Cancelable iris-templates using key-dependent wavelet transforms

To enable cancelable biometrics, we apply two variants of key-dependent wavelet transforms (parameterised filters and wavelet packets) and combinations thereof in the feature extraction stage of a classical, wavelet-based iris recognition scheme. The CASIA V3 Interval iris database is used and experimental results on the matching performance and key sensitivity employing the cancelable transforms confirm that the proposed approach is secure and accurate.