Introduction of cylinder quality measure into Minutia Cylinder-Code based fingerprint matching

Abstract

Poor data quality is responsible for many or even most matching errors in fingerprint recognition systems. It became obvious that particular effort is needed in adaptation of the state-of-the-art minutiae-based fingerprint matching techniques to real-world conditions using quality measures. In this paper, we address a challenging problem of how to associate local quality measures to local minutiae descriptors, in particular Minutia Cylinder-Code (MCC), in order to obtain better recognition rates. Firstly, we introduce a new local quality measure, called Cylinder Quality Measure (CQM), corresponding to each MCC descriptor by combining the qualities of individual minutiae involved. Then, we propose a method for incorporating such quality measures into fingerprint matching through a quality-based relaxation procedure. Our experiments on the FVC2002 (DB1 and DB3) and FVC2004 (DB3) databases demonstrate that integrating the cylinder quality measure through the proposed procedure improves the overall matching performance comparing to the state-of-the-art MCC based fingerprint matching algorithms.