False Cores Reduction Based on Global Features of Fingerprint Orientation Field

Abstract

Singular point detection is a primary step in fingerprint recognition. Many approaches have been proposed, but the positive error rate is still too high. This paper proposes a new method based on global information of fingerprint orientation field to reduce false cores. The proposed method first estimates pixel-level orientation field and extract candidate singular points using the classic nested-Poincare index-based method. Then, both the opening direction of each candidate cores and the corresponding region along the opposite direction to the opening direction are calculated. Finally, the angle between the opening direction of a core and the orientation field in the region along the opposite direction of the opening direction is calculated as a new feature to further reduce false cores in the candidate set. Experimental results show that the error rate of the proposed method is lower than traditional algorithms. The total error rate decreases 29.5% and the false positive rate of cores decreases 35.1% comparing with NPI-based [12] in the database of FVC2000-DB2a.