MATLAB: How to find the internal and external diameter of a oil seal that I’ve taken from the camera

image processingImage Processing Toolboximage segmentationmeasure external diametermeasure internal diameter

I've tried to get the internal and external diameters of a oil seal using following code.

% Read your image and binarize it
I = imread('E:\MINI PROJECT\images\WP_20180114_11_52_47_Selfie.jpg');
Igray = rgb2gray(I);
BW = imbinarize(Igray);
% Measure the outer radius
BWout = ~BW;
BWout = imfill(BWout,'holes');
statOuter = regionprops(BWout,{'EquivDiameter','Centroid'});
outerRadius = statOuter.EquivDiameter/2;
% Measure the inner radius
BWin = imclearborder(BW);
BWin = imopen(BWin, strel('disk',5)); % Remove noise
statInner = regionprops(BWin,{'EquivDiameter','Centroid'})
innerRadius = statInner.EquivDiameter/2;
% Show the result
figure
imshow(I)
hold on
viscircles(statOuter.Centroid, outerRadius,'Color','r')
viscircles(statInner.Centroid, innerRadius,'Color','r')

It gives answers only for some pictures but it didn't give an answer for following image

It gives this error

Error using  / 
Too many input arguments.

Best Answer

The problem is that your image capture conditions are so horrendous as to virtually preclude accurate measurements. Here are some tips:

Use a gray scale camera.
Use a uniform white background, not one all wavy and wrinkled.
Use uniform illumination, not one with bright and dark spots and gradients.
Use a light box that is white all around the interior to help get uniform illumination and eliminate shadows. Plans for cheap ones made from a cardboard box and white paint can be found on the internet.
You may need to use a telecentric lens if the object is not really flat.
Make sure the camera is directly overhead the center of the ring.
Take a shot of the background and divide your image by it to get rid of lens shading.
Put a standard in your image, like a white ceramic tile so you can multiply by a factor if the tile intensity does not match what it's supposed to be. For example if, in your "reference" image the tile is 220 gray levels, and for some test image it's 200, then you need to multiply your image by 220/200 to bring the intensity up to what it's supposed to be.
Use a camera with fixed, manual settings, not automatic settings that can change for any snapshot.

Due to your lousy initial image, the binarization process didn't find the proper threshold.

I've fixed your code to make it work with this image:

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 = 20;
%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = 'WP_20180114_11_52_47_Selfie.jpg';
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)
% Display image.
subplot(2, 3, 1);
imshow(rgbImage, []);
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;
% Convert to gray scale, but only if it's color, otherwise you'll get an error.
if numberOfColorChannels >= 3
  grayImage = rgb2gray(rgbImage);
else
  grayImage = rgbImage;
end
% Show histogram
subplot(2, 3, 2);
imhist(grayImage);
grid on;
drawnow;
title('Histogram of Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
% Binarize by thresholding.
% BW = imbinarize(grayImage);
thresholdGrayLevel = 90;
% Put a red line on the histogram there
hold on;
line([thresholdGrayLevel, thresholdGrayLevel], ylim, 'Color', 'r', 'LineWidth', 2);
BW = grayImage < thresholdGrayLevel;
% Display the image.


subplot(2, 3, 3);
imshow(BW, []);
axis on;
title('BinaryImage', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Take the largest blob only, to get rid of noise.

BW = bwareafilt(BW, 1);
% Fill holes to get final outer binary image.
BWout = imfill(BW, 'holes');
% Display the image.
subplot(2, 3, 4);
imshow(BWout, []);
axis on;
title('Outer BinaryImage', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Get measurements for outer ring.
statOuter = regionprops(BWout,{'EquivDiameter','Centroid'});
outerRadius = statOuter.EquivDiameter/2
% Find the inner radius
BWin = imclearborder(~BW);
% Take the largest blob only, to get rid of noise.
BWin = bwareafilt(BWin, 1);
% BWin = imopen(BWin, strel('disk', 5)); % Remove noise
% Display the image.
subplot(2, 3, 5);
imshow(BWin, []);
axis on;
title('Inner BinaryImage', 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
% Measure the inner radius
statInner = regionprops(BWin, 'EquivDiameter', 'Centroid')
innerRadius = statInner.EquivDiameter/2;
% Show the result
subplot(2, 3, 6);
imshow(rgbImage);
hold on
viscircles(statOuter.Centroid, outerRadius, 'Color', 'r')
viscircles(statInner.Centroid, innerRadius, 'Color', 'r')
message = sprintf('The inner radius = %.2f pixels.\nThe outer radius = %.2f pixels.', innerRadius, outerRadius);
title(message, 'FontSize', fontSize, 'Interpreter', 'None');
uiwait(helpdlg(message));

Related Solutions

MATLAB: How to find the internal and external radius of a ring using matlab image processing toolbox

By measuring the 'equivalent diameter' for each region, you can obtain the inner and outer radius. Here is an example.

% Read your image and binarize it
I = imread('Oil_Seal_Top_370003A__34285.1413827494.1280.1280.jpg');
Igray = rgb2gray(I);
BW = imbinarize(Igray);
% Measure the outer radius
BWout = ~BW;
BWout = imfill(BWout,'holes');
statOuter = regionprops(BWout,{'EquivDiameter','Centroid'});
outerRadius = statOuter.EquivDiameter/2;
% Measure the inner radius
BWin = imclearborder(BW);
BWin = imopen(BWin, strel('disk',5)); % Remove noise
statInner = regionprops(BWin,{'EquivDiameter','Centroid'})
innerRadius = statInner.EquivDiameter/2;
% Show the result
figure
imshow(I)
hold on
viscircles(statOuter.Centroid, outerRadius,'Color','r')
viscircles(statInner.Centroid, innerRadius,'Color','r')

The result is:

>> innerRadius
innerRadius =
278.8980
>> outerRadius
outerRadius =
374.5866

MATLAB: How to remove irregular shaped cells in this image

OK, here, try this, adjusting thresholding parameters as needed.

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 = 20;
% Check that user has the specified Toolbox installed and licensed.
hasLicenseForToolbox = license('test', 'image_toolbox');   % license('test','Statistics_toolbox'), license('test','Signal_toolbox')
if ~hasLicenseForToolbox
  % User does not have the toolbox installed, or if it is, there is no available license for it.
  % For example, there is a pool of 10 licenses and all 10 have been checked out by other people already.
  ver % List what toolboxes the user has licenses available for.
  message = sprintf('Sorry, but you do not seem to have the Image Processing Toolbox.\nDo you want to try to continue anyway?');
  reply = questdlg(message, 'Toolbox missing', 'Yes', 'No', 'Yes');
  if strcmpi(reply, 'No')
    % User said No, so exit.
    return;
  end
end
%===============================================================================
% Read in gray scale demo image.
folder = pwd; % Determine where demo folder is (works with all versions).
baseFileName = 'image.png';
% Get the full filename, with path prepended.
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
rgbImage = imread(fullFileName);
% Display the image.





subplot(2, 2, 1);
imshow(rgbImage, []);
title('Original Image', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;
hp = impixelinfo();
% Get the dimensions of the image.  
% numberOfColorChannels should be = 1 for a gray scale image, and 3 for an RGB color image.
[rows, columns, numberOfColorChannels] = size(rgbImage);
if numberOfColorChannels > 1
  % It's not really gray scale like we expected - it's color.
  % Use weighted sum of ALL channels to create a gray scale image.
%   grayImage = rgb2gray(rgbImage); 
  % ALTERNATE METHOD: Convert it to gray scale by taking only the green channel,
  % which in a typical snapshot will be the least noisy channel.
  grayImage = rgbImage(:, :, 1); % Take red channel.
else
  grayImage = rgbImage; % It's already gray scale.
end
% Display the image.
subplot(2, 2, 1);
imshow(grayImage, []);
title('Gray Scale Image', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;
%------------------------------------------------------------------------------
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0.04, 1, 0.96]);
% 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 binary image.
binaryImage = grayImage > 10;
% Get rid of white frame.
binaryImage = imclearborder(binaryImage);
% Display the image.
subplot(2, 2, 1);
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;
% Fill holes
binaryImage = imfill(binaryImage, 'holes');
% Display the image.
subplot(2, 2, 2);
imshow(binaryImage, []);
title('Binary Image', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;
% Let's measure things to see what we're starting with.
props = regionprops(binaryImage, 'Solidity', 'Area', 'perimeter');
allAreas = [props.Area]
allSolidities = [props.Solidity]
allCircularities = 4 * pi * allAreas ./ [props.Perimeter] .^ 2
% Display the histograms.
subplot(2, 2, 3);
histogram(allSolidities);
grid on;
title('Histogram of Solidities', 'FontSize', fontSize, 'Interpreter', 'None');
subplot(2, 2, 4);
histogram(allCircularities);
grid on;
title('Histogram of circularities', 'FontSize', fontSize, 'Interpreter', 'None');
% Take the 24 smoothest blobs.
% Get rid of blobs less solid than 0.85%.
binaryImage2 = bwpropfilt(binaryImage, 'Solidity', [.85, inf]);
figure;
% Display the image.
subplot(2, 1, 1);
imshow(binaryImage2, []);
title('Binary Image2 - high solidity', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;
% Get rid of blobs with low circularity.
highCircularityIndexes = find(allCircularities > 0.6);
labeledImage = bwlabel(binaryImage);
binaryImage3 = ismember(labeledImage, highCircularityIndexes);
% Display the image.
subplot(2, 1, 2);
imshow(binaryImage3, []);
title('Binary Image3 - high circularity', 'FontSize', fontSize, 'Interpreter', 'None');
axis on;

Best Answer

Related Solutions

MATLAB: How to find the internal and external radius of a ring using matlab image processing toolbox

MATLAB: How to remove irregular shaped cells in this image

Related Question