You may do this easily with the following code:

A = double(A); B = double(B);

d = sum((A(:)-B(:)).^2) / prod(size(A));

psnr = 10*log10(255*255/d);

Above code if very simplistic, however, You may visit my webpage in researchgate where I have a despeckle filtering toolbox as well as an image quality evalution toolbox in MATLAB to download. There are a lot functions available including psnr.

You may do this easily with the following code:

A = double(A); B = double(B);

d = sum((A(:)-B(:)).^2) / prod(size(A));

psnr = 10*log10(255*255/d);

Above code if very simplistic, however, You may visit my webpage in researchgate where I have a despeckle filtering toolbox as well as an image quality evalution toolbox in MATLAB to download. There are a lot functions available including psnr.

//Find MSE and then you can go for PSNR & SNR.

//For the gray image (0 to 255), convert both the image to double.

im1 = double(im1);

im2 = double(im2);

//Find the mean squared error

mse = sum((im1(:)-im2(:)).^2) / prod(size(im1));

// now find the psnr, as peak=255

psnr = 10*log10(255*255/mse);

//save this matlab function as mse_psnr.m

//To calculate PSNR follow instruction

function [mse,psnr] = mse_psnr(im1,im2)

// find the size of image1

N = size(im1);

//convert image into double

x=im2double(im1);

y=im2double(im2);

//Now calculate MSE then PSNR for a original and encrypted image

acc = 0;

for k1=1:N(1)

for k2=1:N(2)

acc = acc+ ( x(k1,k2) - y(k1,k2) )^2;

end

end

mse = acc/(N(1)*N(2));

//calculate psnr for the original and encrypted image

psnr = 10*log10((255^2)/mse);

find attachment

ref = imread('pout.tif');

A = imnoise(ref,'salt & pepper', 0.02);

[peaksnr, snr] = psnr(A, ref);

fprintf('\n The Peak-SNR value is %0.4f', peaksnr);

fprintf('\n The SNR value is %0.4f \n', sn

http://www.mathworks.com/help/images/ref/psnr.html#bt5uhgi-2_1

Will there be any difference in programming, while calculating the PSNR of a gray image with one band and a multispectral image with three or more bands? 

X = imread('Image Name');

Xapp = X;

Xapp(X

By using standard queation

function PSNR = psnr(distImg, origImg) origImg = double(origImg); distImg = double(distImg); [M N] = size(origImg); error = origImg - distImg; MSE = sum(sum(error .* error)) / (M * N); if(MSE > 0) PSNR = 10*log(255*255/MSE) / log(10); else PSNR = 99; end end

peaksnr = psnr(A,ref) calculates the peak signal-to-noise ratio for the image A, with the image ref as the reference. A and ref must be of the same size and class.

https://metacpan.org/pod/Math::PSNR

This will help

Suppose you have two images A and B of size mxn. Now write the following code:

for i=i:1:m

for j=1:1:n

P=power((A(i,j)-B(i,j)),2);

end

end

MSE=P/(m*n);

PSNR=10*log(255*255/MSE);