Fusion in fingerprint authentication: two finger types vs. two scanner types

This paper presents our study on fingerprint fusion in particular in three scenario sets: a) two fingers captured by the same scanner; b) the same finger captured by two different scanners; and c) two fingers both captured by two different scanners. As a test data set we use GUC100 multi-scanner fingerprint database which contains fingerprint images of all ten fingers from 100 subjects using a number of different fingerprint scanners. In total 780 fusion scenarios are studied. Our analysis indicate that score level fusion using average rule provides improvement in all scenarios. The fusion of the same fingers from different scanners appears to provide more performance improvement compared to the fusion of different fingers from the same scanner. Furthermore, we also reveal that fusion of different fingers both collected by different scanners are the best. Interestingly, results suggest that for fusion differences in scanner type are more valuable than differences in finger type.