How to isolate certain part of image?

Suppose i have a eye image, in that image i draw a circle. Now i want to isolate the circle part from the rest of image.

[Susanna Moore]

For my view, to just isolate and obtain the image circle part, you can use a third-party image processing library (free trial).Generally, you can easily crop the part.

Answer 1

[Image Analyst]

All right, I have one expecially for circles that's simpler than the other one (which perhaps was ignored because its length scared you off). Don't worry - the main code in this is only one line long. Mostly it's long because of all the comments and fancy things like displaying images and giving titles to them. The main line of code is this:

maskedImage(~circleImage) = 0; % Zero image outside the circle mask.

Which you can change to

maskedImage(~circleImage) = 255; % Whiten image outside the circle mask.

if you want white instead of black.

Try this demo (also attached):

% Demo to mask an image with a circle.
% Requires the Image Processing Toolbox.
%
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
imtool close all;  % Close all imtool figures.
clear;  % Erase all existing variables.
workspace;  % Make sure the workspace panel is showing.
fontSize = 20;

% Change the current folder to the folder of this m-file.
if(~isdeployed)
  cd(fileparts(which(mfilename)));
end
  
% Read in a standard MATLAB gray scale demo image.
folder = fullfile(matlabroot, '\toolbox\images\imdemos');
% Comment out whichever demo image you don not want to use.
baseFileName = 'cameraman.tif'; % Grayscale demo image.
baseFileName = 'peppers.png'; % Color demo image.

fullFileName = fullfile(folder, baseFileName);
% See if the image exists.
if ~exist(fullFileName, 'file')
  % Doesn't exist in that folder. See if it exists anywhere on the path.
  fullFileName = baseFileName;
  if ~exist(fullFileName, 'file')
    errorMessage = sprintf('Error: file %s not found', fullFileName);
    uiwait(warndlg(errorMessage));
    return;
  end
end
% Read in the image from disk.
originalImage = imread(fullFileName);
% Get the dimensions of the image.  numberOfColorBands should be = 1.
[rows, columns, numberOfColorBands] = size(originalImage);
% Display the original gray scale image.
subplot(2, 2, 1);
imshow(originalImage, []);
% Change imshow to image() if you don't have the Image Processing Toolbox.
title('Original Image', 'FontSize', fontSize);
% Enlarge figure to full screen.
set(gcf, 'Position', get(0,'Screensize')); 
set(gcf,'name','Image Analysis Demo','numbertitle','off') 

% Initialize parameters for the circle,
% such as it's location and radius.
circleCenterX = 130; 
circleCenterY =  75; % square area 0f 500*500 
circleRadius = 50;    % big circle radius 

% Initialize an image to a logical image of the circle. 
circleImage = false(rows, columns); 
[x, y] = meshgrid(1:columns, 1:rows); 
circleImage((x - circleCenterX).^2 + (y - circleCenterY).^2 <= circleRadius.^2) = true; 
% Display it in the upper right plot. 
subplot(2,2,2); 
imshow(circleImage, []); 
% Change imshow to image() if you don't have the Image Processing Toolbox.
title('Circle Mask', 'FontSize', fontSize); 
set(gcf, 'Position', get(0,'Screensize')); % Maximize figure.
drawnow;

% Mask the image with the circle.
if numberOfColorBands == 1
  maskedImage = originalImage; % Initialize with the entire image.
  maskedImage(~circleImage) = 0; % Zero image outside the circle mask.
else
  % Mask the image.
  maskedImage = bsxfun(@times, originalImage, cast(circleImage,class(originalImage)));
end

% Display it in the lower right plot. 
subplot(2, 3, 5); 
imshow(maskedImage, []); 
% Change imshow to image() if you don't have the Image Processing Toolbox.
title('Image masked with the circle.', 'FontSize', fontSize);

[Image Analyst]

Hello Umme - are you still alive? Any reply?

[Umme Tania]

[Umme Tania]

Hi...i tried your demo.......but when i use eye image as a input it look like this.

[Image Analyst]

You have an RGB image. I edited the answer to include a version that works for RGB images.

[Umme Tania]

Thanks .....now it's working

[Dhananjaya Kumarajati]

thank you very much, for your code, its helps solve my problem.

[Ariel Avshalumov]

What should I do if I want to select several such circles in an image? And what about if I want the rest of the image outsides of circles to be a variable changing gray?

I tried to do this with squares but I was having quite a bit of trouble. https://www.mathworks.com/matlabcentral/answers/410634-selectively-grab-regions-of-pixels-from-one-image-to-transcribe-to-another?s_tid=prof_contriblnk

[Image Analyst]

Ariel, post a new question with the image you're starting with and the one you want to end up with. Otherwise all I can say is to do the code once for each circle you want.

[Ariel Avshalumov]

Here is the new question.

https://www.mathworks.com/matlabcentral/answers/411180-chart-regions-of-pixels-onto-new-image

[Keerthi D]

Suppose i have a colour leaf image, in that image i draw freehand. Now i want to isolate the freehand part from the rest of image.sir,I am beginner in this field.please help me.

[Keerthi D]

sendt the code through my mail.

mailid:[e-mail]

[Image Analyst]

Keethi, I did that here in this link

[ashwani yadav]

How to do this for a square region?

[Image Analyst]

Call drawrectangle(), imrect(), or rbbox() to get the rows and columns of the box.

Answer 2

[Image Analyst]

See my masking demo. You should be able to adapt it to do what you want. Let me know if you can't.

% Demo to have the user freehand draw an irregular shape over a gray scale image.
% Then it creates new images:
% (1) where the drawn region is all white inside the region and untouched outside the region,
% (2) where the drawn region is all black inside the region and untouched outside the region,
% (3) where the drawn region is untouched inside the region and all black outside the region.
% It also (4) calculates the mean intensity value and standard deviation of the image within that shape,
% (5) calculates the perimeter, centroid, and center of mass (weighted centroid), and
% (6) crops the drawn region to a new, smaller separate image.

% Change the current folder to the folder of this m-file.
if(~isdeployed)
  cd(fileparts(which(mfilename)));
end
clc;  % Clear command window.
clear;  % Delete all variables.
close all;  % Close all figure windows except those created by imtool.
imtool close all;  % Close all figure windows created by imtool.
workspace;  % Make sure the workspace panel is showing.
fontSize = 16;

% Read in a standard MATLAB gray scale demo image.
folder = fullfile(matlabroot, '\toolbox\images\imdemos');
baseFileName = 'cameraman.tif';
% 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);
imshow(grayImage, []);
axis on;
title('Original Grayscale Image', 'FontSize', fontSize);
set(gcf, 'Position', get(0,'Screensize')); % Maximize figure.
message = sprintf('Left click and hold to begin drawing.\nSimply lift the mouse button to finish');
uiwait(msgbox(message));
hFH = imfreehand();
% Create a binary image ("mask") from the ROI object.
binaryImage = hFH.createMask();
xy = hFH.getPosition;

% Now make it smaller so we can show more images.
subplot(2, 3, 1);
imshow(grayImage, []);
axis on;
drawnow;
title('Original Grayscale Image', 'FontSize', fontSize);

% Display the freehand mask.
subplot(2, 3, 2);
imshow(binaryImage);
axis on;
title('Binary mask of the region', 'FontSize', fontSize);

% Label the binary image and computer the centroid and center of mass.
labeledImage = bwlabel(binaryImage);
measurements = regionprops(binaryImage, grayImage, ...
    'area', 'Centroid', 'WeightedCentroid', 'Perimeter');
area = measurements.Area
centroid = measurements.Centroid
centerOfMass = measurements.WeightedCentroid
perimeter = measurements.Perimeter

% Calculate the area, in pixels, that they drew.
numberOfPixels1 = sum(binaryImage(:))
% Another way to calculate it that takes fractional pixels into account.
numberOfPixels2 = bwarea(binaryImage)

% Get coordinates of the boundary of the freehand drawn region.
structBoundaries = bwboundaries(binaryImage);
xy=structBoundaries{1}; % Get n by 2 array of x,y coordinates.
x = xy(:, 2); % Columns.
y = xy(:, 1); % Rows.
subplot(2, 3, 1); % Plot over original image.
hold on; % Don't blow away the image.
plot(x, y, 'LineWidth', 2);
drawnow; % Force it to draw immediately.

% Burn line into image by setting it to 255 wherever the mask is true.
burnedImage = grayImage;
burnedImage(binaryImage) = 255;
% Display the image with the mask "burned in."
subplot(2, 3, 3);
imshow(burnedImage);
axis on;
caption = sprintf('New image with\nmask burned into image');
title(caption, 'FontSize', fontSize);

% Mask the image and display it.
% Will keep only the part of the image that's inside the mask, zero outside mask.
blackMaskedImage = grayImage;
blackMaskedImage(~binaryImage) = 0;
subplot(2, 3, 4);
imshow(blackMaskedImage);
axis on;
title('Masked Outside Region', 'FontSize', fontSize);
% Calculate the mean
meanGL = mean(blackMaskedImage(binaryImage));
sdGL = std(double(blackMaskedImage(binaryImage)));

% Put up crosses at the centriod and center of mass
hold on;
plot(centroid(1), centroid(2), 'r+', 'MarkerSize', 30, 'LineWidth', 2);
plot(centerOfMass(1), centerOfMass(2), 'g+', 'MarkerSize', 20, 'LineWidth', 2);

% Now do the same but blacken inside the region.
insideMasked = grayImage;
insideMasked(binaryImage) = 0;
subplot(2, 3, 5);
imshow(insideMasked);
axis on;
title('Masked Inside Region', 'FontSize', fontSize);

% Now crop the image.
leftColumn = min(x);
rightColumn = max(x);
topLine = min(y);
bottomLine = max(y);
width = rightColumn - leftColumn + 1;
height = bottomLine - topLine + 1;
croppedImage = imcrop(blackMaskedImage, [leftColumn, topLine, width, height]);
% Display cropped image.
subplot(2, 3, 6);
imshow(croppedImage);
axis on;
title('Cropped Image', 'FontSize', fontSize);

% Put up crosses at the centriod and center of mass
hold on;
plot(centroid(1)-leftColumn, centroid(2)-topLine, 'r+', 'MarkerSize', 30, 'LineWidth', 2);
plot(centerOfMass(1)-leftColumn, centerOfMass(2)-topLine, 'g+', 'MarkerSize', 20, 'LineWidth', 2);

% Report results.
message = sprintf('Mean value within drawn area = %.3f\nStandard deviation within drawn area = %.3f\nNumber of pixels = %d\nArea in pixels = %.2f\nperimeter = %.2f\nCentroid at (x,y) = (%.1f, %.1f)\nCenter of Mass at (x,y) = (%.1f, %.1f)\nRed crosshairs at centroid.\nGreen crosshairs at center of mass.', ...
meanGL, sdGL, numberOfPixels1, numberOfPixels2, perimeter, ...
centroid(1), centroid(2), centerOfMass(1), centerOfMass(2));
msgbox(message);

[Shyme Bhate]

@Image Analyst, in your this above mentioned code of freehand, Is it possible that we freely select the specific part in exact color, no need to convert to binary and then cropped that. After crooping save both the part of images like 1:That we cropped and 2: The remaining image(without that cropped part) ?

Kindly pls help

[Shyme Bhate]

Error :::

Error using iptassert (line 19)

Size of I doesn't match size information found in the first input argument.

Error in regionprops>ParseInputs (line 1228)

iptassert(isequal(sizeImage,size(I)), ...

Error in regionprops (line 209)

[I,requestedStats,officialStats] = ParseInputs(imageSize, argOffset, args{:});

Error in freehand_masking_demo (line 66)

measurements = regionprops(binaryImage, grayImage, ..

[Image Analyst]

Shyme, I just copied and pasted it and it ran fine. How could your binary image possibly be a different size than the gray scale image? How did you alter it? Post your modified code. Also, you're using a version later than r2008b, right?

[Shyme Bhate]

No, on my case its not working properly, like see in the image it also includes the other part as well (the tiny micro bleed sky blue in color) Actually want to separate both the parts from on another and save separetly . But I am unble to do this

[Image Analyst]

The demo is made to work with a gray scale image, not a color image. Use rgb2gray() or else use the Color Thresholder app on the Apps tab of the tool ribbon.

[Shyme Bhate]

the original image was the gray scale image , the image attach here is actually. after run that code

[Shyme Bhate]

@Image Analyst, please help me in this issue, I am so worried. I just want to separate both the parts (tumorous and non-tumoros) from MRI and save separetly both parts.

[Image Analyst]

Why is your MRI image in color? MRI images are normally grayscale. Did you get one that was already marked up/annotated somehow? If so, make sure you get original gray scale images.

For an automatic method, see my attached example where it segments the tumor based on intensity.

Answer 3

[Ashutosh]

Umme, do you want to create a separate image with just the part within the circle and everything else as black?

[Umme Tania]

Yes but with white background

[Ashutosh]

No issues,

Do the following:

1) loop over all source image pixels 2) check F(X,Y)<0 to see if your pixel is inside the circle defined by equation F(X,Y)=0. 3) For all pixels for which isInsideCircle is true, copy source pixels, else fill a value 255;

Hope this is clear?

[Umme Tania]

I don't understand no.2...........can u please elaborate....

[Ashutosh]

put the coordinates of the point to the equation of a circle centred at a,b and test for values to be less than or equal to zero. The point within the circle will have a negative value for eqn.