An approach for iris segmentation in constrained environments

Abstract

Iris recognition has become a popular technique for differentiating individuals on the basis of their iris texture with high accuracy. One of the decisive steps of iris recognition is iris segmentation because it notably affects the accuracy of feature extraction and matching steps. Most state-of-the-art algorithms use circular Hough transform (CHT) for segmenting the iris from an eye image. But, CHT does not work efficiently for eye images having less contrast. Therefore, a new approach is proposed here for isolating and normalizing the iris region, which is more robust than CHT. Experiments are performed on IITD iris database. The proposed algorithm works better than the traditional CHT.