Comparing 2 images intensities

down votefavorite

I have two images 1 and 2. I want to get the v (intensity) value of the hsv images; then I want the v (intensity) value of the first image equal to v (intesity) value of the second image?

I used this code to get the v;

v = image1(:, :, 3);

u = image2(:, :, 3);

How do I make both u and v the same value?

Thanks

Answer 1

[Jeff E]

The code below will take the hue and saturation values from image1, and the value from image2, and merge them into one new image. Said another way, you are replacing the V signal from image1 with the V signal from image2.

new_image1 = cat(3, image1(:,:,1) , image1(:,:,2), image2(:,:,3));

Your last question "How do I make both u and v the same value?" doesn't make sense, to me.

[Ramo]

Its because i had two images of the same scene that are taken at different times, therefore the two images will have different intensities. So now i want to equalise their intesities so they look the same.

Answer 2

[Image Analyst]

Try something like this:

hsv1 = rgb2hsv(rgbImage1); % Convert to hsv color space.
hsv2 = rgb2hsv(rgbImage2); % Convert to hsv color space.
hsvOut = hsv1; % Initialize output array.
hsvOut(:,:,3) = hsv2(:,:,3);  % Replace intensity of 1 with 2
rgbOut = rgb2hsv(hsvOut); % convert back to rgb color space.

[Ramo]

I have tried this:

V1 = rgb2hsv(image1);

V2 = rgb2hsv(image2);

v1 = V1(:, :, 3);

v2 = V1(:, :, 3);

hsvOut = 0.5*(v1+ v2);

imshow(hsvOut)

%It wont convert back to rgb ?

rgbOut = hsv2rgb(hsvOut);

figure; imshow(rgbOut)

Thanks,

[Image Analyst]

Yeah, of course that won't work because hsvOut is not a 3D image. Plus v1 and v2 are both the same thing: the v channel of V1. Why did you not want to do what I suggested? Try it like I said instead.

[Ramo]

Your way doesnt work too!?

what about something like that:

y = rgb2hsv(base);
x = rgb2hsv(unregistered);
v1 = y(:,:,3);
v2 = x(:,:,3);

v3 = zeros(size(v1));
g = size(v1);
 x_axis = g(1);
 y_axis = g(2);
 for i = 1:x_axis,

       for j = 1:y_axis,
      v3(j) =0.5*( v1(j)+ v2(j));
       end 
   end 

   %to put the calculated value into the other matrix
   for k = 1:x_axis,

       for l = 1:y_axis,
           v1(l) = v3(j);
       end 
   end

   %putting the images together 

   final = zeros(x_axis, y_axis,3);
   final(:,:,1) = y(:,:,1);
   final(:,:,2) = y(:,:,2);
   final(:,:,3) = v1;

   %converting back to rgb 

final1 = hsv2rgb(final);
 figure; imshow(final1)

Thanks,

[Image Analyst]

You say

v3(j) =0.5*( v1(j)+ v2(j));

so you're not replacing 1 with 2, you're replacing 1 with the average of image 1 and 2, which is not what you originally asked, though it may be what you want.

[Ramo]

Thats true, because if the difference between the two intensities of the images are big then working the average would give you a better result (less noise too)- that's what I thought. However I wouldn't mind using either methods as long as it works!

[Image Analyst]

So are we done here? If so, please mark my answer as Accepted. Thanks.

[Ramo]

Your code didn't work though. however i voted you!