L1-norm-based 2DPCA

Xuelong Li*, Yanwei Pang, Yuan Yuan

*Corresponding author for this work

Research output: Contribution to journalArticle

Abstract

In this paper, we first present a simple but effective L1-norm-based two-dimensional principal component analysis (2DPCA). Traditional L2-norm-based least squares criterion is sensitive to outliers, while the newly proposed L1-norm 2DPCA is robust. Experimental results demonstrate its advantages.

Original languageEnglish
Pages (from-to)1170-1175
Number of pages6
JournalIEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Volume40
Issue number4
Early online date15 Jan 2010
DOIs
Publication statusPublished - Aug 2010

Keywords

  • L1 norm
  • outlier
  • subspace
  • two-dimensional principal component analysis (2DPCA)

Fingerprint Dive into the research topics of 'L1-norm-based 2DPCA'. Together they form a unique fingerprint.

Cite this