Uncorrelated neighborhood preserving projections for face recognition

Authors:
Guoqiang Wang;Xiang Gao
Affiliations:
Department of Computer and Information Engineering, Luoyang Institute of Science and Technology, Luoyang, Henan P.R. China;Department of Computer and Information Engineering, Luoyang Institute of Science and Technology, Luoyang, Henan P.R. China
Venue:
AICI'11 Proceedings of the Third international conference on Artificial intelligence and computational intelligence - Volume Part III
Year:
2011

Citing 8
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Think globally, fit locally: unsupervised learning of low dimensional manifolds

The Journal of Machine Learning Research
Principal Manifolds and Nonlinear Dimensionality Reduction via Tangent Space Alignment

SIAM Journal on Scientific Computing
Face Recognition Using Laplacianfaces

IEEE Transactions on Pattern Analysis and Machine Intelligence
Graph Embedding and Extensions: A General Framework for Dimensionality Reduction

IEEE Transactions on Pattern Analysis and Machine Intelligence
Eigenfaces for recognition

Journal of Cognitive Neuroscience
Face recognition using neighborhood preserving projections

PCM'05 Proceedings of the 6th Pacific-Rim conference on Advances in Multimedia Information Processing - Volume Part II
Neighborhood preserving projections (NPP): a novel linear dimension reduction method

ICIC'05 Proceedings of the 2005 international conference on Advances in Intelligent Computing - Volume Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

Feature extraction is a crucial step for face recognition. In this paper, based on Neighborhood Preserving Projections (NPP), a novel feature extraction method called Uncorrelated Neighborhood Preserving Projections (UNPP) is proposed for face recognition. The improvement of UNPP method over NPP method benefits mostly from two aspects: One aspect is that UNPP preserves the within-class neighboring geometry by taking into account the class label information; the other aspect is that the extracted features via UNPP are statistically uncorrelated with minimum redundancy. Experimental results on the publicly available ORL face database show that the proposed UNPP approach provides a better representation of the data and achieves much higher recognition accuracy.