Some Refinement on Iris Localization Algorithm

Full Text PDF PDF
Author(s) Abikoye O.C. | Omolehin J.O. | Sadiku J.S.
Pages 1835-1841
Volume 2
Issue 11
Date November, 2012
Keywords Biometrics, Iris recognition, Iris localization, Geometry, Inner and Outer boundaries

Abstract

Biometrics recognition is a common and reliable way to authenticate the identity of a living person based on physiological or behavioral characteristics. Iris recognition is one of the newer biometric recognition technologies used for personal identification. It is reliable and widely used. In general a typical iris recognition system consists of three basic module which include image acquisition, Iris Localization & pre-processing, Iris texture extraction & signature encoding and lastly Iris signature matching for recognition or verification. One of the most important steps in iris recognition systems is iris localization, which is related to the detection of the exact location and contour of the iris in an image. (i.e it defines the inner and outer boundaries of iris region) Obviously, the performance of the identification system is closely related to the precision of the iris localization step. In this study, an efficient algorithm for iris localization is proposed. The algorithm proposed can accurately define both the inner and outer boundaries of the iris irrespective of the geometry it may be (circle or eclipse) by capturing the parameters that represents the geometry.

< Back to November Issue