Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
Local minutiae descriptors such as Minutia Cylinder-Code (MCC) are becoming more popular in modern fingerprint matching systems. The matching performance depends a lot on the fingerprint image quality in global and local levels. Rejecting 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 rejection methods to filter out low quality pairs of MCC descriptors using minutiae qualities, with the final aim of improving global matching accuracy. Moreover, we propose an efficient rejection method based on discarding the low quality elements from local similarity matrix for MCC-based matching. Our extensive experiments on three different databases (FVC2002 DB2, FVC2002 DB3 and FVC2004 DB3) show that 1) the proper rejection of low quality MCC pairs from local similarity matrix either independently or using pairwise measures can improve the MCC based matching performance, 2) for the proposed rejection method, the quality of central minutiae is more efficient as cylinder quality measure than the average minutiae qualities in each descriptor.
Gaétan Jean A de Rassenfosse, Kyle William Higham