Study On Algorithm Of Iris Recognition Based On Texture Analysis And Wavelet Transform

With the rapid development of information technology, people have increasingly highrequirements in identification accuracy, practicality and safety. The traditional identificationmethods can’t satisfy the requirements of the modern world. In recent years, based onbiological recognition technology on its own unique advantages obtained a rapid developmentand application. In the existing each kind of biometrics, iris is non-invasive, uniqueness andstability etc, and use it to identify themselves with higher accuracy, at present the irisrecognition technology is considered the most has the broad application prospect ofbiometrics one.General iris identification systems mainly include iris image acquisition, iris imagepreprocessing, iris feature extraction and iris feature matching four parts. Among themprevailing localization and feature extraction is the most important part.According to the ring feature and gray variation characteristics of iris inherent, this paperwill divide iris position into two parts: inside edge localization and outer edge localization.First, the inside edge of the positioning threshold segmentation and curve fitting. According togray histogram segment pupil area, using binary preliminary will pupil segmentation out, thenin pupil binary image in search for the biggest connecting block eliminate eyelash and part ofthe darker areas in the interference, and finally in binary image finds the pupil edge points, theleast-square method estimates the radius and circle parameters of the pupil edge, get theaccurate positioning of iris inside edge. Then, positioning the outside edge, adopted calculusoperator, according to iris inner boundary parameter narrow within the scope of the centre of acircle, can avoid blind search, improve localization speed. Using this algorithm positioningaccuracy reached98.28%.In the iris feature extraction process, in view of the current existing feature extraction method of the shortcomings, in the following three aspects are improved:(1) the improvementto retain texture area;(2) postpone two direction extract texture feature signal;(3) use aderivative modulus maxima has better result than second derivative with zero detect mutatingof function f (x). In this paper, first, the selection of the texture characteristics was improved,and then postpone two direction characteristics extracted, and then using a derivative ofGaussian function as wavelet to characteristic signal make wavelet transformation, usingmodulus maxima location estimation singularity position, and feature encoding, and finallythe similarity of comparative feature codes, thus fulfilling the matching recognition. Using thealgorithm for the recognition rate reached96.89%.This algorithm in VS2008platform used CASIA1.0provided by the Chinese academy ofsciences automation iris database was tested, and results show that this algorithm can not onlyeffectively iris identification, but also has good recognition effect.