Question

Actually I have already asked this question in official Q&A but didn’t get any answer yet.

My task is to use kmeans clusterization not for the whole image but only for it’s masked part. So as input I have two images:

1. Masked image.
2. Image converted to Lab color space.

And if I clusterize image on n clusters, after clusterization with mask I want to have image with n+1 clusters (+1 because of mask).

Of course I researched and googled it but found nothing.

Thanks for any advice.

Answer 1

Create another image, copy the data unmasked data in it, and use this matrix to perform your kmeans. This is how it goes:

[edit]

The following does not work, it only black-out pixels in the mask, but tmp has same dimension as original image.
cv::Mat tmp;
labImage.copyTo(tmp, mask);

You should allocate the tmp matrix beforehand, and fill it with a loop over the mask:

cv::Mat tmp = cv::Mat::zeros(cv::countNonZero(mask), 1, labImage.type());
int counter = 0;
for (int r = 0; r < mask.rows; ++r)
  for (int c = 0; c < mask.cols; ++c) 
    if (!mask.at<unsigned char>(r, c))
      // I assume Lab pixels are stored as a vector of floats
      tmp.at<cv::Vec3f>(counter++, 0) = labImage.at<cv::Vec3b>(r, c);

[/edit]

cv::kmeans(tmp, k, labels);

// Now to compute your image of labels
cv::Mat labelsImage = cv::Mat(labImage.size(), CV_32S, k); // initialize pixel values to K, which is the index of your N+1 cluster

// Now loop through your pixel mask and set the correspondance in your labelImage
int counter = 0;
for (int r = 0; r < mask.rows; ++r)
  for (int c = 0; c < mask.cols; ++c) 
    if (!mask.at<unsigned char>(r, c))
      labelsImage.at<int>(r, c) = labels.at<int>(counter++, 0);