I want to stretch an elliptical object in an image until it forms a circle. My program currently inputs an image with an elliptical object (eg. coin at an angle), thresholds and binarizes it, isolates the region of interest using edge-detect/bwboundaries(), and performs regionprops() to calculate major/minor axis lengths.
Essentially, I want to use the 'MajorAxisLength' as the diameter and stretch the object on the minor axis to form a circle. Any suggestions on how I should approach this would be greatly appreciated. I have appended some code for your perusal (unfortunately I don't have enough reputation to upload an image, the binarized image looks like a white ellipse on a black background).
EDIT: I'd also like to apply this technique to the gray-scale version of the image, to examine what the stretch looks like.
code snippet:
rgbImage = imread(fullFileName);
redChannel = rgbImage(:, :, 1);
binaryImage = redChannel < 90;
labeledImage = bwlabel(binaryImage);
area_measurements = regionprops(labeledImage,'Area');
allAreas = [area_measurements.Area];
biggestBlobIndex = find(allAreas == max(allAreas));
keeperBlobsImage = ismember(labeledImage, biggestBlobIndex);
measurements = regionprops(keeperBlobsImage,'Area','MajorAxisLength','MinorAxisLength')
You know the diameter of the circle and you know the center is the location where the major and minor axes intersect. Thus, just compute the radius r from the diameter, and for every pixel in your image, check to see if that pixel's Euclidean distance from the cirlce's center is less than r. If so, color the pixel white. Otherwise, leave it alone.
[M,N] = size(redChannel);
new_image = zeros(M,N);
for ii=1:M
for jj=1:N
if( sqrt((jj-center_x)^2 + (ii-center_y)^2) <= radius )
new_image(ii,jj) = 1.0;
end
end
end
This can probably be optimzed by using the meshgrid function combined with logical indices to avoid the loops.
I finally managed to figure out the transform required thanks to a lot of help on the matlab forums. I thought I'd post it here, in case anyone else needed it.
stats = regionprops(keeperBlobsImage, 'MajorAxisLength','MinorAxisLength','Centroid','Orientation');
alpha = pi/180 * stats(1).Orientation;
Q = [cos(alpha), -sin(alpha); sin(alpha), cos(alpha)];
x0 = stats(1).Centroid.';
a = stats(1).MajorAxisLength;
b = stats(1).MinorAxisLength;
S = diag([1, a/b]);
C = Q*S*Q';
d = (eye(2) - C)*x0;
tform = maketform('affine', [C d; 0 0 1]');
Im2 = imtransform(redChannel, tform);
subplot(2, 3, 5);
imshow(Im2);
Related
so I am working for my disertation thesis and I have to detect the pupil from images using Hough Transform. So far I wrote a code that identifies 2 circles on my image, but right now I have to keep the black circle from the pupil.
When I run the code, it identifies me the pupil, but also a random circle on the cheek. My professor said that I should calculate the pixels mean and, considering the fact that the pupil is black, to keep the pixels from only that region. I don't know how to do this.
I will let my code here to have a look and if someone has an ideea on how should I write this and keep only the black pixels would be great. I also attached to this the final image to see what I obtained.
close all
clear all
path='C:\Users\Ioana PMEC\OneDrive\Ioana personal\Disertatie\test.jpg';
%Citire imagine initiala
xx = imread(path);
figure
imshow(xx)
title('Imagine initiala');% Binarizarea imaginii initiale
yy = rgb2gray(xx);
figure
imshow(yy);
title('Imagine binarizata');
e = edge(yy, 'canny');
imshow(e);
radii = 11:1:30;
h = circle_hough(e, radii, 'same', 'normalise');
peaks = circle_houghpeaks(h, radii, 'nhoodxy', 15, 'nhoodr', 21, 'npeaks', 2);
imshow(yy);
hold on;
for peak = peaks
[x, y]=circlepoints(peak(3));
plot(x+peak(1), y+peak(2), 'r-');
end
hold off
testimage
finalimage
I implemented something which should get the task done for you. The example is done with the image you provided.
Step 1: Read the file(s) and convert them to grayscale.
path = %user input;
RGB = imread(path);
lab = rgb2lab(RGB);
grayscale_image = rgb2gray(RGB);
Step 2: Do the Hough transformation with given parameters.
These, and also the sensitivity can be adapted according to your task. Hint: Play around in the Image Segmenter toolbox for fast parameter finding. Next, the inferred circles are converted to integer values, since these are required for indexing.
min_radius = 10;
max_radius = 50;
% Find circles
[centers,radii,~] = imfindcircles(RGB,[min_radius max_radius],'ObjectPolarity','dark','Sensitivity',0.95);
centers = uint16(centers);
radii = uint16(radii);
The annotated image appears as follows:
Step 3: Get the brightness values of the circles.
From the circle center and radius values, we infer their respective brightness. It is sufficient to only check for the x and y pixel values left/right and above/below the center. (-1 is just a safety margin to completely stay within the circles.)
brightness_checker = zeros(2, max(radii), 2);
for i=1:size(centers,1)
current_radii = radii(i)-1;
for j=1:current_radii
% X-center minus radius, step along x-axis
brightness_checker(i, j, 1) = grayscale_image((centers(i,2) - current_radii/2) + j,...
(centers(i,1) - radii(i)/2) + j);
% Y-center minus radius, step along y-axis
brightness_checker(i, j, 2) = grayscale_image((centers(i,2) - current_radii/2) + j,...
(centers(i,1) - current_radii/2) + j);
end
end
Step 4: Check which circle is a pupil.
The determined value of 30 could potentially be enhanced.
median_x = median(brightness_checker(:,:,1),2);
median_y = median(brightness_checker(:,:,2),2);
is_pupil = (median_x<30)&(median_y<30);
pupils_center = centers(is_pupil == true,:);
Step 5: Draw the pupils.
The marker can be changed. Refer to:
https://de.mathworks.com/help/matlab/ref/matlab.graphics.chart.primitive.line-properties.html
figure
imshow(grayscale_image);
hold on
plot(centers(:,1), centers(:,2), 'r+', 'MarkerSize', 20, 'LineWidth', 2);
hold on
plot(pupils_center(:,1), pupils_center(:,2), 'b+', 'MarkerSize', 20, 'LineWidth', 2);
This is the final output:
This is the problem I have: I have an image as shown below. I want to detect the circular region which I have marked with a red line for display here (that particular bright ring).
Initially, this is what I do for now: (MATLAB)
binaryImage = imdilate(binaryImage,strel('disk',5));
binaryImage = imfill(binaryImage, 'holes'); % Fill holes.
binaryImage = bwareaopen(binaryImage, 20000); % Remove small blobs.
binaryImage = imerode(binaryImage,strel('disk',300));
out = binaryImage;
img_display = immultiply(binaryImage,rgb2gray(J1));
figure, imshow(img_display);
The output seems to be cut on one of the parts of the object (for a different image as input, not the one displayed above). I want an output in such a way that it is symmetric (its not always a perfect circle, when it is rotated).
I want to strictly avoid im2bw since as soon as I binarize, I lose a lot of information about the shape.
This is what I was thinking of:
I can detect the outer most circular (almost circular) contour of the image (shown in yellow). From this, I can find out the centroid and maybe find a circle which has a radius of 50% (to locate the region shown in red). But this won't be exactly symmetric since the object is slightly tilted. How can I tackle this issue?
I have attached another image where object is slightly tilted here
I'd try messing around with the 'log' filter. The region you want is essentially low values of the 2nd order derivative (i.e. where the slope is decreasing), and you can detect these regions by using a log filter and finding negative values. Here's a very basic outline of what you can do, and then tweak it to your needs.
img = im2double(rgb2gray(imread('wheel.png')));
img = imresize(img, 0.25, 'bicubic');
filt_img = imfilter(img, fspecial('log',31,5));
bin_img = filt_img < 0;
subplot(2,2,1);
imshow(filt_img,[]);
% Get regionprops
rp = regionprops(bin_img,'EulerNumber','Eccentricity','Area','PixelIdxList','PixelList');
rp = rp([rp.EulerNumber] == 0 & [rp.Eccentricity] < 0.5 & [rp.Area] > 2000);
bin_img(:) = false;
bin_img(vertcat(rp.PixelIdxList)) = true;
subplot(2,2,2);
imshow(bin_img,[]);
bin_img(:) = false;
bin_img(rp(1).PixelIdxList) = true;
bin_img = imfill(bin_img,'holes');
img_new = img;
img_new(~bin_img) = 0;
subplot(2,2,3);
imshow(img_new,[]);
bin_img(:) = false;
bin_img(rp(2).PixelIdxList) = true;
bin_img = imfill(bin_img,'holes');
img_new = img;
img_new(~bin_img) = 0;
subplot(2,2,4);
imshow(img_new,[]);
Output:
Just a quick question. I've an image and I've extracted a certain point (feature), I know the coordinates of that point in every frame.
Say x1 and y1.
I need a circular ROI form that point on the image with a radius that I chose.
I tried impoly and roipoly - not sure how to use either of these when I know the point in the image.
Thanks
Since you know the coordinates of the center of the ROI along with the radius, you can modify a bit the code provided by #Jonas here to create a circular mask in a quite efficient way.
Example:
clc;clear
Im = imread('coins.png');
[rNum,cNum,~] = size(Im);
%// Define coordinates and radius
x1 = 60;
y1 = 100;
radius = 40;
%// Generate grid with binary mask representing the circle. Credit to Jonas for original code.
[xx,yy] = ndgrid((1:rNum)-y1,(1:cNum)-x1);
mask = (xx.^2 + yy.^2)<radius^2;
%// Mask the original image
Im(mask) = uint8(0);
imshow(Im)
Output:
EDIT
If you want to see only the outer edge of the ROI to see the center, add a logical condition with some tolerance for the radius of a smaller circle. Something like this:
mask = (xx.^2 + yy.^2)<radius^2 & (xx.^2 + yy.^2)>(radius-tol)^2;
With a tol of 2 it looks like this:
I'm extracting the outline of blob the following way:
bw = im2bw(image, threshold);
boundaries = bwboundaries(bw);
plot(boundaries(:, 2), boundaries(:, 1), 'k', 'LineWidth', 2);
what I would like to do now, is to scale boundaries so that I can plot a smaller version of the boundaries inside the original boundaries. Is there an easy way to do this?
Here's an example on what the result should look like: black is the original bounding box, and red is the same bounding box, just scaled (but with same center as black box).
EDIT:
I guess I can scale each point individually, but then I still have to recenter the coordinates. Is there a better way of doing this?
scale = 0.7
nbr_points = size(b, 1);
b_min = nan(nbr_points, 2);
for k = 1 : nbr_points
b_min(k, :) = ([scale 0; 0 scale] * b(k, 1:2)')';
end
Just creating a function which does this should be easy.
function scaledB = scaleBoundaries(B,scaleFactor)
% B is a cell array of boundaries. The output is a cell array
% containing the scaled boundaries, with the same center of mass
% as the input boundaries.
%%
for k = 1:length(B)
scaledB{k} = B{k} .* scaleFactor;
com = mean(B{k}); % Take the center of mass of each boundary
sCom = mean(scaledB{k}); % Take the center of mass of each scaled boundary
difference = com-sCom; % Difference between the centers of mass
% Recenter the scaled boundaries, by adding the difference in the
% centers of mass to the scaled boundaries:
scaledB{k}(:,1) = scaledB{k}(:,1) + difference(1);
scaledB{k}(:,2) = scaledB{k}(:,2) + difference(2);
end
end
Or did you want to avoid something unoptimized for speed purposes?
I have two images. One is the original, and the another is rotated.
Now, I need to discover the angle that the image was rotated. Until now, I thought about discovering the centroids of each color (as every image I will use has squares with colors in it) and use it to discover how much the image was rotated, but I failed.
I'm using this to discover the centroids and the color in the higher square in the image:
i = rgb2gray(img);
bw = im2bw(i,0.01);
s = regionprops(bw,'Centroid');
centroids = cat(1, s.Centroid);
colors = impixel(img,centroids(1),centroids(2));
top = max(centroids);
topcolor = impixel(img,top(1),top(2));
You can detect the corners of one of the colored rectangles in both the image and the rotated version, and use these as control points to infer the transformation between the two images (like in image registration) using the CP2TFORM function. We can then compute the angle of rotation from the affine transformation matrix:
Here is an example code:
%# read first image (indexed color image)
[I1 map1] = imread('http://i.stack.imgur.com/LwuW3.png');
%# constructed rotated image
deg = -15;
I2 = imrotate(I1, deg, 'bilinear', 'crop');
%# find blue rectangle
BW1 = (I1==2);
BW2 = imrotate(BW1, deg, 'bilinear', 'crop');
%# detect corners in both
p1 = corner(BW1, 'QualityLevel',0.5);
p2 = corner(BW2, 'QualityLevel',0.5);
%# sort corners coordinates in a consistent way (counter-clockwise)
p1 = sortrows(p1,[2 1]);
p2 = sortrows(p2,[2 1]);
idx = convhull(p1(:,1), p1(:,2)); p1 = p1(idx(1:end-1),:);
idx = convhull(p2(:,1), p2(:,2)); p2 = p2(idx(1:end-1),:);
%# make sure we have the same number of corner points
sz = min(size(p1,1),size(p2,1));
p1 = p1(1:sz,:); p2 = p2(1:sz,:);
%# infer transformation from corner points
t = cp2tform(p2,p1,'nonreflective similarity'); %# 'affine'
%# rotate image to match the other
II2 = imtransform(I2, t, 'XData',[1 size(I1,2)], 'YData',[1 size(I1,1)]);
%# recover affine transformation params (translation, rotation, scale)
ss = t.tdata.Tinv(2,1);
sc = t.tdata.Tinv(1,1);
tx = t.tdata.Tinv(3,1);
ty = t.tdata.Tinv(3,2);
translation = [tx ty];
scale = sqrt(ss*ss + sc*sc);
rotation = atan2(ss,sc)*180/pi;
%# plot the results
subplot(311), imshow(I1,map1), title('I1')
hold on, plot(p1(:,1),p1(:,2),'go')
subplot(312), imshow(I2,map1), title('I2')
hold on, plot(p2(:,1),p2(:,2),'go')
subplot(313), imshow(II2,map1)
title(sprintf('recovered angle = %g',rotation))
If you can identify a color corresponding to only one component it is easier to:
Calculate the centroids for each image
Calculate the mean of the centroids (in x and y) for each image. This is the "center" of each image
Get the red component color centroid (in your example) for each image
Subtract the mean of the centroids for each image from the red component color centroid for each image
Calculate the ArcTan2 for each of the vectors calculated in 4), and subtract the angles. That is your result.
If you have more than one figure of each color, you need to calculate all possible combinations for the rotation and then select the one that is compatible with the other possible rotations.
I could post the code in Mathematica, if you think it is useful.
I would take a variant to the above mentioned approach:
% Crude binarization method to knock out background and retain foreground
% features. Note one looses the cube in the middle
im = im > 1
Then I would get the 2D autocorrelation:
acf = normxcorr2(im, im);
From this result, one can easily detect the peaks, and as rotation carries into the autocorrelation function (ACF) domain, one can ascertain the rotation by matching the peaks between the original ACF and the ACF from the rotated image, for example using the so-called Hungarian algorithm.