{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-supervised-learning-methodology-for-real","title":"A Supervised Learning Methodology for Real-Time Disguised Face Recognition in the Wild","arxiv_id":"1809.02875","date":"2018-09-08","proceeding":null,"authors":["Saumya Kumaar","Abhinandan Dogra","Abrar Majeedi","Hanan Gani","Ravi M. Vishwanath","S. N. Omkar"],"abstract":"Facial recognition has always been a challeng- ing task for computer vision\nscientists and experts. Despite complexities arising due to variations in\ncamera parameters, illumination and face orientations, significant progress has\nbeen made in the field with deep learning algorithms now competing with\nhuman-level accuracy. But in contrast to the recent advances in face\nrecognition techniques, Disguised Facial Identification continues to be a\ntougher challenge in the field of computer vision. The modern day scenario,\nwhere security is of prime concern, regular face identification techniques do\nnot perform as required when the faces are disguised, which calls for a\ndifferent approach to handle situations where intruders have their faces\nmasked. Along the same lines, we propose a deep learning architecture for\ndisguised facial recognition (DFR). The algorithm put forward in this paper\ndetects 20 facial key-points in the first stage, using a 14-layered\nconvolutional neural network (CNN). These facial key-points are later utilized\nby a support vector machine (SVM) for classifying the disguised faces based on\nthe euclidean distance ratios and angles between different facial key-points.\nThis overall architecture imparts a basic intelligence to our system. Our\nkey-point feature prediction accuracy is 65% while the classification rate is\n72.4%. Moreover, the architecture works at 19 FPS, thereby performing in almost\nreal-time. The efficiency of our approach is also compared with the\nstate-of-the-art Disguised Facial Identification methods.","url_abs":"http://arxiv.org/abs/1809.02875v1","url_pdf":"http://arxiv.org/pdf/1809.02875v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-supervised-learning-methodology-for-real","repo_url":"https://github.com/abrarmajeedi/Disguised-Facial-Recognition-DFR","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"face-identification","task_name":"Face Identification"},{"task_slug":"face-recognition","task_name":"Face Recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}