Iris localisation using Fuzzy Centre Detection (FCD) scheme and active contour snake

Mat Ibrahim, Masrullizam and Soraghan , John and Abd Manap, Nurulfajar (2014) Iris localisation using Fuzzy Centre Detection (FCD) scheme and active contour snake. Jurnal Teknologi (Sciences and Engineering), 69 (6). pp. 73-77. ISSN e-ISSN 2180 – 3722

[img]
Preview
PDF
Iris_Localisation_Using_Fuzzy_Centre_Detection_(FCD)_Scheme_and_Active_Contour_Snake.pdf

Download (1MB)

Abstract

Iris localisation is a crucial operation in iris recognition algorithm and also in applications, where irises are the main target object. This paper presents a new method to localise iris by using Fuzzy Centre Detection (FCD) scheme and active contour Snake. FCD scheme which consists of four fuzzy membership functions is purposely designed to find a centre of the iris. By using the centre of iris as the reference point, an active contour Snake algorithm is employed to localise the inner and outer of iris boundary. This proposed method is tested and validated with two categories of image database; iris databases and face database. For iris database, UBIRIS.v1, UBIRIS.v2, CASIA.v1, CASIA.v2, MMU1 and MMU2 are used. Whilst for face databases, MUCT, AT&T, Georgia Tech and ZJUblink databases are chosen to evaluate the capability of proposed method to deal with the small size of the iris in the image database. Based on the experimental result, the proposed method shows promising results for both types of databases, including comparison with the some existing iris localisation algorithm.

Item Type: Article
Uncontrolled Keywords: Iris localization, fuzzy scheme, active conyour, snake algorithm
Subjects: T Technology > T Technology (General)
Divisions: Faculty of Electronics and Computer Engineering > Department of Computer Engineering
Depositing User: Dr. Masrullizam Mat Ibrahim
Date Deposited: 22 Jan 2015 00:54
Last Modified: 28 May 2015 04:35
URI: http://eprints.utem.edu.my/id/eprint/14027
Statistic Details: View Download Statistic

Actions (login required)

View Item View Item