Iris Location And Quality Assessment Algorithm Research And Implementation

Nowadays, information security appears more and more important, while a growing iris recognition technology in this field has shown its great superiority. In the system of iris recognition, Iris localization and iris image quality assessment are very critical. Through have analyzed the existing algorithm, considering the characteristics of iris image, we designed a robust iris localization algorithm in this paper. In allusion to the problems in iris image quality, a step-style process is proposed to evaluate iris image quality. The main tasks of this thesis are as follows:First, consulting several existing iris capture devices, based on the characteristics of iris image captured, a new method to locate pupil and iris is proposed. Put to use the characteristics of pupil and light spot, at first, pupil was located. Then, we adopt edge of iris and curve fitting to location the outside of iris.Second, through analyzing a few existing algorithms and making correlation analysis of all the kinds of factors which affect the quality of iris images step by step, a series of related methods are designed to select eligible iris images to enroll or matching.Finally, a step-by-step assessment model of real-time preprocessing is established. Different thresholds are established in different stages. A image is unqualified as long as it isn't satisfied one of the thresholds, and is removed, then the camera will capture the other image. Only the image that meet the need all the thresholds are eligible to enroll or matching.The algorithms above are simulated in Matlab7.0, and in VC system the time of evaluating each image is less than 0.06s.