Topic: Biometric Symmetry: Implications on Template Protection
by Marta Gomez-Barrero
D19/2.03a, June 22, 2017 (Thursday), 12.00 noon
Keywords — biometrics, entropy, symmetry, amount of information
In the past, many efforts have been directed to develop biometric template protection schemes to secure biometric reference data, i.e. templates. One fundamental premise in the design of such schemes is that the entropy of the templates should be maximised in order to improve the level of protection. In parallel, several works have address the difficult problem of measuring the entropy of biometric characteristics. However, the impact of the correlation present in different parts of a single biometric characteristic (e.g., left and right part of the face) or within two instances of a single subject (e.g., left and right palmprints) on the joint entropy of a multi-biometric template has been frequently overlooked. In this paper we address this issue, proposing a way to measure such correlation from an information theoretical perspective. We then apply the proposed measure to a particular case study based on periocular biometrics, using the MobBIO database. The results show that up to 70% of the information comprised in both periocular regions of a given subject is correlated. Finally, we analyse the implications of such entropy loss on biometric template protection schemes.