Probabilistic orientation field estimation for fingerprint enhancement and verification

Abstract

We present a novel probabilistic method to estimate the orientation field in fingerprint images. Traditional approach based on the smoothing of local image gradients usually generates unsatisfactory results in poor quality regions of fingerprint images. We show how to improve the orientation field estimation by first constructing a Markov random field (MRF) and then inferring the orientation field from the MRF model. The MRF is made up of two components. The first component incorporates a global mixture model of orientation fields learned from training fingerprint examples. The second component enforces a smoothness constraint over the orientation field in the neighboring regions. The improved fingerprint orientation field is useful in fingerprint enhancement and minutiae extraction processes. We show remarkable improvement of fingerprint verification accuracy on a relatively large fingerprint dataset based on the proposed approach.