No, not unless you can get the original gray scale image. You can't do it from a pseudocolored image. If you have the gray scale image, do this
- subtract the mean: grayImage = double(grayImage) - mean2(grayImage);
- take the fft2: FT = fft2(grayImage)
Something like:
grayImage = imread('cameraman.tif');
subplot(2, 2, 1);
imshow(grayImage, []);
title('Original Image', 'FontSize', 20);
grayImage = double(grayImage) - mean2(grayImage);
% Take the FFT.
FT = fft2(grayImage);
% Display the phase image.
subplot(2, 2, 2);
imagImage = imag(FT);
imshow(log(imagImage), [])
title('Imaginary part of FT Image', 'FontSize', 20);
% Display the magnitude image.
subplot(2, 2, 3);
realImage = real(FT);
imshow(log(realImage), [])
title('Real Part of FT Image', 'FontSize', 20);
