Palmprint recognition using Fisher´s linear discriminant

Author

Wu, Xiangqian ; Wang, Kuan-Quan ; Zhang, David

Author_Institution

Dept. of Comput. Sci. & Eng., Harbin Inst. of Technol., China

Volume

5

fYear

2003

fDate

2-5 Nov. 2003

Firstpage

3150

Abstract

In this paper, a novel method for palmprint recognition is proposed. In this method, each pixel of a palmprint image is considered as a coordinate in a high-dimensional image space. A linear projection based on Fisher´s linear discriminant (FLD) is used to project palmprints from this high-dimensional space to a significantly lower dimensional feature space, in which the ratio of the determinant of the between-class scatter to that of the within-class scatter is maximized. High accuracies of 99% and 99.2% have been obtained in one-to-one matching and one-to-300 matching test respectively and the speed of this method is rapid enough for real-time palmprint recognition.

Keywords

biometrics (access control); feature extraction; image recognition; FLD; biometrics; class scatter; feature extraction; fisher linear discriminant; high dimensional image space; linear projection; lower dimensional feature space; one-to-300 matching test; one-to-one matching test; palmprint image; real time palmprint recognition; Biometrics; Computer science; Costs; Feature extraction; Linear discriminant analysis; Matrix decomposition; Pixel; Scattering; Space technology; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2003 International Conference on

Print_ISBN

0-7803-8131-9

Type

conf

DOI

10.1109/ICMLC.2003.1260121

Filename

1260121