Minutiae-based template synthesis and matching for fingerprint authentication

Fingerprint matching is often affected by the presence of intrinsically low quality fingerprints and various distortions introduced during the acquisition process. An effective approach to account for within-class variations is by capturing multiple enrollment impressions of a finger. The focus of this work is on effectively combining minutiae information from multiple impressions of the same finger in order to increase coverage area, restore missing minutiae, and eliminate spurious ones. We propose a new, minutiae-based, template synthesis algorithm which merges several enrollment feature sets into a “super-template”. We have performed extensive experiments and comparisons to demonstrate the effectiveness of the proposed approach using a challenging public database (i.e., FVC2000 Db1) which contains small area, low quality fingerprints.