An efficcient and reliable algorithm for iris recognition based on Gabor filters

This paper presents a personal identification method based on iris. The method includes three steps. In the first one, the eye image is processed in order to obtain a segmented and normalized eye image. This is done by projection profiles, Hough transform and polar transformation. In the second step, the iris image is analyzed by a set of 16 Gabor filters. A signature vector composed of 96 features is obtained. In the third step, iris matching is based on the Euclidean distance between the two corresponding iris vectors. The method has been tested on Casia database. The obtained results show that the method is fast and reliable to segment and to recognize iris image.