Iris features extraction using wave atoms

It is shown that the application of wavelet packet analysis to the feature extraction part of an iris recognition system, is an interesting alternative to Gabor based methods. These methods use iris extraction and unwrapping. Wave atoms is a new transform which is half multi-scale and half multi-directional. This transform offers a better representation of images containing oscillatory patterns and textures than the others known transforms. This article presents an application on wavelet packet and wave atoms analysis in Radon space to the feature extraction part of an iris recognition system. The design and implementation of identification scheme are discussed. In order to evaluate the performance of the algorithm, CASIA1.0 and Phoenix iris databases have been considered. The results show that these methods have a serious potential in iris identification system.