Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/32728
Title: Feature extraction based on Laplacian bidirectional maximum margin criterion
Authors: Yang, W
Wang, J
Ren, M
Yang, J
Zhang, L 
Liu, G
Keywords: Bidirectional
Face recognition
Feature extraction
Laplacian
MMC
Issue Date: 2009
Publisher: Elsevier
Source: Pattern recognition, 2009, v. 42, no. 11, p. 2327-2334 How to cite?
Journal: Pattern recognition 
Abstract: Maximum margin criterion (MMC) based feature extraction is more efficient than linear discriminant analysis (LDA) for calculating the discriminant vectors since it does not need to calculate the inverse within-class scatter matrix. However, MMC ignores the discriminative information within the local structures of samples and the structural information embedding in the images. In this paper, we develop a novel criterion, namely Laplacian bidirectional maximum margin criterion (LBMMC), to address the issue. We formulate the image total Laplacian matrix, image within-class Laplacian matrix and image between-class Laplacian matrix using the sample similar weight that is widely used in machine learning. The proposed LBMMC based feature extraction computes the discriminant vectors by maximizing the difference between image between-class Laplacian matrix and image within-class Laplacian matrix in both row and column directions. Experiments on the FERET and Yale face databases show the effectiveness of the proposed LBMMC based feature extraction method.
URI: http://hdl.handle.net/10397/32728
ISSN: 0031-3203
EISSN: 1873-5142
DOI: 10.1016/j.patcog.2009.03.017
Appears in Collections:Journal/Magazine Article

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

65
Last Week
0
Last month
0
Citations as of Aug 9, 2018

WEB OF SCIENCETM
Citations

53
Last Week
0
Last month
3
Citations as of Aug 16, 2018

Page view(s)

63
Last Week
0
Last month
Citations as of Aug 20, 2018

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.