📄 show_denoising.html
字号:
<html><head> <meta HTTP-EQUIV="Content-Type" CONTENT="text/html;charset=ISO-8859-1"> <title>show_denoising.m</title><link rel="stylesheet" type="text/css" href="../../../m-syntax.css"></head><body><code><span class=h1>% SHOW_DENOISING Image denosing of USPS hand-written numerals.</span><br><span class=help>%</span><br><span class=help>% <span class=help_field>Description:</span></span><br><span class=help>% The input noisy images are denoised using the </span><br><span class=help>% kernel PCA model. The denosing based on linear PCA</span><br><span class=help>% is also computed for comparision. Imgase of</span><br><span class=help>% - Ground truth numerlas</span><br><span class=help>% - Noisy numerals</span><br><span class=help>% - Numerals denoised by kernel PCA</span><br><span class=help>% - Numerals denoised by linear PCA</span><br><span class=help>% are displayed.</span><br><span class=help>%</span><br><span class=help>% See also</span><br><span class=help>% KPCAREC, PCAREC.</span><br><span class=help>%</span><br><hr><span class=help1>% <span class=help1_field>About:</span> Statistical Pattern Recognition Toolbox</span><br><span class=help1>% (C) 1999-2003, Written by Vojtech Franc and Vaclav Hlavac</span><br><span class=help1>% <a href="http://www.cvut.cz">Czech Technical University Prague</a></span><br><span class=help1>% <a href="http://www.feld.cvut.cz">Faculty of Electrical Engineering</a></span><br><span class=help1>% <a href="http://cmp.felk.cvut.cz">Center for Machine Perception</a></span><br><br><span class=help1>% <span class=help1_field>Modification:</span></span><br><span class=help1>% 07-jun-2004, VF</span><br><span class=help1>% 05-may-2004, VF</span><br><span class=help1>% 22-apr-2004, VF</span><br><br><hr>help show_denoising;<br><br><span class=comment>% setting </span><br><span class=comment>%-------------------------------------------------------</span><br>kpca_filename = <span class=quotes>'USPSModelGreedyKPCA.mat'</span>; <span class=comment>% kpca model</span><br>lpca_filename = <span class=quotes>'USPSModelLinPCA.mat'</span>; <span class=comment>% linear PCA model</span><br><br><span class=comment>% USPS databes with noisy images (see help make_noisy_usps).</span><br>input_data_file = <span class=quotes>'/home.dokt/xfrancv/data/usps/usps_noisy'</span>;<br><br><span class=comment>% loading</span><br><span class=comment>%----------------------------------------</span><br>load(kpca_filename,<span class=quotes>'kpca_model'</span>);<br>load(lpca_filename,<span class=quotes>'lpca_model'</span>);<br>load(input_data_file,<span class=quotes>'tst'</span>);<br><br><span class=comment>% get indices of examples to be denoised</span><br><span class=comment>% ---------------------------------------</span><br>inx = [];<br><span class=keyword>for</span> i=1:10,<br> tmp = find(tst.y == i);<br> inx = [inx, tmp(1) ];<br><span class=keyword>end</span><br><br><span class=comment>% get noisy and ground truth numerals</span><br><span class=comment>%----------------------------------------</span><br>noisy_X = tst.X(:,inx); <br>gnd_X = tst.gnd_X(:,inx);<br><br><span class=comment>% Kernel PCA and linear PCA denoising</span><br><span class=comment>%----------------------------------------</span><br>kpca_X = kpcarec( noisy_X, kpca_model);<br>lpca_X = pcarec( noisy_X, lpca_model);<br><br><span class=comment>% display results</span><br><span class=comment>%----------------------------------------</span><br>h=<span class=graph>figure</span>; <span class=graph>set</span>(h,<span class=quotes>'name'</span>,<span class=quotes>'Denoised by greedy KPCA'</span>);<br>showim( kpca_X);<br><br>h=<span class=graph>figure</span>; <span class=graph>set</span>(h,<span class=quotes>'name'</span>,<span class=quotes>'Denoised by linear PCA'</span>);<br>showim( lpca_X);<br><br>h=<span class=graph>figure</span>; <span class=graph>set</span>(h,<span class=quotes>'name'</span>,<span class=quotes>'Ground truth'</span>);<br>showim( gnd_X);<br><br>h=<span class=graph>figure</span>; <span class=graph>set</span>(h,<span class=quotes>'name'</span>,<span class=quotes>'Noisy'</span>);<br>showim( noisy_X);<br><br><span class=comment>%EOF</span><br></code>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -