Empirical Evidence for Iris Match Score Degradation with Time Lapse in ICE 2006

It is widely assumed that, barring traumatic injury to the eye or eye surgery, a person’s iris does not change over time. This implies that iris recognition performance does not degrade as time increases after initial enrollmentalso known as the template-aging problem. We present results of the first study to investigate the validity of this assumption. We explore the effects of time lapse since enrollment on iris biometric match scores using a data set with four years time lapse between the earliest and most recent images of an iris (23 subjects, 46 irises, 6,814 total images). Experimental results are reported for three iris recognition algorithms. We find that the empirical mean of the distribution for similarity scores between iris images of the same person changes over four years–in biometric parlance, the match or genuine distribution changes. The change is statistically significant when comparing the mean of pairs of images taken within 120 days (∼4 months) and over 1200 days (∼3.25 years) for the three algorithms in our study. The mean of the match distribution changes so that the expected performance would degrade due to an increase in the false reject rate. Our results suggest that iris biometric templates undergo aging.