Dynamic sectored random projection for cancelable iris template

Biometrics is an indispensable tool which is being used widely in sensitive authentication applications. The increase in usage of the biometrics has also raised several issues related to the security of the biometrics. Several template protection schemes have been introduced to secure the biometrics from being compromised. Cancelable biometrics is a template protection scheme which enables the biometrics to be revoked like a token or password. The enrolment and matching of the biometrics are performed in a transformed domain. A dynamic sectored random projection for cancelable iris template has been proposed. The technique projects the sectored iris features on a dynamic random projection matrix to generate a transformed template. The dynamic random projection matrix is derived with respect to the iris feature itself and no external key is required. The samples from IIT-Delhi iris and CASIA Iris image version 1.0 databases were used in the experiments. The matching performance, non-invertibility and distinctiveness of the transformed templates generated with the proposed technique, have been analyzed. The transformed templates generated using the proposed approach, have proved to be promising and satisfying the characteristics of cancelable biometrics.