An effective fingerprint verification system is presented. It assumes that an existing reference fingerprint image must validate the identity of a person by means of a test fingerprint image acquired online and in real-time using minutiae matching.
The matching system consists of two main blocks: The first allows for the extraction of essential information from the reference image offline, the second performs the matching itself online. The information is obtained from the reference image by filtering and careful minutiae extraction procedures.
The fingerprint identification is based on triangular 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 reference set, featuring 85 percent correct verification (15 percent false negative) and 0.05 percent false positive, demonstrate the effectiveness of the verification technique.
Source: National Chiao Tung University
Author: Zsolt Miklos Kovacs-Vajna