How to find the local mean of an image?

img   = imread('b.png');
img   = rgb2gray(img);
[m,n] = size(img);
img1  = padarray(img,[1,1],'both');
m=m+2;
n=n+2;
img2  = zeros(m,n);
for i=2:m-1
    for j=2:n-1
         img2(i,j) = uint64(img1(i+1,j)+img1(i+1,j-1)+img1(i+1,j+1)+img1(i,j-1)+img1(i,j+1)+img1(i-1,j-1)+img1(i-1,j)+img1(i-1,j+1)+img1(i,j))/9;        
    end
end
disp(img2);

I'm using this code, still its not giving mw the right answer.

[Alex Mcaulley]

What do you mean with local mean?

[SHILPI GUPTA]

Local mean: Average value of neighbourhood pixels' intensities in 3*3 window of an image. For every pixel, we have to take the mean of neighbourhood pixels' intensities.

[shelan naveed]

CAN YOU EXPLAIN IT WITH AN EXAMPLE PLEASE

[Rik]

@shelan naveed what exactly do you want an explanation of?

Answer 1

[Rik]

The fastest way to get a local average is to do a convolution with a flat structuring element:

%load example image
A=imread(['https://www.google.com/images/branding/googlelogo/',...
    '1x/googlelogo_color_272x92dp.png']);
A=rgb2gray(A);

%define flat 3x3 structuring element
SE=ones(3,3);SE=SE/sum(SE(:));
B=conv2(A,SE,'same');
B=uint8(B);%cast back to uint8, this will round values

figure(1)
subplot(1,2,1)
imshow(A)
title('original')
subplot(1,2,2)
imshow(B)
title('local mean')

[SHILPI GUPTA]

Thanks. It helped!