How to cut out annular of this Image?

Hello,

i want to cut out everything but the annular in between the red circles and display that in an axes.

Heres the original image:

Answer 1

[Image Analyst]

The code below works for this image. Of course it may not work if you change the lighting, exposure, camera angle, F-stop, or clutter (other stuff) in the image, and would need adaptation for those cases.

% Code to analyze grinding wheel
clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clearvars;
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 16;

%=======================================================================================
% Read in image.
fullFileName = fullfile(pwd, 'annular_orig.jpg');
[folder, baseFileName, ext] = fileparts(fullFileName);
rgbImage = imread(fullFileName);
% Shrink it to speed it up
% rgbImage = imresize(rgbImage, 0.75);
% Get the dimensions of the image.
[rows, columns, numberOfColorChannels] = size(rgbImage);
% Display the original image.
subplot(2, 2, 1);
imshow(rgbImage, []);
axis on;
caption = sprintf('Original Color Image "%s"', baseFileName);
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
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')

% Get mask for outer gray, and inner blue parts of the wheel by doing color segmentations.
[wheelMask,maskedRGBImage] = createMaskForWholeWheel(rgbImage);
[blueMask,maskedRGBImage] = createMaskForBlueCenter(rgbImage);

% Clean up noise by filling holes and taking largest blob only.
wheelMask = imfill(wheelMask, 'holes');
wheelMask = bwareafilt(wheelMask, 1);
blueMask = imfill(blueMask, 'holes');
blueMask = bwareafilt(blueMask, 1);
% Display the images.
subplot(2, 2, 2);
imshow(wheelMask);
axis on;
title('Total Wheel Mask', 'FontSize', fontSize, 'Interpreter', 'None');
subplot(2, 2, 3);
imshow(blueMask);
axis on;
title('Blue Center Mask', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

% Get the ring mask
ringMask = wheelMask & ~blueMask;
% Display the image.
subplot(2, 2, 4);
imshow(ringMask);
axis on;
title('Ring Mask', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;

% Find boundaries
boundaries = bwboundaries(ringMask);

% Display the original image with mask boundary over it.
figure;
imshow(rgbImage, []);
axis on;
caption = sprintf('Color Image with Boundary');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo(); % Set up status line to see values when you mouse over the image.
% Plot boundaries
hold on;
numberOfBoundaries = size(boundaries, 1);
for k = 1 : numberOfBoundaries
  thisBoundary = boundaries{k};
  plot(thisBoundary(:,2), thisBoundary(:,1), 'r', 'LineWidth', 3);
end
hold off;

% Get the equivalent circular diameters.
propsWheel = regionprops(wheelMask, 'EquivDiameter');
wheelDiameter = propsWheel.EquivDiameter
propsBlue = regionprops(blueMask, 'EquivDiameter');
blueDiameter = propsBlue.EquivDiameter
% Get the area of the ring and put it up on the image.
ringArea = sum(ringMask(:));
message = sprintf('Area of ring = %d pixels.\nAverage Diameter of Entire Wheel = %.1f pixels.\nAverage Diameter of Blue Part = %.1f pixels.\nAverage Thickness of Edge = %.1f pixels.', ...
  ringArea, wheelDiameter, blueDiameter, wheelDiameter-blueDiameter);
text(20, 150, message, 'FontSize', fontSize, 'Color', 'y', 'FontWeight', 'bold', 'VerticalAlignment', 'top');

function [BW,maskedRGBImage] = createMaskForWholeWheel(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.

% Auto-generated by colorThresholder app on 15-Aug-2018
%------------------------------------------------------

% Convert RGB image to chosen color space
I = rgb2hsv(RGB);

% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.363;
channel1Max = 0.855;

% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.000;
channel2Max = 1.000;

% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.000;
channel3Max = 1.000;

% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
  (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
  (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;

% Initialize output masked image based on input image.
maskedRGBImage = RGB;

% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;

end

function [BW,maskedRGBImage] = createMaskForBlueCenter(RGB)
%createMask  Threshold RGB image using auto-generated code from colorThresholder app.
%  [BW,MASKEDRGBIMAGE] = createMask(RGB) thresholds image RGB using
%  auto-generated code from the colorThresholder app. The colorspace and
%  range for each channel of the colorspace were set within the app. The
%  segmentation mask is returned in BW, and a composite of the mask and
%  original RGB images is returned in maskedRGBImage.

% Auto-generated by colorThresholder app on 15-Aug-2018
%------------------------------------------------------

% Convert RGB image to chosen color space
I = rgb2hsv(RGB);

% Define thresholds for channel 1 based on histogram settings
channel1Min = 0.569;
channel1Max = 0.671;

% Define thresholds for channel 2 based on histogram settings
channel2Min = 0.229;
channel2Max = 1.000;

% Define thresholds for channel 3 based on histogram settings
channel3Min = 0.251;
channel3Max = 1.000;

% Create mask based on chosen histogram thresholds
sliderBW = (I(:,:,1) >= channel1Min ) & (I(:,:,1) <= channel1Max) & ...
  (I(:,:,2) >= channel2Min ) & (I(:,:,2) <= channel2Max) & ...
  (I(:,:,3) >= channel3Min ) & (I(:,:,3) <= channel3Max);
BW = sliderBW;

% Initialize output masked image based on input image.
maskedRGBImage = RGB;

% Set background pixels where BW is false to zero.
maskedRGBImage(repmat(~BW,[1 1 3])) = 0;

end

Answer 2

[Image Analyst]

Do you already have the (x,y) coordinates of the red circles you plotted? If so, you can just use polyarea().

Or do you not have that and need to do color segmentation to find the whole wheel and the gray outer part?

You should improve your image capture situation. The white background should fill the entire background and not have wood showing. Also you should use better lighting so that you don't have shadows.

[Nimos Sereth]

No, I just painted the circles using Paint to show what I was working on. I want to find the outer circle using color segmentation but I am not sure as to how to find the smaller one. The lighting condition may not get better, because ultimatly the grinding wheel will be put into the machine, where a consistent lighting cannot be garanteed.

I tried searching for a method whereby I could pick 3 points along the circumference and not worry about anything else, but so far I culdn't find a solution.

EDIT: I just found a way by getting the mouse coordinates and calculating the radius.

[Image Analyst]

This is a very easy project that any competent industrial machine vision company could do for you. Contact a local company and have them come over to your factory and inspect your setup.

[Nimos Sereth]

Sorry if this was unclear in my initial question, but the problem is not the calculation of the percentage but rather "How to delete everything but the space between the two red circles". I will chnage the initial question.

[Image Analyst]

It's easy but complicated somewhat by the fact that you're choosing not to use a big enough sheet of white paper. So what you need to do is first to identify the wood and make that white. You can use the color thresholder app to do that. Then use it again in HSV color space to find the gray outer ring, and the inner blue ring. Now you have two masks and can do whatever you want. Give it a try - it's not hard. Ask again if you tried but just can't figure it out.

[Nimos Sereth]

Thanks alot, I did it by using 3 points around the outer and inner circumference to establish two circles and then using a mask which only shows elements in bewtween the radii. Again thanks for your help!