Title
An alternative formulation of kernel LPP with application to image recognition
Abstract
Locality preserving projections (LPP) is a new subspace feature extraction method which seeks to preserve the local structure and intrinsic geometry of the data space. As the LPP model is linear, it may fail to extract the nonlinear features. This paper proposes to address this problem using an alternative formulation, kernel locality preserving projections (KLPP). Our algorithm consists of two steps: kernel principal component analysis (KPCA) plus LPP. We provide an outline for implementing KLPP. Experiments on the ORL face database and PolyU palmprint database demonstrate the effectiveness of the proposed algorithm.
Year
DOI
Venue
2006
10.1016/j.neucom.2006.01.006
Neurocomputing
Keywords
DocType
Volume
Kernel principal component analysis (KPCA),Locality preserving projections (LPP),Kernel LPP (KLPP),Image recognition
Journal
69
Issue
ISSN
Citations 
13
0925-2312
6
PageRank 
References 
Authors
0.52
0
4
Name
Order
Citations
PageRank
Guiyu Feng11749.92
Dewen Hu21290101.20
David Zhang37365360.85
Zongtan Zhou441233.89