Image Processing Reference
In-Depth Information
An image (say
A
) of size
M
×
N
is initially fuzzified using the following
formula:
gg
−
(5.1)
min
μ
A
g
()
=
g
−
g
max in
where
g
is the grey level that ranges from 0 to
L
−a1
g
min
and
g
max
are the minimum and maximum values of the grey levels of
the image, respectively
Based on the fuzzy set, the membership degree of the
IF
image is calcu-
lated as
λ
−
1
μ
(;)
g
λ
=−−
11
(
μ
())
g
IFS
A
Using standard fuzzy negation, φ(
x
) = (1 −
x
)
λ
, λ
≥ 1, the non-membership
function is given as
(5.2)
ν
(;)
g
λ ϕμ
=
( (;))
g
λ
IFS
IFS
or
λ
ν
(;)( (;)) ,
g
λ
=−
1
μ
g
λ
λ
≥
1
IFS
IFS
(5.3)
( ; )
(
λλ
−
1
)
=−
(
1
μλ
g
A
The hesitation degree is
π
(;)
g
λ
=−
1
μ
( ;) (;)
g
λ
−
ν
g
λ
IFS
IFS
IFS
As λ
is not fixed for all the images, the optimum value of λ
is obtained using
IF
entropy. The optimum values are calculated using different entropies.
There are many types of entropies suggested by different authors. These are
1. Entropy by Burillo and Bustince [4]
1
1
M
−
N
−
1
∑
=
∑
(5.4)
1
−
(
μ
(
g
)
+
ν
(
g
))
EA
(
)
=
(
1
−
μ
(
g
)
−
ν
(
g
))
e
Aij Aij
1
IFS
A
ij Aij
MN
×
j
0
i
=
0
2. Entropy by Vlachos and Sergiadis [17]
1
1
−
∑
0
N
M
−
2
1
2
μν
()() ()
() ()
g
g
+
π
g
Aij Aij Aij
EA
MN
(
)
=
(5.5)
2
IFS
2
2
2
×
π
g
+
μ
g
+
ν
(()
g
ij
Aij
A
ij
A
j
=
0
i
=
Search WWH ::
Custom Search