L1-norm-based (2D)2PCA

DOI

10.2991/iccsee.2013.324How to use a DOI?

Keywords

bidirectional two-dimension principal component analysis, l2-norm, outliers, L1-norm, Optimization

Abstract

Traditional bidirectional two-dimension (2D) principal component analysis ((2D)2PCA-L2) is sensitive to outliers because its objective function is the least squares criterion based on L2-norm. This paper proposes a simple but effective L1-norm-based bidirectional 2D principal component analysis ((2D)2PCA-L1), which jointly takes advantage of the merits of bidirectional 2D subspace learning and L1-norm-based distance criterion. Experimental results on two popular face databases show that the proposed method is more robust to outliers than several methods based on principal component analysis in the fields of data compression and object recognition.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Fujin Zhong
PY  - 2013/03
DA  - 2013/03
TI  - L1-norm-based (2D)2PCA
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 1293
EP  - 1296
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.324
DO  - 10.2991/iccsee.2013.324
ID  - Zhong2013/03
ER  -