A comparison of GEC-based feature selection and weighting for multimodal biometric recognition

Author

Alford, Aniesha ; Popplewell, Khary ; Dozier, Gerry ; Bryant, Kelvin ; Kelly, John ; Adams, Josh ; Abegaz, Tamirat ; Shelton, Joseph ; Ricanek, Karl ; Woodard, Damon L.

Author_Institution

Center for Adv. Studies in Identity Sci., North Carolina A & T State Univ., Greensboro, NC, USA

fYear

2011

fDate

5-8 June 2011

Firstpage

2725

Lastpage

2728

Abstract

In this paper, we compare the performance of a Steady-State Genetic Algorithm (SSGA) and an Estimation of Distribution Algorithm (EDA) for multi-biometric feature selection and weighting. Our results show that when fusing face and periocular modalities, SSGA-based feature weighting (GEFeW_SSGA) produces higher average recognition accuracies, while EDA-based feature selection (GEFeS_EDA) performs better at reducing the number of features needed for recognition.

Keywords

biometrics (access control); distributed algorithms; feature extraction; genetic algorithms; EDA; GEC; SSGA; estimation of distribution algorithm; feature selection; feature weighting; multimodal biometric recognition; steady-state genetic algorithm; Accuracy; Face; Face recognition; Feature extraction; Iris recognition; Probes; Eigenface; Estimation of Distribution Algorithm; Feature Selection; Feature Weighting; Local Binary Pattern; Steady-State Genetic Algorithm;

fLanguage

English

Publisher

ieee

Conference_Titel

Evolutionary Computation (CEC), 2011 IEEE Congress on

Conference_Location

New Orleans, LA

ISSN

Pending

Print_ISBN

978-1-4244-7834-7

Type

conf

DOI

10.1109/CEC.2011.5949959

Filename

5949959