Fingerprint recognition using directional micropattern histograms and LVQ networks

The paper is about designing a fingerprint recognition system that makes use of the directional micropattern histograms of a fingerprint image for local ridge orientation calculation, core point detection, and feature extraction. An improved learning vector quantization network is also proposed to avoid the unfairness of the winning rate and to determine a proper number of hidden units. Experimental results show that the recognition rate of the proposed method is 99.62% for a small-scale fingerprint database.