A Method for the Identification of Noisy Regions in Normalized Iris Images

Author

Proença, Hugo ; Alexandre, Luís A.

Author_Institution

Dept. of Informatics, Univ. da Beira Interior, Covilha

Volume

4

fYear

0

fDate

0-0 0

Firstpage

405

Lastpage

408

Abstract

In this paper we propose a new method for the identification of noisy regions in normalized iris images. Starting from a normalized and dimensionless iris image in the polar coordinate system, our goal consists in the classification of every pixel as "noise" or "not noise". This classification could be helpful in the posterior feature extraction or feature comparison stages regarding the construction of biometric iris signatures more robust to noise. We propose the extraction of 8 well known features for each pixel of the images followed by the classification through a neural network

Keywords

biometrics (access control); eye; feature extraction; image classification; neural nets; biometric iris signatures; feature comparison; iris recognition; neural network; noisy image region identification; normalized iris images; pixel classification; polar coordinate system; posterior feature extraction; Biometrics; Eyelashes; Eyelids; Feature extraction; Focusing; Iris recognition; Neural networks; Optical reflection; Pixel; Working environment noise;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.100

Filename

1699864