Image Enhancement - Medical Image Processing: Advanced Fuzzy Set Theoretic Techniques - page 88

(c)

(a) (b)

(d) (e)

FIGURE 5.3
(a) Blood vessel (BV2) image, (b) enhancement using the FEV, (c) enhancement using the INT
operator, (d) enhancement using the NINT operator and (e) enhancement using histogram
hyperbolization.

5.4 Intuitionistic Fuzzy Enhancement Methods
In this section to improve the enhancement quality, IF methods are used for
image enhancement as it considers two uncertainties: the membership and
non-membership degrees as compared to one uncertainty in a fuzzy set. So,
it is expected to obtain better results as IF [2] set considers more uncertainties
and medical images also contain uncertainties. There is very little work on
IF enhancement of medical images, and these are described with examples.

5.4.1 Entropy-Based Enhancement Methods

In IF enhancement, both membership and non-membership values of an IF
image are required to determine. To find the degrees, an optimum value of
the constant parameter is required. Entropy-based methods used IF entropy
to find the optimum value of the constant term.
Method I : This method was suggested by Vlachos and Sergiadis [17]. The
image is initially fuzzified, and then an IF image is created using the mem-
bership and non-membership functions. An IF image is written as

Ax = {, (), ()}, μν g g g ∈ {,,, , 012 … L − 1 }

IFS A A

where g is the pixel value.