The Impact of Temporal Proximity between Samples on Eye Movement Biometric Identification

Abstract

Abstract. Eye movements identification is an interesting alternative to other biometric identification methods. It compiles both physiological and behavioral aspects and therefore it is difficult to forge. However, the main obstacle to popularize this methodology is lack of general recommendations considering eye movement biometrics experiments. Another problem is lack of commonly available databases of eye movements. Different authors present their methodologies using their own datasets of samples recorded with different devices and scenarios. It excludes possibility to compare different approaches. It is obvious that the way the samples were recorded influences the overall results. This work tries to investigate how one of the elements -temporal proximity between subsequent measurements -influences the identification results. A dataset of 2556 eye movement recordings collected for over 5 months was used as the basis of analyses. The main purpose of the paper is to identify the impact of sampling and classification scenarios on the overall identification results and to recommend scenarios for creation of future datasets.

Eye movements during scene understanding for biometric identification

“…Support Vector Machines (SVM) [5] and Classification and Regression Trees (CART) [2] have been employed for classification as they have shown good results in previous studies [6,12]. …”

“…Human eyes mainly exhibit smooth pursuit movements while following moving objects, but for biometric identification [6,11,12,15] and [18] two different moving objects have been employed. The first type is moving smoothly on the screen while the second one is in the form of an object jumping from point to point in a uniform or random pattern.…”

A Survey of Automatic Person Recognition Using Eye Movements

“…In studies related to eye movements, features are generally characterized by their source, which includes X-Y coordinates, saccades,¯xations, and scan paths. The most common method is to use the X-Y coordinates of the eye movements directly as features, 7,15,17 however to reduce redundancy their representation such as Mel-Frequency Cepstral Coe±cients (MFCC) 5 have also been employed. Features based on saccades normally include saccades amplitude, latency, accuracy, and maximum angular velocity.…”

“…In Ref. 15 the authors have investigated the e®ects of di®erent time interval between recording sessions on the identi¯cation rates. The database was collected over a¯ve months period using an Ober2 eye tracker given a jumping point stimulus.…”

“…This study is an extension of Ref. 15, in which the authors have only focused on the e®ects of MTI. The authors have improved upon several aspects,¯rst they have examined the e®ects of pre-processing in addition to MTI, second they have used a much larger database and have also improved upon the previous recognition results.…”