1D-LDA vs. 2D-LDA: When is vector-based linear discriminant analysis better than matrix-based?

DOI10.1016/j.patcog.2007.11.025zbMath1138.68051MaRDI QIDQ2427343

Stan Z. Li, Wei-Shi Zheng, Jian Huang Lai

Publication date: 9 May 2008

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

Full work available at URL: https://doi.org/10.1016/j.patcog.2007.11.025

zbMATH Keywords

pattern recognition; Fisher's linear discriminant analysis; matrix-based representation; vector-based representation

Mathematics Subject Classification ID

68T10: Pattern recognition, speech recognition

Related Items

Classification With the Matrix-Variate-t Distribution, Block-wise 2D kernel PCA/LDA for face recognition, A two-dimensional neighborhood preserving projection for appearance-based face recognition, Perturbation LDA: Learning the difference between the class empirical mean and its expectation, Regularized generalized eigen-decomposition with applications to sparse supervised feature extraction and sparse discriminant analysis, Separable linear discriminant analysis, Feature extraction based on Laplacian bidirectional maximum margin criterion

Uses Software

• FastICA
• FERET
• CMU PIE

Cites Work

• Unnamed Item
• Independent component analysis, a new concept?
• Face representation using independent component analysis
• Regularized discriminant analysis and its application to face recognition
• Two-dimensional discriminant transform for face recognition
• From image vector to matrix: A straightforward image projection technique -- IMPCA vs. PCA
• Face recognition based on 2D Fisherface approach
• Face recognition using direct, weighted linear discriminant analysis and modular subspaces
• (2D)\(^{2}\)LDA: an efficient approach for face recognition
• An optimal transformation for discriminant and principal component analysis
• Learning the parts of objects by non-negative matrix factorization
• Generalized low rank approximations of matrices
• Face recognition based on the uncorrelated discriminant transformation
• A direct LDA algorithm for high-dimensional data -- with application to face recognition