Discarding low quality minutia cylinder-code pairs for improved fingerprint comparison

Abstract

Local minutiae descriptors such as Minutia Cylinder-Code (MCC) are becoming increasingly popular in modern fingerprint verification systems. The verification performance depends on the fingerprint image quality in global and local levels. Discarding part of the lowest quality samples based on quality measures is a universal approach being widely used for improving the performance of biometric recognition systems. In this work, we evaluate several different discarding methods to filter out low quality pairs of MCC descriptors using minutiae qualities, with the final aim of improving global comparison accuracy. Moreover, we propose an efficient MCC based fingerprint comparison method based on discarding the low quality elements from local similarity matrix. Our extensive experiments on three different databases (FVC2002 DB2, FVC2002 DB3 and FVC2004 DB3) show that 1) the proper discarding of low quality MCC pairs from local similarity matrix either independently or using pairwise measures can improve the MCC based comparison performance, 2) for the proposed discarding method, the quality of central minutiae is more efficient as cylinder quality measure than the average minutiae qualities in each descriptor.