Biometric Template Selection: A Case Study in Fingerprints

Abstract

A biometric authentication system operates by acquiring biometric data from a user and comparing it against the template data stored in a database in order to identify a person or to verify a claimed identity. Most systems store multiple templates per user to account for variations in a person’s biometric data. In this paper we propose two techniques to automatically select prototype fingerprint templates for a finger from a given set of fingerprint impressions. The first method, called DEND, performs clustering in order to choose a template set that best represents the intra-class variations, while the second method, called MDIST, selects templates that have maximum similarity with the rest of the impressions and, therefore, represent typical measurements of biometric data. Matching results on a database of 50 different fingers, with 100 impressions per finger, indicate that a systematic template selection procedure as presented here results in better performance than random template selection.