Face recognition using 2DLDA algorithm

Kongsontana, Sittinon; Rangsanseri, Yuttapong

doi:10.1109/ISSPA.2005.1581028

Face recognition using 2DLDA algorithm

Author(s)

Kongsontana, Sittinon

Rangsanseri, Yuttapong

Date Issued

December 1, 2005

Type

Conference Paper

DOI

10.1109/ISSPA.2005.1581028

Abstract

This paper proposes Two-Dimensional Linear Discriminant Analysis (2DLDA) for feature extraction which used for face recognition application. This method is developed from Fisher Linear Discrimnant (FLD) and Two-Dimensional Principle Component Analysis (2DPCA). In this method, 2DLDA directly uses the image matrix to calculate the between-class scatter matrix and within-class scatter matrix. Moreover, 2DLDA will be handling the problem that the within-class scatter matrix maybe singular. The experimental results indicated that the 2DLDA method is more computationally efficient than conventional methods. © 2005 IEEE.

Citation

Proceedings 8th International Symposium on Signal Processing and Its Applications Isspa 2005, 2, 675-678, 2005