Skip to main content

Table 5 Test set segmentation errors (comparison with ground truth) 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
Average E 1 [%] CAHT IFPP OSIRIS WAHET CAHT IFPP OSIRIS WAHET
CAHT 2.47 2.56 2.46 2.33 2.95 2.88 2.73 2.80
IFPP   5.75 3.67 3.08   4.98 3.62 3.41
OSIRIS    5.27 3.01    5.69 3.10
WAHET     3.45     5.95
Average E 2 [%]         
CAHT 3.75 3.87 3.75 3.55 4.28 3.82 3.61 3.74
IFPP   10.09 5.58 4.65   6.37 4.77 4.49
OSIRIS    8.20 4.59    7.48 4.11
WAHET     5.20     7.85
Outlier count (E 1>10%)         
CAHT 10 10 9 6 10 6 4 9
IFPP   131 30 11   57 21 24
OSIRIS    78 19    108 19
WAHET     38     105
  1. Results where the fused result improves over both individual methods are given in bold, fused results improving over one of the individual methods are given in italics