

Performance Evaluation
For each database and for each algorithm:
 Each sample in the subset A is matched against the remaining samples of the
same finger to compute the False Non Match Rate
FNMR (also referred as False Rejection Rate  FRR). If the
matching g against h is performed, the symmetric one (i.e.,
h against g) is not executed to avoid correlation. The total
number of genuine tests (in case no enrollment rejections occur) is:
((8*7) /2) * 100 = 2,800
 The first sample of each finger in the subset A is matched against the first
sample of the remaining fingers in A to compute the False Match Rate FMR (also referred as False Acceptance Rate  FAR).
If the matching g against h is performed, the symmetric one (i.e., h against g)
is not executed to avoid correlation. The total number of false acceptance tests (in case no enrollment rejections occur)
is:
((100*99) /2) = 4,950
For each algorithm and for each database, the following performance indicators are reported:
 REJ_{ENROLL} (Number of rejected fingerprints during enrollment)
 REJ_{NGRA} (Number of rejected fingerprints during genuine matches)
 REJ_{NIRA} (Number of rejected fingerprints during impostor matches)
 Impostors and Genuines distributions
 FMR(t)/FNMR(t) curves
 ROC(t) curve
 EER (equalerrorrate)
 EER^{*} (the value that EER would take if the matching failures were excluded from the computation of FMR and FNMR)
 ZeroFMR (the lowest FNMR at which no False Matches occur)
 ZeroFNMR (the lowest FMR at which no False NonMatches occur)
 Average enrollment time
 Average matching time
The following average performance indicators are reported over the four databases:
 Average EER
 Average EER^{*}
 Average REJ_{ENROLL} (Average number of rejected fingerprints during enrollment)
 Average REJ_{MATCH} (Average number of rejected fingerprints during genuine and impostor matches)
 Average enrollment time
 Average matching time
Please refer to FVC2000 Technical Report for a detailed explanation of the performance indicators.

