MATLAB Answers


help with edge processing in an image.

Asked by mounim
on 19 Dec 2012

HeY everyone

i hope someone can help me with a project, what i am trying to do is calculating the angle between 2 bones. I already got some help with drawing the axis of the bones from this forum. but as you can see, in the the bottom part i have 2 bones, what can do to only get the axis through the thicker bone ( i only want to define the edge of the thicker bone )? anyhelp will be appreciated, thanks

close all;
imtool close all;
fontSize = 20;
grayImage = imread('6.jpg');
% Get the dimensions of the image.  
% numberOfColorBands should be = 1.
[rows columns numberOfColorBands] = size(grayImage)
% Convert to grayscale
if numberOfColorBands > 1
	grayImage = grayImage(:, :, 2);
% Crop away white boundary
%grayImage = grayImage(1:840, 1:450);
% Binarize the image
binaryImage = grayImage > 128;
% Display the original gray scale image.
% subplot(2, 2, 1);
imshow(grayImage, []);
% for loop to define the range of interest for the bone 1
for k=30:100
     oneRow = binaryImage(k, :);
     leftEdge = find(oneRow, 1, 'first');
     rightEdge = find(oneRow, 1, 'last');
     hold on;
     midpoints(k) = (leftEdge + rightEdge)/2;
     plot(leftEdge, k, 'rx','LineWidth',2);
     plot(rightEdge, k, 'rx','LineWidth',2)
     plot(midpoints(k), k, 'yx','LineWidth',2);
new_x = linspace(1, 400);
coeffs = polyfit(X, midpoints, 1);
new_y = polyval(coeffs, new_x);
plot(new_y,new_x, '-','LineWidth',2);
% for loop to define the range of interest for the bone 1
for i=700:800
     oneRow1 = binaryImage(i, :);
     leftEdge1 = find(oneRow1, 1, 'first');
     rightEdge1 = find(oneRow1, 1, 'last');
     hold on;
if isempty(leftEdge1)
   midpoint1(i) = 0;
   midpoints1(i) = (leftEdge1 + rightEdge1)/2;
     plot(leftEdge1, i, 'rx','LineWidth',2);
     plot(rightEdge1, i, 'rx','LineWidth',2);
     plot(midpoints1(i), i, 'yx','LineWidth',2);
new_x1 = linspace(500, 900);
coeffs1 = polyfit(X1, midpoints1, 1);
new_y1 = polyval(coeffs1, new_x1);
plot(new_y1,new_x1, '-','LineWidth',2);
Femur = abs(atand(coeffs(1)));
Tibia = abs(atand(coeffs1(1)));
Angle = Femur + Tibia;
title(Angle , 'FontSize', fontSize);


2 Answers

Answer by Image Analyst
on 20 Dec 2012
 Accepted answer

You have to threshold the lower part of your image to detect the bones. Then scan each line and determine if there are two big sections, or just one. If there are two, take just the biggest one.


Answer by mounim
on 20 Dec 2012

please anyone ?


Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply today