Variational level set method and game theory applied for nonideal iris recognition

Kaushik Roy; Prabir Bhattacharya

doi:10.1109/ICIP.2009.5414156

Variational level set method and game theory applied for nonideal iris recognition

Kaushik Roy
, Prabir Bhattacharya

Computer Science

CIISE, Concordia University

Research output: Contribution to journal › Conference article › peer-review

5 Scopus citations

Abstract

We present an efficient algorithm for iris recognition using the variational level set approach and the coalitional game theory. To segment a nonideal iris image accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Daubechies Wavelet Transform (DBWT) is used to extract the textural features, and an iterative algorithm, called the Contribution-Selection Algorithm (CSA), in the context of coalitional game theory is used to select a subset of informative features without compromising the recognition rate. The verification performance of the proposed scheme is validated using the UBIRIS Version 2, the ICE 2005, and the WVU datasets. ©2009 IEEE.

Original language	English
Article number	5414156
Pages (from-to)	2721-2724
Number of pages	4
Journal	Proceedings - International Conference on Image Processing, ICIP
DOIs	https://doi.org/10.1109/ICIP.2009.5414156
State	Published - Jan 1 2009
Event	2009 IEEE International Conference on Image Processing, ICIP 2009 - Cairo, Egypt Duration: Nov 7 2009 → Nov 10 2009

Keywords

Coalitional game theory
Contribution selection algorithm
Iris recognition
Variational level set evolution

Access to Document

10.1109/ICIP.2009.5414156

Cite this

@article{c571937760c948fd897fb0d13cd979c5,

title = "Variational level set method and game theory applied for nonideal iris recognition",

abstract = "We present an efficient algorithm for iris recognition using the variational level set approach and the coalitional game theory. To segment a nonideal iris image accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Daubechies Wavelet Transform (DBWT) is used to extract the textural features, and an iterative algorithm, called the Contribution-Selection Algorithm (CSA), in the context of coalitional game theory is used to select a subset of informative features without compromising the recognition rate. The verification performance of the proposed scheme is validated using the UBIRIS Version 2, the ICE 2005, and the WVU datasets. {\textcopyright}2009 IEEE.",

keywords = "Coalitional game theory, Contribution selection algorithm, Iris recognition, Variational level set evolution",

author = "Kaushik Roy and Prabir Bhattacharya",

year = "2009",

month = jan,

day = "1",

doi = "10.1109/ICIP.2009.5414156",

language = "English",

pages = "2721--2724",

journal = "Proceedings - International Conference on Image Processing, ICIP",

issn = "1522-4880",

publisher = "IEEE Computer Society",

note = "2009 IEEE International Conference on Image Processing, ICIP 2009 ; Conference date: 07-11-2009 Through 10-11-2009",

}

TY - JOUR

T1 - Variational level set method and game theory applied for nonideal iris recognition

AU - Roy, Kaushik

AU - Bhattacharya, Prabir

PY - 2009/1/1

Y1 - 2009/1/1

N2 - We present an efficient algorithm for iris recognition using the variational level set approach and the coalitional game theory. To segment a nonideal iris image accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Daubechies Wavelet Transform (DBWT) is used to extract the textural features, and an iterative algorithm, called the Contribution-Selection Algorithm (CSA), in the context of coalitional game theory is used to select a subset of informative features without compromising the recognition rate. The verification performance of the proposed scheme is validated using the UBIRIS Version 2, the ICE 2005, and the WVU datasets. ©2009 IEEE.

AB - We present an efficient algorithm for iris recognition using the variational level set approach and the coalitional game theory. To segment a nonideal iris image accurately, we deploy a variational level set based curve evolution scheme, which uses significantly larger time step for numerically solving the evolution partial differential equation (PDE), and therefore, speeds up the curve evolution process drastically. Daubechies Wavelet Transform (DBWT) is used to extract the textural features, and an iterative algorithm, called the Contribution-Selection Algorithm (CSA), in the context of coalitional game theory is used to select a subset of informative features without compromising the recognition rate. The verification performance of the proposed scheme is validated using the UBIRIS Version 2, the ICE 2005, and the WVU datasets. ©2009 IEEE.

KW - Coalitional game theory

KW - Contribution selection algorithm

KW - Iris recognition

KW - Variational level set evolution

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=77951942176&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=77951942176&origin=inward

U2 - 10.1109/ICIP.2009.5414156

DO - 10.1109/ICIP.2009.5414156

M3 - Conference article

SN - 1522-4880

SP - 2721

EP - 2724

JO - Proceedings - International Conference on Image Processing, ICIP

JF - Proceedings - International Conference on Image Processing, ICIP

M1 - 5414156

T2 - 2009 IEEE International Conference on Image Processing, ICIP 2009

Y2 - 7 November 2009 through 10 November 2009

ER -

Variational level set method and game theory applied for nonideal iris recognition

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this