Robust linear dimensionality reduction

Authors:
Y. Koren;L. Carmel
Affiliations:
AT&T Labs, Florham Park, NJ, USA;-
Venue:
IEEE Transactions on Visualization and Computer Graphics
Year:
2004

Citing 0
Cited 25

The theoretical analysis of GLRAM and its applications

Pattern Recognition
Globally Maximizing, Locally Minimizing: Unsupervised Discriminant Projection with Applications to Face and Palm Biometrics

IEEE Transactions on Pattern Analysis and Machine Intelligence
FreeViz-An intelligent multivariate visualization approach to explorative analysis of biomedical data

Journal of Biomedical Informatics
Uncorrelated multilinear principal component analysis through successive variance maximization

Proceedings of the 25th international conference on Machine learning
Supervised Principal Geodesic Analysis on Facial Surface Normals for Gender Classification

SSPR & SPR '08 Proceedings of the 2008 Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
A local time Fukunage-Koontz transformation for speech emotional recognition

ICAIT '08 Proceedings of the 2008 International Conference on Advanced Infocomm Technology
Development of a hybrid methodology for dimensionality reduction in Mahalanobis-Taguchi system using Mahalanobis distance and binary particle swarm optimization

Expert Systems with Applications: An International Journal
Uncorrelated multilinear discriminant analysis with regularization and aggregation for tensor object recognition

IEEE Transactions on Neural Networks
Drawing graphs by eigenvectors: theory and practice

Computers & Mathematics with Applications
Independent components extraction from image matrix

Pattern Recognition Letters
An Innovative Weighted 2DLDA Approach for Face Recognition

PCM '09 Proceedings of the 10th Pacific Rim Conference on Multimedia: Advances in Multimedia Information Processing
Face recognition using discriminant locality preserving projections

Image and Vision Computing
Uncorrelated multilinear principal component analysis for unsupervised multilinear subspace learning

IEEE Transactions on Neural Networks
Letters: Robust kernel discriminant analysis and its application to feature extraction and recognition

Neurocomputing
Temporally local maximum signal fraction analysis for artifact removal from biomedical signals

IEEE Transactions on Signal Processing
Dimensionality reduction techniques for blog visualization

Expert Systems with Applications: An International Journal
Distance metric learning by minimal distance maximization

Pattern Recognition
Blockwise projection matrix versus blockwise data on undersampled problems: Analysis, comparison and applications

Pattern Recognition
Gender discriminating models from facial surface normals

Pattern Recognition
An Innovative Weighted 2DLDA Approach for Face Recognition

Journal of Signal Processing Systems
An improvement on PCA algorithm for face recognition

ISNN'05 Proceedings of the Second international conference on Advances in Neural Networks - Volume Part I
Improvement on PCA and 2DPCA algorithms for face recognition

CIVR'05 Proceedings of the 4th international conference on Image and Video Retrieval
Selecting good views of high-dimensional data using class consistency

EuroVis'09 Proceedings of the 11th Eurographics / IEEE - VGTC conference on Visualization
Structural decomposition trees

EuroVis'11 Proceedings of the 13th Eurographics / IEEE - VGTC conference on Visualization
Graph drawing by classical multidimensional scaling: new perspectives

GD'12 Proceedings of the 20th international conference on Graph Drawing

Quantified Score

Hi-index	0.01

Visualization

Abstract

We present a novel family of data-driven linear transformations, aimed at finding low-dimensional embeddings of multivariate data, in a way that optimally preserves the structure of the data. The well-studied PCA and Fisher's LDA are shown to be special members in this family of transformations, and we demonstrate how to generalize these two methods such as to enhance their performance. Furthermore, our technique is the only one, to the best of our knowledge, that reflects in the resulting embedding both the data coordinates and pairwise relationships between the data elements. Even more so, when information on the clustering (labeling) decomposition of the data is known, this information can also be integrated in the linear transformation, resulting in embeddings that clearly show the separation between the clusters, as well as their internal structure. All of this makes our technique very flexible and powerful, and lets us cope with kinds of data that other techniques fail to describe properly.