A Novel Approach to Minimize the Impact of Non Ideal Samples in Iris Recognition System

Iris recognition is a rapidly growing, widely accepted biometric authentication and an interesting field of research. This paper proposes a novel technique for reducing FRR using Feature Similarity Index Measure (FSIM). In the proposed algorithm, a matching coefficient is generated that gives the estimate of that sample image, best suitable for further processing. Analysis of the results has been performed by calculating the number of correct matches of the subject from the CASIA-Iris v.3 Lamp database. The results prove that the proposed algorithm reduces the False Rejection Rate in Iris Recognition System.