An Approach to Biometric Identification by Using Low-Frequency Eye Tracker

Abstract

Biometric identification is one of the most secure existing identification methods. Algorithms based on eye tracking techniques are being studied now by many authors as eye trackers had become more accessible during the last few years. This paper is related to a biometric identification approach and a problem of providing accurate identification results by using low-frequency eye tracker. This paper presents a review of the related works in the field as well as a general classification of different identification types. We stated a formal description of a saccade and an analyzed fragment of the gaze trajectory containing a saccade, which is based on the finite differences method, and revealed features of the eye movements that can be used for the identification purpose. Two classifiers are proposed and compared based on the experimental results obtained for them.