Online fingerprint template improvement

Abstract

This work proposes a technique that improves fingerprint templates by merging and averaging minutiae of multiple fingerprints. The weighted averaging scheme enables the template to change gradually with time in line with changes of the skin and imaging conditions. The recursive nature of the algorithm greatly reduces the storage and computation requirements of this technique. As a result, the proposed template improvement procedure can be performed online during the fingerprint verification process. Extensive experimental studies demonstrate the feasibility of the proposed algorithm.