Group for Research in Decision Analysis

Markov Models for Directional Field and Singularity Extraction in Fingerprint Images

Sarat Dass

Reliable extraction of features from fingerprint images is crucial for subsequent fingerprint-based recognition. Often, fingerprint images are corrupted by noise which make the feature extraction step difficult. In this talk, a Bayesian formulation is proposed for reliable and robust extraction of the directional field in fingerprint images using a class of spatially smooth priors. The spatial smoothness allows for robust directional field estimation in the presence of moderate noise levels. In order to extract singularities, parametric singularity templates are proposed. The parametric models enable joint extraction of the directional field and the singularities in fingerprint impressions by dynamic updating of feature information. This allows for the detection of singularities that may have previously been missed, as well as better aligning the directional field around detected singularities. The best rates of spurious detection and missed singularities given by the algorithm are 4.9% and 7.1%, respectively, based on the NIST 4 database.