Modulation domain reference point detection for fingerprint recognition

Abstract

Accurate reference point detection is one of the first and most important signal processing steps in automatic fingerprint identification systems. The fingerprint reference point, which is also known as the core point, except in the case of arch type fingerprints, is defined as the location where the concave ridge curvature attains a maximum. We introduce a multi-resolution reference point detection algorithm that calculates the Poincare index in the modulation domain using an AM-FM model of the fingerprint image. We present experimental results where this new algorithm is tested against the FVC 2000 Database 2 and a second database from the University of Bologna. In both cases, we find that the modulation domain algorithm delivers accuracy and consistency that exceed those of a recent competing technique (Jain, A.K. et al., IEEE Trans. Image Proc., vol.9, no.5, p.846-59, 2000) based on integration of sine components in two adjacent regions.