Evaluation of User Identification Methods for Realizing an Authentication System Using s-EMG

Abstract

At the present time, mobile devices such as tablet-type PCs and smart phones have widely penetrated into our daily lives. Therefore, an authentication method that prevents shoulder surfing is needed. We are investigating a new user authentication method for mobile devices that uses surface electromyogram (s-EMG) signals, not screen touching. The s-EMG signals, which are detected over the skin surface, are generated by the electrical activity of muscle fibers during contraction. Muscle movement can be differentiated by analyzing the s-EMG. Taking advantage of the caracteristics, we proposed a method that uses a list of gestures as a password in the previous study. In this paper, we employed support vector machines and attempted to improve the gesture recognition method by introducing correlation coefficient and cross-correlation. A series of experiments was carried out in order to evaluate the performance of the method.