A convergent solution to two dimensional linear discriminant analysis

Author

Chen, Wei ; Huang, Kaiqi ; Tan, Tieniu ; Tao, Dacheng

Author_Institution

Nat. Lab. of Pattern Recognition, CAS, Beijing, China

fYear

2009

fDate

7-10 Nov. 2009

Firstpage

4133

Lastpage

4136

Abstract

The matrix based data representation has been recognized to be effective for face recognition because it can deal with the undersampled problem. One of the most popular algorithms, the two dimensional linear discriminant analysis (2DLDA), has been identified to be effective to encode the discriminative information for training matrix represented samples. However, 2DLDA does not converge in the training stage. This paper presents an evolutionary computation based solution, referred to as E-2DLDA, to provide a convergent training stage for 2DLDA. In E-2DLDA, every randomly generated candidate projection matrices are first normalized. The evolutionary computation method optimizes the projection matrices to best separate different classes. Experimental results show E-2DLDA is convergent and outperforms 2DLDA.

Keywords

convergence; data structures; evolutionary computation; face recognition; learning (artificial intelligence); matrix algebra; 2DLDA; evolutionary computation based solution; face recognition; matrix based data representation; matrix represented sample training; randomly generated candidate projection matrices; two dimensional linear discriminant analysis; Automation; Content addressable storage; Error analysis; Evolutionary computation; Face recognition; Laboratories; Linear discriminant analysis; Optimization methods; Pattern recognition; Tensile stress; 2DLDA; Evolutionary computation; convergence; subspace learning;

fLanguage

English

Publisher

ieee

Conference_Titel

Image Processing (ICIP), 2009 16th IEEE International Conference on

Conference_Location

Cairo

ISSN

1522-4880

Print_ISBN

978-1-4244-5653-6

Electronic_ISBN

1522-4880

Type

conf

DOI

10.1109/ICIP.2009.5413462

Filename

5413462