I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
,
p
p
.
1
4
9
9
~
1
5
1
4
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
:
1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
3
.
pp
1
4
9
9
-
1
5
1
4
1499
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Integ
ra
ted
NIR
-
H
E ba
sed
SP
O
T
-
5
ima
g
e enhance
ment me
thod
for fe
a
tu
res pr
ese
rv
a
tion a
nd edge
detec
tion
F
a
rizuwa
na
Ak
ma
Z
ulk
if
le
1
,
Ro
ha
y
a
nti
H
a
s
s
a
n
2
,
M
o
ha
mm
a
d Na
zir
Ahm
a
d
3
,
Sh
a
hree
n K
a
s
im
4
,
T
o
le
Su
t
ik
no
5
,
Sh
a
hli
za
Abd
H
a
lim
6
1
F
a
k
u
lt
i
S
a
in
s K
o
m
p
u
ter d
a
n
M
a
t
e
m
a
ti
k
,
Un
iv
e
rsiti
Tek
n
o
l
o
g
i
M
A
RA,
Ku
a
la P
il
a
h
,
M
a
lay
sia
1,
2
,6
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
,
F
a
c
u
lt
y
o
f
E
n
g
i
n
e
e
rin
g
,
Un
i
v
e
rsiti
Te
k
n
o
lo
g
i
M
a
lay
sia
,
Jo
h
o
r
Ba
h
ru
,
M
a
la
y
sia
3
In
stit
u
te
o
f
Visu
a
l
In
f
o
rm
a
ti
c
s,
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
,
B
a
n
g
i
,
M
a
lay
sia
4
F
a
c
u
lt
y
o
f
C
o
m
p
u
ti
n
g
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
,
U
n
iv
e
rsiti
Tu
n
Hu
ss
e
in
O
n
n
M
a
lay
sia
,
P
a
rit
Ra
ja
,
M
a
lay
sia
5
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
E
n
g
i
n
e
e
rin
g
,
F
a
c
u
lt
y
o
f
I
n
d
u
strial
Tec
h
n
o
lo
g
y
,
Un
i
v
e
rsitas
Ah
m
a
d
Da
h
la
n
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l
17
,
2
0
2
1
R
ev
is
ed
Oct
6
,
2021
Acc
ep
ted
Oct
23
,
2
0
2
1
Re
c
e
n
tl
y
,
m
a
n
y
re
se
a
rc
h
e
rs
h
a
v
e
d
irec
ted
t
h
e
ir
a
tt
e
n
t
io
n
t
o
m
e
th
o
d
s
o
f
p
re
d
ictin
g
sh
o
re
li
n
e
s
b
y
th
e
u
se
o
f
m
u
lt
is
p
e
c
tral
ima
g
e
s.
Th
u
s,
a
sim
p
le
a
n
d
o
p
ti
m
ise
d
m
e
th
o
d
u
si
n
g
ima
g
e
e
n
h
a
n
c
e
m
e
n
ts
is
p
ro
p
o
se
d
t
o
imp
ro
v
e
t
h
e
l
o
w
c
o
n
tras
t
o
f
th
e
S
a
telli
te
p
o
u
r
l'
Ob
se
rv
a
ti
o
n
d
e
la
Terre
-
5
(S
P
OT
-
5
)
ima
g
e
s
in
th
e
d
e
tec
ti
o
n
o
f
sh
o
re
li
n
e
s.
T
h
e
n
e
a
r
-
in
fra
re
d
(NIR)
c
h
a
n
n
e
l
is
i
m
p
o
rtan
t
i
n
th
is
st
u
d
y
t
o
e
n
su
re
th
e
c
o
n
tras
t
o
f
t
h
e
v
e
g
e
tate
d
a
re
a
a
n
d
se
a
c
la
ss
ifi
c
a
ti
o
n
,
d
u
e
to
t
h
e
h
i
g
h
re
flec
tan
c
e
o
f
lea
v
e
s
in
th
e
n
e
a
r
in
fra
r
e
d
wa
v
e
len
g
th
re
g
i
o
n
.
Th
is
stu
d
y
u
se
d
fi
v
e
sc
e
n
e
s
o
f
in
tere
st
to
sh
o
w
th
e
d
iffere
n
t
re
su
lt
s
in
sh
o
re
li
n
e
d
e
tec
ti
o
n
.
Th
e
re
su
l
ts
d
e
m
o
n
stra
ted
t
h
a
t
t
h
e
p
ro
p
o
se
d
m
e
th
o
d
p
e
rfo
rm
e
d
i
n
a
n
e
n
h
a
n
c
e
d
m
a
n
n
e
r
a
s
c
o
m
p
a
re
d
t
o
c
u
rre
n
t
m
e
th
o
d
s
wh
e
n
d
e
a
li
n
g
wit
h
th
e
lo
w
c
o
n
tras
t
ra
ti
o
o
f
S
P
OT
-
5
ima
g
e
s.
As
a
re
su
lt
,
b
y
u
ti
li
si
n
g
th
e
n
e
a
r
-
i
n
fra
re
d
h
ist
o
g
r
a
m
e
q
u
a
li
z
a
ti
o
n
(NIR
-
HE),
th
e
c
o
n
tras
t
o
f
a
ll
d
a
tas
e
ts
wa
s
e
fficie
n
tl
y
re
sto
re
d
,
p
r
o
d
u
c
in
g
a
h
i
g
h
e
r
e
fficie
n
c
y
in
e
d
g
e
d
e
tec
ti
o
n
,
a
n
d
a
c
h
iev
in
g
h
ig
h
e
r
o
v
e
ra
ll
a
c
c
u
ra
c
y
.
T
h
e
i
m
p
r
o
v
e
d
fil
terin
g
m
e
th
o
d
sh
o
we
d
sig
n
ifi
c
a
n
tl
y
b
e
tt
e
r
sh
o
re
li
n
e
d
e
tec
ti
o
n
re
su
lt
s
t
h
a
n
t
h
e
o
th
e
r
fil
ter
m
e
th
o
d
s.
It
wa
s
c
o
n
c
lu
d
e
d
t
h
a
t
t
h
is
m
e
th
o
d
wo
u
ld
b
e
u
se
fu
l
f
o
r
d
e
tec
ti
n
g
a
n
d
m
o
n
it
o
rin
g
t
h
e
sh
o
r
e
li
n
e
e
d
g
e
i
n
Tan
ju
n
g
P
iai.
K
ey
w
o
r
d
s
:
Fil
ter
in
g
m
eth
o
d
His
to
g
r
am
eq
u
alis
atio
n
I
m
ag
e
en
h
an
ce
m
en
t
Sh
o
r
elin
e
d
etec
tio
n
SP
OT
-
5
im
ag
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Far
izu
wan
a
Ak
m
a
Z
u
l
k
if
le
Fak
u
lti Sain
s
Ko
m
p
u
ter
d
a
n
Ma
tem
atik
,
Un
iv
er
s
iti T
ek
n
o
l
o
g
i M
AR
A
C
awa
n
g
an
Neg
er
i Sem
b
ilan
K
am
p
u
s
Ku
ala
Pil
ah
,
Ku
ala
Pil
ah
,
Neg
er
i Sem
b
ilan
,
Ma
lay
s
ia
E
m
ail: f
ar
izu
wan
a@
u
itm
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Sh
o
r
elin
e
d
elin
ea
tio
n
is
d
if
f
icu
lt,
tim
e
-
co
n
s
u
m
in
g
,
an
d
s
o
m
etim
es
im
p
o
s
s
ib
le
f
o
r
th
e
en
ti
r
e
co
astal
s
y
s
tem
wh
en
u
s
in
g
tr
ad
itio
n
al
g
r
o
u
n
d
s
u
r
v
ey
in
g
tech
n
iq
u
es
[
1
]
–
[
5
]
.
C
o
n
s
eq
u
en
tly
,
i
n
s
atellite
im
ag
es,
th
er
e
is
a
n
ee
d
to
o
v
er
c
o
m
e
th
e
d
if
f
icu
lties
in
th
e
ex
tr
ac
tio
n
o
f
s
h
o
r
elin
es
[
3
]
–
[
2
1
]
.
Ma
n
y
c
o
m
p
u
tatio
n
al
m
et
h
o
d
s
ar
e
y
et
to
b
e
im
p
r
o
v
e
d
,
an
d
c
o
m
p
r
eh
en
s
iv
e
m
eth
o
d
o
l
o
g
ies
ar
e
n
ee
d
ed
to
b
e
d
e
v
elo
p
e
d
to
ex
tr
ac
t
th
e
co
m
p
lex
p
r
o
p
er
ties
o
f
m
u
lti
-
f
ea
tu
r
es
in
s
atellite
im
ag
es
[
2
]
,
[
6
]
,
[
2
2
]
–
[
3
4
]
.
T
h
e
ch
allen
g
es
o
f
s
h
o
r
elin
e
d
etec
tio
n
ar
e
f
ac
ed
d
u
r
i
n
g
th
e
ex
tr
ac
tio
n
o
f
d
en
s
e
ar
ea
f
ea
tu
r
es,
wh
en
th
e
s
atellite
im
ag
es
s
u
f
f
er
f
r
o
m
s
u
r
f
ac
e
r
ef
lecta
n
ce
d
u
r
in
g
d
ata
ac
q
u
is
itio
n
[
2
]
,
[
4
]
,
[
5
]
,
[
2
2
]
,
[
3
1
]
,
[
3
2
]
,
[
3
5
]
,
[
3
6
]
.
T
h
e
cu
r
r
en
t
m
eth
o
d
s
ar
e
d
i
s
cu
s
s
ed
to
an
aly
s
e
th
e
lim
itatio
n
s
th
at
o
cc
u
r
d
u
r
i
n
g
s
h
o
r
elin
e
d
etec
tio
n
.
T
h
er
e
ar
e
s
ev
er
al
o
b
jectiv
es e
x
p
lain
e
d
,
wh
ich
in
d
icate
as
to
wh
y
th
is
r
esear
ch
is
b
ein
g
co
n
d
u
cted
t
o
n
o
tify
th
e
im
p
o
r
tan
ce
o
f
ac
c
o
m
p
lis
h
in
g
th
e
g
o
al.
Fu
r
th
er
m
o
r
e,
Satellite
p
o
u
r
l'
Ob
s
er
v
atio
n
d
e
la
T
er
r
e
-
5
(
SP
OT
-
5
)
im
ag
e
s
ar
e
u
s
ed
th
r
o
u
g
h
o
u
t
th
is
s
tu
d
y
b
y
u
tili
zin
g
t
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
9
9
-
1
5
1
4
1500
p
an
-
s
h
ar
p
e
n
ed
im
a
g
e
with
a
co
m
b
in
atio
n
o
f
th
e
f
alse
c
o
lo
r
co
m
p
o
s
ites
wh
ich
co
n
s
i
s
t
o
f
n
ea
r
-
in
f
r
ar
e
d
(
NI
R
)
,
r
ed
,
an
d
g
r
ee
n
c
h
an
n
els.
Su
b
s
eq
u
en
tly
,
th
e
c
o
n
t
r
asts
o
f
th
e
SP
OT
-
5
im
ag
es
ar
e
im
p
r
o
v
ed
b
y
in
teg
r
atin
g
th
e
n
ea
r
i
n
f
r
ar
e
d
h
is
to
g
r
am
e
q
u
aliza
tio
n
(
NI
R
-
HE
)
m
eth
o
d
f
o
r
f
ea
tu
r
es
p
r
e
s
er
v
atio
n
an
d
e
d
g
e
d
etec
tio
n
[
2
3
]
,
[
3
3
]
,
[
3
7
]
–
[
4
0
]
.
An
im
ag
e
ca
p
tu
r
ed
in
b
ad
w
ea
th
er
o
f
ten
y
ield
s
lo
w
co
n
tr
ast
r
esu
lts
,
d
u
e
to
p
er
s
is
ten
t
clo
u
d
co
v
er
an
d
h
az
i
n
ess
,
wh
ich
atten
u
ates
s
ce
n
e
r
ad
ian
ce
[
2
3
]
,
[
4
1
]
.
H
en
ce
,
elec
tr
o
m
a
g
n
etic
e
n
er
g
y
is
u
n
ab
le
to
r
ea
ch
th
e
s
en
s
o
r
b
ef
o
r
e
it
p
ass
es
th
r
o
u
g
h
a
s
u
b
s
tan
tial
atm
o
s
p
h
e
r
ic
s
ce
n
e
[
2
3
]
,
[
4
2
]
.
Haz
y
d
a
y
s
in
Ma
lay
s
ia
ar
e
m
o
s
t
lik
ely
to
o
cc
u
r
f
r
o
m
J
an
u
ar
y
to
Feb
r
u
a
r
y
an
d
f
r
o
m
J
u
n
e
to
Au
g
u
s
t
[
4
3
]
,
[
4
4
]
.
Haz
e
is
th
e
ap
p
ea
r
an
ce
o
f
a
t
m
o
s
p
h
e
r
i
c
a
b
s
o
r
p
ti
o
n
a
n
d
s
c
a
t
t
e
r
i
n
g
o
f
g
a
s
e
s
.
T
h
e
p
a
r
t
ic
l
es
t
h
a
t
c
a
u
s
e
t
h
e
h
a
z
y
a
p
p
e
a
r
a
n
c
e
m
a
y
o
r
i
g
i
n
a
t
e
f
r
o
m
m
a
n
y
s
o
u
r
c
e
s
,
s
o
m
e
o
f
w
h
ic
h
a
r
e
n
a
t
u
r
a
l
s
o
u
r
c
es
a
n
d
s
o
m
e
o
f
w
h
i
c
h
a
r
e
a
n
t
h
r
o
p
o
g
e
n
i
c
s
o
u
r
c
e
s
[
4
5
]
–
[
4
7
]
.
Natu
r
al
s
o
u
r
ce
s
in
clu
d
e
th
e
o
ce
an
s
,
f
o
r
ests
an
d
th
e
g
r
o
u
n
d
s
u
r
f
ac
e.
Ho
wev
er
,
a
m
ajo
r
ity
o
f
th
e
p
ar
ticu
lates
o
r
ig
in
ate
f
r
o
m
h
u
m
an
ac
tiv
iti
es
s
u
ch
as
o
p
en
b
u
r
n
in
g
,
lan
d
clea
r
in
g
an
d
th
e
co
m
b
u
s
tio
n
o
f
f
o
s
s
il
f
u
els
in
in
d
u
s
tr
ial
b
o
iler
s
.
I
m
ag
es
tak
e
n
with
s
u
r
f
ac
e
r
ef
lecta
n
ce
c
o
n
d
itio
n
s
will
b
e
a
f
f
ec
ted
b
y
th
e
lo
w
co
n
tr
ast
[
4
2
]
.
T
h
er
ef
o
r
e,
m
is
class
if
icatio
n
o
f
f
ea
tu
r
es
m
ay
o
cc
u
r
d
u
e
to
l
o
w
co
n
tr
ast.
T
h
e
ef
f
icien
c
y
o
f
th
e
h
az
e
r
em
o
v
al
m
eth
o
d
to
r
em
o
v
e
h
az
e
is
p
r
o
b
ab
ly
n
o
t
q
u
ite
as
s
u
f
f
icien
t
as
th
e
m
u
ltis
p
ec
tr
al
d
ata
ap
p
lied
,
wh
ich
is
m
ea
n
t
f
o
r
r
etr
ie
v
in
g
f
ea
t
u
r
es in
th
e
in
co
r
r
ec
t c
lass
es.
Mo
r
eo
v
er
,
im
ag
er
y
with
th
e
p
r
es
en
ce
o
f
s
u
r
f
ac
e
r
ef
lecta
n
ce
is
p
r
o
n
e
to
h
av
e
wea
k
ed
g
es,
p
o
o
r
v
is
ib
ilit
y
,
an
d
m
is
class
if
ied
p
ix
els
[
4
6
]
–
[
5
0
]
.
As
a
r
esu
lt,
th
is
wo
u
ld
p
r
o
d
u
ce
in
ef
f
i
cien
t
ex
tr
a
ctio
n
o
f
m
u
lticlas
s
es,
wh
ich
ca
u
s
es
m
is
s
in
g
lin
e
cu
es
an
d
a
m
ix
t
u
r
e
o
f
f
ea
tu
r
es.
I
n
o
r
d
er
to
p
r
o
d
u
ce
a
p
r
ed
ictio
n
o
f
s
h
o
r
elin
e
ch
a
n
g
es,
th
e
s
ec
o
n
d
ch
allen
g
e
is
to
ca
ter
,
wh
ich
i
s
to
im
p
r
o
v
e
t
h
e
f
ilter
in
g
m
et
h
o
d
b
y
s
h
ar
p
en
i
n
g
th
e
im
ag
e
b
o
u
n
d
a
r
ies
an
d
eli
m
in
atin
g
th
e
p
r
o
b
lem
o
f
m
is
cl
ass
if
ied
p
ix
els
o
f
th
e
s
h
o
r
elin
e
.
Un
f
o
r
tu
n
ately
,
th
e
p
r
ed
ictio
n
o
f
s
h
o
r
elin
es
is
o
f
te
n
p
o
o
r
b
ec
au
s
e
o
f
i
n
ac
cu
r
ate
f
ea
tu
r
es
d
u
e
to
m
is
class
if
icatio
n
.
T
h
e
im
ag
es m
ay
lo
s
e
im
ag
e
in
f
o
r
m
atio
n
[
5
1
]
.
As
a
co
n
s
eq
u
en
ce
,
an
im
p
r
o
v
ed
f
ilter
in
g
m
eth
o
d
is
ess
en
tia
l
f
o
r
d
r
awin
g
m
o
r
e
r
eliab
le
ed
g
es
f
o
r
s
h
o
r
elin
es,
with
a
h
ig
h
ac
cu
r
ac
y
o
f
f
ea
tu
r
es
class
if
ica
tio
n
.
T
h
ese
wo
u
ld
ev
en
tu
ally
p
r
o
d
u
ce
clea
r
r
ec
o
g
n
itio
n
a
n
d
ex
tr
ac
ti
o
n
o
f
s
h
o
r
elin
es
[
2
]
,
[
4
]
,
[
2
2
]
,
[
3
2
]
,
[
3
5
]
.
Ad
d
itio
n
ally
,
f
o
r
e
ac
h
ap
p
licatio
n
an
d
im
ag
e,
a
cu
s
to
m
im
a
g
e
en
h
an
ce
m
en
t
m
eth
o
d
,
an
d
an
a
d
ju
s
tm
en
t
o
f
c
o
n
tr
ast
wh
ile
p
r
es
er
v
in
g
th
e
e
d
g
es
ar
e
u
s
u
ally
n
ec
ess
ar
y
.
T
h
e
g
o
al
o
f
NI
R
-
HE
u
s
in
g
th
e
NI
R
ch
an
n
el
is
to
im
p
r
o
v
e
t
h
e
im
ag
e
co
n
tr
ast
a
n
d
h
en
ce
t
o
m
ak
e
it
s
u
itab
le
f
o
r
class
if
icatio
n
o
f
v
eg
etatio
n
in
f
ea
tu
r
e
ex
tr
ac
tio
n
[
2
]
,
[
2
8
]
,
[
3
3
]
,
[
3
8
]
,
[
4
0
]
,
[
4
8
]
,
[
5
2
]
–
[
5
5
]
.
T
h
e
f
alse
co
lo
r
c
o
m
p
o
s
ite
im
ag
e
i
s
en
h
an
ce
d
u
s
in
g
HE
alg
o
r
it
h
m
.
T
h
e
r
an
g
e
o
f
b
r
i
g
h
tn
ess
v
a
lu
es
p
r
esen
ted
in
an
im
ag
e
is
r
ef
er
r
ed
to
as
a
co
n
tr
ast.
T
h
u
s
,
th
e
co
n
tr
ast
is
en
h
an
ce
d
ef
f
icien
tly
b
y
u
s
in
g
HE
i
n
a
SP
OT
-
5
im
ag
e.
An
ad
v
an
tag
e
o
f
th
is
m
eth
o
d
i
s
th
at
it m
an
ip
u
lates th
e
NI
R
c
h
an
n
el,
g
r
ee
n
ch
a
n
n
el
an
d
r
ed
ch
an
n
el
[
5
6
]
–
[
6
7
]
.
B
y
u
tili
zin
g
th
e
N
I
R
ch
an
n
el,
it
is
im
p
o
r
tan
t
t
o
n
o
te
th
at
t
h
e
d
ee
p
p
e
n
etr
atio
n
o
f
its
lo
n
g
wav
elen
g
th
m
ak
es
it
p
o
s
s
ib
le
to
u
n
v
eil
th
e
d
etails
o
f
v
e
g
etatio
n
t
h
at
co
u
ld
o
t
h
er
wis
e
b
e
lo
s
t
en
tire
ly
[
4
9
]
,
[
5
3
]
,
[
6
2
]
,
[
6
8
]
–
[
7
0
]
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
NI
R
-
HE
m
eth
o
d
is
to
im
p
r
o
v
e
th
e
lo
w
co
n
tr
ast
o
f
a
n
im
ag
e
ca
u
s
ed
b
y
s
u
r
f
ac
e
r
ef
lecta
n
ce
is
s
u
es.
T
h
is
p
ap
er
is
co
m
p
o
s
ed
o
f
s
ev
er
al
s
ec
tio
n
s
.
S
ec
tio
n
2
d
is
cu
s
s
es
r
e
s
ea
r
ch
m
eth
o
d
o
n
im
ag
e
en
h
an
ce
m
e
n
t,
p
a
n
-
s
h
ar
p
e
n
in
g
,
in
teg
r
atin
g
NI
R
ch
an
n
el
a
n
d
im
ag
e
class
if
icatio
n
.
Sectio
n
3
e
x
p
lain
s
th
e
an
aly
s
is
o
f
th
e
im
ag
e
en
h
a
n
ce
m
en
t
m
eth
o
d
an
d
a
n
aly
s
is
o
f
f
ea
tu
r
e
s
ig
n
atu
r
es.
T
h
e
co
n
clu
s
io
n
s
an
d
r
ec
o
m
m
en
d
atio
n
s
f
o
r
f
u
tu
r
e
w
o
r
k
ar
e
p
r
esen
ted
i
n
s
ec
tio
n
4.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
I
ma
g
e
enha
ncem
ent
Ma
n
y
r
esear
ch
er
s
in
r
ec
en
t y
e
ar
s
h
av
e
f
o
cu
s
ed
o
n
im
ag
es tak
en
in
b
ad
wea
th
er
,
wh
ich
o
f
t
en
p
r
o
d
u
ce
lo
w
co
n
tr
ast
r
esu
lts
d
u
e
to
th
e
p
r
esen
ce
o
f
s
u
r
f
ac
e
r
ef
le
ctan
ce
in
th
e
atm
o
s
p
h
er
e,
w
h
ich
r
ed
u
ce
s
s
ce
n
e
r
ad
ian
ce
[
7
1
]
.
I
n
th
e
p
r
o
ce
s
s
o
f
im
ag
e
en
h
an
ce
m
en
t,
t
h
e
n
o
is
e
will
b
e
r
em
o
v
ed
f
r
o
m
th
e
im
ag
es,
an
d
th
e
i
m
ag
e
co
n
tr
ast
will
b
e
en
h
a
n
ce
d
.
L
o
w
co
n
tr
ast
im
ag
es
with
wea
k
ed
g
es
p
o
s
e
ch
allen
g
es
in
th
e
f
ield
s
o
f
co
m
p
u
ter
v
is
io
n
an
d
p
atter
n
r
ec
o
g
n
itio
n
[
7
2
]
.
Ho
wev
er
,
t
h
e
all
y
ea
r
r
o
u
n
d
tr
o
p
ical
h
o
t
a
n
d
h
u
m
id
clim
ate
in
Ma
lay
s
ia
is
also
a
ch
allen
g
in
g
p
r
o
b
lem
b
ec
au
s
e
o
f
th
e
r
elev
an
ce
b
etwe
en
th
e
p
er
s
is
ten
t
clo
u
d
co
v
e
r
s
an
d
h
az
y
d
ay
s
.
R
em
o
v
i
n
g
t
h
e
n
o
is
es
ca
n
in
cr
ea
s
e
th
e
v
is
ib
ilit
y
o
f
th
e
s
ce
n
e
,
co
r
r
ec
tin
g
th
e
co
l
o
r
s
h
if
t
a
f
f
ec
ted
b
y
th
e
air
lig
h
t
[
7
3
]
.
I
m
ag
es
with
s
u
r
f
ac
e
r
ef
lecta
n
c
e
co
n
d
itio
n
s
will
r
ed
u
ce
v
is
ib
ilit
y
,
an
d
l
o
w
co
n
tr
ast
im
a
g
es
r
ed
u
ce
th
e
p
er
f
o
r
m
an
ce
o
f
v
a
r
io
u
s
im
ag
e
p
r
o
ce
s
s
in
g
an
d
co
m
p
u
ter
v
is
io
n
tech
n
iq
u
es
[
4
1
]
.
T
h
e
d
e
h
az
in
g
m
eth
o
d
is
a
s
tan
d
ar
d
tech
n
iq
u
e
to
r
em
o
v
e
s
u
r
f
ac
e
r
ef
lecta
n
ce
an
d
en
s
u
r
e
h
ig
h
im
ag
e
v
is
ib
ilit
y
,
as
we
ll
as
to
co
r
r
ec
t
th
e
co
lo
r
s
h
if
t
ca
u
s
ed
b
y
t
h
e
air
li
g
h
t
[
7
4
]
.
T
h
e
im
ag
e
with
th
e
p
r
esen
ce
o
f
s
u
r
f
ac
e
r
e
f
lecta
n
c
e
is
s
u
es
is
p
r
o
n
e
to
h
av
e
b
iased
lo
w
co
n
tr
ast s
ce
n
e
r
ad
ian
ce
.
Ho
wev
er
,
h
az
e
r
e
m
o
v
al
h
as b
ee
n
a
ch
allen
g
in
g
is
s
u
e
wh
er
e
th
e
h
a
zy
s
itu
atio
n
is
d
ep
en
d
en
t
o
n
u
n
k
n
o
wn
d
ep
th
in
f
o
r
m
atio
n
[
7
4
]
.
Acc
o
r
d
in
g
to
[
7
5
]
,
th
e
o
r
ig
in
al
d
etails
o
f
im
a
g
es
n
ee
d
to
b
e
p
r
eser
v
e
d
,
ev
en
th
o
u
g
h
th
e
v
is
u
ality
o
f
a
n
im
ag
e
h
as
b
ee
n
im
p
r
o
v
e
d
.
Ma
n
y
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
ad
d
r
ess
in
g
th
e
p
r
o
b
lem
o
f
s
u
r
f
ac
e
r
ef
lecta
n
c
e
co
n
d
itio
n
s
u
ch
as
h
az
y
an
d
clo
u
d
y
co
n
d
itio
n
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
teg
r
a
ted
N
I
R
-
HE
b
a
s
ed
S
P
OT
-
5
ima
g
e
en
h
a
n
ce
men
t m
et
h
o
d
fo
r
fea
tu
r
es
…
(
F
a
r
iz
u
w
a
n
a
A
kma
Zu
lkifle
)
1501
T
h
ese
ap
p
r
o
ac
h
es
ar
e
ca
teg
o
r
ized
in
to
two
ty
p
es:
m
u
ltip
le
im
ag
e
p
r
o
ce
s
s
in
g
o
r
ad
d
i
tio
n
al
in
f
o
r
m
atio
n
m
eth
o
d
s
[
7
6
]
–
[
7
9
]
,
an
d
s
in
g
l
e
im
ag
e
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
es
[
2
9
]
,
[
4
2
]
,
[
4
3
]
,
[
7
3
]
,
[
8
0
]
–
[
8
2
]
.
T
h
er
ef
o
r
e,
a
co
m
p
r
eh
e
n
s
iv
e
s
tu
d
y
to
im
p
r
o
v
e
th
e
s
u
r
f
ac
e
r
e
f
lecta
n
ce
p
r
o
b
lem
wh
ile
m
ain
tain
in
g
d
etailed
in
f
o
r
m
atio
n
o
n
an
im
ag
e
is
h
ig
h
l
y
r
ec
o
m
m
en
d
ed
.
2
.
2
.
P
a
n
-
s
ha
rpening
o
f
SPO
T
-
5
im
a
g
es
As
d
ep
icted
in
Fig
u
r
e
1
,
p
a
n
-
s
h
ar
p
en
in
g
was
u
s
ed
to
in
cr
ea
s
e
th
e
s
p
atial
r
eso
lu
tio
n
,
a
n
d
to
p
r
o
v
id
e
b
etter
v
is
u
aliza
tio
n
o
f
a
m
u
lti
b
an
d
im
ag
e
,
u
s
in
g
a
lo
wer
-
r
e
s
o
lu
tio
n
an
d
s
in
g
le
-
b
an
d
im
a
g
e
[
8
3
]
–
[
8
6
]
.
Pan
-
s
h
ar
p
en
in
g
is
th
e
p
r
o
ce
s
s
o
f
m
er
g
in
g
m
u
ltis
p
ec
tr
al
an
d
p
an
c
h
r
o
m
atic
im
ag
er
y
,
th
er
e
b
y
cr
e
atin
g
a
s
in
g
le
h
ig
h
-
r
eso
lu
tio
n
co
lo
u
r
im
ag
e
.
A
p
a
n
ch
r
o
m
atic
im
a
g
e
co
n
tain
s
o
n
ly
o
n
e
wid
e
c
h
an
n
el
o
f
r
ef
lect
an
ce
d
ata.
Mo
d
er
n
m
u
ltis
p
ec
tr
al
s
ca
n
n
er
s
also
g
en
er
ally
in
clu
d
e
s
o
m
e
r
ad
iati
o
n
at
s
lig
h
tly
lo
n
g
er
wav
elen
g
th
s
th
an
r
ed
lig
h
t,
ca
lled
n
ea
r
in
f
r
ar
e
d
.
Pan
ch
r
o
m
atic
im
ag
es
ca
n
b
e
g
en
er
all
y
co
llected
with
a
h
ig
h
er
s
p
at
ial
r
eso
lu
tio
n
th
an
a
m
u
ltis
p
ec
tr
a
l
im
ag
e,
b
ec
au
s
e
th
e
b
r
o
ad
s
p
ec
tr
al
r
an
g
e
a
llo
ws
f
o
r
s
m
aller
d
etec
to
r
s
to
b
e
u
s
ed
wh
ile
m
ain
tain
in
g
a
h
i
g
h
s
ig
n
al
-
to
-
n
o
is
e
r
atio
[
7
]
,
[
8
4
]
,
[
8
7
]
,
[
8
8
]
.
I
n
c
o
n
tr
ast,
a
m
u
ltis
p
ec
tr
a
l
im
ag
e
is
o
n
e
th
at
co
n
tain
s
m
o
r
e
t
h
an
o
n
e
s
p
ec
tr
al
ch
an
n
el.
A
s
im
p
le
e
x
am
p
le
o
f
a
m
u
ltis
p
ec
tr
al
im
ag
e
is
a
c
o
lo
u
r
im
a
g
e
wh
ich
c
o
n
tain
s
th
r
ee
ch
a
n
n
els,
co
r
r
e
s
p
o
n
d
in
g
t
o
th
e
r
e
d
,
g
r
ee
n
an
d
b
lu
e
wav
elen
g
t
h
ch
an
n
els
o
f
t
h
e
elec
tr
o
m
ag
n
etic
s
p
ec
tr
u
m
[
8
9
]
–
[
1
0
5
]
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
et
h
o
d
2
.
3
.
I
nte
g
ra
t
ing
nea
r
-
infr
a
r
ed
cha
nn
els
Af
ter
th
e
p
r
o
ce
s
s
,
a
m
u
ltib
an
d
r
aster
d
ataset
(
R
,
G,
B
)
is
p
r
o
d
u
ce
d
.
T
h
en
,
th
e
d
ata
im
a
g
e
c
an
ch
o
o
s
e
eith
er
a
s
in
g
le
ch
a
n
n
el
o
f
d
ata
o
r
ca
n
f
o
r
m
a
co
l
o
u
r
c
o
m
p
o
s
ite
f
r
o
m
m
u
ltip
le
ch
an
n
els
[
8
4
]
.
A
co
m
b
in
atio
n
o
f
an
y
th
r
ee
av
ailab
le
ch
an
n
els
with
in
a
d
ataset
ca
n
cr
ea
te
r
e
d
,
g
r
ee
n
,
an
d
b
lu
e
(
R
GB
)
co
m
p
o
s
ites
[
1
0
6
]
–
[
1
1
3
]
.
T
h
er
e
ar
e
m
a
n
y
p
o
s
s
ib
le
s
ch
em
es
f
o
r
p
r
o
d
u
cin
g
a
n
R
GB
co
m
p
o
s
ite
o
r
f
alse
co
lo
u
r
co
m
p
o
s
ite
im
ag
es.
Ho
wev
er
,
ea
ch
s
ch
em
e
h
as
th
e
ab
ilit
y
to
d
etec
t
s
p
ec
if
ic
o
b
j
ec
ts
in
an
im
ag
e.
I
n
t
h
is
s
tu
d
y
,
th
e
f
alse
c
o
lo
u
r
co
m
p
o
s
ites
in
clu
d
e
th
e
NI
R
c
h
an
n
el,
th
e
g
r
ee
n
ch
a
n
n
el
(
G)
an
d
th
e
r
ed
ch
a
n
n
el
(
R
)
,
as
d
ep
icted
in
Fig
u
r
e
2
.
T
h
is
in
teg
r
atio
n
o
f
NI
R
ch
an
n
els is
s
u
itab
le
f
o
r
d
etec
tin
g
v
e
g
etatio
n
an
d
wate
r
b
o
d
ies.
T
h
er
e
is
a
co
m
b
in
atio
n
o
f
th
e
f
alse
co
l
o
u
r
co
m
p
o
s
ite
u
s
ed
in
d
etec
tin
g
v
eg
etatio
n
,
with
th
e
r
e
d
c
h
an
n
el
r
ep
lace
d
in
th
e
NI
R
c
h
an
n
el.
T
h
e
u
s
e
o
f
t
h
e
NI
R
ch
an
n
el
ca
n
h
elp
f
i
n
d
a
s
u
itab
le
lo
ca
l
p
at
ch
f
o
r
air
lig
h
t
-
c
o
lo
u
r
esti
m
ati
o
n
[
5
1
]
.
Fig
u
r
e
2
s
h
o
ws
a
co
m
p
ar
is
o
n
o
f
th
e
h
is
to
g
r
am
b
etwe
en
an
R
GB
im
ag
e
an
d
f
alse
co
lo
u
r
im
ag
es.
T
h
e
h
is
to
g
r
am
s
h
o
ws
th
at
th
e
cu
r
v
e
f
o
r
an
R
GB
im
ag
e
is
w
ith
in
th
e
r
an
g
e
o
f
8
9
an
d
1
2
2
,
wh
i
le
th
e
f
alse
co
lo
u
r
im
ag
e
lies
in
th
e
r
an
g
e
b
etwe
en
2
5
an
d
2
0
0
.
T
h
is
in
d
icate
s
th
at
a
p
ix
el
d
o
es
n
o
t
s
p
an
a
f
u
ll
r
an
g
e
of
R
GB
im
ag
es.
Mo
r
eo
v
e
r
,
th
e
p
ea
k
s
ig
n
al
-
to
n
o
is
e
r
atio
(
PS
NR
)
v
alu
e
f
o
r
th
e
f
alse
co
lo
u
r
im
ag
e
is
s
h
o
wn
to
b
e
s
lig
h
tly
h
ig
h
er
t
h
an
th
at
o
f
th
e
R
GB
im
ag
e,
d
u
e
to
th
e
NI
R
c
h
an
n
el’
s
in
teg
r
atio
n
o
n
to
th
e
i
m
ag
e
[
1
1
4
]
–
[
1
1
7
]
.
T
h
is
en
co
u
r
ag
es
th
e
u
s
e
o
f
a
f
alse
co
lo
u
r
im
ag
e
th
r
o
u
g
h
o
u
t
th
e
s
tu
d
y
an
d
th
e
p
r
esen
ce
o
f
an
NI
R
ch
an
n
el,
wh
ich
m
a
k
es th
e
v
eg
etatio
n
m
o
r
e
v
ib
r
an
t a
n
d
h
elp
s
with
ed
g
e
d
etec
tio
n
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
[1
18]
.
Alth
o
u
g
h
th
e
NI
R
ch
an
n
el
h
e
lp
s
im
p
r
o
v
e
v
eg
etatio
n
an
d
w
ater
b
o
d
y
d
etec
tio
n
,
th
e
im
ag
e
n
ee
d
s
to
u
n
d
e
r
g
o
im
ag
e
en
h
a
n
ce
m
en
ts
,
in
o
r
d
er
to
im
p
r
o
v
e
its
im
ag
e
co
n
tr
ast
an
d
to
im
p
r
o
v
e
its
ex
tr
ac
ted
e
d
g
e
d
etec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
9
9
-
1
5
1
4
1502
(
a)
(
b
)
Fig
u
r
e
2
.
C
o
m
p
a
r
is
o
n
h
is
to
g
r
a
m
b
etwe
en
(
a)
R
GB
im
ag
e
an
d
(
b
)
f
alse c
o
lo
u
r
An
im
ag
e
co
n
tain
s
o
n
e
o
r
m
o
r
e
co
lo
u
r
ch
an
n
els,
wh
ich
d
ef
i
n
es
th
e
p
ix
el
lo
ca
tio
n
.
T
h
e
co
n
v
er
s
io
n
o
f
im
ag
es
is
ac
h
iev
ed
th
r
o
u
g
h
a
co
lo
u
r
m
ap
.
T
h
e
m
o
s
t
co
m
m
o
n
co
lo
u
r
m
ap
is
g
r
ay
s
ca
le,
wh
ich
in
v
o
lv
es
all
s
h
ad
es
o
f
g
r
e
y
f
r
o
m
b
lack
t
o
wh
ite.
T
h
er
e
f
o
r
e,
g
r
ay
s
ca
le
is
p
ar
ticu
lar
l
y
well
s
u
ited
t
o
im
ag
es
with
h
i
g
h
in
ten
s
ity
[
1
1
9
]
–
[
1
2
2
]
.
I
n
ad
d
itio
n
to
u
tili
zin
g
f
alse
co
lo
u
r
,
a
m
ap
ca
n
b
etter
d
is
p
lay
th
e
in
ten
s
ity
in
im
ag
es
[
1
2
3
]
.
T
h
er
e
f
o
r
e,
f
alse
co
lo
u
r
im
a
g
es
ar
e
m
o
s
tly
a
b
le
to
d
elin
ea
te
an
d
i
d
en
tify
f
ea
tu
r
es
f
o
r
a
h
u
m
an
o
b
s
er
v
er
.
A
n
in
ten
s
ity
s
ca
le
k
n
o
wn
as
th
e
g
r
ay
s
ca
le
lev
el,
i
s
in
a
d
ig
ital
im
ag
e
with
an
m
x
n
ar
r
ay
o
f
v
alu
es,
f
o
r
ea
ch
p
ix
el
in
a
s
in
g
le
s
am
p
le,
co
n
tain
in
g
th
e
im
ag
e
in
te
n
s
ity
in
f
o
r
m
atio
n
.
I
n
th
e
8
b
its
p
er
s
am
p
le
p
ix
el,
u
p
to
2
5
6
s
h
a
d
es o
f
g
r
ay
ar
e
u
tili
ze
d
.
T
h
e
co
n
v
er
s
io
n
o
f
an
R
GB
im
ag
e
to
g
r
ay
s
ca
le
is
a
co
m
m
o
n
ap
p
r
o
ac
h
u
s
ed
to
r
etain
in
f
o
r
m
atio
n
r
eg
ar
d
in
g
b
r
ig
h
tn
ess
,
a
n
d
f
o
r
d
is
ca
r
d
in
g
th
e
v
alu
es
o
f
h
u
e
an
d
s
atu
r
atio
n
.
E
ac
h
p
ix
el
is
m
ad
e
u
p
o
f
th
r
ee
co
lo
u
r
s
,
in
cl
u
d
in
g
r
ed
,
g
r
ee
n
an
d
b
lu
e,
wh
ich
a
r
e
u
s
ed
to
d
escr
ib
e
in
te
n
s
ity
.
I
n
th
e
R
GB
co
lo
u
r
m
o
d
el,
a
co
lo
u
r
im
a
g
e
r
ep
r
esen
ts
th
e
in
ten
s
ity
f
u
n
ctio
n
p
r
esen
ted
in
(
1
)
,
I
= (
I
R
, I
G
,
I
B
)
(
1
)
wh
er
e
I
R
r
e
p
r
esen
ts
th
e
in
ten
s
ity
v
alu
e
o
f
th
e
p
ix
el
in
t
h
e
r
e
d
ch
an
n
el,
I
G
r
ep
r
esen
ts
th
e
in
ten
s
ity
v
alu
e
o
f
th
e
p
ix
el
in
th
e
g
r
ee
n
c
h
an
n
el,
an
d
I
B
r
ep
r
esen
ts
th
e
in
ten
s
ity
v
alu
e
o
f
th
e
p
ix
el
in
t
h
e
b
lu
e
ch
a
n
n
el.
T
h
e
in
ten
s
ity
o
f
ea
ch
co
l
o
u
r
ch
an
n
el
is
u
s
u
ally
s
to
r
e
d
th
r
o
u
g
h
th
e
u
s
e
o
f
eig
h
t
b
its
.
T
h
er
ef
o
r
e,
m
u
ltis
p
ec
tr
al
im
ag
e
s
s
to
r
e
m
u
ltip
le
v
alu
es
f
o
r
ea
c
h
p
ix
el,
ca
p
tu
r
ed
th
r
o
u
g
h
th
e
am
o
u
n
t
o
f
lig
h
t
in
d
i
f
f
er
en
t
ch
an
n
els
o
f
th
e
elec
tr
o
m
a
g
n
et
ic
s
p
ec
tr
u
m
.
T
h
e
co
m
m
o
n
m
u
ltis
p
ec
tr
al
im
ag
es
ar
e
R
G
B
,
w
h
ich
co
n
tain
th
r
ee
ch
an
n
els
th
at
c
o
r
r
esp
o
n
d
to
t
h
e
R
,
G
a
n
d
B
r
eg
io
n
s
o
f
t
h
e
s
p
ec
t
r
u
m
[
3
9
]
,
[
6
0
]
,
[
8
4
]
,
[
8
8
]
,
[
9
4
]
.
Ho
wev
e
r
,
th
r
o
u
g
h
o
u
t
t
h
e
s
tu
d
y
,
t
h
e
f
alse
co
lo
u
r
im
a
g
e
is
u
s
ed
,
wh
er
e
th
e
th
r
ee
ch
a
n
n
els
co
r
r
esp
o
n
d
to
th
e
NI
R
,
R
an
d
G
r
eg
io
n
s
.
C
o
n
v
er
tin
g
a
f
alse
co
lo
u
r
im
ag
e
to
a
g
r
a
y
s
ca
le
im
ag
e
in
v
o
l
v
es
m
ap
p
in
g
a
th
r
ee
-
ch
an
n
el
im
ag
e
(
m
=3
)
to
a
s
in
g
le
ch
an
n
el
im
ag
e
(
n
=1
)
.
T
h
er
ef
o
r
e,
a
s
im
p
le
ap
p
r
o
ac
h
is
co
n
s
id
er
ed
,
wh
ich
in
v
o
lv
es a
v
er
ag
in
g
th
e
th
r
ee
ch
a
n
n
el
v
al
u
es,
as p
r
esen
ted
in
(
2
)
:
I
= (
I
NIR
+ I
R
+
IG
)
/ 3
(
2
)
wh
er
e
I
NIR
, I
R
an
d
I
G
ar
e
th
e
N
I
R
,
r
ed
an
d
g
r
ee
n
ch
an
n
els o
f
th
e
in
p
u
t im
a
g
e,
r
esp
ec
tiv
ely
.
Ho
wev
er
,
th
e
r
esu
ltin
g
im
a
g
e
is
n
o
t
eq
u
ally
s
en
s
itiv
e
to
all
f
r
eq
u
e
n
cies.
T
h
er
ef
o
r
e,
th
e
ch
an
n
el
av
er
ag
e
is
test
ed
b
y
in
c
r
ea
s
in
g
th
e
weig
h
t
o
f
th
e
NI
R
ch
a
n
n
el.
A
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
t
h
as
b
ee
n
p
r
o
p
o
s
ed
b
y
m
o
d
if
y
in
g
th
e
weig
h
t
o
f
th
e
NI
R
ch
an
n
el.
As
a
r
esu
lt,
th
e
g
r
ay
lev
els
f
o
r
ea
ch
ch
a
n
n
el
ar
e
ca
lcu
lated
an
d
im
p
lem
en
ted
,
th
r
o
u
g
h
u
s
in
g
(
3
)
,
I
’
= (
(
r
*
I
NIR
)
+ I
R
+ I
G
)
/t
(
3
)
wh
er
e
‘
r
’
is
th
e
n
u
m
b
er
o
f
ad
d
in
g
th
e
NI
R
ch
an
n
el,
‘
NI
R
’
is
n
ea
r
-
in
f
r
ar
ed
,
‘
G’
is
g
r
ee
n
,
‘
R
’
is
r
ed
,
an
d
‘
t’
is
a
ch
an
n
el’
s
to
tal
n
u
m
b
er
.
T
h
e
g
r
a
y
lev
els
f
o
r
ea
c
h
co
lo
u
r
ch
an
n
el
ar
e
ca
lcu
lated
an
d
im
p
lem
en
ted
.
I
n
r
e
g
ar
d
s
to
f
a
ls
e
co
lo
u
r
v
alu
es,
NI
R
is
1
0
2
,
R
is
9
0
,
a
n
d
G
is
7
5
.
T
h
en
th
e
im
ag
e
is
test
ed
to
co
n
v
er
t
b
ac
k
to
th
e
f
alse
co
lo
u
r
,
th
r
o
u
g
h
u
s
ag
e
o
f
a
n
o
n
-
r
e
p
licatin
g
tr
a
n
s
f
o
r
m
atio
n
.
T
h
is
s
tep
en
s
u
r
e
s
th
at
th
e
ch
an
g
es
o
f
th
e
ad
d
itio
n
al
NI
R
ch
a
n
n
e
l
s
er
v
e
to
m
ak
e
th
e
im
ag
e
d
a
r
k
e
r
o
r
b
r
ig
h
ter
,
an
d
also
t
o
en
s
u
r
e
th
at
th
e
v
alu
es a
r
e
s
till
with
in
th
e
r
an
g
e
o
f
8
-
b
it
v
alu
es.
T
h
er
ef
o
r
e,
th
e
th
r
ee
s
ep
ar
ate
co
lo
u
r
ch
an
n
els
ar
e
s
h
o
wn
th
r
o
u
g
h
s
ettin
g
s
,
wh
ile
th
e
o
th
er
co
lo
u
r
ch
an
n
el
is
ze
r
o
.
Fo
r
ex
am
p
le,
th
e
NI
R
ch
an
n
el
is
v
is
u
alize
d
th
r
o
u
g
h
(
4
)
.
I
NIR
= I
NIR
;
I
R
= 0
;
I
G
=0
;
(
4
)
T
h
er
ef
o
r
e,
th
e
g
r
ay
s
ca
le
im
ag
e
is
f
o
r
m
ed
th
r
o
u
g
h
u
tili
s
in
g
v
alu
es f
r
o
m
th
e
N
I
R
ch
an
n
el
as
(
5
)
.
I’
NIR
= I
NIR
;
I
’
R
= I
NIR
;
I
’
G
= I
N
IR
;
(
5
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
teg
r
a
ted
N
I
R
-
HE
b
a
s
ed
S
P
OT
-
5
ima
g
e
en
h
a
n
ce
men
t m
et
h
o
d
fo
r
fea
tu
r
es
…
(
F
a
r
iz
u
w
a
n
a
A
kma
Zu
lkifle
)
1503
Fro
m
th
e
r
esu
lts
s
h
o
wn
ab
o
v
e,
th
e
av
er
ag
e
ap
p
r
o
ac
h
ten
d
s
to
in
cr
ea
s
e
th
e
co
n
tr
ast.
T
h
e
f
o
r
m
u
la
m
an
i
p
u
lates
th
e
NI
R
ch
an
n
el
weig
h
t,
w
h
er
e
t
h
e
ch
a
n
n
el
r
ef
lects
m
o
r
e
t
h
an
o
th
er
ch
an
n
els,
g
iv
en
th
at
t
h
e
h
u
m
an
v
is
u
al
s
y
s
tem
is
m
o
r
e
s
en
s
itiv
e
to
th
e
NI
R
ch
an
n
el
th
an
to
th
e
o
th
e
r
ch
an
n
els.
T
h
e
ad
v
an
tag
es
ar
e
th
at
th
e
d
iv
is
io
n
b
y
f
o
u
r
im
p
lem
en
ts
,
d
u
e
to
an
av
er
ag
e
o
f
th
r
ee
ch
an
n
els
an
d
th
e
ad
d
itio
n
o
f
o
n
e
ch
an
n
el
weig
h
t
,
th
r
o
u
g
h
m
u
ltip
les
o
f
two
,
b
y
th
e
weig
h
t
o
f
th
e
NI
R
ch
an
n
el.
T
h
er
ef
o
r
e
,
it
m
ay
in
cr
ea
s
e
th
e
NI
R
ch
an
n
el’
s
weig
h
t.
Ho
wev
er
,
if
th
e
a
v
er
ag
e
u
s
ed
is
m
o
r
e
th
an
two
c
h
an
n
els
o
f
th
e
NI
R
c
h
an
n
el,
th
en
t
h
e
im
ag
es
will
s
h
o
w
g
r
ea
ter
co
n
tr
ast,
an
d
will
ca
u
s
e
im
ag
e
in
f
o
r
m
atio
n
lo
s
s
an
d
m
ix
ed
p
ix
els.
As
a
r
esu
lt,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
s
u
itab
le
f
o
r
a
l
o
w
co
n
tr
ast
im
ag
e
o
f
SP
OT
-
5
,
wh
er
eb
y
m
u
ltip
ly
in
g
b
y
two
in
to
th
e
weig
h
t
o
f
NI
R
,
will
m
ak
e
th
e
ch
an
n
el
r
ef
lect
th
e
v
eg
etatio
n
in
th
e
ar
ea
o
f
T
an
ju
n
g
Piai.
I
n
th
is
ca
s
e,
th
e
p
lan
ts
r
ef
lect
NI
R
an
d
g
r
ee
n
lig
h
t,
a
n
d
ab
s
o
r
b
r
e
d
.
T
h
er
ef
o
r
e,
th
e
ch
an
n
el
r
ef
le
cts
m
o
r
e
NI
R
th
an
g
r
ee
n
,
wh
er
eb
y
p
lan
t
-
c
o
v
er
e
d
lan
d
ap
p
ea
r
s
to
b
e
d
ee
p
r
e
d
[
3
0
]
.
2
.
4
.
I
ma
g
e
cla
s
s
if
ica
t
io
n
T
h
e
im
ag
e
class
if
icatio
n
p
r
o
ce
s
s
m
u
s
t b
e
p
er
f
o
r
m
ed
t
o
id
en
ti
f
y
an
d
c
o
m
p
ar
e
t
h
e
ac
cu
r
ac
y
b
y
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
[
3
3
]
,
[
124]
–
[
1
5
4
]
.
I
n
th
is
s
tu
d
y
,
a
f
ew
p
o
ly
g
o
n
s
am
p
les
wer
e
cr
ea
ted
f
o
r
tr
ain
in
g
class
es.
T
h
ese
co
m
p
r
is
ed
o
f
f
o
u
r
class
es,
n
am
ely
:
v
eg
etat
io
n
,
d
ev
elo
p
e
d
a
r
ea
,
s
ea
,
an
d
s
o
il.
T
h
ese
f
o
u
r
f
ea
tu
r
es
ar
e
s
elec
ted
n
o
t
o
n
ly
b
ec
au
s
e
th
ey
ar
e
u
s
ef
u
l
f
o
r
s
h
o
r
elin
e
e
d
g
e
d
etec
tio
n
,
b
u
t
als
o
b
ec
a
u
s
e
th
ese
a
r
e
ess
en
tial
f
o
r
m
o
s
t
u
r
b
a
n
p
lan
n
in
g
ap
p
licatio
n
s
wh
ich
in
clu
d
e
d
ev
elo
p
m
en
t
o
f
ar
ea
s
,
s
h
o
r
e
lin
e
an
d
v
eg
etatio
n
ex
tr
ac
tio
n
.
T
h
r
o
u
g
h
o
u
t
th
e
SV
M
m
eth
o
d
,
th
e
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
[
1
2
6
]
,
[
1
3
0
]
,
[
1
4
6
]
,
[
1
5
4
]
f
o
r
k
er
n
el
ty
p
e
an
d
th
e
th
r
esh
o
ld
v
al
u
e
o
f
0
.
7
0
ar
e
u
s
ed
f
o
r
th
e
class
if
icatio
n
p
r
o
ce
s
s
.
Sev
er
al
tr
ial
-
an
d
-
er
r
o
r
r
u
n
v
alu
es
u
s
in
g
a
th
r
esh
o
ld
v
alu
e
in
b
et
wee
n
th
e
r
an
g
e
o
f
0
.
1
0
an
d
0
.
7
0
ar
e
ch
o
s
en
in
th
e
in
itial
e
x
p
er
im
en
ts
.
T
h
ese
p
ar
am
eter
s
o
b
tain
e
d
a
h
ig
h
er
a
cc
u
r
ac
y
p
e
r
f
o
r
m
an
ce
lev
el
wit
h
m
o
r
e
t
h
an
7
8
%
ac
cu
r
ac
y
f
o
r
all
d
atasets
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Ana
ly
s
is
o
f
t
he
i
m
a
g
e
e
nh
a
ncem
ent
m
et
ho
d
T
h
e
in
ten
s
ity
of
th
e
co
n
tr
as
t
en
h
an
ce
m
en
t
m
eth
o
d
h
as
b
ee
n
o
b
s
er
v
ed
th
r
o
u
g
h
th
e
en
h
an
ce
d
im
ag
es
[
1
5
5
]
–
[
1
6
5
]
.
B
y
u
s
in
g
NI
R
,
th
e
r
ed
-
co
lo
r
ed
p
ix
el
s
ar
e
p
r
o
d
u
ce
d
,
an
d
it
is
m
o
r
e
o
b
v
io
u
s
wh
en
r
ep
r
esen
tin
g
th
e
h
ea
lt
h
y
v
eg
et
atio
n
ar
ea
.
NI
R
h
elp
s
p
en
etr
at
e
f
u
r
th
er
th
a
n
th
e
v
is
ib
le
ch
an
n
el,
d
u
e
to
its
lo
n
g
wav
elen
g
th
.
I
n
t
h
is
ca
s
e,
a
d
ar
k
er
im
ag
e
is
ass
u
m
ed
to
b
e
u
n
ab
le
to
r
ef
lect
an
y
s
o
lar
en
e
r
g
y
,
wh
ich
in
d
icate
s
th
e
h
is
to
g
r
am
o
f
a
n
ea
r
ly
ze
r
o
d
ig
ital
n
u
m
b
er
o
r
b
r
ig
h
tn
ess
v
alu
e.
I
f
th
e
im
a
g
e
p
r
esen
ts
s
u
r
f
ac
e
r
e
f
lecta
n
ce
,
th
en
th
e
h
is
to
g
r
am
o
f
th
e
v
i
s
ib
le
ch
an
n
el
s
h
o
ws
a
s
h
ar
p
in
cr
ea
s
e
in
o
cc
u
r
r
en
ce
f
r
eq
u
en
cy
at
th
e
lo
wer
-
co
n
tr
ast lev
el.
T
h
er
e
f
o
r
e,
t
h
e
p
ix
el
in
ten
s
ity
h
is
to
g
r
am
’
s
lef
t
war
d
s
s
k
ew
in
d
icate
s
th
at
th
e
im
ag
e
is
co
n
s
id
er
ed
to
h
av
e
a
d
ar
k
lev
el,
with
a
lo
w
b
r
ig
h
tn
ess
lev
el;
an
d
if
th
e
p
ix
el
in
ten
s
ity
h
is
to
g
r
am
is
s
k
ewe
d
to
th
e
r
ig
h
t,
th
en
th
e
im
ag
e
is
co
n
s
id
er
e
d
t
o
h
av
e
a
h
ig
h
er
b
r
ig
h
tn
ess
lev
el.
Mo
r
eo
v
er
,
f
o
r
th
e
c
o
n
tr
as
t
lev
el,
if
th
e
p
ix
el
in
ten
s
ity
h
is
to
g
r
am
f
o
cu
s
es
o
n
th
e
ce
n
ter
o
f
th
e
h
is
to
g
r
am
,
th
en
th
e
im
ag
e
will
h
av
e
lo
wer
co
n
tr
ast.
On
th
e
o
th
er
h
an
d
,
if
th
e
p
ix
el
in
ten
s
ity
h
is
to
g
r
am
is
d
is
tr
ib
u
ted
th
r
o
u
g
h
o
u
t
th
e
h
is
to
g
r
am
r
an
g
e,
th
e
im
ag
e
will
h
av
e
a
h
ig
h
er
co
n
tr
ast
lev
el.
T
h
is
i
n
d
icato
r
was
u
s
ed
t
o
ass
ess
t
h
e
im
ag
e
en
h
an
ce
m
en
t
m
eth
o
d
s
,
u
s
in
g
a
v
a
r
iety
o
f
illu
m
in
atio
n
s
f
o
r
o
p
tim
al
p
er
f
o
r
m
an
ce
[
2
8
]
,
[
8
5
]
,
[
8
6
]
,
[
1
0
5
]
,
[
1
4
0
]
,
[
1
6
6
]
.
T
h
e
H
E
m
e
t
h
o
d
w
a
s
u
s
e
d
t
o
a
p
p
l
y
i
m
a
g
e
e
n
h
a
n
c
e
m
e
n
t
i
n
d
i
v
i
d
u
a
l
l
y
t
o
t
h
e
g
r
a
y
-
l
e
v
e
l
i
m
a
g
e
s
[
1
6
7
]
–
[
1
7
6
]
.
T
h
e
NI
R
ch
a
n
n
el
was
in
teg
r
ated
in
to
th
e
f
alse
co
lo
r
c
o
m
p
o
s
ite,
co
m
b
in
in
g
th
e
r
ed
an
d
g
r
ee
n
ch
an
n
els,
in
s
tead
o
f
th
e
r
ed
,
b
lu
e
an
d
g
r
ee
n
c
h
an
n
els.
T
h
e
f
u
s
io
n
cr
iter
ia
wer
e
b
ased
o
n
th
e
o
b
s
e
r
v
atio
n
o
f
th
e
NI
R
ch
an
n
el
im
ag
es,
wh
ich
h
a
v
e
h
ig
h
er
co
n
tr
ast.
T
h
er
ef
o
r
e,
th
e
NI
R
ch
an
n
el
was
u
s
ed
to
r
ef
in
e
th
e
im
ag
e’
s
co
n
tr
ast.
T
h
e
HE
m
eth
o
d
e
n
h
an
ce
s
th
e
im
a
g
e
b
y
d
is
tr
ib
u
ti
n
g
th
e
im
ag
e
b
r
ig
h
tn
ess
lev
el
s
eq
u
ally
ac
r
o
s
s
th
e
b
r
ig
h
tn
ess
s
ca
le
[
1
]
,
[
1
1
]
,
[
1
5
]
,
[
2
1
]
,
[
4
4
]
,
[
5
3
]
,
[
5
4
]
,
[
7
2
]
,
[
9
4
]
,
[
1
1
9
]
,
[
1
3
6
]
,
[
1
4
0
]
,
[
1
4
5
]
,
[
1
5
0
]
,
[
1
5
9
]
,
[
1
6
8
]
,
[
1
6
9
]
,
[
1
7
2
]
,
[
1
7
5
]
.
F
u
r
th
er
m
o
r
e,
th
e
i
n
ten
s
ity
o
f
th
e
co
n
tr
ast
en
h
a
n
ce
m
en
t
m
eth
o
d
is
m
ea
s
u
r
e
d
th
r
o
u
g
h
th
e
r
o
o
t
m
ea
n
s
q
u
ar
e
(
R
MS)
,
wh
er
e
th
e
h
ig
h
er
th
e
R
MS
v
alu
e,
th
e
b
etter
th
e
c
o
n
tr
ast
im
ag
e
[
2
2
]
,
[
3
5
]
,
[
4
8
]
,
[
1
7
8
]
–
[
1
8
1
]
.
As
d
ep
icted
in
T
ab
le
1
,
th
e
im
a
g
e
en
h
an
ce
m
en
t
m
et
h
o
d
s
f
o
r
SP
OT
-
5
im
ag
es
h
av
e
b
ee
n
c
o
m
p
ar
e
d
a
n
d
r
an
to
p
r
o
d
u
ce
th
e
b
est
ap
p
r
o
ac
h
.
T
h
e
r
esu
lts
o
f
th
e
h
is
to
g
r
am
o
f
c
o
lo
u
r
p
ix
el
in
ten
s
ity
d
is
tr
ib
u
tio
n
wer
e
an
aly
ze
d
.
At
th
is
p
o
in
t
th
e
f
o
u
r
m
eth
o
d
s
p
r
o
d
u
ce
d
th
r
ee
co
lo
u
r
ed
p
ix
els,
in
clu
d
in
g
h
ea
lth
y
v
eg
etatio
n
ar
ea
s
in
d
icate
d
b
y
r
ed
p
ix
els,
wate
r
ar
ea
s
in
d
icate
d
b
y
b
lu
e
p
ix
els,
a
n
d
n
o
n
-
v
e
g
etate
d
/d
ev
elo
p
e
d
ar
ea
s
in
d
icate
d
b
y
wh
ite
p
ix
el
s
.
T
h
e
R
MS
v
alu
es
f
o
r
th
e
in
it
ial
im
ag
e
h
a
v
e
s
h
o
w
n
th
e
lo
west
v
alu
es,
wh
en
c
o
m
p
a
r
ed
to
o
t
h
er
m
eth
o
d
s
.
Fo
r
th
e
d
ar
k
c
h
an
n
el
p
r
io
r
(
DC
P)
m
eth
o
d
,
th
e
R
MS
v
alu
e
o
f
s
ce
n
e
th
r
ee
was
0
.
2
4
4
1
.
T
h
er
ef
o
r
e,
th
e
im
ag
e
was
n
o
t
f
u
lly
e
n
h
an
ce
d
to
its
o
p
tim
u
m
lev
el,
a
f
ter
w
h
ich
it
tu
r
n
e
d
d
ar
k
an
d
th
e
v
e
g
etatio
n
was
h
ar
d
er
to
id
en
tify
.
T
h
e
HE
m
eth
o
d
p
e
r
f
o
r
m
e
d
an
im
a
g
e
co
n
t
r
ast
en
h
an
ce
m
e
n
t
in
d
iv
id
u
ally
to
th
e
g
r
ay
-
le
v
el
im
ag
e.
T
h
e
HE
m
eth
o
d
r
em
o
v
ed
th
e
s
u
r
f
ac
e
r
ef
lecta
n
ce
in
a
n
im
a
g
e
an
d
en
h
an
ce
d
th
e
im
ag
e
c
o
n
tr
ast
o
f
th
e
g
r
ay
im
ag
e.
T
h
er
ef
o
r
e,
t
h
e
HE
m
eth
o
d
p
r
o
d
u
ce
s
b
etter
co
n
tr
a
s
t,
wh
en
c
o
m
p
ar
e
d
to
th
e
D
C
P
m
eth
o
d
,
w
h
ich
p
r
o
d
u
ce
s
an
im
ag
e
with
v
er
y
h
ig
h
b
r
i
g
h
tn
ess
,
f
o
r
all
s
p
ec
t
r
al
ch
an
n
els.
T
h
e
HE
m
et
h
o
d
p
r
o
d
u
ce
d
an
R
MS
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
9
9
-
1
5
1
4
1504
v
a
l
u
e
w
h
i
c
h
i
s
n
e
a
r
l
y
e
q
u
a
l
t
o
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
,
s
p
e
c
i
f
ic
a
l
l
y
0
.
4
1
9
2
f
o
r
s
c
e
n
e
o
n
e
,
0
.
4
4
7
8
f
o
r
s
c
e
n
e
t
w
o
,
a
n
d
0
.
4
6
1
2
f
o
r
s
c
e
n
e
t
h
r
e
e
.
H
o
w
e
v
e
r
,
t
h
e
d
e
c
o
r
r
e
l
a
t
i
o
n
s
t
r
e
tch
(
D
E
C
OR
R
)
r
e
s
u
l
ts
a
r
e
m
o
r
e
s
u
i
t
a
b
le
f
o
r
d
e
n
s
i
t
y
-
b
a
s
e
d
v
e
g
e
t
a
ti
o
n
a
n
a
l
y
s
is
,
f
r
o
m
w
h
i
c
h
i
t
is
f
i
t
a
n
d
a
b
l
e
t
o
d
i
s
t
i
n
g
u
i
s
h
m
o
r
e
t
h
a
n
o
n
e
f
e
a
t
u
r
e
[
1
8
2
]
-
[
1
9
4
]
.
On
th
e
o
th
e
r
h
an
d
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
en
h
a
n
ce
d
th
e
im
ag
e
b
y
d
is
tr
ib
u
tin
g
its
b
r
ig
h
tn
ess
lev
el
s
to
g
eth
er
with
th
e
wh
o
le
b
r
ig
h
tn
ess
s
ca
le
[
1
1
8
]
,
[
1
9
3
]
.
T
h
er
ef
o
r
e,
th
e
i
m
ag
e
h
as
b
ee
n
im
p
r
o
v
ed
to
its
o
p
tim
u
m
lev
el,
with
o
u
t
lo
s
in
g
d
etails
o
r
ca
u
s
in
g
s
h
if
ts
in
co
lo
u
r
.
T
h
e
R
MS
v
alu
e
f
o
r
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
h
o
w
s
th
e
h
ig
h
est
v
alu
e,
wh
en
co
m
p
ar
ed
t
o
o
th
e
r
s
.
Fro
m
th
is
r
esu
lt,
it
ca
n
b
e
co
n
clu
d
ed
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
v
id
es
a
h
ig
h
er
im
ag
e
q
u
ality
af
te
r
im
ag
e
e
n
h
an
ce
m
en
t,
an
d
th
e
im
a
g
e
is
s
u
r
f
ac
e
r
ef
lecta
n
ce
-
f
r
ee
.
Ad
d
itio
n
ally
,
th
e
p
ea
k
s
ig
n
al
-
to
-
n
o
is
e
r
atio
(
PS
NR
)
is
co
m
m
o
n
ly
u
s
ed
as
a
m
ea
s
u
r
e
f
o
r
im
ag
e
q
u
ality
r
ec
o
n
s
tr
u
ctio
n
.
PS
NR
is
th
e
r
atio
b
etwe
en
m
ax
im
u
m
p
o
s
s
ib
le
p
o
wer
an
d
co
r
r
u
p
tin
g
n
o
is
e
w
h
ich
im
p
ac
ts
an
im
ag
e’
s
r
ep
r
esen
tatio
n
.
On
th
e
co
n
tr
ar
y
,
th
e
m
e
an
s
q
u
ar
e
er
r
o
r
(
MSE
)
r
ep
r
es
en
ts
th
e
cu
m
u
lativ
e
s
q
u
ar
ed
e
r
r
o
r
b
etwe
en
th
e
en
h
an
ce
d
im
a
g
e
a
n
d
t
h
e
in
itial
im
ag
e.
As
a
r
esu
lt,
PS
NR
an
d
MSE
ar
e
in
ter
r
elate
d
.
W
h
er
e
th
er
e
is
h
ig
h
er
PS
NR
an
d
lo
wer
MSE
,
a
b
etter
co
n
tr
ast
ca
n
b
e
ac
h
iev
ed
[
9
8
]
,
[
1
7
1
]
,
[
1
9
5
]
–
[
1
9
9
]
.
T
ab
le
2
s
h
o
ws
a
co
m
p
ar
is
o
n
o
f
PS
NR
an
d
MSE
r
esu
lts
,
w
h
en
u
s
in
g
th
e
d
if
f
er
e
n
t
m
eth
o
d
s
.
As
s
ee
n
in
th
e
T
ab
le
2
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
th
e
h
ig
h
est
PS
NR
wh
e
n
co
m
p
ar
ed
to
th
e
o
th
e
r
m
et
h
o
d
s
.
T
h
e
u
s
e
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
v
id
es
a
g
r
ea
ter
co
n
t
r
ast
lev
el,
f
o
llo
win
g
th
e
p
r
o
ce
s
s
o
f
im
p
r
o
v
in
g
th
e
lo
w
-
co
n
tr
ast
im
ag
es.
T
h
er
ef
o
r
e,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
im
p
r
o
v
es a
n
im
a
g
e
’
s
co
n
tr
ast,
wh
en
co
m
p
ar
e
d
to
o
th
er
m
eth
o
d
s
.
T
ab
le
1
.
Ov
e
r
all
o
b
s
er
v
atio
n
o
f
R
MS
f
o
r
Scen
e
1
,
Scen
e
2
,
S
ce
n
e
3
,
Scen
e
4
,
an
d
Scen
e
5
T
ab
le
2
.
C
o
m
p
a
r
is
o
n
o
f
PS
NR
an
d
MSE
r
esu
lt u
s
in
g
a
d
if
f
er
en
t m
eth
o
d
D
C
P
HE
D
EC
O
R
R
P
r
o
p
o
se
d
M
e
t
h
o
d
P
S
N
R
S
c
e
n
e
1
6
.
6
1
4
3
1
2
.
6
2
9
7
1
3
.
8
1
4
7
1
8
.
1
7
4
5
S
c
e
n
e
2
1
0
.
1
9
7
5
1
3
.
8
1
4
7
1
4
.
6
6
6
2
1
7
.
7
9
3
8
S
c
e
n
e
3
1
0
.
4
3
4
7
1
4
.
8
5
8
3
1
5
.
1
1
5
8
1
8
.
0
8
9
1
S
c
e
n
e
4
1
1
.
3
9
1
7
1
4
.
6
5
6
8
1
3
.
3
5
0
9
1
7
.
1
5
3
8
S
c
e
n
e
5
1
1
.
3
2
8
4
1
3
.
8
1
4
7
1
6
.
8
1
9
8
1
8
.
2
3
3
6
M
S
E
S
c
e
n
e
1
1
.
4
1
7
9
3
.
5
4
9
1
2
.
7
0
1
6
1
.
0
0
4
5
S
c
e
n
e
2
6
.
2
1
3
4
2
.
7
0
1
6
2
.
0
0
2
2
1
.
0
8
0
7
S
c
e
n
e
3
5
.
8
8
3
2
2
.
1
2
4
5
2
.
2
2
0
5
1
.
0
0
9
6
S
c
e
n
e
4
4
.
7
1
9
7
2
.
2
2
5
4
3
.
0
0
6
0
1
.
2
5
2
3
S
c
e
n
e
5
4
.
7
8
8
9
2
.
7
0
1
6
1
.
3
5
2
4
1
.
2
4
3
2
3
.
2
.
Ana
ly
s
is
o
f
f
e
a
t
ure
s
ig
na
t
ures
Featu
r
e
ex
tr
ac
tio
n
allo
ws
f
o
r
a
more
-
ac
cu
r
ate
d
etec
tio
n
o
f
f
ea
tu
r
es,
as
a
r
esu
lt
o
f
th
e
im
ag
e’
s
en
h
an
ce
m
e
n
ts
[
1
5
]
,
[
1
6
]
,
[
3
9
]
,
[
8
9
]
,
[
1
4
3
]
–
[
1
4
5
]
,
[
1
4
8
]
.
T
h
e
s
ig
n
atu
r
e
o
f
f
ea
tu
r
e
class
es
co
u
ld
b
e
d
is
tin
g
u
is
h
ed
f
r
o
m
co
m
p
lex
s
u
r
f
ac
e
tex
tu
r
es.
Star
tin
g
with
im
a
g
e
p
r
e
-
p
r
o
ce
s
s
in
g
th
r
o
u
g
h
im
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
teg
r
a
ted
N
I
R
-
HE
b
a
s
ed
S
P
OT
-
5
ima
g
e
en
h
a
n
ce
men
t m
et
h
o
d
fo
r
fea
tu
r
es
…
(
F
a
r
iz
u
w
a
n
a
A
kma
Zu
lkifle
)
1505
en
h
an
ce
m
e
n
t,
a
co
m
p
r
eh
en
s
i
v
e
m
eth
o
d
o
f
f
ea
tu
r
es
ex
t
r
a
ctio
n
h
as
b
ee
n
im
p
lem
en
ted
,
cr
ea
tin
g
a
u
s
ef
u
l
r
ep
r
esen
tatio
n
o
f
t
h
e
d
e
v
elo
p
e
d
ar
ea
s
,
v
eg
etatio
n
,
s
ea
,
an
d
n
atu
r
al
g
r
o
u
n
d
.
I
m
a
g
e
en
h
a
n
ce
m
en
t
is
ap
p
lied
to
th
e
in
itial
im
ag
e,
in
o
r
d
er
to
p
r
o
d
u
ce
an
en
h
an
ce
d
im
ag
e
f
o
r
p
u
r
p
o
s
es
o
f
b
etter
clar
ity
.
C
an
n
y
ed
g
e
d
etec
tio
n
[
7
]
,
[
1
1
7
]
,
[
1
6
0
]
wa
s
u
s
ed
to
d
etec
t
s
h
o
r
elin
es.
N
eith
er
th
e
So
b
el,
Pre
witt
n
o
r
L
o
g
m
eth
o
d
s
wer
e
ab
le
to
d
etec
t
s
h
o
r
e
ed
g
es.
Acc
o
r
d
in
g
t
o
th
e
r
esu
lts
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
d
e
m
o
n
s
tr
ated
th
e
b
est
ed
g
e
d
etec
tio
n
.
Min
im
u
m
a
n
d
m
ax
i
m
u
m
th
r
e
s
h
o
ld
s
wer
e
test
ed
.
Ho
wev
er
,
th
e
th
r
esh
o
ld
at
0
.
0
7
p
r
o
d
u
ce
s
t
h
e
b
est
r
esu
lts
.
I
n
DC
P,
th
e
r
esu
lt
s
h
o
wed
th
e
lo
west
d
etec
tio
n
w
h
en
co
m
p
ar
ed
to
o
th
e
r
m
eth
o
d
s
.
I
n
Scen
e
2
,
th
e
ed
g
e
co
u
ld
n
o
t
b
e
d
etec
ted
d
u
e
to
t
h
e
im
ag
e
’
s
lo
w
co
n
tr
ast.
Fo
r
HE
,
th
e
e
d
g
e
d
etec
t
io
n
in
Scen
e
2
s
h
o
we
d
th
at
th
e
e
d
g
e
c
o
u
ld
n
o
t
b
e
d
etec
ted
d
u
e
to
t
h
e
im
a
g
e’
s
b
r
ig
h
tn
ess
.
T
h
e
im
ag
e
co
n
s
is
ted
o
f
m
is
class
if
ied
p
ix
els.
Ho
wev
er
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
h
o
wed
t
h
e
b
est
s
h
o
r
elin
e
ed
g
e
d
etec
tio
n
.
All
th
e
e
d
g
es
wer
e
d
etec
ted
,
an
d
alm
o
s
t
all
s
u
r
f
ac
e
r
ef
lecta
n
ce
was
r
em
o
v
ed
.
An
im
ag
e’
s
lev
el
o
f
co
n
tr
ast
af
f
ec
ts
th
e
s
h
o
r
elin
e
d
etec
tio
n
r
esu
lts
.
B
y
u
s
in
g
th
e
C
an
n
y
ed
g
e
d
etec
to
r
as
th
e
ed
g
e
d
e
tecto
r
f
o
r
s
h
o
r
elin
es
in
th
e
s
u
r
f
ac
e
r
ef
lecta
n
ce
im
ag
es,
a
r
o
b
u
s
t a
n
d
v
e
r
y
-
h
ig
h
en
h
a
n
ce
m
en
t le
v
el
was a
ch
i
ev
ed
.
T
h
e
im
p
r
o
v
em
en
t
o
f
o
v
er
all
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
p
r
o
v
id
ed
a
co
r
r
ec
te
d
in
p
u
t
im
a
g
e
an
d
p
r
o
d
u
ce
d
b
etter
f
ea
tu
r
e
ex
tr
ac
tio
n
,
wh
en
co
m
p
ar
ed
t
o
th
e
in
itial im
ag
e.
T
h
e
av
er
ag
e
ac
c
u
r
ac
y
o
f
th
e
i
n
itial im
ag
e
f
o
r
all
d
atasets
wa
s
7
6
.
3
9
%,
p
r
o
d
u
ci
n
g
a
lo
w
-
q
u
ality
co
n
t
r
ast,
d
u
e
to
th
e
p
r
esen
ce
o
f
s
u
r
f
ac
e
r
ef
lecta
n
ce
.
T
h
e
DC
P
m
eth
o
d
f
o
r
all
d
atasets
s
h
o
we
d
th
at
th
e
en
h
an
ce
d
im
ag
es
p
r
o
d
u
ce
d
a
lo
w
q
u
ality
o
f
co
n
tr
a
s
t
with
an
ac
cu
r
ac
y
th
at
was
ab
o
u
t
8
9
.
7
8
%
an
d
K
ap
p
a
v
alu
e
was
0
.
8
6
as
d
ep
ict
ed
in
T
ab
le
3
.
As
ex
p
lain
e
d
a
b
o
v
e,
th
e
e
n
h
an
ce
d
im
ag
e
r
esu
lts
o
f
th
e
HE
m
eth
o
d
f
o
r
all
d
atasets
,
h
av
e
p
r
o
d
u
ce
m
o
r
e
in
ten
s
ity
v
alu
es
wh
i
ch
ac
h
iev
ed
h
i
g
h
er
v
alu
es
f
o
r
all
d
atasets
wh
en
c
o
m
p
ar
ed
with
th
e
DC
P
m
eth
o
d
.
T
h
e
a
v
er
ag
e
ac
c
u
r
ac
y
f
o
r
a
ll
d
atasets
is
m
o
r
e
th
an
8
0
%,
wh
ile
th
e
Ka
p
p
a
v
al
u
e
is
m
o
r
e
t
h
an
0
.
8
3
.
Fo
r
t
h
e
DE
C
OR
R
,
th
e
en
h
an
ce
d
im
ag
e
p
r
o
d
u
ce
d
a
n
8
7
.
9
1
%
av
e
r
ag
e
ac
cu
r
ac
y
f
o
r
all
d
atasets
,
wh
ile
th
e
m
ea
n
o
f
th
e
Kap
p
a
v
alu
e
is
0
.
8
2
.
T
h
e
ac
cu
r
ac
y
an
d
Kap
p
a
v
alu
e
ac
h
iev
ed
a
h
ig
h
er
v
alu
e
f
o
r
all
d
ata
s
ets,
wh
en
co
m
p
a
r
ed
with
t
h
e
o
th
e
r
m
eth
o
d
s
.
T
h
is
r
esu
lt
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
m
eth
o
d
p
r
o
d
u
ce
d
b
etter
r
esu
lts
wh
en
class
if
ied
with
th
e
f
o
u
r
class
f
ea
tu
r
es.
T
h
ese
in
clu
d
ed
v
eg
etatio
n
ar
ea
s
,
d
e
v
elo
p
ed
ar
ea
s
,
n
atu
r
al
g
r
o
u
n
d
an
d
s
o
il.
T
h
e
a
v
er
ag
e
ac
cu
r
a
cy
f
o
r
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
was f
o
u
n
d
t
o
b
e
m
o
r
e
th
an
8
5
%,
wh
ile
th
e
av
er
a
g
e
o
f
Kap
p
a
v
al
u
e
was 0
.
8
8
.
T
ab
le
3
.
Per
f
o
r
m
an
ce
ev
alu
ati
o
n
A
c
c
u
r
a
c
y
(
%)
K
a
p
p
a
A
c
c
u
r
a
c
y
(
%)
K
a
p
p
a
S
c
e
n
e
1
I
n
i
t
i
a
l
I
mag
e
8
2
.
0
9
0
.
7
3
S
c
e
n
e
4
I
n
i
t
i
a
l
I
mag
e
8
0
.
4
0
.
7
1
D
C
P
8
9
.
7
8
0
.
8
6
D
C
P
8
3
.
1
4
0
.
8
HE
9
1
.
0
6
0
.
8
8
HE
8
8
.
9
2
0
.
8
4
D
EC
O
R
R
9
1
.
9
6
0
.
8
9
D
EC
O
R
R
9
2
.
1
2
0
.
8
8
P
r
o
p
o
se
d
M
e
t
h
o
d
9
2
.
7
5
0
.
9
P
r
o
p
o
se
d
M
e
t
h
o
d
9
4
.
2
6
0
.
9
S
c
e
n
e
2
I
n
i
t
i
a
l
I
mag
e
6
8
.
5
8
0
.
5
5
S
c
e
n
e
5
I
n
i
t
i
a
l
I
mag
e
7
3
.
5
5
0
.
6
9
D
C
P
8
2
.
5
5
0
.
7
6
D
C
P
8
6
.
2
4
0
.
8
2
HE
7
9
.
0
6
0
.
7
1
HE
8
7
.
4
6
0
.
8
3
D
EC
O
R
R
8
4
.
0
9
0
.
7
8
D
EC
O
R
R
8
9
.
6
7
0
.
8
5
P
r
o
p
o
se
d
M
e
t
h
o
d
8
7
.
3
4
0
.
8
2
P
r
o
p
o
se
d
M
e
t
h
o
d
9
2
.
1
2
0
.
8
8
S
c
e
n
e
3
I
n
i
t
i
a
l
I
mag
e
7
8
.
5
0
.
6
9
D
C
P
8
6
.
9
9
0
.
8
1
HE
9
3
.
6
1
0
.
9
2
D
EC
O
R
R
8
6
.
5
7
0
.
8
P
r
o
p
o
se
d
M
e
t
h
o
d
9
5
.
2
8
0
.
9
3
4.
CO
NCLU
SI
O
N
I
n
th
is
s
tu
d
y
,
an
im
ag
e
e
n
h
an
ce
m
en
t
m
eth
o
d
was
p
r
o
p
o
s
ed
f
o
r
lo
w
co
n
tr
ast
im
ag
es,
f
o
r
m
ed
d
u
e
to
th
e
s
u
r
f
ac
e
r
ef
lecta
n
ce
in
SP
OT
-
5
im
ag
es.
T
h
er
ef
o
r
e,
a
f
a
ls
e
co
lo
u
r
co
m
p
o
s
ite,
in
clu
d
i
n
g
th
e
n
e
a
r
-
in
fra
re
d
(NIR)
,
g
r
ee
n
a
n
d
r
ed
c
h
an
n
els
,
was
ch
o
s
en
in
o
r
d
e
r
to
in
c
r
e
ase
th
e
v
eg
etatio
n
’
s
c
o
n
tr
ast,
as
in
d
icate
d
in
r
e
d
.
B
y
u
s
in
g
h
ist
o
g
ra
m
e
q
u
a
l
iza
ti
o
n
(
HE
)
,
th
e
im
a
g
e
was
ad
ju
s
ted
in
o
r
d
e
r
to
m
i
n
im
ize
th
e
p
r
o
b
lem
o
f
d
a
r
k
er
s
p
o
ts
o
r
s
u
r
f
ac
e
r
e
f
lecta
n
ce
.
T
h
e
m
o
d
if
icatio
n
o
f
th
e
weig
h
t
o
f
t
h
e
NI
R
ch
an
n
el
m
a
d
e
th
e
v
e
g
eta
tio
n
r
ef
lect
th
e
NI
R
an
d
g
r
ee
n
lig
h
t.
As a
r
esu
lt,
th
e
NI
R
-
HE
m
eth
o
d
ef
f
icien
tly
r
esto
r
ed
c
o
n
tr
ast f
o
r
all
d
atasets
,
p
r
o
d
u
cin
g
a
h
ig
h
er
e
f
f
icien
cy
in
ed
g
e
d
e
tectio
n
,
an
d
ac
h
iev
in
g
h
ig
h
er
o
v
er
all
ac
c
u
r
ac
y
.
Ad
d
itio
n
al
ly
,
th
e
r
o
o
t
m
ea
n
s
q
u
ar
e
(
R
MS)
s
h
o
wed
im
p
r
o
v
ed
v
alu
es.
T
h
e
ac
cu
r
ac
y
a
n
d
k
ap
p
a
v
al
u
e
wer
e
o
b
tain
e
d
,
in
o
r
d
er
to
e
v
alu
ate
th
e
m
ax
im
u
m
p
er
f
o
r
m
an
ce
o
f
th
e
en
h
a
n
ce
d
im
ag
es
.
A
s
u
cc
ess
r
ate
o
f
m
o
r
e
th
a
n
8
0
%
wa
s
ac
h
iev
ed
b
y
u
s
in
g
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
wh
ic
h
p
r
o
v
ed
t
h
at
it c
o
u
ld
ass
is
t in
h
ig
h
ac
cu
r
ac
y
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
ACK
NO
WL
E
DG
E
M
E
NT
T
h
e
au
th
o
r
s
g
r
atef
u
lly
ac
k
n
o
wled
g
e
Un
iv
er
s
iti
T
ek
n
o
lo
g
i
MA
R
A,
Un
iv
er
s
iti
T
ek
n
o
lo
g
i
Ma
lay
s
ia,
Un
iv
er
s
iti
Keb
an
g
s
aa
n
Ma
lay
s
ia,
Un
iv
er
s
iti
T
u
n
Hu
s
s
ein
O
n
n
an
d
U
n
iv
er
s
itas
Ah
m
ad
Dah
lan
f
o
r
s
u
p
p
o
r
tin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
9
9
-
1
5
1
4
1506
th
is
co
llab
o
r
ativ
e
r
esear
ch
in
th
e
p
r
esen
t
wo
r
k
,
a
n
d
also
wo
u
ld
lik
e
to
th
an
k
Ma
lay
s
ian
R
em
o
te
Sen
s
in
g
Ag
en
cy
,
wh
ich
p
r
o
v
i
d
ed
SP
OT
-
5
d
ata;
an
d
th
e
Ma
lay
s
ian
Go
v
er
n
m
e
n
t
an
d
Dep
a
r
tm
en
t
o
f
Su
r
v
e
y
an
d
Ma
p
p
in
g
Ma
lay
s
ia
(
J
UPEM
)
wh
ich
p
r
o
v
i
d
ed
to
p
o
g
r
a
p
h
y
an
d
g
az
ettes
r
elate
d
to
th
e
T
an
ju
n
g
Piai
ar
ea
.
T
an
ju
n
g
Piai
J
o
h
o
r
Natio
n
al
Par
k
s
taf
f
p
r
o
v
id
e
d
u
s
ef
u
l
in
f
o
r
m
atio
n
ab
o
u
t
th
e
s
tu
d
y
s
ite.
T
h
is
r
esear
ch
was
s
u
p
p
o
r
ted
b
y
th
e
M
y
th
Sch
o
l
ar
s
h
ip
Sch
em
e
o
f
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
Ma
lay
s
ia
an
d
th
e
G
-
Hea
r
t
s
ch
em
e
u
n
d
er
th
e
Gate
s
Sch
o
lar
s
Fo
u
n
d
atio
n
.
W
e
also
h
u
m
b
ly
ac
k
n
o
wled
g
e
th
e
FR
GS/1
/2
0
2
0
/I
C
T
0
2
/UT
M/0
3
/1
o
f
FR
GS g
r
an
t f
u
n
d
ed
b
y
th
e
Min
is
tr
y
o
f
E
d
u
ca
tio
n
,
Ma
lay
s
ia
.
RE
F
E
R
E
NC
E
S
[1
]
R.
Ae
d
la,
G
.
S
.
Dw
a
ra
k
ish
,
a
n
d
D.
V.
Re
d
d
y
,
“
Au
to
m
a
ti
c
S
h
o
re
l
in
e
De
tec
ti
o
n
a
n
d
Ch
a
n
g
e
De
tec
ti
o
n
An
a
l
y
sis
o
f
Ne
trav
a
ti
-
G
u
rp
u
rRiv
e
rm
o
u
th
Us
i
n
g
Hist
o
g
ra
m
E
q
u
a
li
z
a
ti
o
n
a
n
d
Ad
a
p
ti
v
e
T
h
re
sh
o
l
d
i
n
g
Tec
h
n
i
q
u
e
s,”
A
q
u
a
ti
c
Pro
c
e
d
ia
,
v
o
l.
4
,
p
p
.
5
6
3
–
5
7
0
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/
j.
a
q
p
ro
.
2
0
1
5
.
0
2
.
0
7
3
.
[2
]
B.
Ch
a
n
d
ra
b
a
b
u
Na
ik
a
n
d
B.
A
n
u
ra
d
h
a
,
“
E
x
trac
ti
o
n
o
f
wa
ter
-
b
o
d
y
a
re
a
fro
m
h
ig
h
-
re
so
lu
ti
o
n
Lan
d
sa
t
ima
g
e
ry
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tric
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(I
J
ECE
)
,
v
o
l
.
8
,
n
o
.
6
.
p
p
.
4
1
1
1
–
4
1
1
9
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
8
i6
.
p
p
.
4
1
1
1
-
4
1
1
9
.
[3
]
Y.
S
h
a
fiei,
F
.
F
a
g
h
i
h
i,
H.
He
y
d
a
ri,
a
n
d
A.
H.
S
a
lem
i,
“
Lab
o
ra
to
r
y
i
n
v
e
sti
g
a
ti
o
n
o
f
t
h
e
imp
a
c
t
o
f
a
ir
p
o
ll
u
t
io
n
o
n
p
a
rti
a
l
d
isc
h
a
r
g
e
in
c
e
p
ti
o
n
v
o
lt
a
g
e
o
f
i
n
su
lat
o
rs
in
a
sp
e
c
ifi
c
re
g
io
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
in
e
e
rin
g
(IJ
ECE
)
,
v
o
l.
1
1
,
n
o
.
6
.
p
p
.
4
6
3
4
–
4
6
4
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
6
.
p
p
4
6
3
4
-
4
6
4
0
.
[4
]
Y.
S
a
ri,
P
.
B
.
P
ra
k
o
so
,
a
n
d
A.
R.
Ba
sk
a
ra
,
“
Ap
p
l
ica
ti
o
n
o
f
n
e
u
ra
l
n
e
two
r
k
m
e
th
o
d
f
o
r
r
o
a
d
c
ra
c
k
d
e
tec
ti
o
n
,
”
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
t
io
n
C
o
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l.
1
8
,
n
o
.
4
.
p
p
.
1
9
6
2
–
1
9
6
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/
TE
LKOMNIKA.V
1
8
I
4
.
1
4
8
2
5
.
[5
]
N.
M
.
Na
wi,
M
.
M
a
k
h
tar,
M
.
Z.
S
a
li
k
o
n
,
a
n
d
Z.
A.
Afi
p
,
“
A
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
c
las
sifica
ti
o
n
tec
h
n
iq
u
e
s
o
n
p
re
d
ictin
g
f
lo
o
d
r
isk
,
”
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
(IJ
EE
CS
)
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
1
3
4
2
–
1
3
5
0
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
8
.
i3
.
p
p
1
3
4
2
-
1
3
5
0
.
[6
]
M
.
A.
Zay
tar
a
n
d
C.
El
Am
ra
n
i,
“
S
a
telli
te
ima
g
e
in
p
a
in
ti
n
g
with
d
e
e
p
g
e
n
e
ra
ti
v
e
a
d
v
e
rsa
rial
n
e
u
ra
l
n
e
two
r
k
s,”
IAE
S
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
(IJ
-
AI)
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
1
2
1
–
1
3
0
,
M
a
r.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai.
v
1
0
.
i
1
.
p
p
1
2
1
-
1
3
0
.
[7
]
T.
H.
P
h
a
n
,
D.
C
.
Tra
n
,
a
n
d
M
.
F
.
Ha
ss
a
n
,
“
Vie
tn
a
m
e
se
c
h
a
ra
c
ter
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
CNN
m
o
d
e
l
with
re
d
u
c
e
d
c
h
a
ra
c
ter
c
las
se
s,”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
fo
rm
a
ti
c
s
(BE
EI)
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
9
6
2
–
9
6
9
,
Ap
r.
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/ee
i.
v
1
0
i
2
.
2
8
1
0
.
[8
]
Y.
Yu
h
e
n
d
ra
a
n
d
J.
T
.
S
.
S
u
m
a
n
ty
o
,
“
As
se
ss
m
e
n
t
o
f
Lan
d
sa
t
8
T
IRS
d
a
ta
c
a
p
a
b
il
it
y
fo
r
t
h
e
p
re
li
m
in
a
ry
st
u
d
y
o
f
g
e
o
th
e
rm
a
l
e
n
e
r
g
y
re
so
u
rc
e
s
i
n
Wes
t
S
u
m
a
tra,”
T
E
L
KOM
NIKA
(T
e
lec
o
mm
u
n
ica
ti
o
n
Co
m
p
u
t
in
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
2
7
3
7
–
2
7
4
7
,
Oc
t.
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/t
e
lk
o
m
n
i
k
a
.
v
1
8
i
5
.
1
6
1
7
2
.
[9
]
I.
S
.
Al
-
M
e
ji
b
l
i,
J.
K
.
Alwa
n
,
a
n
d
D.
H.
Ab
d
,
“
T
h
e
e
f
fe
c
t
o
f
g
a
m
m
a
v
a
lu
e
o
n
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
i
n
e
p
e
rfo
rm
a
n
c
e
with
d
iffere
n
t
k
e
rn
e
ls,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(IJ
ECE
)
,
v
o
l.
1
0
,
n
o
.
5
,
p
p
.
5
4
9
7
–
5
5
0
6
,
Oc
t.
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
0
i5
.
p
p
5
4
9
7
-
5
5
0
6
.
[1
0
]
M
.
R.
Al
-
Ha
d
id
i
,
B.
AlS
a
a
id
a
h
,
a
n
d
M
.
Al
-
G
a
wa
g
z
e
h
,
“
G
li
o
b
las
to
m
a
s
b
ra
in
tu
m
o
u
r
se
g
m
e
n
tatio
n
b
a
se
d
o
n
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tric
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(I
J
ECE
)
,
v
o
l
.
1
0
,
n
o
.
5
,
p
p
.
4
7
3
8
–
4
7
4
4
,
Oc
t.
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
c
e
.
v
1
0
i5
.
p
p
4
7
3
8
-
4
7
4
4
.
[1
1
]
N.
S
a
b
ri,
N.
S
h
a
fe
k
a
h
Ka
ss
im,
S
.
Ib
ra
h
im,
R.
R
o
sla
n
,
N.
N.
A.
M
a
n
g
sh
o
r,
a
n
d
Z.
I
b
ra
h
im,
“
Nu
t
rien
t
d
e
ficie
n
c
y
d
e
tec
ti
o
n
i
n
M
a
ize
(Zea
m
a
y
s
L.
)
lea
v
e
s
u
sin
g
ima
g
e
p
ro
c
e
ss
in
g
,
”
IAE
S
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Art
if
icia
l
In
telli
g
e
n
c
e
(IJ
-
AI)
,
v
o
l
.
9
,
n
o
.
2
,
p
p
.
3
0
4
–
3
0
9
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
1
5
9
1
/i
jai
.
v
9
.
i2
.
p
p
3
0
4
-
3
0
9
.
[1
2
]
D.
F
e
b
rian
S
e
n
g
k
e
y
,
A.
Ja
c
o
b
u
s,
a
n
d
F
.
J
o
h
a
n
e
s
M
a
n
o
p
p
o
,
“
Eff
e
c
ts
o
f
k
e
r
n
e
ls
a
n
d
th
e
p
r
o
p
o
rti
o
n
o
f
train
in
g
d
a
t
a
o
n
t
h
e
a
c
c
u
ra
c
y
o
f
S
VM
se
n
ti
m
e
n
t
a
n
a
ly
sis
in
lec
tu
re
r
e
v
a
l
u
a
ti
o
n
,
”
IA
ES
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Art
if
icia
l
In
telli
g
e
n
c
e
(IJ
-
AI)
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
7
3
4
–
7
4
3
,
De
c
.
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jai.
v
9
.
i
4
.
p
p
7
3
4
-
7
4
3
.
[1
3
]
C.
Jitt
a
wiriy
a
n
u
k
o
o
n
,
“
Esti
m
a
ti
o
n
o
f
re
g
re
ss
io
n
-
b
a
se
d
m
o
d
e
l
with
b
u
l
k
n
o
isy
d
a
ta,”
I
n
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(IJ
ECE
)
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
3
6
4
9
–
3
6
5
6
,
Oc
t.
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
9
i5
.
p
p
3
6
4
9
-
3
6
5
6
.
[1
4
]
M
.
Dim
y
a
ti
,
A.
F
a
u
z
y
,
a
n
d
A
.
S
.
P
u
tra,
“
Re
m
o
te
se
n
si
n
g
tec
h
n
o
l
o
g
y
f
o
r
d
isa
ste
r
m
it
i
g
a
ti
o
n
a
n
d
re
g
io
n
a
l
in
fra
stru
c
tu
re
p
lan
n
in
g
i
n
u
rb
a
n
a
re
a
:
a
re
v
iew
,
”
T
EL
KOM
NIKA
(T
e
lec
o
mm
u
n
ica
ti
o
n
Co
m
p
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l
.
1
7
,
n
o
.
2
,
p
p
.
6
0
1
–
6
0
8
,
Ap
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
2
9
2
8
/t
e
l
k
o
m
n
i
k
a
.
v
1
7
i
2
.
1
2
2
4
2
.
[1
5
]
S
.
K.
Ja
m
e
e
l,
S
.
Ay
d
in
,
a
n
d
N.
H.
G
h
a
e
b
,
“
Lo
c
a
l
in
fo
rm
a
ti
o
n
p
a
tt
e
rn
d
e
sc
rip
to
r
f
o
r
c
o
rn
e
a
l
d
ise
a
se
s
d
iag
n
o
sis,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
6
.
p
p
.
4
9
7
2
–
4
9
8
1
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
6
.
p
p
4
9
7
2
-
4
9
8
1
.
[1
6
]
A.
N.
Ra
z
z
a
q
,
R.
G
h
a
z
a
li
,
N.
K
.
El
A
b
b
a
d
i,
a
n
d
H.
A.
H.
Al
Na
ffa
k
h
,
“
Lev
e
n
b
e
rg
-
m
a
rq
u
a
rd
t
b
a
c
k
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
wi
th
tec
h
e
b
y
c
h
e
v
e
m
o
m
e
n
ts
fo
r
fa
c
e
d
e
tec
ti
o
n
,
”
B
u
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
,
v
o
l.
1
0
,
n
o
.
5
.
p
p
.
2
5
4
8
–
2
5
5
6
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/ee
i.
v
1
0
i
5
.
2
3
6
4
.
[1
7
]
B.
C.
C
.
M
e
n
g
,
D.
S
.
A
.
Da
m
it
,
a
n
d
N.
S
.
Da
m
a
n
h
u
ri,
“
Co
m
p
a
r
a
ti
v
e
stu
d
ies
o
f
m
u
lt
isc
a
le
e
d
g
e
d
e
tec
ti
o
n
u
si
n
g
d
iffere
n
t
e
d
g
e
d
e
tec
t
o
rs
f
o
r
m
ri
th
ig
h
,
”
B
u
ll
e
ti
n
o
f
El
e
c
trica
l
E
n
g
in
e
e
rin
g
a
n
d
I
n
fo
rm
a
ti
c
s
,
v
o
l.
1
0
,
n
o
.
4
.
p
p
.
1
9
7
9
–
1
9
8
6
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/
EE
I.
V
1
0
I
4
.
2
2
2
0
.
[1
8
]
A.
Ab
u
h
a
m
d
a
h
,
W.
Bo
u
li
la,
G
.
M
.
Ja
ra
d
a
t,
A.
M
.
Qu
teis
h
a
t,
M
.
K.
Alsm
a
d
i,
a
n
d
I.
A.
Alm
a
ra
sh
d
e
h
,
“
A
n
o
v
e
l
p
o
p
u
lat
i
o
n
-
b
a
se
d
lo
c
a
l
se
a
rc
h
f
o
r
n
u
rse
r
o
ste
rin
g
p
r
o
b
lem
,
”
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
1
.
p
p
.
4
7
1
–
4
8
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
c
e
.
v
1
1
i1
.
p
p
4
7
1
-
4
8
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
teg
r
a
ted
N
I
R
-
HE
b
a
s
ed
S
P
OT
-
5
ima
g
e
en
h
a
n
ce
men
t m
et
h
o
d
fo
r
fea
tu
r
es
…
(
F
a
r
iz
u
w
a
n
a
A
kma
Zu
lkifle
)
1507
[1
9
]
A.
Hu
ss
e
in
Ali,
M
.
Na
wa
f
Ab
b
o
d
,
M
.
Kh
a
m
e
e
s
Kh
a
lee
l,
M
.
A
b
d
u
l
g
h
a
f
o
o
r
M
o
h
a
m
m
e
d
,
a
n
d
T.
S
u
ti
k
n
o
,
“
Larg
e
sc
a
le
d
a
ta
a
n
a
ly
sis
u
sin
g
M
Ll
i
b
,
”
T
EL
KOM
NIKA
(T
e
lec
o
mm
u
n
ic
a
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l.
1
9
,
n
o
.
5
,
p
p
.
1
7
3
5
–
1
7
4
6
,
Oc
t.
2
0
2
1
,
d
o
i:
1
0
.
1
2
9
2
8
/t
e
lk
o
m
n
i
k
a
.
v
1
9
i5
.
2
1
0
5
9
.
[2
0
]
M
.
Z.
N.
Al
-
Da
b
a
g
h
,
“
Au
to
m
a
t
e
d
tu
m
o
r
se
g
m
e
n
tatio
n
in
M
R
b
ra
in
ima
g
e
u
sin
g
f
u
z
z
y
C
-
m
e
a
n
s
c
lu
ste
rin
g
a
n
d
se
e
d
e
d
re
g
io
n
m
e
th
o
d
o
lo
g
y
,
”
IA
ES
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Arti
fi
c
ia
l
In
tell
ig
e
n
c
e
,
v
o
l.
1
0
,
n
o
.
2
.
p
p
.
2
8
4
–
2
9
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jai.
v
1
0
.
i
2
.
p
p
2
8
4
-
2
9
0
.
[2
1
]
S
.
Ya
k
in
,
T.
Ha
sa
n
u
d
d
i
n
,
a
n
d
N.
Ku
rn
iati,
“
Ap
p
li
c
a
ti
o
n
o
f
c
o
n
ten
t
b
a
se
d
ima
g
e
re
tri
e
v
a
l
i
n
d
i
g
it
a
l
ima
g
e
se
a
rc
h
sy
ste
m
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
,
v
o
l.
1
0
,
n
o
.
2
.
p
p
.
1
1
2
2
–
1
1
2
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/E
EI
.
V1
0
I
2
.
2
7
1
3
.
[2
2
]
D.
G
h
o
ra
i
a
n
d
G
.
S
.
Bh
u
n
ia,
“
Au
to
m
a
ti
c
sh
o
re
li
n
e
d
e
tec
ti
o
n
a
n
d
it
s
fo
re
c
a
st:
a
c
a
se
stu
d
y
o
n
Dr.
Ab
d
u
l
Ka
lam
Isla
n
d
in
t
h
e
se
c
ti
o
n
o
f
Ba
y
o
f
Be
n
g
a
l,
”
Ge
o
c
a
rt
o
In
ter
n
a
ti
o
n
a
l
,
p
p
.
1
–
2
0
,
S
e
p
.
2
0
2
0
,
d
o
i:
1
0
.
1
0
8
0
/
1
0
1
0
6
0
4
9
.
2
0
2
0
.
1
8
1
5
8
6
8
.
[2
3
]
A.
P
.
R
u
iz
-
Be
lt
ra
n
,
A.
As
t
o
rg
a
-
M
o
a
r,
P
.
S
a
ll
e
s,
a
n
d
C.
M
.
A
p
p
e
n
d
in
i,
“
S
h
o
rt
-
Term
S
h
o
re
li
n
e
T
re
n
d
De
tec
ti
o
n
P
a
tt
e
rn
s
Us
in
g
S
P
OT
-
5
Im
a
g
e
F
u
sio
n
i
n
th
e
No
rt
h
we
st
o
f
Yu
c
a
tan
,
M
e
x
ico
,
”
Est
u
a
rie
s
a
n
d
C
o
a
sts
,
v
o
l.
4
2
,
n
o
.
7
,
p
p
.
1
7
6
1
–
1
7
7
3
,
N
o
v
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/s1
2
2
3
7
-
0
1
9
-
0
0
5
7
3
-
7.
[2
4
]
A.
Wi
d
i
p
a
m
in
to
e
t
a
l.
,
“
Ro
o
f
m
a
teria
ls
id
e
n
ti
fica
ti
o
n
b
a
se
d
o
n
p
leia
d
e
s
sp
e
c
tral
re
sp
o
n
se
s
u
sin
g
su
p
e
rv
ise
d
c
las
sifica
ti
o
n
,
”
T
EL
KOM
NIK
A
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l.
1
9
,
n
o
.
2
,
p
p
.
6
9
0
–
7
0
4
,
Ap
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/t
e
l
k
o
m
n
i
k
a
.
v
1
9
i
2
.
1
8
1
5
5
.
[2
5
]
M
.
B.
S
a
leh
e
t
a
l.
,
“
Alg
o
rit
h
m
fo
r
d
e
tec
ti
n
g
d
e
fo
re
sta
ti
o
n
a
n
d
fo
re
st
d
e
g
ra
d
a
ti
o
n
u
sin
g
v
e
g
e
t
a
ti
o
n
in
d
ice
s,”
T
e
lko
mn
ika
(
T
e
lec
o
mm
u
n
ic
a
ti
o
n
Co
mp
u
t
in
g
El
e
c
tro
n
ics
a
n
d
Co
n
t
ro
l)
,
v
o
l.
1
7
,
n
o
.
5
.
p
p
.
2
3
3
5
–
2
3
4
5
,
2
0
1
9
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.
v
1
7
i5
.
1
2
5
8
5
.
[2
6
]
C.
De
wi
a
n
d
A.
Ba
su
k
i,
“
Id
e
n
ti
fy
in
g
c
it
ro
n
e
ll
a
p
la
n
ts
fr
o
m
UA
V
ima
g
e
ry
u
si
n
g
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
,
”
T
e
lko
mn
ika
(
T
e
lec
o
mm
u
n
ic
a
ti
o
n
Co
mp
u
t
in
g
El
e
c
tro
n
ics
a
n
d
Co
n
t
ro
l)
,
v
o
l.
1
6
,
n
o
.
4
.
p
p
.
1
8
7
7
–
1
8
8
5
,
2
0
1
8
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.
v
1
6
i4
.
7
4
5
0
.
[2
7]
R.
A.
Ha
m
z
a
h
,
M
.
M
.
R
o
sla
n
,
A.
F
.
B.
Ka
d
m
in
,
S
.
F
.
B.
A
.
G
a
n
i,
a
n
d
K.
A.
A.
Az
iz,
“
JPG
,
P
NG
a
n
d
B
M
P
ima
g
e
c
o
m
p
re
ss
io
n
u
sin
g
d
isc
re
te
c
o
sin
e
tran
sfo
rm
,
”
T
e
lko
mn
ika
(T
e
lec
o
mm
u
n
ica
ti
o
n
C
o
mp
u
ti
n
g
E
lec
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l
.
1
9
,
n
o
.
3
.
p
p
.
1
0
1
0
–
1
0
1
6
,
2
0
2
1
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.v
1
9
i
3
.
1
4
7
5
8
.
[2
8
]
M
.
C.
G
.
Ba
b
u
a
n
d
M
.
C.
P
a
d
m
a
,
“
S
e
m
a
n
ti
c
fe
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
f
o
r
h
y
p
e
rsp
e
c
tral
c
ro
p
c
las
sifica
ti
o
n
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
i
e
n
c
e
,
v
o
l.
2
3
,
n
o
.
1
.
p
p
.
3
8
7
–
3
9
5
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
2
3
.
i
1
.
p
p
3
8
7
-
3
9
5
.
[2
9
]
W.
-
W.
C
h
e
n
a
n
d
H.
-
K.
Ch
a
n
g
,
“
Esti
m
a
ti
o
n
o
f
sh
o
re
li
n
e
p
o
si
ti
o
n
a
n
d
c
h
a
n
g
e
fr
o
m
sa
telli
te
ima
g
e
s
c
o
n
sid
e
ri
n
g
ti
d
a
l
v
a
riatio
n
,
”
Estu
a
rin
e
,
C
o
a
st
a
l
a
n
d
S
h
e
lf
S
c
ie
n
c
e
,
v
o
l
.
8
4
,
n
o
.
1
,
p
p
.
5
4
–
6
0
,
Au
g
.
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
e
c
ss
.
2
0
0
9
.
0
6
.
0
0
2
.
[3
0
]
E.
I.
Jo
u
r
n
a
l,
“
Ho
w
to
in
terp
re
t
a
fa
lse
c
o
lo
r
sa
telli
te
ima
g
e
.
”
2
0
2
1
,
[On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
:
//
e
ij
o
u
rn
a
l.
c
o
m
/p
ri
n
t/
a
rti
c
les
/
h
o
w
-
to
-
in
ter
p
re
t
-
a
-
fa
lse
-
c
o
lo
r
-
sa
telli
te
-
ima
g
e
.
[3
1
]
B.
Ca
ste
ll
e
e
t
a
l.
,
“
S
a
telli
te
-
d
e
riv
e
d
sh
o
re
li
n
e
d
e
tec
ti
o
n
a
t
a
h
ig
h
-
e
n
e
rg
y
m
e
so
-
m
a
c
ro
ti
d
a
l
b
e
a
c
h
,
”
G
e
o
mo
rp
h
o
lo
g
y
,
v
o
l.
3
8
3
.
2
0
2
1
,
d
o
i:
1
0
.
1
0
1
6
/j
.
g
e
o
m
o
rp
h
.
2
0
2
1
.
1
0
7
7
0
7
.
[3
2
]
Y.
Tajima
,
L.
Wu
,
a
n
d
K.
Wat
a
n
a
b
e
,
“
De
v
e
lo
p
m
e
n
t
o
f
a
sh
o
re
li
n
e
d
e
tec
ti
o
n
m
e
th
o
d
u
si
n
g
a
n
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
b
a
se
d
o
n
sa
telli
te
sa
r
ima
g
e
ry
,
”
Rem
o
te
S
e
n
sin
g
,
v
o
l.
1
3
,
n
o
.
1
2
.
2
0
2
1
,
d
o
i:
1
0
.
3
3
9
0
/rs1
3
1
2
2
2
5
4
.
[3
3
]
S
.
Dh
in
g
ra
a
n
d
D.
Ku
m
a
r,
“
A
re
v
iew
o
f
re
m
o
tely
se
n
se
d
sa
telli
te
ima
g
e
c
las
sifica
ti
o
n
,
”
I
n
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
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
9
,
n
o
.
3
.
p
p
.
1
7
2
0
–
1
7
3
1
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
c
e
.
v
9
i
3
.
p
p
.
1
7
2
0
-
1
7
3
1
.
[3
4
]
M
.
S
.
Al
G
o
b
i
,
D.
Be
n
a
ti
a
,
a
n
d
M
.
Ba
li
,
“
A
h
y
b
ri
d
a
lg
o
rit
h
m
fo
r
wa
v
e
-
fro
n
t
c
o
rre
c
ti
o
n
s
a
p
p
li
e
d
to
sa
telli
te
-
to
-
g
ro
u
n
d
las
e
r
c
o
m
m
u
n
ica
ti
o
n
,
”
T
e
lko
mn
ika
(
T
e
lec
o
mm
u
n
ic
a
ti
o
n
Co
mp
u
t
in
g
E
lec
tro
n
ics
a
n
d
Co
n
t
ro
l)
,
v
o
l.
1
8
,
n
o
.
3
.
p
p
.
1
2
5
9
–
1
2
6
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.v
1
8
i
3
.
1
2
9
6
0
.
[3
5
]
F
.
Ri
b
a
s,
G
.
S
ima
rro
,
J.
Arria
g
a
,
a
n
d
P
.
L
u
q
u
e
,
“
Au
to
m
a
ti
c
sh
o
re
li
n
e
d
e
tec
ti
o
n
fro
m
v
i
d
e
o
ima
g
e
s
b
y
c
o
m
b
in
i
n
g
in
fo
rm
a
ti
o
n
fr
o
m
d
iffere
n
t
m
e
th
o
d
s,”
Rem
o
te S
e
n
sin
g
,
v
o
l.
1
2
,
n
o
.
2
2
.
p
p
.
1
–
2
3
,
2
0
2
0
,
d
o
i:
1
0
.
3
3
9
0
/
rs1
2
2
2
3
7
1
7
.
[3
6
]
S
.
Ho
ż
y
ń
a
n
d
J.
Zale
ws
k
i,
“
S
h
o
r
e
li
n
e
d
e
tec
ti
o
n
a
n
d
lan
d
se
g
m
e
n
t
a
ti
o
n
fo
r
a
u
to
n
o
m
o
u
s
su
rfa
c
e
v
e
h
icle
n
a
v
i
g
a
ti
o
n
with
t
h
e
u
se
o
f
a
n
o
p
ti
c
a
l
sy
ste
m
,
”
S
e
n
so
rs
(S
wi
tze
rla
n
d
)
,
v
o
l
.
2
0
,
n
o
.
1
0
.
2
0
2
0
,
d
o
i:
1
0
.
3
3
9
0
/s
2
0
1
0
2
7
9
9
.
[3
7
]
D.
F
u
r
b
e
rg
,
Y.
Ba
n
,
a
n
d
A.
N
a
sc
e
tt
i,
“
M
o
n
i
to
ri
n
g
o
f
u
r
b
a
n
iza
ti
o
n
a
n
d
a
n
a
l
y
sis
o
f
e
n
v
ir
o
n
m
e
n
tal
imp
a
c
t
i
n
S
to
c
k
h
o
lm
wit
h
S
e
n
ti
n
e
l
-
2
A
a
n
d
S
P
OT
-
5
M
u
lt
is
p
e
c
tral
Da
ta,”
Rem
o
te
S
e
n
si
n
g
,
v
o
l.
1
1
,
n
o
.
2
0
.
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/rs
1
1
2
0
2
4
0
8
.
[3
8
]
R.
P
.
S
il
a
lah
i,
I
.
N.
S
.
Ja
y
a
,
T.
Ti
ry
a
n
a
,
a
n
d
F
.
M
u
li
a
,
“
As
se
ss
in
g
t
h
e
c
ro
wn
c
lo
su
re
o
f
n
y
p
a
o
n
UA
V
ima
g
e
s
u
sin
g
mean
-
sh
ift
se
g
m
e
n
tatio
n
a
lg
o
rit
h
m
,
”
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
9
,
n
o
.
3
.
p
p
.
7
2
2
–
7
3
0
,
2
0
1
8
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
9
.
i3
.
p
p
7
2
2
-
7
3
0
.
[3
9
]
S
.
L
.
K.
Re
d
d
y
,
C
.
V
Ra
o
,
P
.
Ra
jes
h
Ku
m
a
r,
R.
V.
G
.
An
jan
e
y
u
l
u
,
a
n
d
B.
G
o
p
a
la
Krish
n
a
,
“
An
i
n
d
e
x
b
a
se
d
ro
a
d
fe
a
tu
re
e
x
trac
ti
o
n
fr
o
m
LAND
S
AT
-
8
OLI
ima
g
e
s,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
2
.
p
p
.
1
3
1
9
–
1
3
3
6
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
2
.
p
p
1
3
1
9
-
1
3
3
6
.
[4
0
]
B.
Isk
a
n
d
a
r,
I.
N.
S
.
Ja
y
a
,
a
n
d
M
.
B.
S
a
leh
,
“
Cro
w
n
c
lo
su
re
se
g
m
e
n
tatio
n
o
n
we
tl
a
n
d
l
o
wla
n
d
f
o
re
st u
sin
g
t
h
e
m
e
a
n
sh
ift
a
l
g
o
rit
h
m
,
”
I
n
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
2
4
,
n
o
.
2
.
p
p
.
9
6
5
–
9
7
7
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
2
4
.
i
2
.
p
p
9
6
5
-
9
7
7
.
[4
1
]
J.
-
H.
Kim
,
W
.
-
D.
Ja
n
g
,
J.
-
Y.
S
im,
a
n
d
C.
-
S
.
Kim
,
“
Op
ti
m
ize
d
c
o
n
t
ra
st
e
n
h
a
n
c
e
m
e
n
t
f
o
r
re
a
l
-
ti
m
e
i
m
a
g
e
a
n
d
v
i
d
e
o
d
e
h
a
z
in
g
,
”
J
o
u
rn
a
l
o
f
Vi
su
a
l
C
o
mm
u
n
ica
ti
o
n
a
n
d
Ima
g
e
Rep
re
se
n
ta
ti
o
n
,
v
o
l.
2
4
,
n
o
.
3
,
p
p
.
4
1
0
–
4
2
5
,
Ap
r.
2
0
1
3
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jv
c
ir.
2
0
1
3
.
0
2
.
0
0
4
.
[4
2]
J.
Lo
n
g
,
Z.
S
h
i,
W.
Tan
g
,
a
n
d
C.
Zh
a
n
g
,
“
S
in
g
le
Re
m
o
te
S
e
n
sin
g
I
m
a
g
e
De
h
a
z
in
g
,
”
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
L
e
tt
e
rs
,
v
o
l.
1
1
,
n
o
.
1
,
p
p
.
5
9
–
6
3
,
Ja
n
.
2
0
1
4
,
d
o
i:
1
0
.
1
1
0
9
/
LG
RS
.
2
0
1
3
.
2
2
4
5
8
5
7
.
[4
3
]
“
M
a
lay
sia
M
e
teo
ro
l
o
g
ica
l
De
p
a
rt
m
e
n
t.
”
2
0
1
8
,
[On
li
n
e
].
Av
a
il
a
b
le:
h
tt
p
:/
/www
.
m
e
t.
g
o
v
.
m
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
2
0
2
1
:
1
4
9
9
-
1
5
1
4
1508
[4
4
]
K.
M
.
K
.
Ku
Yu
so
f
,
S
.
S
.
Ism
a
il
,
A.
Az
id
,
M
.
S
.
A.
S
a
n
i,
N.
M
.
I
sa
,
a
n
d
M
.
Z
.
M
o
h
a
m
a
t
Zaw
a
wi,
“
Va
riab
il
it
y
o
n
p
a
rti
c
u
late
m
a
tt
e
r
a
n
d
m
e
teo
r
o
lo
g
y
d
a
tas
e
t
d
u
ri
n
g
th
e
h
a
z
y
p
e
ri
o
d
in
e
a
ste
rn
re
g
i
o
n
o
f
P
e
n
in
s
u
lar
M
a
lay
sia
,
”
Da
t
a
in
Brief
,
v
o
l.
2
9
.
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
d
i
b
.
2
0
2
0
.
1
0
5
2
1
0
.
[4
5
]
Y.
-
H.
S
h
ia
u
,
P
.
-
Y
.
Ch
e
n
,
H.
-
Y.
Ya
n
g
,
C.
-
H.
C
h
e
n
,
a
n
d
S
.
-
S
.
Wa
n
g
,
“
Wei
g
h
te
d
h
a
z
e
re
m
o
v
a
l
m
e
th
o
d
with
h
a
l
o
p
re
v
e
n
ti
o
n
,
”
J
o
u
rn
a
l
o
f
Vi
s
u
a
l
C
o
mm
u
n
ic
a
ti
o
n
a
n
d
Ima
g
e
Re
p
re
se
n
ta
ti
o
n
,
v
o
l.
2
5
,
n
o
.
2
,
p
p
.
4
4
5
–
4
5
3
,
F
e
b
.
2
0
1
4
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jv
c
ir.
2
0
1
3
.
1
2
.
0
1
1
.
[4
6
]
B.
A.
S
c
h
ich
tel
e
t
a
l.
,
“
Us
in
g
IM
P
ROV
E
sp
e
c
iate
d
a
e
ro
so
l
c
o
n
c
e
n
tratio
n
s
to
trac
k
tren
d
s
in
a
n
t
h
r
o
p
o
g
e
n
ic
h
a
z
e
,
”
v
o
l.
3
.
p
p
.
2
2
5
1
–
2
2
5
8
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/
j.
a
tmo
sre
s.2
0
1
8
.
0
5
.
0
0
8
.
[4
7
]
L.
P
e
i,
Z.
Ya
n
,
D.
Ch
e
n
,
a
n
d
S
.
M
iao
,
“
Cli
m
a
te
v
a
riab
i
li
ty
o
r
a
n
th
ro
p
o
g
e
n
ic
e
m
issio
n
s:
wh
ich
c
a
u
se
d
Be
ij
in
g
Ha
z
e
?
,
”
En
v
iro
n
me
n
ta
l
Res
e
a
rc
h
L
e
tt
e
rs
,
v
o
l
.
1
5
,
n
o
.
3
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
8
-
9
3
2
6
/ab
6
f
1
1
.
[4
8
]
S
.
Y.
J.
P
ra
se
ty
o
,
B.
H.
S
ima
n
j
u
n
tak
,
K.
D.
Ha
rto
m
o
,
a
n
d
W
.
S
u
li
s
ty
o
,
“
Co
m
p
u
ter
m
o
d
e
l
f
o
r
tsu
n
a
m
i
v
u
ln
e
ra
b
il
i
t
y
u
sin
g
se
n
t
in
e
l
2
a
a
n
d
srtm
ima
g
e
s
o
p
ti
m
ize
d
b
y
m
a
c
h
in
e
lea
rn
in
g
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
fo
rm
a
t
ics
,
v
o
l.
1
0
,
n
o
.
5
.
p
p
.
2
8
2
1
–
2
8
3
5
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/ee
i.
v
1
0
i5
.
3
1
0
0
.
[4
9
]
M
.
H.
X.
Wai,
A.
H
u
o
n
g
,
a
n
d
X
.
Ng
u
,
“
S
o
il
m
o
istu
re
le
v
e
l
p
re
d
ictio
n
u
si
n
g
o
p
t
ica
l
tec
h
n
i
q
u
e
a
n
d
a
rti
ficia
l
n
e
u
ra
l
n
e
two
rk
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
2
.
p
p
.
1
7
5
2
–
1
7
6
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
2
.
p
p
1
7
5
2
-
1
7
6
0
.
[5
0
]
M
.
Dim
y
a
ti
,
K
u
stiy
o
,
a
n
d
R
.
D
.
Dim
y
a
ti
,
“
P
a
d
d
y
field
c
las
sific
a
ti
o
n
wit
h
M
OD
IS
-
terra
m
u
lt
i
-
t
e
m
p
o
ra
l
ima
g
e
tran
sfo
rm
a
ti
o
n
u
sin
g
p
h
e
n
o
lo
g
ic
a
l
a
p
p
ro
a
c
h
i
n
Ja
v
a
Isla
n
d
,
”
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
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
2
.
p
p
.
1
3
4
6
–
13
5
8
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
je
c
e
.
v
9
i2
.
p
p
.
1
3
4
6
-
1
3
5
8
.
[5
1
]
A.
Al
F
u
g
u
ra
,
L
.
Bil
la,
a
n
d
B
.
P
ra
d
h
a
n
,
“
S
e
m
i
-
a
u
to
m
a
ted
p
r
o
c
e
d
u
re
s
fo
r
sh
o
re
li
n
e
e
x
trac
ti
o
n
u
sin
g
sin
g
le
RAD
ARSAT
-
1
S
AR
ima
g
e
,
”
Est
u
a
rin
e
,
Co
a
sta
l
a
n
d
S
h
e
lf
S
c
ien
c
e
,
v
o
l.
9
5
,
n
o
.
4
,
p
p
.
3
9
5
–
4
0
0
,
De
c
.
2
0
1
1
,
d
o
i:
1
0
.
1
0
1
6
/
j.
e
c
ss
.
2
0
1
1
.
1
0
.
0
0
9
.
[5
2
]
Q.
A.
Al
-
h
u
ss
a
in
Ha
d
i,
“
Ve
in
p
a
lm
re
c
o
g
n
it
i
o
n
m
o
d
e
l
u
sin
g
f
u
sio
n
o
f
fe
a
t
u
re
s,”
T
e
lko
mn
ika
(
T
e
lec
o
mm
u
n
ica
t
io
n
Co
mp
u
t
in
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l
.
1
8
,
n
o
.
6
,
p
p
.
2
9
2
1
–
2
9
2
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.
v
1
8
i6
.
1
6
1
4
9
.
[5
3
]
K.
I.
Ah
m
e
d
,
M
.
H.
Ha
b
a
e
b
i
,
a
n
d
M
.
R.
Isla
m
,
“
A
re
a
l
ti
m
e
v
e
in
d
e
tec
ti
o
n
sy
ste
m
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
0
,
n
o
.
1
.
p
p
.
1
2
9
–
1
3
7
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
5
9
1
/IJEE
CS
.
V1
0
.
I1
.
P
P
1
2
9
-
1
3
7
.
[5
4
]
K.
I.
A
h
m
e
d
,
M
.
H
.
Ha
b
a
e
b
i
,
a
n
d
M
.
D.
Isla
m
,
“
S
m
a
rt
p
h
o
n
e
a
i
d
e
d
re
a
l
-
ti
m
e
b
l
o
o
d
v
e
in
d
e
tec
ti
o
n
s
y
ste
m
,
”
Bu
ll
e
ti
n
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s
,
v
o
l.
8
,
n
o
.
3
.
p
p
.
1
0
9
6
–
1
1
0
7
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/ee
i.
v
8
i
3
.
1
5
1
4
.
[5
5
]
M
.
A.
An
we
r,
S
.
M
.
S
h
a
re
e
f,
a
n
d
A.
M
.
Ali,
“
Ac
c
i
d
e
n
t
v
e
h
icle
t
y
p
e
s
c
las
sifica
ti
o
n
:
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
b
e
twe
e
n
d
iffere
n
t
d
e
e
p
lea
rn
i
n
g
m
o
d
e
ls,”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
2
1
,
n
o
.
3
.
p
p
.
1
4
7
4
–
1
4
8
4
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
2
1
.
i3
.
p
p
1
4
7
4
-
1
4
8
4
.
[5
6
]
A.
A.
Ala
b
d
e
l
A
b
a
ss
a
n
d
N.
P
.
Div
v
a
la,
“
An
e
n
h
a
n
c
e
d
OFDM
l
ig
h
t
we
ig
h
t
p
h
y
sic
a
l
lay
e
r
e
n
c
ry
p
ti
o
n
sc
h
e
m
e
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
1
1
,
n
o
.
3
.
p
p
.
2
1
7
8
–
2
1
9
0
,
2
0
2
1
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jec
e
.
v
1
1
i
3
.
p
p
2
1
7
8
-
2
1
9
0
.
[5
7
]
Ha
n
d
o
k
o
,
J.
H.
P
ra
tam
a
,
a
n
d
B.
W.
Y
o
h
a
n
e
s,
“
Traffic
sig
n
d
e
tec
ti
o
n
o
p
ti
m
iza
ti
o
n
u
sin
g
c
o
lo
r
a
n
d
sh
a
p
e
se
g
m
e
n
tatio
n
a
s
p
re
-
p
r
o
c
e
ss
in
g
sy
ste
m
,
”
T
e
lko
mn
ika
(T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l)
,
v
o
l.
1
9
,
n
o
.
1
.
p
p
.
1
7
3
–
1
8
1
,
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.
V1
9
I1
.
1
6
2
8
1
.
[5
8
]
M
.
A
h
m
e
d
,
M
.
S
a
ll
e
h
,
M
.
I.
C
h
a
n
n
a
,
a
n
d
M
.
F
.
R
o
h
a
n
i,
“
En
e
rg
y
e
fficie
n
t
r
o
u
ti
n
g
p
ro
t
o
c
o
ls
fo
r
UW
S
N:
A
re
v
iew
,
”
T
e
lko
mn
ika
(T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l.
1
5
,
n
o
.
1
.
p
p
.
2
1
2
–
2
1
9
,
2
0
1
7
,
d
o
i:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.
v
1
5
i1
.
4
7
0
6
.
[5
9
]
I.
S
.
Am
iri
a
n
d
S
.
E.
Ala
v
i,
“
S
e
v
e
ra
l
m
o
d
e
-
lo
c
k
e
d
p
u
lse
s
g
e
n
e
ra
ti
o
n
a
n
d
tran
sm
issio
n
o
v
e
r
s
o
li
t
o
n
b
a
se
d
o
p
ti
c
a
l
tran
sm
issio
n
li
n
k
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
,
n
o
.
2
.
p
p
.
2
8
8
–
2
9
3
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
1
.
i2
.
p
p
2
8
8
-
2
9
3
.
[6
0
]
T.
Ne
g
a
ra
,
I.
N.
S
.
Ja
y
a
,
C
.
Ku
sm
a
n
a
,
I.
M
a
n
su
r
,
a
n
d
N
.
A.
S
a
n
t
i,
“
Dro
n
e
ima
g
e
-
b
a
se
d
p
a
ra
m
e
ters
fo
r
a
ss
e
ss
in
g
th
e
v
e
g
e
tatio
n
c
o
n
d
it
i
o
n
th
e
re
c
lam
a
ti
o
n
s
u
c
c
e
ss
in
p
o
st
-
m
i
n
in
g
o
il
e
x
p
l
o
ra
ti
o
n
,
”
T
e
lko
mn
ika
(T
e
le
c
o
mm
u
n
ica
t
io
n
Co
mp
u
t
in
g
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l)
,
v
o
l.
1
9
,
n
o
.
1
.
p
p
.
1
0
5
–
1
1
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
2
9
2
8
/T
EL
KO
M
NIK
A.V
1
9
I
1
.
1
6
6
6
3
.
[6
1
]
H.
M
.
El
-
Ha
g
e
e
n
,
A.
M
.
Ala
twi,
a
n
d
A.
N.
Z.
Ra
sh
e
d
,
“
Las
e
r
m
e
a
su
re
d
ra
te
e
q
u
a
ti
o
n
s
with
v
a
rio
u
s
tran
sm
issio
n
c
o
d
e
rs
fo
r
o
p
ti
m
u
m
o
f
d
a
ta
tran
s
m
issio
n
e
rro
r
ra
tes
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
2
0
,
n
o
.
3
.
p
p
.
1
4
0
6
–
1
4
1
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/
ij
e
e
c
s.v
2
0
.
i3
.
p
p
1
4
0
6
-
1
4
1
2
.
[6
2
]
S
.
H.
Er
n
,
A.
H
u
o
n
g
,
W
.
M
.
Ha
fiza
h
Wan
M
a
h
m
u
d
,
a
n
d
X.
N
g
u
,
“
P
o
rta
b
le
a
n
d
wire
les
s
ima
g
in
g
o
f
d
o
rsa
l
h
a
n
d
v
e
in
,
”
I
n
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
9
,
n
o
.
2
.
p
p
.
6
9
3
–
7
0
0
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
9
.
i
2
.
p
p
6
9
3
-
7
0
0
.
[6
3
]
I.
S
.
Am
iri
,
A.
N.
Z.
Ra
sh
e
d
,
a
n
d
P
.
Yu
p
a
p
in
,
“
I
n
flu
e
n
c
e
o
f
d
e
v
ice
to
d
e
v
ice
in
terc
o
n
n
e
c
ti
o
n
e
lem
e
n
ts
o
n
th
e
sy
ste
m
b
e
h
a
v
io
r
a
n
d
sta
b
il
it
y
,
”
In
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
lec
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
1
8
,
n
o
.
2
.
p
p
.
8
4
3
–
8
4
7
,
2
0
2
0
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
8
.
i2
.
p
p
8
4
3
-
8
4
7
.
[6
4
]
I.
S
.
Am
iri
,
A.
N.
Z
.
Ra
sh
e
d
,
a
n
d
P
.
Yu
p
a
p
i
n
,
“
Z
S
h
a
p
e
d
li
k
e
re
s
o
n
a
to
r
with
c
ry
sta
l
i
n
th
e
p
re
se
n
c
e
o
f
flat
m
irro
r
b
a
se
d
sta
n
d
i
n
g
wa
v
e
ra
ti
o
fo
r
o
p
ti
c
a
l
a
n
te
n
n
a
sy
ste
m
s,”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
7
,
n
o
.
3
.
p
p
.
1
4
0
5
–
1
4
0
9
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
7
.
i3
.
p
p
1
4
0
5
-
1
4
0
9
.
[6
5
]
I.
S
.
Am
iri
a
n
d
A.
N.
Zak
i
Ra
s
h
e
d
,
“
S
imu
lati
v
e
stu
d
y
o
f
sim
p
l
e
rin
g
re
so
n
a
t
o
r
-
b
a
se
d
b
re
ws
ter
p
late
fo
r
p
o
we
r
sy
ste
m
o
p
e
ra
ti
o
n
sta
b
i
li
ty
,
”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
1
6
,
n
o
.
2
.
p
p
.
1
0
7
0
–
1
0
7
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
5
9
1
/i
jee
c
s.v
1
6
.
i
2
.
p
p
1
0
7
0
-
1
0
7
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.