Non-linear classification for iris patterns

Author

Sheela, S.V. ; Vijaya, P.A.

Author_Institution

B M S Coll. of Eng., Bangalore, India

fYear

2011

fDate

7-9 April 2011

Firstpage

1

Lastpage

5

Abstract

Biometric authentication based on iris patterns is used for personal identification. Important attributes to identity applications include accuracy, speed and template size. Iris patterns are segmented by considering the maximum area of the connected components in the binary images. The iris region is decomposed into subregions. Hu moments are applied to the minimum variance subregions (MVS). The summation of the moment values in these subregions is given as input to Support Vector Machine (SVM) and feed forward Neural Network (NN). The prominent results of False Rejection Rate (FRR) 2.5% and False Acceptance Rate (FAR) 0.0% was obtained for SVM. With NN classifier, prominent results of FRR 4.2% and FAR 0.0% are obtained.

Keywords

image classification; image segmentation; iris recognition; support vector machines; Hu moments; biometric authentication; false acceptance rate; false rejection rate; feed forward neural network; iris patterns; minimum variance subregions; nonlinear classification; support vector machine; Artificial neural networks; Databases; Ice; Iris recognition; Kernel; Polynomials; Support vector machines; Hu moments; Quadtree representation; Region splitting; minimum variance subregions;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia Computing and Systems (ICMCS), 2011 International Conference on

Conference_Location

Ouarzazate

ISSN

Pending

Print_ISBN

978-1-61284-730-6

Type

conf

DOI

10.1109/ICMCS.2011.5945674

Filename

5945674