Title :
An Iris Location Method Based on the Active Contour
Author :
Zhijia, Zhang ; Haifeng, Zhang ; Weiqi, Yuan
Author_Institution :
Shenyang Universtiy of Technol., Shenyang, China
fDate :
March 31 2009-April 2 2009
Abstract :
This paper presents two improved snake models to respectively locate the pupil-iris and iris-sclera edge in order to enhance the location accuracy problem caused by the non-standard circle characteristic of them. To locate the pupil-iris edge, the gradient image of iris without being filtered was directly used and the normalized vector normal to every snake node was added to help; to locate the iris-sclera edge, the normalized vector at every snake node pointing to the centroid of the contour based on the traditional snake was added to help. Large amount of experiments are carried out on the CASIA iris image database which shows that the accuracy rate is 99.51% and compared to the classical iris location algorithms such as the algorithm of Daugman and Hough transform combined with edge detection operator, the proposed models has a more accurate result.
Keywords :
edge detection; gradient methods; active contour; gradient image; iris location; iris-sclera edge location; location accuracy; normalized vector; pupil-iris edge location; snake model; Active contours; Algorithm design and analysis; Biometrics; Calculus; Computer science; Feature extraction; Greedy algorithms; Image databases; Image edge detection; Iris recognition; active contour; iris location; normalized vector; snake;
Conference_Titel :
Computer Science and Information Engineering, 2009 WRI World Congress on
Conference_Location :
Los Angeles, CA
Print_ISBN :
978-0-7695-3507-4
DOI :
10.1109/CSIE.2009.28