A Contrario Detection of False Matches in Iris Recognition

The pattern of the human iris contains rich information which provides one of the most accurate methods for recognition of individuals. Identification through iris recognition is achieved by matching a biometric template generated from the texture of the iris against an existing database of templates. This relies on the assumption that the probability of two different iris generating similar templates is very low. This assumption opens a question: how can one be sure that two iris templates are similar because they were generated from the same iris and not because of some other random factor?

In this paper we introduce a novel technique for iris matching based on the

a contrario

framework, where two iris templates are decided to belong to the same iris according to the unlikelyness of the similarity between them. This method provides an intuitive detection thresholding technique, based on the probability of occurence of the distance between two templates. We perform tests on different iris databases captured in heterogeneous environments and we show that the proposed identification method is more robust than the standard method based on the Hamming distance.