Title :
Iris localization: Detecting accurate pupil contour and localizing limbus boundary
Author :
Jarjes, Ann A. ; Wang, Kuanquan ; Mohammed, Ghassan J.
Author_Institution :
Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol. (HIT), Harbin, China
Abstract :
Iris-based recognition system is highly dependent on the accuracy of iris localization. In this paper, a new algorithm for iris localization is presented, it detects the precise pupil contour and localizes limbus boundary. The pupil boundary is first localized by fitting a circle to the set of pupil boundary points detected by using the angular integral projection function (AIPF). Then, the precise contour is detected using active contour model initialized on the pupil circle. While for the localization of limbus boundary, the AIPF is applied again within two rectangles on both iris sides. Experimental results on CASIA V3.0 iris image database, prove that the proposed algorithm improves the accuracy and performance of iris localization.
Keywords :
iris recognition; object recognition; AIPF; CASIA V3.0; Iris localization; Iris-based recognition system; Limbus boundary localization; accurate pupil contour detection; active contour model; angular integral projection function; iris image database; pupil circle; Active contours; Biometrics; Fingerprint recognition; Image databases; Image edge detection; Image segmentation; Integral equations; Iris recognition; Isolation technology; Robotics and automation; active contour; angular integral projection; biometrics; iris localization;
Conference_Titel :
Informatics in Control, Automation and Robotics (CAR), 2010 2nd International Asia Conference on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-5192-0
Electronic_ISBN :
1948-3414
DOI :
10.1109/CAR.2010.5456828
