IREX VI : Temporal Stability of Iris Recognition Accuracy

Abstract

Purpose: This work was conducted determine whether iris recognition accuracy decreases with the time lapsed between collection of initial enrollment and recognition images. More specifically, it seeks to quantify accuracy changes associated with any permanent changes to the iris and its proximal anatomy. This study is intended to quantify natural ageing effects in a healthy population; medical conditions and injuries can rapidly and severely affect recognition, so these are out of scope.Background: Stability is a required definitional property for a biometric to be useful. Quantitative statements of stability are operationally important as they dictate re-enrollment schedules e.g. of a face on a passport. The ophthalmologists who filed initial patents on iris recognition posited the iris to be "extremely stable" over "many years" but that "features which do develop" do so "rather slowly" [31]. A further patent held that irises have "texture of high complexity, that prove to be immutable over a person's life" [21]. This view held until several recent empirical studies suggested otherwise. Those studies, and ours, were motivated to check the veracity of the 1994 patent's assertion that an enrolled iris can be viable over decades. Two studies, using separate iris image collections from the University of Notre Dame, reported a large increase in false rejection rates [8,29]. The studies made attempts to account for several possible causes of the observed ageing, but could not conclude that the iris texture itself was changing. Their results, however, were widely reported [59,24, 3] with statements such as "irises, rather than being stable over a lifetime, are susceptible to ageing effects that steadily change the appearance over time" [33]. A further study, however, identified pupil-dilation[27] as the primary causal variable. Operational iris systems have identified individuals over periods up to 10 years[5] and 7 years [6].Conclusions: Using two large operational datasets, we find no evidence of a widespread iris ageing effect. Specifically, the population statistics (mean and variance) are constant over periods of up to nine years. This is consistent with the ability to enroll most individuals and see no degradation in overall recognition accuracy. Furthermore, we compute an ageing rate for how quickly recognition degrades with changes in the iris anatomy; this estimate suggests that iris recognition of average individuals will remain viable over decades. However, given the large population sizes, we identify a small percentage of individuals whose recognition scores do degrade consistent with disease or an ageing effect. These results are confined to adult populations. Additionally, we show that the template ageing reported in the Notre Dame studies is largely due to systematic dilation change over the collection period. Pupil dilation varies under environmental and several biological influences, with variations occuring on timescales ranging from below one second up to several decades. Our data suggests that the...

Understanding the subject-specific effects of pupil dilation on iris recognition in the NIR spectrum

“…To show efficacy in their approach, existence and uniqueness conditions were determined followed by different numerical simulations to show the deformation response of the iris region. Additionally, template effects were explored by Grother et al [17] who investigated the temporal stability of iris recognition systems. Their results confirm with the works of [18] and [15] that the difference in pupil dilation remains evident in iris recognition algorithms.…”

“…Our motivation for this work comes from the observations of [15], [17] and [19] that the dilation differences between the acquired and enrolled iris images affect iris matching accuracy. Furthermore, pupil dilation levels are different for each individual and these variations need to be considered.…”

“…Furthermore, pupil dilation levels are different for each individual and these variations need to be considered. Previous investigations, such as from the works of [12], [13], [15] and [17], are mainly empirical characterizations, which are limiting because they are dependent on the particular dataset and technology at hand. Additionally, the aforementioned works neglect to consider the complete effects of pupil activity that are dependent on the iris muscle activity and the neurological delay.…”

“…Next, we propose a methodology to determine the individually-based parameters where we test of our proposed process on a database of subject-specific near infrared (NIR) iris videos to show efficacy in our approach. Our work is an advancement of the prior art because we provide an analytical basis for describing the effects of pupil motion that are also present in the NIR spectrum, which can be expanded to explore other dilation defects such as aging [17]. Also, our model can be applied to understanding the impact of dilation on iris recognition from a state perspective [20].…”

“…Although iris recognition methods have demonstrated good matching accuracy on large datasets [17], a number of challenges are yet to be satisfactorily resolved. One such challenge is the impact of pupil dilation on the performance of iris recognition systems.…”