I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
,
p
p
.
3
40
2
~
3
4
1
0
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ec
e.
v
7
i6
.
p
p
3
40
2
-
341
0
3402
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Fu
zz
y
Regio
n Me
rg
ing
U
sing
Fu
zzy Si
m
ila
ri
ty M
ea
sure
m
ent
o
n I
m
a
g
e Seg
m
en
tatio
n
Wa
w
a
n
G
un
a
w
a
n
1
,
Ag
us
Z
a
ina
l A
rif
in
2
,
Ra
ra
s
m
a
y
a
I
nd
ra
s
w
a
ri
3
,
Dini Adni
Na
v
a
s
t
a
ra
4
1
De
p
a
rtme
n
t
o
f
S
c
ien
c
e
,
In
f
o
rm
a
t
ic
En
g
in
e
e
rin
g
,
I
n
stit
u
t
T
e
k
n
o
lo
g
i
S
u
m
a
tera
,
Ba
n
d
a
r
L
a
m
p
u
n
g
,
In
d
o
n
e
sia
2
,
3,
4
De
p
a
rtem
e
n
t
o
f
In
f
o
r
m
a
ti
c
s,
I
n
stit
u
t
T
e
k
n
o
lo
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r,
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
8
,
2
0
1
7
R
ev
i
s
ed
Sep
8
,
2
0
1
7
A
cc
ep
ted
Sep
25
,
2
0
1
7
S
o
m
e
i
m
a
g
e
’s
re
g
io
n
s
h
a
v
e
u
n
b
a
lan
c
e
in
f
o
r
m
a
ti
o
n
,
su
c
h
a
s
b
lu
rre
d
c
o
n
to
u
r
,
sh
a
d
e
,
a
n
d
u
n
e
v
e
n
b
rig
h
t
n
e
ss
.
T
h
o
se
re
g
io
n
s
a
re
c
a
ll
e
d
a
s
a
m
b
ig
u
o
u
s
re
g
io
n
s
.
Am
b
ig
u
o
u
s
re
g
io
n
c
a
u
se
p
ro
b
lem
d
u
rin
g
re
g
io
n
m
e
rg
in
g
p
ro
c
e
ss
in
in
tera
c
ti
v
e
ima
g
e
s
e
g
m
e
n
tatio
n
b
e
c
a
u
se
th
a
t
re
g
io
n
h
a
s
d
o
u
b
le
in
f
o
r
m
a
ti
o
n
,
b
o
t
h
a
s
o
b
jec
t
a
n
d
b
a
c
k
g
ro
u
n
d
.
W
e
p
ro
p
o
se
d
a
n
e
w
re
g
io
n
m
e
rg
i
n
g
stra
teg
y
u
sin
g
f
u
z
z
y
si
m
il
a
rit
y
m
e
a
su
re
m
e
n
t
f
o
r
i
m
a
g
e
s
e
g
m
e
n
tatio
n
.
T
h
e
p
ro
p
o
se
d
m
e
th
o
d
h
a
s
f
o
u
r
s
tep
s
;
t
h
e
f
irst
s
tep
is
i
n
it
ial
se
g
m
e
n
tatio
n
u
sin
g
mean
-
sh
if
t
a
lg
o
rit
h
m
.
T
h
e
s
e
c
o
n
d
ste
p
is
g
iv
in
g
ma
rk
e
rs
m
a
n
u
a
ll
y
to
in
d
ica
te
th
e
o
b
jec
t
a
n
d
b
a
c
k
g
ro
u
n
d
re
g
io
n
.
T
h
e
th
ird
st
ep
is
d
e
term
in
in
g
th
e
f
u
z
z
y
re
g
io
n
o
r
a
m
b
ig
u
o
u
s
re
g
io
n
in
t
h
e
im
a
g
e
s
.
T
h
e
las
t
st
ep
is
f
u
z
z
y
re
g
io
n
m
e
r
g
in
g
u
sin
g
f
u
z
z
y
si
m
il
a
rit
y
m
e
a
su
re
m
e
n
t
.
Th
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s
d
e
m
o
n
stra
ted
th
a
t
th
e
p
r
o
p
o
se
d
m
e
th
o
d
is
a
b
le
to
se
g
m
e
n
t
n
a
tu
ra
l
im
a
g
e
s
a
n
d
d
e
n
tal
p
a
n
o
ra
m
ic
im
a
g
e
s
su
c
c
e
ss
f
u
ll
y
w
it
h
th
e
a
v
e
ra
g
e
v
a
lu
e
o
f
m
isc
l
a
ss
i
f
ica
ti
o
n
e
rro
r
(M
E
)
1
.
9
6
%
a
n
d
5
.
4
7
%
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
:
Am
b
i
g
u
o
u
s
r
eg
io
n
I
m
ag
e
s
e
g
m
e
n
tatio
n
Fu
zz
y
r
eg
io
n
m
er
g
in
g
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
W
a
w
an
Gu
n
a
w
a
n
,
Dep
ar
t
m
en
t o
f
Scie
n
ce
,
I
n
f
o
r
m
atic
s
E
n
g
in
ee
r
i
n
g
,
I
n
s
tit
u
t T
ek
n
o
lo
g
i Su
m
ater
a,
B
an
d
ar
L
a
m
p
u
n
g
,
I
n
d
o
n
es
ia
.
E
m
ail:
w
a
w
a
n
.
g
u
n
a
w
a
n
@
if
.
i
t
er
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Seg
m
en
tatio
n
is
a
b
asic
p
r
o
ce
s
s
i
n
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
T
h
e
p
u
r
p
o
s
e
o
f
s
e
g
m
en
tatio
n
i
s
to
d
iv
id
e
th
e
i
m
a
g
e
i
n
to
r
eg
io
n
s
t
h
at
h
av
e
h
o
m
o
g
en
o
u
s
f
ea
tu
r
es
o
r
h
a
v
e
t
h
e
s
a
m
e
ch
ar
ac
ter
is
tics
,
e.
g
.
,
c
o
n
to
u
r
s
,
co
lo
r
s
,
a
n
d
co
n
tr
ast
[
1
]
,
[
2
]
.
I
n
g
en
er
al,
im
ag
e
s
e
g
m
e
n
tatio
n
m
eth
o
d
s
ca
n
b
e
d
iv
id
ed
a
m
o
n
g
t
h
r
ee
ca
teg
o
r
ies,
n
a
m
el
y
au
to
m
at
ic,
s
e
m
i
-
a
u
to
m
at
ic,
an
d
m
an
u
al
[
3
]
.
Au
to
m
a
tic
i
m
a
g
e
s
e
g
m
e
n
tatio
n
m
eth
o
d
s
ca
n
b
e
ca
teg
o
r
ized
in
t
o
s
ev
er
al
g
r
o
u
p
s
,
n
a
m
el
y
t
h
e
h
is
to
g
r
a
m
-
b
ased
,
ed
g
e
-
b
ased
,
r
eg
io
n
-
b
ased
[
4
]
,
[
5
]
,
an
d
h
y
b
r
id
tech
n
iq
u
e
[
6
]
.
A
lt
h
o
u
g
h
a
u
to
m
at
ic
s
e
g
m
en
ta
tio
n
m
eth
o
d
i
s
f
ast,
o
p
ti
m
izat
io
n
p
r
o
ce
s
s
n
ee
d
s
to
b
e
d
o
n
e
to
g
et
t
h
e
o
p
ti
m
al
p
ar
am
eter
s
th
at
g
r
ea
tl
y
a
f
f
ec
t t
h
e
ac
cu
r
ac
y
o
f
au
to
m
atic
s
e
g
m
en
tatio
n
r
es
u
lt
s
[
7
]
.
Au
to
m
a
tic
s
e
g
m
en
ta
tio
n
m
eth
o
d
s
h
av
e
d
r
a
w
b
ac
k
s
w
h
e
n
th
e
o
b
j
ec
t
an
d
th
e
b
ac
k
g
r
o
u
n
d
r
eg
io
n
o
f
th
e
i
m
a
g
e
d
id
n
o
t
h
a
v
e
a
clea
r
d
iv
id
in
g
li
n
e,
ca
u
s
i
n
g
a
d
i
f
f
er
en
ce
i
n
p
er
ce
p
tio
n
b
et
w
ee
n
t
h
e
r
es
u
lt
s
o
f
t
h
e
s
eg
m
e
n
tatio
n
m
eth
o
d
a
n
d
t
h
e
u
s
er
'
s
w
is
h
e
s
[
8
]
.
Se
m
i
-
a
u
to
m
atic
s
e
g
m
en
ta
tio
n
m
et
h
o
d
h
a
s
b
ee
n
d
ev
elo
p
ed
to
o
v
er
co
m
e
t
h
at
p
r
o
b
le
m
b
y
p
r
o
v
id
in
g
ad
d
itio
n
a
l
i
n
f
o
r
m
a
tio
n
f
r
o
m
t
h
e
u
s
er
to
a
s
s
i
s
t
th
e
s
y
s
te
m
in
t
h
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
.
U
n
d
er
th
ese
co
n
d
itio
n
s
,
o
u
r
s
t
u
d
y
u
s
ed
a
s
e
m
i
-
a
u
to
m
atic
s
e
g
m
e
n
tatio
n
ap
p
r
o
ac
h
o
r
o
f
ten
r
e
f
er
r
ed
to
as th
e
in
ter
ac
tiv
e
i
m
ag
e
s
eg
m
e
n
tatio
n
.
I
n
i
n
ter
ac
ti
v
e
i
m
a
g
e
s
e
g
m
e
n
ta
tio
n
,
u
s
er
ca
n
i
n
ter
ac
t
b
y
p
r
o
v
id
in
g
i
n
p
u
t
(
u
s
er
m
ar
k
i
n
g
)
th
a
t
h
elp
s
t
h
e
s
y
s
te
m
in
t
h
e
d
eter
m
i
n
atio
n
o
f
th
e
o
b
j
ec
t
an
d
th
e
b
ac
k
g
r
o
u
n
d
ar
ea
in
th
e
i
m
a
g
e.
Se
v
er
al
s
tu
d
ies
r
elate
d
to
s
e
m
i
-
a
u
to
m
a
tic
s
eg
m
e
n
tatio
n
h
av
e
b
ee
n
p
r
o
p
o
s
ed
b
y
[
3
]
,
[
9
]
-
[
1
2
]
.
B
ased
o
n
th
o
s
e
s
tu
d
y
,
in
ter
ac
tiv
e
i
m
ag
e
s
eg
m
e
n
tatio
n
co
n
s
is
t
o
f
f
o
u
r
m
ai
n
s
tag
e
s
.
T
h
e
f
ir
s
t
s
ta
g
e
is
d
iv
id
in
g
th
e
i
m
ag
e
i
n
to
s
ev
er
al
s
m
all
r
eg
io
n
s
(
r
eg
io
n
s
p
lit
tin
g
)
to
g
et
t
h
e
i
n
i
tial
s
e
g
m
en
ta
tio
n
.
T
h
e
s
ec
o
n
d
s
tag
e
is
u
s
er
m
ar
k
in
g
m
a
n
u
al
l
y
s
o
m
e
r
e
g
io
n
s
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
u
z
z
y
R
eg
io
n
Mer
g
in
g
Usi
n
g
F
u
z
z
y
S
imila
r
ity
Mea
s
u
r
e
men
t o
n
I
ma
g
e
S
e
g
men
ta
tio
n
(
W
a
w
a
n
Gu
n
a
w
a
n
)
3403
o
b
j
ec
t
o
r
b
ac
k
g
r
o
u
n
d
.
T
h
e
th
ir
d
s
tag
e
i
s
t
h
e
e
x
tr
ac
ti
n
g
ea
c
h
r
eg
io
n
b
ased
o
n
its
f
ea
tu
r
es,
s
u
ch
as
co
lo
r
,
s
h
ap
e,
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
,
tex
t
u
r
e,
o
r
s
ize
o
f
th
e
r
e
g
io
n
.
T
h
e
las
t
s
tag
e
is
m
er
g
i
n
g
all
r
eg
io
n
s
,
to
g
et
t
w
o
clu
s
ter
s
w
h
ic
h
ar
e
b
ac
k
g
r
o
u
n
d
an
d
o
b
ject.
So
m
e
r
eg
io
n
s
h
a
v
e
u
n
b
ala
n
c
e
in
f
o
r
m
atio
n
v
alu
e
s
,
s
u
c
h
a
s
b
lu
r
r
ed
co
n
to
u
r
,
s
h
ad
e,
a
n
d
u
n
e
v
e
n
b
r
ig
h
t
n
es
s
.
I
n
t
h
i
s
s
tu
d
y
,
w
e
r
ef
er
t
h
o
s
e
r
eg
io
n
s
a
s
a
m
b
i
g
u
o
u
s
r
e
g
io
n
s
.
T
h
e
a
m
b
i
g
u
o
u
s
r
e
g
io
n
is
v
er
y
in
f
lu
e
n
tia
l
in
t
h
e
p
r
o
ce
s
s
o
f
r
eg
io
n
s
p
lit
tin
g
b
ec
au
s
e
th
e
y
ar
e
v
er
y
s
i
m
ilar
h
e
n
c
e
it
is
d
if
f
icu
lt
to
s
ep
ar
ate
th
e
m
.
T
h
e
a
m
b
ig
u
o
u
s
r
eg
io
n
w
il
l
b
e
co
n
s
id
er
ed
a
s
in
g
le
r
eg
io
n
e
v
en
th
o
u
g
h
t
h
e
r
eg
io
n
h
as
t
w
o
v
alu
e
s
o
f
in
f
o
r
m
atio
n
,
w
h
ic
h
ar
e
o
b
j
ec
t
s
an
d
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
atio
n
.
T
h
is
ca
n
lead
to
er
r
o
r
d
u
r
in
g
th
e
r
eg
io
n
m
er
g
i
n
g
p
r
o
ce
s
s
f
o
r
ca
u
s
i
n
g
o
v
er
s
e
g
m
en
tatio
n
.
F
ig
u
r
e
1
(
A
)
is
a
n
ex
a
m
p
le
o
f
th
e
a
m
b
i
g
u
o
u
s
r
e
g
io
n
,
w
e
ca
n
s
ee
t
h
at
th
e
co
lo
r
in
th
e
r
eg
io
n
is
v
er
y
s
i
m
ilar
(
f
u
zz
y
r
eg
io
n
)
s
o
it
w
o
u
ld
b
e
d
if
f
icu
lt
to
s
ep
ar
ate
th
e
r
eg
io
n
[
1
3
]
-
[1
4]
.
I
n
Fi
g
u
r
e
1
(
B
)
,
alth
o
u
g
h
t
h
o
s
e
t
w
o
r
eg
io
n
s
t
h
at
h
av
e
s
i
m
ilar
co
lo
r
,
th
er
e
is
a
clea
r
lin
e
b
etw
ee
n
t
h
o
s
e
r
eg
io
n
s
h
en
ce
it
w
i
ll b
e
ea
s
y
to
s
ep
ar
at
e
th
e
m
.
Fig
u
r
e
1
.
Dif
f
er
en
t
tr
a
n
s
itio
n
c
o
lo
r
in
th
e
r
eg
io
n
.
(
A
)
T
h
e
a
m
b
ig
u
o
u
s
re
g
io
n
,
(
B
)
No
n
-
a
m
b
ig
u
o
u
s
r
e
g
io
n
T
h
e
am
b
i
g
u
o
u
s
r
eg
io
n
w
ill
af
f
ec
t
th
e
r
e
g
io
n
m
er
g
i
n
g
p
r
o
ce
s
s
b
ec
au
s
e
t
h
e
a
m
b
i
g
u
o
u
s
r
eg
io
n
ca
u
s
e
d
o
v
er
s
eg
m
en
tatio
n
i
n
t
h
e
r
eg
i
o
n
s
p
litt
i
n
g
p
r
o
ce
s
s
.
I
n
b
in
ar
y
r
eg
io
n
m
er
g
i
n
g
(
B
R
M)
[
1
0
]
,
[
1
5
]
ea
ch
r
eg
io
n
h
as
o
n
l
y
o
n
e
p
r
o
b
ab
ilit
y
(
cr
is
p
f
u
zz
y
)
to
b
e
in
th
e
o
b
j
ec
t
o
r
b
ac
k
g
r
o
u
n
d
clu
s
ter
.
Fo
r
i
m
ag
es
t
h
at
h
a
v
e
an
a
m
b
ig
u
o
u
s
r
eg
io
n
,
b
i
n
ar
y
r
eg
i
o
n
m
er
g
in
g
ca
n
n
o
t b
e
d
o
n
e
b
ec
au
s
e
t
h
e
r
eg
io
n
h
as t
w
o
i
n
f
o
r
m
atio
n
v
al
u
es.
I
n
t
h
is
s
t
u
d
y
,
w
e
p
r
o
p
o
s
e
a
n
e
w
s
tr
ate
g
y
f
o
r
r
eg
io
n
m
er
g
i
n
g
,
n
a
m
el
y
f
u
zz
y
r
e
g
io
n
m
er
g
in
g
,
u
s
in
g
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
in
i
n
ter
ac
ti
v
e
i
m
a
g
e
s
e
g
m
e
n
tatio
n
.
O
u
r
co
n
tr
ib
u
tio
n
to
t
h
is
r
esear
ch
is
t
h
e
f
u
zz
y
r
e
g
io
n
m
er
g
i
n
g
(
F
R
M)
p
r
o
ce
s
s
w
h
er
e
ea
ch
r
e
g
io
n
w
i
l
l b
e
m
er
g
ed
u
s
i
n
g
f
u
zz
y
s
i
m
il
ar
it
y
m
ea
s
u
r
e
m
e
n
ts
,
s
o
a
m
b
ig
u
o
u
s
r
eg
io
n
s
w
it
h
i
n
t
h
e
i
m
a
g
e
ca
n
b
e
s
ep
ar
ated
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
p
u
t
i
m
a
g
es
t
h
at
ar
e
u
s
ed
f
o
r
th
is
s
t
u
d
y
ar
e
n
at
u
r
al
i
m
a
g
es
a
n
d
d
en
tal
p
an
o
r
a
m
ic
i
m
ag
es.
T
h
e
n
atu
r
al
i
m
a
g
es
ar
e
o
b
tain
ed
f
r
o
m
r
ea
l
-
w
o
r
ld
o
b
j
ec
ts
w
ith
d
i
f
f
er
e
n
t
b
ac
k
g
r
o
u
n
d
s
a
n
d
o
b
j
ec
ts
.
Den
tal
p
an
o
r
a
m
ic
i
m
a
g
es
ar
e
o
b
tain
e
d
f
r
o
m
Air
lan
g
g
a
U
n
i
v
er
s
it
y
Ho
s
p
ital
[
1
6
]
.
Ov
er
all
,
w
e
u
s
e
d
g
r
a
y
s
ca
le
i
m
a
g
es.
I
n
th
is
s
tu
d
y
,
w
e
f
o
cu
s
ed
j
u
s
t
on
t
h
e
r
eg
io
n
m
er
g
i
n
g
s
tr
at
eg
y
to
o
v
er
co
m
e
t
h
e
a
m
b
ig
u
o
u
s
r
eg
io
n
s
o
n
t
h
e
i
m
a
g
e.
W
e
f
i
n
d
t
h
e
o
p
ti
m
al
s
i
m
ilar
it
y
b
et
w
ee
n
r
eg
io
n
s
u
s
i
n
g
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t.
T
h
e
s
tep
s
o
f
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
c
an
b
e
s
ee
n
in
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
Stag
es o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
2
.
1
.
I
nitia
l Seg
m
ent
a
t
io
n
I
n
itial
s
e
g
m
e
n
tatio
n
a
i
m
s
to
d
iv
id
e
th
e
i
m
a
g
e
i
n
to
s
e
v
er
al
s
m
all
r
e
g
io
n
s
t
h
at
s
h
ar
e
s
i
m
ilar
ch
ar
ac
ter
is
tic
s
.
I
n
th
is
s
t
u
d
y
,
t
o
g
et
in
itia
l
s
e
g
m
e
n
tat
io
n
w
e
u
s
e
m
ea
n
-
s
h
i
f
t
s
eg
m
e
n
tatio
n
s
o
f
t
w
ar
e
cr
ea
ted
b
y
A
B
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
4
0
2
–
3
4
1
0
3404
E
d
is
o
n
S
y
s
te
m
.
T
h
e
i
m
a
g
e
i
s
d
iv
id
ed
i
n
to
s
e
v
er
al
r
eg
i
o
n
s
b
ased
u
p
o
n
t
h
e
p
r
o
b
ab
ilit
y
d
en
s
it
y
g
r
ad
ie
n
t
f
u
n
ctio
n
s
.
T
h
e
r
esu
lt
o
f
t
h
e
in
itial
s
eg
m
e
n
tatio
n
u
s
in
g
t
h
e
m
ea
n
-
s
h
i
f
t
al
g
o
r
ith
m
is
b
etter
th
an
o
th
er
m
et
h
o
d
s
o
f
lo
w
-
lev
e
l
s
e
g
m
e
n
tatio
n
,
b
ec
au
s
e
it
i
s
co
n
s
id
er
in
g
th
e
s
p
atial
i
n
f
o
r
m
atio
n
an
d
s
h
ap
e
o
f
t
h
e
o
b
j
e
ct
i
m
ag
e
[
1
0
]
.
2
.
2
.
M
a
rk
er
s
I
n
ter
ac
tiv
e
i
m
a
g
e
s
eg
m
e
n
tatio
n
p
r
o
v
id
es
u
s
er
i
n
ter
ac
tio
n
w
i
th
t
h
e
s
e
g
m
en
tatio
n
s
y
s
te
m
in
th
e
f
o
r
m
o
f
m
ar
k
er
s
.
Ma
n
u
a
l
m
ar
k
i
n
g
i
s
o
n
e
o
f
th
e
m
o
s
t
m
aj
o
r
s
tag
e
s
in
th
e
in
ter
ac
ti
v
e
s
eg
m
e
n
tati
o
n
b
ec
au
s
e
i
t
w
il
l
af
f
ec
t
th
e
s
e
g
m
en
tatio
n
r
es
u
lt.
I
n
ter
ac
tiv
e
i
m
ag
e
s
e
g
m
en
tati
o
n
is
v
er
y
s
e
n
s
iti
v
e
to
th
e
q
u
a
lit
y
o
f
m
ar
k
i
n
g
an
d
th
e
n
u
m
b
er
o
f
m
ar
k
er
[
1
7
]
.
Fig
u
r
e
3
i
llu
s
tr
ates
th
e
r
e
g
io
n
m
ar
k
i
n
g
p
r
o
ce
s
s
f
o
r
n
at
u
r
al
a
n
d
d
en
tal
p
a
n
o
r
a
m
ic
i
m
a
g
e
s
,
t
h
e
g
r
ee
n
li
n
e
i
n
d
ica
tes
t
h
e
o
b
j
ec
t
r
eg
io
n
a
n
d
t
h
e
b
lu
e
li
n
e
in
d
icate
s
t
h
e
b
ac
k
g
r
o
u
n
d
r
e
g
io
n
.
T
h
e
f
ea
t
u
r
es
o
f
t
h
e
r
e
g
io
n
s
th
a
t
h
as
b
ee
n
m
ar
k
ed
as
o
b
j
ec
t
o
r
b
ac
k
g
r
o
u
n
d
i
s
ca
r
r
ied
o
u
t
to
d
eter
m
in
e
its
ch
ar
ac
ter
is
tic
s
.
Fig
u
r
e
3
.
R
esu
lts
o
f
i
n
it
ial
s
e
g
m
en
tatio
n
a
n
d
u
s
er
m
ar
k
i
n
g
2
.
3
.
I
nitia
liza
t
io
n o
f
F
uzzy
Reg
io
n
E
ac
h
m
e
m
b
er
o
f
th
e
f
u
zz
y
s
et
h
a
s
a
d
eg
r
ee
o
f
m
e
m
b
er
s
h
ip
v
alu
e
t
h
at
d
eter
m
i
n
es
th
e
p
o
ten
tial
m
e
m
b
er
s
ca
n
en
ter
a
f
u
zz
y
.
T
h
is
s
tag
e
is
u
s
ed
to
f
i
n
d
th
e
f
u
zz
y
r
eg
io
n
i
n
th
e
i
m
ag
e,
w
h
er
e
th
e
p
ar
am
e
ter
s
o
f
ea
ch
r
eg
io
n
t
h
at
h
as
b
ee
n
m
ar
k
ed
as
th
e
o
b
j
ec
t
an
d
b
ac
k
g
r
o
u
n
d
w
ill
b
e
ca
lcu
la
ted
.
P
ar
am
eter
o
b
tain
ed
b
y
f
i
n
d
in
g
th
e
h
i
g
h
e
s
t
g
r
a
y
lev
e
l
at
ea
ch
m
ar
k
er
o
f
r
eg
io
n
b
ac
k
g
r
o
u
n
d
(
)
an
d
f
r
o
m
t
h
e
s
m
alle
s
t
g
r
a
y
le
v
el
at
ea
ch
m
ar
k
er
o
f
o
b
j
ec
t
r
eg
io
n
(
)
.
v
alu
e
w
ill
al
w
a
y
s
s
m
al
ler
th
a
n
th
e
v
a
lu
e
o
f
.
T
h
e
v
alu
e
o
f
an
d
is
ca
lcu
lated
u
s
in
g
E
q
.
1
-
3
.
Fi
g
u
r
e
4
s
h
o
w
s
t
h
e
ill
u
s
tr
atio
n
o
f
t
h
e
d
eter
m
i
n
atio
n
o
f
(
)
an
d
(
)
p
ar
am
eter
s
to
d
escr
ib
e
th
e
v
alu
e
o
f
an
d
.
Fu
zz
y
r
eg
io
n
is
an
a
m
b
i
g
u
o
u
s
r
e
g
io
n
o
f
t
h
e
i
m
ag
e
w
h
ic
h
in
te
n
s
it
y
i
s
al
w
a
y
s
b
et
w
ee
n
an
d
.
I
n
itial
s
ee
d
o
f
b
ac
k
g
r
o
u
n
d
r
eg
io
n
is
th
e
ar
ea
b
et
w
ee
n
an
d
th
e
m
i
n
i
m
al
g
r
a
y
le
v
el
i
n
th
e
h
is
to
g
r
a
m
.
I
n
itial
s
ee
d
o
f
o
b
j
ec
t
r
eg
io
n
is
th
e
ar
ea
b
et
w
ee
n
an
d
th
e
m
ax
i
m
a
l g
r
a
y
lev
el
o
n
t
h
e
h
is
t
o
g
r
a
m
.
=
ma
x
(
;
(
)
)
(
1
)
=
min
(
;
(
)
)
(
2
)
(
)
=
{
=
;
=
,
>
=
;
=
,
ℎ
(
3
)
Af
ter
th
e
f
u
zz
y
r
eg
io
n
w
as
f
o
u
n
d
,
th
e
n
ex
t
s
tep
is
ca
lcu
la
te
th
e
m
e
m
b
er
s
h
ip
f
u
n
c
tio
n
i
n
th
e
g
r
a
y
lev
el
h
i
s
to
g
r
a
m
.
S
-
f
u
n
ctio
n
ca
lcu
late
s
th
e
b
ac
k
g
r
o
u
n
d
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
an
d
Z
-
f
u
n
cti
o
n
ca
lcu
lates
t
h
e
o
b
j
ec
t
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
.
E
ac
h
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
is
co
n
tr
o
lled
b
y
a
p
o
in
t
=
127
an
d
is
ca
lcu
lated
u
s
i
n
g
E
q
.
4
an
d
E
q
.
5
.
Fig
u
r
e
5
illu
s
tr
ates S
-
f
u
n
ct
i
o
n
th
at
f
o
r
m
s
t
h
e
letter
S
w
i
th
a
g
r
ee
n
li
n
e
o
n
t
h
e
h
is
to
g
r
a
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
u
z
z
y
R
eg
io
n
Mer
g
in
g
Usi
n
g
F
u
z
z
y
S
imila
r
ity
Mea
s
u
r
e
men
t o
n
I
ma
g
e
S
e
g
men
ta
tio
n
(
W
a
w
a
n
Gu
n
a
w
a
n
)
3405
Fig
u
r
e
4
.
I
n
itializes t
h
e
f
u
zz
y
r
eg
io
n
i
n
th
e
h
is
to
g
r
a
m
Fig
u
r
e
5
.
Dete
r
m
in
a
tio
n
o
f
S
-
f
u
n
ct
io
n
an
d
Z
-
f
u
n
ctio
n
i
n
t
h
e
g
r
a
y
le
v
el
h
is
to
g
r
a
m
T
h
e
s
m
aller
t
h
e
v
a
lu
e
o
f
g
r
a
y
lev
e
l
in
th
e
h
i
s
to
g
r
a
m
,
t
h
e
g
r
ea
ter
t
h
e
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
o
f
b
ac
k
g
r
o
u
n
d
in
th
e
h
i
s
to
g
r
a
m
.
Z
-
f
u
n
ctio
n
f
o
r
m
s
t
h
e
letter
Z
w
it
h
r
ed
li
n
e
o
n
t
h
e
h
is
to
g
r
a
m
.
T
h
e
lar
g
er
th
e
v
alu
e
o
f
g
r
a
y
le
v
el
in
th
e
h
is
to
g
r
a
m
,
t
h
e
g
r
ea
ter
th
e
g
r
a
y
le
v
el
m
e
m
b
er
s
h
ip
f
u
n
c
tio
n
o
f
o
b
j
e
ct
in
th
e
h
is
to
g
r
a
m
.
W
e
u
s
e
S
-
f
u
n
ctio
n
an
d
Z
-
f
u
n
ctio
n
b
ec
au
s
e
th
e
s
e
f
u
n
ctio
n
s
co
n
s
id
er
th
e
m
e
m
b
er
s
h
ip
f
u
n
c
tio
n
o
f
th
e
o
b
j
ec
t a
n
d
th
e
b
ac
k
g
r
o
u
n
d
o
b
j
ec
t a
ls
o
ag
ain
s
t a
co
n
tr
ad
icto
r
y
b
ac
k
g
r
o
u
n
d
.
(
)
=
(
;
,
,
)
=
{
0
,
<
2
{
−
−
}
2
,
≤
≤
1
−
2
{
−
−
}
2
,
<
≤
1
,
>
(
4
)
(
)
=
1
−
(
;
,
,
)
(
5
)
2
.
4
.
F
uzzy
Reg
io
n
M
er
g
in
g
T
h
e
last
s
tag
e
is
f
u
zz
y
r
e
g
i
o
n
m
er
g
i
n
g
f
o
r
ea
ch
f
u
zz
y
r
eg
io
n
f
i
…
.
r
ϵ
F
.
W
e
u
s
e
f
u
zz
y
s
i
m
i
la
r
it
y
m
ea
s
u
r
e
m
e
n
t
o
n
i
n
itial
s
ee
d
o
f
b
ac
k
g
r
o
u
n
d
r
eg
io
n
C
B
an
d
i
n
iti
al
s
ee
d
o
f
o
b
j
ec
t
r
eg
io
n
C
O
.
Fu
z
z
y
s
i
m
ilar
i
t
y
ca
lcu
lated
b
ased
o
n
th
e
s
i
m
il
ar
it
y
b
et
w
ee
n
t
h
e
g
r
a
y
le
v
el
an
d
th
e
in
te
n
s
it
y
,
m
e
m
b
er
s
h
i
p
f
u
n
c
tio
n
s
,
an
d
th
e
d
if
f
er
e
n
ce
o
f
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
w
ith
t
h
e
o
r
d
in
al
s
et.
Fu
z
z
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
en
t
δ
ca
lcu
late
s
th
e
in
i
tial
s
u
b
s
et
o
f
g
lo
b
al
i
n
f
o
r
m
atio
n
C
B
an
d
C
O
to
lo
ca
l
i
n
f
o
r
m
atio
n
o
n
ea
ch
f
u
zz
y
r
eg
io
n
f
i
in
t
h
e
i
m
a
g
e
a
s
illu
s
tr
ated
in
Fig
u
r
e
6
.
Si
m
ilar
it
y
v
al
u
e
δ
f
o
r
s
et
(
C
X
∪
{
f
ig
}
)
,
in
i
tial
s
ee
d
o
f
an
ar
ea
C
X
,
m
e
m
b
er
s
h
ip
o
f
a
ll
g
g
r
a
y
le
v
el
i
n
th
e
f
u
zz
y
r
eg
io
n
f
i
,
an
d
g
r
a
y
le
v
el
i
n
ten
s
it
y
h
(
g
)
,
ca
n
b
e
ca
lcu
lated
u
s
i
n
g
E
q
.
6
.
(
C
x
∪
{
f
ij
}
)
=
∑
g
=
1
n
(
g
−
fm
(
C
x
∪
{
f
ig
}
)
2
∑
z
=
1
n
h
(
g
)
,
(
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
4
0
2
–
3
4
1
0
3406
Fig
u
r
e
6
.
Fu
zz
y
r
e
g
io
n
m
er
g
i
n
g
u
s
in
g
f
u
zz
y
s
i
m
i
lar
it
y
m
ea
s
u
r
e
m
en
t
Fu
zz
y
m
ea
n
v
a
lu
e
(
)
o
f
th
e
m
e
r
g
ed
ar
ea
,
th
a
t
i
s
co
n
s
id
er
in
g
t
h
e
g
r
a
y
lev
e
l
i
n
te
n
s
it
y
ℎ
(
)
,
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
s
(
)
,
an
d
th
e
d
i
f
f
er
e
n
ce
o
f
m
e
m
b
er
s
h
i
p
f
u
n
ctio
n
w
it
h
t
h
e
o
r
d
in
al
s
et
|
(
μ
A
(
g
)
−
μ
A
′
(
g
)
|
,
ca
n
b
e
ca
lcu
lated
u
s
i
n
g
E
q
.
7
.
B
ased
o
n
th
e
r
esu
lt
s
o
f
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t,
ea
ch
f
u
zz
y
r
eg
io
n
ca
n
b
e
m
er
g
ed
to
b
ac
k
g
r
o
u
n
d
o
r
o
b
j
ec
t
clu
s
ter
b
ased
o
n
th
e
g
r
ea
te
s
t
s
i
m
i
lar
it
y
o
f
t
h
e
f
u
zz
y
r
eg
io
n
.
Dete
r
m
i
n
i
n
g
t
h
e
s
i
m
i
lar
it
y
v
a
lu
e
in
f
u
zz
y
r
e
g
io
n
ca
n
b
e
ca
lcu
lated
u
s
i
n
g
E
q
.
8
b
y
f
i
n
d
i
n
g
t
h
e
lar
g
est
in
d
ex
.
(
)
=
∑
=
1
ℎ
(
)
×
(
)
×
|
(
(
)
−
′
(
)
)
|
.
(
7
)
=
(
(
∪
{
}
)
∗
(
∪
{
}
)
)
(
8
)
3.
E
XP
E
R
I
M
E
NT
AL
RE
SUL
T
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
is
i
m
p
l
e
m
en
ted
o
n
th
e
1
5
d
en
tal
p
an
o
r
am
ic
i
m
a
g
es
(
th
a
t
h
a
v
e
b
ee
n
u
s
ed
i
n
[
1
2
]
an
d
[
1
6
]
)
an
d
1
0
n
at
u
r
al
i
m
a
g
es
.
Fig
u
r
e
7
s
h
o
w
s
e
v
er
al
o
f
t
h
e
test
i
m
a
g
e
s
a
f
ter
i
n
itia
l
s
e
g
m
e
n
tat
io
n
a
n
d
u
s
er
m
ar
k
i
n
g
p
r
o
ce
s
s
.
Fi
g
u
r
e
8
s
h
o
w
s
t
h
e
g
r
o
u
n
d
tr
u
th
i
m
a
g
es
t
h
at
ar
e
cr
ea
ted
m
a
n
u
a
ll
y
.
Fig
u
r
e
9
s
h
o
w
s
th
e
s
eg
m
e
n
tatio
n
r
e
s
u
lt
s
o
f
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
.
W
e
also
co
m
p
ar
ed
o
u
r
p
r
o
p
o
s
ed
m
et
h
o
d
w
it
h
b
i
n
ar
y
r
eg
io
n
m
er
g
i
n
g
ap
p
r
o
ac
h
p
r
o
p
o
s
ed
b
y
Ni
n
g
et.
al.
[
1
0
]
,
n
a
m
ed
m
a
x
i
m
al
s
i
m
i
lar
it
y
b
ased
r
eg
io
n
m
er
g
in
g
(
MS
R
M)
.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
(
h
)
Fig
u
re
7.
Sa
m
p
le
o
f
i
n
p
u
t i
m
a
g
es
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
u
z
z
y
R
eg
io
n
Mer
g
in
g
Usi
n
g
F
u
z
z
y
S
imila
r
ity
Mea
s
u
r
e
men
t o
n
I
ma
g
e
S
e
g
men
ta
tio
n
(
W
a
w
a
n
Gu
n
a
w
a
n
)
3407
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
(
h
)
Fig
u
r
e
8
.
Gr
o
u
n
d
tr
u
t
h
i
m
a
g
e
s
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
(
h
)
Fig
u
r
e
9.
Seg
m
en
ta
tio
n
r
es
u
lts
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
Seg
m
en
tatio
n
r
es
u
lt
s
o
f
MSR
M
ar
e
s
h
o
w
n
in
F
ig
u
r
e
10
.
E
ac
h
s
eg
m
e
n
ted
i
m
a
g
e
w
ill
b
e
co
m
p
ar
ed
w
it
h
g
r
o
u
n
d
tr
u
t
h
i
m
ag
e
s
to
d
eter
m
i
n
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
s
eg
m
e
n
tat
io
n
r
es
u
lts
.
I
n
t
h
is
s
t
u
d
y
,
th
e
e
v
al
u
atio
n
w
a
s
co
n
d
u
cted
b
y
u
s
i
n
g
m
i
s
cl
ass
i
f
icatio
n
er
r
o
r
(
ME
)
th
at
is
ca
lcu
lated
b
ased
o
n
th
e
E
q
.
9
.
=
1
−
|
∩
|
+
|
∩
|
|
|
+
|
|
,
(
9
)
w
h
er
e
an
d
ar
e
th
e
b
ac
k
g
r
o
u
n
d
an
d
th
e
o
b
j
ec
t
o
f
th
e
g
r
o
u
n
d
tr
u
t
h
i
m
a
g
e,
w
h
i
le
an
d
ar
e
th
e
b
ac
k
g
r
o
u
n
d
a
n
d
th
e
o
b
j
ec
t
o
f
t
h
e
s
e
g
m
e
n
tat
io
n
r
es
u
lt
.
T
h
e
s
m
aller
v
al
u
e
o
f
ME
s
h
o
w
s
t
h
e
s
eg
m
e
n
tatio
n
r
esu
lt
s
m
e
t
h
o
d
is
g
et
tin
g
b
ette
r
an
d
clo
s
er
to
g
r
o
u
n
d
tr
u
t
h
i
m
ag
es
.
T
h
e
i
m
p
le
m
en
ta
tio
n
r
esu
lts
b
ased
o
n
th
e
v
a
lu
e
o
f
ME
f
o
r
s
e
v
er
al
o
f
t
h
e
te
s
t
i
m
a
g
es
i
s
s
h
o
w
n
i
n
T
ab
le
1
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
r
o
v
id
es
b
etter
p
er
f
o
r
m
a
n
c
e
th
a
n
M
SR
M
w
it
h
an
av
er
a
g
e
ME
v
alu
e
4
.
5
5
%
f
o
r
n
atu
r
al
i
m
a
g
es
an
d
5
.
4
6
%
f
o
r
d
en
tal
p
an
o
r
a
m
ic
i
m
a
g
es
.
I
t
w
a
s
co
n
cl
u
d
ed
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
m
o
r
e
r
esi
s
ta
n
t to
th
e
i
n
ter
f
er
e
n
ce
o
f
a
m
b
ig
u
o
u
s
r
eg
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
4
0
2
–
3
4
1
0
3408
(
a)
(
b
)
(
c)
(
d
)
(
e)
(
f
)
(
g
)
(
h
)
Fig
u
r
e
1
0
.
Seg
m
e
n
tatio
n
r
esu
l
ts
o
f
t
h
e
MSR
M
m
et
h
o
d
T
ab
le
1
.
C
o
m
p
ar
is
o
n
r
es
u
lt o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
MSR
M
o
n
s
e
v
er
al
test
i
m
a
g
es
No
I
mag
e
s
M
i
s
c
l
a
ssi
f
i
c
a
t
i
o
n
Er
r
o
r
(
%)
M
S
R
M
P
r
o
p
o
se
d
me
t
h
o
d
a
D
e
n
t
a
l
1
1
.
9
7
2
.
3
8
b
D
e
n
t
a
l
2
1
5
.
6
4
9
.
4
2
c
D
e
n
t
a
l
3
3
3
.
4
7
1
4
.
3
8
d
D
e
n
t
a
l
4
1
7
.
3
7
7
.
7
0
e
N
a
t
u
r
a
l
1
7
.
6
0
7
.
5
2
f
N
a
t
u
r
a
l
2
1
.
1
1
0
.
7
7
g
N
a
t
u
r
a
l
3
0
.
9
1
0
.
9
8
h
N
a
t
u
r
a
l
4
2
.
4
8
3
.
1
6
4.
DIS
CU
SS
I
O
N
B
ased
o
n
th
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
,
t
h
e
d
is
c
u
s
s
io
n
o
f
t
h
is
s
tu
d
y
i
s
d
iv
id
ed
in
to
3
s
ec
tio
n
s
.
Sectio
n
4
.
1
w
il
l
d
is
c
u
s
s
ab
o
u
t
t
h
e
i
n
itial
s
eg
m
e
n
tat
io
n
p
r
o
ce
s
s
u
s
i
n
g
t
h
e
m
ea
n
-
s
h
if
t
al
g
o
r
ith
m
.
Sectio
n
4
.
2
an
al
y
ze
s
u
s
er
m
ar
k
i
n
g
p
r
o
ce
s
s
.
An
d
Sectio
n
4
.
3
w
ill
a
n
al
y
ze
th
e
f
u
zz
y
r
e
g
io
n
m
er
g
in
g
.
4
.
1
.
E
x
peri
m
e
nt
Ana
ly
s
is
o
f
Reg
io
n Spl
it
t
ing
R
eg
io
n
Sp
li
tti
n
g
u
s
i
n
g
m
ea
n
-
s
h
i
f
t
s
o
f
t
w
ar
e
f
r
o
m
E
d
is
o
n
s
y
s
te
m
h
a
s
b
ee
n
s
u
cc
es
s
f
u
l
l
y
i
m
p
le
m
en
ted
to
g
et
th
e
in
i
tial
s
eg
m
e
n
tatio
n
.
T
h
e
i
m
ag
e
ca
n
b
e
d
iv
id
ed
in
to
s
e
v
er
al
h
o
m
o
g
e
n
eo
u
s
r
eg
io
n
s
.
So
m
e
s
t
u
d
ies
also
u
s
ed
th
e
m
ea
n
-
s
h
i
f
t
s
o
f
t
w
ar
e
to
g
et
th
e
in
i
tial
s
e
g
m
e
n
tatio
n
as
p
r
o
p
o
s
ed
b
y
[
3
]
,
[
9
]
-
[
1
2
]
.
T
h
er
e
ar
e
t
w
o
p
ar
am
eter
s
th
at
m
u
s
t
b
e
en
ter
e
d
f
o
r
th
is
ap
p
licatio
n
is
s
p
atial
b
an
d
w
id
t
h
(
s
b
)
an
d
th
e
co
l
o
r
b
an
d
w
id
t
h
(
cb
)
.
I
n
th
is
s
tu
d
y
,
w
e
test
t
h
e
s
p
ati
al
b
an
d
w
id
t
h
v
al
u
es
b
et
w
ee
n
7
-
2
0
f
o
r
n
atu
r
al
im
a
g
e
s
an
d
2
0
-
5
0
f
o
r
d
en
tal
p
an
o
r
a
m
ic
i
m
ag
e
s
.
Fo
r
co
lo
r
b
an
d
w
id
t
h
,
w
e
u
s
e
v
al
u
e
o
f
3
.
5
-
6
.
5
f
o
r
n
atu
r
al
i
m
a
g
e
s
an
d
4
.
5
-
5
.
5
f
o
r
d
en
tal
p
an
o
r
a
m
ic
i
m
ag
e
s
.
On
i
m
a
g
e
t
h
at
h
a
s
an
a
m
b
i
g
u
o
u
s
r
eg
io
n
,
it
is
v
er
y
d
if
f
ic
u
lt
to
g
et
th
e
r
ig
h
t
p
ar
a
m
eter
s
to
o
b
tain
th
e
in
itial
s
e
g
m
e
n
tatio
n
.
Fi
g
u
r
e
1
1
s
h
o
w
s
th
e
ex
a
m
p
le
o
f
in
iti
al
s
eg
m
en
ta
tio
n
w
it
h
d
if
f
er
en
t
p
ar
am
eter
s
.
T
h
e
i
m
a
g
es
i
n
t
h
e
f
ir
s
t
r
o
w
o
n
F
ig
u
r
e
1
1
s
h
o
w
s
t
h
at
t
h
er
e
w
i
ll
b
e
d
if
f
er
e
n
t
i
n
itial
s
eg
m
e
n
tatio
n
r
es
u
lt
u
s
i
n
g
d
if
f
er
e
n
t
p
ar
a
m
eter
s
.
Ho
w
ev
e
r
,
o
v
er
s
eg
m
e
n
tatio
n
is
h
ap
p
en
ed
o
n
t
h
o
s
e
r
es
u
lt
s
b
ec
au
s
e
th
er
e
is
a
m
b
i
g
u
o
u
s
elap
s
ed
ar
ea
s
w
it
h
i
n
th
e
r
eg
io
n
.
T
h
is
is
u
n
li
k
e
th
e
i
n
itia
l
s
e
g
m
e
n
tat
io
n
r
es
u
lts
f
o
r
th
e
i
m
ag
es
i
n
th
e
s
ec
o
n
d
r
o
w
o
n
Fi
g
u
r
e
1
1
.
I
t
ca
n
b
e
c
o
n
clu
d
ed
th
at
t
h
e
a
m
b
i
g
u
o
u
s
r
eg
io
n
w
ill
b
e
v
er
y
i
n
f
lu
e
n
tia
l
at
th
e
ti
m
e
o
f
t
h
e
in
itial
s
eg
m
e
n
tatio
n
an
d
w
ill c
er
tain
l
y
a
f
f
ec
t t
h
e
r
esu
l
ts
o
f
s
e
g
m
e
n
tat
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
F
u
z
z
y
R
eg
io
n
Mer
g
in
g
Usi
n
g
F
u
z
z
y
S
imila
r
ity
Mea
s
u
r
e
men
t o
n
I
ma
g
e
S
e
g
men
ta
tio
n
(
W
a
w
a
n
Gu
n
a
w
a
n
)
3409
(
s
b
=
7
an
d
cb
=
3
.
5
)
(
s
b
=
7
an
d
cb
=
6
.
5
)
(
s
b
=
2
0
an
d
cb
=
4
.
5
)
(
s
b
=
4
0
an
d
cb
=
6
.
5
)
(
s
b
=
7
an
d
cb
=
3
.
5
)
(
s
b
=
7
an
d
cb
=
6
.
5
)
(
s
b
=
2
0
an
d
cb
=
4
.
5
(
s
b
=
4
0
an
d
cb
=
6
.
5
)
Fig
u
r
e
1
1
.
T
est in
itial se
g
m
e
n
t
atio
n
w
it
h
d
if
f
er
en
t
p
ar
a
m
e
ter
4
.
2
.
E
x
peri
m
e
nt
Ana
ly
s
is
o
f
M
a
r
k
er
s
P
ro
ce
s
s
I
n
ter
ac
tiv
e
s
e
g
m
en
tat
io
n
ap
p
r
o
ac
h
is
v
er
y
s
e
n
s
iti
v
e
to
t
h
e
q
u
alit
y
o
f
m
ar
k
i
n
g
a
n
d
th
e
n
u
m
b
er
o
f
u
s
er
m
ar
k
er
.
T
h
is
p
h
e
n
o
m
e
n
o
n
h
as
b
ec
o
m
e
a
m
aj
o
r
co
n
ce
r
n
in
d
eter
m
i
n
in
g
th
e
n
u
m
b
er
o
f
g
iv
e
n
m
ar
k
er
s
t
h
at
w
ill
b
e
u
s
ed
as
a
p
ar
a
m
eter
[
1
7
]
.
T
ab
le
2
s
h
o
w
s
th
e
n
u
m
b
er
o
f
m
ar
k
er
s
b
ased
o
n
th
e
a
v
er
ag
e
v
alu
e
o
f
ME
o
n
t
h
e
n
atu
r
al
an
d
d
en
tal
p
an
o
r
a
m
ic
i
m
ag
e
s
.
N
u
m
b
er
o
f
m
ar
k
er
1
,
m
ea
n
s
t
h
at
t
h
er
e
i
s
o
n
e
m
ar
k
e
r
f
o
r
o
b
j
ec
t
an
d
o
n
e
m
ar
k
er
f
o
r
b
ac
k
g
r
o
u
n
d
s
h
o
w
t
h
e
s
m
alles
t
v
al
u
e
o
f
ME
co
m
p
ar
ed
w
ith
t
w
o
a
n
d
th
r
ee
m
ar
k
e
r
s
.
T
ab
le
2
.
Dete
r
m
i
n
atio
n
o
f
Ma
r
k
er
Nu
m
b
er
I
mag
e
s
N
u
mb
e
r
o
f
M
a
r
k
e
r
s &
M
i
scl
a
ssi
f
i
c
a
t
i
o
n
Er
r
o
r
(
%)
1
2
3
N
a
t
u
r
a
l
2
.
0
4
5
.
0
3
5
.
0
7
D
e
n
t
a
l
P
a
n
o
r
a
mi
c
5
.
4
7
8
.
8
2
1
0
.
3
1
4
.
3
.
E
x
peri
m
e
nt
Ana
ly
s
is
o
f
F
uzzy
Reg
io
n
M
er
g
ing
B
in
ar
y
r
eg
io
n
m
er
g
i
n
g
(
B
R
M)
ap
p
r
o
ac
h
,
as p
r
o
p
o
s
ed
[
1
0
]
is
n
o
t so
e
f
f
ec
t
iv
e
f
o
r
i
m
ag
e
s
t
h
a
t h
a
v
e
a
lo
t
o
f
a
m
b
ig
u
o
u
s
r
eg
io
n
s
.
T
h
e
am
b
ig
u
o
u
s
r
eg
io
n
w
i
ll
lead
to
o
v
er
-
s
e
g
m
en
tatio
n
b
ec
au
s
e
th
er
e
ar
e
s
o
m
e
r
eg
io
n
s
th
at
h
a
v
e
t
w
o
v
a
lu
e
s
o
f
i
n
f
o
r
m
atio
n
,
b
o
th
a
s
b
ac
k
g
r
o
u
n
d
a
n
d
o
b
j
ec
t.
T
o
o
v
er
co
m
e
th
i
s
p
r
o
b
lem
,
th
i
s
s
t
u
d
y
p
r
o
p
o
s
e
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
ts
to
f
i
n
d
th
e
g
r
ea
te
s
t
s
i
m
ilar
it
y
v
al
u
e
f
o
r
t
h
e
a
m
b
ig
u
o
u
s
r
e
g
io
n
.
Fig
u
r
e
1
2
illu
s
tr
ates
t
h
e
d
if
f
er
en
ce
s
o
f
s
eg
m
e
n
tatio
n
r
es
u
lt
i
n
th
e
b
in
ar
y
r
eg
io
n
m
er
g
in
g
(
B
R
M
)
an
d
th
e
p
r
o
p
o
s
ed
f
u
zz
y
r
e
g
io
n
m
er
g
i
n
g
(
F
R
M)
.
I
n
Fig
u
r
e
1
2
(
b
)
,
w
e
ca
n
s
ee
t
h
at
ea
c
h
r
e
g
io
n
h
a
s
o
n
l
y
a
p
r
o
b
ab
ilit
y
v
al
u
e
o
f
0
an
d
1
,
in
co
n
tr
ast to
p
r
o
p
o
s
ed
m
et
h
o
d
in
Fi
g
u
r
e
1
2
(
c)
w
h
er
e
th
e
v
al
u
e
o
f
ea
c
h
r
eg
io
n
r
an
g
e
d
b
et
w
ee
n
0
an
d
1
.
(
a)
(
b
)
(
c)
Fig
u
r
e
1
2
.
(
a)
I
n
itial se
g
m
e
n
t
atio
n
(
b
)
B
in
ar
y
R
eg
io
n
Me
r
g
i
n
g
,
(
c)
Fu
zz
y
R
e
g
io
n
Me
r
g
i
n
g
5.
CO
NCLU
SI
O
NS
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
4
0
2
–
3
4
1
0
3410
I
n
th
is
s
tu
d
y
,
w
e
p
r
o
p
o
s
e
a
n
e
w
s
tr
ateg
y
f
o
r
r
eg
io
n
m
er
g
in
g
p
r
o
ce
s
s
u
s
i
n
g
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
f
o
r
i
m
ag
e
s
e
g
m
en
tatio
n
.
Me
an
-
s
h
i
f
t
al
g
o
r
ith
m
w
a
s
i
m
p
le
m
e
n
ted
to
g
et
i
n
i
tial
s
e
g
m
e
n
tat
io
n
.
I
n
th
e
m
ar
k
i
n
g
p
r
o
ce
s
s
,
u
s
er
g
i
v
e
m
ar
k
er
f
o
r
th
e
ap
p
r
o
p
r
iate
o
b
j
ec
t
an
d
b
ac
k
g
r
o
u
n
d
r
eg
io
n
.
Ou
r
co
n
tr
ib
u
tio
n
o
f
th
is
r
esear
c
h
is
to
s
ep
ar
ate
a
m
b
ig
u
o
u
s
r
eg
io
n
s
i
n
t
h
e
i
m
a
g
e
u
s
i
n
g
f
u
zz
y
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
en
t.
B
ased
o
n
th
e
ex
p
er
i
m
e
n
tal
r
es
u
lt
s
o
n
t
h
e
n
atu
r
al
an
d
d
e
n
tal
p
an
o
r
a
m
ic
i
m
a
g
es
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
s
u
cc
e
s
s
f
u
l
l
y
s
eg
m
e
n
ted
th
e
i
m
a
g
es
w
it
h
a
n
av
er
ag
e
v
a
lu
e
o
f
m
i
s
clas
s
i
f
ic
atio
n
er
r
o
r
(
ME
)
5
.
4
7
%
an
d
1
.
9
6
%,
r
esp
ec
tiv
el
y
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
n
l
y
m
ea
s
u
r
es
i
n
f
o
r
m
atio
n
f
r
o
m
t
h
e
g
r
a
y
le
v
el
f
ea
t
u
r
es
a
n
d
m
e
m
b
er
s
h
ip
f
u
n
c
tio
n
.
T
h
er
ef
o
r
e,
co
m
b
in
i
n
g
in
f
o
r
m
atio
n
f
r
o
m
o
t
h
er
f
ea
t
u
r
es
s
u
c
h
as
s
p
atial
i
n
f
o
r
m
atio
n
,
te
x
t
u
r
e,
an
d
s
h
ap
e
f
o
r
r
eg
io
n
m
er
g
i
n
g
p
r
o
ce
s
s
ca
n
b
e
d
ev
elo
p
ed
f
u
r
th
er
i
n
o
r
d
er
to
o
b
tain
m
o
r
e
ac
cu
r
ate
s
e
g
m
e
n
t
atio
n
r
esu
l
ts
.
RE
F
E
R
E
NC
E
S
[1
]
D.
A
.
F
o
rsy
th
a
n
d
J.
P
o
n
c
e
,
“
Co
m
p
u
ter V
isio
n
:
A
M
o
d
e
rn
A
p
p
ro
a
c
h
,
”
P
re
n
ti
c
e
Ha
ll
,
2
0
0
2
.
[2
]
T
.
P
a
v
li
d
is,
“
S
tru
c
t
u
ra
l
P
a
tt
e
rn
R
e
c
o
g
n
it
io
n
,
”
Be
rli
n
He
i
d
e
lb
e
rg
:
S
p
rin
g
e
r
-
V
e
rlag
,
1
9
7
7
.
[3
]
A
.
Z.
A
ri
f
in
,
e
t
a
l.
,
“
Re
g
io
n
M
e
rg
in
g
S
trate
g
y
Us
in
g
S
tatisti
c
a
l
A
n
a
l
y
si
s
f
o
r
In
tera
c
ti
v
e
I
m
a
g
e
S
e
g
m
e
n
tatio
n
o
n
De
n
tal
P
a
n
o
ra
m
ic
Ra
d
io
g
ra
p
h
s,
”
In
ter
n
a
ti
o
n
a
l
Rev
iew
o
n
Co
m
p
u
ter
s
a
n
d
S
o
f
twa
re
,
v
o
l
/i
ss
u
e
:
12
(
1
)
,
p
p
.
6
3
-
7
4
,
2
0
1
7
.
[4
]
N.
Ka
m
a
ru
d
d
in
,
e
t
a
l.
,
“
L
o
c
a
l
re
g
io
n
-
b
a
se
d
a
c
m
w
it
h
f
ra
c
ti
o
n
a
l
c
a
lcu
lu
s
f
o
r
b
o
u
n
d
a
ry
se
g
m
e
n
tatio
n
in
im
a
g
e
s
w
it
h
in
ten
si
ty
in
h
o
m
o
g
e
n
e
it
y
,
”
M
a
la
y
s
ia
n
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l
/i
ss
u
e
:
29
(
2
)
,
p
p
.
1
2
4
-
1
4
4
,
2
0
1
6
.
[5
]
C.
S
c
ien
c
e
a
n
d
A
.
P
ra
d
e
sh
,
“
Im
a
g
e
S
e
g
m
e
n
tatio
n
Ba
se
d
o
n
D
o
u
b
l
y
T
ru
n
c
a
ted
G
e
n
e
ra
li
z
e
d
L
a
p
lac
e
M
ix
tu
r
e
M
o
d
e
l
a
n
d
K
M
e
a
n
s
Clu
ste
rin
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l
/i
ss
u
e
:
6
(
5
)
,
p
p
.
2
1
8
8
–
2
1
9
6
,
2
0
1
6
.
[6
]
K.
Ha
ris,
e
t
a
l.
,
“
Hy
b
rid
im
a
g
e
se
g
m
e
n
tatio
n
u
sin
g
w
a
ters
h
e
d
s
a
n
d
f
a
st
re
g
io
n
m
e
rg
in
g
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l
/i
ss
u
e
:
7
(
12
)
,
p
p
.
1
6
8
4
–
1
6
9
9
,
1
9
9
8
.
[7
]
H.
Ya
o
,
e
t
a
l.
,
“
A
n
i
m
p
ro
v
e
d
K
-
m
e
a
n
s
c
lu
ste
rin
g
a
lg
o
rit
h
m
fo
r
f
is
h
i
m
a
g
e
se
g
m
e
n
tatio
n
,
”
M
a
th
e
ma
t
ica
l
a
n
d
Co
mp
u
ter
M
o
d
e
ll
in
g
,
v
o
l
/i
ss
u
e
:
58
(
3
-
4
)
,
p
p
.
7
9
0
–
7
9
8
,
2
0
1
3
.
[8
]
K.
M
c
G
u
in
n
e
ss
a
n
d
N.
E.
O’Co
n
n
o
r,
“
A
c
o
m
p
a
ra
ti
v
e
e
v
a
lu
a
ti
o
n
o
f
in
ter
a
c
ti
v
e
se
g
m
e
n
tatio
n
a
lg
o
rit
h
m
s,
”
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l
/
issu
e
:
43
(
2
)
,
p
p
.
4
3
4
–
4
4
4
,
2
0
1
0
.
[9
]
S
.
Ho
re
,
e
t
a
l.
,
“
A
n
In
teg
ra
ted
In
tera
c
ti
v
e
Tec
h
n
iq
u
e
f
o
r
Im
a
g
e
S
e
g
m
e
n
tatio
n
u
si
n
g
S
tac
k
b
a
se
d
S
e
e
d
e
d
Re
g
io
n
G
ro
w
in
g
a
n
d
T
h
re
sh
o
ld
i
n
g
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l
/
issu
e
:
6
(
6
)
,
p
p
.
2
7
7
3
,
2
0
1
6
.
[1
0
]
J.
Ni
n
g
,
e
t
a
l.
,
“
In
tera
c
ti
v
e
i
m
a
g
e
se
g
m
e
n
tatio
n
b
y
m
a
x
i
m
a
l
s
i
m
il
a
rit
y
b
a
se
d
re
g
io
n
m
e
r
g
in
g
,
”
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l
/i
ss
u
e
:
43
(
2
)
,
p
p
.
4
4
5
-
4
5
6
,
2
0
1
0
.
[1
1
]
P
.
S
a
lem
b
ier
a
n
d
L
.
G
a
rrid
o
,
“
Bin
a
ry
p
a
rti
ti
o
n
tree
a
s
a
n
e
ff
ici
e
n
t
re
p
re
se
n
tatio
n
f
o
r
i
m
a
g
e
p
ro
c
e
ss
in
g
,
se
g
m
e
n
tatio
n
,
a
n
d
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l
/
issu
e
:
9
(
4
)
,
p
p
.
5
6
1
–
5
7
6
,
2
0
0
0
.
[1
2
]
A
.
S
.
S
a
n
k
o
h
,
e
t
a
l.
,
“
Ex
trac
ted
P
ix
e
ls
S
im
il
a
rit
y
F
e
a
tu
re
s
(EP
S
F
)
u
sin
g
In
tera
c
ti
v
e
I
m
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
s,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s
,
v
o
l.
1
3
6
,
p
p
.
1
-
8
,
2
0
1
6
.
[1
3
]
A
.
Z.
A
ri
f
in
,
e
t
a
l
.
,
“
Im
a
g
e
th
re
sh
o
ld
in
g
u
si
n
g
u
l
traf
u
z
z
in
e
ss
o
p
ti
m
iza
ti
o
n
b
a
se
d
o
n
ty
p
e
II
f
u
z
z
y
s
e
ts,
”
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
stru
me
n
ta
ti
o
n
,
C
o
mm
u
n
ica
ti
o
n
s,
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
a
n
d
Bi
o
me
d
ica
l
En
g
i
n
e
e
rin
g
(
ICICI
-
BM
E)
,
p
p
.
1
-
6
,
2
0
0
9
.
[1
4
]
G
.
Q.
O.
P
ra
tam
a
su
n
u
,
e
t
a
l.
,
“
Im
a
g
e
th
re
sh
o
ld
i
n
g
b
a
se
d
o
n
in
d
e
x
o
f
f
u
z
z
in
e
s
s
a
n
d
f
u
z
z
y
si
m
il
a
rit
y
m
e
a
su
re
,
”
IEE
E
8
th
I
n
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
C
o
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
A
p
p
li
c
a
ti
o
n
s (
IW
CIA)
,
p
p
.
1
6
1
-
1
6
6
,
2
0
1
5
.
[1
5
]
R.
Do
n
g
,
e
t
a
l
.
,
“
In
tera
c
ti
v
e
ima
g
e
se
g
m
e
n
tatio
n
w
it
h
c
o
lo
r
a
n
d
t
e
x
tu
re
in
f
o
r
m
a
ti
o
n
b
y
re
g
io
n
m
e
rg
in
g
,
”
Ch
in
e
se
Co
n
tro
l
a
n
d
De
c
isio
n
C
o
n
fer
e
n
c
e
(
CCDC
)
,
v
o
l
/i
ss
u
e
:
1
(
3
)
,
p
p
.
7
7
7
–
7
8
3
,
2
0
1
6
.
[1
6
]
R.
In
d
ra
sw
a
ri,
e
t
a
l.
,
“
Tee
th
se
g
m
e
n
tatio
n
o
n
d
e
n
tal
p
a
n
o
ra
m
ic
ra
d
io
g
ra
p
h
s
u
si
n
g
d
e
c
im
a
ti
o
n
-
f
re
e
d
irec
ti
o
n
a
l
f
il
ter
b
a
n
k
th
re
sh
o
l
d
in
g
a
n
d
m
u
lt
istag
e
a
d
a
p
ti
v
e
th
re
sh
o
ld
i
n
g
,
”
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
ti
o
n
&
Co
mm
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
y
ste
ms
(
ICT
S
)
,
p
p
.
4
9
-
5
4
,
2
0
1
5
.
[1
7
]
M
.
Jia
n
a
n
d
C.
Ju
n
g
,
“
In
ter
a
c
ti
v
e
ima
g
e
se
g
m
e
n
tatio
n
u
sin
g
a
d
a
p
t
iv
e
c
o
n
stra
in
t
p
ro
p
a
g
a
ti
o
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Im
a
g
e
Pr
o
c
e
ss
in
g
,
v
o
l
/i
ss
u
e
:
25
(
3
)
,
p
p
.
1
3
0
1
-
1
3
1
1
,
2
0
1
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.