Paper Info
Title
Informative Laplacian Projection
Abstract
A new approach of constructing the similarity matrix for eigendecomposition on graph Laplacians is proposed. We first connect the Locality Preserving Projection method to probability density derivatives, which are then replaced by informative score vectors. This change yields a normalization factor and increases the contribution of the data pairs in low-density regions. The proposed method can be applied to both unsupervised and supervised learning. Empirical study on facial images is provided. The experiment results demonstrate that our method is advantageous for discovering statistical patterns in sparse data areas.
Year
DOI
Venue
2009
10.1007/978-3-642-02230-2_37
Scandinavian Conference on Image Analysis
Keywords
Field
DocType
informative score vector,locality preserving projection method,graph laplacians,informative laplacian projection,sparse data area,experiment result,facial image,change yield,data pair,empirical study,supervised learning,probability density,sparse data,graph laplacian
Facial recognition system,Normalization (statistics),Pattern recognition,Computer science,Projection method,Supervised learning,Artificial intelligence,Eigendecomposition of a matrix,Linear discriminant analysis,Nonlinear dimensionality reduction,Sparse matrix
Conference
Volume
ISSN
Citations 
5575
0302-9743
0
PageRank 
References 
Authors
0.34
9
2
Name
Order
Citations
PageRank
Zhirong Yang128917.27
Jorma Laaksonen21162176.93