How do I use image processing to determine the length of an object in an image?

I have two images, each with a white object of different lengths on a black background. I know the starting length but I need to calculate the final length using image processing. I have attached the images and the histograms. Is there a way of using MatLab to calculate the length of the two images or should I work out the difference in length of the two?

EDIT: Since posting this I have began my experiments. The actual images I am trying to process are the tyres with white stripes on them. The white stripes skew and increase in length in y but all I am interested in is the length in x direction

Answer 1

[Image Analyst]

See if this works for you. It assumes vertical white blob stripe.

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 short g;
format compact;
fontSize = 25;

%===============================================================================
% Get the name of the image the user wants to use.
baseFileName = '1k_100kph_10x5mm.JPG';
baseFileName = '1k_100kph_5x20mm.JPG';
% Get the full filename, with path prepended.
folder = []; % Determine where demo folder is (works with all versions).
fullFileName = fullfile(folder, baseFileName);

%===============================================================================
% Read in a demo image.
grayImage = imread(fullFileName);
% 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(grayImage)
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(grayImage);
  % 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 = grayImage(:, :, 2); % Take green channel.
end
% Display the image.
subplot(2, 2, 1);
imshow(grayImage, []);
axis on;
axis image;
caption = sprintf('Original Gray Scale Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo();

% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0, 0, 1, 1]);
% 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;

% binarize the image.
binaryImage = imbinarize(grayImage); 
% Make sure there is only one blob
binaryImage = bwareafilt(binaryImage, 1);
% Display the image.
subplot(2, 2, 2);
imshow(binaryImage, []);
axis on;
axis image;
caption = sprintf('Binary Image');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo();

% Label the image
labeledImage = bwlabel(binaryImage);
% Make measurements of bounding box
props = regionprops(labeledImage, 'BoundingBox');
width = props.BoundingBox(3);
height = props.BoundingBox(4);
% Display it with the box overlaid on it.
subplot(2, 2, 3);
imshow(grayImage, []);
axis on;
axis image;
caption = sprintf('Gray Scale Image with box overlaid');
title(caption, 'FontSize', fontSize, 'Interpreter', 'None');
drawnow;
hp = impixelinfo();
hold on;
rectangle('Position', props.BoundingBox, 'EdgeColor', 'r', 'LineWidth', 2);
message = sprintf('The width = %f.\nThe height = %f', width, height);
uiwait(helpdlg(message));

If you want the box to be taller, then we'll have to fiddle with imbinarize, or preprocess the image, or come up with another algorithm.

[Malcolm Armstrong]

Thank you very much! I appreciate your help! :)

[Jay Mehta]

What changes should I make to the above code to make it usable for 'n' number of blobs?

And

would you please explain this part of the code once again?

the part

props = regionprops(labeledImage, 'BoundingBox'); width = props.BoundingBox(3); height = props.BoundingBox(4);

I did play with the numbers 3 and 4. When I increased the 3 to 5 the code gave an error ("Index exceeds matrix dimensions"), which I did not understand completely. I understood that the matrix of the image that we have max chosen in the code above is a 4x4 matrix hence anything above this values gives an error. But I did not find any declaration or initialization of any such matrix ... as we are just using [] which I assume to accommodate the max possible matrix that can be formed by the image that we choose.

Hoping to get my concepts clear.

Regards, Conceptuality. JM

[K G V Kalyan Sreenivas Kumar]

In which units are the answers in??

I need units of the object to be in mm. how can i do that?

Answer 2

[Khyati Savakia]

You can use "regionprops" function with "BoundingBox" property to find the rectangle containing the white object.

For instance: if you have an image BW, stats = regionprops(BW,'BoundingBox'); This would return the x and y coordinates along with width and height of the white object.

MATLAB Documentation: https://www.mathworks.com/help/images/ref/regionprops.html

[Malcolm Armstrong]

Ok Thank you very much I will give this a try! :)

[Image Analyst]

Won't work if the parts are each rotated by a different angle.

[Malcolm Armstrong]

The images I posted were just an example at the time I posted this. I am actually trying to detect stripes of white paint on a moving tyre. The images blur due to the fast moving tyre but all I'm interested in is the length in the x direction.

Answer 3

[Chukwuebuka Ubah]

Please, I need a code that will help me get the waist and Hip circumference from an image or from camera directly. I would appreciate it.

Please help me