Image Processing Min/Max filter

Hi,

i'm trying to execute a min/max filtering of an image but i'm meeting some problems. The filter consist in calculating the upper and lower envelope. In particularly for the upper envelop (Ue) i substituted for every pixel the max value in a 3X3-pixel neighborhood, and for the lower envelop (Le) the min value. Finally i calculated the filtered image

Im = (Im - Le) ./ (Ue -Le);

but the result is not correct in my opinion. I think the problem is in the the conversion of the format image because i don't well understand the difference between the commands "im2double" and "double".

This is the code

Im = imread('image.bmp');
Im = im2double(Im);

    [r c] = size(Im);

    ImL = zeros(r,c);
    ImU = zeros(r,c);

    for i=2:r-1

        for j=2:c-1

            M = Im(i-1:i+1,j-1:j+1);

            Min = min(M(:));
            Max = max(M(:));

            ImL(i,j) = Min;
            ImU(i,j) = Max;

        end

    end

    AirF = (Air-AirL)./(AirU-AirL);

    AirF = im2uint8(AirF);

Thanks for help

Answer 1

[Alex Taylor]

If you have the image processing toolbox, imerode and imdilate are the min/max filters you are looking for and are much faster than rolling these yourself.

[Marco Rossi]

Thanks for the answer; i didn't know the commands you mentioned, but i'd prefer to implement by myself