Home // ICCGI 2012, The Seventh International Multi-Conference on Computing in the Global Information Technology // View article

An Implementation of Discriminative Common Vector Approach Using Matrices

Authors:
Mehmet Koc
Atalay Barkana

Keywords: one sample problem; common vector; DCVA; two dimensional FLDA

Abstract:
If one sample per class is available in a face recognition problem, vector-based methods which use within-class scatter will fail. The reason for that is the zero within-class matrix. In this paper a two dimensional extension of the discriminative common vector approach (2D-DCVA) is proposed. The performance of the proposed method is compared with discriminative common vector approach (1D-DCVA) and two dimensional Fisher linear discriminant analysis (2D-FLDA) in ORL, FERET, YALE, and UMIST face databases in one sample problem. Our proposed method outperforms 1D-DCVA and 2D-FLDA in all databases.

Pages: 260 to 263

Copyright: Copyright (c) IARIA, 2012

Publication date: June 24, 2012

Published in: conference

ISSN: 2308-4529

ISBN: 978-1-61208-202-8

Location: Venice, Italy

Dates: from June 24, 2012 to June 29, 2012