How can I change the segmented colours to another one?

Hi all,

Currently I work on colour segmentation and intend to change to another one. As you can see, the attached picture 1.jpg is the original picture and has two colours, the blue and the gold (pattern) colours. I followed the provided source code from matlab and changed the gold-pattern colour to the red one (or it could be any other colours), see the 2.jpg image attached. However, the blue colour changed due to "masking process" (conversion from RGB to grayscale). I need to change the blue colour to any other colours (e.g. green) as well. So, the output must be green and red colours. How can I do that? Need help please.

Cheers.

function [sample_regions] = ChangeColor(imin)
  load regioncoordinates;
  nColors = 2;
  sample_regions = false([size(imin,1) size(imin,2) nColors]);

    for count = 1:nColors
      sample_regions(:,:,count) = roipoly(imin,region_coordinates(:,1,count),...
                                          region_coordinates(:,2,count));
    end

    lab_imin = rgb2lab(imin);
    a = lab_imin(:,:,2);
    b = lab_imin(:,:,3);
    color_markers = zeros([nColors, 2]);

    for count = 1:nColors
      color_markers(count,1) = mean2(a(sample_regions(:,:,count)));
      color_markers(count,2) = mean2(b(sample_regions(:,:,count)));
    end

    color_labels = 0:nColors-1;
    a = double(a);
    b = double(b);
    distance = zeros([size(a), nColors]);

    for count = 1:nColors
      distance(:,:,count) = ( (a - color_markers(count,1)).^2 + ...
                          (b - color_markers(count,2)).^2 ).^0.5;
    end

    [~, label] = min(distance,[],3);
    label = color_labels(label);
    clear distance;

    rgb_label = repmat(label,[1 1 3]);
    segmented_images = zeros([size(imin), nColors],'uint8');

    for count = 1:nColors
      color = imin;
      color(rgb_label ~= color_labels(count)) = 0;
      segmented_images(:,:,:,count) = color;
    end 

    lappet = segmented_images(:,:,:,1);

    grayImage = rgb2gray(lappet);

    % Binarize (threshold) the image to find 
    % where the average is brighter than some threshold value.
    thresholdValue = 100; % Change to whatever value you want.
    binaryImage = grayImage > thresholdValue;

    % Extract the individual red, green, and blue color channels.
    redChannel = lappet(:, :, 1);
    greenChannel = lappet(:, :, 2);
    blueChannel = lappet(:, :, 3);

    % Make binary pixels red.
    redChannel(binaryImage) = 255;
    greenChannel(binaryImage) = 0;
    blueChannel(binaryImage) = 0;

    % Get RGB image again.
    newRGB = cat(3, redChannel, greenChannel, blueChannel);
    imshow(newRGB);