Databases
StackOverflow2013
Postsdbo
POEigenvector computation using OpenCV
Body
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POEigenvector computation using OpenCV
    text
    copied!<p>I have this matrix A, representing similarities of pixel intensities of an image. For example: Consider a <code>10 x 10</code> image. Matrix A in this case would be of dimension <code>100 x 100</code>, and element A(i,j) would have a value in the range 0 to 1, representing the similarity of pixel i to j in terms of intensity.</p> <p>I am using OpenCV for image processing and the development environment is C on Linux. </p> <p>Objective is to compute the Eigenvectors of matrix A and I have used the following approach:</p> <pre><code>static CvMat mat, *eigenVec, *eigenVal; static double A[100][100]={}, Ain1D[10000]={}; int cnt=0; //Converting matrix A into a one dimensional array //Reason: That is how cvMat requires it for(i = 0;i &lt; affnDim;i++){ for(j = 0;j &lt; affnDim;j++){ Ain1D[cnt++] = A[i][j]; } } mat = cvMat(100, 100, CV_32FC1, Ain1D); cvEigenVV(&amp;mat, eigenVec, eigenVal, 1e-300); for(i=0;i &lt; 100;i++){ val1 = cvmGet(eigenVal,i,0); //Fetching Eigen Value for(j=0;j &lt; 100;j++){ matX[i][j] = cvmGet(eigenVec,i,j); //Fetching each component of Eigenvector i } } </code></pre> <p><strong>Problem:</strong> After execution I get nearly all components of all the Eigenvectors to be zero. I tried different images and also tried populating A with random values between 0 and 1, but the same result.</p> <p>Few of the top eigenvalues returned look like the following:</p> <pre><code>9805401476911479666115491135488.000000 -9805401476911479666115491135488.000000 -89222871725331592641813413888.000000 89222862280598626902522986496.000000 5255391142666987110400.000000 </code></pre> <p>I am now thinking on the lines of using <a href="http://www710.univ-lyon1.fr/~bouakaz/OpenCV-0.9.5/docs/ref/OpenCVRef_BasicFuncs.htm#decl_cvSVD" rel="noreferrer">cvSVD()</a> which performs singular value decomposition of real floating-point matrix and might yield me the eigenvectors. But before that I thought of asking it here. Is there anything absurd in my current approach? Am I using the right API i.e. <a href="http://www710.univ-lyon1.fr/~bouakaz/OpenCV-0.9.5/docs/ref/OpenCVRef_BasicFuncs.htm#decl_cvEigenVV" rel="noreferrer">cvEigenVV()</a> for the right input matrix (my matrix A is a floating point matrix)?</p> <p>cheers</p>
 

Querying!

 
Guidance
An individual column

Larger individual text columns get their own page to allow for proper reading.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload