Multiclass Linear Dimension Reduction by Weighted Pairwise Fisher Criteria

Abstract

ÐWe derive a class of computationally inexpensive linear dimension reduction criteria by introducing a weighted variant of the well-known K-class Fisher criterion associated with linear discriminant analysis (LDA). It can be seen that LDA weights contributions of individual class pairs according to the Euclidian distance of the respective class means. We generalize upon LDA by introducing a different weighting function. Index TermsÐLinear dimension reduction, Fisher criterion, linear discriminant analysis, Bayes error, approximate pairwise accuracy criterion.

DOI: 10.1109/34.935849

Extracted Key Phrases

2 Figures and Tables

0204060'02'04'06'08'10'12'14'16
Citations per Year

481 Citations

Semantic Scholar estimates that this publication has 481 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Loog2001MulticlassLD, title={Multiclass Linear Dimension Reduction by Weighted Pairwise Fisher Criteria}, author={Marco Loog and Robert P. W. Duin and Reinhold H{\"a}b-Umbach}, journal={IEEE Trans. Pattern Anal. Mach. Intell.}, year={2001}, volume={23}, pages={762-766} }