Skip to main content

Table 6 Test set EER performance for individual algorithms (diagonal) versus pairwise quality-based segmentation fusion

From: Quality-based iris segmentation-level fusion

  (a) CASIA v4 interval database (b) IIT Delhi database
Equal-error rate [%] for LG CAHT IFPP OSIRIS WAHET CAHT IFPP OSIRIS WAHET
CAHT 1.10 1.04 1.03 0.90 0.94 0.45 0.25 0.76
IFPP   5.97 1.24 1.06   2.51 0.58 1.17
OSIRIS    2.10 0.96    3.74 0.70
WAHET     1.71     6.21
Equal-error rate [%] for QSW         
CAHT 0.81 0.74 0.79 0.43 0.94 0.57 0.71 0.89
IFPP   6.48 1.38 0.82   2.66 0.96 1.74
OSIRIS    2.94 0.95    5.41 1.47
WAHET     1.38     5.86
  1. Results where the fused result improves over both individual methods are given in bold