I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
6
,
No
.
4
,
Dec
em
b
er
2
0
1
7
,
p
p
.
2
9
3
~3
0
2
I
SS
N:
2252
-
8814
293
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
AAS
I
m
pro
v
ed
Co
lo
r
Sa
tellit
e I
m
a
g
e S
e
g
m
enta
tion Using
Tsa
llis
Entro
py
and
G
ra
nula
r Co
m
puti
ng
J
a
g
a
n
K
um
a
r
.
N
,
Ag
ila
nd
ee
s
w
a
ri.
L
,
P
ra
bu
k
u
m
a
r.
M
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
n
d
En
g
i
n
e
e
rin
g
,
V
IT
Un
iv
e
rsit
y
,
V
e
ll
o
re
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
1
7
,
2
0
1
7
R
ev
i
s
ed
No
v
1
2
,
2
0
1
7
A
cc
ep
ted
No
v
2
1
,
2
0
1
7
T
h
e
re
s
e
a
rc
h
w
o
rk
is
to
i
m
p
ro
v
e
th
e
se
g
m
e
n
tatio
n
o
f
th
e
c
o
lo
r
sa
telli
te
im
a
g
e
s.
In
th
is
p
r
o
p
o
se
d
m
e
th
o
d
th
e
c
o
l
o
r
sa
telli
te
im
a
g
e
c
a
n
b
e
se
g
m
e
n
ted
b
y
u
sin
g
T
sa
ll
is
e
n
tro
p
y
a
n
d
g
ra
n
u
lar
c
o
m
p
u
ti
n
g
m
e
th
o
d
s
w
it
h
t
h
e
h
e
lp
o
f
c
u
c
k
o
o
se
a
rc
h
a
l
g
o
rit
h
m
.
T
h
e
T
s
a
ll
is
a
n
d
g
ra
n
u
lar
c
o
m
p
u
ti
n
g
m
e
th
o
d
s
w
il
l
u
se
d
to
f
in
d
th
e
m
a
x
i
m
u
m
p
o
ss
ib
il
it
y
o
f
th
re
sh
o
ld
li
m
it
s
a
n
d
t
h
e
c
u
c
k
o
o
se
a
rc
h
w
il
l
f
in
d
th
e
o
p
t
im
ize
d
th
re
sh
o
ld
v
a
lu
e
s
b
a
se
d
o
n
th
re
sh
o
l
d
li
m
it
th
a
t
is
c
a
lcu
late
d
b
y
th
e
T
sa
ll
is
e
n
tro
p
y
a
n
d
g
ra
n
u
lar
c
o
m
p
u
ti
n
g
m
e
th
o
d
s
a
n
d
t
h
e
m
u
lt
il
e
v
e
l
th
re
sh
o
ld
in
g
w
il
l
u
se
d
f
o
r
th
e
se
g
m
e
n
tatio
n
o
f
c
o
lo
r
sa
telli
te
im
a
g
e
s b
a
s
e
d
o
n
t
h
e
o
p
ti
m
ize
d
th
re
sh
o
ld
v
a
lu
e
t
h
a
t
w
il
l
f
in
d
b
y
th
i
s w
o
rk
a
n
d
th
e
se
m
e
th
o
d
s
w
il
l
h
e
lp
to
se
lec
t
th
e
o
p
ti
m
ize
d
th
re
sh
o
ld
v
a
lu
e
s
f
o
r
m
u
lt
ip
le
th
re
sh
o
l
d
i
n
g
e
ff
e
c
t
iv
e
l
y
.
K
ey
w
o
r
d
:
C
u
c
k
o
o
s
ea
r
ch
Gr
an
u
lar
co
m
p
u
ti
n
g
Op
ti
m
ize
Seg
m
en
tatio
n
T
s
allis
Co
p
y
rig
h
t
©
201
7
In
s
t
it
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
:
J
ag
an
k
u
m
ar
,
Sch
o
o
l o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
a
n
d
E
n
g
in
ee
r
i
n
g
,
VI
T
Un
iv
er
s
it
y
,
Vello
r
e
6
3
2
0
1
4
,
T
N,
I
n
d
ia.
E
m
ail:
k
u
m
ar
j
ag
an
0
2
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
o
lo
r
im
a
g
e
s
e
g
m
en
tatio
n
is
t
h
e
ess
e
n
tial
p
r
o
ce
s
s
f
o
r
an
i
m
ag
e.
T
h
e
s
p
litt
in
g
o
f
i
m
a
g
e
in
to
v
ar
io
u
s
p
ar
ts
is
ca
l
led
i
m
ag
e
s
e
g
m
en
tatio
n
.
T
h
e
s
e
g
m
e
n
tatio
n
u
s
e
d
to
m
a
k
e
t
h
e
i
m
a
g
e
to
b
e
u
n
d
er
s
tan
d
ab
le.
T
h
e
i
m
a
g
e
s
e
g
m
e
n
tatio
n
is
u
s
ed
to
f
i
n
d
t
h
e
o
b
j
ec
t
an
d
t
h
e
b
ac
k
g
r
o
u
n
d
o
f
an
i
m
ag
e
b
y
th
e
h
elp
o
f
b
o
u
n
d
ar
ies
lik
e
lin
e,
c
u
r
v
e
etc
[
1
]
.
T
h
e
th
r
es
h
o
ld
in
g
is
b
as
ic
s
e
g
m
en
tatio
n
t
ec
h
n
iq
u
e
o
f
i
m
a
g
es.
B
asica
ll
y
i
m
a
g
e
o
b
j
ec
t
an
d
b
ac
k
g
r
o
u
n
d
is
d
if
f
er
e
n
tiati
n
g
b
y
s
i
n
g
le
v
al
u
e
o
f
t
h
r
es
h
o
ld
.
T
h
e
co
lo
r
i
m
ag
e
ca
n
b
e
t
h
r
es
h
o
ld
b
ased
o
n
th
eir
R
GB
v
al
u
es
o
f
a
n
i
m
ag
e.
W
h
ile
d
is
ti
n
g
u
i
s
h
a
n
i
m
ag
e
in
to
v
ar
io
u
s
d
if
f
er
en
t
r
eg
io
n
s
b
ased
o
n
v
ar
io
u
s
th
r
es
h
o
ld
li
m
it
s
i
s
ca
lled
m
u
lt
ilev
el
th
r
e
s
h
o
ld
i
n
g
[
6
]
.
T
h
e
im
ag
e
i
s
d
i
f
f
er
e
n
tiated
b
y
t
h
e
s
in
g
le
li
m
it
T
a
n
d
i
f
g
r
a
y
v
alu
e
i
s
g
r
ea
ter
th
a
n
T
is
co
n
s
id
er
ed
to
b
e
an
o
b
ject
else
o
th
er
g
r
a
y
v
alu
e
ar
e
co
n
s
id
er
ed
to
b
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
b
asic
tech
n
i
q
u
e
is
n
o
t
g
i
v
e
n
th
e
g
o
o
d
r
e
s
u
lt
w
h
e
n
co
m
i
n
g
to
i
m
ag
e
s
o
f
r
e
m
o
te
s
en
s
i
n
g
b
ec
au
s
e
o
f
t
h
is
t
h
er
e
w
ill b
e
es
s
en
tia
l o
f
m
u
lt
ilev
e
l th
r
es
h
o
ld
i
n
g
[
2
]
.
T
h
e
n
o
n
-
ex
te
n
s
i
v
e
e
n
tr
o
p
y
o
f
i
m
a
g
e
s
e
g
m
en
ta
tio
n
t
h
e
t
h
r
es
h
o
ld
in
g
tech
n
iq
u
e
u
s
ed
o
n
v
ar
io
u
s
k
in
d
s
o
f
g
r
a
y
s
ca
le
i
m
ag
e
s
.
T
h
e
o
p
ti
m
izat
io
n
al
g
o
r
ith
m
h
ad
g
i
v
en
th
e
b
etter
t
h
r
es
h
o
ld
v
al
u
e
b
y
u
s
i
n
g
B
ac
ter
ial
f
o
r
ag
i
n
g
alg
o
r
it
h
m
[
1
]
.
T
h
e
B
ac
ter
ial
f
o
r
ag
i
n
g
al
g
o
r
ith
m
w
a
s
u
s
e
d
T
s
allis
o
b
j
ec
tiv
e
f
u
n
ctio
n
f
o
r
th
e
m
u
ltil
e
v
el
t
h
r
esh
o
ld
i
n
g
a
n
d
t
h
e
y
h
ad
ass
o
ciate
d
w
it
h
G
A
an
d
P
SO
[
4
]
m
et
h
o
d
s
an
d
it
g
o
t
b
etter
r
esu
lt
a
n
d
co
n
v
er
g
e
s
f
a
s
ter
th
a
n
t
h
e
P
SO a
n
d
GA
m
et
h
o
d
s
.
T
h
e
u
n
s
u
p
er
v
is
ed
m
u
l
tile
v
el
th
r
es
h
o
ld
in
g
tech
n
iq
u
e
s
f
o
r
s
eg
m
e
n
ti
n
g
o
f
clo
u
d
ar
ea
s
f
r
o
m
w
ea
t
h
er
s
atellite
i
m
a
g
es
[
2
]
.
I
n
t
h
is
ap
p
r
o
ac
h
g
en
er
ate
s
ev
er
al
b
i
n
ar
y
i
m
a
g
es
f
r
o
m
a
s
et
o
f
p
r
ed
ef
in
ed
t
h
r
es
h
o
ld
v
alu
e
s
,
t
h
en
th
e
y
e
x
tr
ac
ted
an
d
m
ap
p
ed
th
e
co
n
to
u
r
o
f
clo
u
d
y
ar
ea
s
i
n
clu
d
ed
t
h
e
i
m
ag
e
s
eq
u
en
ce
an
d
t
h
e
y
also
u
s
ed
s
o
m
e
o
f
p
r
ep
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
es
li
k
e
Ga
u
s
s
ia
n
s
m
o
o
t
h
in
g
f
o
r
n
o
is
e
r
ed
u
c
tio
n
a
n
d
e
n
h
a
n
ce
d
co
n
tr
ast
b
y
h
is
to
g
r
a
m
eq
u
aliz
atio
n
[
9
,
1
0
]
.
T
h
e
g
o
al
h
er
e
is
to
d
eter
m
i
n
e
a
g
lo
b
al
an
d
co
ar
s
e
th
r
es
h
o
ld
t
h
at
s
ep
ar
ates
th
e
i
m
a
g
e
to
d
is
t
in
c
t
class
e
s
,
th
e
b
ac
k
g
r
o
u
n
d
a
n
d
th
e
f
o
r
eg
r
o
u
n
d
.
T
h
is
p
ap
er
f
o
cu
s
e
s
o
n
a
s
p
ec
if
i
c
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4,
Dec
em
b
er
201
7
:
2
9
3
–
3
0
2
294
clo
u
d
s
eg
m
en
tatio
n
m
eth
o
d
f
o
r
im
a
g
e
o
b
tain
ed
b
y
m
e
teo
r
o
lo
g
ical
s
atellites
[
6
,
9
]
an
d
th
is
al
g
o
r
ith
m
ef
f
ec
tiv
e
l
y
e
x
tr
ac
t
t
h
e
r
ep
r
esen
tati
v
e
ar
ea
s
o
f
clo
u
d
s
a
n
d
s
o
lv
ed
th
e
p
r
o
b
le
m
s
o
f
o
v
er
s
e
g
m
en
tatio
n
a
n
d
u
n
d
er
s
eg
m
e
n
tatio
n
r
elate
d
to
th
e
g
l
o
b
al
th
r
esh
o
ld
in
g
m
eth
o
d
s
.
I
n
th
e
g
r
a
n
u
lar
co
m
p
u
ti
n
g
f
o
r
th
e
s
e
g
m
e
n
tatio
n
it
h
as
t
h
e
f
o
llo
w
in
g
p
r
o
ce
s
s
es
to
ac
h
iev
e
th
e
th
r
es
h
o
ld
in
g
[
4
]
.
T
h
e
g
r
an
u
le
s
ar
e
ch
ar
ac
ter
ized
w
it
h
R
GB
v
alu
es
a
n
d
it
s
h
o
u
ld
co
m
b
i
n
e
th
e
2
g
r
an
u
les
to
g
e
t
lar
g
er
g
r
an
u
le
a
n
d
f
i
n
all
y
,
e
s
ta
b
lis
h
b
y
t
h
e
U
o
p
er
atio
n
o
n
g
r
an
u
le
s
to
g
et
t
h
r
es
h
o
ld
t o
f
g
r
a
n
u
le
s
.
T
h
e
m
ai
n
o
b
j
ec
tiv
e
o
f
th
is
p
ap
er
is
f
o
llo
w
s
,
th
e
s
a
tellite
i
m
ag
e
s
ar
e
ca
p
tu
r
ed
b
y
s
atelli
te
(
R
e
m
o
te
s
en
s
in
g
)
f
r
o
m
t
h
e
s
p
ac
e.
T
h
e
ca
p
tu
r
in
g
th
e
i
m
a
g
es
b
y
t
h
e
u
s
e
o
f
th
e
r
e
m
o
te
s
en
s
i
n
g
d
ev
i
ce
s
(
m
ac
h
in
e
s
)
th
a
t
f
ac
es
m
an
y
p
r
o
b
le
m
s
i
n
th
e
r
e
s
o
lu
tio
n
o
f
th
e
i
m
a
g
es.
T
h
o
s
e
p
r
o
b
lem
s
ar
e
f
o
llo
w
s
a.
Ma
n
y
s
atellite
i
m
a
g
es
h
a
v
e
b
ee
n
af
f
ec
ted
b
y
t
h
e
s
h
ad
o
w
s
o
f
th
e
clo
u
d
in
t
h
e
s
k
y
.
b.
T
h
e
w
h
et
h
er
co
n
d
itio
n
a
n
d
lig
h
t h
a
v
e
b
ig
c
h
an
g
e
s
o
v
er
th
e
s
atellite
i
m
ag
e
s
.
c.
Ob
j
ec
ts
ar
e
b
l
o
ck
ed
b
y
tr
ee
s
a
n
d
s
h
ad
o
w
s
s
u
r
r
o
u
n
d
in
g
o
b
j
ec
t
w
it
h
s
i
m
ilar
co
lo
r
s
i.e
.
,
r
o
o
f
to
p
s
.
T
h
ese
co
n
d
itio
n
s
ca
n
m
a
k
e
t
h
e
o
b
j
ec
ts
p
r
ed
ictab
ilit
y
i
m
p
o
s
s
ib
le
[
1
]
.
B
ased
o
n
th
e
ab
o
v
e
d
etails
e
x
p
lan
atio
n
t
h
e
e
x
i
s
ti
n
g
a
lg
o
r
it
h
m
s
th
e
i
m
a
g
e
s
eg
m
e
n
tatio
n
co
lo
r
i
m
ag
e
s
u
s
i
n
g
m
u
ltil
e
v
el
t
h
r
es
h
o
ld
in
g
ap
p
r
o
ac
h
th
at
ar
e
a
cr
itical
an
d
ch
all
en
g
in
g
tas
k
an
d
it
ta
k
e
s
h
u
g
e
n
u
m
b
er
o
f
lin
e
co
d
in
g
to
d
o
n
e
th
e
s
e
g
m
en
tatio
n
an
d
i
n
m
u
ltil
e
v
el
th
r
es
h
o
ld
in
g
h
as
s
o
m
e
p
r
o
b
le
m
w
h
e
n
t
h
e
le
v
el
in
cr
ea
s
es
t
h
at
w
i
ll
p
r
o
d
u
ce
th
e
g
o
o
d
r
esu
lt
an
d
b
ec
au
s
e
o
f
m
o
r
e
lev
els
in
t
h
r
es
h
o
ld
in
g
h
a
v
e
also
in
cr
ea
s
ed
th
e
co
m
p
u
tatio
n
al
co
s
t h
ig
h
er
an
d
m
o
r
eo
v
er
th
e
ti
m
e
o
f
co
m
p
u
t
atio
n
al
also
i
n
cr
ea
s
ed
.
I
n
th
is
p
r
o
p
o
s
ed
m
et
h
o
d
i
m
p
r
o
v
e
th
e
s
e
g
m
e
n
tat
io
n
b
ased
o
n
T
s
allis
e
n
tr
o
p
y
a
n
d
g
r
a
n
u
lar
co
m
p
u
ti
n
g
m
et
h
o
d
s
w
it
h
t
h
e
h
elp
o
f
C
S
o
p
tim
izatio
n
alg
o
r
it
h
m
an
d
th
e
p
ap
er
[
6
]
h
av
e
p
r
o
v
ed
th
at
th
e
C
S
i
s
t
h
e
b
est
o
p
tim
izatio
n
al
g
o
r
ith
m
w
h
e
n
co
m
p
ar
ed
to
th
e
o
t
h
er
s
.
T
h
e
r
est
o
f
t
h
e
p
ap
er
is
o
r
g
an
ized
a
s
f
o
llo
w
s
,
s
ec
tio
n
2
w
il
l b
e
ex
p
lai
n
ab
o
u
t t
h
e
co
n
c
ep
ts
th
at
ar
e
u
s
ed
in
th
i
s
al
g
o
r
ith
m
,
s
ec
tio
n
3
w
ill b
e
th
e
p
r
o
p
o
s
ed
w
o
r
k
,
s
ec
t
io
n
4
co
n
tain
s
t
h
e
ex
p
er
i
m
en
tal
r
esu
lt
s
an
d
i
n
s
ec
tio
n
5
w
il
l b
e
th
e
co
n
cl
u
s
io
n
.
2.
RE
SE
A
RCH
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
co
n
tai
n
s
t
h
e
ex
p
lan
atio
n
o
f
th
e
v
ar
io
u
s
m
et
h
o
d
s
th
at
ar
e
u
s
ed
in
th
e
s
eg
m
en
tatio
n
o
f
th
e
co
lo
r
s
atellite
i
m
ag
e.
2
.
1
.
T
s
a
llis
E
ntr
o
py
T
h
e
en
tr
o
p
y
i
s
t
h
e
m
ea
s
u
r
e
th
e
s
tate
s
lo
g
ar
ith
m
ical
l
y
w
it
h
s
ig
n
if
ican
t
p
r
o
b
ab
ilit
y
o
f
b
ein
g
o
cc
u
p
ied
.
T
h
e
T
s
allis
en
tr
o
p
y
is
al
s
o
ca
l
led
n
o
n
-
ex
te
n
s
iv
e
e
n
tr
o
p
y
.
T
h
e
ad
v
an
ta
g
e
o
f
th
e
T
s
alli
s
en
tr
o
p
y
m
et
h
o
d
is
t
h
e
u
s
e
o
f
g
lo
b
al
p
r
o
p
er
ty
an
d
o
b
jectiv
e
p
r
o
p
er
ty
o
f
t
h
e
i
m
ag
e
s
[
2
,
5
]
.
An
d
(
1
)
a.
L
-
g
r
a
y
lev
el
b
et
w
ee
n
{
0
,
1
,
2
,
…,
(
L
-
1)
}.
b.
h
(
i)
p
ix
els i
n
g
r
a
y
lev
e
l i
an
d
i
t sh
o
u
ld
in
0
≤
i≤
(
L
-
1)
.
c.
N
is
to
tal
n
u
m
b
er
o
f
p
i
x
els i
n
a
g
iv
e
n
i
m
ag
e.
d.
P
i is p
r
o
b
a
b
ilit
y
v
al
u
atio
n
.
T
h
r
esh
o
ld
in
g
f
o
r
m
u
ltil
e
v
el
u
s
in
g
T
s
alli
s
d
ef
i
n
e
b
lo
w
.
(
2
)
W
h
er
e,
(
3
)
I
n
th
e
ab
o
v
e
f
o
r
m
u
la,
t
1
, t
2
,
.
.
.
.
.
,
t
M
ar
e
th
r
esh
o
ld
lev
el
s
an
d
it
s
h
o
u
ld
b
e
in
t
1
<t
2
<t
3
.......< t
M
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
I
mp
r
o
ve
d
C
o
lo
r
S
a
tellite I
ma
g
e
S
eg
men
ta
tio
n
Usi
n
g
Ts
a
llis
…
(
Ja
g
a
n
K
u
ma
r
)
295
2
.
2
G
ra
nu
la
r
Co
m
p
uting
(
G
rC)
T
h
is
alg
o
r
ith
m
i
s
s
o
l
v
i
n
g
th
e
v
ar
io
u
s
p
r
o
b
le
m
s
b
y
u
s
i
n
g
v
ar
io
u
s
m
et
h
o
d
s
an
d
to
o
l
s
an
d
t
h
is
co
m
p
u
ti
n
g
is
p
r
o
ce
s
s
i
n
g
o
v
er
th
e
g
r
an
u
les.
I
t
ta
k
es
t
h
e
p
i
x
el
s
o
f
a
n
i
m
ag
e
a
n
d
co
m
b
i
n
es
t
h
e
p
ix
el
s
to
g
et
th
e
g
r
an
u
les
b
ased
o
n
d
i
m
en
s
io
n
th
at
is
g
i
v
en
b
y
u
s
er
an
d
t
h
e
v
alu
e
s
co
n
tai
n
s
i
n
a
g
r
a
n
u
le
a
r
e
ap
p
ea
r
b
ased
o
n
th
e
p
r
o
b
ab
ilit
y
o
f
th
e
p
i
x
els i
n
th
e
g
r
a
n
u
le[
1
,
1
2
]
.
R
o
u
g
h
e
n
tr
o
p
y
(
l)
=e
/2
[
o
b
j_
r
o
u
g
h
n
es
s
(
l)
lo
g
e(
o
b
j
_
r
o
u
g
h
n
es
s
(
l
)
)
+b
ac
k
_
r
o
u
g
h
n
ess
(
l)
lo
g
e(
b
a
ck
_
r
o
u
g
h
n
e
s
s
(
l)
)
]
;
T
o
p
t=A
r
g
m
ax
(
R
o
u
g
h
e
n
tr
o
p
y
(
l)
)
;
(
4
)
2
.
3
Cuck
o
o
s
ea
rc
h
I
t
is
an
o
p
ti
m
izatio
n
al
g
o
r
it
h
m
a
n
d
it
h
as
b
ee
n
p
r
o
ce
s
s
s
a
m
e
as
c
u
c
k
o
o
.
T
h
e
C
u
ck
o
o
Sear
ch
alg
o
r
ith
m
ca
n
f
i
n
d
t
h
e
n
e
w
s
o
lu
tio
n
i
s
atte
m
p
ted
to
b
e
ex
a
m
i
n
e
o
v
er
t
h
e
p
r
ev
io
u
s
l
y
f
o
u
n
d
ed
f
in
e
s
t
r
esu
lt
s
[
2
,
5
,
6
]
.
T
h
er
e
ar
e
3
s
tep
s
as f
o
llo
w
s
.
a.
T
h
e
cu
ck
o
o
p
u
ts
an
e
g
g
i
n
t
h
e
n
est t
h
at
is
r
a
n
d
o
m
l
y
s
elec
ted
.
b.
T
h
e
f
in
es
t n
es
t c
o
n
tai
n
s
t
h
e
g
r
ea
t q
u
alit
y
o
f
eg
g
s
.
c.
T
h
e
p
r
o
b
ab
ilit
y
o
f
f
i
n
d
in
g
d
est
in
atio
n
n
es
t b
y
d
esti
n
atio
n
b
ir
d
p
a
is
b
elo
n
g
s
to
[
0
,
1
]
.
3.
PR
O
P
O
SE
D
AL
G
O
RI
T
H
M
:
I
n
t
h
is
alg
o
r
it
h
m
t
h
e
t
h
r
es
h
o
ld
in
g
o
f
m
u
lt
ilev
e
l
i
s
u
s
i
n
g
f
o
r
t
h
e
co
lo
r
s
atell
ite
i
m
a
g
e
s
eg
m
e
n
t
a
n
d
f
o
r
th
e
o
p
ti
m
iza
tio
n
p
u
r
p
o
s
e
th
e
o
p
ti
m
izatio
n
a
lg
o
r
it
h
m
ca
lle
d
cu
ck
o
o
s
ea
r
ch
(
C
S)
is
u
s
e
d
to
d
is
co
v
er
th
e
o
p
tim
ized
th
r
e
s
h
o
ld
ed
v
a
lu
e
s
o
f
t
h
e
co
lo
r
s
atell
ite
i
m
a
g
es
t
h
at
i
s
s
u
p
p
o
r
ted
b
y
n
o
n
_
ex
te
n
s
iv
e
en
tr
o
p
y
th
at
is
ca
lled
T
s
allis
e
n
tr
o
p
y
an
d
an
o
th
er
s
u
p
p
o
r
tin
g
m
eth
o
d
ca
lled
g
r
an
u
lar
co
m
p
u
ti
n
g
.
T
h
e
b
o
th
t
h
e
t
s
alli
s
e
n
tr
o
p
y
an
d
g
r
a
n
u
lar
co
m
p
u
ti
n
g
ar
e
co
m
b
in
e
a
n
d
u
s
ed
to
f
in
d
t
h
e
m
a
x
i
m
u
m
p
o
s
s
i
b
le
lev
el
s
o
f
th
e
t
h
r
es
h
o
ld
in
g
f
o
r
a
n
i
m
a
g
e.
Fi
n
all
y
in
ex
p
er
i
m
en
t
al
s
ec
tio
n
,
w
e
h
a
v
e
co
m
p
ar
e
d
th
e
q
u
alit
y
b
et
w
ee
n
o
r
i
g
in
al
i
m
ag
e
an
d
r
e
s
u
l
t
i
m
a
g
e
b
y
u
s
i
n
g
f
o
llo
w
in
g
m
at
r
ices M
SE,
P
SNR
,
SS
I
M,
an
d
NC
C
.
T
h
e
f
lo
w
c
h
ar
t o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
s
h
o
w
n
i
n
F
i
g
u
r
e
1.
Fig
u
r
e
1
.
Flo
w
C
h
a
rt
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4,
Dec
em
b
er
201
7
:
2
9
3
–
3
0
2
296
T
h
e
ab
o
v
e
f
lo
w
ch
ar
t
ca
n
b
e
ex
p
lain
ed
a
s
f
o
llo
w
s
.
First
s
elec
t
th
e
i
n
p
u
t
s
atel
lite
i
m
a
g
e
f
r
o
m
t
h
e
d
ataset
an
d
t
h
e
i
n
p
u
t
i
m
a
g
e
f
o
r
m
at
s
h
o
u
ld
b
e
o
n
.
j
p
eg
o
r
.
p
n
g
f
o
r
m
a
t
t
h
at
is
i
m
p
o
r
tan
t.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
i
s
u
s
ed
to
s
li
g
h
tl
y
ch
a
n
g
e
t
h
e
ap
p
ea
r
an
ce
o
f
an
i
m
a
g
e.
Her
e
in
t
h
is
w
o
r
k
u
s
i
n
g
t
h
e
t
w
o
p
r
ep
r
o
ce
s
s
in
g
tech
n
iq
u
es.
I
n
cr
ea
s
e
o
r
d
ec
r
e
ase
th
e
s
ize
o
f
i
m
a
g
es
u
s
i
n
g
r
esize
f
u
n
c
tio
n
i
n
MA
T
L
A
B
an
d
r
em
o
v
i
n
g
th
e
n
o
is
es
o
f
an
i
m
ag
e
b
y
th
e
h
elp
o
f
f
il
ter
.
T
o
ca
lcu
late
o
p
ti
m
iz
e
th
r
es
h
o
ld
v
al
u
e
b
ased
3
m
et
h
o
d
s
.
T
h
e
f
ir
s
t
t
w
o
m
et
h
o
d
s
ar
e
u
s
ed
to
f
in
d
th
e
m
a
x
i
m
u
m
p
o
s
s
ib
ilit
y
o
f
th
e
v
alu
e
s
th
o
s
e
ar
e
T
s
allis
en
tr
o
p
y
an
d
g
r
a
n
u
lar
co
m
p
u
ti
n
g
b
ased
o
n
f
o
r
m
u
la
(
2
,
4
)
an
d
an
o
th
er
o
n
e
is
th
e
o
p
ti
m
izat
io
n
alg
o
r
it
h
m
t
h
at
is
ca
lled
cu
ck
o
o
s
ea
r
ch
alg
o
r
ith
m
it i
s
u
s
ed
to
d
is
co
v
er
y
t
h
e
o
p
ti
m
ized
th
r
es
h
o
ld
li
m
it f
r
o
m
t
h
e
d
eter
m
i
n
ed
p
o
s
s
ib
i
lit
y
.
4.
RE
SUL
T
S
A
N
D
ANA
L
Y
SI
S
I
n
th
is
al
g
o
r
ith
m
t
h
e
s
at
ellite
i
m
ag
e
s
o
r
d
ataset
ar
e
u
s
ed
f
r
o
m
t
h
e
N
A
S
A
w
eb
s
ite
(
h
ttp
://ear
th
o
b
s
er
v
ato
r
y
.
n
a
s
a.
g
o
v
/I
m
a
g
es/?
eo
cn
=to
p
n
av
&
eo
c
i=i
m
a
g
es
).
T
h
e
co
n
f
i
g
u
r
atio
n
r
eq
u
ir
e
m
e
n
t
o
f
th
is
w
o
r
k
i
s
MA
T
L
A
B
2
0
1
3
s
o
f
t
w
ar
e
an
d
th
e
o
p
er
atin
g
s
y
s
t
e
m
s
h
o
u
ld
b
e
w
i
n
d
o
w
s
7
w
it
h
h
ar
d
d
is
k
ca
p
ac
ity
ca
n
b
e
3
0
GB
w
it
h
b
asic
k
e
y
b
o
ar
d
.
T
h
e
f
o
llo
w
i
n
g
T
ab
le
1
co
n
tain
s
o
p
ti
m
ized
th
r
es
h
o
ld
v
alu
e
s
t
h
at
ar
e
ca
lcu
lated
b
y
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
.
T
ab
le
1
.
Op
tim
ized
T
h
r
esh
o
ld
Valu
es
o
f
Dif
f
er
e
n
t I
m
a
g
es
with
Di
f
f
er
en
t T
h
r
esh
o
ld
L
ev
e
ls
I
mag
e
N
o
L
e
v
e
l
s
O
p
t
i
mi
z
e
d
T
h
r
e
sh
o
l
d
V
a
l
u
e
s
1
5
6
8
12
5
5
,
1
1
3
,
1
6
3
,
2
1
5
,
2
1
5
5
1
,
9
5
,
9
5
,
1
6
5
,
1
6
5
,
2
3
0
3
0
,
6
4
,
1
0
0
,
1
2
9
,
1
6
6
,
1
9
8
,
2
3
1
3
3
,
6
5
,
8
1
,
1
0
9
,
1
3
8
,
1
5
2
,
1
7
3
,
1
9
4
,
2
1
7
,
2
4
3
,
2
4
3
,
2
4
3
2
5
6
8
12
4
9
,
1
0
3
,
1
0
3
,
1
6
6
,
2
1
4
3
6
,
8
4
,
1
3
5
,
1
8
2
,
1
8
2
,
2
2
3
24
,
5
7
,
8
8
,
1
3
0
,
1
5
9
,
1
9
6
,
2
2
8
1
7
,
4
5
,
6
2
,
8
5
,
1
0
5
,
1
2
7
,
1
5
6
,
1
7
7
,
2
0
5
,
2
2
4
,
2
2
4
,
2
2
4
3
5
6
8
12
4
6
,
9
5
,
1
6
0
,
2
1
5
,
2
1
5
2
6
,
9
0
,
9
0
,
1
8
2
,
1
8
2
,
2
2
3
2
4
,
5
7
,
8
8
,
1
3
0
,
1
5
9
,
1
9
6
,
2
2
8
1
7
,
4
5
,
6
2
,
8
5
,
1
0
5
,
1
2
7
,
1
5
6
,
1
7
7
,
2
0
5
,
2
2
4
,
2
2
4
,
2
2
4
4
5
6
8
12
4
1
,
4
1
,
9
0
,
1
5
3
,
2
0
9
4
5
,
9
5
,
9
5
,
1
4
8
,
1
9
0
,
2
2
4
2
3
,
5
1
,
1
0
4
,
1
4
0
,
1
7
4
,
2
0
0
,
2
0
0
,
2
3
2
1
3
,
2
9
,
5
1
,
7
8
,
1
0
8
,
1
3
4
,
1
6
4
,
1
8
6
,
1
8
6
,
2
0
0
,
2
3
1
,
2
4
3
5
5
6
8
12
4
6
,
4
6
,
1
0
3
,
1
5
7
,
2
1
5
3
6
,
7
8
,
1
2
3
,
1
6
5
,
1
6
5
,
2
1
9
4
3
,
7
7
,
1
3
4
,
1
7
0
,
1
7
0
,
1
9
8
,
2
2
5
30
,
4
6
,
7
1
,
9
0
,
1
1
3
,
1
5
1
,
1
7
0
,
1
8
5
,
2
1
1
,
2
3
6
,
2
3
6
6
5
6
8
12
5
2
,
1
0
8
,
1
6
6
,
2
1
2
,
2
1
2
3
7
,
8
1
,
1
2
7
,
1
7
6
,
2
1
8
,
2
1
8
7
0
,
7
0
,
7
0
,
1
0
7
,
1
3
6
,
1
6
4
,
1
9
1
,
2
2
8
1
3
,
4
3
,
6
2
,
9
3
,
1
1
2
,
1
3
5
,
1
5
6
,
1
7
8
,
1
9
7
,
2
1
6
,
2
1
6
,
2
3
7
7
5
6
8
12
5
0
,
5
0
,
1
0
2
,
1
5
8
,
2
0
7
4
4
,
8
7
,
8
7
,
1
2
6
,
1
7
1
,
2
1
8
2
8
,
7
9
,
7
9
,
1
3
1
,
1
6
7
,
1
6
7
,
1
9
1
,
2
2
7
3
3
,
3
3
,
6
0
,
6
0
,
7
4
,
9
0
,
1
1
2
,
1
3
9
,
1
6
6
,
1
8
6
,
2
2
1
,
2
3
9
8
5
6
8
12
4
1
,
5
7
,
1
1
0
,
1
6
5
,
2
1
5
4
5
,
9
1
,
1
3
4
,
1
7
7
,
2
1
8
,
2
1
8
5
2
,
5
2
,
5
2
,
8
9
,
1
2
9
,
1
5
5
,
1
9
2
,
2
3
3
1
4
,
3
5
,
6
3
,
9
0
,
9
0
,
1
0
6
,
1
0
6
,
1
3
0
,
1
5
9
,
1
7
9
,
2
1
7
,
2
3
6
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
I
mp
r
o
ve
d
C
o
lo
r
S
a
tellite I
ma
g
e
S
eg
men
ta
tio
n
Usi
n
g
Ts
a
llis
…
(
Ja
g
a
n
K
u
ma
r
)
297
4
.
1
.
T
he
Or
ig
ina
l I
m
a
g
es a
n
d it
s
H
is
t
o
g
ra
m
A1
A2
A3
A4
B1
B2
B3
B4
A5
A
6
A7
A8
B5
B6
B7
B8
Fig
u
r
e
2
.
I
n
th
e
A
b
o
v
e
F
i
g
u
r
es (
A1
-
A8
)
ar
e
Or
ig
in
al
Satellit
e
I
m
a
g
es a
n
d
F
i
g
u
r
e
s
(
B1
-
B8
)
ar
e
T
h
eir
E
q
u
al
L
e
n
t H
is
to
g
r
a
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4,
Dec
em
b
er
201
7
:
2
9
3
–
3
0
2
298
4
.
2
.
T
hresh
o
ld
L
ev
els
5
Fig
u
r
e
3
.
T
h
e
5
L
ev
els T
h
r
esh
o
ld
in
g
B
ased
Seg
m
e
n
ted
I
m
a
g
es
w
ith
T
h
eir
His
to
g
r
a
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
I
mp
r
o
ve
d
C
o
lo
r
S
a
tellite I
ma
g
e
S
eg
men
ta
tio
n
Usi
n
g
Ts
a
llis
…
(
Ja
g
a
n
K
u
ma
r
)
299
4
.
3
.
T
hresh
o
ld
L
ev
els
6
Fig
u
r
e
4
.
T
h
e
6
L
ev
els T
h
r
esh
o
ld
in
g
B
ased
Seg
m
e
n
ted
I
m
a
g
es W
ith
T
h
eir
His
to
g
r
a
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4,
Dec
em
b
er
201
7
:
2
9
3
–
3
0
2
300
4
.
4
.
T
hresh
o
ld
L
ev
els
8
Fig
u
r
e
5
.
T
h
e
8
lev
els th
r
es
h
o
ld
in
g
b
ased
s
e
g
m
e
n
ted
i
m
ag
e
s
w
it
h
t
h
eir
h
i
s
to
g
r
a
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
I
mp
r
o
ve
d
C
o
lo
r
S
a
tellite I
ma
g
e
S
eg
men
ta
tio
n
Usi
n
g
Ts
a
llis
…
(
Ja
g
a
n
K
u
ma
r
)
301
4
.
5
.
T
hresh
o
ld
L
ev
els
12
Fig
u
r
e
6
.
T
h
e
1
2
lev
els th
r
e
s
h
o
ld
in
g
b
ased
s
e
g
m
e
n
ted
i
m
ag
es
w
ith
t
h
eir
h
is
to
g
r
a
m
s
4
.
6
.
Q
ua
lity
M
ea
s
ure
m
ent
R
esu
lt
s
T
h
e
ab
o
v
e
T
ab
le
co
n
tain
s
m
a
tr
ices
r
es
u
lts
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
n
d
t
h
e
al
g
o
r
ith
m
h
as
g
i
v
en
th
e
b
etter
r
esu
lts
t
h
an
t
h
e
r
es
u
lt o
f
p
ap
er
[
1
]
.
T
ab
le
2
.
Ma
tr
ices o
f
P
r
o
p
o
s
ed
A
l
g
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
6
,
No
.
4,
Dec
em
b
er
201
7
:
2
9
3
–
3
0
2
302
5
.
CO
NCLUS
I
O
N
I
n
th
i
s
p
r
o
p
o
s
ed
m
et
h
o
d
th
e
co
lo
r
s
atellite
i
m
a
g
e
s
e
g
m
en
ta
t
io
n
h
as
ac
h
ie
v
ed
th
e
g
o
o
d
r
esu
lts
b
y
th
e
h
elp
o
f
c
u
ck
o
o
s
ea
r
ch
a
n
d
t
h
at
h
av
e
s
u
p
p
o
r
ted
b
y
T
s
alli
s
en
t
r
o
p
y
an
d
Gr
a
n
u
la
r
co
m
p
u
ti
n
g
an
d
b
ec
au
s
e
o
f
th
is
n
e
w
alg
o
r
it
h
m
t
h
e
r
es
u
lt
h
a
v
e
g
o
t
th
e
v
er
y
o
p
ti
m
ized
th
r
e
s
h
o
ld
v
al
u
es
b
ec
au
s
e
o
f
th
i
s
o
p
tim
ized
th
r
es
h
o
ld
v
alu
e
s
t
h
e
ex
ec
u
tio
n
ti
m
e
a
n
d
co
m
p
u
tatio
n
a
l
co
s
t
h
a
v
e
r
ed
u
ce
d
to
v
er
y
lo
w
er
an
d
t
h
e
s
eg
m
en
tatio
n
o
f
co
lo
r
s
atellite
i
m
a
g
e
h
a
v
e
d
o
n
e
ef
f
e
ctiv
el
y
w
h
e
n
co
m
p
ar
e
to
th
e
p
r
ev
io
u
s
al
g
o
r
ith
m
[
1
,
2
]
.
RE
F
E
R
E
NC
E
[1
]
P
.
D
.
S
a
th
y
a
A
n
d
R
.
Ka
y
a
lv
izh
i
.
,
“
Op
ti
m
u
m
M
u
lt
il
e
v
e
l
I
m
a
g
e
T
h
re
sh
o
ld
in
g
Ba
se
d
o
n
T
sa
ll
is
En
tro
p
y
M
e
th
o
d
W
it
h
Ba
c
teria
l
F
o
ra
g
in
g
A
l
g
o
rit
h
m
”
.
[2
]
Ha
ss
a
n
Id
Be
n
Id
d
e
r
A
n
d
Na
b
il
L
a
a
c
h
f
o
u
b
i
.,”
Un
su
p
e
rv
ise
d
M
u
lt
i
lev
e
l
T
h
re
sh
o
ld
i
n
g
M
e
th
o
d
f
o
r
W
e
a
th
e
r
S
a
telli
te
Clo
u
d
S
e
g
m
e
n
tatio
n
”
.
[3
]
A
sh
ish
Ku
m
a
r
Bh
a
n
d
a
ri,
V
in
e
e
t
Ku
m
a
r
S
in
g
h
,
A
n
il
Ku
m
a
r,
G
iri
s
h
Ku
m
a
r
S
in
g
h
,
“
Cu
c
k
o
o
S
e
a
rc
h
A
lg
o
rit
h
m
a
n
d
W
in
d
Driv
e
n
Op
ti
m
iza
ti
o
n
Ba
se
d
S
tu
d
y
o
f
S
a
telli
te
I
m
a
g
e
S
e
g
m
e
n
tatio
n
F
o
r
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
in
g
Us
in
g
Ka
p
u
r’s E
n
t
ro
p
y
”
.
[4
]
Ho
n
g
b
in
g
L
iu
,
L
e
i
L
i
A
n
d
Ch
a
n
g
A
n
Wu
.,”
Co
lo
r
Im
a
g
e
S
e
g
m
e
n
tatio
n
A
lg
o
rit
h
m
s
Ba
s
e
d
o
n
G
ra
n
u
lar
Co
m
p
u
ti
n
g
Clu
ste
rin
g
”
.
[5
]
Ag
ra
w
a
l
.
S
,
P
a
n
d
a
.
R
,
Bh
u
y
a
n
.
S
&
P
a
n
ig
ra
h
i
.
B
.
K
.,”
T
sa
ll
is
En
tro
p
y
B
a
se
d
Op
ti
m
a
l
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
i
n
g
Us
in
g
Cu
c
k
o
o
S
e
a
rc
h
A
lg
o
rit
h
m
,
S
w
a
r
m
a
n
d
Ev
o
lu
ti
o
n
a
ry
Co
m
p
u
tatio
n
”
,
2
0
1
3
.
[6
]
Bh
a
n
d
a
ri
.
A
.
K
,
Ku
m
a
r
.
A
,
S
in
g
h
.
G
.
K
,
”
T
sa
ll
is
En
tro
p
y
Ba
s
e
d
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
in
g
F
o
r
C
o
l
o
re
d
S
a
telli
te
Im
a
g
e
S
e
g
m
e
n
tatio
n
Us
in
g
Ev
o
l
u
ti
o
n
a
ry
A
lg
o
rit
h
m
s
”
,
2
0
1
5
.
[7
]
A
li
.
M
.,
S
iarry
,
P
.
,
&
P
a
n
t
,
M
.
,
”
A
n
Eff
i
c
ien
t
Diff
e
re
n
ti
a
l
Ev
o
lu
ti
o
n
Ba
se
d
A
lg
o
rit
h
m
f
o
r
S
o
lv
in
g
M
u
lt
i
O
b
jec
ti
v
e
Op
ti
m
iza
ti
o
n
P
ro
b
lem
s”
,
2
0
1
2
.
[8
]
Bh
a
n
d
a
ri
.
A
.
K
,
Ku
m
a
r
,
A
.,
S
in
g
h
,
G
.
K
.
,
&
S
o
n
i
,
V
.
,
”
P
e
rf
o
rm
a
n
c
e
S
tu
d
y
o
f
Ev
o
lu
ti
o
n
a
ry
A
lg
o
rit
h
m
f
o
r
Diffe
re
n
t
W
a
v
e
let
F
il
ters
f
o
r
S
a
telli
te Im
a
g
e
De
n
o
isin
g
Us
in
g
S
u
b
Ba
n
d
A
d
a
p
ti
v
e
T
h
re
sh
o
ld
”
,
2
0
1
5
.
[9
]
Bh
a
n
d
a
ri
,
A
.
K
,
S
o
n
i
,
V
,
Ku
m
a
r
,
A
,
&
S
in
g
h
,
G
.
K
.,”
Cu
c
k
o
o
S
e
a
rc
h
A
l
g
o
rit
h
m
Ba
s
e
d
S
a
telli
te
I
m
a
g
e
Co
n
tras
t
a
n
d
Brig
h
tn
e
ss
En
h
a
n
c
e
m
e
n
t
Us
in
g
D
WT
–
S
V
D
”
,
2
0
1
4
.
[1
0
]
M
a
n
ik
a
n
d
a
n
,
S
.,
Ra
m
a
r
,
K
.,
W
il
lj
u
ice
,
I
.
M
.,&
S
rin
iv
a
sa
g
a
n
,
K
.
G
.
,
”
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
i
n
g
f
o
r
S
e
g
m
e
n
tatio
n
o
f
M
e
d
ica
l
Bra
in
Im
a
g
e
s U
sin
g
Re
a
l
Co
d
e
d
G
e
n
e
ti
c
A
l
g
o
rit
h
m
”
,
2
0
1
4
.
[1
1
]
Oliv
a
,
D
.,
Cu
e
v
a
s
,
E
.,
P
a
jare
s
,
G
.,
Zald
iv
a
r
,
D
.
,
&
P
e
re
z
-
Cisn
e
ro
s
,
M
.,”
M
u
lt
i
lev
e
l
T
h
re
sh
o
ld
i
n
g
S
e
g
m
e
n
tatio
n
Ba
se
d
o
n
Ha
rm
o
n
y
S
e
a
rc
h
Op
ti
m
iz
a
ti
o
n
”
,
2
0
1
3
.
[1
2
]
P
a
tra
,
S
.,
G
a
u
ta
m
,
R
.
,
&
S
in
g
la
,
A
.,”
A
No
v
e
l
Co
n
tex
t
S
e
n
siti
v
e
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
i
n
g
f
o
r
I
m
a
g
e
S
e
g
m
e
n
tatio
n
”
,
2
0
1
4
.
[1
3
]
Ha
m
m
o
u
c
h
e
,
K
.,
Dia
f
,
M
.
,
&
S
i
a
rr
y
,
P
.,”
A
M
u
lt
il
e
v
e
l
A
u
to
m
a
ti
c
T
h
re
sh
o
ld
in
g
M
e
t
h
o
d
Ba
se
d
o
n
A
G
e
n
e
ti
c
A
l
g
o
rit
h
m
f
o
r
F
a
st I
m
a
g
e
S
e
g
m
e
n
tatio
n
”
,
2
0
0
8
.
[1
4
]
Ha
m
d
a
o
u
i
,
F
.
,
S
a
k
ly
,
A
.
,
A
n
d
M
ti
b
a
a
,
A
.,”
A
n
Eff
icie
n
t
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
i
n
g
M
e
th
o
d
f
o
r
Im
a
g
e
S
e
g
m
e
n
tatio
n
Ba
se
d
o
n
T
h
e
Hy
b
rid
iza
ti
o
n
Of
M
o
d
if
ied
P
S
O
a
n
d
Otsu
’s
M
e
t
h
o
d
”
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.