Convert matlab image svd method to opencv - opencv

Question

I want to write a program with opencv by c++ in the visual studio.
My code is following matlab code:
close all
clear all
clc
%reading and converting the image
inImage=imread('pic.jpg');
inImageD=double(inImage);
[U,S,V]=svd(inImageD);
% Using different number of singular values (diagonal of S) to compress and
% reconstruct the image
dispEr = [];
numSVals = [];
for N=5:25:300
% store the singular values in a temporary var
C = S;
% discard the diagonal values not required for compression
C(N+1:end,:)=0;
C(:,N+1:end)=0;
% Construct an Image using the selected singular values
D=U*C*V';
% display and compute error
figure;
buffer = sprintf('Image output using %d singular values', N)
imshow(uint8(D));
title(buffer);
error=sum(sum((inImageD-D).^2));
% store vals for display
dispEr = [dispEr; error];
numSVals = [numSVals; N];
end
What's your opinion to do this? I want to save image in a text file and retrieve it from file into the Mat array. I've written this part as follow:
Mat image;
FileStorage read_file("pic_file.txt", FileStorage::READ);
read_file["pic"] >> image;
read_file.release();
Mat P;
image.convertTo(P, CV_32FC3,1.0/255);
SVD svda(P); //or SVD::compute(P,W,U,V);
But I have problem with SVD function and it doesn't work. Is there anything to do for computing SVD compression of an image?
Thank You so much.
Vahids.

Answer 1

Here is my code:
int main(int argc, char* argv[])
{
// Image matrix
Mat img;
Mat result;
//---------------------------------------------
//
//---------------------------------------------
namedWindow("Source Image");
namedWindow("Result");
// Load image in grayscale mode
img=imread("D:\\ImagesForTest\\cat.bmp",0);
img.convertTo(img,CV_32FC1,1.0/255.0);
cout << "Source size:" << img.rows*img.cols <<" elements "<< endl;
// create SVD
cv::SVD s;
// svd result
Mat w,u,vt;
// computations ...
s.compute(img,w,u,vt);
// collect Sigma matrix (diagonal - is eigen values, other - zeros)
// we got it in as vector, transform it to diagonal matrix
Mat W=Mat::zeros(w.rows,w.rows,CV_32FC1);
for(int i=0;i<w.rows;i++)
{
W.at<float>(i,i)=w.at<float>(i);
}
// reduce rank to k
int k=25;
W=W(Range(0,k),Range(0,k));
u=u(Range::all(),Range(0,k));
vt=vt(Range(0,k),Range::all());
// Get compressed image
result=u*W*vt;
cout << "Result size:" << u.rows*u.cols+k+vt.rows*vt.cols <<" elements "<< endl;
//---------------------------------------------
//
//---------------------------------------------
imshow("Source Image", img);
imshow("Result", result);
cvWaitKey(0);
return 0;
}
Source and result images.