Combining Multiple Matchers for Fingerprint Verification: A Case Study in FVC2004

Abstract. Combining different algorithms submitted to the Third International Fingerprint Verification Competition (FVC2004) is studied. For this work, the matching results of more than 40 fingerprint systems from both academy and industry are available on standard benchmark data. In particular, we concentrate on score-level fusion of the different algorithms, studying the correlation between them by using featuresubset-selection techniques. Based on the general algorithmic descriptions provided by the participants, some interesting experimental findings are obtained.

• Type: Conference
• Year: 2005
• Where: ICIAP
• Authors: Julian Fiérrez-Aguilar, Loris Nanni, Javier Ortega-Garcia, Raffaele Cappelli, Davide Maltoni
• Keywords: General Algorithmic Descriptions, ICIAP 2005, Image Processing, Standard Benchmark Data, Third International Fingerprint