Person recognition based on touch screen gestures using computational intelligence methods

Abstract

Biometrics is based on the analysis of biometric features and is usually used for person recognition. In this article we analyze biometric features related to touch screen gestures. The proposed approach to person identification has a great application potential due to the popularity of mobile devices, so research in this area will be an important direction of technological development. The aims of this research are to design and build a data acquisition system to collect surveys resulting from the execution of single finger gestures on a mobile device screen and to propose data preprocessing procedure and to indicate the best classification method for person recognition based on these surveys. The experiment with fifty persons, nine gestures and ten repetitions was performed, so 4 500 surveys acquired and analyzed within the developed system. Depending on the classification method the accuracy of the task of gesture-based person recognition was in the range from 96.60% to 99.29%. All the patterns, which achieved the highest performance in terms of the typical performance measures consist of a single connected movement of a finger over the touch screen. The patterns which include multiple disconnected segments and/or taps are less successful in the task of recognizing people.