Robust algorithm for fingerprint identification with a simple image descriptor

Abstract

The paper describes a fingerprint recognition system consisting of image preprocessing, filtration, feature extraction and matching for recognition. The image preprocessing includes normalization based on mean value and variation. The orientation field is extracted and Gabor filter is used to prepare the fingerprint image for further processing. For singular point detection the Poincare index with partitioning method is used. The ridgeline thinning is presented and so is the minutia extraction by CN algorithm. Different Toeplitz matrix descriptions are in the work. Their behavior against abstract set of points is tested. The presented algorithm has proved its successful use in identification of shifted, rotated and partial acquired fingerprints without additional scaling. © 2011 Springer-Verlag.