Table 2: Comparison of the proposed approach with Besbes et al. [3], Jagadeesan et al. [18], and Conti et al. [25] (FAR, FRR, and response time (mean) in seconds).

AuthorMethodsModalitiesFAR (RBF
SVM)
FRR (RBF
SVM)
FAR
(Poly SVM)
FRR
(Poly SVM)
Training time (RBF
SVM)
Testing time
(RBF
SVM)
Training time (Poly SVM)Testing time
(Poly SVM)

Besbes et al. [3]Feature level fusionFingerprint14%22%16%22%5.70.355.890.29
Iris12%15%14%18%4.820.285.20.32
Fusion4%10%4%10%4.30.204.980.24

Jagadeesan et al. [18]Feature level fusionFingerprint2%17%8%18%6.020.316.880.34
Iris1%12%6%15%4.340.265.200.28
Fusion0%9%0%9%4.980.205.010.21

Conti et al.
[25]
Feature level fusionFingerprint2%17%8%19%5.470.285.900.30
Iris1%10%6%16%5.690.255.760.27
Fusion0%8%0%9%4.580.194.690.22

Proposed systemFeature level fusionFingerprint4%13%8%15%5.220.24.780.21
Iris2%12%4%16%3.250.254.940.16
Fusion0%6%0%7%3.270.123.980.19