Study And Application On Personal Identification Based On Iris Pattern

Biological recognition technology has been widely used in recent world.Iris recognition is an emerging biometric technology.For its exclusive,stability,collectible and not invadable,iris recognition is being more and more regarded by people.In recent years,iris recognition has made progress in technology research and application, and has a wide prospect and market.Compared with face,voice fingerprint and other biometric technology,iris recognition has higher precision.The system based on iris recognition is made up of several parts:iris preprocessing,iris locating,iris normalization,iris feature extracting,coding and iris code matching.In the aspects of iris preprocessing,the paper uses two kinds of methods to get rid of the noise,that is median filer and improving the salt and the pepper filer.In order to get the inner boundary of iris,we use threshold value division to separate the pupil from the image,then perform point hough transform to determine the radius and center of the pupil.We use improving Daugman integral arithmetic operators to determine the range of the outer round according to the radius and center of the pupil. We changed the curvilinear integral to surface integral in the thin ring around the curve so that the influence of noise can be decreased.The paper improves the traditional iris normalization algorithm and work out the iris normalization algorithm based-on line picked-up to normalize the annular region of iris into a rectangle.It adopt the method of bilinear insert during the normalization.To get a better iris image,we use histogram to equalize the iris image.Algorithm based on Gabor transform is used to extract and code the feature of iris. We need to calculate the hamming distance of both of iris codes to judge whether the two irises come from one person.Judging from the results of the experiment,the identify system in this paper come to a higher right rate.