Dynamic FingerPrint based on human motion and posture

The feasibility of generating a Dynamic FingerPrint (DFP) for an individual is explored. DFP is a unique signature generated based on a combination of body part movements. The body movements are obtained using a sensor suit recording inertial signals that are subsequently modeled on a humanoid frame with 23 degrees of freedom (DOF). Measured signals include position, velocity, acceleration, orientation, angular velocity and angular acceleration. DTW (Dynamic Time Warping) is used to classify the individual´s identity. The approach is described and the characteristics of the algorithms are presented. It is anticipated that these approaches will have applications in surveillance and security, medical science and animation modeling. Classification results show an accuracy rate of 100% for the 10 subjects studied during validation.