Iris recognition is a new method for personal identification based on the biological features, which has the significant value in the information and security field. In contrast with the other biometrics identification, it has the following advantages: abundant and unique textures, high precision, secular stability, more credibility, and difficult to be forged, in addition, iris capturing can not infringe users. Above all, Iris recognition, as an emerging biometric recognition approach, is becoming a very active topic in both research and practical applications.Iris recognition is a kind of pattern recognition. At first we have introduced the structure of iris recognition system. A typicial system is composed of iris image obtaining, iris image preprocessing (including iris location, normalization, image emphasizing), iris features extraction and encoding, pattern matching, classifier designing, and so on.In the thesis, the threshold of grey and edge tracing are used to get the centre and radius of inner circle of iris. And the Hough transform and Canny operators are used to extract that of outer circle of iris. Thus we can separate the iris from eye. In order to remove the effects caused by displacement and zoom of iris image, iris image is transformed from Cartesian coordinates to polar coordinates. For improving the effect of iris recognition and reducing the influence of unsymmetrical illumination, the iris image is transformed by histogram equalization.Wavelet transform is a time-frequency analytical method which is characterized by Multi Resolution Analysis. For feature extraction, Haar Wavelet transform is used to extract the feature of iris image by decomposition to 3 levels. The tests show that compared with Daugman iris recognition algorithm, this method has improved the coded length and coded time.For iris recognition, judging iris'outcome by Hamming distance. Experiment shows the approach speediness and feasibility. |