Performance evaluation of Independent Component Analysis in an iris recognition system

Author

Bouraoui, Imen ; Chitroub, Salim ; Bouridane, Ahmed

Author_Institution

Signal & Image Process. Lab., USTHB, Algiers, Algeria

fYear

2010

fDate

16-19 May 2010

Firstpage

1

Lastpage

7

Abstract

The overall performance of any iris recognition system relies on the performance of its components, which are preprocessing, feature extraction and matching. Feature extraction is the important step of such recognition system, but it is strongly dependent on the pre-processing step that is consisting of localising and normalising the iris. In this paper, Independent Component Analysis (ICA), which is a recently developed statistical method for data analysis, is applied for extracting the features for iris region of interest that are statistically independent. Based on some mathematical criteria, the performance of ICA is evaluated by using two different subsets of CASIA-V3 iris image database. The obtained results are convincing and some future improved research works are subsequently envisaged.

Keywords

data analysis; feature extraction; image matching; independent component analysis; iris recognition; performance evaluation; statistical analysis; CASIA-V3 iris image database; data analysis; feature extraction; feature matching; independent component analysis; iris recognition system; performance evaluation; statistical method; Entropy; Feature extraction; Iris; Iris recognition; Random variables; Transforms; Vectors; Biometrics; Feature extraction; ICA; Image pre-processing; Iris recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Systems and Applications (AICCSA), 2010 IEEE/ACS International Conference on

Conference_Location

Hammamet

Print_ISBN

978-1-4244-7716-6

Type

conf

DOI

10.1109/AICCSA.2010.5586977

Filename

5586977