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.
1
2
,
No
.
1
,
Octo
b
er
201
8
,
p
p
.
1
1
7
~
12
6
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
1
.
p
p
117
-
1
2
6
117
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
Paper Mo
ney
Re
c
o
g
niz
er
Using
F
ea
ture
Descrip
tor
Nur
H
a
dis
u
k
m
a
na
,
Adri
Yu
dia
nto
N
P
F
a
c
u
lt
y
o
f
Co
m
p
u
ti
n
g
,
P
re
sid
e
n
t
Un
iv
e
rsit
y
,
Cik
a
ra
n
g
,
Be
k
a
si,
1
7
5
5
0
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
,
2
0
1
8
R
ev
i
s
ed
A
p
r
2
1
,
2
0
1
8
A
cc
ep
ted
J
u
n
1
4
,
2
0
1
8
P
e
o
p
le
a
re
stil
l
u
si
n
g
p
a
p
e
r
m
o
n
e
y
f
o
r
d
a
il
y
tran
sa
c
ti
o
n
;
t
h
is,
h
o
w
e
v
e
r,
w
il
l
e
x
p
o
se
so
m
e
d
iff
icu
lt
y
f
o
r
v
isu
a
ll
y
i
m
p
a
ired
p
e
o
p
le.
T
h
o
u
g
h
th
e
y
c
a
n
stil
l
re
a
d
th
e
n
o
m
in
a
l
v
a
lu
e
o
f
th
e
p
a
p
e
r
m
o
n
e
y
b
y
th
e
h
e
lp
o
f
o
th
e
r
p
e
o
p
le
o
r
b
y
to
u
c
h
in
g
th
e
tac
ti
le
f
e
a
tu
re
,
th
e
y
c
a
n
n
o
t
d
e
p
e
n
d
u
p
o
n
o
th
e
rs
a
ll
t
h
e
ti
m
e
n
o
r
to
u
c
h
in
g
th
e
tac
ti
le
f
e
a
tu
re
p
ro
p
e
rly
i
f
th
e
p
a
p
e
r
m
o
n
e
y
is
wo
rn
.
S
o
m
e
a
lt
e
rn
a
ti
v
e
s
h
a
v
e
b
e
e
n
p
ro
p
o
se
d
a
n
d
c
o
n
d
u
c
ted
.
O
n
e
o
f
th
e
m
is
u
sin
g
m
o
n
e
y
v
a
lu
e
re
c
o
g
n
it
io
n
a
p
p
l
ica
ti
o
n
.
T
h
e
a
p
p
li
c
a
ti
o
n
w
il
l
re
c
o
g
n
ize
n
o
m
in
a
l
v
a
lu
e
o
f
p
a
p
e
r
m
o
n
e
y
c
o
m
p
a
rin
g
th
e
im
a
g
e
o
f
th
e
p
a
p
e
r
w
it
h
d
a
ta
b
a
se
.
T
h
is
p
ro
c
e
ss
is
u
sin
g
a
fe
a
tu
re
e
x
tra
c
ti
o
n
a
lg
o
rit
h
m
c
a
ll
e
d
ORB
fe
a
tu
re
d
e
sc
rip
to
r.
It
h
a
s b
e
e
n
u
se
d
f
o
r
six
(6
)
d
if
f
e
re
n
t
ty
p
e
s o
f
c
u
rre
n
c
ies
th
a
t
a
re
5
m
o
st t
ra
d
e
d
c
u
rre
n
c
ies
a
n
d
In
d
o
n
e
sia
c
u
rre
n
c
y
a
n
d
a
lso
f
o
r
d
iff
e
re
n
t
t
y
p
e
s
o
f
n
o
m
in
a
ls
(b
il
ls)
.
K
ey
w
o
r
d
s
:
B
an
k
n
o
te
B
lin
d
C
o
d
e
Featu
r
e
Descr
ip
to
r
Featu
r
e
Ma
tc
h
in
g
OR
B
Alg
o
r
it
h
m
P
ap
er
M
o
n
e
y
R
ec
o
g
n
izer
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
:
Nu
r
Had
is
u
k
m
a
n
a
,
Facu
lt
y
o
f
C
o
m
p
u
tin
g
,
P
r
esid
en
t U
n
i
v
er
s
it
y
,
C
ik
ar
a
n
g
,
B
ek
a
s
i,
1
7
5
5
0
,
I
n
d
o
n
esia
.
E
m
ail:
n
u
r
h
ad
is
u
k
m
a
n
a
@
p
r
esid
en
t.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
ev
er
y
d
a
y
li
f
e,
p
eo
p
le
ar
e
u
s
i
n
g
b
an
k
n
o
tes
f
o
r
b
u
s
i
n
es
s
.
T
h
ey
p
la
y
i
m
p
o
r
tan
t
r
o
le
in
f
in
a
n
cia
l
tr
an
s
ac
tio
n
s
an
d
ar
e
u
s
ed
as
o
f
f
icial
cu
r
r
en
c
y
an
d
m
ed
i
u
m
o
f
ex
c
h
an
g
e
f
o
r
g
o
o
d
s
an
d
s
er
v
ices.
I
t
is
ex
p
ec
ted
th
at
e
v
er
y
p
er
s
o
n
ca
n
u
s
e
it
w
it
h
o
u
t
n
ee
d
ed
h
e
lp
s
f
r
o
m
o
th
er
s
.
T
h
e
n
o
m
in
al
v
a
lu
e
o
f
p
ap
er
m
o
n
e
y
o
r
b
an
k
n
o
tes s
h
o
u
ld
b
e
ea
s
il
y
to
r
ec
o
g
n
ize
f
o
r
all
p
eo
p
le.
T
h
ey
,
h
o
w
e
v
er
ex
p
o
s
e
s
o
m
e
d
if
f
ic
u
lt
y
to
ce
r
tain
d
is
ab
le
p
er
s
o
n
s
.
V
is
u
all
y
i
m
p
air
ed
(
B
lin
d
)
p
eo
p
le
h
ar
d
ly
r
ec
o
g
n
ize
t
h
e
n
o
m
i
n
al
o
f
th
e
b
a
n
k
n
o
tes
o
r
p
ap
er
m
o
n
e
y
s
o
t
h
e
y
n
ee
d
h
elp
f
r
o
m
an
o
th
er
p
er
s
o
n
f
o
r
r
ea
d
in
g
t
h
e
n
o
m
in
a
l o
f
th
e
b
a
n
k
n
o
te
s
.
So
m
e
s
tates
li
k
e
C
an
ad
a
a
n
d
A
u
s
tr
alia
h
a
v
e
b
ee
n
tr
y
i
n
g
t
o
ad
d
s
o
m
e
b
li
n
d
co
d
e
f
ea
t
u
r
es
to
t
h
eir
p
ap
er
m
o
n
e
y
,
s
u
c
h
a
s
tact
ile
f
ea
tu
r
e,
a
b
r
aille
-
li
k
e
f
ea
tu
r
e
[
1
]
.
W
h
er
ea
s
I
n
d
o
n
esia
h
a
s
i
m
p
le
m
en
ted
th
e
b
lin
d
co
d
e
in
th
e
f
o
r
m
o
f
t
h
e
co
m
b
i
n
atio
n
o
f
b
r
aille
f
ea
tu
r
e
an
d
e
m
b
o
s
s
ed
tr
ian
g
le,
cir
cle,
an
d
r
ec
tan
g
le
s
h
ap
ed
[
2
]
.
Un
f
o
r
tu
n
atel
y
,
t
h
ese
b
li
n
d
co
d
e
f
ea
tu
r
es
d
o
n
o
t
w
o
r
k
p
r
o
p
er
l
y
w
h
e
n
ev
er
t
h
e
b
an
k
n
o
tes
ar
e
cr
u
m
p
led
o
r
th
e
p
ap
er
m
o
n
e
y
ar
e
w
o
r
n
o
u
t.
T
o
el
i
m
i
n
ate
t
h
e
p
r
o
b
le
m
,
m
an
y
r
esear
ch
e
s
h
av
e
b
ee
n
co
n
d
u
cted
.
So
m
e
t
h
e
r
esear
c
h
es
p
r
o
d
u
ce
d
d
ev
ices
f
o
r
id
en
ti
f
y
i
n
g
an
d
r
ec
o
g
n
izi
n
g
b
an
k
n
o
tes
(
cu
r
r
en
c
y
)
[
3
]
,
[
4
]
.
T
h
o
u
g
h
th
e
d
ev
ice
s
w
o
r
k
w
ell,
th
e
y
ar
e
to
o
r
ig
id
an
d
d
ed
icate
d
d
ev
ic
es,
i.e
.
,
t
h
e
y
ca
n
b
e
u
s
ed
f
o
r
o
n
l
y
ce
r
tain
b
an
k
n
o
te
s
.
E
n
h
a
n
ce
m
e
n
t
o
f
d
ev
ice
f
u
n
ctio
n
alitie
s
n
ee
d
s
i
m
p
r
o
v
e
m
en
t o
f
d
ev
ice
cir
c
u
itr
y
.
Oth
er
r
esear
c
h
es
p
r
o
d
u
ce
d
ap
p
licatio
n
s
s
u
c
h
a
s
a
m
o
b
ile
a
p
p
licatio
n
f
o
r
c
u
r
r
en
c
y
r
ec
o
g
n
itio
n
an
d
au
th
e
n
tica
tio
n
[
5
]
.
Ho
w
e
v
er
,
ag
ain
it
d
o
es
w
o
r
k
o
n
l
y
f
o
r
a
s
p
ec
if
ic
a
n
d
ce
r
tai
n
cu
r
r
en
c
y
an
d
it
i
s
n
o
t
clea
r
w
h
et
h
er
it u
s
e
s
s
o
m
e
f
ea
t
u
r
e
d
etec
tio
n
m
e
th
o
d
f
o
r
r
ec
o
g
n
izi
n
g
t
h
e
o
b
j
ec
t.
T
h
is
p
ap
er
in
tr
o
d
u
ce
s
s
o
m
e
a
p
p
licatio
n
s
y
s
te
m
to
r
ec
o
g
n
iz
e
th
e
n
o
m
i
n
al
o
f
v
ar
io
u
s
b
an
k
n
o
te
s
o
r
cu
r
r
en
cies
f
o
r
v
is
u
all
y
i
m
p
air
ed
p
eo
p
le
w
ith
h
i
g
h
ac
c
u
r
ac
y
.
I
t
u
s
es
f
ea
t
u
r
e
ex
tr
ac
tio
n
alg
o
r
ith
m
ca
lled
OR
B
f
ea
t
u
r
e
d
escr
ip
to
r
[6
].
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
117
–
1
2
6
118
2.
T
H
E
O
RI
T
I
CAL R
E
V
I
E
WS
T
h
is
s
ec
tio
n
d
i
s
cu
s
s
e
s
s
o
m
e
f
u
n
d
a
m
en
tals
s
t
u
d
y
o
n
C
o
m
p
u
te
r
Vis
io
n
e
s
p
ec
iall
y
i
m
ag
e
p
r
o
ce
s
s
in
g
,
f
ea
t
u
r
e
d
etec
to
r
,
f
ea
tu
r
e
d
escr
ip
to
r
,
an
d
m
atc
h
i
n
g
al
g
o
r
ith
m
.
2
.
1
G
re
y
Sca
le
I
m
ag
e
p
r
o
ce
s
s
in
g
i
s
a
m
et
h
o
d
to
co
n
v
er
t
an
i
m
ag
e
in
to
a
d
i
g
ital
f
o
r
m
an
d
p
er
f
o
r
m
s
o
m
e
o
p
er
atio
n
o
n
it.
An
i
m
a
g
e
is
an
ar
r
a
y
o
r
m
atr
ix
o
f
p
i
x
els
r
ep
r
esen
ted
i
n
r
o
w
s
a
n
d
co
lu
m
n
s
.
I
n
w
h
ich
co
n
tai
n
s
in
f
o
r
m
atio
n
o
f
in
ten
s
it
y
r
ep
r
es
en
ted
b
y
B
lu
e
-
Gr
ee
n
-
R
ed
(
B
GR
)
o
r
g
r
a
y
-
s
ca
le
[
7
]
.
T
h
e
B
GR
i
m
a
g
e
co
n
ta
in
s
i
n
f
o
r
m
atio
n
o
f
b
l
u
e,
g
r
ee
n
,
a
n
d
r
ed
in
te
n
s
it
y
.
Me
an
w
h
ile,
g
r
a
y
-
s
ca
le
i
m
a
g
e
o
n
l
y
co
n
tai
n
t
h
e
i
n
ten
s
i
t
y
o
f
w
h
ite.
Sp
ec
i
f
icall
y
,
a
n
8
-
b
it
g
r
a
y
-
s
ca
le
i
m
a
g
e
co
n
ta
in
s
b
lack
in
te
n
s
it
y
th
at
th
e
v
alu
e
r
an
g
ed
f
r
o
m
0
to
2
5
5
.
T
h
e
lo
w
er
it
s
v
a
lu
e,
t
h
e
d
ar
k
er
th
e
i
m
a
g
e,
s
o
a
p
i
x
el
with
i
n
te
n
s
it
y
o
f
0
is
b
lack
,
m
ea
n
w
h
ile
a
p
ix
e
l
w
it
h
i
n
te
n
s
it
y
2
5
5
is
w
h
ite.
An
i
llu
s
tr
ati
o
n
o
f
p
i
x
el
i
n
a
g
r
a
y
-
s
ca
le
i
m
a
g
e
ca
n
b
e
s
ee
n
at
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
Gr
ay
-
Sca
le
I
llu
s
tr
ati
o
n
,
f
r
o
m
0
(
lef
t)
to
2
5
5
(
r
ig
h
t)
2
.
2
F
AST
F
ea
t
ure
Det
ec
t
o
r
Featu
r
e
is
a
p
iece
o
f
in
f
o
r
m
a
ti
o
n
in
i
m
a
g
e
th
at
co
n
tain
ed
in
k
e
y
p
o
in
t
s
th
at
ar
e
r
elev
an
t
to
th
e
i
m
a
g
e.
A
k
e
y
p
o
i
n
t it
s
elf
is
a
p
o
in
t i
n
an
i
m
ag
e
t
h
at
i
n
ter
es
tin
g
e
n
o
u
g
h
to
b
e
an
a
l
y
ze
d
.
Us
u
all
y
,
h
u
m
an
r
ec
o
g
n
ize
t
h
i
s
"
in
ter
esti
n
g
p
o
in
t”
as
d
o
t,
cr
o
s
s
,
o
r
co
r
n
er
.
T
h
er
e
ar
e
s
o
m
e
alg
o
r
ith
m
s
to
d
etec
t
f
ea
t
u
r
es
i
n
an
i
m
ag
e,
o
n
e
o
f
w
h
ic
h
is
F
AST
.
F
A
ST
(
Featu
r
es
f
r
o
m
A
cc
e
ler
ated
Seg
m
en
t
T
est)
is
an
alg
o
r
ith
m
th
at
u
s
ed
to
d
etec
t
a
f
ea
tu
r
e
k
e
y
p
o
in
t.
F
AST
alg
o
r
ith
m
is
v
er
y
f
ast,
b
ec
au
s
e
t
h
e
id
ea
is
it
w
o
r
k
s
b
y
o
n
l
y
co
m
p
ar
in
g
th
e
in
te
n
s
it
y
o
f
it
s
1
6
n
eig
h
b
o
r
in
g
p
ix
el
s
as it
is
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
Fig
u
r
e
2
.
T
est p
ix
el
(
p
)
an
d
its
1
6
s
u
r
r
o
u
n
d
in
g
p
ix
el
s
[
8
]
T
h
e
f
ir
s
t
s
tep
is
to
tak
e
a
te
s
t
p
ix
el
p
f
r
o
m
th
e
i
m
ag
e.
T
h
en
,
ass
u
m
e
t
h
at
th
e
i
n
ten
s
it
y
o
f
t
h
is
p
ix
el
i
s
I
p
.
Set a
th
r
esh
o
ld
in
ten
s
it
y
v
al
u
e
T
.
A
s
s
u
m
e
th
at
t
h
i
s
th
r
es
h
o
ld
in
ten
s
it
y
v
al
u
e
T
is
2
0
% o
f
th
e
tex
t p
ix
el.
Nex
t,
co
n
s
id
er
a
cir
cle
o
f
1
6
p
ix
els
s
u
r
r
o
u
n
d
i
n
g
th
e
test
p
ix
el
w
it
h
r
ad
iu
s
o
f
3
.
T
h
en
,
ch
ec
k
th
e
in
te
n
s
it
y
o
f
t
h
o
s
e
1
6
p
ix
el
s
wh
eth
er
it
is
ab
o
v
e
o
r
b
elo
w
t
h
e
I
p
b
y
t
h
e
v
a
lu
e
o
f
T
.
I
f
th
er
e
ar
e
m
o
r
e
t
h
an
1
2
p
ix
els
f
it
t
h
at
cr
iter
ia,
t
h
en
th
e
test
p
ix
el
ca
n
b
e
co
n
s
id
er
ed
as
an
i
n
ter
est
in
g
p
o
in
t.
R
ep
ea
t
th
e
p
r
o
ce
d
u
r
e
f
o
r
all
p
ix
els
f
r
o
m
t
h
e
i
m
a
g
e.
T
o
f
asten
t
h
e
alg
o
r
it
h
m
,
t
h
e
c
o
m
p
u
ter
ca
n
c
h
ec
k
t
h
e
p
ix
el
u
m
b
er
1
,
5
,
9
,
an
d
1
3
f
ir
s
t.
I
f
at
least
th
r
ee
o
u
t
o
f
f
o
u
r
p
ix
el
s
ar
e
ab
o
v
e
th
e
th
r
e
s
h
o
ld
v
a
lu
e,
t
h
en
c
h
ec
k
all
t
h
e
1
6
p
ix
els.
W
ith
t
h
i
s
ad
d
itio
n
al
s
tep
,
th
e
co
m
p
u
ter
w
ill
h
av
e
ea
r
l
y
in
f
o
r
m
atio
n
b
e
f
o
r
e
ch
ec
k
i
n
g
all
t
h
e
1
6
p
ix
els
[
9
]
.
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
P
a
p
er Mo
n
ey
R
ec
o
g
n
iz
er Usi
n
g
F
ea
tu
r
e
Descri
p
to
r
(
N
u
r
H
a
d
is
u
kma
n
a
)
119
2
.
3
B
RIE
F
F
ea
t
ure
Descript
o
r
Af
ter
d
etec
ti
n
g
k
e
y
p
o
in
ts
f
r
o
m
th
e
i
m
a
g
e,
t
h
e
n
e
x
t
s
tep
is
to
d
escr
ib
e
th
e
k
e
y
p
o
i
n
t
i
ts
elf
.
T
h
i
s
d
escr
ip
tio
n
is
to
f
i
n
d
th
e
s
i
m
il
ar
it
y
b
et
w
ee
n
2
k
e
y
p
o
in
t
s
.
T
h
e
p
r
o
ce
s
s
to
f
in
d
t
h
e
s
i
m
ilar
i
t
y
b
et
w
ee
n
f
ea
tu
r
es
w
il
l b
e
ex
p
lain
ed
f
u
r
t
h
er
in
t
h
e
m
atch
in
g
al
g
o
r
ith
m
.
T
h
er
e
ar
e
ter
m
s
s
u
c
h
as
s
ca
l
e
in
v
ar
ia
n
t
an
d
r
o
tatio
n
in
v
ar
ian
t.
A
s
ca
le
i
n
v
ar
ia
n
t
d
escr
i
p
to
r
m
ea
n
s
th
at
t
h
is
d
escr
ip
to
r
w
ill
d
etec
t
a
s
a
m
e
i
m
a
g
e
w
it
h
d
if
f
er
en
t
s
ca
les
as
s
i
m
ilar
.
Me
an
w
h
ile,
a
r
o
tatio
n
in
v
ar
ian
t
d
escr
ip
to
r
m
ea
n
s
t
h
at
th
is
d
esc
r
ip
to
r
w
il
l d
etec
t a
s
a
m
e
i
m
a
g
e
w
it
h
d
if
f
er
e
n
t a
n
g
le
o
f
r
o
tati
o
n
as si
m
ilar
.
T
h
er
e
ar
e
tw
o
t
y
p
e
s
o
f
d
escr
i
p
to
r
f
r
o
m
h
o
w
t
h
e
y
co
n
tai
n
t
h
e
d
escr
ip
tio
n
d
ata,
w
h
ic
h
ar
e
b
in
ar
y
an
d
n
o
n
-
b
in
ar
y
d
e
s
cr
ip
to
r
.
On
e
o
f
b
in
ar
y
f
ea
t
u
r
e
d
escr
ip
to
r
s
is
B
R
I
E
F
(
B
in
ar
y
R
o
b
u
s
t
I
n
d
ep
en
d
en
t
E
le
m
en
tar
y
Featu
r
es).
B
R
I
E
F
d
escr
ip
to
r
is
m
o
r
e
ef
f
i
cien
t
t
h
a
n
n
o
n
-
b
i
n
ar
y
f
ea
t
u
r
e
d
escr
ip
to
r
s
,
b
ec
au
s
e
it
is
u
s
in
g
a
b
in
ar
y
f
ea
t
u
r
e
t
h
at
ar
e
co
m
p
u
tatio
n
al
an
d
s
p
ac
e
ch
ea
p
.
B
R
I
E
F
w
o
r
k
s
b
y
r
a
n
d
o
m
l
y
ta
k
e
a
p
air
o
f
p
o
in
ts
A
an
d
B
in
a
k
e
y
p
o
in
t,
a
n
d
t
h
en
co
m
p
ar
e
i
ts
i
n
te
n
s
it
y
.
I
f
p
o
in
t
A
i
s
h
av
i
n
g
a
g
r
ea
ter
in
te
n
s
it
y
v
alu
e
th
an
p
o
in
t
B
,
th
e
n
i
t
w
il
l
p
r
o
d
u
ce
a
b
in
ar
y
o
f
1
,
els
e
it
w
ill
p
r
o
d
u
ce
b
in
ar
y
o
f
0
.
R
ep
ea
t
th
i
s
p
r
o
ce
s
s
u
n
t
il
2
5
6
ti
m
es.
Fin
a
ll
y
,
a
2
5
6
b
it f
ea
tu
r
e
i
s
p
r
o
d
u
ce
d
.
I
t u
s
es r
an
d
o
m
s
a
m
p
le
to
s
elec
t th
e
t
est lo
ca
tio
n
[
1
0
]
.
2
.
4
O
RB
Alg
o
rit
h
m
E
v
en
t
h
o
u
g
h
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
B
R
I
E
F
is
b
etter
th
an
n
o
n
-
b
in
ar
y
f
ea
tu
r
e
d
escr
ip
to
r
s
,
B
R
I
E
F
is
n
o
t
class
i
f
ied
as
r
o
tatio
n
i
n
v
ar
ia
n
ce
d
escr
ip
to
r
,
w
h
ic
h
m
ea
n
s
th
at
it
ca
n
n
o
t
d
etec
t
s
a
m
e
r
esu
lt
(
ca
lled
a
s
in
v
ar
ia
n
ce
)
i
f
th
e
o
b
j
ec
t is r
o
ta
ted
.
OR
B
(
Or
ien
ted
F
A
ST
an
d
R
o
tated
B
R
I
E
F)
is
an
alg
o
r
ith
m
th
a
t
co
m
b
in
ed
t
h
e
F
A
ST
d
etec
to
r
an
d
B
R
I
E
F
d
escr
ip
to
r
.
Si
m
ilar
to
B
R
I
E
F,
OR
B
al
s
o
p
r
o
d
u
ce
s
a
2
5
6
b
it
f
ea
t
u
r
e.
T
h
e
id
ea
o
f
t
h
is
alg
o
r
it
h
m
i
s
to
m
ak
e
a
b
i
n
ar
y
d
escr
ip
to
r
th
at
b
o
th
s
ca
le
an
d
r
o
tatio
n
in
v
ar
ia
n
t.
OR
B
w
o
r
k
s
b
y
c
alcu
la
tin
g
t
h
e
o
r
ien
tatio
n
w
h
e
n
d
etec
tin
g
th
e
k
e
y
p
o
i
n
t
u
s
in
g
F
AST
al
g
o
r
ith
m
.
I
t
ca
n
f
i
n
d
t
h
e
o
r
ien
tatio
n
b
y
s
i
m
p
l
y
ca
lc
u
lati
n
g
t
h
e
ce
n
tr
o
id
,
ce
n
ter
o
f
m
ass
,
o
f
th
e
p
atc
h
e
s
ar
o
u
n
d
ea
ch
k
e
y
p
o
in
ts
.
No
t
o
n
l
y
t
h
at,
b
y
m
ak
in
g
all
th
e
p
atch
e
s
u
n
if
o
r
m
with
ce
n
tr
o
id
,
it
tu
r
n
s
o
u
t
th
at
t
h
er
e
is
an
o
p
ti
m
a
l
v
alu
e
f
r
o
m
B
R
I
E
F d
escr
ip
to
r
th
at
ca
n
b
e
tr
ain
ed
i
n
s
tead
o
f
o
n
l
y
u
s
in
g
r
an
d
o
m
p
air
s
[
7
]
.
2
.
5
F
ea
t
ure
M
a
t
ching
Featu
r
e
Ma
tc
h
i
n
g
i
s
a
n
al
g
o
r
ith
m
t
h
at
i
s
u
s
i
n
g
f
ea
t
u
r
es
to
f
in
d
t
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
i
m
ag
es.
T
h
e
id
ea
o
f
f
in
d
i
n
g
a
m
atc
h
is
b
y
f
in
d
in
g
t
h
e
least
d
if
f
er
e
n
ce
b
etw
ee
n
f
ea
t
u
r
es.
T
h
is
d
if
f
er
e
n
ce
is
ca
lled
d
is
tan
ce
.
I
m
ag
e
s
to
b
e
m
atc
h
ed
ca
n
b
e
class
i
f
ied
as
q
u
er
y
i
m
a
g
e
an
d
tr
ain
i
m
a
g
e.
Q
u
er
y
i
m
a
g
e
i
s
th
e
i
m
a
g
e
w
h
o
s
e
f
ea
t
u
r
es
to
b
e
m
atc
h
ed
in
tr
ain
i
m
ag
e.
Q
u
er
y
i
m
ag
e
is
ca
p
t
u
r
ed
d
ir
ec
tly
f
r
o
m
ca
m
er
a.
Me
an
w
h
ile,
tr
ain
i
m
ag
e
is
a
s
et
o
f
i
m
ag
e
s
in
w
h
ic
h
th
e
f
ea
tu
r
e
s
o
f
th
e
i
m
a
g
es
h
av
e
b
ee
n
d
etec
ted
an
d
ex
tr
ac
ted
.
T
h
e
f
ea
tu
r
es
o
f
s
u
c
h
i
m
a
g
es
i
n
th
e
tr
ai
n
i
m
ag
e
ar
e
u
s
u
all
y
s
a
v
ed
in
to
f
i
le
o
r
d
ata
b
ase.
T
h
e
r
elatio
n
b
etw
ee
n
q
u
er
y
a
n
d
tr
ain
i
m
ag
e
s
is
s
h
o
w
n
b
y
F
ig
u
r
e
3
.
I
t
ca
n
b
e
s
ee
n
,
f
r
o
m
F
ig
u
r
e
3
,
th
at
ea
c
h
f
ea
t
u
r
e
in
q
u
er
y
i
m
ag
e
ca
n
o
n
l
y
h
av
e
a
n
o
t
h
er
o
n
e
m
atc
h
w
it
h
f
ea
t
u
r
e
i
n
tr
ai
n
i
m
a
g
e.
M
ea
n
w
h
ile,
ea
c
h
f
ea
tu
r
e
i
n
tr
ain
i
m
a
g
e
ca
n
h
a
v
e
m
u
ltip
le
m
atch
es
w
it
h
f
ea
tu
r
e
s
in
q
u
e
r
y
i
m
a
g
e.
Fig
u
r
e
3
.
Ma
tch
in
g
al
g
o
r
ith
m
d
em
o
n
s
tr
atio
n
B
r
u
te
f
o
r
ce
f
ea
tu
r
e
m
atc
h
i
n
g
i
s
a
m
et
h
o
d
to
co
m
p
ar
e
f
ea
t
u
r
e
s
in
q
u
er
y
an
d
tr
ai
n
i
m
a
g
es
b
y
s
ea
r
ch
i
n
g
th
e
clo
s
est
d
is
ta
n
ce
b
et
w
ee
n
a
f
ea
tu
r
e
in
q
u
er
y
i
m
a
g
e
an
d
f
ea
tu
r
es
in
tr
ai
n
i
m
a
g
e.
T
h
is
p
r
o
ce
s
s
w
il
l
b
e
d
o
n
e
f
o
r
all
f
ea
t
u
r
es
in
q
u
er
y
i
m
ag
e
.
So
,
if
th
er
e
is
M
n
u
m
b
er
o
f
d
ata
in
q
u
er
y
i
m
a
g
e
an
d
N
n
u
m
b
er
o
f
d
ata
in
tr
ain
i
m
a
g
e,
th
er
e
w
ill b
e
M
x
N
p
r
o
ce
s
s
o
f
h
a
m
m
i
n
g
d
i
s
tan
ce
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
117
–
1
2
6
120
Fig
u
r
e
4
s
h
o
w
s
t
h
e
p
r
o
ce
s
s
o
f
b
r
u
te
f
o
r
ce
f
ea
t
u
r
e
m
atc
h
i
n
g
alg
o
r
ith
m
.
T
h
e
f
ir
s
t
s
tep
(
a)
s
h
o
w
s
t
h
e
p
r
o
ce
s
s
o
n
f
in
d
i
n
g
th
e
s
h
o
r
te
s
t
d
is
tan
ce
b
et
w
ee
n
a
f
ea
t
u
r
e
in
q
u
er
y
i
m
a
g
e
an
d
all
f
ea
t
u
r
es
in
tr
ain
i
m
a
g
e.
E
ac
h
li
n
e
in
t
h
e
p
ict
u
r
e
s
h
o
w
s
th
e
h
a
m
m
i
n
g
d
is
ta
n
ce
p
r
o
ce
s
s
o
cc
u
r
s
i
n
t
h
e
p
r
o
ce
s
s
.
Me
an
w
h
ile,
th
e
t
h
ick
r
ed
lin
e
s
h
o
w
s
t
h
e
m
in
i
m
u
m
d
i
s
t
an
ce
.
Step
(
a)
to
s
tep
(
c)
s
h
o
w
s
th
at
f
ir
s
t,
s
ec
o
n
d
,
an
d
th
ir
d
f
ea
tu
r
e
in
q
u
er
y
i
m
a
g
e
d
o
n
e
r
esp
ec
tiv
el
y
.
Fin
all
y
,
th
e
la
s
t
s
tep
(
d
)
s
h
o
w
s
t
h
at
ea
ch
f
ea
tu
r
e
i
n
q
u
er
y
i
m
ag
e
alr
ea
d
y
h
as
it
s
m
atc
h
,
o
r
f
in
d
s
it
s
m
in
i
m
u
m
d
is
tan
ce
.
Fig
u
r
e
4
.
B
r
u
te
Fo
r
ce
Featu
r
e
Ma
tch
i
n
g
2
.
5
.
1
K
-
M
a
j
o
rit
y
Alg
o
rit
h
m
T
h
e
f
ea
tu
r
e
m
atc
h
i
n
g
ca
n
b
e
s
p
ee
d
u
p
b
y
i
m
p
le
m
e
n
ti
n
g
K
-
Ma
j
o
r
ity
C
lu
s
ter
in
g
to
r
ed
u
ce
n
u
m
b
er
o
f
f
ea
t
u
r
es
i
n
th
e
l
is
t.
K
-
Ma
j
o
r
ity
alg
o
r
it
h
m
w
o
r
k
s
b
y
f
ir
s
tl
y
ch
o
o
s
in
g
K
n
u
m
b
er
o
f
d
ata
t
h
at
w
ill
b
e
u
s
ed
as
ce
n
tr
o
id
.
C
en
tr
o
id
is
a
ce
n
ter
o
f
clu
s
ter
,
w
h
ic
h
all
o
f
t
h
e
co
r
r
esp
o
n
d
in
g
d
ata
as
s
i
g
n
ed
to
.
T
h
e
n
ex
t
s
tep
is
to
ass
i
g
n
t
h
e
co
r
r
esp
o
n
d
in
g
d
ata
to
th
e
ce
n
tr
o
id
b
y
ch
o
o
s
i
n
g
t
h
e
clo
s
est
d
i
s
tan
ce
b
et
w
ee
n
t
h
e
d
ata
an
d
ce
n
tr
o
id
u
s
i
n
g
h
a
m
m
in
g
d
is
ta
n
ce
.
Af
te
r
ass
ig
n
i
n
g
all
t
h
e
d
ata
to
co
r
r
esp
o
n
d
in
g
ce
n
tr
o
id
,
th
e
n
ex
t
s
tep
is
to
f
in
d
th
e
n
e
w
ce
n
tr
o
id
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
in
g
d
ata
b
y
u
s
in
g
m
aj
o
r
i
t
y
v
o
ti
n
g
.
Si
n
ce
t
h
e
d
ata
is
i
n
b
in
ar
y
s
tr
i
n
g
f
o
r
m
,
m
aj
o
r
ity
v
o
ti
n
g
ca
n
w
o
r
k
s
w
e
l
l b
y
c
h
o
o
s
i
n
g
th
e
“w
i
n
n
er
”
b
y
co
u
n
tin
g
th
e
n
u
m
b
er
o
f
v
o
tes
b
et
w
ee
n
0
’
s
o
r
1
’
s
in
ea
c
h
b
it.
T
h
e
p
r
o
ce
s
s
o
f
h
a
m
m
in
g
d
is
tan
ce
,
m
aj
o
r
it
y
v
o
ti
n
g
,
a
n
d
u
p
d
ati
n
g
ce
n
tr
o
id
w
il
l
b
e
r
ep
ea
ted
u
n
ti
l
th
e
ce
n
tr
o
id
is
n
o
t
ch
a
n
g
ed
an
y
m
o
r
e.
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
ai
m
o
f
t
h
e
r
e
s
ea
r
ch
is
to
d
ev
elo
p
an
ap
p
licatio
n
t
h
at
co
u
ld
d
etec
t
t
h
e
n
o
m
i
n
al
o
f
t
h
e
b
an
k
n
o
tes
an
d
/o
r
th
e
p
ap
er
m
o
n
e
y
o
f
s
ev
er
al
cu
r
r
e
n
cies
i
m
p
le
m
en
ti
n
g
f
u
n
d
a
m
e
n
tals
th
a
t
h
a
v
e
b
e
en
d
is
c
u
s
s
ed
in
t
h
e
p
r
ev
io
u
s
s
ec
tio
n
.
T
h
is
ap
p
licat
io
n
w
il
l
h
elp
a
n
d
as
s
is
t
t
h
e
v
is
u
all
y
i
m
p
air
ed
p
eo
p
le
to
d
eter
m
i
n
e
t
h
e
v
al
u
es
o
f
th
e
p
ap
er
m
o
n
e
y
t
h
e
y
h
a
v
e.
I
t,
th
er
ef
o
r
e
u
s
e
s
R
ap
id
A
p
p
licat
io
n
Dev
elo
p
m
e
n
t (
R
AD)
f
o
r
t
h
e
ap
p
licatio
n
.
T
h
e
ap
p
licatio
n
co
n
s
is
t
s
o
f
t
w
o
m
ai
n
p
ar
ts
th
a
t
ar
e
tr
ain
i
m
a
g
e
g
e
n
er
ato
r
an
d
n
o
m
i
n
al
o
r
i
m
ag
e
r
ea
d
er
.
T
h
e
f
ir
s
t p
ar
t o
f
t
h
e
ap
p
licatio
n
w
i
ll
g
en
er
ate
d
ataset
f
r
o
m
p
ap
er
m
o
n
e
y
i
m
a
g
es
(
tr
ain
i
m
a
g
e)
a
n
d
s
a
v
e
th
e
s
et
i
n
to
d
atab
ase.
T
h
e
s
et
w
il
l
b
e
u
s
ed
a
s
r
e
f
er
en
ce
s
f
o
r
th
e
s
ec
o
n
d
p
ar
t
o
f
t
h
e
ap
p
lica
tio
n
to
id
e
n
ti
f
y
t
h
e
i
m
a
g
e
th
at
i
s
ca
p
tu
r
ed
(
q
u
er
y
i
m
ag
e)
a
n
d
g
i
v
e
co
r
r
ec
t
an
d
v
alid
s
o
lu
tio
n
o
f
t
h
e
i
m
ag
e
w
h
ic
h
is
t
h
e
n
o
m
in
al
o
f
th
e
p
ap
er
m
o
n
e
y
.
T
h
e
ap
p
licatio
n
m
o
d
el
is
s
h
o
w
n
b
y
F
i
g
u
r
e
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
P
a
p
er Mo
n
ey
R
ec
o
g
n
iz
er Usi
n
g
F
ea
tu
r
e
Descri
p
to
r
(
N
u
r
H
a
d
is
u
kma
n
a
)
121
Fig
u
r
e
5
.
W
o
r
k
f
lo
w
o
f
t
h
e
A
p
p
licatio
n
4.
CO
M
P
O
NE
NT
D
E
T
A
I
L
S
Fig
u
r
e
5
s
h
o
w
s
co
m
p
o
n
e
n
ts
o
f
th
e
t
w
o
p
ar
ts
o
f
th
e
ap
p
licatio
n
.
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
b
r
i
ef
l
y
ab
o
u
t
r
o
les o
f
th
e
co
m
p
o
n
e
n
ts
.
4
.
1
Da
t
a
s
et
G
ener
a
t
o
r
I
n
o
r
d
er
to
g
en
er
ate
d
ataset
th
at
is
s
av
ed
i
n
d
atab
ase,
th
i
s
p
ar
t h
as b
ee
n
d
iv
id
ed
in
to
s
ev
er
a
l
co
m
p
o
n
e
n
t
s
.
4
.
1
.
1
Select
T
ra
in I
m
a
g
e
T
h
is
co
m
p
o
n
e
n
t
w
i
ll
s
elec
t
a
s
et
o
f
p
ap
er
m
o
n
e
y
i
m
ag
e
s
t
o
b
e
u
s
ed
a
s
t
ra
in
i
m
a
g
e.
E
ac
h
o
f
t
h
e
i
m
a
g
es
w
ill
b
e
s
a
v
ed
in
to
a
f
il
e.
T
h
ese
f
ile
m
u
s
t
b
e
s
av
ed
i
n
to
a
s
p
ec
if
ic
f
o
ld
er
in
w
h
ich
t
h
is
co
m
p
o
n
en
t
w
i
ll
ea
s
il
y
p
ic
k
all
o
f
th
e
f
ile
s
.
E
v
er
y
p
ap
er
m
o
n
e
y
h
a
s
t
w
o
i
m
ag
e
s
b
ec
au
s
e
p
ap
er
m
o
n
e
y
h
as
t
w
o
s
id
es.
T
h
e
co
m
p
o
n
e
n
t
al
s
o
p
ar
s
es
th
e
p
r
o
p
er
ties
o
f
ea
ch
i
m
a
g
e
v
ia
it
s
f
ilen
a
m
e
i
n
to
n
o
m
in
a
l,
cu
r
r
en
c
y
,
a
n
d
s
id
e
o
f
th
e
i
m
a
g
e
an
d
s
a
v
ed
in
to
s
o
m
e
d
ata
s
tr
u
ct
u
r
e
ca
lled
P
DT
(
P
ictu
r
e
DaT
a)
in
d
ataset.
4
.
1
.
2
I
m
a
g
e
I
dentif
ier
a
nd
E
x
t
ra
c
t
o
r
T
h
is
co
m
p
o
n
en
t
w
ill
id
e
n
ti
f
y
o
r
d
etec
t
k
e
y
p
o
in
ts
o
f
all
i
m
a
g
es
i
n
t
h
e
tr
ain
i
m
a
g
e.
Af
ter
t
h
at,
it
w
il
l
tr
an
s
f
o
r
m
th
e
s
e
k
e
y
p
o
in
t
s
i
n
t
o
th
e
f
ea
t
u
r
es
o
f
t
h
e
i
m
a
g
e
s
.
T
h
ese
t
w
o
i
m
p
o
r
ta
n
t
w
o
r
k
s
ar
e
ac
h
ie
v
ed
b
y
OR
B
alg
o
r
ith
m
.
Ke
y
p
o
in
t
id
e
n
ti
f
ic
a
tio
n
s
ar
e
d
o
n
e
b
y
O
R
B
d
esc
r
ip
to
r
w
h
er
ea
s
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
s
ar
e
co
n
d
u
cted
b
y
i
m
p
le
m
e
n
ti
n
g
O
R
B
d
escr
i
p
to
r
.
Fig
u
r
e
6
s
h
o
w
s
k
e
y
p
o
in
t
id
e
n
ti
f
icatio
n
o
f
I
n
d
o
n
es
ia
p
ap
er
m
o
n
e
y
(
I
DR
)
w
h
o
s
e
n
o
m
i
n
al
i
s
2
0
.
0
0
0
r
u
p
iah
s
.
T
h
e
i
m
a
g
e
f
ea
tu
r
e
s
d
ata
ar
e
s
av
ed
in
to
a
d
if
f
er
e
n
t
d
ata
s
tr
u
ctu
r
e
s
n
a
m
ed
as
T
C
0
(
T
r
an
s
f
o
r
m
a
n
d
C
o
m
p
ile
)
in
t
h
e
d
ataset.
T
h
e
ex
i
s
te
n
ce
o
f
T
C
0
is
cr
u
cial
e
s
p
ec
iall
y
i
n
f
ea
tu
r
e
m
atc
h
i
n
g
b
et
w
ee
n
q
u
er
y
i
m
a
g
e
an
d
an
i
m
ag
e
i
n
tr
ai
n
i
m
a
g
e.
Fig
u
r
e
6
.
Ke
y
p
o
in
t I
d
en
ti
f
icat
io
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
117
–
1
2
6
122
4
.
1
.
3
F
ea
t
ure
Clus
t
er
I
n
o
r
d
er
to
r
ed
u
ce
n
u
m
b
er
o
f
f
ea
t
u
r
es
o
f
tr
ain
i
m
ag
e
,
th
e
s
e
f
ea
t
u
r
es
ca
n
b
e
cl
u
s
ter
ed
b
y
u
s
i
n
g
K
-
Ma
j
o
r
ity
al
g
o
r
ith
m
t
h
at
i
s
b
r
ief
l
y
ex
p
lai
n
ed
i
n
s
ec
t
io
n
2
.
5
.
1
.
T
h
e
r
esu
lt o
f
f
ea
t
u
r
e
cl
u
s
ter
i
n
g
w
ill
b
e
s
av
ed
i
n
to
an
o
th
er
d
ata
s
tr
u
ct
u
r
e,
n
a
m
ed
as
T
C
1
in
th
e
d
ataset.
Us
in
g
K
-
Ma
j
o
r
it
y
al
g
o
r
ith
m
,
n
u
m
b
er
f
ea
tu
r
e
e
n
tr
ies
i
n
T
C
0
w
il
l b
e
ass
u
m
ed
p
o
in
t
s
wh
ile
t
h
e
en
tr
ie
s
in
T
C
1
w
i
ll b
ec
o
m
e
ce
n
tr
o
id
s
.
4
.
1
.
4
Da
t
a
s
et
Co
nfig
ura
t
io
n
A
ll
d
ata
th
at
ar
e
p
r
o
d
u
ce
d
an
d
s
a
v
ed
in
ap
p
r
o
p
r
iate
d
ata
s
tr
u
ct
u
r
es
at
p
r
ev
io
u
s
s
ta
g
e
s
m
u
s
t
b
e
co
n
f
i
g
u
r
ed
as
d
a
ta
s
et
in
s
u
c
h
a
w
a
y
t
h
at
it
w
ill b
e
ea
s
y
to
r
e
tr
iev
e
to
m
atch
a
n
i
m
a
g
e
o
f
tr
ain
i
m
a
g
e
an
d
q
u
er
y
i
m
a
g
e
an
d
t
h
er
e
f
o
r
e
it
co
u
ld
s
h
o
w
th
e
n
o
m
i
n
al
v
al
u
e
o
f
t
h
e
q
u
er
y
i
m
a
g
e.
T
h
e
co
n
f
i
g
u
r
at
i
o
n
o
f
t
h
e
d
ataset
is
s
h
o
w
n
b
y
F
i
g
u
r
e
7
.
Fig
u
r
e
7
.
Data
s
et
C
o
n
f
i
g
u
r
atio
n
Sin
ce
n
u
m
b
er
o
f
en
tr
ies
in
T
C
1
is
less
th
a
n
th
a
t
o
f
en
tr
ies
in
T
C
0
th
en
an
ad
d
itio
n
al
d
a
ta
s
tr
u
ct
u
r
e
m
u
s
t
b
e
ad
d
ed
.
T
h
is
d
ata
s
tr
u
ctu
r
e,
n
a
m
ed
as
T
C
r
1
,
h
as
a
f
u
n
ctio
n
as
r
o
u
ti
n
g
tab
le
th
at
m
ap
s
o
n
e
o
r
m
o
r
e
en
tr
ies i
n
T
C
0
o
n
to
o
n
e
en
tr
y
i
n
T
C
1
.
4
.
2
I
m
a
g
e
Rea
der
T
h
is
s
ec
o
n
d
p
ar
t
o
f
th
e
ap
p
li
ca
tio
n
h
as
al
s
o
s
ev
er
al
co
m
p
o
n
en
t
s
;
ea
ch
o
f
w
h
ich
h
as
d
if
f
er
en
t
a
n
d
s
p
ec
if
ic
r
o
le
as d
is
c
u
s
s
ed
b
r
ief
l
y
b
el
o
w
.
4
.
2
.
1
View
I
m
a
g
e
T
h
e
s
ec
o
n
d
p
ar
t
o
f
t
h
e
ap
p
li
ca
tio
n
s
tar
ts
b
y
v
ie
w
i
n
g
a
n
i
m
ag
e
o
f
p
ap
er
m
o
n
e
y
o
f
th
e
s
elec
ted
cu
r
r
en
c
y
.
T
h
is
ac
tio
n
is
ac
h
ie
v
ed
b
y
ac
ti
v
ati
n
g
t
h
e
ca
m
er
a
t
h
at
i
s
e
m
b
ed
d
ed
in
a
m
o
b
ile
d
ev
ice.
T
h
is
p
r
o
ce
s
s
w
il
l
ta
k
e
s
o
m
e
d
u
r
atio
n
o
f
ti
m
e
s
in
ce
it
al
s
o
ac
ti
v
ates
t
h
e
s
e
co
n
d
co
m
p
o
n
en
t
o
f
I
m
a
g
e
R
e
ad
er
to
id
en
tify
k
e
y
p
o
in
ts
o
f
t
h
e
i
m
a
g
e.
4
.
2
.
2
I
m
a
g
e
I
dentif
ier
a
nd
E
x
t
ra
c
t
o
r
Af
ter
ac
ti
v
ati
n
g
th
e
m
o
b
ile
d
ev
ice
ca
m
er
a
w
h
ic
h
v
ie
w
s
a
p
ap
er
m
o
n
e
y
i
m
a
g
e,
th
i
s
co
m
p
o
n
en
t
is
au
to
m
at
icall
y
ac
ti
v
ated
.
I
t
s
ta
r
ts
d
et
ec
tin
g
k
e
y
p
o
in
t
s
o
f
t
h
e
i
m
a
g
e
an
d
t
h
en
cr
ea
te
s
an
d
ex
tr
ac
ts
f
ea
t
u
r
es
o
f
th
e
i
m
ag
e
f
r
o
m
t
h
e
k
e
y
p
o
in
t
s
.
T
h
e
f
ea
tu
r
es o
f
t
h
e
i
m
ag
e
ar
e
s
en
t t
h
e
n
e
x
t c
o
m
p
o
n
en
t.
T
h
is
p
r
o
ce
s
s
u
s
es
s
i
m
ilar
al
g
o
r
ith
m
a
s
d
escr
ib
ed
in
s
ec
tio
n
4
.
1
.
2
.
T
h
e
d
if
f
er
en
ce
is
th
at
th
i
s
co
m
p
o
n
e
n
t
id
e
n
ti
f
ies
k
e
y
p
o
in
ts
a
n
d
ex
tr
ac
t
s
th
e
m
i
n
to
f
e
atu
r
es
o
f
s
in
g
le
i
m
a
g
e
w
h
ile
th
e
co
m
p
o
n
e
n
t
i
n
s
ec
tio
n
4
.
1
.
2
im
p
le
m
e
n
ts
t
h
e
s
a
m
e
alg
o
r
it
h
m
f
o
r
a
s
et
o
f
i
m
a
g
es.
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
P
a
p
er Mo
n
ey
R
ec
o
g
n
iz
er Usi
n
g
F
ea
tu
r
e
Descri
p
to
r
(
N
u
r
H
a
d
is
u
kma
n
a
)
123
4
.
2
.
3
F
ea
t
ure
M
a
t
cher
T
h
is
co
m
p
o
n
en
t
r
u
n
s
w
h
e
n
e
v
er
th
e
f
ea
t
u
r
es
o
f
i
m
ag
e
g
e
n
er
ated
b
y
t
h
e
p
r
ev
io
u
s
co
m
p
o
n
en
t
ar
e
r
ea
d
y
.
T
h
e
r
o
le
o
f
th
is
co
m
p
o
n
en
t
i
s
to
f
i
n
d
an
i
m
a
g
e
in
t
h
e
d
ataset
th
at
h
as
s
i
m
i
lar
f
ea
t
u
r
es
w
it
h
t
h
e
i
m
a
g
e
th
at
is
v
ie
w
ed
b
y
th
e
ca
m
er
a.
I
t
s
ea
r
ch
es
th
e
f
ea
t
u
r
es
in
T
C
1
b
y
f
i
n
d
in
g
t
h
e
s
m
alles
t
h
a
m
m
i
n
g
d
is
ta
n
ce
.
T
h
is
is
d
o
n
e
b
y
u
s
i
n
g
Ha
m
m
i
n
g
b
r
u
te
f
o
r
ce
alg
o
r
ith
m
.
O
n
ce
th
i
s
s
tep
is
co
m
p
leted
,
th
e
p
r
o
ce
s
s
co
n
tin
u
es
f
i
n
d
in
g
th
e
i
n
d
ex
o
f
th
e
f
ea
t
u
r
es
i
n
T
C
0
th
r
o
u
g
h
T
C
r
1
.
T
h
en
it
u
s
es
th
e
T
C
0
in
d
e
x
to
g
et
th
e
c
o
r
r
ec
t
d
a
ta
th
at
ar
e
n
o
m
i
n
al,
s
id
e
a
n
d
cu
r
r
en
c
y
o
f
th
e
i
m
ag
e
i
n
P
DT
.
4
.
2
.
4
Sh
o
w
Resul
t
T
h
is
co
m
p
o
n
e
n
t
h
as
r
o
le
to
s
h
o
w
t
h
e
r
esu
lt
f
r
o
m
t
h
e
p
r
ev
io
u
s
s
ta
g
e
(
co
m
p
o
n
en
t)
.
T
h
e
r
esu
lt
is
ac
tu
all
y
d
ata
tex
t
co
n
ta
in
i
n
g
t
h
e
in
f
o
r
m
at
io
n
o
f
t
h
e
n
o
m
in
a
l,
th
e
s
id
e
an
d
th
e
c
u
r
r
en
c
y
o
f
th
e
p
ap
er
m
o
n
e
y
i
m
a
g
e
t
h
at
i
s
v
ie
w
ed
b
y
th
e
c
a
m
er
a
o
f
a
m
o
b
ile
d
e
v
ice.
T
h
is
d
ata
te
x
t
i
s
t
h
en
p
ass
ed
to
an
A
P
I
th
at
co
u
ld
co
n
v
er
t t
h
e
d
ata
tex
t i
n
to
a
s
p
ee
ch
.
E
v
e
n
tu
a
ll
y
t
h
e
ap
p
licatio
n
is
u
s
i
n
g
E
n
g
lis
h
-
b
ased
tex
t t
o
s
p
ee
ch
A
P
I
.
5.
RE
SU
L
T
AND
ANA
L
YS
I
S
Th
e
d
ev
elo
p
m
e
n
t o
f
t
h
e
ap
p
licatio
n
h
a
s
s
h
o
w
n
s
e
v
er
al
t
h
in
g
s
:
a.
I
t
p
r
o
ce
s
s
es
a
s
et
o
f
i
m
a
g
es
f
r
o
m
6
d
i
f
f
er
en
t
cu
r
r
en
c
ies
,
i
.
e.
,
I
n
d
o
n
esia
n
R
u
p
ia
h
(
I
DR
)
,
th
e
Un
i
ted
Stated
o
f
Am
er
ican
Do
llar
(
USD)
,
Au
s
tr
alia
n
Do
llar
(
AUD)
,
E
u
r
o
p
ea
n
C
o
m
m
u
n
it
y
E
u
r
o
(
E
UR
)
.
Un
ited
K
i
n
g
d
o
m
P
o
u
n
d
s
ter
li
n
g
(
GB
P
)
,
an
d
J
ap
an
Yen
(
J
P
Y
)
.
b.
I
t p
r
o
d
u
ce
s
ar
o
u
n
d
2
5
0
0
OR
B
f
ea
tu
r
e
s
f
o
r
th
e
i
m
a
g
es
.
R
es
u
lts
o
f
t
h
e
ap
p
licatio
n
h
a
v
e
b
ee
n
co
m
p
ar
ed
to
o
t
h
er
s
,
esp
ec
iall
y
[
4
]
f
o
r
a
s
et
o
f
n
o
m
i
n
als
I
D
R
cu
r
r
en
c
y
.
C
o
m
p
ar
i
s
o
n
s
ar
e
d
o
n
e
i
n
t
w
o
a
s
p
ec
ts
:
th
e
ac
cu
r
ac
y
o
f
r
ec
o
g
n
izin
g
t
h
e
n
o
m
in
a
ls
an
d
r
esp
o
n
s
e
ti
m
e
o
f
th
e
ap
p
licatio
n
s
.
T
h
is
s
ec
tio
n
w
o
u
ld
also
s
h
o
w
t
h
e
r
e
s
u
l
ts
o
f
t
h
e
ap
p
licatio
n
in
t
h
e
t
w
o
asp
ec
ts
f
o
r
all
o
th
e
r
cu
r
r
ec
ies
o
n
th
e
av
er
a
g
e.
5
.
1
Rec
o
g
nitio
n Ac
cura
cy
o
f
T
wo
M
et
ho
ds
Fig
u
r
e
8
s
h
o
w
s
t
h
e
ap
p
licatio
n
ac
c
u
r
ac
y
in
d
etec
ti
n
g
an
d
r
e
co
g
n
izi
n
g
t
h
e
c
u
r
r
en
c
y
n
o
m
in
als.
I
t
al
s
o
s
h
o
w
s
t
h
e
ac
cu
r
ac
y
o
f
[
4
]
to
r
ec
o
g
n
ize
th
e
n
o
m
in
al
s
.
Fi
g
u
r
e
8
,
an
d
also
f
ig
u
r
e
9
,
u
s
e
O
C
R
a
n
d
OR
B
in
t
h
e
leg
en
d
to
r
ep
r
esen
t t
h
is
ap
p
lic
atio
n
an
d
[
4
]
.
Sev
er
al
t
h
in
g
s
ca
n
b
e
p
o
in
ted
o
u
t f
r
o
m
f
i
g
u
r
e
8
.
a.
L
e
g
en
d
O
R
B
r
ep
r
esen
ts
r
ec
o
g
n
itio
n
m
et
h
o
d
s
th
a
t u
s
ed
b
y
t
h
is
ap
p
licatio
n
w
h
er
ea
s
OC
R
is
u
s
ed
b
y
[
4
]
.
b.
No
m
i
n
als
o
f
I
DR
c
u
r
r
en
c
y
ar
e
1
,
0
0
0
,
2
,
0
0
0
,
5
,
0
0
0
,
1
0
,
0
0
0
,
2
0
,
0
0
0
,
5
0
,
0
0
0
,
an
d
1
0
0
,
0
0
0
r
u
p
iah
s
,
w
h
ic
h
b
ec
o
m
e
X
-
a
x
is
.
c.
T
h
e
m
i
n
i
m
u
m
ac
c
u
r
ac
y
v
a
lu
e
th
at
is
o
b
tain
ed
b
y
OR
B
m
et
h
o
d
is
8
7
%
f
o
r
5
0
0
0
r
u
p
iah
,
w
h
er
ea
s
OC
R
p
r
o
d
u
ce
s
m
in
i
m
u
m
v
al
u
e
ar
o
u
n
d
5
5
% f
o
r
th
e
s
a
m
e
n
o
m
in
a
l.
d.
T
h
e
m
ax
i
m
u
m
v
al
u
e
o
b
tai
n
e
d
b
y
O
R
B
is
ar
o
u
n
d
9
7
%
wh
ich
h
ap
p
en
s
f
o
r
1
0
0
0
0
0
r
u
p
iah
.
T
h
e
s
a
m
e
th
i
n
g
al
s
o
h
ap
p
en
s
i
n
O
C
R
f
o
r
2
0
0
0
0
,
5
0
0
0
0
an
d
1
0
0
0
0
0
r
u
p
iah
s
.
e.
OR
B
m
et
h
o
d
p
r
o
d
u
ce
s
m
o
r
e
s
tab
le
r
esu
lt
i
n
r
ec
o
g
n
izin
g
t
h
e
n
o
m
i
n
als
co
m
p
ar
ed
to
OC
R
.
OR
B
g
iv
e
s
th
e
d
if
f
er
en
ce
ar
o
u
n
d
1
0
%
b
etw
ee
n
m
in
i
m
u
m
an
d
m
ax
i
m
u
m
v
al
u
e
s
.
OC
R
p
r
o
d
u
ce
s
a
b
ig
g
er
d
i
f
f
er
e
n
ce
v
alu
e
t
h
at
i
s
4
2
%.
f.
On
t
h
e
av
er
a
g
e,
OR
B
p
r
o
d
u
ce
s
ar
o
u
n
d
9
2
.
8
6
%
o
f
ac
cu
r
ac
y
w
h
ic
h
is
b
etter
t
h
a
n
OC
R
t
h
at
g
i
v
es
ar
o
u
n
d
8
5
.
7
1
%.
Fig
u
r
e
8
.
I
DR
N
o
m
i
n
als
-
R
ec
o
g
n
iz
in
g
A
cc
u
r
ac
y
0
20
40
60
80
1
0
0
1
2
0
1
0
0
0
2
0
0
0
5
0
0
0
1
0
0
0
0
2
0
0
0
0
5
0
0
0
0
1
0
0
0
0
0
Pe
r
c
e
n
t
a
g
e
%
Re
c
ogn
ition
Ac
c
u
r
ac
y
O
C
R
O
R
B
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
117
–
1
2
6
124
5
.
2
Respo
ns
e
T
i
m
e
o
f
T
w
o
M
et
ho
ds
Fig
u
r
e
9
s
h
o
w
s
t
h
e
ap
p
licatio
n
r
esp
o
n
s
e
ti
m
e
in
d
etec
ti
n
g
an
d
r
ec
o
g
n
izi
n
g
t
h
e
cu
r
r
e
n
c
y
n
o
m
in
al
s
.
I
t
also
s
h
o
w
s
t
h
e
ac
c
u
r
ac
y
o
f
[
4
]
to
r
ec
o
g
n
ize
th
e
n
o
m
i
n
als.
Fig
u
r
e
9
.
I
DR
No
m
i
n
als
-
R
ec
o
g
n
iz
in
g
R
e
s
p
o
n
s
e
T
i
m
e
Sev
er
al
t
h
in
g
s
ca
n
b
e
p
o
in
ted
o
u
t f
r
o
m
F
ig
u
r
e
9
.
a.
No
m
i
n
als
o
f
I
DR
c
u
r
r
en
c
y
ar
e
1
,
0
0
0
,
2
,
0
0
0
,
5
,
0
0
0
,
1
0
,
0
0
0
,
2
0
,
0
0
0
,
5
0
,
0
0
0
,
an
d
1
0
0
,
0
0
0
r
u
p
iah
s
.
T
h
e
y
f
u
n
ctio
n
as X
-
ax
is
.
b.
T
h
e
lo
n
g
est
r
esp
o
n
s
e
ti
m
e
p
r
o
d
u
ce
d
b
y
O
R
B
m
eth
o
d
i
s
ar
o
u
n
d
4
.
7
s
ec
o
n
d
f
o
r
1
0
0
0
0
r
u
p
iah
,
w
h
er
ea
s
OC
R
p
r
o
d
u
ce
s
t
h
e
lo
n
g
est r
es
p
o
n
s
e
ti
m
e
i
s
7
s
ec
o
n
d
,
w
h
ic
h
h
ap
p
en
s
f
o
r
5
0
0
0
r
u
p
iah
.
c.
T
h
e
f
astes
t
r
e
s
p
o
n
s
e
ti
m
e
p
r
o
d
u
ce
d
b
y
O
R
B
is
ar
o
u
n
d
4
.
3
s
ec
o
n
d
w
h
ic
h
h
ap
p
en
s
f
o
r
2
0
0
0
an
d
1
0
0
0
0
0
r
u
p
iah
s
.
T
h
e
OC
R
p
r
o
d
u
ce
s
th
e
f
a
s
te
s
t r
esp
o
n
s
e
ti
m
e
o
f
4
.
2
s
ec
o
n
d
,
w
h
ich
h
ap
p
en
s
f
o
r
1
0
0
0
0
0
r
u
p
iah
.
d.
OR
B
m
et
h
o
d
p
r
o
d
u
ce
s
m
o
r
e
s
tab
le
p
er
f
o
r
m
a
n
ce
i
n
r
esp
o
n
s
e
t
i
m
e
co
m
p
ar
ed
to
OC
R
.
OR
B
g
i
v
es
th
e
d
if
f
er
e
n
ce
ar
o
u
n
d
0
.
4
s
ec
o
n
d
b
et
w
ee
n
m
in
i
m
u
m
a
n
d
m
a
x
i
m
u
m
v
al
u
es.
O
C
R
g
iv
e
s
a
b
i
g
g
er
d
i
f
f
er
en
ce
v
alu
e
t
h
at
i
s
2
.
8
s
ec
o
n
d
e.
On
th
e
a
v
er
ag
e,
O
R
B
p
r
o
d
u
ce
s
r
esp
o
n
s
e
ti
m
e
ar
o
u
n
d
4
.
4
s
ec
o
n
d
o
f
ac
cu
r
ac
y
a
n
d
OC
R
g
i
v
es
ar
o
u
n
d
5
.
4
s
ec
o
n
d
.
f.
On
e
k
e
y
p
o
in
t
o
f
s
tab
le
p
er
f
o
r
m
an
ce
o
f
OR
B
i
s
th
at
th
e
u
s
e
o
f
K
-
Ma
j
o
r
it
y
al
g
o
r
ith
m
f
o
r
f
e
atu
r
e
m
atc
h
i
n
g
p
r
o
ce
s
s
.
5
.
3
Curre
ncies Re
co
g
nitio
n Ac
c
ura
cy
Fig
u
r
e
1
0
s
h
o
w
s
th
e
ac
c
u
r
ac
y
p
er
f
o
r
m
an
ce
o
f
th
e
ap
p
licatio
n
to
d
etec
t
an
d
r
ec
o
g
n
i
ze
f
o
r
a
l
l
cu
r
r
en
cies.
I
t g
iv
e
s
av
er
a
g
e
v
a
lu
es
f
r
o
m
s
et
o
f
n
o
m
i
n
als
f
r
o
m
ea
ch
o
f
cu
r
r
en
cie
s
.
Fig
u
r
e
1
0
.
C
u
r
r
en
cies
-
R
ec
o
g
n
izin
g
A
cc
u
r
ac
y
Fig
u
r
e
1
0
also
s
h
o
w
s
t
h
at:
a.
C
u
r
r
en
c
ies I
DR
,
U
SD,
A
UD,
E
UR
,
GB
P
,
an
d
J
P
Y
f
u
n
ct
io
n
as X
-
a
x
is
.
b.
T
h
e
m
i
n
i
m
u
m
ac
c
u
r
ac
y
v
al
u
e
th
at
is
o
b
tai
n
ed
b
y
O
R
B
m
et
h
o
d
is
8
8
% f
o
r
GB
P
.
0
1
2
3
4
5
6
7
8
1
0
0
0
2
0
0
0
5
0
0
0
1
0
0
0
0
2
0
0
0
0
5
0
0
0
0
1
0
0
0
0
0
T
i
m
e
i
n
S
econd
R
e
sp
o
n
se
T
i
m
e
O
C
R
ORB
84
86
88
90
92
94
IDR
U
S
D
AUD
EU
R
G
B
P
JP
Y
Pe
r
c
e
n
t
a
g
e
%
Re
c
ogn
ition
Ac
c
u
r
ac
y
O
R
B
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
P
a
p
er Mo
n
ey
R
ec
o
g
n
iz
er Usi
n
g
F
ea
tu
r
e
Descri
p
to
r
(
N
u
r
H
a
d
is
u
kma
n
a
)
125
c.
T
h
e
m
a
x
i
m
u
m
v
al
u
e
is
ar
o
u
n
d
9
3
% f
o
r
I
DR
.
d.
E
v
en
t
h
o
u
g
h
t
h
e
ac
c
u
r
ac
y
o
f
OR
B
m
eth
o
d
te
n
d
s
to
b
e
d
ec
r
ea
s
ed
,
b
u
t
t
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
ap
p
licatio
n
is
co
n
s
id
er
ed
to
b
e
s
tab
le
b
ec
au
s
e
OR
B
g
i
v
es
s
m
all
d
if
f
er
en
ce
r
an
g
e
ar
o
u
n
d
1
5
%
b
et
w
ee
n
m
i
n
i
m
u
m
a
n
d
m
ax
i
m
u
m
v
a
lu
e
s
.
e.
On
t
h
e
av
er
ag
e,
O
R
B
p
r
o
d
u
ce
s
ar
o
u
n
d
9
0
.
5
% o
f
ac
cu
r
ac
y
f
o
r
cu
r
r
en
cies a
p
p
lied
.
f.
T
h
e
ap
p
licatio
n
,
o
n
th
e
av
er
ag
e,
g
iv
e
s
h
i
g
h
ac
cu
r
ac
y
i
n
d
etec
tin
g
an
d
r
ec
o
g
n
izin
g
t
h
e
cu
r
r
e
n
cies.
5
.
4
Respo
ns
e
T
i
m
e
f
o
r
Curre
nci
es
Fig
u
r
e
1
1
s
h
o
w
s
th
e
ap
p
licati
o
n
’
s
av
er
ag
e
r
esp
o
n
s
e
ti
m
e
p
er
f
o
r
m
an
ce
i
n
d
etec
tin
g
a
n
d
r
ec
o
g
n
izi
n
g
s
et
o
f
n
o
m
i
n
als o
f
c
u
r
r
en
cie
s
t
h
at
ar
e
ap
p
lied
.
T
h
is
co
u
ld
als
o
s
h
o
w
:
a.
C
u
r
r
en
c
ies I
DR
,
U
SD,
A
UD,
E
UR
,
GB
P
,
an
d
J
P
Y
f
u
n
ct
io
n
as X
-
a
x
is
.
b.
T
h
e
m
a
x
i
m
u
m
r
esp
o
n
s
e
ti
m
e
t
h
at
w
as o
b
tain
ed
b
y
O
R
B
m
et
h
o
d
is
5
.
2
s
ec
o
n
d
,
w
h
ic
h
o
cc
u
r
s
f
o
r
GB
P
.
c.
T
h
e
m
i
n
i
m
u
m
r
e
s
p
o
n
s
e
ti
m
e
i
s
ar
o
u
n
d
4
.
4
s
ec
o
n
d
f
o
r
I
DR
.
d.
E
v
en
t
h
o
u
g
h
t
h
e
r
es
n
p
o
n
s
e
ti
m
e
o
f
OR
B
m
et
h
o
d
ten
d
s
t
o
b
e
in
cr
esed
,
b
u
t
t
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
ap
p
licatio
n
is
co
n
s
id
er
ed
to
b
e
s
tab
le
b
ec
au
s
e
OR
B
g
iv
e
s
s
m
all
d
if
f
er
e
n
ce
r
an
g
e
o
f
r
esp
o
n
s
e
ti
m
e,
w
h
ic
h
is
ar
o
u
n
d
0
.
8
s
ec
o
n
d
b
et
w
ee
n
m
i
n
i
m
u
m
a
n
d
m
a
x
i
m
u
m
v
alu
es.
e.
O
n
t
h
e
av
er
ag
e,
O
R
B
g
i
v
es r
e
s
p
o
n
s
e
ti
m
e
o
f
4
.
9
s
ec
o
n
d
f
o
r
cu
r
r
en
cies a
p
p
lied
.
f.
T
h
e
ap
p
licatio
n
,
o
n
th
e
av
er
ag
e,
p
r
o
d
u
ce
s
q
u
ite
f
ast
r
esp
o
n
s
e
ti
m
e,
w
h
ich
i
s
les
s
t
h
a
n
5
s
ec
o
n
d
,
in
d
etec
tin
g
a
n
d
r
ec
o
g
n
izi
n
g
th
e
cu
r
r
en
cies.
Fig
u
r
e
1
1
.
C
u
r
r
en
cies
R
esp
o
n
s
e
T
im
e
6.
CO
NCLU
SI
O
N
T
h
e
r
esear
ch
o
n
th
e
p
r
o
b
lem
o
f
t
h
e
v
is
u
all
y
i
m
p
air
ed
p
eo
p
le
in
r
ec
o
g
n
izi
n
g
t
h
e
p
a
p
er
m
o
n
e
y
,
esp
ec
iall
y
t
h
e
w
o
r
n
o
u
t
p
ap
er
m
o
n
e
y
,
h
as
en
ab
led
th
e
d
ev
el
o
p
m
e
n
t
o
f
m
o
b
ile
ap
p
licatio
n
u
tili
zi
n
g
th
e
ca
m
er
a
o
f
th
e
m
o
b
ile
d
ev
ice.
T
h
e
ap
p
licatio
n
is
ab
le
to
ab
le
r
ec
o
g
n
ize
th
e
n
o
m
in
a
l
o
f
t
h
e
p
ap
er
m
o
n
e
y
f
r
o
m
an
y
d
if
f
er
e
n
t a
n
g
le
ev
e
n
i
f
t
h
e
p
ap
er
is
r
o
tated
.
I
t a
ls
o
r
ec
o
g
n
ize
s
th
e
n
o
m
i
n
al
o
f
t
h
e
p
ap
er
m
o
n
e
y
ev
e
n
t
h
o
u
g
h
t
h
e
p
ap
er
is
f
o
ld
ed
o
r
w
o
r
n
o
u
t.
T
h
e
r
esp
o
n
s
e
ti
m
e
to
r
ec
o
g
n
ize
th
e
n
o
m
i
n
al
o
f
t
h
e
p
ap
er
m
o
n
e
y
o
n
th
e
a
v
er
a
g
e
is
less
t
h
an
5
s
ec
o
n
d
w
it
h
t
h
e
ac
cu
r
ac
y
a
v
er
ag
el
y
9
0
%.
An
ex
ten
s
io
n
o
f
t
h
e
r
esear
ch
c
an
b
e
co
n
d
u
cted
to
i
m
p
r
o
v
e
th
e
f
o
llo
w
in
g
.
a.
I
n
cr
ea
s
in
g
t
h
e
ac
cu
r
ac
y
o
f
t
h
e
ap
p
licatio
n
u
p
to
1
0
0
%.
b.
Min
i
m
izi
n
g
th
e
r
esp
o
n
s
e
ti
m
e
to
at
m
o
s
t 3
s
ec
o
n
d
.
c.
P
r
o
v
id
in
g
m
o
r
e
tex
t to
s
p
ee
ch
A
P
I
th
a
n
E
n
g
lis
h
-
b
ased
o
n
l
y
.
RE
F
E
R
E
NC
E
S
[1
]
S
a
m
u
e
l,
C.
M
a
k
in
g
Ba
n
k
No
tes
A
c
c
e
ss
ib
le
f
o
r
Ca
n
a
d
ian
s
L
iv
in
g
w
it
h
Bli
n
d
n
e
ss
o
r
L
o
w
V
isio
n
.
B
a
n
k
o
f
Ca
n
a
d
a
Rev
iew
(W
in
ter
).
2
0
0
9
-
10;
29
–
36
.
[2
]
Ha
rto
n
o
T
r
y
,
Ca
h
a
y
a
F
it
ra
R
o
m
a
n
.
T
h
e
E
f
fe
c
ti
v
e
n
e
ss
o
f
Bli
n
d
Co
d
e
s
a
n
d
S
e
c
u
rit
y
F
e
a
tu
re
s
f
o
r
T
h
e
Bli
n
d
a
n
d
T
h
e
P
re
v
e
n
ti
o
n
o
f
F
ra
u
d
o
n
T
h
e
In
d
o
n
e
sia
n
Ru
p
iah
.
Asi
a
P
a
sifi
c
Fra
u
d
J
o
u
rn
a
l
.
2
0
1
7
;
2
(
2
)
[
3
]
A
.
Hin
w
o
o
d
,
P
.
P
re
sto
n
,
G
.
J.
S
u
a
n
in
g
,
N.
H.
L
o
v
e
ll
.
Ba
n
k
n
o
te
re
c
o
g
n
it
io
n
f
o
r
th
e
v
isio
n
im
p
a
ired
.
Au
str
a
la
si
a
n
Ph
y
sic
a
l
&
En
g
in
e
e
rin
g
S
c
ien
c
e
s in
M
e
d
icin
e
.
2
0
0
6
;
2
9
(2
):
2
2
9
-
2
3
3
.
[4
]
G
u
n
a
d
h
i
A
lb
e
rt,
Iv
a
n
Da
n
iel,
Les
tarin
in
g
sih
Dia
n
a
,
A
n
d
y
a
rd
ja
W
id
y
a
,
Yu
li
a
ti
.
Id
e
n
ti
f
ica
ti
o
n
To
o
l
o
f
Ru
p
iah
Ba
n
k
n
o
te
f
o
r
Bli
n
d
P
e
o
p
le
w
it
h
A
u
d
io
Ou
t
p
u
t
Us
in
g
Op
ti
c
a
l
Ch
a
r
a
c
ter
Re
c
o
g
n
it
io
n
(OCR)
M
e
th
o
d
.
AR
PN
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
A
p
p
l
ied
S
c
ien
c
e
.
2
0
1
6
;
1
1
(
1
3
)
:
8
1
1
3
-
8
1
2
1
.
4
4
.
2
4
.
4
4
.
6
4
.
8
5
5
.
2
5
.
4
IDR
US
D
A
U
D
E
U
R
G
B
P
J
P
Y
Ti
m
e
i
n Se
cond
Re
sp
o
n
se
Tim
e
ORB
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2502
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
117
–
1
2
6
126
[5
]
S
a
g
a
r
S
wa
ti
,
M
o
d
a
l
S
h
a
h
e
e
n
,
S
e
th
A
p
o
o
rv
a
,
S
h
a
h
Ro
o
p
v
a
ti
,
De
s
h
p
a
n
d
e
A
k
a
n
k
sh
a
.
A
n
A
n
d
ro
i
d
A
p
p
li
c
a
ti
o
n
f
o
r
In
d
ian
C
u
rre
n
c
y
Re
c
o
g
n
it
io
n
a
n
d
A
u
th
e
n
t
ica
ti
o
n
f
o
r
Bli
n
d
.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
Ne
two
rk
.
2
0
1
6
:
5
(
2
):
3
2
4
-
3
2
9
.
[6
]
Et
h
a
n
Ru
b
lee
,
Vin
c
e
n
t
Ra
b
a
u
d
,
Ku
rt
Ko
n
o
li
g
e
,
G
a
r
y
R.
Bra
d
sk
i:
ORB:
A
n
e
ff
i
c
ien
t
a
lt
e
rn
a
ti
v
e
to
S
IF
T
o
r
S
URF.
ICCV
2
0
1
1
:
2
5
6
4
-
2
5
7
1
.
[7
]
Ch
risto
p
h
e
r
Ka
n
a
n
,
G
a
rriso
n
W
.
Co
tt
re
ll
,
C
o
lo
r
-
to
-
G
ra
y
sc
a
le:
Do
e
s th
e
M
e
th
o
d
M
a
tt
e
r
i
n
Im
a
g
e
Re
c
o
g
n
it
io
n
?
,
PL
o
S
ON
E
.
2
0
1
2
;
7
(
1
):
1
-
7.
[8
]
Ro
ste
n
E,
Dru
m
m
o
n
d
T
,
M
a
c
h
in
e
lea
rn
in
g
fo
r
h
ig
h
sp
e
e
d
c
o
rn
e
r
d
e
tec
ti
o
n
.
9
th
Eu
p
r
o
e
a
n
Co
n
f
e
re
n
c
e
o
n
Co
m
p
u
ter
V
isio
n
.
2
0
0
6
;
1
:
4
3
0
–
4
4
3
.
[9
]
V
isw
a
n
a
th
a
n
,
De
e
p
a
k
G
e
e
th
a
.
F
e
a
tu
re
s f
ro
m
A
c
c
e
l
e
ra
ted
S
e
g
m
e
n
t
T
e
st (
F
A
S
T
)
.
2011
;
1
-
5.
[1
0
]
Ca
lo
n
d
e
r
M
ich
a
e
l,
L
e
p
e
ti
t
V
in
c
e
n
t,
S
trec
h
a
Ch
risto
p
h
,
F
u
a
P
a
sc
a
l
.
BR
IEF
:
Bi
n
a
ry
Ro
b
u
st
In
d
e
p
e
n
d
e
n
t
El
e
me
n
ta
ry
Fea
tu
re
s
.
1
1
th
Eu
ro
p
e
a
n
C
o
n
f
e
re
n
c
e
o
n
Co
m
p
u
ter
V
isi
o
n
.
He
ra
k
li
o
.
2
0
1
0
;
7
7
8
-
7
9
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.