Temporal stability of visual search-driven biometrics

Abstract

Previously, we have shown the potential of using an individual's visual search pattern as a possible biometric. That study focused on viewing images displaying dot-patterns with different spatial relationships to determine which pattern can be more effective in establishing the identity of an individual. In this follow-up study we investigated the temporal stability of this biometric. We performed an experiment with 16 individuals asked to search for a predetermined feature of a random-dot pattern as we tracked their eye movements. Each participant completed four testing sessions consisting of two dot patterns repeated twice. One dot pattern displayed concentric circles shifted to the left or right side of the screen overlaid with visual noise, and participants were asked which side the circles were centered on. The second dot-pattern displayed a number of circles (between 0 and 4) scattered on the screen overlaid with visual noise, and participants were asked how many circles they could identify. Each session contained 5 untracked tutorial questions and 50 tracked test questions (200 total tracked questions per participant). To create each participant's "fingerprint", we constructed a Hidden Markov Model (HMM) from the gaze data representing the underlying visual search and cognitive process. The accuracy of the derived HMM models was evaluated using cross-validation for various time-dependent train-test conditions. Subject identification accuracy ranged from 17.6% to 41.8% for all conditions, which is significantly higher than random guessing (1/16 = 6.25%). The results suggest that visual search pattern is a promising, temporally stable personalized fingerprint of perceptual organization.

DeepEyedentificationLive: Oculomotoric Biometric Identification and Presentation-Attack Detection Using Deep Neural Networks

“…Spawned by the seminal works of Kasprowski and Ober [4] and Bednarik et al [5], and fueled by competitions in the following decade [14], [15], these methods can be subsumed into three categories: aggregational [16], [17], [18], statistical [19], [20], [21], [22] and generative methods. Suitable generative methods include Markov [23], [24] and graphical models [11], [25], [26].…”

Deep Gaze Velocity Analysis During Mammographic Reading for Biometric Identification of Radiologists

“…For eye tracking data, proposed approaches include frequency analysis using the fast Fourier transform (Kinnunen et al, 2010), statistical analysis of velocity (Silver & Biggs, 2006), and morphological analysis based on graph-based representations (Rigas, Economou, & Fotopoulos, 2012) to name a few. In our previous studies (Yoon et al, 2014(Yoon et al, , 2015, we employed HMMs, a probabilistic model with promising performance for classifying independent temporal sequences. HMMs capture temporal sequence dynamics using a state transition matrix, based on the Viterbi algorithm (Viterbi, 1967).…”

“…For example, Rothkopf and Pelz (2004) adapted hidden Markov models (HMMs) to characterize gaze velocities for the classification of different types of visual behavior. In our previous studies (Yoon et al, 2014(Yoon et al, , 2015, we also investigated the properties of gaze velocity using HMMs for general viewing of cognitive-dot stimuli related to the Gestalt grouping principles of similarity, continuation, proximity, and closure (Yoon et al, 2014), and for expert viewing of regions of interest within mammographic images (Yoon et al, 2015). Both studies suggested that gaze velocity is a promising biometric feature for general and medical viewing tasks.…”