Title :
Noise removal and impainting model for iris image
Author :
Junzhou Huang ; Wang, Yunhong ; Cui, Jiali ; Tan, Tieniu
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
Abstract :
Noise removal is an important problem for iris recognition. If the iris regions were not correctly segmented in iris images, segmented iris regions possibly include noises, namely eyelashes, eyelids, reflections and pupil. Noises influence the features of both noise regions and their neighboring regions, which will result in poor recognition performance. To solve this problem, this paper proposes a method for removing noises and impainting iris images. The whole procedure includes three steps: 1) localization and normalization, 2) noise removal based on phase congruency and 3) iris image impainting. A series of experiments show that the proposed method has encouraging performance for improving the recognition accuracy.
Keywords :
eye; feature extraction; image denoising; image recognition; image segmentation; eyelash; eyelid; image segmentation; impainting model; iris recognition; localization; noise removal; normalization; phase congruency; pupil; Eyelashes; Eyelids; Filtering; Image edge detection; Image processing; Image recognition; Image segmentation; Iris recognition; Laboratories; Noise shaping;
Conference_Titel :
Image Processing, 2004. ICIP '04. 2004 International Conference on
Print_ISBN :
0-7803-8554-3
DOI :
10.1109/ICIP.2004.1419437
