The maximized discriminative subspace for manifold learning problem

Authors:
Yuting Tao;Jian Yang
Affiliations:
Nanjing University of Science and Technology, Nanjing, China;Nanjing University of Science and Technology, Nanjing, China
Venue:
IScIDE'12 Proceedings of the third Sino-foreign-interchange conference on Intelligent Science and Intelligent Data Engineering
Year:
2012

Citing 8
Cited 0

PCA versus LDA

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convex Optimization

Convex Optimization
Face Recognition Using Laplacianfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Local Discriminant Embedding and Its Variants

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Down-Sampling Face Images and Low-Resolution Face Recognition

ICICIC '08 Proceedings of the 2008 3rd International Conference on Innovative Computing Information and Control
LPP solution schemes for use with face recognition

Pattern Recognition
A Multiple Maximum Scatter Difference Discriminant Criterion for Facial Feature Extraction

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Quantified Score

Hi-index	0.00

Visualization

Abstract

Manifold learning problem, aims to seek some directions, which can keep the local structure and neighborhood of each sample as much as possible. In the conventional manifold learning approaches, feature extraction is performed in the original data space. In this paper, a new method called "the maximized discriminant subspace algorithm" (MDS) is implemented before feature extraction and classification. Extensive experiments show the better classification results than the conventional manifold approaches, due to projecting the original data onto the maximized discriminant subspace in a preliminary phase before feature extraction and classification in the transformed data space.