Characterizing biometric behavior through haptics and Virtual Reality

Haptics technology allows users to interact via the sense of touch by applying forces, vibrations and/or motions to users. With this technology, particularly by using force-feedback haptic devices (like stylus-based haptic devices), data directly generated by the user as he/she interacts with a system can be recorded and used-feature space- for authentication purposes. In this paper, nonlinear transformations are applied to the original feature space in order to produce Euclidean 3D spaces preserving the similarity structure of the samples, which are represented with Virtual Reality (VR) techniques. By using these new spaces, it is visualized how certain features (i.e. position, pressure and torque) contain more meaningful information that can characterize a biometric profile when virtually signing.