Color Iris Authentication using Color Models

Abstract

Iris authentication is a popular method where persons are accurately authenticated. During authentication phase the features are extracted which are unique. Iris authentication uses IR images for authentication. This proposed work uses color iris images for authentication. Experiments are performed using ten different color models. This paper is focused on performance evaluation of color models used for color iris authentication. This proposed method is more reliable which cope up with different noises of color iris images. The experiments reveals the best selection of color model used for iris authentication. The proposed method is validated on UBIRIS noisy iris database. The results demonstrate that the accuracy is 92.1%, equal error rate of 0.072 and computational time is 0.039 seconds.