Study On Iris Recognition Alogrithm

With the increasing emphasis on security, automated personal identification based on biometrics has been receiving extensive attention over the past decade. Iris recognition, a kind of biological characteristic recognition, springs up as a result of the social and economical development, and it shows great advantages. Iris recognition technology with its huge potential is relatively new among different kinds of biometric recognition technologies. For example, the characteristics of one's iris are steady all one's life, the capturing of iris image is non-invasive, and issues of iris possess the characters of living issues on account of the zooming process of pupils, which prevents counterfeiting. A typical iris recognition system includes iris imaging, iris location, iris recogntion and pattern matching. It involves numerous displine domains, such as computer vision and digital image processing, wavelet theory, pattern recognition etc. Iris location and recognition are the key of iris recognition system. In this paper we have introduced the birth, development and current situation of research on the iris recognition technique and studied the exisiting iris recognition algorithms. Then the algorithms on iris location are studied and the disadvantages are pointed. A new approach based on mathematic morphology and contours trace is put forward. After studing the means of Daugman's encode of iris texture, we adopted 2-D Gabor wavelet that was advanced by Daugman to extract the feature. The iris image texture can be divided into many bands whose engegy centralize in one frequency. We put forward a new encoding method that calculates every band's cross energy spectra with Gabor wavelets. The experiment results show that this location algorithm is faster and this encoding method is effective and reasonable. At the end of this thesis some existing problems are pointed out, then the good future of iris recognition technology is predicted.