The Blank Stare: Retrieving Unique Eye Tracking Signatures Independent of Visual Stimuli

TL;DR

This paper investigates eye tracking signatures for biometric identification, comparing spatial and temporal approaches, and introduces Fourier analysis for spatial signatures, with empirical validation over extended periods.

Contribution

It presents a novel analysis method using Fourier transformation for spatial eye tracking signatures and compares different paradigms for biometric recognition.

Findings

Spatial and temporal signatures are stable over weeks and months.

Fourier analysis enhances the robustness of spatial signatures.

Empirical data supports the viability of eye tracking for biometric identification.

Abstract

Using Low Cost Portable Eye Tracking for Biometric Identification Or Verification: Eye tracking technologies have in recent years become available outside of specialised labs, and are starting to become integrated in tablets and virtual reality headsets. This offers new opportunities for use in common office- and home environments, such as for biometric recognition (identification or verification), alone or in combination with other technologies. This paper exposes two fundamentally different approaches that have been suggested, based on spatial and temporal signatures respectively. While deploying different stimulation paradigms for recording, it also proposes an alternative way to analyze spatial domain signatures using Fourier transformation. Empirical data recorded from two subjects over two weeks, three months apart, are found to support previous results. Further, variations and stability of some of the proposed signatures are analyzed over the extended timeframe and under slightly varying conditions.