A NEW OBJECTIVE CRITERION FOR IRIS LOCALIZATION
Abstract
Iris localization is the most important step in iris recognition systems. For commonly used databases, exact data is not given which describe the true results of localization. To cope with this problem a new objective criterion for iris localization is proposed in this paper based on our visual system. A specific number of points are selected on pupil boundary, iris boundary, upper eyelid and lower eyelid using the original image and then distance from these points to the result of complete iris localization has been calculated. If the determined distance is below a certain threshold then iris localization is considered correct. Experimental results show that proposed criterion is very effective.References
A. Basit and M.Y. Javed, Optics and Lasers
in Engineering 45 (2007) 1107.
J. Kim, S. Cho and J. Choi, Journal of VLSI
Signal Processing 38 (2004) 147.
W. Boles and B. Boashash, IEEE Trans.
Signal Processing 46 (1998) 1185.
J. G. Daugman, Pattern Recognition 36
(2003) 279.
R. Wildes, Proceedings of the IEEE, 85
(1997) 1348.
J. Cui, Y. Wang, T. Tan, L. Ma and Z. Sun,
SPIE Defense and Security Symposium
(2004) 401.
L. Ma, Y. Wang and T. Tan, Iris recognition
based multi-channel Gabor filtering, The fifth
Asian Conference on Computer Vision
(2002) pp. 23-25.
X. Guang-Zhu, Z. Zai-feng and M. Yi-de, The
Journal of China universities of posts and
telecommunications 15 (2008) 96.
J. G. Daugman, IEEE Transactions on
Pattern Analysis and Machine Intelligence 5
(1993) 1148.
J. Canny, IEEE Transactions on Pattern
Analysis and Machine Intelligence PAMI-8
(1986) 679.
P.V.C. Hough, Method and means for
recognizing complex patterns, U.S. Patent 3
654 (1962).
H. Proenca and L. A. Alexandre, Ubiris: A
noisy iris image database, 13th International
Conference on Image Analysis and
Processing (2005) pp. 970-977.
L. Ma, T. Tan, Y. Wang and D. Zhang, IEEE
Trans. Pattern Analysis and Machine
Intelligence 25 (2003) 1519.
C. Tian, Q. Pan, Y. Cheng and Q. Gao, Fast
Algorithm and Application of Hough
Transform in Iris Segmentation, 3rd
International Conference on Machine
Learning and Cybernetics (2004) pp. 3977-
L. Masek and P. Kovesi, Biometric
Identification System Based on Iris Patterns,
The School of Computer Science and
Software Engineering: The University of
Western Australia (2003).
A. Rad, R. Safabakhsh, N. Qaragozlou and
M. Zaheri, Fast iris and pupil localization and
eyelid removal using gradient vector pairs
and certainty factors, Irish Machine Vision
and Image Processing Conference (2004)
pp. 82-91.
CASIA-Iris Image Database version 1.0,
Chinese Academy of Sciences, Institute of
Automation China,
http://www.sinobiometrics. com accessed
(2003).