Improving fingerprint recognition performance based on feature fusion and adaptive registration pattern

This paper proposes an adaptive registration pattern based fingerprint matching method dealing with the non-linear deformations in fingerprint. The "registration pattern" between two fingerprints is the optimal registration of every part of one fingerprint with respect to the other fingerprint. Registration patterns generated from imposter's matching attempts are different from those patterns from genuine matching attempts, although they share some similarities in the aspect of minutiae. In this paper, we combine minutiae, associate ridges and orientation fields to determine the registration pattern between two fingerprints and match them. The proposed matching scheme has two stages. An offline, training stage, derives a genuine registration pattern base from a set of genuine matching attempts. Then, an online matching stage registers the two fingerprints and determines the registration pattern. A further fine matching is conducted. In addition, the block orientation field is used as the global feature of a fingerprint to improve the performance of this method. And 2^nd and 3^rd relational structures between minutiae are applied to promote the fingerprint matching method. Experimental results evaluated by FVC2004 demonstrate that the proposed algorithm is an accurate one.