Method Of Iris Recognition Based On Zero-Crossing Detection

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 biometrical 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't infringe users. Above all, Researchers have paid much attention to iris recognition and done much work in the region. Iris recognition, as an emerging biometric recognition approach, is becoming a very active topic in both research and practical applications. 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 of other researchers, a discussion is elaborately made on the key techniques concerning the location of iris circle,pre-procession of iris images, coding of iris texture and technology of classification.Additionally,some improved and creative approaches to these problems are put forward. And by analyzing some problems in this region, this paper focuses on the following problems: Firstly due to limitation of image capturing condition, the iris images has low contrast and may have non-uniform brightness, and all these strongly affects the subsequent processing in feature extraction and matching. Secondly, efforts in feature extraction are still limited.We first locate the iris region by a credible method. Then a simple yet effective local contrast enhancement method, namely histogram equalization is proposed to enhance image. Wavelet zero-crossing and a bank of spatial filters whose kernels are suitable for iris recognition, are then used to capture local characteristics of the iris so as to produce discriminating texture features. And a mass frequency to fine matching scheme is used in the classification. finally test the adaption of the algorithm using different wavelet filter. Experimental results show that the proposed method has an encouraging performance.