How to remove specified part in image and count number of objects in the image

Hello guys,

I would like to remove the part which is at the bottom right.

After that I need to caculate the number of objects in the image.

Thanks so much for your help in advance

Answer 1

[Image Analyst]

You can erase the lower right corner of the image like this:

rgbImage(end-50 : end, end-100 : end, :) = 0;

There are more general ways to erase anything outside of the circle, but you don't need that if all you want to do is erase the micron bar and it's in the same location for all your images -- you can simply set that portion to zero like I did above.

However if you want to see the more general way, even though you don't need it, let me know. It probably involves imclose, imclearborder, and bwareafilt

[Jialin Men]

Hello Image Analyst,

That is very nice of you.

And yes, I also want to know how to use imclose, imclearborder, and bwarefilt to remove specified part of object in the image.

Thanks so much

[Image Analyst]

Can you post a gray scale image - the original image before you segmented it into a binary image?

[Image Analyst]

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 = 18;

fileName = 'Objects in circle.png'
grayImage = imread(fileName);
[rows, columns, numberOfColorChannels] = size(grayImage)
if numberOfColorChannels > 1
	grayImage = grayImage(:, :, 1); % Take red channel only.
end
subplot(2, 2, 1);
imshow(grayImage)
axis on
impixelinfo
title('Original Image', 'FontSize', fontSize);
% Get a mask of white blobs.
mask = grayImage > 0;
% Get rid of white frame around his screenshot image.
mask = imclearborder(mask);
% Fill holes
se = strel('disk', 10, 8);
mask2 = imclose(mask, se);
mask2 = imfill(mask2, 'holes');
% Take largest and invert it.
mask2 = ~bwareafilt(mask2, 1);
% Display image.
subplot(2, 2, 2);
imshow(mask2)
axis on
impixelinfo
title('Mask Image', 'FontSize', fontSize);

% Use mask to erase pixels.
grayImage(mask2) = 0;
% Display image.
subplot(2, 2, 3);
imshow(grayImage)
axis on
impixelinfo
title('Masked Image', 'FontSize', fontSize);

% Count number of particles in mask
mask(mask2) = false;
% Label each blob with 8-connectivity, so we can make measurements of it
[labeledImage, numberOfBlobs] = bwlabel(mask, 4);
% Apply a variety of pseudo-colors to the regions.
coloredLabelsImage = label2rgb (labeledImage, 'hsv', 'k', 'shuffle');
% Display the pseudo-colored image.
subplot(2, 2, 4);
imshow(mask);
imshow(coloredLabelsImage);
% Get all the blob properties.  Can only pass in originalImage in version R2008a and later.
props = regionprops(labeledImage, 'Area');
numberOfBlobs = numel(props)
caption = sprintf('%d particles', numberOfBlobs)
title(caption, 'FontSize', fontSize);

[Jialin Men]

This is original image.

Thanks very much for your help.

[Jialin Men]

Hallo Image Analyst,

For the original image, is it same procedure?

best regards

[Image Analyst]

Yes it's easier because we don't have the zeros penetrating into the circle area, so it's easier to get the background mask. See attached.

You can get my interactive thresholding app here:

https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle

or else just segment the masked gray scale image however you were doing it instead of thresholding.

[Jialin Men]

Hallo Image Analyst.

That is very nice of you.

I sincerely appreciate your so kindly help. That really helps me a lot.

Best regards

JL.

Answer 2

[Sulaymon Eshkabilov]

See this solution post: https://www.mathworks.com/matlabcentral/answers/486087-remove-specific-objects-from-an-image