MATLAB: Image normalization (same mean and same std)

image processingImage Processing Toolboxmatrix manipulationnormalization

Hello, How can i normalize two images (put then with the same mean and the same standart deviation) Thank you.

For an approximate match, try imhistmatch() to match the histograms of the two images. Otherwise, just do simple math, something like

newImage1 = (image1-mean1)*std2/std1 + mean2;

Hi Joe,

Maybe I miss understood what you were aiming for but try logical indexing.

img = imread('pout.tif');
h_im = imshow(img);
e = imellipse(gca,[55 10 120 120]);
BW = createMask(e,h_im);
imshow(BW)
std2(img)
std2(img(BW))

Does this give you what you were looking for?

The idea here is simple. std2(A) gives the same as as std(A(:))

But the important thing is if you only want part of A, use the logical indexing to get those numbers.

Simple example:

a = [1 2 3 4; 2 3 4 5; 2 3 4 4; 4 4 1 2]
BW=a>=3
a(BW)
std2(a(BW))

Hope this helps.

To calculate the mean of all pixels in the image, without regard to what color channel they came from (if it's a color image), you do

meanIntensity = mean(img(:));

What you did will not do it, as I'm sure you found out.