And watch out for the titles that are not 28 x 28. This code does not assume that the image is an exact integer multiple of 28 in each direction, and it does not throw away any partial blocks.
Now image_blocks{J,K} will be the 1 x 1 block corresponding to the pixel at TheImage{J,K}
I cannot think of any advantage of dividing into 1 x 1 blocks, unless perhaps it is for convenience in holding the bit equivalent as a unit ? But if that is the situation then
Best Answer