An efficient and robust iris location algorithm plays a very important role in a real iris recognition system. A novel and efficient iris automatic location method is presented in this study. It includes following two...An efficient and robust iris location algorithm plays a very important role in a real iris recognition system. A novel and efficient iris automatic location method is presented in this study. It includes following two steps mainly： pu- pil location and iris outer boundary location. A digital eye image was divided into many small rectangular blocks with fixed size in the pupil location, and the block with the smallest average intensity was selected as a reference area. Then image binarization was implemented taking the average intensity of the reference area as a threshold. At last the center coordinates and radius of pupil were estimated by extending the reference area to the pupil＇s boundaries in the binary iris image. In the iris outer location, two local parts of the eye image were selected and transformed into polar coordinates from Cartesian reference. In order to detect the fainter outer boundary of the iris quickly, a novel edge detector was used to locate boundaries of the two parts. The center coordinates and radius of the iris outer boundary can be estimated using the fusion of the locating results of the two local parts and the location information of the pupil. The algorithm was tested on CASIA vl.0 and MMU vl.0 digital eye image databases and experimental results show that the proposed method has satisfying performance and good robustness.展开更多
基金Projects 6057201 supported by the National Natural Science Foundation of ChinaLZ985-231-582627 by the 985 Special Study Project of Lanzhou University
文摘An efficient and robust iris location algorithm plays a very important role in a real iris recognition system. A novel and efficient iris automatic location method is presented in this study. It includes following two steps mainly： pu- pil location and iris outer boundary location. A digital eye image was divided into many small rectangular blocks with fixed size in the pupil location, and the block with the smallest average intensity was selected as a reference area. Then image binarization was implemented taking the average intensity of the reference area as a threshold. At last the center coordinates and radius of pupil were estimated by extending the reference area to the pupil＇s boundaries in the binary iris image. In the iris outer location, two local parts of the eye image were selected and transformed into polar coordinates from Cartesian reference. In order to detect the fainter outer boundary of the iris quickly, a novel edge detector was used to locate boundaries of the two parts. The center coordinates and radius of the iris outer boundary can be estimated using the fusion of the locating results of the two local parts and the location information of the pupil. The algorithm was tested on CASIA vl.0 and MMU vl.0 digital eye image databases and experimental results show that the proposed method has satisfying performance and good robustness.
