The massive explosion and ubiquity of computing devices and the outreach ofthe web have been the most defining events of the century so far. As more andmore people gain access to the internet, traditional know-something andhave-something authentication methods such as PINs and passwords are proving tobe insufficient for prohibiting unauthorized access to increasingly personaldata on the web. Therefore, the need of the hour is a user-verification systemthat is not only more reliable and secure, but also unobtrusive andminimalistic. Keystroke Dynamics is a novel Biometric Technique; it is not onlyunobtrusive, but also transparent and inexpensive. The fusion of keystrokedynamics and Face Recognition engenders the most desirable characteristics of averification system. Our implementation uses Hidden Markov Models (HMM) formodelling the Keystroke Dynamics, with the help of two widely used FeatureVectors: Keypress Latency and Keypress Duration. On the other hand, FaceRecognition makes use of the traditional Eigenfaces approach.The results showthat the system has a high precision, with a False Acceptance Rate of 5.4% anda False Rejection Rate of 9.2%. Moreover, it is also future-proof, as thehardware requirements, i.e. camera and keyboard (physical or on-screen), havebecome an indispensable part of modern computing.
展开▼
