Bi-directional weighted modular B2DPCA for finger vein recognition

Author

Guan, Fengxu ; Wang, Kejun ; Wu, Qiuyu

Author_Institution

Coll. of Autom., Harbin Eng. Univ., Harbin, China

Volume

1

fYear

2010

fDate

16-18 Oct. 2010

Firstpage

93

Lastpage

97

Abstract

Due to the restriction of acquisition equipment and other reasons, the finger vein line appeared broken, torsion, translation and other deformation in local area. Therefore, the traditional methods got low recognition accuracy. In this paper, combining the advantages of modular method and bi-directional weighted B2DPCA with eigenvalue normalization; the bidirectional two-dimensional principal component analysis (B2DPCA) algorithm is improved. The bi-directional weighted modular B2DPCA (BWMB2DPCA) algorithm is proposed in order to extract the local feature of finger vein effective. The nearest neighbor classifier was used to distinguish different fingers. Experimental results show that whether in the little training samples, or in the multiple training samples, this method can obtain a better recognition effect than 2DPCA, B2DPCA, WB2DPCA and MB2DPCA.

Keywords

biometrics (access control); eigenvalues and eigenfunctions; feature extraction; image classification; image recognition; pattern classification; principal component analysis; bidirectional two-dimensional principal component analysis; bidirectional weighted modular B2DPCA; eigenvalue normalization; feature extraction; finger vein recognition; nearest neighbor classifier; Covariance matrix; Eigenvalues and eigenfunctions; Feature extraction; Fingers; Image recognition; Training; Veins; B2DPCA; bidirectional weighted modular B2DPCA; finger vein recognition; local feature;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Signal Processing (CISP), 2010 3rd International Congress on

Conference_Location

Yantai

Print_ISBN

978-1-4244-6513-2

Type

conf

DOI

10.1109/CISP.2010.5646294

Filename

5646294