Efficient database techniques for identification with fuzzy vault templates

Abstract

The authentication based on biometric information has several advantages compared to solely password-based systems, which has led to a growing interest of industry and of public authorities in biometric-based systems. To meet the high security standards concerning biometric data, template protection systems such as the fuzzy vault are indispensable to maintain the secrecy of the critical information. Several publications have discussed the application of fuzzy vault to fingerprint authentication systems. However, for identification purposes in large databases the fuzzy vault protection of the biometric reference data poses severe efficiency challenges. In this work, we examine and compare the performance of three different approaches to enable the identification based on protected fingerprint minutiae templates also for large databases. All three approaches calculate a prioritization of the database entries exploiting filtering techniques and indexing structures. Based on this prioritization a search performing the complex exact comparison of database and query template is steered and thus will faster find a match.