MATLAB: Connected Components on Input Image

connected components on input imageImage Processing Toolbox

Hi all

I want to visualize my compnents on original input image. I have performed foregorund detection by some background subtraction algorithm. Let say I have foregorund mask fgmask and input frame I.I have performed the connected component analysis like that

I=input Image;

FgMask=binary Image;

labelImage=bwlabel(FgMask,8);

blobMeasurements = regionprops(labeledImage, I, 'all');

numberOfBlobs = size(blobMeasurements, 1);

Now what I want to do, actually I do not need bounding box on foreground region, I want to label foregorund region into original input Image (foregorund region should be labeled from red colours) instead of bounding box.HOw can I perform that??

Every help is appreciated.

Best Answer

You can tint your image red in the foreground regions

redChannel = grayImage; % Initialize.
redChannel(binaryImage) = 255; % Max out red in foreground pixels.
% Create an RGB image.
tintedImage = cat(3, redChannel, grayImage, grayImage);
imshow(tintedImage);

Related Solutions

MATLAB: Binary Image – Black region detection

Mohsina, try this:

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format short g;
format compact;
fontSize = 25;
%===============================================================================

% Get the name of the image the user wants to use.
baseFileName = 'image1.png';
% Get the full filename, with path prepended.
folder = []; % Determine where demo folder is (works with all versions).
fullFileName = fullfile(folder, baseFileName);
%===============================================================================
% Read in a demo image.
grayImage = imread(fullFileName);
% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage)
if numberOfColorChannels > 1
  % It's not really gray scale like we expected - it's color.
  % Use weighted sum of ALL channels to create a gray scale image.
  grayImage = rgb2gray(grayImage);
  % ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,
  % which in a typical snapshot will be the least noisy channel.
  % grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the image.



subplot(2, 2, 1);
imshow(grayImage, []);
axis on;
axis image;
caption = sprintf('Original Gray Scale Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo();
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0, 1, 1]);
% 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;
% Create binary image of the black blobs from grayscale image.
binaryImage = grayImage == 0;
% Get rid of the background.
binaryImage = imclearborder(binaryImage);
% Display the image.
subplot(2, 2, 2);
imshow(binaryImage, []);
axis on;
axis image;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Label the blobs
[labeledImage, numBlobs] = bwlabel(binaryImage);
% Display the image.
subplot(2, 2, 2);
imshow(binaryImage, []);
axis on;
axis image;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Let's assign each blob a different color to visually show the user the distinct blobs.
coloredLabels = label2rgb (labeledImage, 'hsv', 'k', 'shuffle'); % pseudo random color labels
% coloredLabels is an RGB image.  We could have applied a colormap instead (but only with R2014b and later)
subplot(2, 2, 3);
imshow(coloredLabels);
axis on;
axis image; % Make sure image is not artificially stretched because of screen's aspect ratio.
caption = sprintf('Pseudo colored labels, from label2rgb().');
title(caption, 'FontSize', fontSize);
drawnow;
% Make measurements of bounding box.
props = regionprops(labeledImage, 'BoundingBox');
% Display the image.
subplot(2, 2, 4);
imshow(binaryImage, []);
axis on;
axis image;
title('Binary Image with Boxes', 'FontSize', fontSize, 'Interpreter', 'None');
% Display the bounding boxes around them.
hold on;
for k = 1 : numBlobs
  thisBoundingBox = props(k).BoundingBox
  rectangle('Position', thisBoundingBox, ...
    'EdgeColor', 'c', 'LineWidth', 2);
end

MATLAB: Center of Mass, metal foam

The key to getting the centroid of all the blobs together instead of getting each individually is to make a labeled image where the image is floating point, not binary. If it's binary, regionprops() will internally label each connected component and report the centroids of each component individually, which you said you don't want when you said "center of mass of the black circles" (at least that's how I'm interpreting it).

Try this.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 22;
%--------------------------------------------------------------------------------------------------------

%    READ IN IMAGE
folder = pwd;
baseFileName = 'image.png';
% Get the full filename, with path prepended.
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
grayImage = imread(fullFileName);
% Get the dimensions of the image.
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(grayImage);
if numberOfColorChannels > 1
	% It's not really gray scale like we expected - it's color.
	% Use weighted sum of ALL channels to create a gray scale image.
	grayImage = rgb2gray(grayImage);
	% ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,
	% which in a typical snapshot will be the least noisy channel.
	% grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the image.

subplot(2, 2, 1);
imshow(grayImage, []);
title('Original Grayscale Image', 'FontSize', fontSize, 'Interpreter', 'None');
impixelinfo;
hFig = gcf;
hFig.WindowState = 'maximized'; % May not work in earlier versions of MATLAB.
drawnow;
%--------------------------------------------------------------------------------------------------------
%    EXTRACTION OF IMAGE
% Get a binary image
binaryImage = grayImage < 128;
% Get rid of the surround.
binaryImage = imclearborder(binaryImage);
subplot(2, 2, 2);
imshow(grayImage, []);
impixelinfo;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
impixelinfo;
% Fill holes
binaryImage = imfill(binaryImage, 'holes');
% Display the image.
subplot(2, 2, 3);
imshow(binaryImage, []);
title('Black Blobs', 'FontSize', fontSize, 'Interpreter', 'None');
axis('on', 'image');
% Find the center of mass, which is the same as the centroid since all we have is a binary image.
% Casting the binary image to double is the KEY to making sure we get just one
% centroid rather than a centroid for each and every blob individually.
labeledImage = double(binaryImage);
props = regionprops(labeledImage, 'Centroid')
xCentroid = props.Centroid(1);
yCentroid = props.Centroid(2);
% Plot a red crosshairs there
hold on;
plot(xCentroid, yCentroid, 'r+', 'MarkerSize', 200, 'LineWidth', 3);
caption = sprintf('Centroid of black blobs at (%.2f, %.2f)', xCentroid, yCentroid);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

If you actually want all the individual centroids, you can do

labeledImage = double(binaryImage);

but you said you already did that and have the individual centroids already.

Best Answer

Related Solutions

MATLAB: Binary Image – Black region detection

MATLAB: Center of Mass, metal foam

Related Question