Pixel-level singular point detection from multi-scale Gaussian filtered orientation field

Abstract

Singular point, as a global feature, plays an important role in fingerprint recognition. Inconsistent detection of singular points apparently gives an affect to fingerprint alignment, classification, and verification accuracy. This paper proposes a novel approach to pixel-level singular point detection from the orientation field obtained by multi-scale Gaussian filters. Initially, a robust pixel-level orientation field is estimated by a multi-scale averaging framework. Then, candidate singular points in pixel-level are extracted from the complex angular gradient plane derived directly from the pixel-level orientation field. The candidate singular points are finally validated via a cascade framework comprised of nested Poincare indices and local feature-based classification. Experimental results over the FVC 2000 DB2 confirm that the proposed method achieves robust and accurate orientation field estimation and consistent pixel-level singular point detection. The experimental results exhibit a low computational cost with better performance. Thus, the proposed method can be employed in real-time fingerprint recognition.