{"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/fmcode-a-3d-in-the-air-finger-motion-based","title":"FMCode: A 3D In-the-Air Finger Motion Based User Login Framework for Gesture Interface","arxiv_id":"1808.00130","date":"2018-08-01","proceeding":null,"authors":["Duo Lu","Dijiang Huang"],"abstract":"Applications using gesture-based human-computer interface require a new user\nlogin method with gestures because it does not have a traditional input method\nto type a password. However, due to various challenges, existing gesture-based\nauthentication systems are generally considered too weak to be useful in\npractice. In this paper, we propose a unified user login framework using 3D\nin-air-handwriting, called FMCode. We define new types of features critical to\ndistinguish legitimate users from attackers and utilize Support Vector Machine\n(SVM) for user authentication. The features and data-driven models are\nspecially designed to accommodate minor behavior variations that existing\ngesture authentication methods neglect. In addition, we use deep neural network\napproaches to efficiently identify the user based on his or her\nin-air-handwriting, which avoids expansive account database search methods\nemployed by existing work. On a dataset collected by us with over 100 users,\nour prototype system achieves 0.1% and 0.5% best Equal Error Rate (EER) for\nuser authentication, as well as 96.7% and 94.3% accuracy for user\nidentification, using two types of gesture input devices. Compared to existing\nbehavioral biometric systems using gesture and in-air-handwriting, our\nframework achieves the state-of-the-art performance. In addition, our\nexperimental results show that FMCode is capable to defend against client-side\nspoofing attacks, and it performs persistently in the long run. These results\nand discoveries pave the way to practical usage of gesture-based user login\nover the gesture interface.","url_abs":"http://arxiv.org/abs/1808.00130v1","url_pdf":"http://arxiv.org/pdf/1808.00130v1.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":"fmcode-a-3d-in-the-air-finger-motion-based","repo_url":"https://github.com/duolu/fmkit","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"user-identification","task_name":"User Identification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}