Exploring gender prediction from iris biometrics

Fairhurst M., ERBİLEK M., Da Costa-Abreu M.

14th International Conference of the Biometrics Special Interest Group, BIOSIG 2015, Darmstadt, Germany, 9 - 11 September 2015, vol.P-245, (Full Text) identifier

  • Publication Type: Conference Paper / Full Text
  • Volume: P-245
  • Doi Number: 10.1109/biosig.2015.7314602
  • City: Darmstadt
  • Country: Germany
  • Middle East Technical University Northern Cyprus Campus Affiliated: No

Abstract

Prediction of gender characteristics from iris images has been investigated and some successful results have been reported in the literature, but without considering performance for different iris features and classifiers. This paper investigates for the first time an approach to gender prediction from iris images using different types of features (including a small number of very simple geometric features, texture features and a combination of geometric and texture features) and a more versatile and intelligent classifier structure. Our proposed approaches can achieve gender prediction accuracies of up to 90% in the BioSecure Database.