How to crop an irregular shape from the image?

My topic of the project is to detect and segment the optic disk. First of all, i want to remove the black background at four corners.

I have found the region of eye and labelled with red circle as shown in the figure. Now i am facing a problem which is how to crop the region?

Can someone please advise? Thank you.

Answer 1

[Image Analyst]

OK, it seems you were unable to take my steps and code it up so I've done it for you.

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 = 'Screenshot (329).png';
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)
% Crop off screenshot stuff
rgbImage = rgbImage(132:938, 352:1566, :);
% Display image.
subplot(2, 2, 1);
imshow(rgbImage, []);
impixelinfo;
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;
% Take one of the color channels, whichever one seems to have more contrast..
colorChannelToUse = 2;
grayImage = rgbImage(:, :, colorChannelToUse);
% Display the color segmentation mask image.
subplot(2, 2, 2);
imshow(grayImage, []);
caption = sprintf('Color Channel %d', colorChannelToUse)
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
impixelinfo;
axis('on', 'image');
drawnow;

%=======================================================================================
% Threshold the image to get the optics disk.
lowThreshold = 112;
highThreshold = 255;
% Use interactive File Exchange utility by Image Analyst to to the interactive thresholding.
% https://www.mathworks.com/matlabcentral/fileexchange/29372-thresholding-an-image?s_tid=srchtitle
% [lowThreshold, highThreshold] = threshold(114, 255, grayImage);
mask = grayImage >= lowThreshold & grayImage <= highThreshold;
% Now do clean up by hole filling, and getting rid of small blobs.
mask = imfill(mask, 'holes');
mask = bwareafilt(mask, 1); % Take largest blob only.
% mask = bwconvhull(mask);
% Display the color segmentation mask image.
subplot(2, 2, 3);
imshow(mask, []);
title('Final Mask', 'FontSize', fontSize, 'Interpreter', 'None');
impixelinfo;
axis('on', 'image');
drawnow;
% Get x and y
boundary = bwboundaries(mask);
x = boundary{1}(:, 2);
y = boundary{1}(:, 1);
subplot(2, 2, 1);
% Display image with optics disc outlined over it.
subplot(2, 2, 4);
imshow(rgbImage, []);
impixelinfo;
axis on;
caption = sprintf('With Boundary Outlining the Disc');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Display boundary
hold on;
plot(x, y, 'b-', 'LineWidth', 2);

%=======================================================================================
findBoundingCircle = false;
if findBoundingCircle
    % Find the minimum bounding circle using John D'Errico's File Exchange
    % https://www.mathworks.com/matlabcentral/fileexchange/34767-a-suite-of-minimal-bounding-objects?s_tid=srchtitle
    % Get the minimum bounding circle.
    hullflag = true;
    [center,radius] = minboundcircle(x,y,hullflag)
    % Show circle
    viscircles(center, radius, 'color', 'r');
    caption = sprintf('With Boundary and Bounding Circle');
    title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
end
uiwait(helpdlg('Done!'));

If it works for you can you click the "Accept this answer" otherwise, say why it didn't work.

[ZWY]

Hi, thank you for you code.

This code works fine only for this image. However, my project is targeted on 80 images which the threshold value needs to be manually changed for every image.

Do you have any suggestions? Can i use fuzzy c mean?

Thank you.

[Image Analyst]

Try the interactive threshold link given in the code. Or try the attached triangle threshold.

[ZWY]

Could you provide the code for the interactive threshold? I could not find the link.

Thanks.

[Image Analyst]

Link for interactive/visual threshold:

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

It's one of many in my File Exchange:

Image Analyst's File Exchange

[ZWY]

Thank you very much

Answer 2

[Tala]

Image analyst beautifully explains here

https://www.mathworks.com/matlabcentral/answers/1683749-how-to-crop-a-masked-area-polygon-shape-out-of-an-image#answer_930129

In order to create a circle mask, see this

https://www.mathworks.com/matlabcentral/fileexchange/47905-createcirclesmask-m

[ZWY]

Hi Tala, thank you for the reply.

Regarding the circle mask, i have tried it but the command window shows the error:

Unrecognized function or variable 'createCirclesMask'

Do you have any other suggestions?

[Tala]

I just had a chance to open your image on a PC. your image is not a complete circle,maybe thats why!

Also, I am not clear what do you mean by crop. Your image is already cropped since the back ground is zero.

[Walter Roberson]

https://www.mathworks.com/matlabcentral/fileexchange/47905-createcirclesmask-m

[ZWY]

Hi Tala, you are right, I do not need to crop the image. Now i have known the problem and thank you for your time.

Thank Walter too!

Answer 3

[Image Analyst]

You don't need to get rid of the black background. That is not the first step, nor even anything you need to do.

Your first step should be to go here:

http://www.visionbib.com/bibliography/contentsmedical.html#Medical%20Applications,%20CAT,%20MRI,%20Ultrasound,%20Heart%20Models,%20Brain%20Models

and look at the sections:

• 20.5 Retinal Images, Analysis of Eye, etc.
• 20.5.1 Eye, Cornea, Corneal Images
• 20.5.2 Optic Disc Location, Optic Disc Detection
• 20.5.3 Retinal Images, Angiography, Blood Vessels in the Eye
• 20.5.3.1 Retinal Microaneurysms, Detection
• 20.5.4 Glaucoma Retinopathy, Retinal Analysis Application
• 20.5.5 Cataracts, Detection, Analysis, Surgery
• 20.5.6 Diabetic Retinopathy, Retinal Analysis Application
• 20.5.7 Macular Degeneration Detection, Retinal Analysis Application
• 20.5.8 Retinal Images, Optical Coherence Tomography, OCT

to see how it's done in section 20.5.2.

One simplistic approach would be to use the blue channel and threshold to find the optics disc. Then I'd use bwconvhull() to get its convex hull.