An effective fingerprint verification system is presented. It assumes that
an existing reference fingerprint image must validate the identity of a per
son by means of a Lest fingerprint image acquired online and in real-time u
sing minutiae matching. The matching system consists of two main blocks: Th
e first allows for the extraction of essential information from the referen
ce image offline, the second performs the matching itself online. The infor
mation is obtained from the reference image by filtering and careful minuti
ae extraction procedures. The fingerprint identification is based on triang
ular matching to cope with the strong deformation of fingerprint images due
to static friction or finger rolling. The matching is finally validated by
Dynamic Time Warping. Results reported on the NIST Special Database 4 refe
rence set, featuring 85 percent correct verification (15 percent false nega
tive) and 0.05 percent false positive, demonstrate the effectiveness of the
verification technique.