Iris recognition based on non-separable wavelet

This paper focuses on the rotation noise of iris recognition. Current iris recognition systems are unable to deal with the rotation noise perfectly. We propose a novel method for iris matching that decompose iris picture into wavelet subband coefficients via 16 non-separable wavelet filters, and use generalized Gaussian density (GGD) modeling of each non-separable orthogonal wavelet coefficients as a means of feature extraction, then compute the Kullback-Leibler distance (KLD) between GGDs and compare the iris code using the Kullback-Leibler distance. Experiments show that the proposed method is rotation invariance, it does not decrease their recognition rate, when the iris image is rotated.