A novel approach for iris segmentation and normalization

Author

Shamsi, Mahboubeh ; Rasouli, Abdolreza

Author_Institution

Fac. of Comput. Sci. & Inf. Syst., Islamic Azad Univ., Bardsir, Iran

fYear

2009

fDate

4-6 Aug. 2009

Firstpage

557

Lastpage

562

Abstract

Iris is a desirable biometric representation of an individual for security-related applications. However the iris segmentation and normalization process is challenging due to the presence of eye lashes that occlude the iris, the dilation of pupils due to different light illumination and several other uncontrolled factors. In this work, we enhanced Daugman method to locate the iris and normalized it from Polar to Cartesian coordinate. The algorithm is tested using iris images from CASIA database and MMU database. The percentage detection on MMU iris database is 99% and that of CASIS is 98%. Our approach is feasible to produce an iris template for identity identification and biometric watermarking application.

Keywords

biometrics (access control); image recognition; image segmentation; watermarking; Cartesian coordinate; Daugman method; biometric watermarking; eye lash; identity identification; iris normalization; iris segmentation; iris template; light illumination; Biometrics; Eyelids; Genetics; Humans; Image databases; Iris; Lenses; Muscles; Pigmentation; Waveguide discontinuities; automatic segmentation; biometric identification; iris recognition; recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Applications of Digital Information and Web Technologies, 2009. ICADIWT '09. Second International Conference on the

Conference_Location

London

Print_ISBN

978-1-4244-4456-4

Electronic_ISBN

978-1-4244-4457-1

Type

conf

DOI

10.1109/ICADIWT.2009.5273923

Filename

5273923