How to find area of specific region in binary image ?

For example, I have image with

1. region1 white,
2. region2 black,
3. region3 white,
4. region4 black and
5. region5 white.

How can I know pixel density in region4 and how to convert that specific area mm2/cm2 ?

[Image Analyst]

What do you mean by pixel density? All regions of the image have the same density (pixels per unit area). Or do you mean "optical density", in other words, intensity of a gray scale image in region 4?

[Junaid Dar Dar]

Yes, If we can know the intensity of specific region as each has different area, we can calculate area in mm2/cm2.

Answer 1

[Image Analyst]

See my Image Segmentation Tutorial in my File Exchange:

Image Analyst's File Exchange

In short, segment your image by thresholding or whatever to get a mask, then do

props = regionprops(mask, grayImage, 'Area', 'MeanIntensity');
for k = 1 : numel(props)
    fprintf('Blob #%d has an area of %d pixels (%.2f sq. cm), and mean intensity of %.2f\n', ...
        k, props(k).Area, props(k).Area * cmPerPixel^2, props(k).MeanIntensity);
end

To see how to determine the number of pixels per cm, see my attached spatial calibration demo.

[Junaid Dar Dar]

In grayscale image we can get mask by specifying intensity (0-255), but in binary if we select 0 or 1, it selects all 0's or 1's. It makes it difficult to make mask of targeted area.

[Image Analyst]

But you already have a mask (binary) image. You attached it as random.png. You can then label it and use ismember() to extract out one or more "targeted" blobs. Like if you want the 3rd blob, do

[labeledImage, numBlobs] = bwlabel(mask);
blob3 = ismember(labeledImage, 3);
props = regionprops(mask, grayImage, 'Area', 'MeanIntensity');

Not sure what else you're looking for. Please try to explain better. Post an annotated image to show what region you're talking about (what's the "targeted area"), and attach the gray scale image that you want the mean intensity of.

[Junaid Dar Dar]

I try using above code, but it is giving 3 different values of areas for white region, but i need only one value of 3rd blob. See attachment "practice".

[Image Analyst]

Try this and you'll see the areas of the 3 regions are

allAreas =

344470 520607 787221

The area of the 3rd blob (the right-most one) is 787221 pixels.

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 = 'random.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, []);
axis('on', 'image');
title('Original Grayscale Image', 'FontSize', fontSize, 'Interpreter', 'None');
impixelinfo;
hFig = gcf;
hFig.WindowState = 'maximized'; % May not work in earlier versions of MATLAB.
drawnow;

%--------------------------------------------------------------------------------------------------------
%    SEGMENTATION OF IMAGE
% Get a binary image
mask = imbinarize(grayImage);
% Display the mask.
subplot(2, 2, 2);
imshow(mask, []);
axis('on', 'image');
impixelinfo;
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');

% Label each blob with 8-connectivity, so we can make measurements of it
[labeledImage, numberOfBlobs] = bwlabel(mask, 8);
% Apply a variety of pseudo-colors to the regions.
coloredLabelsImage = label2rgb (labeledImage, 'hsv', 'k', 'shuffle');
% Display the pseudo-colored image.
subplot(2, 2, 3);
imshow(coloredLabelsImage);
caption = sprintf('Labeled Image with %d Regions', numberOfBlobs);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

% Get the area of each blob.
props = regionprops(mask, 'Area');
allAreas = [props.Area]

% Show bar chart of areas.
subplot(2, 2, 4);
bar(allAreas);
grid on;
caption = sprintf('Areas of the %d Regions in Pixels', numberOfBlobs);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');

msgbox('Done');

[Junaid Dar Dar]

Thank you for your answers.

It partially solve my probelm, like first i was getting area of all regions as a single answer.Now, through this I can get areas of three regions serparately. But I need single output, as area of 3rd blob only. Hope I can get best through this.

[Image Analyst]

areaOfBlob3 = allAreas(3);

I think that's SO obvious that I'm not sure it's what you mean, so try to explain better.