Study of an Extensive Set of Eye Movement Features: Extraction Methods and Statistical Analysis

Accounting for Visual Field Abnormalities when Using Eye-tracking to Diagnose Reading Problems in Neurological Degeneration

State-of-the-art eye trackers provide valuable information for diagnosing reading problems by measuring and interpreting people's gaze paths as they read through text. Abnormal conditions such as visual field defects, however, can seriously confound most of today's existing methods for interpreting reading gaze patterns. Our objective was to research how visual field defects impact reading gaze path patterns, so the effects of such neurological pathologies can be explicitly incorporated into more comprehensive reading diagnosis methodologies. A cross-sectional, non-randomized, pilot clinical study including 45 patients with various neurologic disorders and 30 normal controls was designed. Participants underwent ophthalmologic/neuropsychologic and eye-tracker examinations using two reading tests of words and numbers. The results showed that the use of the eye tracker showed that patients with brain damage and an altered visual field require more time to complete a reading-text test by fixating a greater number of times (p < 0.001); with longer fixations (p = 0.03); and a greater number of saccades in these patients (p = 0.04). Our study showed objective differences in eye movement characteristics in patients with neurological diseases and an altered visual field who complained of reading difficulties. These findings should be considered as a bias factor and deserve further investigation.

Analysis of eye movements of workers in safe and unsafe behaviors using a video-based method

Analyzing eye movements of workers in safe and unsafe behaviors can reduce accidents. With a video-based method, the angular velocity of gaze direction (AVGD) represents micro-movements in gaze and angular velocity in saccade is used to analyze eye movements. A similar behavior simulation experiment is designed to collect operation videos, and an eye movement information extraction and processing framework is constructed to quantify and analyze eye movements. The results show that: the root mean square and movement frequency of AVGD can be used to recognize unsafe behavior; in operations with attention target fixation, compared with safe behavior, workers in unsafe behavior have higher angular velocity, movement frequency and turn frequency of eye movements; and in operations with attention target change, eye movement rules of workers in safe and unsafe behaviors depend on operation types. The results can provide features for unsafe behavior recognition and theoretical bases for safety training.

An Effective Gaze-Based Authentication Method with the Spatiotemporal Feature of Eye Movement

Eye movement has become a new behavioral feature for biometric authentication. In the eye movement-based authentication methods that use temporal features and artificial design features, the required duration of eye movement recordings are too long to be applied. Therefore, this study aims at using eye movement recordings with shorter duration to realize authentication. And we give out a reasonable eye movement recording duration that should be less than 12 s, referring to the changing pattern of the deviation degree between the gaze point and the stimulus point on the screen. In this study, the temporal motion features of the gaze points and the spatial distribution features of the saccade are using to represent the personal identity. Two datasets are constructed for the experiments, including 5 s and 12 s of eye movement recordings. On the datasets constructed in this paper, the open-set authentication results show that the Equal Error Rate of our proposed methods can reach 10.62% when recording duration is 12 s and 12.48% when recording duration is 5 s. The closed-set authentication results show that the Equal Error Rate of our proposed methods can reach 5.25% when recording duration is 12 s and 7.82% when recording duration is 5 s. It demonstrates that the proposed method provides a reference for the eye movements data-based identity authentication.

GazeBase, a large-scale, multi-stimulus, longitudinal eye movement dataset

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.