Elakkiya Ellavarason defended her Master's Thesis on 'Effects of Ageing on Iris Biometric Recognition'

The topic ‚ageing‘ has gained interest in the field of iris biometrics in recent years and is under investigation. Being fully aware of the fact that iris biometric recognition systems are successfully deployed on large-scale projects such as Indian UID(ongoing), UAE border immigration service, etc., it is crucial to consider the reliability factor on using iris as a biometric modal for long period usage. The goal of the thesis is to investigate effects of ageing on iris biometrics. The experimental investigation is divided into three parts, first, to find out the presence of iris ageing using different iris processing algorithms. Second, to analyze if the ageing effect is subject-specific. The final part is to analyse the metrics on which iris ageing is proved.

The investigation of template ageing for iris biometrics was done on ND-Iris- Template-Aging-2008-2010 database, which contains dataset with two years of elapsed time between the earliest and most recent iris images. Analysis of ageing effects across six different iris recognition algorithms present in the iris processing software USIT, reveal performance degradation across all of these algorithms. This suggests that the decrease in false non-match rate is not algorithm specific.

Further, results of subject-specific analysis reveal that variations in pose and illumination can greatly contribute to increased comparison score. Therefore, in order to analyse ageing effects, it is necessary to introduce strict standards for acquiring good quality iris image which could keep these variations at a minimum level. Results obtained using the multi-instance image analysis across different feature extraction algorithm gave interesting results which challenges the metrics on which ageing is proven.