Improved iris localization method for iris recognition

Sida Liang; Aijun Zeng; Liyuan Gu; Jingpei Hu; Huijie Huang

doi:10.1117/12.2501225

24 July 2018 Improved iris localization method for iris recognition

Sida Liang, Aijun Zeng, Liyuan Gu, Jingpei Hu, Huijie Huang

Author Affiliations +

Proceedings Volume 10827, Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018); 108271M (2018) https://doi.org/10.1117/12.2501225
Event: Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018), 2018, Shanghai, China

Abstract

Iris recognition technology has advantages of high security and high stability and can realize non-contact and living recognition. For iris recognition, iris localization is the first step. The localization precision is assurance of high recognition rate. The existing iris localization method has shortage of slow speed. In this paper, an improved iris region localization method is proposed. Firstly, the images are preprocessed with Gaussian blur algorithm. Then the center of the pupil is coarsely located by Gaussian template convolution operation. Finally, the center and the outer edge of the iris are precisely located based on the Integral-differential operation. In experiments, CASIA iris database is used to test the improved iris region localization method. The results show that the location time can be less than 200 ms and the location precision can reach 98. 82%. This method’s usefulness is verified and can promote the application of the iris recognition

Citation Download Citation

Sida Liang, Aijun Zeng, Liyuan Gu, Jingpei Hu, and Huijie Huang "Improved iris localization method for iris recognition", Proc. SPIE 10827, Sixth International Conference on Optical and Photonic Engineering (icOPEN 2018), 108271M (24 July 2018); https://doi.org/10.1117/12.2501225

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE