Abstract
This manuscript presents GazeBase, a large-scale longitudinal dataset containing 12,334 monocular eye-movement recordings captured from 322 college-aged participants. Participants completed a battery of seven tasks in two contiguous sessions during each round of recording, including a – (1) fixation task, (2) horizontal saccade task, (3) random oblique saccade task, (4) reading task, (5/6) free viewing of cinematic video task, and (7) gaze-driven gaming task. Nine rounds of recording were conducted over a 37 month period, with participants in each subsequent round recruited exclusively from prior rounds. All data was collected using an EyeLink 1000 eye tracker at a 1,000 Hz sampling rate, with a calibration and validation protocol performed before each task to ensure data quality. Due to its large number of participants and longitudinal nature, GazeBase is well suited for exploring research hypotheses in eye movement biometrics, along with other applications applying machine learning to eye movement signal analysis. Classification labels produced by the instrument’s real-time parser are provided for a subset of GazeBase, along with pupil area.
Highlights
Background & SummaryDue to their demonstrated uniqueness and persistence[1], human eye movements are a desirable modality for biometric applications[2]
Ensuring performance robustness with respect to data quality, and further investigating both task dependency and requisite recording duration is necessary to transition this technology to widespread commercial adoption
The exploration of emerging deep learning techniques, which have proven successful for more traditional biometric modalities[9], has been limited for eye movement biometrics
Summary
Due to their demonstrated uniqueness and persistence[1], human eye movements are a desirable modality for biometric applications[2]. Since their original consideration in the early 2000s3, eye movement biometrics have received substantial attention within the security literature[4] Recent interest in this domain is accelerating, due to the proliferation of gaze tracking sensors throughout modern consumer products, including automotive interfaces, traditional computing platforms, and head-mounted devices for virtual and augmented reality applications. Is well suited for supporting further investigation of emerging machine learning biometric techniques to the eye movement domain, such as metric learning[22,23] Beyond this target application, the resulting dataset is useful for exploring numerous additional research hypotheses in various areas of interest, including eye movement classification and prediction. This dissemination will help improve quality in subsequent research by providing a diverse set of recordings for benchmarking across the community[2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
