Original image
T
Enhanced image
f(x, y)
g(x, y)
T
(a)
Input f (x, y)
Output g (x, y)
T
(b)
Input f (x, y)
Output g (x, y)
40
Biomedical Signal and Image Processing
FIGURE 3.1 Schematic diagram of image restoration techniques as computational machines.
FIGURE 3.2 Schematic diagram of (a) mask processing and (b) point processing techniques.
3.2 POINT PROCESSING
Point processing involves a mathematical transformation that modifies the values of
the pixels in the original image to create the values of the corresponding pixels in
the enhanced image. The mathematical expression for such a transformation can be
described as follows:
g x y
( , ) = T [ f (x, y ) ]
(3.1)
where
f(x, y) is the original (input) image
g(x, y) is the enhanced (output) image
T describes the transformation between the two images
The exact choice of the transformation is identified by the exact objectives of the
point processing task. Point processing is often performed on an image to improve
the quality of an image using the manipulation of the gray-level range of the image.
Different methods of point processing and their specific objectives are described in
the following.