A Study of Iris Segmentation Methods using Fuzzy C-Means and K-Means Clustering Algorithm

A biometric system provides automatic identification of an individual based on a unique feature or characteristic possessed by the individual. Among most of the biometric methods, Iris recognition is regarded as the most reliable and accurate biometric identification system. The performance of iris recognition system highly depends on the accurate segmentation. For the Iris Segmentation there is a lot of methods that have been proposed in several decades. This present research work explores the Iris Segmentation process along with Fuzzy C-Means algorithm and K-Means clustering algorithm. The segmentation technique presented in this paper includes image acquisition, filtering, inner boundary localization, outer boundary localization and exclusion of eyelids and eyelashes. In this paper segmentation process are implemented using images from CASIA iris dataset image available on net. All the algorithms are implemented separately and the results are obtained. As a result Segmentation using FCM produces high accuracy rate of 98.20% and low error rate when compared to methods. Index Terms Iris Recognition, Segmentation, Boundary localization, Fuzzy C-Means clustering algorithm, K-Means clustering algorithm