How to eliminate uneven illumination from an imgae with respect to another image?

One of my approach is like this. I am not sure about this approach

    1) There are two images im1 and im2. Extract the R G B content of im1.
    2)Calculate the normalized value for each content
    3)Reform a color image.
    4)Repeat the process for im2
    5)Compare each pixel and replace the content of im2 with im1.

I tried to normalize one of the image but didn't get a good output

Image_rgb = imread('aswathy_33_crop.jpg');
Image_rgb = double(Image_rgb);
figure;imshow(uint8(Image_rgb));

    Image_red = Image_rgb(:,:,1);
  Image_green = Image_rgb(:,:,2);
  Image_blue = Image_rgb(:,:,3);

   [row,col] = size(Image_rgb(:,:,1));

   for y = 1:row 
      for x = 1:col 
     Red = Image_red(y,x);
     Green = Image_green(y,x);
     Blue = Image_blue(y,x);

      if(Red == 0 && Green==0 && Blue==0)
          Red = 1;
          Green = 1;
          Blue = 1;
      end

        NormalizedRed = Red/(Red + Green + Blue);
        NormalizedGreen = Green/(Red + Green + Blue);
        NormalizedBlue = Blue/(Red + Green + Blue);

   Image_red(y,x) = NormalizedRed;
   Image_green(y,x) = NormalizedGreen;
   Image_blue(y,x) = NormalizedBlue;
     end
  end
  Image_rgb(:,:,1) = Image_red;
  Image_rgb(:,:,2) = Image_green;
  Image_rgb(:,:,3) = Image_blue;

     new_image1 = cat(3, Image_rgb(:,:,1) ,Image_rgb(:,:,2), Image_rgb(:,:,3));

     figure; imshow(uint8(255*new_image1));

[B.k Sumedha]

What do u mean by good output?

[aswathy nair]

@Bk Sumedha. I have posted the input and output images

[B.k Sumedha]

k try addig this

Image_rgb = Image_rgb .* Image_rgb;

[B.k Sumedha]

And also i didnt find any images here:(

[aswathy nair]

Sorry I forgot to save the edit. Can you please suggest me whether my approach is correct or not based on my question.

Answer 1

[B.k Sumedha]

Image=imread('aswathy_33_crop.jpg');  
Image_rgb =Image;
  Image_rgb = imresize(Image_rgb, [400 400]);
  Image_rgb = double(Image_rgb);
  %figure;imshow(uint8(Image_rgb));

    Image_red = Image_rgb(:,:,1);
    Image_green = Image_rgb(:,:,2);
    Image_blue = Image_rgb(:,:,3);
    %figure;imshow(uint8(Image_red));

    [row,col] = size(Image_rgb(:,:,1));

    for y = 1:row %-->numberof rows in image
       for x = 1:col %-->number of columns in the image
          Red = Image_red(y,x);
          Green = Image_green(y,x);
          Blue = Image_blue(y,x);

        NormalizedRed = Red/sqrt(Red^2 + Green^2 + Blue^2);
        NormalizedGreen = Green/sqrt(Red^2 + Green^2 + Blue^2);
        NormalizedBlue = Blue/sqrt(Red^2 + Green^2 + Blue^2);

        Image_red(y,x) = NormalizedRed;
        Image_green(y,x) = NormalizedGreen;
        Image_blue(y,x) = NormalizedBlue;
       end
    end

    Image_rgb(:,:,1) = Image_red;
    Image_rgb(:,:,2) = Image_green;
    Image_rgb(:,:,3) = Image_blue;

    Image_rgb = Image_rgb .* Image_rgb;
  imshow(Image_rgb);

Try with this

Answer 2

[Image Analyst]

No, that won't do it. And I don't know what you mean by with respect to another image. The best way to flatten out an image to "undo" the non-uniform illumination is to snap an image of a uniform white or gray sheet and then convert this to a "percentage" image where each pixel is the percentage of the max gray level in the image. Then take your sample/test image and divide it by the percentage image. This will make it as if every pixel in your image had the same illumination (exposure) as the brightest pixel in your image.

See attached demos.

Another good way to flatten out the non-uniform illumination, if you don't have an image of a blank, uniform scene, is to call adapthisteq. It is less optimal than the way where you divide by the blank shot.