io/2D-Geo-Clustering\",\"manuscriptTitle\":\"Efficient Unsupervised Clustering of Facial Geometry and Head Orientation Using 2D Landmarks\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2026-02-11 02:54:51\",\"doi\":\"10.21203/rs.3.rs-8719610/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"5f443730-f119-4409-905c-050fcb2c1d10\",\"owner\":[],\"postedDate\":\"February 11th, 2026\",\"published\":true,\"recentEditorialEvents\":[{\"type\":\"decision\",\"content\":\"Rejected\",\"date\":\"2026-05-14T00:28:52+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-05-13T17:02:53+00:00\",\"index\":57,\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"80855139843815003474851063720604267729\",\"date\":\"2026-05-06T15:40:57+00:00\",\"index\":55,\"fulltext\":\"\"}],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"posted\",\"subjectAreas\":[],\"tags\":[],\"updatedAt\":\"2026-05-14T00:39:21+00:00\",\"versionOfRecord\":[],\"versionCreatedAt\":\"2026-02-11 02:54:51\",\"video\":\"\",\"vorDoi\":\"\",\"vorDoiUrl\":\"\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-8719610\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-8719610\",\"identity\":\"rs-8719610\",\"version\":[\"v1\"]},\"buildId\":\"XKTyCvWXoU3ODBz1xrDgd\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}