The paper is about designing a fingerprint recognition system thatmakes use of the directional micropattern histograms of a fingerprintimage for local ridge orientation calculation, core point detection, andfeature extraction. An improved learning vector quantization network isalso proposed to avoid the unfairness of the winning rate and todetermine a proper number of hidden units. Experimental results showthat the recognition rate of the proposed method is 99.62% for asmall-scale fingerprint database
展开▼