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
.
1
,
J
an
u
ar
y
201
8
,
p
p
.
2
4
3
~
2
48
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i1
.
p
p
2
4
3
-
2
48
243
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
Co
ntent
Ba
sed I
m
a
g
e Re
trieva
l U
sing
La
cuna
rity a
nd Colo
r
M
o
m
ents
o
f
S
k
i
n
Disea
ses
I
G
u
s
t
i A
y
u T
riw
a
y
un
i
1
,
I
K
et
ut
G
ede
Da
r
m
a
P
utr
a
2
,
I
P
utu
Ag
us
E
k
a
P
ra
t
a
m
a
3
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
De
p
a
rt
m
e
n
t,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Ud
a
y
a
n
a
Un
iv
e
rsit
y
Ka
m
p
u
s Un
u
d
,
B
u
k
it
Jim
b
a
ra
n
,
Ba
li
,
In
d
o
n
e
sia
-
8
0
3
6
1
1
telp
/f
a
x
:
(0
3
6
1
)
7
0
1
9
5
4
,
7
0
4
8
4
5
/
(0
3
6
1
)
7
0
1
9
0
7
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
11
,
2
0
1
7
R
ev
i
s
ed
No
v
2
7
,
2
0
1
7
A
cc
ep
ted
Dec
1
0
,
2
0
1
7
T
h
e
re
se
a
rc
h
c
o
n
d
u
c
ted
c
o
n
t
rib
u
ted
in
t
h
e
f
o
rm
o
f
CBIR
a
p
p
li
c
a
ti
o
n
w
h
ich
w
a
s
d
e
v
e
lo
p
e
d
u
sin
g
tex
tu
re
a
n
d
c
o
l
o
r
f
e
a
tu
re
e
x
trac
ti
o
n
in
se
a
rc
h
in
g
th
e
c
o
n
ten
ts
in
f
o
rm
a
ti
o
n
o
f
a
n
o
b
jec
t
o
f
s
k
in
d
ise
a
se
i
m
a
g
e
.
T
h
e
tex
tu
re
d
f
e
a
tu
re
is
e
x
trac
ted
u
sin
g
L
a
c
u
n
a
rit
y
,
w
h
il
e
f
o
r
c
o
lo
r
f
e
a
tu
re
e
x
trac
ti
o
n
u
sin
g
Co
lo
r
M
o
m
e
n
ts
a
s
w
e
ll
a
s
a
c
o
m
b
in
a
ti
o
n
o
f
b
o
t
h
m
e
th
o
d
s.
T
h
e
re
su
lt
s
o
f
c
o
lo
r
c
h
a
ra
c
teristic
e
x
tra
c
ti
o
n
tes
t
u
sin
g
Co
lo
r
M
o
m
e
n
ts
M
e
th
o
d
y
ield
e
d
im
a
g
e
s
c
o
rre
sp
o
n
d
in
g
to
1
0
0
%
sim
il
a
rit
y
p
e
rc
e
n
tag
e
s
a
n
d
e
x
p
e
ri
m
e
n
tatio
n
o
f
te
x
tu
re
c
h
a
ra
c
teristic
e
x
tra
c
ti
o
n
u
si
n
g
L
a
c
u
n
a
rit
y
M
e
th
o
d
y
ield
e
d
im
a
g
e
s
c
o
rre
sp
o
n
d
in
g
to
a
p
e
rc
e
n
tag
e
o
f
su
it
a
b
il
it
y
o
f
2
5
%
,
f
o
ll
o
w
e
d
b
y
a
c
o
m
b
in
e
d
tes
t
o
f
b
o
th
m
e
th
o
d
s
a
n
d
t
h
e
n
o
rm
a
li
z
a
ti
o
n
p
ro
c
e
ss
p
ro
d
u
c
e
s
i
m
a
g
e
s
c
o
rre
sp
o
n
d
in
g
t
o
a
p
e
rc
e
n
tag
e
o
f
c
o
n
f
o
rm
it
y
o
f
6
0
%
.
K
ey
w
o
r
d
s
:
C
o
lo
r
Mo
m
e
n
t
s
C
o
n
te
n
t
B
ased
I
m
ag
e
R
etr
iev
al
I
m
ag
e
R
etr
iev
a
L
ac
u
n
ar
it
y
Sk
i
n
d
is
ea
s
e
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
:
I
Gu
s
ti
Ay
u
T
r
i
w
a
y
u
n
i
,
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
Dep
a
r
t
m
en
t,
Facu
l
t
y
o
f
E
n
g
in
ee
r
i
n
g
,
Ud
a
y
a
n
a
Un
i
v
er
s
i
t
y
Ka
m
p
u
s
Un
u
d
,
B
u
k
it J
i
m
b
ar
an
,
B
ali,
I
n
d
o
n
esia
-
803611
telp
/f
a
x
: (
0
3
6
1
)
7
0
1
9
5
4
,
7
0
4
8
4
5
/ (
0
3
6
1
)
7
0
1
9
0
7
E
m
ail:
a
y
u
tr
i
w
a
y
u
n
i@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
d
ev
elo
p
m
e
n
t
o
f
i
n
f
o
r
m
ati
o
n
s
y
s
te
m
s
tec
h
n
o
lo
g
y
i
n
th
e
p
r
esen
t
ti
m
e
m
a
k
es
th
e
h
u
m
a
n
n
ee
d
f
o
r
in
f
o
r
m
atio
n
co
n
ti
n
u
es
to
i
n
cr
e
ase.
Su
c
h
i
n
f
o
r
m
atio
n
i
s
n
o
t
li
m
ited
to
n
o
n
-
v
is
u
al
d
ata
(
te
x
t
an
d
v
o
ice)
,
b
u
t
i
n
v
is
u
al
f
o
r
m
(
i
m
ag
e
an
d
v
id
e
o
)
.
A
cc
o
r
d
in
g
to
r
esear
c
h
ti
t
led
"
A
R
ev
iew
P
a
p
er
o
n
C
o
n
ten
t
B
a
s
ed
I
ma
g
e
R
etri
ev
a
l
"
,
I
m
a
g
e
R
etr
ie
v
al
is
a
tech
n
iq
u
e
u
s
ed
to
s
ea
r
ch
t
h
e
i
m
a
g
e
o
f
a
d
atab
ase
th
at
h
a
s
s
i
m
ilar
ch
ar
ac
ter
is
tic
s
o
f
th
e
i
m
a
g
e
q
u
er
y
.
E
ac
h
i
m
ag
e
h
a
s
u
n
iq
u
e
lo
w
-
le
v
el
f
ea
tu
r
e
in
f
o
r
m
at
io
n
.
E
x
a
m
p
le
s
o
f
lo
w
-
lev
el
f
ea
t
u
r
es
ar
e
co
lo
r
,
tex
t
u
r
e,
s
h
ap
e,
a
n
d
s
o
o
n
.
T
h
ese
f
ea
tu
r
es
ar
e
f
u
r
t
h
er
co
m
p
ar
ed
b
etw
ee
n
t
h
e
i
m
a
g
e
s
i
n
th
e
i
m
ag
e
r
etr
ie
v
al
s
y
s
te
m
.
T
h
er
e
ar
e
tw
o
ap
p
r
o
ac
h
es
in
i
m
ag
e
r
etr
ie
v
al,
n
a
m
el
y
I
m
a
g
e
B
ased
R
etr
iev
al
(
T
B
I
R
)
b
ased
o
n
i
m
a
g
e
m
eta
d
ata
an
d
C
o
n
te
n
t
B
ased
I
m
ag
e
R
etr
iev
al
(
C
B
I
R
)
i
n
f
o
r
m
ati
o
n
b
as
ed
o
n
i
m
a
g
e
co
n
ten
t i
n
f
o
r
m
atio
n
T
h
e
cu
r
r
en
t te
x
t
-
b
a
s
ed
s
ea
r
ch
tech
n
iq
u
e
(
T
B
I
R
)
is
n
o
t
y
e
t f
u
ll
y
u
s
ab
le
b
ec
au
s
e
t
h
e
n
a
m
e
o
f
a
f
ile
ca
n
n
o
t
p
r
esen
t
its
co
n
te
n
ts
a
n
d
th
e
i
m
ag
e
it
s
elf
h
as
v
er
y
v
ar
iab
l
e
ch
ar
ac
ter
is
tics
[
1
]
.
T
h
er
ef
o
r
e,
to
k
n
o
w
th
e
e
x
ac
t
k
e
y
w
o
r
d
is
v
er
y
i
n
f
lu
e
n
tial
i
n
th
is
te
x
t
-
b
ased
p
r
o
ce
s
s
s
o
th
at
th
e
d
esire
d
im
a
g
e
ca
n
b
e
d
is
p
la
y
ed
[
2
]
.
T
h
is
ca
n
b
e
s
ee
n
in
Go
o
g
le
i
m
a
g
e
s
ea
r
ch
in
g
ca
n
n
o
t
f
i
n
d
o
p
tim
al
r
esu
lt
s
an
d
d
o
es
n
o
t
r
esp
o
n
d
to
w
h
at
i
s
ex
p
ec
ted
b
ec
au
s
e
t
h
e
s
ea
r
c
h
tec
h
n
iq
u
e
is
o
n
l
y
b
a
s
ed
o
n
t
h
e
f
ile
n
a
m
e
a
n
d
r
esu
lted
in
a
m
es
s
y
s
ea
r
ch
.
Seei
n
g
t
h
e
p
r
o
b
lem
o
f
tex
t
-
b
ased
tech
n
iq
u
es
is
n
ee
d
ed
alter
n
ati
v
e
ap
p
r
o
ac
h
w
it
h
an
o
t
h
er
i
m
a
g
e
r
etr
iev
al
m
et
h
o
d
th
at
is
C
o
n
te
n
t
B
ased
I
m
a
g
e
R
etr
ie
v
al
(
C
B
I
R
)
w
h
ic
h
ai
m
s
to
a
v
o
id
th
e
u
s
e
o
f
te
x
t
u
al
d
escr
ip
ti
o
n
[
3
]
.
C
B
I
R
i
s
a
m
et
h
o
d
o
lo
g
y
f
o
r
i
m
a
g
e
d
ata
r
ec
all
b
ased
o
n
th
e
co
n
ten
t
i
n
f
o
r
m
at
io
n
o
f
a
n
i
m
a
g
e,
s
u
c
h
as
co
lo
r
,
tex
tu
r
e,
an
d
s
h
ap
e
[
4
]
.
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
.
1
,
J
an
u
ar
y
201
8
:
243
–
2
48
244
B
ased
o
n
th
e
ab
o
v
e
d
escr
ip
tio
n
,
th
e
b
a
s
ic
f
r
a
m
e
w
o
r
k
u
n
d
er
ly
in
g
t
h
e
d
esi
g
n
o
f
t
h
i
s
C
B
I
R
a
p
p
licatio
n
is
to
c
h
o
o
s
e
t
h
e
m
o
s
t
e
f
f
ec
t
iv
e
f
ea
t
u
r
e
to
r
ep
r
esen
t
th
e
co
n
ten
ts
o
f
t
h
e
i
m
a
g
e
[
5
]
.
Am
o
n
g
t
h
e
m
o
s
t
p
o
p
u
lar
co
n
ten
t
a
n
d
i
m
a
g
e
ar
e
th
e
co
l
o
r
an
d
tex
t
u
r
e
f
ea
t
u
r
es
[
6
]
.
C
o
lo
r
f
ea
tu
r
e
is
th
e
m
o
s
t
f
r
eq
u
en
tl
y
u
s
ed
f
ea
tu
r
e
i
n
C
B
I
R
b
ec
au
s
e
it
h
as
a
s
tr
o
n
g
co
r
r
elatio
n
w
it
h
th
e
b
asic
o
b
ject
o
f
an
i
m
a
g
e.
T
h
e
C
o
lo
r
M
o
m
e
n
t
s
m
et
h
o
d
ca
n
b
e
u
s
ed
to
ex
tr
ac
t
co
lo
r
f
ea
t
u
r
es
.
I
m
ag
e
ca
n
b
e
r
ec
o
g
n
iz
ed
b
y
t
h
e
r
e
g
u
lar
it
y
o
f
p
ix
e
l
-
s
h
ap
ed
p
atter
n
s
b
y
u
tili
zi
n
g
te
x
tu
r
e
f
ea
t
u
r
es.
T
h
e
L
ac
u
n
ar
it
y
m
et
h
o
d
is
in
cl
u
d
ed
in
th
e
m
et
h
o
d
u
s
ed
f
o
r
th
e
ca
lcu
latio
n
o
f
t
h
e
d
is
tr
ib
u
tio
n
o
f
v
ac
a
n
c
y
d
e
g
r
ee
s
(
lacu
n
as)
in
th
e
i
m
a
g
e
an
d
it
is
clo
s
el
y
r
elate
d
to
th
e
te
x
tu
r
e
i
m
a
g
e
an
al
y
s
is
[
7
]
.
T
h
e
r
etr
iev
al
p
r
o
ce
s
s
i
n
th
e
C
B
I
R
ap
p
licatio
n
d
esig
n
d
e
v
elo
p
ed
in
t
h
is
p
ap
er
,
co
m
b
i
n
e
s
co
lo
r
an
d
tex
t
u
r
e
f
ea
tu
r
e
s
as
co
lo
r
an
d
t
ex
tu
r
e
ca
p
tu
r
e
d
if
f
er
en
t
asp
ec
ts
.
C
o
m
b
i
n
atio
n
s
ar
e
m
ad
e
u
p
o
f
t
w
o
t
y
p
es,
b
o
th
s
er
ial
an
d
p
ar
allel.
T
h
e
s
er
ial
co
m
b
in
atio
n
is
a
f
ea
t
u
r
e
ex
t
r
ac
tio
n
p
r
o
ce
s
s
b
ased
o
n
th
e
ca
lcu
latio
n
o
f
t
h
e
s
i
m
ilar
it
y
o
f
o
n
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
w
h
ile
t
h
e
co
m
b
in
at
io
n
in
p
ar
allel,
t
h
e
co
m
b
in
at
io
n
o
f
co
lo
r
an
d
tex
tu
r
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
i
s
ex
p
ec
te
d
to
im
p
r
o
v
e
t
h
e
i
m
ag
e
r
etr
iev
al
p
er
f
o
r
m
a
n
ce
i
n
th
e
ca
l
cu
latio
n
p
h
ase
o
f
s
i
m
ilar
it
y
b
et
w
ee
n
t
h
e
t
w
o
f
ea
tu
r
e
ex
tr
ac
tio
n
s
w
it
h
t
h
e
q
u
er
y
i
m
ag
e.
2.
RE
S
E
ARCH
M
E
T
H
O
D
L
ac
u
n
ar
it
y
w
o
r
k
s
i
n
t
w
o
m
et
h
o
d
s
n
a
m
ed
Di
f
f
er
en
tial
B
o
x
-
C
o
u
n
ti
n
g
(
DB
C
)
a
n
d
Gli
n
d
in
g
B
o
x
[
3
]
.
Glin
d
i
n
g
B
o
x
i
s
a
m
et
h
o
d
u
s
e
d
to
ca
lcu
late
b
in
ar
y
i
m
ag
e
s
i
n
L
ac
u
n
ar
it
y
.
C
alc
u
latio
n
o
f
Glin
d
i
n
g
B
o
x
b
e
g
in
s
b
y
ca
lc
u
lati
n
g
a
b
o
x
w
it
h
s
iz
e
o
f
r
s
id
e
an
d
all
p
r
o
ce
s
s
ed
i
m
a
g
e
w
ill
b
e
s
ea
r
ch
ed
its
L
ac
u
n
ar
it
y
v
a
lu
e
b
y
lo
g
g
i
n
g
t
h
e
m
ass
o
f
b
o
x
,
S
[
8
]
.
Glid
in
g
-
B
o
x
m
et
h
o
d
s
ta
g
e
b
eg
in
s
b
y
p
laci
n
g
b
o
x
o
r
s
q
u
a
r
e
b
o
x
w
i
th
r
x
r
s
ize
in
co
r
n
er
L
e
f
t
o
v
er
t
h
e
i
m
a
g
e,
th
e
n
t
h
e
b
o
x
w
i
ll
c
h
ec
k
e
v
er
y
p
ix
el
th
a
t
co
n
tai
n
s
1
o
r
0
u
n
til
f
in
al
l
y
th
e
e
n
tire
p
ix
el
is
p
ass
ed
b
y
t
h
e
b
o
x
.
T
h
is
b
o
x
m
o
v
es
f
r
o
m
t
h
e
to
p
lef
t
co
r
n
er
o
f
th
e
i
m
a
g
e
th
r
o
u
g
h
t
h
e
p
ix
el
s
p
er
p
ix
el
o
f
th
e
i
m
a
g
e
u
n
til
all
t
h
e
p
ix
e
ls
in
th
e
i
m
a
g
e
ar
e
id
en
tif
ied
.
W
h
en
th
is
b
o
x
is
in
a
ce
r
tain
p
ix
el,
th
e
p
r
o
g
r
a
m
w
il
l
ca
lcu
late
e
v
er
y
p
ix
el
v
a
lu
e
p
ass
ed
b
y
w
h
ic
h
it
is
co
n
s
id
er
ed
an
o
b
j
ec
t
in
th
e
i
m
a
g
e
[
7
]
.
T
h
e
f
r
eq
u
en
c
y
o
f
th
e
d
i
s
tr
ib
u
tio
n
o
f
p
ix
e
l
co
n
t
en
t
o
b
tai
n
ed
i
n
ea
c
h
b
o
x
is
d
en
o
ted
b
y
n
(
M,
r
)
w
h
ic
h
w
il
l
t
h
e
n
b
e
u
s
ed
to
d
eter
m
in
e
Q
(
M,
r
)
as
t
h
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
ea
ch
v
alu
e
i
n
t
h
e
b
o
x
o
b
tain
ed
f
r
o
m
th
e
d
is
tr
ib
u
tio
n
o
f
di
s
tr
ib
u
tio
n
p
er
p
ix
el
b
y
t
h
e
m
a
x
i
m
u
m
to
tal
n
u
m
b
er
o
f
T
h
e
co
u
r
s
e
o
f
t
h
e
b
o
x
is
d
en
o
ted
b
y
N
(
r
)
.
Fu
r
t
h
er
m
o
r
e,
th
ese
t
w
o
d
is
tr
ib
u
tio
n
s
w
ill b
e
p
r
o
ce
s
s
ed
b
y
t
h
e
f
o
llo
w
in
g
f
o
r
m
u
la:
=
∑
2
Q
(
,
r
)
−
[
∑
(
,
)
]
2
[
∑
(
,
)
]
2
)
(
1
)
W
ith
:
Λ(
r
)
:
L
ac
u
n
ar
it
y
w
it
h
b
o
x
s
ize
r
.
M
: T
h
e
m
a
s
s
o
f
ea
c
h
p
ix
el
t
h
at
t
h
e
b
o
x
p
ass
es.
Q(
m
,
r
)
: p
r
o
b
a
b
ilit
y
o
f
M
i
n
r
-
s
q
u
ar
e.
DB
C
m
et
h
o
d
th
at
w
as
d
ev
el
o
p
ed
b
ased
o
n
th
e
p
r
ev
io
u
s
m
et
h
o
d
o
f
L
ac
u
n
ar
it
y
is
Gli
d
in
g
B
o
x
m
e
th
o
d
,
co
m
m
o
n
l
y
u
s
ed
to
ca
lc
u
late
t
h
e
v
al
u
e
o
f
L
ac
u
n
ar
it
y
i
n
b
i
n
ar
y
i
m
ag
e.
T
h
e
DB
C
m
et
h
o
d
w
a
s
f
ir
s
t
in
tr
o
d
u
ce
d
b
y
Do
n
g
o
n
th
e
p
r
o
p
o
s
ed
es
ti
m
ated
f
r
ac
tal
d
i
m
en
s
io
n
s
o
f
Sar
k
ar
an
d
C
h
au
d
h
u
r
i
.
I
n
g
en
er
al,
L
ac
u
n
ar
it
y
ca
lcu
latio
n
u
s
i
n
g
DB
C
m
eth
o
d
is
d
o
n
e
o
n
s
e
v
er
al
w
i
n
d
o
w
an
d
b
o
x
s
izes
[
9
]
.
A
cu
b
e
w
i
t
h
r
x
r
x
r
s
ize
(
r
=
3
,
5
,
7
,
.
.
.
)
is
p
lace
d
a
b
o
v
e
th
e
t
o
p
lef
t
co
r
n
er
o
f
th
e
i
m
a
g
e
w
i
n
d
o
w
w
i
th
t
h
e
s
ize
W
x
W
.
F
o
r
ea
ch
r
x
r
x
r
-
s
ized
B
o
x
,
th
e
m
i
n
i
m
u
m
a
n
d
m
ax
i
m
u
m
v
al
u
es
o
f
p
i
x
els
in
th
e
b
o
x
w
ill
b
e
Val
u
e
o
f
u
an
d
v
.
F
u
r
th
er
m
o
r
e
f
r
o
m
th
e
d
ata
w
ill b
e
o
b
tain
ed
th
e
r
elati
v
e
len
g
t
h
o
f
t
h
e
co
lu
m
n
,
a
s
f
o
l
lo
w
s
:
(
,
)
=
−
−
1
(
2
)
W
h
er
e
i a
n
d
j
ar
e
im
ag
e
co
o
r
d
in
ates.
=
∑
,
(
,
)
(
3
)
W
ith
:
Mr
: M
ass
f
r
o
m
g
r
a
y
s
ca
le
i
m
a
g
e.
n
r
(
i,j
)
: Relati
v
e
h
ei
g
h
t o
f
t
h
e
co
lu
m
n
w
it
h
th
e
co
o
r
d
in
ates i,
j
.
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
C
o
n
ten
t B
a
s
ed
I
ma
g
e
R
etri
ev
a
l U
s
in
g
La
cu
n
a
r
ity
a
n
d
C
o
lo
r
Mo
men
ts
…
(
I
Gu
s
ti A
yu
Tr
iw
a
yu
n
i
)
245
C
o
lo
r
Mo
m
e
n
t
s
is
a
m
et
h
o
d
u
s
ed
to
d
is
tin
g
u
is
h
i
m
ag
e
s
b
ase
d
o
n
th
eir
co
lo
r
f
ea
tu
r
e
s
.
T
h
e
b
asis
o
f
t
h
is
m
et
h
o
d
is
t
h
e
as
s
u
m
p
tio
n
t
h
at
t
h
e
c
o
lo
r
d
is
tr
ib
u
tio
n
i
n
a
n
i
m
ag
e
ca
n
b
e
e
x
p
r
ess
ed
as
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
.
T
h
er
ef
o
r
e,
th
e
r
esu
lti
n
g
ac
c
u
r
ac
y
is
co
n
s
tan
t
ev
e
n
th
o
u
g
h
t
h
e
i
m
a
g
e
s
ize
c
h
an
g
e
s
[
1
0
]
.
C
o
lo
r
Mo
m
e
n
ts
ar
e
ca
lled
co
m
p
ac
t
b
ec
au
s
e
t
h
e
y
c
an
co
m
p
r
ess
co
lo
r
i
m
ag
e
i
n
f
o
r
m
atio
n
i
n
to
m
u
lt
ip
le
v
al
u
es.
T
h
is
co
lo
r
ex
tr
ac
to
r
d
o
es
n
o
t
r
eq
u
ir
e
q
u
an
tizatio
n
in
p
r
e
-
p
r
o
ce
s
s
s
tag
e
s
b
ec
au
s
e
C
o
lo
r
Mo
m
e
n
ts
o
n
l
y
s
to
r
es
th
e
d
o
m
in
a
n
t
f
ea
tu
r
e
o
f
co
lo
r
d
is
tr
ib
u
tio
n
in
t
h
e
d
atab
ase.
T
h
is
m
et
h
o
d
u
s
es
t
h
r
ee
m
ai
n
m
o
m
e
n
ts
o
f
co
lo
r
i
m
a
g
e
d
is
tr
ib
u
tio
n
,
ie
m
ea
n
,
s
tan
d
ar
d
d
ev
iatio
n
,
a
n
d
s
k
e
w
n
es
s
,
s
o
th
i
s
m
et
h
o
d
y
ie
ld
s
th
r
ee
v
al
u
es
f
o
r
ea
ch
co
lo
r
co
m
p
o
n
e
n
t
[
1
1
]
.
T
h
ese
th
r
ee
m
o
m
en
t
s
ca
n
b
e
d
ef
i
n
ed
as f
o
llo
w
s
:
=
1
∑
=
1
(
4
)
=
√
1
∑
(
=
1
−
)
2
)
(
5
)
=
√
1
∑
−
=
1
3
)
3
)
(
6
)
W
ith
:
E
: M
ea
n
.
: Stan
d
ar
d
d
ev
iatio
n
.
S
: Sk
e
w
n
es
s
.
N
: N
u
m
b
er
o
f
p
i
x
els.
i
: Cu
r
r
en
t c
o
m
p
o
n
e
n
t c
o
lo
r
in
d
ex
(
ex
a
m
p
le:
1
=
H,
2
=
S,
3
=
V)
.
j
: T
h
e
o
r
d
er
o
f
p
ix
els.
P
_
i
j
: D
ef
i
n
es t
h
e
i
-
th
v
al
u
e
o
f
t
h
e
co
lo
r
co
m
p
o
n
en
t o
n
j
-
th
i
m
a
g
e
p
ix
els.
Data
s
i
m
ilar
it
y
i
s
t
h
e
r
elat
io
n
s
h
ip
o
f
t
h
e
s
i
m
ilar
it
y
o
r
p
r
o
x
i
m
it
y
o
f
t
h
e
d
is
ta
n
ce
m
ea
s
u
r
e
m
en
t
b
et
w
ee
n
t
w
o
d
ata
o
b
j
ec
ts
.
T
h
e
d
eg
r
ee
o
f
s
i
m
ilar
it
y
in
t
h
e
f
o
r
m
o
f
a
v
a
lu
e
(
s
co
r
e)
a
n
d
b
ased
o
n
t
h
e
v
al
u
e
o
f
t
w
o
d
ata
o
b
j
ec
ts
w
ill
b
e
s
aid
to
b
e
s
i
m
ilar
o
r
n
o
t.
T
h
e
v
alu
e
o
f
t
h
e
m
ea
s
u
r
e
m
e
n
t
d
ata
s
i
m
ilar
it
y
w
il
l
b
e
g
r
ea
ter
if
th
e
co
m
p
ar
ed
o
b
j
ec
ts
m
o
r
e
s
i
m
ila
r
o
r
s
i
m
ilar
.
W
h
ile
d
ata
d
is
s
i
m
ilar
it
y
i
s
t
h
e
le
v
el
o
f
in
eq
u
a
lit
y
o
f
m
ea
s
u
r
e
m
e
n
t
b
et
w
ee
n
t
w
o
d
ata
o
b
j
ec
ts
.
T
h
e
v
al
u
e
o
f
d
ata
d
is
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
w
ill
b
e
lo
w
er
i
f
th
e
co
m
p
ar
ed
o
b
j
ec
t
is
m
o
r
e
s
i
m
ilar
.
T
h
e
d
is
tan
ce
u
s
ed
in
t
h
i
s
r
esear
ch
is
ec
l
u
d
ie
n
d
is
ta
n
ce
[
1
2
]
.
=
√
∑
(
−
)
2
=
1
(
7
)
Si
m
i
lar
i
m
a
g
es o
f
th
e
p
r
o
ce
s
s
ar
e
an
al
y
ze
d
f
o
r
ac
cu
r
ac
y
u
s
in
g
p
r
ec
is
io
n
.
E
x
a
m
p
le:
A
S (
I
m
ag
e
r
etr
iev
ed
)
=
3
,
A
U
(
i
m
a
g
e
r
etr
iev
ed
r
elev
a
n
t)
=
1
0
.
Pr
e
c
ision
=
100%
=
3
10
100%
=
30
%
(
9
)
3.
RE
SU
L
T
S
AND
A
N
AL
Y
SI
S
I
m
ag
e
p
r
o
ce
s
s
i
n
g
p
r
o
ce
s
s
i
s
d
iv
id
ed
in
to
t
w
o
d
ata
in
s
er
tio
n
an
d
q
u
er
y
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
.
T
h
er
e
is
a
k
n
o
w
led
g
e
b
ase
o
n
th
e
C
B
I
R
s
y
s
te
m
t
h
at
i
s
a
tr
ai
n
in
g
d
at
a
co
n
s
is
tin
g
o
f
a
s
e
t
o
f
v
ec
to
r
s
ch
ar
ac
ter
is
t
ic
o
f
tex
t
u
r
es a
n
d
co
lo
r
s
th
at
h
av
e
b
ee
n
d
ef
i
n
ed
.
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
.
1
,
J
an
u
ar
y
201
8
:
243
–
2
48
246
C
i
t
r
a
q
u
e
r
y
gra
y
s
c
a
l
e
E
k
s
t
r
a
k
s
i
L
a
c
u
n
a
r
i
t
y
K
o
n
v
e
r
s
i
k
e
H
S
V
M
a
t
r
i
k
s
H
,
S
,
d
a
n
V
E
k
s
t
ra
k
s
i
C
o
l
o
r
M
o
m
e
n
t
s
K
o
n
v
e
rs
i
k
e
H
S
V
M
a
t
ri
k
s
H
,
S
,
d
a
n
V
E
k
s
t
ra
k
s
i
C
o
l
o
r
M
o
m
e
n
t
s
P
e
m
b
a
n
g
u
n
a
n
ba
s
i
s
pe
n
ge
t
a
hu
a
n
S
i
m
i
l
a
ri
t
y
d
a
n
ra
n
k
i
n
g
C
o
m
p
u
t
a
t
i
o
n
Q
U
E
R
Y
P
R
O
C
E
S
S
I
N
G
S
i
m
i
l
a
r
i
t
y
d
a
n
r
a
n
k
i
n
g
C
om
pu
t
a
t
i
on
gra
y
s
c
a
l
e
E
k
s
t
r
a
k
s
i
L
a
c
u
n
a
r
i
t
y
D
a
t
a
I
n
s
e
r
t
i
o
n
Fig
u
r
e
2
.
S
y
s
te
m
w
o
r
k
f
lo
w
T
h
e
test
w
as
co
n
d
u
cted
to
d
eter
m
in
e
t
h
e
ef
f
ec
t
o
f
co
m
b
in
at
i
o
n
o
f
co
lo
r
an
d
tex
tu
r
e
f
ea
t
u
r
e
s
in
i
m
a
g
e
r
etr
iev
al
p
er
f
o
r
m
a
n
ce
.
E
ac
h
test
p
er
f
o
r
m
ed
,
ca
lc
u
lated
it
s
p
r
ec
is
io
n
v
al
u
e
(
ca
n
b
e
c
alled
th
e
v
alu
e
o
f
ac
cu
r
ac
y
)
.
T
h
e
p
r
ec
is
io
n
v
alu
e
u
s
ed
is
th
e
a
v
er
ag
e
p
r
ec
is
io
n
v
al
u
e
o
f
all
t
h
e
i
m
a
g
es
te
s
te
d
in
a
class
.
T
h
e
test
r
esu
lt
s
ar
e
s
h
o
w
n
in
T
ab
le
1
.
T
ests
o
n
th
e
co
m
b
in
atio
n
o
f
th
e
C
o
lo
r
Mo
m
e
n
t
s
m
e
th
o
d
s
T
ab
le
1
,
it
is
k
n
o
w
n
t
h
at
t
h
e
p
r
ec
is
io
n
v
alu
e
s
th
at
h
a
v
e
b
ee
n
a
v
er
a
g
ed
in
ea
c
h
clas
s
o
f
1
0
class
e
s
,
w
i
th
th
e
s
m
alle
s
t
ac
c
u
r
ac
y
r
esu
lt
s
s
h
o
w
ed
3
5
%
ac
n
e
g
r
ad
e
an
d
th
e
h
ig
h
est
r
e
s
u
lt
s
o
b
tai
n
ed
n
u
m
m
m
u
lar
,
u
r
ticar
ia
an
d
v
itti
lig
o
g
r
ad
es
with
a
n
ac
cu
r
ac
y
o
f
1
0
0
%.
Ur
ticar
ia
an
d
v
itt
ili
g
o
class
es
h
av
e
th
e
h
ig
h
es
t
p
r
ec
is
io
n
v
al
u
es
b
et
w
ee
n
t
h
e
o
th
er
i
m
a
g
e
cla
s
s
es
b
ec
au
s
e
th
e
i
m
ag
e
s
in
th
e
n
u
m
m
m
u
lar
,
u
r
ticar
ia
an
d
v
it
tili
g
o
class
es
h
a
v
e
al
m
o
s
t
eq
u
al
co
lo
r
v
ar
i
atio
n
s
o
f
b
o
th
o
b
j
ec
t
an
d
b
ac
k
g
r
o
u
n
d
co
lo
r
.
W
h
ile
th
e
ac
n
e
cla
s
s
h
a
s
a
co
m
p
lex
b
ac
k
g
r
o
u
n
d
th
at
a
f
f
ec
ts
t
h
e
r
esu
lt
s
o
f
th
e
ex
tr
ac
t
io
n
p
r
o
ce
s
s
.
T
ab
le
1
.
T
est r
esu
lts
o
f
C
o
lo
r
Mo
m
en
t
s
No
C
l
a
ss
P
r
e
c
i
ssi
o
n
1
A
c
n
e
3
5
%
2
A
c
r
o
p
u
st
u
l
o
si
s
5
3
%
3
A
l
o
p
e
c
i
a
7
0
%
4
D
e
r
mat
i
t
i
s
8
8
%
5
H
e
man
g
i
o
ma
5
3
%
6
I
c
h
t
h
y
o
si
s
9
0
%
7
M
o
l
l
u
scu
m
5
0
%
8
N
u
mm
u
l
a
r
1
0
0
%
9
U
r
t
i
c
a
r
i
a
1
0
0
%
10
V
i
t
t
i
l
i
g
o
1
0
0
%
T
ab
le
2
.
T
est r
esu
lts
o
f
L
ac
u
n
ar
it
y
No
C
l
a
ss
P
r
e
c
i
ssi
o
n
1
A
c
n
e
1
0
%
2
A
c
r
o
p
u
st
u
l
o
si
s
1
5
%
3
A
l
o
p
e
c
i
a
1
5
%
4
D
e
r
mat
i
t
i
s
2
5
%
5
H
e
man
g
i
o
ma
2
3
%
6
I
c
h
t
h
y
o
si
s
1
3
%
7
M
o
l
l
u
scu
m
1
0
%
8
N
u
mm
u
l
a
r
2
5
%
9
U
r
t
i
c
a
r
i
a
1
3
%
10
V
i
t
t
i
l
i
g
o
2
5
%
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
C
o
n
ten
t B
a
s
ed
I
ma
g
e
R
etri
ev
a
l U
s
in
g
La
cu
n
a
r
ity
a
n
d
C
o
lo
r
Mo
men
ts
…
(
I
Gu
s
ti A
yu
Tr
iw
a
yu
n
i
)
247
T
ests
o
n
th
e
L
ac
u
n
ar
it
y
m
eth
o
d
T
ab
le
2
,
w
ith
th
e
s
m
alle
s
t
ac
cu
r
ac
y
r
e
s
u
l
t
s
h
o
w
ed
1
0
%
ac
n
e
a
n
d
m
o
llu
s
c
u
m
clas
s
an
d
th
e
h
i
g
h
est
r
e
s
u
l
t
w
as
o
b
tain
ed
d
er
m
atiti
s
,
n
u
m
m
u
lar
an
d
v
itt
ili
g
o
clas
s
w
it
h
2
5
%
ac
cu
r
ac
y
.
T
h
is
is
b
ec
a
u
s
e
th
e
i
m
a
g
e
'
s
s
i
m
ilar
it
y
to
th
e
tex
t
u
r
e
is
af
f
ec
ted
b
y
th
e
d
ec
o
m
p
o
s
itio
n
le
v
el
o
f
a
n
i
m
a
g
e.
T
ab
le
3
.
T
est r
esu
lts
C
o
m
b
in
a
tio
n
o
f
L
ac
u
n
ar
it
y
an
d
C
o
lo
r
Mo
m
en
t
s
No
C
l
a
ss
P
r
e
c
i
ssi
o
n
1
A
c
n
e
1
8
%
2
A
c
r
o
p
u
st
u
l
o
si
s
2
5
%
3
A
l
o
p
e
c
i
a
6
0
%
4
D
e
r
mat
i
t
i
s
5
5
%
5
H
e
man
g
i
o
ma
2
3
%
6
I
c
h
t
h
y
o
si
s
5
3
%
7
M
o
l
l
u
scu
m
2
8
%
8
N
u
mm
u
l
a
r
1
5
%
9
U
r
t
i
c
a
r
i
a
2
5
%
10
V
i
t
t
i
l
i
g
o
2
0
%
I
n
T
ab
le
3
,
a
tw
o
-
f
ea
tu
r
e
co
m
b
in
atio
n
te
s
t
y
ield
ed
th
e
s
m
all
est
ac
cu
r
ac
y
i
n
t
h
e
1
5
%
n
u
m
m
u
lar
class
an
d
th
e
h
ig
h
es
t r
esu
l
t o
b
tain
ed
b
y
t
h
e
alo
p
ec
ia
class
w
it
h
a
n
ac
cu
r
ac
y
o
f
6
0
%.
Fig
u
r
e
2
.
Gr
ap
h
o
f
P
er
ce
n
tag
e
Fig
u
r
e
2
is
t
h
e
p
er
ce
n
ta
g
e
g
r
ap
h
o
f
th
e
C
o
lo
r
Mo
m
e
n
ts
,
L
ac
u
n
ar
it
y
a
n
d
C
o
m
b
i
n
atio
n
Me
t
h
o
d
s
,
s
h
o
w
i
n
g
t
h
e
p
r
ec
is
io
n
v
al
u
es
th
at
h
a
v
e
b
ee
n
av
er
a
g
ed
o
n
ea
ch
class
o
f
1
0
class
es,
w
it
h
th
e
s
m
alle
s
t
p
r
ec
is
io
n
v
alu
e
o
f
3
5
%
ac
n
e
g
r
ad
e
a
n
d
th
e
h
ig
h
es
t
r
es
u
lt
o
b
tain
ed
b
y
n
u
m
m
m
u
lar
,
u
r
ticar
ia
a
n
d
v
i
t
tili
g
o
cla
s
s
es
w
it
h
1
0
0
%
p
r
ec
is
io
n
v
al
u
e.
T
h
e
p
e
r
ce
n
tag
e
d
if
f
er
e
n
ce
is
o
b
tain
e
d
b
ec
au
s
e
th
e
i
m
a
g
es
in
t
h
e
n
u
m
m
m
u
lar
,
u
r
ticar
ia
an
d
v
itti
lig
o
cla
s
s
es
h
a
v
e
al
m
o
s
t
th
e
s
a
m
e
co
lo
r
v
ar
iatio
n
s
as
o
b
j
ec
t
c
o
lo
r
an
d
b
ac
k
g
r
o
u
n
d
co
lo
r
w
h
ile
t
h
e
ac
n
e
class
h
as
a
co
m
p
le
x
b
ac
k
g
r
o
u
n
d
th
at
a
f
f
ec
ts
t
h
e
e
x
tr
ac
tio
n
p
r
o
ce
s
s
.
L
ac
u
n
ar
it
y
m
eth
o
d
,
w
ith
t
h
e
s
m
al
lest
ac
cu
r
ac
y
o
f
ac
n
e
a
n
d
m
o
ll
u
s
c
u
m
1
0
%
an
d
t
h
e
h
i
g
h
e
s
t
r
esu
lts
o
b
tain
ed
class
d
er
m
atiti
s
,
n
u
m
m
u
lar
an
d
v
itti
lig
o
w
it
h
2
5
%
p
r
ec
is
s
io
n
v
al
u
e.
T
h
e
d
i
f
f
er
e
n
ce
is
ca
u
s
ed
b
y
t
h
e
s
i
m
ilar
it
y
o
f
t
h
e
i
m
ag
e
to
t
h
e
tex
t
u
r
e
is
af
f
ec
ted
b
y
th
e
d
ec
o
m
p
o
s
iti
o
n
lev
el
o
f
a
n
i
m
a
g
e.
T
h
e
s
ec
o
n
d
co
m
b
i
n
atio
n
o
f
co
m
b
in
at
io
n
s
o
f
L
ac
u
n
ar
it
y
an
d
C
o
lo
r
Mo
m
en
t
s
Me
t
h
o
d
s
is
th
e
s
m
a
lles
t
p
r
ec
is
io
n
r
esu
l
t
in
t
h
e
ac
n
e
a
n
d
m
o
ll
u
s
c
u
m
c
lass
es
o
f
1
8
%
an
d
th
e
h
i
g
h
est
y
ield
i
n
th
e
cla
s
s
o
f
d
er
m
atiti
s
,
n
u
m
m
u
lar
a
n
d
v
it
tili
g
o
w
it
h
a
p
r
ec
is
io
n
v
alu
e
o
f
6
0
%.
4.
C
O
NCLU
SI
O
N
T
h
e
C
B
I
R
tech
n
iq
u
e
ap
p
lied
to
th
e
d
ev
elo
p
ed
ap
p
licatio
n
i
s
to
s
ea
r
ch
f
o
r
i
m
a
g
e
s
t
h
at
h
av
e
s
i
m
ilar
itie
s
w
it
h
t
h
e
s
p
ec
i
f
ic
i
m
a
g
e
cr
iter
i
a
o
f
a
s
et
o
f
i
m
a
g
es
b
y
p
er
f
o
r
m
i
n
g
a
co
m
p
ar
i
s
o
n
b
et
w
ee
n
t
h
e
q
u
er
y
i
m
a
g
e
a
n
d
th
e
i
m
a
g
e
p
r
ese
n
t
i
n
t
h
e
d
atab
ase
b
ased
o
n
th
e
i
m
ag
e
co
n
te
n
t
i
n
f
o
r
m
atio
n
.
I
m
a
g
e
r
etr
ie
v
a
l
u
s
in
g
1
0
0
tr
ai
n
in
g
d
ata
an
d
4
s
k
in
d
is
ea
s
e
s
k
i
n
t
est
d
ata
w
it
h
L
ac
u
n
ar
it
y
a
n
d
C
o
lo
r
Mo
m
e
n
ts
Me
t
h
o
d
f
o
r
it
s
f
ea
tu
r
e
ex
tr
ac
tio
n
.
B
ased
o
n
th
e
r
esu
lts
o
f
ex
p
er
i
m
en
ts
an
d
an
a
l
y
s
is
o
f
r
esear
c
h
o
n
th
e
ap
p
licatio
n
o
f
b
o
th
m
eth
o
d
s
in
t
h
e
C
B
I
R
ap
p
licatio
n
ca
n
b
e
d
r
aw
n
co
n
clu
s
io
n
th
at
i
s
,
th
e
ap
p
licatio
n
p
er
f
o
r
m
a
n
ce
r
esu
lt
s
ar
e
v
er
y
g
o
o
d
if
u
s
i
n
g
C
o
lo
r
Mo
m
en
t
s
Me
th
o
d
to
r
ea
c
h
1
0
0
% a
cc
u
r
ac
y
a
n
d
d
ec
r
ea
s
ed
ap
p
licatio
n
p
er
f
o
r
m
a
n
ce
in
L
ac
u
n
ar
it
y
Me
t
h
o
d
w
it
h
th
e
h
i
g
h
e
s
t
ac
c
u
r
ac
y
p
er
ce
n
ta
g
e
o
f
2
5
%
.
P
er
f
o
r
m
a
n
ce
w
h
e
n
b
o
th
m
eth
o
d
s
ar
e
co
m
b
i
n
ed
th
at
is
t
h
e
r
es
u
lt
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
.
1
,
J
an
u
ar
y
201
8
:
243
–
2
48
248
ac
cu
r
ac
y
o
f
6
0
%.
C
o
m
b
in
at
io
n
o
f
s
i
m
i
lar
it
y
e
x
tr
ac
tio
n
ca
lc
u
latio
n
Me
th
o
d
s
C
o
lo
r
Mo
m
e
n
ts
a
n
d
L
ac
u
n
ar
it
y
h
av
e
b
etter
ap
p
licatio
n
ac
cu
r
a
c
y
co
m
p
ar
ed
to
tex
tu
r
e
f
ea
tu
r
e
ex
tr
ac
tio
n
o
n
l
y
.
RE
F
E
R
E
NC
E
S
[1
]
L
.
X
ia,
Z.
P
e
n
g
,
A
.
Ca
i,
a
n
d
H.
W
a
n
g
,
“
M
e
d
ica
l
Im
a
g
e
R
e
tri
e
v
a
l
Ba
se
d
o
n
S
h
a
p
e
F
e
a
tu
re
s
in
DCT
Do
m
a
in
,
”
T
e
lko
mn
ika
I
n
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
.
,
v
o
l.
1
2
,
n
o
.
2
,
p
p
.
1
1
1
6
–
1
1
2
4
,
2
0
1
4
.
[2
]
N.
Ja
in
,
S
.
S
h
a
rm
a
,
R.
M
.
S
a
ira
m
,
a
n
d
S
.
Ra
m
,
“
Co
n
ten
t
Ba
se
d
Im
a
g
e
Re
tri
e
v
a
l
u
sin
g
Co
m
b
in
a
ti
o
n
o
f
Co
l
o
r
,
S
h
a
p
e
a
n
d
T
e
x
tu
re
F
e
a
tu
re
s,” n
o
.
1
,
2
0
1
3
.
[3
]
M
.
N.
Ba
rro
s
F
il
h
o
a
n
d
F
.
J.
a
S
o
b
re
ira,
“
A
c
c
u
ra
c
y
o
f
lac
u
n
a
rit
y
a
lg
o
rit
h
m
s
in
Tex
tu
re
Clas
si
f
i
c
a
ti
o
n
o
f
h
ig
h
sp
a
ti
a
l
re
so
lu
ti
o
n
im
a
g
e
s
f
ro
m
u
rb
a
n
a
re
a
s,”
T
h
e
In
ter
n
a
ti
o
n
a
l
Arc
h
ive
s
o
f
th
e
Ph
o
t
o
g
ra
mm
e
try
,
R
e
mo
t
e
S
e
n
sin
g
a
n
d
S
p
a
t
ia
l
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s.
,
n
o
.
3
6
,
p
p
.
4
1
7
–
4
2
2
,
2
0
0
8
.
[4
]
C.
Yo
u
n
e
ss
,
E.
A
.
Kh
a
li
d
,
O.
M
o
h
a
m
m
e
d
,
a
n
d
A
.
Bra
h
i
m
,
“
Ne
w
M
e
th
o
d
o
f
Co
n
ten
t
Ba
se
d
I
m
a
g
e
Re
tri
e
v
a
l
b
a
s
e
d
o
n
2
-
D
ES
P
RIT
M
e
th
o
d
a
n
d
th
e
G
a
b
o
r
F
il
ters
,
”
T
e
lko
mn
ik
a
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
in
e
e
rin
g
.
,
v
o
l
.
1
5
,
n
o
.
2
,
p
p
.
3
1
3
–
3
2
0
,
2
0
1
5
.
[5
]
M
.
Ya
s
m
in
,
M
.
S
h
a
rif
,
I.
Iru
m
,
a
n
d
S
.
M
o
h
si
n
,
“
A
n
e
ff
icie
n
t
c
o
n
ten
t
b
a
se
d
im
a
g
e
re
tri
e
v
a
l
u
sin
g
EI
c
las
si
f
ica
ti
o
n
a
n
d
c
o
l
o
r
f
e
a
tu
re
s,”
J
o
u
rn
a
l
o
f
Ap
p
li
e
d
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
lo
g
y
.
,
v
o
l.
1
2
,
n
o
.
5
,
p
p
.
8
7
7
–
8
8
5
,
2
0
1
4
.
[
6]
I
Ke
tu
t
G
e
d
e
Da
r
m
a
P
u
tra
a
n
d
Erd
iaw
a
n
,
“
Hig
h
P
e
rf
o
rm
a
n
c
e
P
a
lm
p
rin
t
Id
e
n
ti
f
ica
ti
o
n
S
y
ste
m
Ba
se
d
On
Tw
o
Dim
e
n
sio
n
a
l
G
a
b
o
r,
”
T
e
lko
m
n
ik
a
In
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
.,
p
p
.
3
0
9
–
3
1
8
,
2
0
1
0
.
[7
]
S
.
W
.
M
y
in
t,
V
.
M
e
se
v
,
a
n
d
N.
L
a
m
,
“
Urb
a
n
tex
tu
ra
l
a
n
a
l
y
sis
f
r
o
m
re
m
o
te
se
n
so
r
d
a
ta:
Lac
u
n
a
rit
y
m
e
a
su
re
m
e
n
ts
b
a
se
d
o
n
th
e
d
if
f
e
r
e
n
ti
a
l
b
o
x
c
o
u
n
ti
n
g
m
e
th
o
d
,
”
Ge
o
g
ra
p
h
ica
l
An
a
lys
is.
De
p
a
rtme
n
t
o
f
Ge
o
g
ra
p
h
y
.
,
v
o
l.
3
8
,
n
o
.
4
,
p
p
.
3
7
1
–
3
9
0
,
2
0
0
6
.
[8
]
M
.
M
u
c
h
tar,
N.
S
u
c
iati,
a
n
d
C.
F
a
ti
c
h
a
h
,
“
F
ra
c
tal
Dim
e
n
sio
n
a
n
d
L
a
c
u
n
a
rit
y
Co
m
b
in
a
ti
o
n
f
o
r
P
lan
t
L
e
a
f
Clas
sif
ic
a
ti
o
n
,
”
J
u
rn
a
l
Ilm
u
Ko
m
p
u
ter
d
a
n
In
f
o
rm
a
si.
,
v
o
l.
9
,
n
o
.
2
,
p
.
9
6
,
2
0
1
6
.
[9
]
P
.
Do
n
g
,
“
T
e
st
o
f
a
N
e
w
L
a
c
u
n
a
rit
y
Esti
m
a
ti
o
n
M
e
th
o
d
f
o
r
Im
a
g
e
T
e
x
tu
re
A
n
a
l
y
sis
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Rem
o
te S
e
n
si
n
g
.
,
v
o
l.
2
1
,
n
o
.
1
7
,
p
p
.
3
3
6
9
–
3
3
7
3
,
2
0
0
0
.
[1
0
]
A
.
S
a
m
e
ri
y
a
,
“
Co
n
ten
t
-
Ba
se
d
Im
a
g
e
R
e
tri
e
v
a
l
u
sin
g
Co
lo
r
M
o
m
e
n
ts
,
W
a
v
e
let
M
o
m
e
n
ts
&
S
V
M
Clas
sif
ier,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Di
g
it
a
l
A
p
p
li
c
a
ti
o
n
&
Co
n
tem
p
o
ra
ry
re
se
a
rc
h
,
v
o
l.
2
,
n
o
.
1
1
,
2
0
1
4
.
[1
1
]
N.
Ke
e
n
,
“
Co
lo
r
m
o
m
e
n
ts,
”
S
c
h
o
o
l
Of
I
n
fo
rm
a
ti
c
s,
Un
ive
rs
it
y
Of
Ed
in
b
u
r
g
h
,
p
p
.
3
–
6
,
2
0
0
5
.
[1
2
]
D.
P
u
tra,
Pen
g
o
l
a
h
a
n
Ci
tra
Di
g
it
a
l
.
Yo
g
y
a
k
a
rta:
A
n
d
i
Off
s
e
t,
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.