It is important for a fingerprint classification system to validate the captured core point. The proposed approach aligns the impression region of interest based on Poincare's core points and the local orientation field first. Then, the location of the detected Poincare's core is refined by searching the neighboring ridge curve with the largest curvature based on the Henry system. The presented precise Henry-based core point classifier, which uses a method of locating wavelet extrema for core point detection, consists of skeletonization, 2-D non-separable wavelet transform, curve tracing, and core point localization. This enables it to overcome the shortcoming of the Poincare index and simultaneously address the ambiguity of core sub-region of interest. The innovative framework was tested on the NIST-4, FVC2002 DB1, and FVC2002 DB2 databases. Experimental results compare favorably to state-of-the-art singular point detectors.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com