I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
,
p
p
.
6
3
3
~
6
3
6
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
9
.
i3
.
p
p
6
3
3
-
636
633
J
o
ur
na
l ho
m
ep
a
ge
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Rev
iew
a
bo
ut
Va
rio
us Sa
tellit
e
I
ma
g
e Seg
m
en
tatio
n
Sh
a
bir A
h
m
ed
M
ir
,
T
.
P
a
d
m
a
.
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
A
M
ET
Un
iv
e
rsit
y
,
Ch
e
n
n
a
i,
I
n
d
ia
De
p
a
rtme
n
t
o
f
c
o
m
p
u
ter A
p
p
li
c
a
io
n
s,
S
o
n
a
Co
ll
e
g
e
o
f
T
e
c
h
n
o
lo
g
y
,
S
a
lem
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
30
,
2
0
1
7
R
ev
i
s
ed
J
an
15
,
2
0
1
8
A
cc
ep
ted
Feb
4
,
2
0
1
8
In
th
is
p
a
p
e
r,
a
re
v
ie
w
a
b
o
u
t
d
i
ff
e
r
e
n
t
a
lg
o
rit
h
m
is
p
ro
p
o
se
d
e
f
ficie
n
tl
y
to
se
g
m
e
n
t
th
e
sa
telli
te
i
m
a
g
e
s.
S
e
g
m
e
n
tatio
n
o
f
I
m
a
g
e
is
o
n
e
o
f
th
e
p
ro
m
isin
g
a
n
d
a
c
ti
v
e
r
e
se
a
r
c
h
e
s
in
re
c
e
n
t
y
e
a
r
s
.
A
s
li
tera
tu
re
p
ro
v
e
th
a
t
re
g
io
n
se
g
m
e
n
tatio
n
w
il
l
p
r
o
d
u
c
e
b
e
tt
e
r
re
su
lt
s.
Hu
m
a
n
v
isu
a
l
p
e
rc
e
p
ti
o
n
is
m
o
re
e
ffe
c
ti
v
e
th
a
n
a
n
y
m
a
c
h
in
e
v
isio
n
sy
ste
m
s
f
o
r
e
x
trac
ti
n
g
se
m
a
n
ti
c
in
f
o
rm
a
ti
o
n
f
ro
m
i
m
a
g
e
.
T
h
e
re
a
re
v
a
rio
u
s
se
g
m
e
n
tatio
n
tec
h
n
iq
u
e
s
a
re
a
v
a
il
a
b
le.
F
u
z
z
y
C
M
e
a
n
s
(F
C
M
),
Ex
p
e
c
tatio
n
M
in
im
iza
ti
o
n
(
EM
)
a
n
d
K
-
M
e
a
n
s
a
lg
o
rit
h
m
is
d
e
v
e
lo
p
e
d
t
o
e
stim
a
te
p
a
ra
m
e
ters
o
f
th
e
p
rio
r
p
ro
b
a
b
il
it
ies
a
n
d
l
ik
e
li
h
o
o
d
p
ro
b
a
b
il
it
ies
.
F
i
n
a
ll
y
P
e
a
k
S
ig
n
a
l
to
No
ise
Ra
ti
o
(P
S
NR) i
s ca
lcu
late
d
f
o
r
a
ll
t
h
e
a
l
g
o
rit
h
m
s an
d
re
v
ie
w
e
d
.
.
K
ey
w
o
r
d
s
:
EM
F
CM
K
-
m
e
a
n
s
P
S
NR
S
a
telli
te Im
a
g
e
se
g
m
e
n
tatio
n
Co
p
y
rig
h
t
©
2
0
1
8
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sh
ab
ir
A
h
m
ed
Mir
,
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
,
A
ME
T
Un
i
v
er
s
it
y
,
C
h
en
n
ai,
I
n
d
ia.
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
s
tu
d
y
a
n
d
t
h
e
e
x
tr
ac
tio
n
o
f
t
h
e
d
i
f
f
er
e
n
t
e
le
m
e
n
t
s
th
at
co
m
p
o
s
e
a
n
i
m
a
g
e
c
o
n
s
tit
u
te
a
f
u
n
d
a
m
en
ta
l
task
i
n
th
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
an
d
ch
ai
n
an
a
l
y
s
is
.
I
n
f
ac
t,
t
h
e
n
ec
es
s
it
y
to
r
ep
lace
th
e
h
u
m
an
o
b
s
er
v
er
b
y
a
co
m
p
u
ter
f
o
r
i
m
ag
e
an
al
y
s
is
w
as
i
n
t
h
e
o
r
ig
i
n
o
f
th
e
d
ev
elo
p
m
en
t o
f
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
2.
B
ACK
G
RO
UND
Su
r
v
e
y
ab
o
u
t
a
u
to
m
atic
d
ete
ctio
n
&
c
lass
if
icatio
n
o
f
co
m
p
u
ter
v
i
s
io
n
is
p
r
esen
ted
i
n
[
1
]
.
B
ias,
tire
d
n
ess
a
n
d
lo
s
s
o
f
in
ter
e
s
t
ar
e
th
e
v
ar
io
u
s
f
ac
to
r
s
in
f
lu
en
ce
t
h
e
d
ec
is
io
n
-
m
a
k
in
g
p
o
w
er
o
f
h
u
m
a
n
-
in
s
p
ec
to
r
s
.
Di
f
f
er
e
n
t
r
ice
g
r
ai
n
s
ar
e
class
if
ied
a
n
d
id
en
ti
f
ie
d
au
to
m
atica
ll
y
u
s
i
n
g
m
ac
h
i
n
e
v
is
io
n
s
y
s
te
m
s
o
th
ese
j
o
b
s
n
ee
d
au
to
m
at
io
n
.
Au
to
m
a
ted
s
ep
ar
atio
n
o
f
to
u
c
h
in
g
g
r
ai
n
s
i
n
d
ig
ita
l
i
m
a
g
es
o
f
th
i
n
s
ec
tio
n
s
is
d
is
c
u
s
s
ed
i
n
[
2
]
.
T
o
u
ch
in
g
g
r
ai
n
se
ctio
n
s
ar
e
s
ep
ar
ated
u
s
i
n
g
c
o
m
p
u
ter
alg
o
r
it
h
m
i
n
b
in
ar
y
i
m
ag
e
s
o
f
g
r
a
n
u
lar
m
ater
ial.
C
h
ar
ac
ter
is
tic
s
h
ar
p
co
n
tact
w
ed
g
e
s
o
f
to
u
c
h
in
g
g
r
ain
s
ec
tio
n
s
in
o
u
tli
n
e
ar
e
d
et
ec
ted
u
s
i
n
g
th
is
al
g
o
r
ith
m
.
I
f
t
h
e
an
g
le
is
s
m
a
ller
th
an
u
s
er
d
ef
in
ed
t
h
r
esh
o
ld
v
a
lu
e,
in
t
er
s
ec
tio
n
w
i
ll c
r
ea
te
af
t
er
ch
ec
k
i
n
g
.
Seg
m
en
tatio
n
tec
h
n
iq
u
es
a
n
d
ag
g
r
eg
a
te
i
m
a
g
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
f
o
r
ag
g
r
e
g
ate
s
ize
an
d
s
h
ap
e
ev
alu
a
tio
n
is
d
escr
ib
ed
in
[
3
]
.
E
n
tit
y
ag
g
r
e
g
ate
p
ar
ticle
s
h
a
p
e
an
d
s
ize
p
r
o
p
er
ties
ar
e
an
al
y
ze
d
an
d
ex
tr
ac
ted
u
s
i
n
g
i
m
ag
e
p
r
o
ce
s
s
in
g
a
n
d
a
cq
u
is
itio
n
tec
h
n
iq
u
es.
Dig
ital
s
in
g
le
len
s
r
ef
lex
ca
m
er
a
i
s
u
s
ed
to
ca
p
tu
r
e
th
e
ag
g
r
e
g
ated
i
m
a
g
es
a
n
d
th
ese
s
eg
m
e
n
ted
i
m
a
g
es
ar
e
f
ed
in
t
o
th
e
v
alid
ated
u
n
i
v
er
s
i
t
y
to
c
alcu
late
t
h
e
p
ar
ticle
s
h
ap
e
an
d
s
ize
f
o
r
f
lat
a
n
d
elo
n
g
ated
r
atio
.
I
m
ag
e
p
r
o
ce
s
s
in
g
b
ased
r
ice
g
r
ad
in
g
is
ex
p
lai
n
ed
i
n
[
4
]
.
L
en
g
t
h
,
s
h
ap
e,
co
lo
r
,
in
ter
n
al
d
am
a
g
e
o
f
r
ice
is
th
e
f
ea
t
u
r
es
u
s
ed
to
d
if
f
er
en
tia
te
th
e
r
ice
g
r
ad
e
u
s
i
n
g
m
ac
h
i
n
e
v
i
s
io
n
.
De
g
r
ee
lev
el
o
f
r
ice
is
an
al
y
ze
d
an
d
d
if
f
er
e
n
tiated
b
y
h
is
to
g
r
a
m
,
R
GB
co
lo
r
m
o
d
el
an
d
e
d
g
e
d
etec
tio
n
etc.
Ma
ch
i
n
e
v
is
io
n
s
y
s
te
m
b
ased
ef
f
icien
t
m
et
h
o
d
f
o
r
q
u
alit
y
a
n
al
y
s
i
s
o
f
r
ice
is
p
r
esen
ted
i
n
[
5
]
.
Ma
ch
in
e
v
i
s
io
n
i
s
u
s
ed
to
ass
es
s
th
e
q
u
a
lit
y
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
6
3
3
–
6
3
6
634
th
e
I
n
d
ia
n
b
as
m
ati
Or
y
za
s
ati
v
a
L
v
ar
iet
y
r
ice
an
d
Or
y
za
s
a
tiv
a
L
r
ice
s
ize
i
s
ca
lc
u
lated
u
s
in
g
m
ac
h
in
e
v
i
s
io
n
w
it
h
c
h
alk
y
d
etec
tio
n
a
n
d
b
r
o
k
en
r
ice.
C
h
al
k
i
n
es
s
i
n
R
ice:
P
o
ten
t
i
al
f
o
r
e
v
alu
a
tio
n
w
it
h
i
m
a
g
e
an
al
y
s
i
s
i
s
d
is
c
u
s
s
ed
i
n
[
6
]
.
I
m
a
g
e
in
f
o
r
m
atio
n
p
r
o
ce
s
s
i
n
g
is
e
v
a
lu
ated
ef
f
ec
ti
v
el
y
in
t
h
i
s
m
et
h
o
d
w
ith
i
n
e
x
p
en
s
iv
e
co
m
p
u
te
r
an
d
ch
alk
i
n
es
s
is
ca
teg
o
r
ized
an
d
m
ea
s
u
r
ed
u
s
i
n
g
d
i
g
ital i
m
a
g
e
s
ca
n
n
er
.
T
h
en
m
et
h
o
d
’
s
f
ea
s
ib
ilit
y
is
as
s
es
s
ed
.
Satellite
an
d
m
ed
ical
i
m
ag
e
s
eg
m
e
n
tat
io
n
b
ased
o
n
m
u
ltip
l
e
k
er
n
el
f
u
zz
y
c
-
Me
a
n
s
al
g
o
r
ith
m
w
i
t
h
AL
S
m
et
h
o
d
is
e
x
p
lain
ed
i
n
[
7
]
.
Mu
ltip
le
k
er
n
el
f
u
zz
y
c
-
m
ea
n
s
i
s
u
s
ed
to
g
e
n
er
ate
in
itial
co
n
to
u
r
c
u
r
v
e
d
u
r
in
g
t
h
e
cu
r
v
e
as
leak
i
n
g
at
th
e
b
o
u
n
d
ar
y
.
I
n
i
tial
co
n
to
u
r
cu
r
v
e
i
s
g
en
er
ated
u
s
i
n
g
m
u
l
ti
p
le
k
er
n
el
f
u
zz
y
c
-
m
ea
n
s
d
u
r
in
g
t
h
e
c
u
r
v
e
p
r
o
p
ag
atio
n
as
leak
i
n
g
at
th
e
b
o
u
n
d
ar
y
.
Fi
n
all
y
d
i
f
f
er
e
n
t
in
f
o
r
m
at
io
n
’
s
ar
e
co
m
b
i
n
ed
u
s
i
n
g
m
u
ltip
le
k
er
n
el
f
u
zz
y
c
-
m
ea
n
s
i
n
s
e
g
m
e
n
tatio
n
al
g
o
r
it
h
m
.
An
o
u
tco
m
e
o
f
p
er
io
d
ized
s
m
al
l
s
id
e
g
a
m
es
w
it
h
a
n
d
w
it
h
o
u
t
m
e
n
tal
i
m
ag
er
y
o
n
p
la
y
i
n
g
ab
ilit
y
a
m
o
n
g
i
n
ter
co
lleg
iate
le
v
el
s
o
c
ce
r
p
lay
er
s
is
al
s
o
d
escr
ib
es
th
at
[
8
]
.
I
m
a
g
e
S
u
p
er
R
eso
l
u
tio
n
Usi
n
g
W
av
elet
T
r
an
s
f
o
r
m
atio
n
B
ased
Gen
etic
Alg
o
r
it
h
m
ex
p
lain
ed
i
n
[
9
]
.
A
n
in
teg
r
ate
d
in
ter
ac
tiv
e
tec
h
n
iq
u
e
f
o
r
i
m
ag
e
s
eg
m
e
n
tatio
n
u
s
in
g
s
tac
k
b
ased
s
ee
d
ed
r
eg
io
n
g
r
o
w
i
n
g
an
d
t
h
r
es
h
o
ld
in
g
m
et
h
o
d
is
d
is
cu
s
s
ed
in
[
1
0
]
.
Fo
r
an
al
y
z
in
g
t
h
e
o
p
ti
m
al
p
er
f
o
r
m
an
ce
o
f
p
est
i
m
a
g
e
s
eg
m
e
n
tatio
n
is
d
is
c
u
s
s
ed
a
s
in
[
1
1
]
.
I
m
ag
e
s
e
g
m
en
tatio
n
b
ased
o
n
d
o
u
b
l
y
tr
u
n
ca
ted
g
en
er
alize
d
L
ap
lace
m
i
x
tu
r
e
m
o
d
el
an
d
k
m
ea
n
s
cl
u
s
ter
i
n
g
i
s
d
is
c
u
s
s
ed
in
[
1
2
]
.
3.
T
H
E
P
RO
B
L
E
M
Am
o
n
g
t
h
e
v
ar
io
u
s
t
y
p
e
s
o
f
s
eg
m
e
n
tat
io
n
m
eth
o
d
s
t
h
er
e
m
a
y
b
e
m
o
r
e
p
r
o
b
lem
s
o
cc
u
r
r
ed
in
d
u
r
in
g
th
e
s
e
g
m
en
tatio
n
o
f
th
e
s
atelli
te
i
m
a
g
es.
So
m
e
o
f
t
h
e
p
r
o
b
lem
s
ar
e
li
k
e
d
ata
lo
s
s
,
m
i
s
-
s
e
g
m
en
tatio
n
,
etc.
So
i
n
o
r
d
er
t
o
o
v
er
co
m
e
t
h
is
w
e
w
il
l
b
e
s
tatin
g
s
o
m
e
o
f
th
e
s
a
tellit
e
i
m
ag
e
s
eg
m
e
n
tatio
n
m
et
h
o
d
s
ar
e
d
is
cu
s
s
ed
.
4.
P
RO
P
O
SE
D
SO
L
UT
I
O
NS
4
.
1
.
E
x
pect
a
t
io
n
M
a
x
i
m
iza
t
i
o
n
An
i
ter
ativ
e
m
eth
o
d
i
s
ca
l
led
as
E
M
al
g
o
r
ith
m
to
d
is
co
v
e
r
m
a
x
i
m
u
m
li
k
eli
h
o
o
d
o
r
m
a
x
i
m
u
m
a
p
o
s
ter
io
r
i
p
ar
am
eter
s
es
ti
m
a
t
io
n
in
s
tati
s
tical
m
o
d
els.
E
x
p
ec
tatio
n
s
tep
is
p
er
f
o
r
m
in
g
b
y
E
M
i
ter
atio
n
alter
n
ati
v
el
y
a
n
d
it
cr
ea
tes
a
f
u
n
ct
io
n
u
s
i
n
g
c
u
r
r
en
t
e
s
ti
m
at
e
o
f
th
e
lo
g
-
l
ik
eli
h
o
o
d
f
o
r
th
e
m
ax
i
m
izatio
n
s
tep
an
d
p
ar
am
eter
s
.
Fin
al
l
y
late
n
t
v
ar
iab
le
d
is
tr
ib
u
tio
n
is
d
eter
m
i
n
ed
b
y
t
h
ese
est
i
m
a
ted
p
ar
a
m
eter
s
i
n
th
e
n
e
x
t
ex
p
ec
tatio
n
s
tep
.
T
h
e
iter
atio
n
o
f
E
M
alter
n
ate
s
b
et
w
ee
n
p
er
f
o
r
m
i
n
g
a
n
E
x
p
ec
tatio
n
(
E
)
s
tep
,
w
h
ich
cr
ea
tes
a
f
u
n
ctio
n
f
o
r
th
e
ex
p
ec
tat
io
n
o
f
t
h
e
l
o
g
-
li
k
eli
h
o
o
d
,
ev
al
u
ated
u
s
i
n
g
t
h
e
c
u
r
r
en
t
esti
m
ate
f
o
r
t
h
e
p
ar
a
m
eter
s
,
an
d
m
ax
i
m
izatio
n
(
M)
s
tep
,
w
h
ic
h
co
m
p
u
te
s
p
ar
a
m
eter
s
m
ax
i
m
izi
n
g
t
h
e
p
r
ed
ictab
le
lo
g
-
li
k
elih
o
o
d
f
o
u
n
d
o
n
t
h
e
E
s
tep
.
Dis
tr
ib
u
tio
n
o
f
th
e
la
te
n
t v
ar
iab
les i
s
d
eter
m
i
n
ed
b
y
u
s
i
n
g
th
i
s
p
ar
a
m
eter
in
t
h
e
n
e
x
t E
s
tep
(
Fig
u
r
e
1
)
.
(
a)
(
b
)
Fig
u
r
e
1
.
(
a)
Or
ig
in
al
i
m
a
g
e
a
n
d
(
b
)
Seg
m
e
n
ted
I
m
a
g
e
u
s
in
g
E
M
alg
o
r
ith
m
4
.
2
.
F
uzzy
C
M
ea
ns
T
h
e
m
et
h
o
d
o
f
clu
s
ter
in
g
w
h
i
ch
allo
w
s
o
n
e
p
iece
o
f
d
ata
to
b
elo
n
g
to
t
w
o
o
r
m
o
r
e
clu
s
ter
s
is
ca
lled
FC
M.
I
t
is
m
a
x
i
m
u
m
u
s
ed
f
o
r
p
atter
n
r
ec
o
g
n
itio
n
.
C
lu
s
ter
an
al
y
s
i
s
in
v
o
lv
e
s
ass
i
g
n
in
g
d
at
a
p
o
in
ts
to
clu
s
ter
s
(
also
ca
lled
b
u
ck
et
s
,
b
in
s
,
o
r
cla
s
s
es),
o
r
h
o
m
o
g
e
n
eo
u
s
clas
s
es,
s
u
c
h
t
h
at
ite
m
s
i
n
t
h
e
s
a
m
e
class
o
r
cl
u
s
ter
ar
e
as si
m
ilar
as p
o
s
s
ib
le,
w
h
ile
it
e
m
s
b
elo
n
g
i
n
g
to
d
if
f
er
e
n
t c
la
s
s
es a
r
e
as d
is
s
i
m
ilar
as p
o
s
s
ib
le
(
Fig
u
r
e
2
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
R
ev
iew
a
b
o
u
t V
a
r
io
u
s
S
a
tellite I
ma
g
e
S
e
g
men
ta
tio
n
(
S
h
a
b
ir
A
h
med
Mir
)
635
(
a)
(
b
)
Fig
u
r
e
2
.
(
a)
Or
ig
i
n
al
i
m
a
g
e
a
n
d
(
b
)
Seg
m
e
n
ted
I
m
a
g
e
u
s
in
g
FC
M
al
g
o
r
ith
m
4
.
3
.
K
-
M
ea
ns
Clus
t
er
ing
Vec
to
r
q
u
an
tizatio
n
m
et
h
o
d
is
also
ca
lled
as
k
-
m
ea
n
s
cl
u
s
t
er
in
g
,
o
r
ig
i
n
all
y
f
r
o
m
s
i
g
n
al
p
r
o
ce
s
s
in
g
,
th
at
i
s
ad
m
ir
ed
f
o
r
clu
s
ter
s
t
u
d
y
i
n
d
ata
m
in
i
n
g
.
K
-
m
ea
n
s
clu
s
ter
in
g
i
s
to
p
an
el
n
a
n
n
o
tatio
n
s
i
n
to
k
cl
u
s
ter
s
i
n
w
h
ic
h
ea
ch
o
b
s
er
v
atio
n
b
elo
n
g
s
to
th
e
cl
u
s
ter
w
it
h
t
h
e
b
o
r
d
er
in
g
m
ea
n
,
h
elp
in
g
as
a
p
r
o
to
ty
p
e
o
f
t
h
e
clu
s
ter
.
T
h
is
o
u
tco
m
e
i
n
a
p
ar
titi
o
n
in
g
o
f
th
e
d
ata
s
p
ac
e
in
to
Vo
r
o
n
o
i c
ells
(
Fig
u
r
e
3
)
.
(
a)
(
b
)
Fig
u
r
e
3
.
(
a)
Or
ig
in
al
i
m
a
g
e
a
n
d
(
b
)
Seg
m
e
n
ted
I
m
a
g
e
u
s
in
g
K
-
Me
a
n
s
al
g
o
r
ith
m
5.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
R
ev
ie
w
o
f
s
e
g
m
e
n
ti
n
g
t
h
e
s
at
ellite
i
m
ag
e
u
s
i
n
g
F
C
M,
E
M
an
d
K
-
Me
a
n
s
is
p
r
ese
n
ted
in
t
h
is
p
ap
er
.
Fro
m
th
e
i
n
v
e
s
ti
g
atio
n
al
r
es
u
lt
s
th
e
i
m
a
g
e
s
eg
m
e
n
tatio
n
u
s
in
g
t
h
e
p
r
o
p
o
s
ed
m
eth
o
d
w
as
f
o
u
n
d
to
b
e
m
o
r
e
v
is
u
all
y
te
m
p
ti
n
g
t
h
a
n
o
th
er
e
x
is
t
in
g
al
g
o
r
ith
m
s
.
Fig
u
r
e
1
,
2
,
3
s
h
o
w
s
th
e
p
r
o
p
o
s
ed
s
eg
m
en
ted
i
m
a
g
e
u
s
i
n
g
E
M,
FC
M
an
d
K
-
Me
a
n
s
al
g
o
r
ith
m
tec
h
n
iq
u
e.
T
h
e
r
esu
lts
s
h
o
w
th
a
t
th
i
s
m
eth
o
d
i
s
a
v
er
y
e
f
f
icie
n
t
o
p
tim
izatio
n
a
n
d
o
b
tain
ed
P
SNR
v
al
u
e
i
s
s
h
o
w
n
i
n
T
ab
le
1
.
T
ab
le
1
.
C
o
m
p
ar
is
o
n
o
f
Dif
f
er
en
t te
ch
n
iq
u
es
RE
F
E
R
E
NC
E
S
[1
]
Da
lj
e
e
t
K.
A
u
to
m
a
ti
c
d
e
tec
ti
o
n
&
c
las
si
f
ica
ti
o
n
o
f
ric
e
u
sin
g
c
o
m
p
u
ter
v
isio
n
-
a
su
rv
e
y
,
In
ter
n
a
ti
o
n
a
l
jo
u
r
n
a
l
o
f
in
n
o
v
a
ti
v
e
re
se
a
rc
h
in
sc
ien
c
e
,
e
n
g
in
e
e
rin
g
a
n
d
tec
h
n
o
lo
g
y
.
2
0
1
5
;
4
-
9.
[2
]
V
a
n
d
e
n
Be
rg
EH,
M
e
e
ste
rs
AG
CA
,
Ke
n
ter
J
A
M
,
S
c
h
lag
e
r
W
.
Au
to
ma
ted
se
p
a
r
a
ti
o
n
o
f
t
o
u
c
h
i
n
g
g
ra
in
s in
d
ig
i
ta
l
ima
g
e
s o
f
th
i
n
se
c
ti
o
n
s,
C
o
mp
u
ter
s
&
g
e
o
sc
ien
c
e
s.
2
0
0
2
;
2
8
(2
):
1
7
9
-
1
9
0
.
[3
]
M
o
a
v
e
n
i
M
,
W
a
n
g
S
,
Ha
rt
J,
T
u
tu
m
lu
e
r
E,
A
h
u
ja
N.
A
g
g
re
g
a
te
size
a
n
d
s
h
a
p
e
e
v
a
lu
a
ti
o
n
u
si
n
g
se
g
me
n
t
a
ti
o
n
tec
h
n
iq
u
e
s
a
n
d
a
g
g
re
g
a
te
im
a
g
e
p
ro
c
e
ss
in
g
a
lg
o
rith
ms
,
Re
v
ise
d
M
a
n
u
sc
ri
p
t
1
3
-
4
1
6
7
f
o
r
A
n
n
u
a
l
M
e
e
ti
n
g
Co
m
p
e
n
d
iu
m
o
f
P
a
p
e
rs,
2
0
1
3
.
M
e
t
h
o
d
U
se
d
P
S
N
R
R
a
n
g
e
EM
3
8
.
6
5
F
C
M
3
6
.
2
3
K
-
M
e
a
n
s
4
0
.
5
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
6
3
3
–
6
3
6
636
[4
]
T
a
h
ir
W
P
N,
Hu
ss
in
N,
Htik
e
ZZ
,
Na
in
g
W
YN
.
Rice
g
ra
d
in
g
u
sin
g
im
a
g
e
p
ro
c
e
ss
in
g
,
AR
PN
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s.
2
0
1
5
;
1
0
(2
1
);
1
-
9.
[5
]
Birl
a
R,
Ch
a
u
h
a
n
A
P
S
.
A
n
Eff
i
c
ien
t
M
e
th
o
d
f
o
r
Qu
a
li
ty
A
n
a
l
y
sis
o
f
Rice
Us
in
g
M
a
c
h
in
e
V
isio
n
S
y
ste
m
.
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
s in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
.
2
0
1
5
;
6
(3
):
5
-
9.
[6
]
Yo
sh
io
k
a
Y,
Iw
a
ta
H,
T
a
b
a
ta
M
,
Nin
o
m
iy
a
S
,
Oh
sa
w
a
R.
Ch
a
lk
i
n
e
ss
in
rice
:
p
o
ten
ti
a
l
f
o
r
e
v
a
lu
a
ti
o
n
w
it
h
im
a
g
e
a
n
a
ly
sis
,
Cro
p
S
c
ien
c
e
.
2
0
0
7
;
4
7
(
5
),
2
1
1
3
-
2
1
2
0
.
[7
]
Yu
g
a
n
d
e
r
P
,
S
h
e
sh
a
g
iri
BJ,
S
u
n
a
n
d
a
K,
S
u
sm
it
h
a
E.
M
u
lt
ip
le
k
e
rn
e
l
f
u
z
z
y
C
-
m
e
a
n
s
a
lg
o
rit
h
m
w
it
h
AL
S
m
e
th
o
d
f
o
r
sa
telli
te
a
n
d
m
e
d
ica
l
i
m
a
g
e
s
e
g
m
e
n
tatio
n
,
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
De
v
ice
s,
Circ
u
it
s
a
n
d
S
y
ste
ms
.
2
0
1
2
;
2
4
4
-
2
4
8
.
[8
]
Ku
m
a
r
A
M
,
A
n
o
u
tco
m
e
o
f
p
e
r
io
d
ize
d
sm
a
ll
si
d
e
g
a
m
e
s
w
it
h
a
n
d
w
it
h
o
u
t
m
e
n
tal
im
a
g
e
r
y
o
n
p
lay
in
g
a
b
il
it
y
a
m
o
n
g
in
terc
o
ll
e
g
iate
lev
e
l
so
c
c
e
r
p
lay
e
rs.
In
d
ia
n
J
o
u
r
n
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
.
2
0
1
5
;
8
(3
6
):
1
5
-
2
1
.
[9
]
P
a
n
d
a
S
S
,
Je
n
a
G
,
I
m
a
g
e
S
u
p
e
r
Re
so
lu
ti
o
n
Us
in
g
W
a
v
e
l
e
t
T
r
a
n
sf
o
r
m
a
ti
o
n
Ba
se
d
G
e
n
e
ti
c
A
lg
o
r
it
h
m
.
In
Co
m
p
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
in
Da
ta
M
in
in
g
.
2
0
1
6
;
2
:
3
5
5
-
3
6
1
.
S
p
rin
g
e
r
In
d
ia.
[1
0
]
Ho
re
S
,
Ch
a
k
ra
b
o
rty
S
,
Ch
a
tt
e
rjee
S
,
De
y
N,
As
h
o
u
r
A
S
,
V
a
n
Ch
u
n
g
L
,
L
e
D
N.
A
n
In
teg
ra
t
e
d
In
tera
c
ti
v
e
T
e
c
h
n
iq
u
e
f
o
r
Im
a
g
e
S
e
g
m
e
n
tati
o
n
u
sin
g
S
tac
k
b
a
se
d
S
e
e
d
e
d
R
e
g
io
n
G
r
o
w
in
g
a
n
d
T
h
re
sh
o
ld
in
g
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
t
e
r E
n
g
i
n
e
e
rin
g
.
2
0
1
6
;
6
(
6
):
2
7
7
3
-
2
7
7
8
.
[1
1
]
S
a
n
g
a
ri
S
,
S
a
ra
s
w
a
d
y
D.
A
n
a
l
y
z
in
g
th
e
Op
ti
m
a
l
P
e
rf
o
r
m
a
n
c
e
o
f
P
e
st
Im
a
g
e
S
e
g
m
e
n
tatio
n
u
si
n
g
No
n
L
in
e
a
r
Ob
jec
ti
v
e
As
se
s
s
m
e
n
ts.
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
En
g
i
n
e
e
rin
g
.
2
0
1
6
;
6
(
6
):
2
7
8
9
-
2
7
9
3
.
[1
2
]
J
y
o
th
irm
a
y
i
T
,
Ra
o
KS,
Ra
o
P
S
,
S
a
ty
a
n
a
ra
y
a
n
a
C.
I
m
a
g
e
S
e
g
m
e
n
tatio
n
Ba
se
d
o
n
Do
u
b
ly
T
ru
n
c
a
ted
G
e
n
e
ra
li
z
e
d
L
a
p
lac
e
M
i
x
tu
re
M
o
d
e
l
a
n
d
K
M
e
a
n
s
Clu
ste
rin
g
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
.
2
0
1
6
;
6
(5
):
2
1
8
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.