Robustness of Eye Movement Biometrics Against Varying Stimuli and Varying Trajectory Length

要旨

Recent results suggest that biometric identification based on human's eye movement characteristics can be used for authentication. In this paper, we present three new methods and benchmark them against the state-of-the-art. The best of our new methods improves the state-of-the-art performance by 5.2 percentage points. Furthermore, we investigate some of the factors that affect the robustness of the recognition rate of different classifiers on gaze trajectories, such as the type of stimulus and the tracking trajectory length. We find that the state-of-the-art method only works well when using the same stimulus for testing that was used for training. By contrast, our novel method more than doubles the identification accuracy for these transfer cases. Furthermore, we find that with only 90 seconds of eye tracking data, 86.7% accuracy can be achieved.

キーワード
eye tracking
gaze detection
eye movement biometrics
著者
Christoph Schröder
University of Bremen, Bremen, Germany
Sahar Mahdie Klim Al Zaidawi
University of Bremen, Bremen, Germany
Martin H.U. Prinzler
University of Bremen, Bremen, Germany
Sebastian Maneth
University of Bremen, Bremen, Germany
Gabriel Zachmann
University of Bremen, Bremen, Germany
DOI

10.1145/3313831.3376534

論文URL

https://doi.org/10.1145/3313831.3376534

会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2020.acm.org/)

セッション: Eye, tongue & muscle

Paper session
316B MAUI
5 件の発表
2020-04-27 23:00:00
2020-04-28 00:15:00
日本語まとめ
読み込み中…