Neural Network Approach to Iris Recognition in Noisy Environment

Iris recognition is a challenging problem in the noisy environment. Our primary focus is to develop the reliable iris recognition system that can work in a noisy imaging environment and to increase the iris recognition rate on CASIA and MMUiris datasets. This research paper proposes two algorithms, first, a novel method for removing noise from the iris image and second, a texture feature extraction method using a combined approach of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM). Our proposed approach give highest recognition rate of 96.5% and low error rate and requires less execution time.