Multi-class pairwise linear dimensionality reduction using heteroscedastic schemes

DOI10.1016/j.patcog.2010.01.018zbMath1214.68327OpenAlexW2069760243WikidataQ60327856 ScholiaQ60327856MaRDI QIDQ969086

Claudio Henríquez, B. John Oommen, Luis G. Rueda

Publication date: 11 May 2010

Published in: Pattern Recognition (Search for Journal in Brave)

Full work available at URL: http://hdl.handle.net/11250/137854

zbMATH Keywords

linear dimensionality reductionFisher's discriminant analysisChernoff-based dimensionality reductionheteroscedastic discriminant analysispairwise multi-class classification

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10)

Related Items

Heteroscedastic linear feature extraction based on sufficiency conditions

Uses Software

• UCI-ml
• KPCA plus LDA

Cites Work

• Unnamed Item
• Unnamed Item
• Linear dimensionality reduction by maximizing the Chernoff distance in the transformed space
• Data dimensionality estimation methods: A survey.
• A reformative kernel Fisher discriminant analysis
• An efficient approach to compute the threshold for multi-dimensional linear classifiers
• A direct LDA algorithm for high-dimensional data -- with application to face recognition