A linear regression analysis of the effects of age related pupil dilation change in iris biometrics

Abstract

Medical studies have shown that average pupil size decreases linearly throughout adult life. Therefore, on average, the longer the time between acquisition of two images of the same iris, the larger the difference in dilation between the two images. Several studies have shown that increased difference in dilation causes an increase in the false nonmatch rate for iris recognition. Thus, increased difference in pupil dilation is one natural mechanism contributing to an iris template aging effect. We present an experimental analysis of the change in genuine match scores in the context of dilation differences due to aging.