MATLAB: I need a code for Color co-occurence descriptors considering color information

cbirimage processing

I need a code for Color CO-occurance descriptor (feature) which is used in Content-Based Image Retrieval (CBIR)

Best Answer

Call rgb2ind to get unique color indices with quantization. Then call graylevel co-occurrence on the indexed image.

Related Solutions

MATLAB: How to convert gray or indexed images to color images

That image is a 2D image, an indexed image with a color map. It's not a 3D color RGB image. You need to convert it to an RGB image if you recognize it's an indexed image. Replace your loop with this:

for k = 1:numel(bmpFiles)
  fullInputFileName = fullfile(inputFolder,bmpFiles(k).name)
  [originalImage, colorMap] = imread(fullInputFileName);
  [rows, columns, numberOfColorChannels] = size(originalImage)
  if ~isempty(colorMap) && numberOfColorChannels == 1
    % It's an indexed image with a colormap.
    % Convert it to RGB color
    originalImage = ind2rgb(originalImage, colorMap);
    [rows, columns, numberOfColorChannels] = size(originalImage)
  end
  fullOutputFileName = fullfile(outputFolder, bmpFiles(k).name);
  outputImage = imresize(originalImage, [100,50]);
  [rows columns numberOfColorChannels] = size(outputImage);
  if numberOfColorChannels == 1
    % It's monochrome, so convert to color.
    outputImage = cat(3, outputImage, outputImage, outputImage);
  end
  
  figure,imshow(outputImage);
  imwrite(outputImage, fullOutputFileName);
end

MATLAB: ‘jet’ countour plot over grayscale image

I suggest you use the File Exchange contribution "freezeColors" on the grayscale image.

Best Answer

Related Solutions

MATLAB: How to convert gray or indexed images to color images

MATLAB: ‘jet’ countour plot over grayscale image

Related Question