Analysis of pattern recognition techniques for in-air signature biometrics

Abstract

Keywords:Biometrics Signature Accelerometer Hidden Markov models Bayes Dynamic time warpingAs a result of advances in mobile technology, new services which benefit from the ubiquity of these devices are appearing. Some of these services require the identification of the subject since they may access private user information. In this paper, we propose to identify each user by drawing his/her handwritten signature in the air (in-air signature). In order to assess the feasibility of an in-air signature as a biometric feature, we have analysed the performance of several well-known pattern recognition techniques-Hidden Markov Models, Bayes classifiers and dynamic time warping-to cope with this problem. Each technique has been tested in the identification of the signatures of 96 individuals. Furthermore, the robustness of each method against spoofing attacks has also been analysed using six impostors who attempted to emulate every signature. The best results in both experiments have been reached by using a technique based on dynamic time warping which carries out the recognition by calculating distances to an average template extracted from several training instances. Finally, a permanence analysis has been carried out in order to assess the stability of in-air signature over time.

Distinguishing users with capacitive touch communication

“…More recently, innovative uses of the various sensors available in most smart phones have led to a number of unconventional techniques. For example, there are proposals [8,28] for in-air gesture based authentication mechanism which uses the accelerometer sensors of the mobile device. Being easily visible to an adversary, such a scheme suffers from an unpleasant tradeoff between coming up with complex gestures and being susceptible to copy attacks, and can also be socially awkward.…”

SEGAUTH: A segment-based approach to behavioral biometric authentication

“…Compared to physiological biometrics, behavioral biometrics, which is embedded in humans’ behavior, is more difficult to steal or mimic and therefore causes less privacy concerns. Among growing interests in applying behavioral biometrics to security and privacy protection, gesture or motion based behavioral biometric authentication has attracted a great deal of research efforts (e.g., [1], [4], [18], [21], [24], [22], [19], [32], [30], [3]).…”

Behavioural Biometrics Using Electricity Load Profiles

“…Recently, a number of biometric approaches have gone beyond the typical physiological characteristics of the users and consider also behavioral aspects, such as gait [7], signature [8], or even HCI-related behaviors [9], such as keystrokes, mouse dynamics [10], [11] or Internet browsing histories [12]. All these approaches fall under the context of behavioral biometrics [9] and provide key tools to build accurate models of the users.…”