Pattern Recognition, International Conference on (2004)
Aug. 23, 2004 to Aug. 26, 2004
Junzhou Huang , Chinese Academy of Sciences, Beijing, P.R. China
Yunhong Wang , Chinese Academy of Sciences, Beijing, P.R. China
Tieniu Tan , Chinese Academy of Sciences, Beijing, P.R. China
Jiali Cui , Chinese Academy of Sciences, Beijing, P.R. China
As the first stage, iris segmentation is very important for an iris recognition system. If the iris regions were not correctly segmented, there would possibly exist four kinds of noises in segmented iris regions: eyelashes, eyelids, reflections and pupil, which will result in poor recognition performance. This paper proposes a new noise-removing approach based on the fusion of edge and region information. The whole procedure includes three steps: 1) rough localization and normalization, 2) edge information extraction based on phase congruency, and 3) the infusion of edge and region information. Experimental results on a set of 2,096 images show that the proposed method has encouraging performance for improving the recognition accuracy.
Y. Wang, T. Tan, J. Cui and J. Huang, "A New Iris Segmentation Method for Recognition," Pattern Recognition, International Conference on(ICPR), Cambridge UK, 2004, pp. 554-557.