I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
4
,
No
.
3
,
Sep
tem
b
er
201
5
,
p
p
.
81
~
88
I
SS
N:
2252
-
8938
81
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
J
AI
The O
p
ti
m
a
l Thr
esho
ld
ing
Techni
que f
o
r I
m
a
g
e S
e
g
m
entaio
n
Using
F
u
zz
y
O
tsu
Metho
d
P.
Ra
m
ba
b
u
1
,
C.
Na
g
a
Ra
j
u
2
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
JN
T
UK
,
Ka
k
in
a
d
a
,
In
d
ia
.
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
&
En
g
in
e
e
rin
g
,
YSR
E
n
g
in
e
e
ri
n
g
c
o
ll
e
g
e
o
f
Y V
U,
P
r
o
d
d
a
tu
r
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
2
,
2
0
1
5
R
ev
i
s
ed
J
u
l
y
1
2
,
2
0
1
5
A
cc
ep
ted
A
u
g
u
s
t
1
,
2
0
1
5
Im
a
g
e
S
e
g
m
e
n
tatio
n
p
lay
s
a
v
e
r
y
i
m
p
o
rtan
t
ro
le
i
n
im
a
g
e
p
ro
c
e
ss
in
g
.
T
h
e
sin
g
le
-
m
in
d
e
d
n
e
ss
o
f
i
m
a
g
e
s
e
g
m
e
n
tatio
n
is
to
p
a
rti
ti
o
n
t
h
e
im
a
g
e
in
to
a
se
t
o
f
d
isc
o
n
n
e
c
ted
re
g
io
n
s
w
it
h
th
e
h
o
m
o
g
e
n
e
o
u
s
a
n
d
u
n
if
o
rm
a
tt
rib
u
tes
li
k
e
in
ten
sity
,
to
n
e
,
c
o
l
o
r
a
n
d
tex
tu
re
.
T
h
e
re
a
re
v
a
rio
u
s
m
e
th
o
d
s
f
o
r
im
a
g
e
se
g
m
e
n
tatio
n
b
u
t
n
o
m
e
th
o
d
is
s
u
it
a
b
le f
o
r
lo
w
c
o
n
tras
t
im
a
g
e
s.
In
th
is
p
a
p
e
r,
w
e
a
re
p
re
se
n
ti
n
g
a
n
e
ff
icie
n
t
a
n
d
o
p
ti
m
a
l
th
re
sh
o
ld
in
g
im
a
g
e
se
g
m
e
n
tatio
n
tec
h
n
iq
u
e
th
a
t
c
a
n
b
e
u
se
d
t
o
se
p
a
ra
te
th
e
o
b
jec
t
a
n
d
b
a
c
k
g
ro
u
n
d
p
ix
e
ls
o
f
th
e
im
a
g
e
to
i
m
p
ro
v
e
th
e
q
u
a
li
ty
o
f
lo
w
c
o
n
tras
t
ima
g
e
s.
T
h
is
in
n
o
v
a
ti
v
e
m
e
th
o
d
c
o
n
si
sts
o
f
tw
o
ste
p
s.
F
ir
stly
f
u
z
z
y
lo
g
ics
a
re
u
se
d
to
f
in
d
o
p
ti
m
u
m
m
e
a
n
v
a
lu
e
u
sin
g
S
-
c
u
rv
e
w
it
h
a
u
to
m
a
ti
c
se
le
c
ti
o
n
o
f
c
o
n
tro
ll
e
d
p
a
ra
m
e
ter
s
to
a
v
o
id
t
h
e
f
u
z
z
in
e
ss
in
th
e
i
m
a
g
e
.
S
e
c
o
n
d
ly
,
th
e
f
u
z
z
y
lo
g
i
c
’s
o
p
ti
m
a
l
th
re
sh
o
l
d
v
a
lu
e
u
se
d
in
Otsu
m
e
th
o
d
to
im
p
ro
v
e
th
e
c
o
n
tras
t
o
f
th
e
im
a
g
e
.
T
h
is
m
e
th
o
d
,
g
iv
e
s
b
e
tt
e
r
re
su
lt
s
th
a
n
trad
it
io
n
a
l
Otsu
a
n
d
F
u
z
z
y
lo
g
ic
tec
h
n
iq
u
e
s.
T
h
e
g
ra
p
h
s an
d
ta
b
les
o
f
v
a
lu
e
s
sh
o
w
th
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
is
su
p
e
rio
r
to
trad
it
i
o
n
a
l
m
e
th
o
d
s.
K
ey
w
o
r
d
:
B
C
V
Fu
zz
y
L
o
g
ic
Ots
u
Seg
m
en
tatio
n
Co
p
y
rig
h
t
©
2
0
1
5
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
:
P.
R
am
b
ab
u
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
&
E
n
g
in
ee
r
i
n
g
,
J
a
w
ah
ar
lal
Ne
h
r
u
T
ec
h
n
o
lo
g
ic
al
Un
i
v
er
s
it
y
Kak
in
ad
a,
Kak
i
n
ad
a,
An
d
h
r
a
P
r
ad
esh
,
I
n
d
ia.
E
m
ail:
r
p
e
m
u
la
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
I
m
ag
e
s
eg
m
e
n
tatio
n
p
la
y
s
a
n
i
m
p
o
r
tan
t
r
o
le
i
n
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
an
d
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
.
I
t
is
o
f
te
n
u
s
ed
to
p
ar
titi
o
n
an
i
m
a
g
e
i
n
to
s
ep
ar
ate
r
eg
io
n
s
,
w
h
ic
h
id
ea
ll
y
co
r
r
esp
o
n
d
to
d
if
f
er
en
t
r
ea
l
w
o
r
ld
o
b
j
ec
ts
.
I
t
is
a
m
aj
o
r
s
tep
to
w
ar
d
s
co
n
te
n
t
a
n
al
y
s
i
s
an
d
i
m
ag
e
u
n
d
er
s
tan
d
i
n
g
.
Ots
u
m
eth
o
d
[
1
]
is
a
v
er
y
p
o
p
u
lar
g
lo
b
al
au
to
m
atic
t
h
r
es
h
o
lo
d
in
g
tech
n
iq
u
e,
w
h
ich
ca
n
b
e
ap
p
lied
to
a
w
id
e
r
an
g
e
o
f
ap
p
licatio
n
s
.
T
h
is
m
et
h
o
d
is
s
elec
ted
b
y
m
ax
i
m
izi
n
g
t
h
e
d
i
s
cr
i
m
i
n
a
n
t
m
ea
s
u
r
e
η
.
Ot
s
u
m
et
h
o
d
is
n
o
n
p
ar
a
m
etr
ic
a
n
d
u
n
s
u
p
er
v
is
ed
n
a
tu
r
e
o
f
t
h
r
es
h
o
ld
s
elec
tio
n
.
I
n
o
r
d
er
to
in
cr
ea
s
es
t
h
e
e
f
f
ec
tiv
e
n
es
s
o
f
ca
lcu
latio
n
f
o
r
th
e
o
p
tim
a
l
th
r
es
h
o
ld
s
o
f
an
i
m
a
g
e,
P
in
g
-
S
u
n
g
,
et
al
[
2
]
,
s
u
g
g
ested
a
f
aster
v
er
s
io
n
o
f
Ot
s
u
’
s
m
et
h
o
d
.
I
n
th
is
m
et
h
o
d
,
f
ir
s
t,
a
co
n
d
itio
n
is
d
ef
i
n
ed
t
h
at
m
a
x
i
m
izi
n
g
th
e
m
o
d
if
ied
b
et
w
ee
n
-
c
lass
v
ar
ian
ce
(
B
C
V)
th
at
is
s
a
m
e
as
to
t
h
e
co
n
d
itio
n
o
f
m
a
x
i
m
izi
n
g
t
h
e
u
s
u
al
B
C
V
is
p
r
o
p
o
s
ed
f
o
r
i
m
ag
e
s
e
g
m
en
ta
ti
o
n
.
B
ased
o
n
t
h
is
co
n
d
itio
n
,
in
o
r
d
er
to
f
in
d
th
e
o
p
tim
al
t
h
r
es
h
o
ld
v
alu
e
a
r
ec
u
r
s
i
v
e
alg
o
r
it
h
m
i
s
d
esig
n
e
d
.
B
ased
o
n
im
p
r
o
v
ed
th
r
es
h
o
ld
in
g
al
g
o
r
ith
m
,
C
h
.
H
i
m
a
B
i
n
d
u
[
3
]
,
p
r
o
p
o
s
ed
a
n
ew
o
p
ti
m
ized
Ot
s
u
m
et
h
o
d
.
T
h
is
m
eth
o
d
r
ed
u
ce
s
th
e
o
p
er
atin
g
ti
m
e
an
d
i
n
cr
ea
s
es th
e
r
ep
ar
ab
ilit
y
f
ac
to
r
i
n
m
e
d
ical
i
m
a
g
e
s
e
g
m
en
ta
tio
n
.
D
L
i
u
,
et
al
[
4
]
p
r
o
v
es
th
at
i
n
m
u
l
tile
v
el
t
h
r
esh
o
ld
i
n
g
b
ased
o
n
m
i
n
i
m
izi
n
g
th
e
w
i
t
h
in
-
cla
s
s
v
ar
ian
ce
,
t
h
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
o
f
b
o
th
Ots
u
m
e
th
o
d
a
n
d
K
-
m
ea
n
s
m
et
h
o
d
is
s
a
m
e.
I
n
o
r
d
er
to
d
o
m
u
lti
lev
el
th
r
e
s
h
o
ld
i
n
g
,
a
t
w
o
-
s
tag
e
Ots
u
o
p
tim
izatio
n
ap
p
r
o
ac
h
w
a
s
p
r
o
p
o
s
ed
b
y
D
H
u
n
a
n
g
et
al
[
5
]
.
T
h
is
m
eth
o
d
is
ca
lled
as
m
o
d
i
f
ied
t
w
o
-
s
ta
g
e
m
u
lti
th
r
es
h
o
ld
Ot
s
u
(
T
SMO)
.
T
h
is
p
r
o
ce
d
u
r
e
g
i
v
e
s
t
h
e
s
a
m
e
r
es
u
lt
s
a
s
o
b
tai
n
ed
b
y
u
s
i
n
g
tr
ad
itio
n
al
Ot
s
u
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
3
,
Sep
tem
b
e
r
201
5
:
81
–
88
82
m
et
h
o
d
.
T
h
e
m
ain
ad
v
a
n
ta
g
e
o
f
th
is
m
et
h
o
d
is
d
ec
r
ea
s
es
th
e
r
eq
u
ir
ed
co
m
p
u
tatio
n
ti
m
e
f
o
r
lar
g
e
n
u
m
b
er
o
f
clu
s
ter
s
.
X
Ya
n
g
et
al,
[
6
]
,
p
r
esen
ted
a
n
e
w
tec
h
n
iq
u
e
t
h
at
i
m
p
r
o
v
e
s
th
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
Ots
u
alg
o
r
ith
m
.
HJ
Vala
et
al
[
7
]
,
p
r
o
v
id
es th
e
in
f
o
r
m
atio
n
ab
o
u
t
th
e
d
if
f
er
e
n
t O
t
s
u
al
g
o
r
ith
m
s
an
d
co
m
p
ar
e
th
e
p
er
f
o
r
m
an
ce
s
o
f
th
ese
m
et
h
o
d
s
.
VP
P
atel
et
al
[
8
]
im
p
le
m
e
n
ted
th
e
Ot
s
u
m
eth
o
d
in
d
if
f
er
en
t
ap
p
r
o
ac
h
es
li
k
e
iter
atio
n
ap
p
r
o
ac
h
an
d
cu
s
to
m
ap
p
r
o
ac
h
.
T
h
e
y
i
m
p
le
m
en
ted
t
h
e
s
e
te
ch
n
iq
u
es
in
M
A
T
L
A
B
a
n
d
c
o
m
p
ar
e
t
h
e
r
es
u
lt
s
an
d
s
h
o
w
s
t
h
at
b
o
t
h
h
a
s
g
i
v
en
al
m
o
s
t
th
e
s
a
m
e
t
h
r
es
h
o
ld
v
alu
e
f
o
r
s
e
g
m
e
n
ti
n
g
th
e
i
m
a
g
e
b
u
t
cu
s
to
m
ap
p
r
o
ac
h
r
eq
u
ir
es
less
co
m
p
u
tatio
n
s
.
F
ir
s
tl
y
,
th
e
id
ea
o
f
e
n
t
r
o
p
y
f
o
r
th
r
es
h
o
ld
in
g
w
as
u
s
ed
b
y
P
u
n
[
1
0
]
,
th
is
w
a
s
e
x
ten
d
ed
b
y
Kap
u
r
et
al
[
9
]
,
in
en
tr
o
p
y
b
ased
al
g
o
r
ith
m
s
.
T
h
is
m
et
h
o
d
co
n
cl
u
d
es
th
at
w
h
e
n
th
e
s
u
m
m
atio
n
o
f
th
e
b
ac
k
g
r
o
u
n
d
an
d
o
b
j
ec
t
en
tr
ies
r
ea
ch
es
it
s
m
a
x
i
m
u
m
,
th
e
t
h
r
esh
o
ld
v
al
u
e
i
s
o
b
tain
ed
.
B
y
u
s
i
n
g
th
e
p
ix
el
s
g
r
a
y
v
alu
e
a
n
d
lo
ca
l
av
er
ag
e
o
f
n
eig
h
b
o
r
h
o
o
d
g
r
ay
v
al
u
es
o
f
t
h
e
p
ix
el
s
,
a
2
D
h
is
to
g
r
a
m
w
as
d
eter
m
in
ed
a
n
d
b
y
u
s
in
g
t
h
is
A
b
u
taleb
ex
te
n
d
ed
Kap
u
r
’
s
m
et
h
o
d
u
s
i
n
g
2
D
e
n
tr
o
p
ies
[
1
1
]
.
A
s
a
n
en
h
a
n
ce
m
en
t,
th
i
s
tech
n
iq
u
e
i
s
s
i
m
p
li
f
ied
b
y
A
D
B
r
in
k
[
1
2
]
.
I
n
1
9
6
5
,
Z
ad
eh
p
r
o
p
o
s
ed
f
u
zz
y
lo
g
ic
i
n
h
i
s
r
e
s
ea
r
ch
Fu
zz
y
Sets
[
1
3
]
.
He
w
ell
-
d
ef
in
ed
th
e
f
u
zz
y
s
et
s
an
d
f
u
zz
y
lo
g
ic
i
n
ad
d
itio
n
al
t
o
th
e
m
e
m
b
er
s
h
ip
f
u
n
ct
io
n
wh
ich
as
s
ig
n
ea
c
h
g
r
ad
e
to
a
v
a
lu
e
b
et
w
ee
n
1
an
d
0
an
d
i
n
tr
o
d
u
ce
s
t
h
eo
r
etica
l
b
a
ck
g
r
o
u
n
d
.
I
n
s
e
g
m
en
ta
tio
n
p
r
o
ce
s
s
,
Fu
zz
y
b
a
s
ed
tech
n
iq
u
es
w
er
e
u
s
ed
b
y
n
u
m
er
o
u
s
a
u
th
o
r
s
.
T
o
s
elec
t
t
h
e
t
h
r
es
h
o
ld
v
al
u
e,
c
-
p
ar
titi
o
n
en
tr
o
p
y
f
u
zz
y
w
as
u
s
ed
b
y
C
h
en
g
et
al
[
1
4
]
.
T
o
ac
h
iev
e
t
h
i
s
,
m
a
x
i
m
u
m
e
n
tr
o
p
y
p
r
in
c
ip
le
an
d
f
u
zz
y
c
-
p
ar
t
itio
n
w
as
u
s
ed
.
T
h
e
y
h
a
v
e
as
s
u
m
ed
a
f
i
x
ed
an
d
k
n
o
w
n
n
u
m
b
er
o
f
t
h
e
cl
u
s
te
r
s
an
d
cla
s
s
if
ied
th
e
p
ix
el
s
in
to
t
h
ese
cl
u
s
ter
s
.
T
h
e
u
l
tr
a
-
f
u
zz
y
(
f
u
zz
y
I
I
)
alg
o
r
ith
m
s
u
s
ed
to
f
i
n
d
th
e
t
h
r
esh
o
ld
v
al
u
e
s
u
g
g
ested
b
y
T
izh
o
o
s
h
[
1
5
]
.
C
.
Na
g
a
R
aj
u
et
al
[
1
6
]
,
th
e
y
d
er
i
v
e
f
u
zz
y
r
u
les
f
o
r
π
–
f
u
n
ctio
n
.
B
y
u
s
i
n
g
ef
f
ec
ti
v
e
s
elec
tio
n
o
f
R
e
g
io
n
o
f
I
n
ter
es
t
(
R
OI
)
,
th
is
p
r
o
ce
d
u
r
e
is
to
o
p
tim
ize
th
e
i
m
a
g
e
th
r
es
h
o
ld
.
T
o
esti
m
ate
th
e
f
u
zz
in
e
s
s
o
f
an
i
m
a
g
e
a
n
d
to
d
eter
m
i
n
e
an
ad
eq
u
ate
th
r
esh
o
l
d
v
alu
e,
b
y
u
tili
zi
n
g
th
e
m
e
a
s
u
r
e
o
f
f
u
zz
i
n
es
s
,
Am
b
ar
Du
tta,
e
t
al
[
1
7
]
,
p
r
o
p
o
s
ed
a
t
w
o
-
s
tag
e
f
u
zz
y
s
et
th
eo
r
etic
ap
p
r
o
ac
h
to
i
m
ag
e
th
r
es
h
o
ld
in
g
.
T
o
av
o
id
th
e
f
u
zz
i
n
es
s
i
n
t
h
e
i
m
a
g
e
a
n
d
m
a
k
es
g
o
o
d
r
eg
i
o
n
s
i
n
t
h
e
i
m
a
g
e,
a
n
e
w
s
eg
m
e
n
tatio
n
tec
h
n
iq
u
e
b
y
u
s
i
n
g
t
h
e
f
u
zz
y
lo
g
ic
w
h
ic
h
p
r
o
d
u
ce
o
p
ti
m
al
t
h
r
es
h
o
ld
v
al
u
e
w
a
s
p
r
o
p
o
s
ed
b
y
C
Nag
a
R
aj
u
et
al
[
1
8
]
.
C
Nag
a
R
aj
u
et
al
[
1
9
]
,
p
r
o
p
o
s
ed
a
n
e
w
tec
h
n
iq
u
e
to
ad
d
r
ess
th
e
m
u
lti
-
d
i
m
en
s
io
n
al
o
p
ti
m
ized
p
r
o
b
le
m
w
it
h
o
p
ti
m
al
t
h
r
es
h
o
ld
in
g
u
s
in
g
f
u
zz
y
en
tr
o
p
y
f
o
r
i
m
a
g
e
e
n
h
a
n
ce
m
en
t.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
2.
1
.
O
t
s
u M
e
t
ho
d
Ots
u
m
e
th
o
d
[
1
]
is
a
v
er
y
p
o
p
u
lar
g
lo
b
al
a
u
to
m
at
ic
t
h
r
esh
o
lo
d
in
g
tec
h
n
iq
u
e.
Fo
r
t
h
e
g
i
v
en
i
m
ag
e,
th
e
p
ix
e
ls
ca
n
b
e
d
en
o
ted
in
g
r
a
y
le
v
el
s
,
-
.
A
t
ea
c
h
g
r
a
y
le
v
e
l,
th
e
n
u
m
b
er
o
f
p
i
x
els
d
e
n
o
ted
b
y
an
d
th
e
to
tal
p
ix
el
s
o
f
i
m
a
g
e
b
y
.
T
h
e
g
r
a
y
lev
e
l
h
i
s
to
g
r
a
m
is
n
o
r
m
alize
d
b
y
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
t
io
n
f
u
n
cti
o
n
:
∑
(
1
)
W
e
ass
ig
n
ed
as
th
e
th
r
esh
o
l
d
v
alu
e,
to
class
if
y
t
h
e
b
ac
k
g
r
o
u
n
d
an
d
o
b
j
ec
t
o
f
th
e
i
m
ag
e,
th
e
n
o
r
m
a
lized
f
r
ac
tio
n
o
f
p
i
x
els
w
i
ll b
e
u
s
ed
.
(
)
∑
(
)
(
2
)
(
)
∑
(
)
(
3
)
(
)
(
)
(
4
)
T
h
e
b
ac
k
g
r
o
u
n
d
m
ea
n
a
n
d
o
b
ject
m
ea
n
o
f
g
r
a
y
lev
el
v
al
u
e
o
f
p
ix
el
s
w
ill b
e
:
(
)
∑
(
)
(
)
(
)
∑
(
)
(
5
)
(
)
∑
(
)
(
)
(
)
∑
(
)
(
6
)
T
h
e
w
h
o
le
g
r
a
y
le
v
el
i
m
ag
e,
w
h
o
s
e
m
ea
n
v
al
u
e
is
ca
lc
u
late
d
as
:
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Th
e
Op
tima
l Th
r
esh
o
ld
in
g
Tech
n
iq
u
e
f
o
r
I
ma
g
e
S
e
g
men
ta
io
n
u
s
in
g
F
u
z
z
y…
.
(
P.
R
a
mb
a
b
u
)
83
∑
(
)
∑
(
)
∑
(
)
(
7
)
T
h
e
b
ac
k
g
r
o
u
n
d
v
ar
ia
n
ce
an
d
o
b
j
ec
t v
ar
ian
ce
o
f
g
r
a
y
lev
e
l v
alu
e
o
f
p
ix
e
ls
w
ill b
e
:
(
)
∑
(
)
(
)
∑
(
)
(
)
∑
(
)
(
)
(
8
)
(
)
∑
(
)
(
)
∑
(
)
(
)
∑
(
)
(
)
(
9
)
T
h
en
,
th
e
w
h
o
le
g
r
a
y
le
v
el
i
m
ag
e,
w
h
o
s
e
v
ar
ian
ce
i
s
ca
lcu
la
ted
as
:
∑
(
)
(
)
(
1
0
)
W
ith
in
-
cla
s
s
a
n
d
b
et
w
ee
n
-
clas
s
v
ar
ian
ce
T
h
e
v
ar
ian
ce
ca
n
b
e
d
ef
in
ed
a
s
:
(
)
(
)
(
)
(
)
(
)
(
(
)
)
(
)
(
(
)
)
(
)
(
)
(
1
1
)
W
h
er
e
(
)
is
th
e
w
it
h
i
n
–
class
v
a
r
ian
ce
an
d
(
)
is
th
e
b
et
w
ee
n
-
clas
s
v
ar
ian
ce
.
2
.
1
.
1
.
Det
er
m
ini
ng
t
he
t
hresh
o
ld
Sin
ce
t
h
e
to
tal
v
ar
ia
n
ce
d
o
es n
o
t d
ep
en
d
o
n
,
th
e
m
i
n
i
m
izi
n
g
w
i
ll b
e
th
e
m
a
x
i
m
izi
n
g
.
L
et
’
s
co
n
s
id
er
m
a
x
i
m
izi
n
g
,
w
e
ca
n
r
e
w
r
ite
as
:
,
(
)
(
)
-
(
)
(
)
(
1
2
)
W
h
er
e,
(
)
∑
(
)
.
I
n
o
r
d
er
to
m
ax
i
m
ize
s
,
s
tar
ts
f
r
o
m
th
e
co
m
m
en
ce
m
e
n
t
o
f
th
e
h
i
s
to
g
r
a
m
an
d
ch
ec
k
ea
ch
g
r
a
y
lev
el
i
m
a
g
e
v
alu
e
f
o
r
t
h
e
li
k
el
ih
o
o
d
o
f
b
ein
g
t
h
e
t
h
r
es
h
o
ld
.
Ots
u
m
e
th
o
d
p
r
o
v
ed
th
at
o
p
tim
al
t
h
r
es
h
o
ld
is
th
e
v
al
u
e
t
h
at
m
ax
i
m
ize
t
h
e
b
e
t
w
ee
n
-
clas
s
v
ar
ia
n
ce
as:
*
(
)
+
(
1
3
)
2
.
1
.
2
.
L
i
m
it
a
t
io
ns
o
f
t
he
O
t
s
u
m
et
ho
d
W
e
co
u
ld
n
o
t
f
i
n
d
a
g
o
o
d
u
n
i
o
n
o
f
th
r
es
h
o
ld
s
to
th
e
g
lo
b
al
o
p
ti
m
u
m
f
o
r
t
h
e
g
r
a
y
le
v
el
i
m
ag
e
s
b
y
u
s
i
n
g
th
e
tr
ad
itio
n
al
O
ts
u
alg
o
r
ith
m
.
T
h
e
Ots
u
alg
o
r
it
h
m
i
s
s
u
i
tab
le
o
n
l
y
w
h
e
n
th
er
e
ar
e
t
w
o
clas
s
es
i
n
th
e
i
m
a
g
e.
I
f
th
er
e
ex
i
s
ts
m
o
r
e
t
h
an
t
w
o
cla
s
s
es
i
n
th
e
i
m
a
g
e,
th
e
m
et
h
o
d
m
u
s
t
b
e
cu
s
to
m
ize
d
in
o
r
d
er
to
d
ec
id
e
th
e
m
u
lti
t
h
r
esh
o
ld
s
.
I
t
allo
w
s
th
e
lar
g
est
a
m
o
n
g
-
cla
s
s
v
ar
ia
n
ce
an
d
th
e
least
in
-
cla
s
s
v
ar
i
an
ce
.
T
h
e
im
a
g
e
is
d
iv
id
es
in
to
t
w
o
g
r
o
u
p
s
b
y
u
s
in
g
Ots
u
alg
o
r
it
h
m
,
y
et
n
o
ac
tu
al
s
e
n
s
e
is
m
ad
e
b
y
d
iv
i
s
io
n
b
ec
au
s
e
o
f
n
o
s
u
itab
le
m
ea
n
v
al
u
e
ca
lc
u
latio
n
w
it
h
eq
u
atio
n
(
1
5
)
.
I
n
v
ar
iab
le
illu
m
i
n
atio
n
co
n
d
itio
n
s
,
th
i
s
m
eth
o
d
co
u
ld
n
o
t
b
e
ap
p
lied
s
tr
aig
h
t.
T
o
av
o
id
t
h
is
,
F
u
zz
y
S
-
cu
r
v
e
m
e
m
b
er
s
h
i
p
f
u
n
ct
io
n
i
s
u
s
ed
to
ca
lc
u
late
th
e
o
p
ti
m
u
m
m
ea
n
v
alu
e.
2
.
2
.
F
uzzy
B
a
s
ed
M
et
ho
do
lo
g
y
A
b
u
taleb
[
1
1
]
an
d
A
D
B
r
in
k
[
1
2
]
d
id
s
o
m
e
g
o
o
d
w
o
r
k
i
n
o
b
tain
i
n
g
t
h
e
s
e
g
m
e
n
tatio
n
o
f
a
g
r
a
y
i
m
a
g
e
in
co
r
p
o
r
atin
g
th
e
s
p
atial
co
r
r
elatio
n
a
m
o
n
g
th
e
p
i
x
els
o
f
th
e
i
m
a
g
e
b
y
co
n
s
tr
u
cti
n
g
th
e
2
D
h
i
s
to
g
r
a
m
.
Fu
n
d
a
m
e
n
tall
y
t
h
ese
m
et
h
o
d
s
attr
ac
t
m
a
x
i
m
u
m
e
n
tr
o
p
y
cr
it
er
io
n
f
u
n
c
tio
n
to
es
tab
lis
h
th
e
o
p
ti
m
al
t
h
r
esh
o
ld
f
o
r
an
y
g
i
v
en
i
m
a
g
e.
Me
asu
r
es
o
f
f
u
zz
i
n
ess
i
n
co
n
tr
ast
to
f
u
zz
y
m
ea
s
u
r
es
in
d
ic
ate
th
e
d
eg
r
ee
o
f
f
u
zz
i
n
es
s
o
f
f
u
zz
y
s
et
.
T
h
e
m
e
m
b
er
s
h
ip
d
eg
r
ee
o
f
an
y
v
al
u
e
in
t
h
e
u
n
i
v
er
s
e
o
f
d
is
c
o
u
r
s
e
ca
n
b
e
e
s
ti
m
ated
b
y
u
s
i
n
g
a
n
y
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
.
T
h
e
m
e
m
b
er
s
h
ip
d
eg
r
ee
ca
n
b
e
e
x
p
r
es
s
ed
b
y
a
m
ath
e
m
atica
l
f
u
n
ct
io
n
(
)
th
at
allo
c
ates,
to
ea
ch
ele
m
e
n
t
in
th
e
s
et,
a
m
e
m
b
er
s
h
ip
d
eg
r
ee
b
etw
ee
n
0
to
1
.
L
et
b
e
th
e
u
n
i
v
er
s
e
o
f
d
is
co
u
r
s
e
an
d
is
an
elem
e
n
t
of
.
Fu
zz
y
s
et
in
is
d
ef
i
n
ed
as
{
(
(
)
)
}
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
3
,
Sep
tem
b
e
r
201
5
:
81
–
88
84
Fig
u
r
e
1
.
T
y
p
ical
S
h
ap
e
o
f
S
–
Me
m
b
er
s
h
ip
F
u
n
ctio
n
S
-
m
e
m
b
er
s
h
ip
f
u
n
ctio
n
is
u
s
e
d
f
o
r
m
o
d
eli
n
g
t
h
e
m
e
m
b
er
s
h
ip
d
eg
r
ee
s
.
T
h
is
f
u
n
ctio
n
i
s
s
u
itab
le
to
r
ep
r
esen
t th
e
s
et
o
f
b
r
ig
h
t p
ix
e
ls
if
i
m
a
g
e
is
co
n
s
id
er
ed
as o
n
e
d
im
e
n
s
io
n
al
s
ig
n
al
a
n
d
is
d
ef
i
n
ed
as
:
(
)
(
)
(
)
∫
∫
.
/
∫
(
.
/
)
∫
(
1
4
)
W
h
er
e
(
)
in
itial
s
ee
d
s
ets,
an
d
co
n
tr
o
ls
S
-
f
u
n
ctio
n
.
2
.
3
.
Aut
o
m
a
t
ic
Sele
ct
io
n o
f
pa
ra
m
et
er
s
T
h
e
S
–
f
u
n
ct
io
n
s
h
o
w
i
n
th
e
Fig
u
r
e
1
ca
n
b
e
c
o
n
tr
o
lled
th
r
o
u
g
h
an
d
p
ar
am
eter
s
.
P
ar
am
et
er
is
ca
lled
th
e
cr
o
s
s
o
v
er
p
o
in
t.
W
h
er
e
th
e
h
i
g
h
er
t
h
e
g
r
a
y
le
v
el
o
f
a
p
ix
el,
h
i
g
h
er
th
e
m
e
m
b
er
s
h
ip
v
al
u
e
an
d
v
ice
v
er
s
a.
Ho
w
e
v
er
th
e
s
elec
tio
n
o
f
p
ar
am
eter
s
is
d
if
f
ic
u
lt
to
au
to
m
at
e
t
h
e
tech
n
iq
u
e.
Her
e
th
e
m
ea
n
(
)
an
d
s
tan
d
ar
d
d
ev
iatio
n
(
)
ar
e
ca
lcu
lated
f
r
o
m
eq
u
at
io
n
s
(
1
5
)
an
d
(
1
6
)
,
f
u
zz
y
s
ee
d
s
et
v
al
u
e
s
,
an
d
ar
e
esti
m
ated
au
to
m
a
ticall
y
as
:
∑
(
)
(
1
5
)
√
∑
(
)
(
1
6
)
Fro
m
eq
u
atio
n
s
(
1
5
)
an
d
(
1
6
)
f
u
zz
y
s
ee
d
s
et
v
al
u
es
,
an
d
ar
e
esti
m
a
ted
au
to
m
at
icall
y
a
s
:
(
1
7
)
(
1
8
)
(
1
9
)
by
s
u
b
s
tit
u
ti
n
g
t
h
ese
p
ar
a
m
e
t
er
s
in
s
-
c
u
r
v
e
w
e
ca
n
ac
h
ie
v
e
b
etter
s
elec
tio
n
o
f
p
ar
a
m
e
te
r
s
f
o
r
lo
w
co
n
tr
asted
i
m
a
g
es.
3.
Q
UA
L
I
T
Y
P
ARAM
E
T
E
RS
3
.
1
.
M
ea
n
Me
an
is
d
ef
i
n
ed
as
th
e
a
v
e
r
ag
e
g
r
a
y
le
v
els
o
f
t
h
e
i
m
a
g
e.
I
n
g
r
a
y
le
v
el
i
m
ag
e
t
h
e
m
ea
n
i
s
ca
lcu
lated
as
:
(
)
∑
∑
(
)
(
2
0
)
W
h
er
e
(
)
is
th
e
g
r
a
y
le
v
el
i
m
a
g
e,
an
d
ar
e
n
u
m
b
er
o
f
r
o
w
s
an
d
n
u
m
b
er
o
f
co
lu
m
n
s
o
f
r
esu
lt
in
g
i
m
a
g
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Th
e
Op
tima
l Th
r
esh
o
ld
in
g
Tech
n
iq
u
e
f
o
r
I
ma
g
e
S
e
g
men
ta
io
n
u
s
in
g
F
u
z
z
y…
.
(
P.
R
a
mb
a
b
u
)
85
3
.
2
.
St
a
nd
a
rd
Dev
ia
t
io
n
T
h
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
g
r
a
y
lev
el
i
m
ag
e
i
s
ca
lcu
la
ted
as
:
(
)
√
∑
∑
(
(
)
)
(
2
1
)
W
h
er
e
(
)
is
th
e
g
r
a
y
le
v
el
th
e
i
m
ag
e,
an
d
ar
e
th
e
n
u
m
b
er
o
f
r
o
w
s
a
n
d
n
u
m
b
er
o
f
co
lu
m
n
s
o
f
th
e
r
esu
lti
n
g
i
m
a
g
e
a
n
d
is
th
e
m
e
an
o
f
t
h
e
i
m
a
g
e.
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
o
elu
cid
ate
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
,
w
e
co
n
s
id
er
1
7
i
m
ag
e
s
as
a
n
i
m
a
g
e
s
et,
it
co
n
tai
n
s
s
i
m
ilar
a
n
d
d
is
s
i
m
ilar
g
r
a
y
lev
el
h
is
to
g
r
a
m
c
h
ar
ac
ter
is
tic
s
,
ch
a
n
g
i
n
g
f
r
o
m
u
n
i
m
o
d
el
to
m
u
lt
i
m
o
d
el
h
i
s
to
g
r
a
m
s
.
Fo
r
ea
ch
s
a
m
p
le
i
m
a
g
e
it
s
h
is
to
g
r
a
m
an
d
a
g
r
o
u
n
d
tr
u
th
i
m
ag
e,
w
h
ic
h
is
p
r
o
d
u
ce
d
m
an
u
all
y
h
a
s
b
ee
n
u
s
ed
a
s
g
o
ld
s
tan
d
ar
d
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
2
,
to
co
m
p
ar
e
r
es
u
lts
an
d
th
eir
p
er
f
o
r
m
an
ce
.
W
e
u
n
d
er
tak
e
t
h
is
p
r
o
ce
s
s
with
t
w
o
m
ea
s
u
r
es
s
i
m
ilar
it
y
a
n
d
d
iv
er
s
it
y
b
et
w
ee
n
t
h
e
o
u
t
p
u
t
i
m
a
g
e
an
d
it
s
co
r
r
esp
o
n
d
in
g
g
r
o
u
n
d
tr
u
t
h
i
m
ag
e.
Fro
m
th
e
e
x
p
er
i
m
e
n
t
s
f
o
r
ea
ch
te
s
t
i
m
a
g
e
w
e
o
b
tain
m
ea
n
(
μ
)
co
m
p
u
ted
f
r
o
m
eq
u
at
io
n
(
2
0
)
is
co
m
p
ar
ed
w
it
h
g
o
ld
s
tan
d
ar
d
i
m
a
g
es
b
y
al
l
th
r
ee
d
i
f
f
er
e
n
t
m
et
h
o
d
s
in
cl
u
d
in
g
Ot
s
u
,
Fu
zz
y
an
d
P
r
o
p
o
s
ed
is
s
h
o
w
n
in
T
ab
le
1
.
Fig
u
r
e
3
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
o
f
m
ea
n
s
(
μ
)
o
f
th
r
ee
d
if
f
er
en
t
m
et
h
o
d
s
co
n
tai
n
in
g
Ot
s
u
,
F
u
zz
y
an
d
P
r
o
p
o
s
ed
.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
g
i
v
es
t
h
e
o
p
ti
m
u
m
t
h
r
es
h
o
ld
v
al
u
e
co
m
p
ar
ed
to
th
e
o
th
er
t
w
o
m
e
th
o
d
s
.
Fro
m
th
e
ex
p
er
i
m
e
n
ts
f
o
r
ea
ch
test
i
m
ag
e
w
e
o
b
tain
s
tan
d
ar
d
d
ev
iatio
n
(
σ
)
co
m
p
u
ted
f
r
o
m
eq
u
atio
n
(
2
1
)
is
co
m
p
ar
ed
w
it
h
g
o
ld
s
tan
d
ar
d
i
m
ag
e
s
b
y
a
ll
t
h
r
ee
d
if
f
er
en
t
m
et
h
o
d
s
in
cl
u
d
in
g
Ots
u
,
Fu
zz
y
an
d
P
r
o
p
o
s
ed
is
s
h
o
w
n
i
n
T
ab
le
2
.
Fig
u
r
e
4
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
o
f
s
ta
n
d
ar
d
d
ev
iatio
n
(
σ
)
o
f
t
h
r
ee
d
if
f
er
e
n
t
m
et
h
o
d
s
i
n
cl
u
d
in
g
O
ts
u
,
F
u
z
z
y
a
n
d
P
r
o
p
o
s
ed
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
g
i
v
es
th
e
o
p
tim
u
m
t
h
r
es
h
o
ld
v
a
lu
e
co
m
p
ar
ed
to
th
e
o
th
er
t
w
o
m
e
th
o
d
s
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
n
f
i
r
m
s
th
e
q
u
alitat
iv
e
en
h
a
n
ce
m
en
t o
v
er
th
e
e
x
is
t
in
g
m
eth
o
d
s
.
Fi
g
u
r
e
2
s
h
o
w
s
t
h
r
e
s
h
o
ld
r
esu
l
ts
o
b
tain
ed
b
y
v
ar
io
u
s
m
et
h
o
d
s
.
Fig
u
r
e
2
.
F
r
o
m
L
e
f
t to
R
i
g
h
t
Or
ig
i
n
al
I
m
a
g
es a
n
d
C
o
r
r
esp
o
n
d
in
g
R
e
s
u
lts
f
o
r
th
e
T
h
r
ee
A
l
g
o
r
ith
m
s
O
ts
u
,
Fu
zz
y
an
d
P
r
o
p
o
s
ed
A
lg
o
r
ith
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
3
,
Sep
tem
b
e
r
201
5
:
81
–
88
86
T
ab
le
1
.
C
o
m
p
ar
is
io
n
o
f
Me
a
n
(
µ
)
f
o
r
Dif
f
er
en
t M
et
h
o
d
s
I
mag
e
N
a
me
M
e
a
n
(
µ
)
O
t
su
’
s
F
u
z
z
y
P
r
o
p
o
se
d
M
1
0
.
0
5
3
9
0
.
7
3
6
6
0
.
4
8
2
4
M
2
0
.
0
1
8
8
0
.
3
1
3
4
0
.
2
1
2
4
M
3
0
.
0
1
2
3
0
.
3
9
2
7
0
.
2
5
7
1
M
4
0
.
0
0
8
4
0
.
5
1
2
2
0
.
3
5
4
9
M
5
0
.
0
1
8
8
0
.
4
2
5
0
0
.
3
5
6
9
M
6
0
.
3
0
5
7
0
.
7
5
3
8
0
.
4
4
4
3
M
7
0
.
0
1
7
6
0
.
7
3
4
4
0
.
4
6
1
7
M
8
0
.
0
5
4
8
0
.
3
1
3
9
0
.
2
6
5
4
M
9
0
.
0
2
5
6
0
.
5
5
5
9
0
.
3
2
8
5
M
1
0
0
.
1
6
1
8
0
.
6
0
6
2
0
.
3
4
2
0
M
1
1
0
.
0
0
0
0
0
.
8
9
3
6
0
.
5
7
1
0
M
1
2
0
.
0
1
2
7
0
.
2
3
0
0
0
.
1
5
0
7
M
1
3
0
.
0
5
0
7
0
.
4
9
6
6
0
.
2
8
8
3
M
1
4
0
.
0
0
6
0
0
.
2
4
2
0
0
.
1
6
3
4
M
1
5
0
.
0
1
2
2
0
.
7
8
3
2
0
.
4
6
8
8
M
1
6
0
.
0
2
9
9
0
.
8
6
4
2
0
.
4
9
8
1
M
1
7
0
.
0
3
5
6
0
.
7
1
5
1
0
.
4
5
1
9
T
ab
le
2
.
C
o
m
p
ar
is
io
n
o
f
Sta
n
d
ar
d
Dev
iatio
n
(
)
f
o
r
Dif
f
er
en
t
M
eth
o
d
s
I
mag
e
N
a
me
S
t
a
n
d
a
r
d
D
e
v
i
a
t
i
o
n
(
)
O
t
su
’
s
F
u
z
z
y
P
r
o
p
o
se
d
M
1
0
.
0
7
6
7
0
.
2
0
4
6
0
.
1
1
4
8
M
2
0
.
0
3
0
3
0
.
1
6
6
2
0
.
1
0
1
4
M
3
0
.
0
2
5
7
0
.
1
4
2
2
0
.
0
8
1
5
M
4
0
.
0
0
8
6
0
.
0
6
4
8
0
.
0
6
4
6
M
5
0
.
0
1
1
7
0
.
0
3
8
6
0
.
0
3
7
4
M
6
0
.
1
3
4
4
0
.
1
1
7
9
0
.
0
6
7
3
M
7
0
.
0
4
5
0
0
.
0
7
7
5
0
.
0
4
7
7
M
8
0
.
0
3
6
1
0
.
0
7
3
4
0
.
0
4
4
9
M
9
0
.
0
7
2
2
0
.
0
8
1
0
0
.
0
4
0
9
M
1
0
0
.
1
3
4
8
0
.
2
1
9
0
0
.
1
1
1
2
M
1
1
0
.
0
0
8
6
0
.
1
4
8
6
0
.
0
7
4
6
M
1
2
0
.
0
1
6
2
0
.
1
4
7
3
0
.
0
8
6
3
M
1
3
0
.
1
1
5
3
0
.
1
5
4
3
0
.
0
8
8
1
M
1
4
0
.
0
1
8
6
0
.
1
4
3
0
0
.
0
7
3
3
M
1
5
0
.
0
5
5
0
0
.
1
7
1
8
0
.
0
9
4
0
M
1
6
0
.
1
1
4
8
0
.
1
3
9
6
0
.
0
6
9
6
M
1
7
0
.
0
9
5
3
0
.
1
6
1
9
0
.
0
8
7
5
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
o
f
M
ea
n
s
f
o
r
th
e
Ots
u
,
F
u
zz
y
a
n
d
P
r
o
p
o
s
ed
Me
th
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Th
e
Op
tima
l Th
r
esh
o
ld
in
g
Tech
n
iq
u
e
f
o
r
I
ma
g
e
S
e
g
men
ta
io
n
u
s
in
g
F
u
z
z
y…
.
(
P.
R
a
mb
a
b
u
)
87
Fig
u
r
e
4
.
C
o
m
p
ar
is
o
n
o
f
Stan
d
ar
d
Dev
iatio
n
f
o
r
th
e
Ot
s
u
,
F
u
zz
y
a
n
d
P
r
o
p
o
s
ed
Me
th
o
d
5.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
b
y
u
s
in
g
th
r
e
e
th
r
esh
o
ld
in
g
tech
n
iq
u
es
o
f
Ots
u
,
Fu
zz
y
a
n
d
P
r
o
p
o
s
ed
m
et
h
o
d
,
d
eter
m
in
ed
t
h
e
o
p
ti
m
al
t
h
r
es
h
o
ld
v
al
u
es
a
n
d
th
e
y
ar
e
test
ed
w
it
h
n
a
tu
r
al
i
m
a
g
es
a
s
well
as
a
v
ar
iet
y
o
f
r
ep
r
esen
tin
g
lo
w
co
n
tr
as
ted
i
m
ag
e
s
f
o
r
i
m
a
g
e
e
n
h
a
n
ce
m
en
t.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
t
h
r
es
h
o
ld
v
al
u
e
co
m
p
ar
ed
w
it
h
ex
is
ti
n
g
Ots
u
an
d
f
u
zz
y
th
r
esh
o
ld
i
n
g
tec
h
n
iq
u
es
f
o
r
i
m
a
g
e
en
h
an
ce
m
e
n
t.
I
t
is
p
r
o
v
ed
th
at
p
r
o
p
o
s
ed
m
et
h
o
d
is
b
est
f
it
f
o
r
ev
en
l
o
w
co
n
tr
as
ted
i
m
a
g
es.
B
y
u
s
in
g
m
ea
n
a
n
d
s
tan
d
ar
d
d
ev
ia
tio
n
,
th
e
tab
le
s
an
d
g
r
ap
h
s
ar
e
co
n
s
tr
u
cted
.
E
v
en
th
o
u
g
h
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
r
o
d
u
ce
s
b
etter
r
esu
lts
,
it
f
ails
to
s
h
o
w
th
e
i
m
p
o
r
tan
t
f
ea
tu
r
e
li
k
e
m
o
o
n
in
i
m
ag
e
M6
in
Fig
u
r
e
2
.
T
h
e
v
alu
es
o
f
a
an
d
c
o
f
S
-
cu
r
v
e
ar
e
d
ef
i
n
ed
au
to
m
at
icall
y
.
W
e
ar
e
n
o
t
ad
d
ed
an
y
n
o
i
s
e
to
th
e
o
r
ig
in
al
i
m
a
g
e
d
ata
s
et.
I
n
f
u
t
u
r
e
w
o
r
k
,
w
e
ca
n
o
v
er
co
m
e
th
o
s
e
p
r
o
b
lem
s
b
y
ex
te
n
d
in
g
t
o
s
p
ec
k
le
n
o
is
e
an
d
p
o
is
o
n
n
o
is
e
r
e
m
o
v
al
a
n
d
f
in
d
all
t
h
e
im
p
o
r
ta
n
t
f
ea
t
u
r
es
o
f
i
m
a
g
e.
RE
F
E
R
E
NC
E
S
[1
]
N
Otsu
.
A
T
h
re
sh
o
ld
S
e
lec
ti
o
n
M
e
th
o
d
f
ro
m
G
r
a
y
-
L
e
v
e
l
Histo
g
ra
m
.
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
st
e
ms
,
M
A
N,
a
n
d
C
y
b
e
rn
e
ti
c
s,
1
9
7
9
;
SMC
-
9
(1
)
:
62
-
66.
[2
]
P
i
n
g
-
S
u
n
g
L
iao
,
T
s
e
-
S
h
e
n
g
Ch
e
n
,
P
a
u
-
C
h
o
o
Ch
u
n
g
.
A
F
a
st
A
l
g
o
rit
h
m
f
o
r
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
in
g
.
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
.
2
0
0
1
;
17
:
7
1
3
-
7
2
7
.
[3
]
Ch
Him
a
Bin
d
u
.
A
n
Im
p
ro
v
e
d
M
e
d
ica
l
Im
a
g
e
S
e
g
m
e
n
tati
o
n
A
lg
o
r
it
h
m
Us
in
g
Otsu
M
e
th
o
d
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Rec
e
n
t
T
re
n
d
s
i
n
E
n
g
i
n
e
e
rin
g
.
2
0
0
9
;
2
(
3
)
.
[4
]
Do
n
g
ju
L
iu
,
Jia
n
Yu
.
Otsu
me
th
o
d
a
n
d
K
-
me
a
n
s.
Nin
t
h
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Hy
b
r
id
In
tel
li
g
e
n
t
S
y
ste
m
s
2
0
0
9
:
3
4
4
-
3
4
9
.
[5
]
De
n
g
-
Yu
a
n
Hu
a
n
g
,
Ta
-
W
e
i
L
in
.
A
u
to
m
a
ti
c
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
in
g
Ba
se
o
n
Tw
o
-
S
tag
e
Otsu
’s
M
e
th
o
d
w
it
h
Clu
st
e
r
De
ter
m
in
a
ti
o
n
b
y
V
a
ll
e
y
Esti
m
a
ti
o
n
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
n
o
v
a
ti
v
e
Co
mp
u
ti
n
g
,
I
n
fo
rm
a
t
io
n
a
n
d
Co
n
tro
l
.
2
0
1
1
;
7
(
10
):
5
6
3
1
-
5
6
4
4
.
[6
]
X
iao
l
u
Ya
n
g
,
X
u
a
n
j
in
g
S
h
e
n
,
Jia
n
w
u
L
o
n
g
,
H
a
ip
e
n
g
Ch
e
n
.
A
n
I
m
p
ro
v
e
d
m
e
d
ian
-
b
a
se
d
Ots
u
ima
g
e
th
re
sh
o
ld
in
g
A
l
g
o
rit
h
m
.
S
c
iV
e
r
se
S
c
ien
c
e
Dire
c
t,
AA
S
RI
Pro
c
e
d
i
a
.
2
0
1
2
;
3
:
4
6
8
-
4
7
3
.
[7
]
He
tal
J V
a
la,
A
sth
a
Ba
x
i
.
A
Re
v
i
e
w
o
n
Otsu
Im
a
g
e
S
e
g
m
e
n
tatio
n
A
l
g
o
rit
h
m
.
IJ
AR
CET
.
2
0
1
3
;
2
(2
)
.
[8
]
S
Ka
lath
iy
a
,
VP
P
a
tel
.
Im
p
le
m
e
n
tatio
n
o
f
Otsu
M
e
t
h
o
d
w
it
h
T
w
o
Diff
e
re
n
t
A
p
p
ro
a
c
h
e
s
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
ft
w
a
re
&
Ha
rd
wa
re
Res
e
a
rc
h
i
n
En
g
i
n
e
e
rin
g
.
2
0
1
4
;
2
(
2
)
.
[9
]
JN
Ka
p
u
r,
P
K
S
a
h
o
o
,
A
KC
W
o
n
g
.
A
n
e
w
m
e
th
o
d
f
o
r
g
ra
y
lev
e
l
p
ictu
re
t
h
re
sh
o
ld
i
n
g
u
sin
g
t
h
e
e
n
tro
p
y
o
f
th
e
h
isto
g
ra
m
.
G
ra
p
h
M
o
d
e
ls
Im
a
g
e
P
r
o
c
e
ss
.
1
9
8
5
;
2
9
(3
):
2
7
3
-
2
8
5
.
[1
0
]
T
P
u
n
.
A
n
e
w
m
e
th
o
d
f
o
r
g
ra
y
-
l
e
v
e
l
p
ictu
re
th
re
sh
o
l
d
i
n
g
u
sin
g
th
e
e
n
tro
p
y
o
f
th
e
h
isto
g
ra
m
.
S
ig
n
a
l
P
r
o
c
e
ss
.
1
9
8
0
;
2
(
3
):
2
2
3
-
2
3
7
.
[1
1
]
A
S
A
b
u
tale
b
.
A
u
to
m
a
ti
c
T
h
re
sh
o
ld
i
n
g
o
f
g
ra
y
-
l
e
v
e
l
p
ictu
re
s
u
si
n
g
tw
o
-
d
im
e
n
sio
n
a
l
e
n
tr
o
p
y
.
Co
m
p
u
ter
v
isio
n
,
G
ra
p
h
ic
s an
d
Im
a
g
e
P
ro
c
e
ss
in
g
.
1
9
8
0
;
(4
7
):
22
-
32
.
[1
2
]
A
D
Br
in
k
.
T
h
re
sh
o
ld
in
g
o
f
d
ig
it
a
l
im
a
g
e
s u
sin
g
tw
o
d
im
e
n
sio
n
a
l
e
n
tro
p
ies
.
P
a
tt
e
rn
re
c
o
g
n
it
i
o
n
,
1
9
8
9
;
2
5
(8
)
:
2
2
-
32
.
[1
3
]
LA
Zad
e
h
,
F
u
z
z
y
S
e
ts.
In
f
o
r
m
a
ti
o
n
a
n
d
C
o
n
tr
o
l.
1
9
6
5
;
(8
)
:
3
3
8
-
3
5
3
.
[1
4
]
HD
Ch
e
n
g
,
Ch
e
n
,
JL
i.
T
h
re
sh
o
ld
se
lec
ti
o
n
b
a
se
d
o
n
f
u
z
z
y
c
-
p
a
rti
ti
o
n
e
n
tro
p
y
a
p
p
ro
a
c
h
.
P
a
tt
e
rn
re
c
o
g
n
it
io
n
.
1
9
9
8
;
3
1
(
7
):
8
5
7
-
8
8
7
.
[1
5
]
HR T
izh
o
o
sh
.
Im
a
g
e
th
re
sh
o
ld
i
n
g
u
sin
g
ty
p
e
II
f
u
z
z
y
se
ts.
P
a
tt
e
rn
r
e
c
o
g
n
it
io
n
,
2
0
0
5
;
(
3
8
):
2
3
6
3
-
2
3
7
2
.
[1
6
]
M
S
e
e
th
a
ra
m
a
P
ra
sa
d
,
T
Div
a
k
a
r
,
B
S
rin
iv
a
sa
Ra
o
,
C
Na
g
a
Ra
ju
.
Un
su
p
e
rv
ise
d
Im
a
g
e
T
h
r
e
sh
o
ld
i
n
g
u
sin
g
F
u
z
z
y
M
e
a
su
re
s.
In
ter
n
a
t
io
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
.
2
0
1
1
;
27
(
2
):
32
-
4
1
.
[1
7
]
Am
b
a
r
Du
tt
a
,
Av
ij
it
Ka
r
,
BN
Ch
a
tt
e
rji
.
F
u
z
z
y
S
e
t
T
h
e
o
re
ti
c
A
p
p
ro
a
c
h
to
Im
a
g
e
T
h
re
sh
o
ld
in
g
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
Ap
p
li
c
a
t
io
n
s
.
2
0
1
1
;
1
(
6
)
:
63
-
7
1
.
0
0.1
0.2
0.3
M
1
M
2
M
3
M
4
M
5
M
6
M
7
M
8
M
9
M
10
M
11
M
12
M
13
M
14
M
15
M
16
M
17
S
t
d
Im
ag
e
S
t
an
da
r
d
D
e
v
i
at
i
o
n
O
t
s
u'
s
F
uz
z
y
P
r
o
po
se
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
4
,
No
.
3
,
Sep
tem
b
e
r
201
5
:
81
–
88
88
[1
8
]
P
G
K
S
iri
sh
a
,
R
P
ra
d
e
e
p
K
u
m
a
r
Re
d
d
y
,
C
Na
g
a
Ra
ju
.
A
n
E
f
f
i
c
ien
t
F
u
z
z
y
T
e
c
h
n
iq
u
e
f
o
r
De
tec
ti
o
n
o
f
Bra
in
T
u
m
o
r
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
s
&
T
e
c
h
n
o
l
o
g
y
.
2
0
1
3
:
8
(
2
):
8
1
3
-
8
1
8
.
[1
9
]
U
S
e
sa
d
ri,
B
S
iv
a
S
a
n
k
a
r,
C
Na
g
a
Ra
ju
.
F
u
z
z
y
En
tro
p
y
Ba
s
e
d
Op
ti
m
a
l
T
h
re
sh
o
ld
in
g
T
e
c
h
n
iq
u
e
f
o
r
Im
a
g
e
En
h
a
n
c
e
m
e
n
t.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
n
S
o
ft
C
o
mp
u
ti
n
g
,
2
0
1
5
;
6
(
2
)
.
BI
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
RA
M
B
A
BU
P
EM
ULA
,
re
c
e
i
v
e
d
h
is
B.
T
e
c
h
De
g
r
e
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
J.N.T
.
Un
iv
e
rsit
y
H
y
d
e
ra
b
a
d
a
n
d
M
.
T
e
c
h
De
g
re
e
in
S
o
f
t
w
a
re
En
g
in
e
e
rin
g
f
ro
m
J.N.T
.
Un
iv
e
rsit
y
H
y
d
e
ra
b
a
d
.
P
re
se
n
tl
y
p
u
rsu
i
n
g
P
h
.
D
i
n
t
h
e
a
re
a
o
f
Dig
it
a
l
Im
a
g
e
P
r
o
c
e
ss
in
g
in
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
J.N.
T
.
Un
iv
e
rsit
y
Ka
k
in
a
d
a
.
He
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
A
s
sista
n
t
P
r
o
f
e
ss
o
r
a
n
d
He
a
d
o
f
th
e
De
p
a
rtm
e
n
t
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
Nim
ra
In
stit
u
te
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
On
g
o
le,
A
n
d
h
ra
P
ra
d
e
sh
.
He
g
o
t
8
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
is
m
e
m
b
e
r
o
f
v
a
ri
o
u
s
p
ro
f
e
ss
io
n
a
l
so
c
ieties
li
k
e
IE
EE
,
A
CM
a
n
d
IS
T
E.
Dr.
C.
Na
g
a
Ra
ju
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
A
ss
o
c
iate
p
ro
f
e
s
so
r
a
n
d
He
a
d
o
f
th
e
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
a
t
YSR
En
g
in
e
e
rin
g
Co
ll
e
g
e
o
f
Yo
g
i
V
e
m
a
n
a
Un
iv
e
rsit
y
,
P
r
o
d
d
a
tu
r,
YSR
Ka
d
a
p
a
District,
A
n
d
h
ra
P
ra
d
e
sh
,
In
d
ia.
He
re
c
e
iv
e
d
h
is
B.
T
e
c
h
D
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
J.N.T
.
Un
iv
e
rsit
y
,
A
n
a
n
tap
u
r
,
a
n
d
M
.
T
e
c
h
De
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
J.N.
T
.
U
n
iv
e
rs
it
y
H
y
d
e
ra
b
a
d
a
n
d
P
h
.
D
i
n
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
f
ro
m
J.N.T
.
Un
iv
e
rsit
y
H
y
d
e
ra
b
a
d
.
He
h
a
s
g
o
t
1
8
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
r
e
c
e
i
v
e
d
re
se
a
rc
h
e
x
c
e
ll
e
n
c
e
a
w
a
rd
,
tea
c
h
in
g
e
x
c
e
l
len
c
e
a
w
a
rd
a
n
d
Ra
y
a
la
se
e
m
a
V
id
h
y
a
ra
tn
a
a
w
a
rd
f
o
r
h
is
c
re
d
it
.
He
w
ro
te
te
x
t
b
o
o
k
o
n
C
&
Da
t
a
S
tru
c
tu
re
s
a
n
d
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
.
He
h
a
s
six
P
h
.
D
sc
h
o
lars
.
He
h
a
s
p
u
b
li
sh
e
d
f
if
t
y
si
x
re
se
a
r
c
h
p
a
p
e
rs
in
v
a
rio
u
s
Na
ti
o
n
a
l
a
n
d
I
n
tern
a
ti
o
n
a
l
Jo
u
rn
a
ls
a
n
d
a
b
o
u
t
th
irt
y
re
s
e
a
rc
h
p
a
p
e
rs
in
v
a
rio
u
s
Na
ti
o
n
a
l
a
n
d
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
s.
He
h
a
s
a
tt
e
n
d
e
d
t
w
e
n
t
y
se
m
in
a
rs an
d
w
o
rk
sh
o
p
s.
He
d
e
li
v
e
re
d
1
0
k
e
y
n
o
te ad
d
re
ss
e
s.
He
is
m
e
m
b
e
r
o
f
v
a
rio
u
s p
r
o
f
e
ss
io
n
a
l
so
c
ieties
li
k
e
IEE
E,
IS
T
E
a
n
d
CS
I.
Evaluation Warning : The document was created with Spire.PDF for Python.