The hit-and-miss transform is a general binary (only) morphological
operation that can be used to look for particular patterns of foreground
and background pixels in an image. It takes a binary image but takes a
trinary structuring element.
Operation - How It Works
The structuring element used in the hit-and-miss transform is extended.
It contains 1's for foreground, 0's for background and spaces for don't care.
If the foreground and background pixels in the structuring element exactly
match foreground and background pixels in the image, then the pixel at the
origin will become the foreground pixel, otherwise (no match) that pixel
will be set to the background pixel. This transform is used to look for
occurences of particular binary patterns in fixed orientations.
If we are interested in finding right angle convex corner points then we
would apply the following four structuring elements and OR together the four
results.
Hit-and-miss transforms are very sensitive to noise, so noise filtering
should be done first. Beware of median which cuts corners!
