to find the ROI surrounding the centroid

I have an image that has several objects in it. I have found the centroid of one of the desired objects in them. I want to create ROI surrounding this centroid alone and make other objects zero or null.

Answer 1

[Image Analyst]

Like I said in your question last month (that you accepted - thanks), that's covered in my Image Segmentation Tutorial. If you don't think it does, the post your code and show why not.

[BV]

I managed to get just the desired object. but the object itself has an incomplete edge i.e., object has black and white color inside it. I need to get the object with unicolor(black) against the background(white).

[BV]

I have uploaded the image.

http://imageshack.us/content_round.php?page=done&id=4tHclKKinZ2tk97Q0qOZpKzX3ZHV480

http://tinypic.com/r/2bofbt/5

http://tinypic.com/view.php?pic=2bofbt&s=5

[Image Analyst]

It's not too hard, just threshold and use bwareaopen() to get rid of small specks. I improved the image by doing a crude background correction by fitting the background to a quadratic.

clc;    % Clear the command window.
clearvars
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;

% Read in a standard MATLAB gray scale demo image.
folder = 'C:\Users\BW\Documents\Temporary';
baseFileName = '2bofbt.jpg';
% Get the full filename, with path prepended.
fullFileName = fullfile(folder, baseFileName);
% Check if file exists.
if ~exist(fullFileName, 'file')
  % File doesn't exist -- didn't find it there.  Check the search path for it.
  fullFileName = baseFileName; % No path this time.
  if ~exist(fullFileName, '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.  
% numberOfColorBands should be = 1.
[rows, columns, numberOfColorBands] = size(grayImage);
if numberOfColorBands > 1
  % It's not really gray scale like we expected - it's color.
  % Convert it to gray scale by taking only the green channel.
  grayImage = grayImage(:, :, 2); % Take green channel.
end
% Display the original gray scale image.
subplot(2, 3, 1);
imshow(grayImage, []);
axis on;
title('Original Grayscale Image', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'units','normalized','outerposition',[0 0 1 1]);
% Give a name to the title bar.
set(gcf,'name','Demo by ImageAnalyst','numbertitle','off') 

% Let's compute and display the histogram.
[pixelCount, grayLevels] = imhist(grayImage);
subplot(2, 3, 4); 
bar(pixelCount);
grid on;
title('Histogram of original image', 'FontSize', fontSize);
xlim([0 grayLevels(end)]); % Scale x axis manually.

%===== BACKGROUND CORRECTION ================================
% Do a crude background correction by fitting to a quadratic.
verticalProfile = sum(grayImage(:,1:200), 2);
subplot(2, 3, 2); 
plot(verticalProfile);
y = (1:rows)';
coeffsV = polyfit(y, verticalProfile, 2);
% Correct image vertically.
correctionCurve = polyval(coeffsV, y);
correctionCurve = correctionCurve / max(correctionCurve);
percentageImage = repmat(correctionCurve, [1, columns]);
grayImage = double(grayImage) ./ percentageImage;
imshow(grayImage, []);
% Same for horizontal direction.
horizontalProfile = sum(grayImage(1:300,:), 1);
subplot(2, 3, 2); 
plot(horizontalProfile);
x = 1:columns;
coeffsH = polyfit(x, horizontalProfile, 2);
% Correct image horizontally.
correctionCurve = polyval(coeffsH, x);
correctionCurve = correctionCurve / max(correctionCurve);
percentageImage = repmat(correctionCurve, [rows, 1]);
grayImage = uint8(double(grayImage) ./ percentageImage);
imshow(grayImage, []);
title('Background Corrected Grayscale Image', 'FontSize', fontSize);
drawnow;
%===== END OF BACKGROUND CORRECTION ================================

% Let's compute and display the histogram.
[pixelCount, grayLevels] = imhist(grayImage);
subplot(2, 3, 5); 
bar(pixelCount);
grid on;
title('Histogram of background corrected image', 'FontSize', fontSize);
xlim([0 grayLevels(end)]); % Scale x axis manually.

% Binarize the image
binaryImage = grayImage < 120;
% Get rid of small particles.
binaryImage = bwareaopen(binaryImage, 100);
% Fill holes.
binaryImage = imfill(binaryImage, 'holes');
% Display the image.
subplot(2, 3, 3);
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize);
% Invert so that the "part" is black instead of white.
binaryImage = ~binaryImage;
% Display the image.
subplot(2, 3, 6);
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize);

[BV]

thank you very much. I can see that small holes in the right corner of the original image has been filled. But I want the bigger region(white portion)on the left side of the bone to be filled up. so that the full image of the bone is visible without missing edges.

[Image Analyst]

Perhaps you might want to use the convex hull by using bwconvhull(). Feel free to adapt my code. I've given you a good start, but I'm not going to do the whole project for you. Good luck.

[BV]

thank you once again) bwconvhull()doesnt work that well. I have a centroid position.I want to create a rectangle of a particular dimension sround this centroid. Is there any function to do make a rect around the centroid? I don know how to use the centroid in 'imrect()'.