Biometric identification via an oculomotor plant mathematical model

Abstract

There has been increased interest in reliable, non-intrusive methods of biometric identification due to the growing emphasis on security and increasing prevalence of identity theft. This paper presents a new biometric approach that involves an estimation of the unique oculomotor plant (OP) or eye globe muscle parameters from an eye movement trace. These parameters model individual properties of the human eye, including neuronal control signal, series elasticity, length tension, force velocity, and active tension. These properties can be estimated for each extraocular muscle, and have been shown to differ between individuals. We describe the algorithms used in our approach and the results of an experiment with 41 human subjects tracking a jumping dot on a screen. Our results show improvement over existing eye movement biometric identification methods. The technique of using Oculomotor Plant Mathematical Model (OPMM) parameters to model the individual eye provides a number of advantages for biometric identification: it includes both behavioral and physiological human attributes, is difficult to counterfeit, non-intrusive, and could easily be incorporated into existing biometric systems to provide an extra layer of security.

On Biometrics With Eye Movements

“…Other researchers in the field of eye movement biometrics have reported results as follows: average false acceptance rate (FAR) from 1.4% to 17.5% and average false rejection rate (FRR) from 12.6% to 28.9% [20] for 9 subjects, and an identification rate of 83% for 12 subjects [21]; FAR 5.4% and FRR 56.6% for 41 subjects [22]; an equal error rate (EER) of nearly 30% for 15 subjects [23]; EER around 35% for 173 subjects [24]; the best EER of 10.8% [28] for 200 subjects; accuracy of 63% for 32 subjects [26], the best accuracy of 43.1% for 22 subjects [26]; and an accuracy of 33.3% for 34 subjects [27]. The results obtained in the present research are at least equally good compared with these preceding studies.…”

“…Those with less than 30-40 subjects can be seen as preliminary investigations purely on statistical grounds. A researcher with a thorough knowledge of machine learning algorithms could show the weaknesses of how inadequately scarce tests have obviously been implemented in some of the previous research [20][21][22][23][24][25][26][27], and some descriptions of the test procedures have been very narrow. In order to achieve statistically reliable and credible results, the validation task has to be done thoroughly and it must follow the correct principles of testing in machine learning.…”

“…Nevertheless, eye movements were found to be less useful for biometric identification than other factors, particularly the distance between the eyes of the subject. Eye movements from 41 subjects have been investigated by utilizing an optimization approach as an oculomotor plant model [22]. An eye movement technique has also been introduced for biometric identification by using face images as stimulations and graph matching methods for the eye movements recognized [23].…”

Human eye movements as a trait for biometrical identification

“…Their most valuable results were obtained for the distance between the eyes, a feature though that does not depend on the dynamics of eye movements. In 2010, Komogortsev et al [7] adopted a different approach for the exploitation of eye movements in biometric identification. They employed the oculomotor plant mathematical model (OPMM) [8], a formulation developed for the description of human eye movements, and used the recorded eye movements from the experimental subjects as an optimization framework for the model's parameters.…”

Eye movements during scene understanding for biometric identification

“…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.…”