Iris Recognition System Based On Biorthogonal Multiwavelets

Biometric Recognition Technology develops very fast recently, which recognizes people by means of some sole and stable features. The operation of this technology is convenient and rapid. The biomedical literature suggests that similar to fingerprints, irises posses distinct features for uniquely identifying a person .Furthermore, iris is located on the naked part of human body as to enable the remote examination in the aid of a machine vision system。For this reason, Identification recognition system based on iris is regarded as a kind of noninvasive human identification technique .Therefore, Iris recognition system has been an active research area in recent years. Symmetry, short supporting, orthogonal and high-order vanishing moment are very important characteristics in signals processing, and it is proved that real coefficient single wavelet can not have these characteristics simultaneously, but multi-wavelets can do, which makes single wavelet be better than multi-wavelets in many aspects. Among the construction method of multi-wavelets, multi-wavelets proposed by Micchelli and Xu has the interval characteristic of self-affine, and it is easy and flexible for the wavelets filter to derive. This filter has the shortest length ofsupported, in the course of formation of transform filter matrix H, there is no overlap ofsupported, meanwhile, it can be reconstructed after wavelets decompose without boundary distortion, so we avoid boundary continuation. In the image processing, this multi-wavelets is a perfect feature extraction, and it can describe the local information feature of the image. In the beginning of this thesis, we introduce the multi-wavelets theory proposed by Charles A, Micchelli and Yuesheng Xu. On this basis, we talk about the derivation of fractal multi-wavelets filter with the interval characteristic of self-affine and the usage of it. According to the ordinary derivation method of biorthogonal multi-wavelets filter, we construct biorthogonal multi-wavelets filter based on the triangle domain, and put forward the algorithms of the decompose and the reconstruction of this filter. In the following, firstly, we talk about image obtain, iris localization, feature extraction, the construction of feature collection, the design of classifier and the match of images in the iris recognition system. Secondly, we give our recognition result. In this thesis, we acquire the iris image through the equipment made by ourselves. The coarsely localization is based on the gray distributing rule of the iris image, and the accurately localization is based on the connection of Canny operator and the Hough transform. Feature extraction is from the orthogonal fractal multi-wavelets filter based on the triangle domain. In the case of the conservation of iris overall feature, in order to use the detail information effectively, we use the connection of the correlation coefficient measure and Euclidean distance of covariance reciprocal with weight value to design the classifier. According to the characteristic of iris image collection, we add the idea of the block to the design of the classifier. Finally, we talk about the robustness of our method. The result of the experiment shows that it is a effective iris recognition system in which feature extraction is from biorthogonal fractal multi-wavelets filter based on the triangle domain, and the design of classifier is on the basis of the correlation coefficient measure and Euclidean distance of covariance reciprocal with weight value.