Image Enhancement - Medical Image Processing: Advanced Fuzzy Set Theoretic Techniques - page 85

Modified
membership
function

Transformation

Input image

Fuzzification

Defuzzification

Enhanced image

FIGURE 5.1
Fuzzy image enhancement.

darkness of the pixels in an image. Then a transformation function is
applied on the membership values to generate new membership values of
the pixels in the image. Finally, an inverse transformation is applied on the
new membership values for transforming back the membership values to a
spatial domain. The principle of fuzzy contrast enhancement is illustrated
in Figure 5.1.
Algorithmically, it can be expressed as

ʹ

μ μ () (()) x = x

− 1

xf ʹ = (()) μ ʹ x

where
μ( x ) is the membership function
ψ(μ( x )) is the transformation of μ( x ) denoted as μ′( x )

In recent years, many researchers [12,13] have applied various fuzzy methods
for contrast enhancement. Before discussing the use of advanced fuzzy
set theoretic techniques in image enhancement, a few fuzzy methods are
discussed briefly in the next section.

5.3 Fuzzy Methods in Contrast Enhancement
In this section, different fuzzy methods for contrast enhancement are
discussed briefly.