GitHub - yuzhounh/G2DPCA_demo_1: Scripts for the paper: Generalized 2-D principal component analysis by Lp-norm for image analysis.

yuzhounh / G2DPCA_demo_1 Public

Notifications You must be signed in to change notification settings
Fork 1
Star 1

Scripts for the paper: Generalized 2-D principal component analysis by Lp-norm for image analysis.

ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=7087369

GPL-3.0 license

1 star 1 fork Branches Tags Activity

Star

Notifications

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 9 Commits
data		data
G2DPCA.m		G2DPCA.m
GPCA.m		GPCA.m
LICENSE		LICENSE
PCA2DL1S.m		PCA2DL1S.m
RSPCA.m		RSPCA.m
Readme		Readme
classify_G2DPCA.m		classify_G2DPCA.m
classify_GPCA.m		classify_GPCA.m
classify_PCA2DL1S.m		classify_PCA2DL1S.m
classify_RSPCA.m		classify_RSPCA.m
m1_add_noise.m		m1_add_noise.m
m1_prepare.m		m1_prepare.m
m2_classify.m		m2_classify.m
m2_reco.m		m2_reco.m
m3_classify_plot.m		m3_classify_plot.m
m3_reco_plot.m		m3_reco_plot.m
m3_reco_plot.png		m3_reco_plot.png
main.m		main.m
manuscript.pdf		manuscript.pdf
para_worker.m		para_worker.m
perct.m		perct.m
pnorm.m		pnorm.m
reco_G2DPCA.m		reco_G2DPCA.m
reco_GPCA.m		reco_GPCA.m
reco_PCA2DL1S.m		reco_PCA2DL1S.m
reco_RSPCA.m		reco_RSPCA.m

Repository files navigation

Generalized two dimensional principal component analysis by Lp-norm for image analysis. 
Copyright (C) 2018 Jing Wang

For 1D algorithms, the image data should be 2D matrix, nSub*(height*width). 
For 2D algorithms, the image data should be 3D matrix, height*width*nSub. 
The images are listed in the subject-by-subject manner. Please refer to the 
manuscript for more information about the experiments.

Variables:
FaceDB, Feret or ORL
x,   image data
rho, a tuning parameter in RSPCA or 2DPCAL1-S
s,   a tuning parameter in GPCA or G2DPCA
p,   a tuning parameter in GPCA or G2DPCA
nPV, number of projection vectors to be calculated
W,   projection vectors

Usage:
Run main.m to play this demo. It takes about 23 hours on a server with 40 CPUs.

Related codes:
2DPCAL1-S, https://github.com/yuzhounh/2DPCAL1-S
G2DPCA, https://github.com/yuzhounh/G2DPCA
G2DPCA_demo_1, https://github.com/yuzhounh/G2DPCA_demo_1
G2DPCA_demo_2, https://github.com/yuzhounh/G2DPCA_demo_2

Contact information:
Jing Wang
wangjing0@seu.edu.cn
yuzhounh@163.com

2018-6-13 22:58:14