Latent fingerprint match using Minutia Spherical Coordinate Code

Abstract

This paper proposes a fingerprint match algorithm using Minutia Spherical Coordinate Code (MSCC). This algorithm is a modified version of Minutia Cylinder Code (MCC). The advantage of this algorithm is its compact feature representation. Binary vector of every minutia only needs 288 bits, while MCC needs 448 or 1792 bits. This algorithm also uses a greedy alignment approach which can rediscover minutiae pairs lost in original stage. Experiments on AFIS data and NIST special data27 demonstrate the effectiveness of the proposed approach. We compare this algorithm to MCC. The experiments show that MSCC has better matching accuracy than MCC. The average compressed feature size is 2.3 Kbytes, while the average compressed feature size of MCC is 4.84 Kbytes in NIST SD27.