MATLAB: How to fullfill segmented region by using region growing

region growing

Can anyone help me on how to make the segmented purple region fulfilled the neighborhood 'empty' area with the same purple color?

The image is actually an overlapped of two brain images: </matlabcentral/answers/uploaded_files/54479/overlapped%20images.png>

The problem is, how to make the region of purple growing and fulfill all it's neighborhood region so that the region is larger.

Actually my intention is to perform region growing before k-means clustering, but it seems like it does not make any sense because both are segmentation. Any idea guys?…

Best Answer

The image is actuall

y an overlapped of two brain images:

Related Solutions

MATLAB: Sir . I have successfully cropped the upper region (in 5 coin) but couldn’t crop lower region from the same image as I need to crop the image so to get center part only as high.

Try this. Adapt as needed, like the percentage of the middle that you want.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;
%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = 'c3.jpg';
folder = pwd
fullFileName = fullfile(folder, baseFileName);
% Check if file exists.
if ~exist(fullFileName, 'file')
  % The file doesn't exist -- didn't find it there in that folder.
  % Check the entire search path (other folders) for the file by stripping off the folder.
  fullFileNameOnSearchPath = baseFileName; % No path this time.
  if ~exist(fullFileNameOnSearchPath, 'file')
    % Still didn't find it.  Alert user.
    errorMessage = sprintf('Error: %s does not exist in the search path folders.', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
%=======================================================================================
% Read in demo image.
rgbImage = imread(fullFileName);
% Get the dimensions of the image.

[rows, columns, numberOfColorChannels] = size(rgbImage)
% Display image.
subplot(3, 3, 1);
imshow(rgbImage, []);
axis on;
caption = sprintf('Original Color Image\n%s', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);
% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')
drawnow;
% Find the max in all color channels.
mask = max(rgbImage, [], 3);
% Take the largest blob only, to get rid of noise.
% mask = bwareafilt(mask, 1);
% Fill any holes in it.
% mask = imfill(mask, 'holes');
% Let's assume it's supposed to be convex.  Make sure.
% mask = bwconvhull(mask);
% Display the image.

subplot(3, 3, 2);
histogram(mask);
% Binarize the image
mask = mask > 225;
% Keep only largest region then invert it to get the coin masks.
mask = ~bwareafilt(mask, 1);
% Fill holes.
mask = imfill(mask, 'holes');
% Get rid of blobs less than 1000 pixels.  There seems to be a few.
mask = bwareafilt(mask, [1000, inf]);
[labeledImage, numBlobs] = bwlabel(mask);
imshow(mask, []);
axis on;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Mask the image with the new, cleaned mask.
% Mask the image using bsxfun() function to multiply the mask by each channel individually.
maskedRgbImage = bsxfun(@times, rgbImage, cast(mask, 'like', rgbImage));
% Display the image.
subplot(3, 3, 3);
imshow(maskedRgbImage, []);
axis on;
title('Masked RGB Image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Get the equivalent bounding box.
props = regionprops(mask, 'BoundingBox', 'area');
allAreas = [props.Area]
plotNumber = 7;
percentage = 0.15; % Percentage of coin the middle part should be.
for k = 1 : length(props)
  % Crop the image
  croppedImage = imcrop(rgbImage, props(k).BoundingBox);
  % Display the images.

  subplot(3, 6, plotNumber);
  imshow(croppedImage, []);
  axis on;
  title('Cropped RGB Image', 'FontSize', fontSize, 'Interpreter', 'None');
  drawnow;
  
  % Now crop out the middle 50%
  % Get the dimensions of the image.
  [rows, columns, numberOfColorChannels] = size(croppedImage);
  row1 = round(rows * (0.5 - percentage));
  row2 = round(rows * (0.5 + percentage));
  col1 = round(rows * (0.5 - percentage));
  col2 = round(rows * (0.5 + percentage));
  middlePart = croppedImage(row1:row2, col1:col2, :);
  % Display the images.
  subplot(3, 6, plotNumber + 1);
  imshow(middlePart, []);
  axis on;
  title('Cropped RGB Image', 'FontSize', fontSize, 'Interpreter', 'None');
  drawnow;
  plotNumber = plotNumber + 2;
end

MATLAB: What is the fit method to exclude the shadow?

Try this:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clearvars;
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;
%=======================================================================================
% Read in image.
fullFileName = fullfile(pwd, '63.jpg');
[folder, baseFileName, ext] = fileparts(fullFileName);
rgbImage = imread(fullFileName);
% Shrink it to speed it up
% rgbImage = imresize(rgbImage, 0.75);
% Get the dimensions of the image.
[rows, columns, numberOfColorChannels] = size(rgbImage);
% Display the original image.
subplot(2, 2, 1);
imshow(rgbImage, []);
axis on;
caption = sprintf('Original Color Image "%s"', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.


% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0.05 1 0.95]);
% Get rid of tool bar and pulldown menus that are along top of figure.
% set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off')
% Get mask for outer gray, and inner blue parts of the wheel by doing color segmentations.
[mask, maskedRGBImage] = createMask(rgbImage);
% Clean up noise by filling holes and taking largest blob only.
mask = imfill(mask, 'holes');
mask = bwareafilt(mask, 1);
% Display the mask image.
subplot(2, 2, 2);
imshow(mask);
axis on;
title('Mask, binary image', 'FontSize', fontSize, 'Interpreter', 'None');
% Mask the image and show the masked image.
subplot(2, 2, 3);
imshow(maskedRGBImage, []);
axis on;
title('Masked RGB image', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Display the original image with mask boundary over it.
subplot(2, 2, 4);
imshow(rgbImage, []);
axis on;
caption = sprintf('Color Image with Boundary');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Plot boundaries
boundaries = bwboundaries(mask);
hold on;
numberOfBoundaries = size(boundaries, 1);
for k = 1 : numberOfBoundaries
  thisBoundary = boundaries{k};
  plot(thisBoundary(:,2), thisBoundary(:,1), 'r', 'LineWidth', 3);
end
hold off;
function [BW,maskedRGBImage] = createMask(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.
% Auto-generated by colorThresholder app on 20-Aug-2018
%------------------------------------------------------
% Convert RGB image to chosen color space
I = rgb2hsv(RGB);
% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.959;
channel1Max = 0.099;
% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.194;
channel2Max = 1.000;
% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.410;
channel3Max = 1.000;
% Create mask based on chosen histogram thresholds
sliderBW = ( (I(:,:,1) >= channel1Min) | (I(:,:,1) <= channel1Max) ) & ...
  (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
  (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;
% Initialize output masked image based on input image.
maskedRGBImage = RGB;
% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;
end

Notes: It's not perfect because you don't have good control over your image capture situation. Get rid of shadows and background clutter to get a better masking.

Best Answer

Related Solutions

MATLAB: Sir . I have successfully cropped the upper region (in 5 coin) but couldn’t crop lower region from the same image as I need to crop the image so to get center part only as high.

MATLAB: What is the fit method to exclude the shadow?

Related Question