Combination of different fingerprint systems: a case study FVC2004

The purpose of our paper is to investigate the correlation among the best state of art algorithms for fingerprint verification presented at FVC2004. For this work, the matching results of more than 40 fingerprint systems from both academy and industry are available on standard benchmark. We show that the fusion among some competitors of FVC2004 permits a drastically reduction of the performance. Particularly interesting is the result obtained by combining the competitors of FVC2004 in terms of Equal Error Rate (the most used parameter in the evaluation of real identification systems), significantly lower than that obtained by the winner of FVC2004. The results of this paper confirm that a multi-matcher system can overcome some of the limitations of a single matcher resulting in a substantial performance improvement