Improving Iris Performance using Segmentation with CASIA Database

Abstract :

We can recognize humans each other according to their numerous characteristics of age. Identity verification (authentication) in computer systems has been traditionally based on something like password, key, card, pin and etc. Things like keys or cards, however, tend to get stolen or lost and passwords or pin are often forgotten or disclosed. To attain more reliable identification we must use realistic characterization of the given person. Automated Biometrics methods are there for the identity verification on the principle of measurable physiological or behavioural uniqueness like fingerprint or voice sample or iris verification. The characteristics are measurable and unique. These appearances should not be duplicable, but it is unfortunately possible to create a copy that is accepted by the biometric system as a true sample. In biometric-based authentication, a legitimate user does not need to remember or carry anything and it is more reliable than traditional authentication schemes. However, the security of biometric systems can be undetermined in a number of ways. For instance, a biometric template can be replaced by an impostor’s template in a system database or it might be stolen and replayed. Consequently, the impostor could gain unauthorized access to a place or a system. Moreover, it has been shown that it is possible to create a physical spoof starting from standard biometric templates. Hence, securing the biometric template is vital to maintain security and integrity of biometric systems. This report actually gives an overview of improving IRIS recognition performance using segmentation with the help of CASIA database.

Authors: G.L.Kavitha, R.Sankar

Article : Improving Iris Performance using Segmentation with CASIA Database

Received: 08 August 2018
Accepted: 19 September 2018
Published: 29 September 2018