Research Of Iris Recognition Based On Wavelet Transform And Mathematical Morphology Theory

Along with the development of modern network and digitalization, the technique of more convenient and reliable on the identification becomes more and more important. One major feature of information age is digital, the conventional identity authentication can’t meet the need of information security, so method based on biometrics emerges as a new identity authentication. Identity information security has become the attention focus. It becomes more and more important to find a new way instead of the traditional memory password. The error rate of iris recognition technology is the lowest among the several common biometric identification technologies, and iris recognition technology is also most approbated. Thanks to the characteristics of iris such as stability and safety, and both the recognition algorithm and application research have wide development prospects. The development and research of Iris identification system become the research focus.Iris identification system usually consists of three parts:iris image preprocessing (iris location, normalized, image enhancement), feature extraction and pattern matching (the certification and recognition). Systematic analysis and sorting the previous studies, this paper use new theory and propose new point of views based on the traditional algorithms. This paper makes deeply research and improvement of iris recognition algorithm. The main work of this paper includes the following respects:(1)In the iris positioning, this paper puts forward a more rapid localization algorithm. The method proposed in this paper is combined of rough positioning and pointwise detection in a limited area can correctly find out the inner and the outer boundary of the iris. Compared with the traditional algorithm, this algorithm is simple, easy to realize, improves the positioning accuracy and avoids the blinding search so as to improve the accuracy of the overall iris identification. Experimental results verify the feasibility of the proposed algorithm.(2)In feature extraction, this paper puts forward the concepts of wavelet transform and mathematical morphology. The use of this approach is an innovation point of this paper. Firstly, extracts iris characteristics though applying3layers wavelet decomposition on the normalized image and using the method of region description operator in mathematical morphology. Wavelet transform (WT) possesses good localized time-frequency characteristics. We also use mathematical morphology for its good characteristic of image processing.(3)In encoding and matching, rough set theory is introduced in the progress of image matching. The matching efficiency will be improved greatly if those pictures which are not bound to be registered can be shut up. So the calculated quantities can be reduced before matching the codes one-by-one bit.All the above algorithms are simulated on the platform of MATLAB7.0with the CASIA V1.0, as the original images which includes756eye images from108different eyes. Experimental results show that the proposed method is convenient and feasible. The wavelet transform combined with mathematical morphology compared with the traditional methods has significantly increased the accuracy of the iris recognition.