Leaderboard

In this leaderboard, you can compare the performance of different algorithms for iris detection using the GI4E database. You can submit your results and share them with other researchers here.

    We can compare the mean error of the algorithms according to two criteria:
  • Accuracy 0.05: The percentage of images whose normalized error is equal or less than 0.05
  • Global Accuracy: (Accuracy 0.05 + Accuracy 0.025 + Accuracy 0.1) / 3

Valid images: Algorithms may return invalid estimations for some images (i.e. NaNs). In those cases, estimations are ignored. Percentage of valid estimations is shown.

Sort by:

Rank Name Accuracy 0.05 Global Accuracy Valid images (%) Actions

1

Eye Loc

98.54

90.07

99.92

2

AccGrad

96.09

86.06

99.43

3

GI4E iris detector

90.56

79.41

99.43