The human iris is one of the most accurate ways to recognize an individual. While algorithms for iris recognition have been studied and commercialized, it is still a challenge to make iris biometric systems less intrusive. Because the human iris is very small high quality iris images with sufficient resolution are difficult to capture. Most commercial iris biometric systems require users to stand close to the camera while remaining still for several seconds or even moving back and forth according to voice prompts. Often with less-than- ideal iris images, blurred images are captured. The goal of this project was to create a means to restore iris patterns for successful recognitions based on image deblurring techniques.
Through this project, the research team developed a novel iris deblurring algorithm that makes use of prior knowledge obtained from the statistics of iris images, the characteristics of pupil and highlight regions, and the depth information from the capture system. An iris capture system was built using a commercial off-the-shelf camera and a depth sensor to evaluate the performance of the algorithm. Experiments show that our iris deblurring algorithm can signiﬁcantly restore blurred iris patterns and make iris capture less intrusive.