A comparison of generalized linear discriminant analysis algorithms

7 Linear discriminant analysis (LDA) is a dimension reduction method which finds an optimal linear transformation that maximizes the class separability. However, in undersampled problems where the number of data samples is smaller than the dimension of data space, it is9 difficult to apply the LDA due to the singularity of scatter matrices caused by high dimensionality. In order to make the LDA applicable, several generalizations of the LDA have been proposed recently. In this paper, we present theoretical and algorithmic relationships among11 several generalized LDA algorithms and compare their computational complexities and performances in text classification and face recognition. Towards a practical dimension reduction method for high dimensional data, an efficient algorithm is proposed, which reduces the computational13 complexity greatly while achieving competitive prediction accuracies. We also present nonlinear extensions of these LDA algorithms based on kernel methods. It is s...

• Type: Journal
• Year: 2008
• Where: PR
• Authors: Cheong Hee Park, Haesun Park
• Keywords: Dimension Reduction Method, Generalized Eigenvalue Problem, Nonlinear Discriminant Analysis, PR 2008