A Fast Method for Iris Image Quality Assessment

With the increasing needs in security systems, iris recognition is relied as one of the most important solutions for biometrics-based identification systems. However, not all of the iris images acquired from the device are clear and sharp enough for recognition. Thus, the quality of iris images is important to the accuracy of iris recognition. Sometimes these images are not good enough due to a variety of factors: defocus blur, motion blur, eyelid occlusion and eyelash occlusion. This paper presents a fast approach for iris image quality assessment which can select the high quality iris images from the image sequences. Experiments used the public and free iris images taken from the CASIA and UBIRIS databases. The results showed that this evaluation system actually reflected the real quality of iris images and significantly improved the overall performance of the iris recognition system.