Research Of Iris Recognition Based On Wave-let Zero-crossing And Filters

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 otherbiometrical identification, it has the following advantages: abundant and unique textures, highprecision, secular stability, more credibility, and difficult to be forged, in addition, iriscapturing can't infringe users. Above all, Researchers have paid much attention to irisrecognition and done much work in the region. Iris recognition, as an emerging biometricrecognition approach, is becoming a very active topic in both research and practicalapplications.In general, a typical iris recognition system includes iris imaging, iris liveness detection,and recognition and this paper focuses on the last issue. Combined with the previous work ofother researchers, a discussion is elaborately made on the key techniques concerning thelocation of iris circle, pre-procession of iris images, coding of iris texture and technology ofclassification. Additionally, some improved and creative approaches to these problems are putforward. And by analyzing some problems in this region, this paper focuses on the followingproblems: Firstly, due to limitation of image capturing condition, the iris images has lowcontrast and may have non-uniform brightness, and all these strongly affects the subsequentprocessing in feature extraction and matching. Secondly, efforts in feature extraction are stilllimited. In addition, the speed of identification should be improved as a real time system.This paper describes a new scheme for iris recognition. We first locate the iris region by acredible method. Then a simple yet effective local contrast enhancement method, namelyblock-based histogram equalization (BHE) is proposed to enhance image. Wave-letzero-crossing and a bank of spatial filters whose kernels are suitable for iris recognition, arethen used to capture local characteristics of the iris so as to produce discriminating texturefeatures. And a coarse to fine matching scheme is used in the classification. Experimentalresults show that the proposed method has an encouraging performance.