Two New Methods for Locating Outer Edge of Iris - Advances in Image and Graphics Technologies - page 345

Two New Methods for Locating Outer Edge of Iris *

Yujie Liu and Hong Tian

Institute of Software of Dalian Jiaotong University, Dalian, China
[e-mail],
[e-mail]

Abstract. The two new methods for locating the outer edge of iris were pre-
sented by researching of iris images. The first is to locate the inner edge of iris
by using canny operator and Hough transform method. The selection of the ap-
propriate threshold is based on the diagram which observes the color distribu-
tion of the iris image; the second is that the circle integral and linear segment
methods to locate the outer edge of iris are presented. We would like to indicate
that the experiment results show that both of the two methods have the follow-
ing qualities: rapidity, availability, real time calculations and accuracy in locat-
ing the iris outer edge.

Keywords: I ris localization, circle integral and linear segment.

1 Introduction

With the growth of the economy and the development of the science and technology,
information security has become one of the most pertinent questions. Biometric cha-
racter identification technology has played a vital role fot the improvement of the
information security. In numerous biometric character identification technologies, iris
recognition technology has attracted a growing number of mathematicians and scien-
tists to explore since its special uniqueness, stability, detect-ability, security, which is
widely regarded as the most promising biometric technologies in 21st century [1].
Iris image segmentation is one of the most important steps in the process of the iris
recognition, and the iris localization is a very critical step for the iris image segmenta-
tion. The quality of the iris localization directly affects the iris recognition. Different
approaches have already been reported in the literature to locate the iris region. John
Daugma [2] in 1993 proposed the first efficient iris location method. He located the
iris boundaries using a relatively time-consuming differential operator. Wildes [3]
then used the gradient criterion and circular Hough transform to locate the iris which
votes the edge information in binary image and determines the iris edge parameters
according to the votes. Although both of the above methods can locate relatively sta-
ble iris edge, but both of them are time consuming and cannot be applied in real-time
system. Zhang Zaifeng [5] put forward a kind of method in 2009 which was based on
* The project is supported by National Natural Science Foundation of China (61074029) and Natural
Science Foundation of Liaoning Province (20102014).