Two dimensional Maximum Margin Criterion

  • Authors:

  • Quanquan Gu; Jie Zhou

  • Affiliations:

  • State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology(TNList), Department of Automation, Tsinghua Universi;State Key Laboratory on Intelligent Technology and Systems, Tsinghua National Laboratory for Information Science and Technology(TNList), Department of Automation, Tsinghua Universi

  • Venue:
  • ICASSP '09 Proceedings of the 2009 IEEE International Conference on Acoustics, Speech and Signal Processing
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Maximum Margin Criterion is a well-known method for feature extraction and dimensionality reduction. In this paper, we propose a novel feature extraction method, namely Two Dimensional Maximum Margin Criterion (2DMMC), specifically for matrix representation data, e.g. images. 2DMMC aims to find two orthogonal projection matrices to project the original matrices to a low dimensional matrix subspace, in which a sample is close to those in the same class but far from those in different classes. Both theoretical analysis and experiments on benchmark face recognition data sets illustrate that the proposed method is very effective and efficient.