An efficient biometric-based continuous authentication scheme with HMM prehensile movements modeling

Abstract Biometric is an emerging technique for user authentication thanks to its efficiency compared the traditional methods, such as passwords and access-cards. However, most existing biometric systems require cooperation of users provide only a login time authentication. To address these drawbacks, we propose in this paper new, efficient continuous scheme based on newly trait that still under development: prehensile movements. In work, model movements through Hidden Markov Model-Universal Background Model (HMM-UBM) with observations Gaussian Mixture (GMM). Unlike literature, gravity signal included. The results experiments conducted public database HMOG proprietary database, collected uncontrolled conditions, have shown are very promising. This new feature will allow be authenticated continuously, passively real time.