An improved 2DPCA algorithm for face recognition

Author

Gan, Jun-Ying ; He, Si-Bin

Author_Institution

Sch. of Inf., Wu Yi Univ., Jiangmen, China

Volume

4

fYear

2009

fDate

12-15 July 2009

Firstpage

2380

Lastpage

2384

Abstract

On the basis of two dimensional principal component analysis, an improved two dimensional principal component analysis (I2DPCA) is presented for face recognition. Firstly, the criterion functions of global and between class scatters of projection features are defined. Secondly, the two defined criterion functions are fused by way of multiplication or addition. Therefore, the criterion function of I2DPCA is produced, and the optimal projection axis vector of I2DPCA algorithm is the vector which maximizes its criterion function. Experimental results show that, the correct recognition rate of I2DPCA is higher than that of 2DPCA. In I2DPCA algorithm, the correct recognition rate fused by way of addition is higher than that by way of multiplication.

Keywords

face recognition; feature extraction; principal component analysis; face recognition; optimal projection axis vector; principal component analysis; projection features; two dimensional analysis; Cybernetics; Face recognition; Feature extraction; Gallium nitride; Helium; Machine learning; Machine learning algorithms; Pattern recognition; Principal component analysis; Scattering; Between-class Scatter; Global Scatter; Improved 2DPCA (I2DPCA); Two-dimensional Principal Component Analysis (2DPCA);

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Learning and Cybernetics, 2009 International Conference on

Conference_Location

Baoding

Print_ISBN

978-1-4244-3702-3

Electronic_ISBN

978-1-4244-3703-0

Type

conf

DOI

10.1109/ICMLC.2009.5212240

Filename

5212240