I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l
E
ng
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
21
,
No
.
2
,
Feb
r
u
ar
y
202
1
,
p
p
.
8
1
1
~
8
2
1
I
SS
N:
2
5
02
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
1
.i
2
.
p
p
8
1
1
-
8
2
1
811
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Indo
nesia
n licens
e plate
recog
nitio
n w
ith
i
m
pro
v
ed
ho
riz
o
ntal
-
v
ertic
a
l edge pro
j
ection
I
da
Nurha
ida
,
I
m
a
m
Nud
ud
din
,
Desi Ra
m
a
y
a
nti
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
M
e
rc
u
Bu
a
n
a
,
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
Feb
2
6
,
2
0
2
0
R
ev
i
s
ed
A
p
r
7
,
2
0
2
0
A
cc
ep
ted
Ma
y
6
,
2
0
2
0
L
ice
n
se
p
late
re
c
o
g
n
it
io
n
(L
P
R)
is
o
n
e
o
f
th
e
c
las
si
c
a
l
p
ro
b
lem
s
i
n
th
e
f
ield
o
f
o
b
jec
t
re
c
o
g
n
it
io
n
.
Its
a
p
p
li
c
a
ti
o
n
is
v
e
ry
c
ru
c
ial
i
n
th
e
a
u
to
m
a
ti
o
n
o
f
tran
sp
o
rtati
o
n
sy
ste
m
sin
c
e
it
h
e
lp
s
to
re
c
o
g
n
ise
a
v
e
h
icle
id
e
n
ti
ty
,
w
h
ich
in
f
o
rm
a
ti
o
n
is
st
o
re
d
i
n
t
h
e
li
c
e
n
se
p
late
.
L
P
R
u
su
a
ll
y
c
o
n
sists
o
f
th
re
e
m
a
jo
r
p
h
a
se
s:
p
r
e
-
p
ro
c
e
ss
in
g
,
li
c
e
n
se
p
late
l
o
c
a
li
sa
ti
o
n
,
o
p
ti
c
a
l
c
h
a
ra
c
ter
re
c
o
g
n
it
io
n
(
OCR).
De
sp
it
e
b
e
in
g
c
las
sic
a
l
,
it
s
im
p
le
m
e
n
tatio
n
f
a
c
e
d
w
it
h
m
u
c
h
m
o
re
c
o
m
p
li
c
a
ted
p
ro
b
lem
s
in
th
e
re
a
l
sc
e
n
a
rio
.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
d
a
n
im
p
ro
v
e
d
L
P
R
a
lg
o
rit
h
m
b
a
se
d
o
n
m
o
d
if
ied
h
o
rizo
n
tal
-
v
e
rti
c
a
l
e
d
g
e
p
ro
jec
ti
o
n
.
T
h
e
m
e
th
o
d
u
s
e
s
f
o
r
d
e
tec
ti
n
g
a
n
d
lo
c
a
li
sin
g
t
h
e
re
g
io
n
o
f
in
tere
st.
It
is
d
o
n
e
u
sin
g
th
e
h
o
rizo
n
tal
a
n
d
v
e
rti
c
a
l
p
ro
jec
ti
o
n
o
f
th
e
i
m
a
g
e
.
Re
late
d
w
o
rk
s
p
ro
v
e
d
th
a
t
th
e
m
o
d
if
ied
h
o
rizo
n
tal
-
v
e
rti
c
a
l
e
d
g
e
p
ro
jec
ti
o
n
is
th
e
sim
p
les
t
m
e
th
o
d
t
o
b
e
im
p
lem
e
n
ted
,
y
e
t
v
e
r
y
e
ff
e
c
ti
v
e
a
g
a
in
st
In
d
o
n
e
sia
n
l
i
c
e
n
s
e
p
late
.
Ho
w
e
v
e
r,
it
s
p
e
r
f
o
r
m
a
n
c
e
g
e
ts
re
d
u
c
e
d
w
h
e
n
sp
e
c
u
lar
re
f
le
c
ti
o
n
o
c
c
u
rs
in
th
e
sa
m
p
le
i
m
a
g
e
.
T
h
e
re
f
o
re
,
m
o
rp
h
o
lo
g
ica
l
o
p
e
ra
ti
o
n
s
a
re
u
ti
li
se
d
in
th
e
p
re
-
p
r
o
c
e
ss
in
g
p
h
a
se
to
re
d
u
c
e
su
c
h
e
ff
e
c
ts
w
h
il
e
p
re
se
rv
in
g
th
e
n
e
e
d
e
d
in
f
o
r
m
a
ti
o
n
.
Ei
g
h
ty
s
a
m
p
le
i
m
a
g
e
s
w
h
ich
c
a
p
tu
re
d
u
si
n
g
v
a
rio
u
s ca
m
e
ra
c
o
n
f
ig
u
ra
ti
o
n
s w
e
re
u
se
d
in
th
is
re
se
a
rc
h
.
Ba
se
d
o
n
th
e
e
x
p
e
ri
m
e
n
tal
re
su
lt
s,
o
u
r
p
ro
p
o
se
d
a
lg
o
rit
h
m
sh
o
w
s
a
n
im
p
ro
v
e
m
e
n
t
c
o
m
p
a
re
d
w
it
h
th
e
p
re
v
io
u
s
stu
d
y
a
n
d
su
c
c
e
ss
f
u
ll
y
d
e
tec
t
7
1
l
ice
n
se
p
late
s in
8
0
im
a
g
e
sa
m
p
l
e
s w
h
ich
re
su
lt
s in
8
8
.
7
5
%
a
c
c
u
ra
c
y
.
K
ey
w
o
r
d
s
:
C
o
m
p
u
ter
v
is
io
n
I
m
ag
e
p
r
o
ce
s
s
i
n
g
L
ice
n
s
e
p
late
r
ec
o
g
n
itio
n
Mo
r
p
h
o
lo
g
y
o
p
er
atio
n
T
h
is
is
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
:
I
d
a
Nu
r
h
aid
a
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
Un
i
v
er
s
ita
s
Me
r
cu
B
u
a
n
a
J
l.
Me
r
u
y
a
Selata
n
n
o
.
1
,
I
n
d
o
n
esia
E
m
ail: id
a.
n
u
r
h
a
id
a@
m
er
cu
b
u
an
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
Ob
j
ec
t
r
ec
o
g
n
itio
n
i
s
o
n
e
o
f
t
h
e
m
o
s
t
i
n
ter
es
tin
g
f
ield
s
a
m
o
n
g
th
e
co
m
p
u
ter
v
i
s
io
n
r
esear
ch
er
s
i
n
ce
it's
ap
p
licab
le
in
m
an
y
s
ec
to
r
s
o
f
o
u
r
ev
er
y
d
a
y
li
f
e.
O
n
e
o
f
t
h
e
clas
s
ical
p
r
o
b
le
m
th
a
t
s
til
l
r
elev
an
t
e
v
e
n
to
d
a
y
w
a
s
licen
s
e
p
late
r
ec
o
g
n
it
io
n
,
b
ec
au
s
e
o
f
th
e
m
a
n
y
c
h
alle
n
g
es
t
h
at
m
u
s
t
b
e
tack
led
s
u
c
h
as
v
ar
iatio
n
s
o
f
th
e
licen
s
e
p
late
c
h
ar
ac
ter
is
tic
s
in
ea
ch
co
u
n
tr
y
ar
o
u
n
d
t
h
e
w
o
r
l
d
,
n
o
is
e
in
t
h
e
i
m
a
g
e,
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
,
etc.
Ma
n
y
r
esear
ch
er
s
ar
o
u
n
d
t
h
e
w
o
r
ld
h
a
v
e
d
ev
e
lo
p
ed
m
an
y
a
lg
o
r
ith
m
s
f
o
r
lice
n
s
e
p
late
r
ec
o
g
n
itio
n
.
Sti
ll,
d
u
e
to
th
e
li
m
ited
s
a
m
p
le,
m
o
s
t
o
f
th
e
m
ar
e
cr
af
te
d
o
n
l
y
f
o
r
a
s
p
ec
if
ic
co
u
n
tr
y
w
it
h
s
p
ec
if
ic
lice
n
s
e
p
late
ch
ar
ac
ter
is
tic
s
(
b
ac
k
g
r
o
u
n
d
co
lo
u
r
,
f
o
r
m
a
t,
f
o
n
t
t
y
p
e,
etc.
)
.
T
h
e
y
m
i
g
h
t
n
o
t
w
o
r
k
f
o
r
o
th
er
co
u
n
tr
ie
s
w
i
th
d
if
f
er
e
n
t lice
n
s
e
p
late
ch
ar
ac
te
r
is
tics
.
L
ice
n
s
e
p
late
i
n
I
n
d
o
n
es
ia
h
a
s
its
u
n
iq
u
e
ch
ar
ac
t
er
i
s
tics
.
I
t
h
as
a
b
lack
co
lo
u
r
ed
b
ac
k
g
r
o
u
n
d
w
it
h
a
w
h
ite
b
o
r
d
er
an
d
tex
t.
T
h
e
u
s
ag
e
o
f
u
n
iq
u
e
alp
h
ab
et
co
d
e
to
d
if
f
er
en
tia
te
licen
s
e
p
lates
ac
r
o
s
s
th
e
r
eg
io
n
s
i
n
I
n
d
o
n
esia,
also
th
e
lice
n
s
e
p
late
is
s
tr
u
ct
u
r
ed
b
ased
o
n
a
s
tan
d
ar
d
is
ed
f
o
r
m
at.
T
h
e
d
etails
a
r
e
d
escr
ib
ed
w
it
h
i
n
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2021
:
8
1
1
-
8
2
1
812
th
e
Fi
g
u
r
e
1
.
L
ice
n
s
e
p
late
r
e
co
g
n
itio
n
u
s
u
all
y
co
n
s
is
t
s
o
f
th
r
ee
m
aj
o
r
p
h
ases
:
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
licen
s
e
p
late
lo
ca
lis
atio
n
,
a
n
d
o
p
tical
ch
ar
ac
ter
r
ec
o
g
n
itio
n
(
O
C
R
)
.
P
r
e
-
p
r
o
ce
s
s
in
g
is
a
p
h
a
s
e
w
h
er
e
t
h
e
in
p
u
t
i
m
a
g
e
w
ill
b
e
p
r
ep
a
r
ed
,
en
h
an
ce
d
,
an
d
o
p
tim
is
ed
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
i
n
g
[
1
,
2
]
.
A
cc
o
r
d
in
g
to
[
3
-
5
]
,
licen
s
e
p
late
lo
ca
lis
atio
n
is
a
p
h
ase
in
w
h
i
ch
t
h
e
v
eh
icle
lice
n
s
e
p
late
ar
ea
is
to
b
e
d
eter
m
in
ed
,
lo
ca
li
s
ed
,
an
d
s
eg
m
e
n
ted
o
u
t
o
f
th
e
o
r
ig
i
n
al
p
ict
u
r
e
to
i
s
o
late
t
h
e
lice
n
s
e
p
late
f
r
o
m
t
h
e
o
t
h
er
o
b
j
ec
ts
w
h
ic
h
co
n
s
id
er
ed
as
n
o
is
e.
Af
ter
th
e
licen
s
e
p
late
h
as
b
ee
n
s
e
g
m
en
ted
an
d
is
o
lated
,
th
e
n
ex
t
p
h
ase
w
ill
b
e
ch
ar
ac
ter
r
ec
o
g
n
itio
n
,
w
h
er
e
all
o
f
th
e
ch
ar
ac
ter
s
w
it
h
i
n
th
e
lice
n
s
e
p
late
w
i
ll
b
e
ex
tr
ac
ted
a
n
d
p
r
o
ce
s
s
ed
b
y
s
o
m
e
s
o
r
t
o
f
al
g
o
r
it
h
m
,
u
s
u
a
ll
y
te
m
p
late
m
atch
in
g
.
Fig
u
r
e
1
.
I
n
d
o
n
esian
l
icen
s
e
p
late
s
tan
d
ar
d
is
ed
f
o
r
m
at
T
h
e
s
tu
d
y
[
3
,
4
]
m
o
d
if
ied
t
h
e
alg
o
r
ith
m
to
ad
ap
t
to
I
n
d
o
n
esian
lice
n
s
e
p
late
c
h
ar
ac
ter
is
ti
cs,
an
d
it
ap
p
r
o
v
es
to
b
e
ef
f
ec
ti
v
e.
T
h
o
s
e
p
ap
er
s
h
a
v
e
r
ev
ie
w
ed
an
d
s
u
m
m
ar
i
s
ed
tech
n
iq
u
e
s
f
o
r
lice
n
s
e
p
lat
e
r
ec
o
g
n
itio
n
in
I
n
d
o
n
es
ia
th
r
o
u
g
h
o
u
t
r
ec
en
t
y
ea
r
s
.
T
h
e
p
ap
er
s
co
n
s
is
t
o
f
a
s
h
o
r
t
d
escr
ip
tio
n
o
f
th
e
r
ev
ie
w
ed
alg
o
r
ith
m
s
an
d
al
s
o
th
e
co
m
p
ar
is
o
n
b
et
w
ee
n
ea
c
h
al
g
o
r
ith
m
.
Desp
ite
b
ei
n
g
e
f
f
ec
ti
v
e,
th
e
al
g
o
r
ith
m
s
till
s
tr
u
g
g
le
s
w
h
e
n
it
f
ac
ed
w
it
h
s
p
ec
u
lar
r
ef
lectio
n
o
r
o
b
j
ec
t
w
i
th
h
i
g
h
s
atu
r
atio
n
in
te
n
s
ities
.
Hid
a
y
atu
llah
,
et
al.
,
[
3
]
in
tr
o
d
u
ce
an
alg
o
r
it
h
m
t
h
at
i
s
h
ea
v
il
y
i
n
f
lu
e
n
ce
d
b
y
[
5
]
b
u
t
w
it
h
a
b
etter
ap
p
r
o
ac
h
to
ad
ap
t
to
t
h
e
I
n
d
o
n
esia
n
lice
n
s
e
p
late.
I
t s
h
o
w
s
th
a
t t
h
e
a
l
g
o
r
ith
m
i
s
p
r
ett
y
u
s
e
f
u
l i
n
d
etec
ti
n
g
I
n
d
o
n
e
s
i
an
lice
n
s
e
p
late
w
it
h
6
3
d
etec
ted
licen
s
e
p
late
o
u
t
o
f
8
0
s
a
m
p
le
i
m
a
g
e
s
.
T
h
e
r
es
ea
r
ch
er
also
s
ta
ted
th
at
o
n
e
o
f
t
h
e
k
e
y
p
r
o
b
lem
s
w
h
ic
h
ca
u
s
e
t
h
e
d
etec
tio
n
to
b
e
a
f
ail
u
r
e
is
s
p
ec
u
lar
r
e
f
lect
io
n
.
Dev
ap
r
i
y
a
et
a
l.,
[
5
]
p
r
o
p
o
s
ed
a
licen
s
e
p
late
r
ec
o
g
n
itio
n
alg
o
r
ith
m
f
o
r
th
e
I
n
d
ian
lice
n
s
e
p
late
th
at
r
el
y
h
ea
v
i
l
y
o
n
t
h
e
m
o
r
p
h
o
lo
g
ica
l
o
p
er
atio
n
.
A
n
o
t
h
er
ap
p
r
o
ac
h
o
f
licen
s
e
p
late
r
ec
o
g
n
i
tio
n
is
p
r
ese
n
ted
b
y
Go
h
il
[
6
]
.
R
esear
ch
[
6
]
p
r
o
p
o
s
ed
a
s
i
m
p
le
y
et
e
f
f
ec
ti
v
e
alg
o
r
ith
m
to
b
e
u
s
ed
f
o
r
C
ali
f
o
r
n
ian
lice
n
s
e
p
late
r
ec
o
g
n
itio
n
.
T
h
e
alg
o
r
ith
m
w
o
r
k
s
b
y
d
e
tectin
g
t
h
e
ar
ea
o
f
v
eh
ic
le
lice
n
s
e
p
late
b
ased
o
n
th
e
h
o
r
izo
n
tal
ed
g
e
a
n
d
v
er
ti
ca
l
ed
g
e
p
r
o
j
ec
tio
n
.
I
t
is
t
h
e
m
o
s
t
s
tr
aig
h
t
f
o
r
w
ar
d
y
et
v
er
y
u
s
e
f
u
l
alg
o
r
ith
m
f
o
r
licen
s
e
p
late
r
ec
o
g
n
it
io
n
.
Ho
w
e
v
er
,
th
is
i
s
n
o
t
v
er
y
s
i
m
p
l
e
to
im
p
le
m
en
t
t
h
is
alg
o
r
ith
m
f
o
r
th
e
I
n
d
o
n
es
ian
licen
s
e
p
late.
I
t
is
h
ar
d
to
ex
p
o
s
e
s
u
ch
r
ec
ta
n
g
u
lar
o
b
j
ec
t
b
ec
au
s
e
I
n
d
o
n
es
ia
n
licen
s
e
p
late
h
a
s
a
b
lack
b
ac
k
g
r
o
u
n
d
,
an
d
s
o
m
eti
m
e
s
t
h
e
w
h
ite
b
o
r
d
er
is
n
o
t
v
is
ib
le
d
u
e
to
t
h
e
li
g
h
t
in
g
co
n
d
itio
n
o
r
g
et
o
b
s
tr
u
cted
b
y
an
o
t
h
er
o
b
j
ec
t.
T
h
er
ef
o
r
e,
i
t
w
il
l
b
e
v
er
y
p
r
o
n
e
to
m
i
s
d
etec
tio
n
.
W
e
b
eliev
e
s
o
m
et
h
i
n
g
co
u
ld
b
e
d
o
n
e
to
i
m
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
alg
o
r
ith
m
.
2.
RE
L
AT
E
D
WO
RK
S
Var
io
u
s
r
esear
ch
f
o
r
licen
s
e
p
late
r
ec
o
g
n
itio
n
h
as
b
ee
n
in
tr
o
d
u
ce
d
u
s
i
n
g
m
a
n
y
a
lg
o
r
ith
m
s
.
A
cc
o
r
d
in
g
to
th
e
p
ap
er
,
it
s
ee
m
s
li
k
e
m
a
n
y
r
e
s
ea
r
ch
er
s
h
av
e
b
ee
n
u
tili
s
in
g
m
o
r
p
h
o
lo
g
y
o
p
er
atio
n
an
d
ed
g
e
d
etec
tio
n
tech
n
iq
u
e
to
co
n
s
tr
u
ct
th
eir
lice
n
s
e
p
late
r
ec
o
g
n
i
tio
n
alg
o
r
ith
m
.
Mo
r
eo
v
er
,
s
o
m
e
r
esea
r
ch
er
ev
e
n
co
m
b
i
n
ed
it
w
it
h
Ma
ch
in
e
L
ea
r
n
in
g
to
h
elp
i
m
p
r
o
v
e
r
ec
o
g
n
it
io
n
ac
cu
r
ac
y
[
7
,
8
]
.
W
e
co
u
ld
n
o
t
ig
n
o
r
e
th
e
f
ac
t
th
at
m
o
r
p
h
o
lo
g
y
o
p
er
atio
n
is
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
tech
n
iq
u
es
to
b
e
u
s
ed
in
o
b
j
ec
t
r
ec
o
g
n
itio
n
[
9
,
1
0
]
.
T
h
e
r
ea
s
o
n
f
o
r
s
u
ch
p
o
p
u
lar
it
y
i
s
t
h
at
m
o
r
p
h
o
lo
g
y
o
p
er
atio
n
w
h
ile
b
ei
n
g
n
o
t
v
er
y
co
m
p
lica
ted
an
d
co
s
tl
y
;
i
t
co
u
ld
ex
p
o
s
e
th
e
w
h
o
le
s
tr
u
c
tu
r
e
o
f
an
o
b
j
ec
t
to
ea
s
e
t
h
e
r
ec
o
g
n
itio
n
o
f
th
e
d
esire
d
o
b
j
ec
t
o
r
to
d
etec
t
an
u
n
d
e
s
ir
ed
o
b
j
ec
t
to
b
e
r
e
m
o
v
ed
f
r
o
m
t
h
e
i
m
a
g
e.
An
o
th
er
ess
e
n
ti
al
tech
n
i
q
u
e
is
ed
g
e
d
etec
tio
n
.
E
d
g
e
d
etec
tio
n
ai
m
s
at
f
i
n
d
in
g
t
h
e
ch
a
n
g
es
i
n
b
r
ig
h
t
n
e
s
s
i
n
an
i
m
a
g
e
to
b
e
u
s
e
d
f
o
r
ca
p
tu
r
in
g
t
h
e
cr
itical
ev
e
n
t
[
1
1
,
1
2
]
.
T
h
e
t
w
o
o
f
t
h
e
m
ar
e
u
s
u
al
l
y
co
m
b
in
ed
[
1
3
]
.
A
lt
h
o
u
g
h
,
s
o
m
e
r
esear
ch
er
s
h
a
v
e
d
ev
elo
p
ed
an
o
b
j
ec
t
r
ec
o
g
n
itio
n
alg
o
r
it
h
m
u
s
in
g
a
n
ed
g
e
d
etec
tio
n
an
d
co
m
p
ar
ab
le
u
s
i
n
g
m
o
r
p
h
o
lo
g
y
o
p
er
atio
n
[
1
4
,
1
5
]
.
T
h
is
alg
o
r
ith
m
o
n
l
y
w
o
r
k
s
ef
f
ec
ti
v
el
y
wh
en
t
h
e
b
o
r
d
er
o
f
th
e
"o
b
j
ec
t
t
o
b
e
r
ec
o
g
n
is
ed
"
is
s
tr
o
n
g
l
y
d
ef
in
ed
.
An
o
th
er
s
i
m
p
li
f
ied
ap
p
r
o
ac
h
to
b
e
u
s
ed
f
o
r
o
b
j
ec
t
r
ec
o
g
n
itio
n
i
s
b
y
u
s
i
n
g
SIFT
(
s
ca
le
-
i
n
v
ar
ia
n
t
f
ea
t
u
r
e
tr
an
s
f
o
r
m
)
,
w
h
ic
h
p
r
o
v
ed
to
b
e
r
o
b
u
s
t
a
g
ain
s
t
t
h
e
c
h
an
g
e
o
f
s
ca
le
an
d
o
r
ien
ta
tio
n
[
1
6
]
.
I
t
is
k
n
o
w
n
a
s
th
e
alg
o
r
it
h
m
f
o
r
o
b
j
ec
t
r
ec
o
g
n
itio
n
.
T
h
e
alg
o
r
ith
m
w
o
r
k
s
b
y
u
til
is
i
n
g
f
ea
t
u
r
es
in
a
n
i
m
a
g
e,
k
n
o
w
n
as
cr
itical
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
I
n
d
o
n
esia
n
licen
s
e
p
la
te
r
ec
o
g
n
itio
n
w
ith
imp
r
o
ve
d
h
o
r
iz
o
n
t
a
l
-
ve
r
tica
l e
d
g
e
p
r
o
jectio
n
(
I
d
a
N
u
r
h
a
id
a
)
813
poi
n
ts
,
to
d
eter
m
in
e
w
h
e
th
er
a
n
o
b
j
ec
t
is
s
i
m
i
lar
o
r
n
o
t.
Ho
w
e
v
er
,
t
h
e
al
g
o
r
ith
m
m
a
y
n
o
t
b
e
g
o
in
g
to
b
e
v
er
y
u
s
e
f
u
l b
ec
au
s
e
o
f
t
h
e
lac
k
o
f
t
ex
tu
r
e
s
an
d
f
ea
tu
r
es i
n
t
h
e
I
n
d
o
n
esia
n
licen
s
e
p
late.
Fo
llo
w
i
n
g
t
h
e
r
esear
c
h
,
[
1
7
]
co
n
d
u
cted
a
s
tu
d
y
to
i
m
p
le
m
e
n
t
t
h
e
a
l
g
o
r
ith
m
f
o
r
t
h
e
I
n
d
o
n
esian
licen
s
e
p
late.
T
h
e
alg
o
r
ith
m
s
till
w
o
r
k
s
e
f
f
e
ctiv
el
y
w
it
h
s
o
m
e
m
o
d
i
f
icatio
n
,
esp
ec
iall
y
in
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
a
s
e
ag
ai
n
s
t
v
ar
io
u
s
I
n
d
o
n
e
s
ia
n
licen
s
e
p
la
te.
Fu
r
th
er
r
esear
ch
h
a
s
b
ee
n
co
n
d
u
cted
b
y
[
1
8
,
1
9
]
.
R
esear
c
h
[
1
8
]
r
esu
lte
d
th
at
th
e
i
m
p
le
m
en
ted
alg
o
r
it
h
m
ca
n
r
ec
o
g
n
is
e
th
e
ch
ar
ac
ter
s
o
n
t
h
e
p
o
lice
p
late
n
u
m
b
er
i
n
t
h
e
av
er
ag
e
p
er
ce
n
tag
e
7
9
,
4
3
%.
K
-
Nea
r
est
Neig
h
b
o
r
s
alg
o
r
ith
m
r
ea
d
s
all
th
ese
c
h
ar
ac
ter
s
.
T
h
e
test
r
esu
lts
s
h
o
w
th
at
t
h
is
v
eh
icle
p
late
r
ec
o
g
n
itio
n
s
y
s
te
m
p
r
o
v
id
es 8
3
,
3
3
% su
cc
es
s
r
ate
f
r
o
m
3
0
test
d
ata.
On
t
h
e
o
th
er
h
a
n
d
,
Da
m
a
y
a
n
ti
et
al.
[
1
9
]
u
s
in
g
d
i
f
f
er
en
t a
p
p
r
o
ac
h
es f
o
r
t
h
e
r
ec
o
g
n
i
tio
n
o
f
t
h
e
lice
n
s
e
p
late.
T
h
e
r
esear
ch
u
tili
s
es
f
ea
tu
r
e
ar
ea
a
n
d
K
-
Nea
r
est
Neig
h
b
o
r
(
KNN)
as
a
clas
s
i
f
icatio
n
m
et
h
o
d
.
I
n
s
u
m
m
ar
y
,
t
h
es
e
r
es
u
lts
s
h
o
w
t
h
at
ac
cu
r
ac
y
o
f
9
9
.
4
4
%.
3.
P
RO
P
O
SE
D
M
E
T
H
O
D
I
n
th
i
s
r
esear
ch
,
w
e
p
r
o
p
o
s
ed
an
i
m
p
r
o
v
ed
Ho
r
izo
n
tal
-
Ver
ti
ca
l
E
d
g
e
P
r
o
j
ec
tio
n
alg
o
r
ith
m
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
m
et
h
o
d
p
r
o
p
o
s
ed
i
n
th
i
s
s
t
u
d
y
h
a
s
an
u
n
u
s
u
al
b
eh
av
io
u
r
b
ec
au
s
e
it
co
u
ld
r
ed
u
ce
th
e
i
n
ten
s
i
t
y
o
f
s
p
ec
u
lar
r
ef
lec
tio
n
b
y
a
s
ig
n
i
f
ican
t
a
m
o
u
n
t
w
h
ile
h
ig
h
li
g
h
ti
n
g
th
e
in
ter
est
p
o
in
t,
w
h
ic
h
i
s
th
e
v
e
h
icle
lice
n
s
e
p
late.
T
h
u
s
i
t
co
u
ld
b
e
v
er
y
u
s
ef
u
l
to
s
ettle
th
e
p
r
o
b
lem
s
.
T
h
e
co
m
p
lete
f
lo
w
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
co
u
ld
b
e
s
ee
n
in
F
ig
u
r
e
2
.
Fig
u
r
e
2
.
Flo
w
c
h
ar
t o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
3
.
1
.
P
re
-
pro
ce
s
s
ing
P
r
e
-
P
r
o
ce
s
s
in
g
is
th
e
p
h
a
s
e
t
o
en
h
a
n
ce
th
e
i
n
p
u
t
i
m
ag
e
a
n
d
r
e
m
o
v
e
u
n
w
an
ted
d
ata,
n
o
is
es,
a
n
d
d
is
to
r
tio
n
f
r
o
m
th
e
in
p
u
t
i
m
ag
e.
T
h
e
p
u
r
p
o
s
e
o
f
i
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
i
s
to
eli
m
in
a
te
ir
r
elev
an
t
in
f
o
r
m
at
io
n
i
n
th
e
i
m
a
g
e,
r
esto
r
e
r
ea
l
u
s
ef
u
l
i
n
f
o
r
m
atio
n
,
en
h
a
n
ce
t
h
e
d
etec
tab
ilit
y
o
f
t
h
e
r
ele
v
a
n
t
i
n
f
o
r
m
atio
n
,
a
n
d
s
i
m
p
li
f
y
th
e
d
ata
to
th
e
m
a
x
i
m
u
m
,
t
h
er
eb
y
i
m
p
r
o
v
in
g
t
h
e
r
eliab
ili
t
y
o
f
i
m
ag
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
r
ec
o
g
n
i
tio
n
.
C
o
m
m
o
n
m
e
th
o
d
s
ar
e:
(
1
)
g
r
a
y
s
ca
le;
(
2
)
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
atio
n
;
(
3
)
i
m
a
g
e
en
h
a
n
ce
m
e
n
t.
T
h
e
g
o
al
o
f
th
is
p
h
ase
i
s
to
e
m
p
h
asi
s
e
u
s
e
f
u
l
i
m
ag
e
i
n
f
o
r
m
atio
n
w
h
ile
r
ed
u
cin
g
u
n
w
an
ted
d
ata.
F
u
r
t
h
er
m
o
r
e,
t
h
e
d
ata
co
llected
h
av
e
m
an
y
er
r
o
r
o
r
n
o
is
e,
s
o
th
at
it n
ee
d
s
to
p
er
f
o
r
m
t
h
e
d
ata
p
r
e
p
r
o
ce
s
s
in
g
o
p
er
atio
n
[
2
0
,
2
1
]
.
3
.
1
.
1
.
RG
B
t
o
g
r
a
y
s
ca
le
co
nv
er
s
io
n
T
h
e
f
ir
s
t
s
tep
i
n
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
ase
i
s
to
co
n
v
er
t
th
e
in
p
u
t
i
m
a
g
e
i
n
to
t
h
e
g
r
a
y
s
ca
le
f
o
r
m
at
.
T
h
e
r
ea
s
o
n
b
eh
in
d
t
h
i
s
co
n
v
er
s
io
n
is
to
s
i
m
p
li
f
y
t
h
e
co
m
p
u
tat
io
n
p
r
o
ce
s
s
i
n
t
h
e
n
e
x
t
s
ta
g
e.
T
h
e
m
o
s
t
co
m
m
o
n
tech
n
iq
u
e
to
co
n
v
er
t
th
e
R
GB
i
m
a
g
e
in
to
g
r
a
y
s
ca
l
e
is
to
u
s
e
th
e
L
u
m
i
n
o
s
it
y
m
e
th
o
d
r
ep
r
esen
ted
in
(
1
)
b
el
o
w
.
T
h
e
r
esu
lt o
f
t
h
is
o
p
er
atio
n
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
3
.
(
1
)
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2021
:
8
1
1
-
8
2
1
814
(
a)
(
b
)
Fig
u
r
e
3
.
C
o
m
p
ar
is
o
n
b
et
w
ee
n
,
(
a)
o
r
ig
in
al
i
m
ag
e
a
n
d
(
b
)
g
r
ay
s
ca
led
i
m
a
g
e
3
.
1
.
2
.
O
penin
g
m
o
rp
ho
lo
g
y
o
pera
t
io
n
T
h
e
n
ex
t
s
tep
is
to
p
er
f
o
r
m
o
p
en
in
g
m
o
r
p
h
o
lo
g
y
o
p
er
atio
n
t
o
th
e
i
m
ag
e.
Op
e
n
i
n
g
m
o
r
p
h
o
lo
g
y
co
u
ld
b
e
ac
h
iev
ed
b
y
i
m
p
le
m
en
t
in
g
th
e
er
o
s
io
n
o
p
er
atio
n
f
ir
s
t,
f
o
llo
w
ed
b
y
t
h
e
d
ilatio
n
o
p
er
atio
n
u
s
i
n
g
t
h
e
s
a
m
e
s
tr
u
ct
u
r
in
g
ele
m
en
t
f
o
r
b
o
th
o
p
er
atio
n
s
[
2
2
]
.
T
h
e
in
f
o
r
m
a
tio
n
r
etr
iev
ed
af
ter
th
i
s
s
tep
is
u
s
e
f
u
l
to
d
etec
t
p
r
o
b
lem
atic
r
eg
io
n
s
ca
u
s
ed
b
y
h
a
v
in
g
to
o
m
u
c
h
co
n
tr
ast/
i
n
ten
s
i
t
y
o
r
r
eg
io
n
s
w
it
h
s
p
ec
u
l
ar
r
ef
lectio
n
,
w
h
ic
h
co
u
ld
co
n
f
u
s
e
t
h
e
lice
n
s
e
p
late
lo
ca
lis
atio
n
al
g
o
r
ith
m
.
Op
en
i
n
g
o
p
er
atio
n
is
d
escr
ib
ed
b
y
(
2
)
.
(
2
)
w
h
er
e
r
ep
r
esen
ts
er
o
s
io
n
o
p
er
atio
n
w
h
i
le
r
ep
r
esen
ts
d
ilatio
n
o
p
er
atio
n
.
T
h
e
o
u
tco
m
e
o
f
t
h
is
o
p
er
atio
n
is
v
i
s
u
al
is
ed
b
y
Fi
g
u
r
e
.
Fig
u
r
e
4
.
T
h
e
r
esu
lt o
f
o
p
en
in
g
m
o
r
p
h
o
lo
g
y
3
.
1
.
3
.
T
o
p
-
ha
t
t
ra
ns
f
o
rm
T
o
p
-
h
at
tr
an
s
f
o
r
m
i
s
o
n
e
o
f
t
h
e
m
o
s
t
u
s
ed
o
p
er
atio
n
s
f
o
r
im
ag
e
e
n
h
an
ce
m
e
n
t
[
2
2
,
2
3
]
.
I
n
th
i
s
ca
s
e
,
th
e
in
p
u
t
i
m
a
g
e
w
ill
b
e
th
e
g
r
ay
s
ca
led
i
m
a
g
e,
an
d
th
e
o
p
en
in
g
co
u
n
ter
p
ar
t
is
th
e
o
u
tco
m
e
o
f
th
e
p
r
ev
io
u
s
s
tep
,
w
h
ic
h
h
o
ld
s
i
n
f
o
r
m
atio
n
ab
o
u
t p
r
o
b
lem
atic
r
eg
io
n
s
a
s
d
escr
ib
ed
b
ef
o
r
e.
T
h
e
p
r
o
b
lem
a
tic
r
eg
io
n
s
w
ill
n
o
lo
n
g
er
d
o
m
i
n
ate
th
e
i
m
a
g
e,
a
n
d
its
i
n
ten
s
it
y
w
ill
b
e
r
ed
u
c
e
d
to
a
s
ig
n
i
f
ica
n
t
a
m
o
u
n
t.
T
h
e
r
eg
io
n
o
f
i
n
ter
est
(
ar
o
u
n
d
th
e
v
e
h
icle
lice
n
s
e
p
late)
w
ill
b
e
e
n
h
an
ce
d
.
T
h
is
en
h
a
n
ce
m
en
t
i
s
w
h
at
w
e
n
ee
d
ed
to
in
cr
ea
s
e
t
h
e
ac
cu
r
ac
y
o
f
Ho
r
izo
n
tal
-
Ver
ti
ca
l
E
d
g
e
P
r
o
j
ec
tio
n
m
et
h
o
d
in
d
etec
ti
n
g
t
h
e
v
eh
icle
lice
n
s
e
p
late.
Fi
g
u
r
e
5
v
is
u
ali
s
es t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
p
r
o
p
o
s
ed
b
y
Dev
ap
r
i
y
a
[
5
]
an
d
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
(
a)
(
b
)
Fig
u
r
e
5
.
C
o
m
p
ar
is
o
n
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
,
(
a)
p
r
e
-
p
r
o
ce
s
s
i
n
g
a
s
p
r
o
p
o
s
ed
b
y
[
3
]
,
(
b
)
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
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
I
n
d
o
n
esia
n
licen
s
e
p
la
te
r
ec
o
g
n
itio
n
w
ith
imp
r
o
ve
d
h
o
r
iz
o
n
t
a
l
-
ve
r
tica
l e
d
g
e
p
r
o
jectio
n
(
I
d
a
N
u
r
h
a
id
a
)
815
3
.
2
.
L
icense pla
t
e
lo
ca
lis
a
t
io
n
Af
ter
t
h
e
en
h
a
n
ce
d
i
m
a
g
e
h
a
s
b
ee
n
r
etr
iev
ed
f
r
o
m
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
ase,
it
i
s
n
o
w
t
h
e
ti
m
e
to
d
etec
t
an
d
lo
ca
lis
e
th
e
v
e
h
ic
le
licen
s
e
p
late.
I
t
m
ea
n
s
th
a
t
th
e
v
e
h
icle
lice
n
s
e
p
late
s
h
o
u
ld
b
e
id
en
tif
ied
p
r
ec
is
el
y
an
d
is
o
lated
f
r
o
m
o
t
h
er
o
b
j
ec
ts
in
th
e
i
m
a
g
e.
3
.
2
.
1
.
Ver
t
ica
l e
dg
e
pro
j
ec
t
io
n
T
h
e
en
h
an
ce
d
i
m
a
g
e
w
ill
b
e
s
ca
n
n
ed
v
er
ticall
y
,
an
d
t
h
e
s
u
m
o
f
all
m
a
g
n
it
u
d
e
d
if
f
er
en
c
es
w
ill
b
e
ca
lcu
lated
co
l
u
m
n
-
w
i
s
e
f
o
r
ev
er
y
r
o
w
o
f
th
e
i
m
ag
e.
All
o
f
t
h
e
o
b
tain
ed
v
al
u
e
a
f
ter
t
h
e
ca
lcu
latio
n
w
il
l
t
h
e
n
b
e
p
r
o
jecte
d
in
to
a
h
is
to
g
r
a
m
r
ep
r
esen
tatio
n
f
o
r
th
e
an
al
y
s
i
s
p
r
o
ce
s
s
.
Fig
u
r
e
6
v
is
u
alis
ed
th
e
s
a
m
p
le
i
m
ag
e
an
d
th
e
h
is
to
g
r
a
m
p
r
o
j
ec
tio
n
alo
n
g
t
h
e
v
er
tica
l e
d
g
e.
T
h
e
h
is
to
g
r
a
m
s
h
o
u
ld
b
e
s
m
o
o
th
ed
u
s
i
n
g
th
e
lo
w
p
ass
f
i
lter
in
o
r
d
er
to
n
o
r
m
ali
s
e
s
u
ch
d
r
asti
c
ch
an
g
es.
T
h
e
r
esu
l
tin
g
v
al
u
es
w
il
l
b
e
a
v
er
ag
ed
to
g
et
a
t
h
r
es
h
o
ld
lev
el.
T
h
e
eli
m
in
at
io
n
p
r
o
ce
s
s
w
ill
y
ield
to
s
eg
m
e
n
tatio
n
o
f
t
h
e
i
m
a
g
e
to
s
ev
er
al
r
o
w
s
b
a
s
ed
o
n
t
h
e
p
r
o
j
ec
tio
n
p
ea
k
s
.
Fig
u
r
e
7
s
h
o
w
s
t
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
ea
ch
h
is
to
g
r
a
m
p
r
o
j
e
ctio
n
f
o
r
ea
ch
o
p
er
atio
n
.
Fig
u
r
e
6
.
Ver
tical
ed
g
e
p
r
o
j
ec
tio
n
ca
lcu
lat
io
n
(
a)
(
b
)
(
c)
Fig
u
r
e
1
.
Ver
tical
ed
g
e
p
r
o
ce
s
s
in
g
v
is
u
alis
a
tio
n
,
(
a)
r
o
u
g
h
h
i
s
to
g
r
a
m
p
r
o
j
ec
tio
n
,
(
b
)
lo
w
p
ass
f
ilter
,
(
c)
h
is
to
g
r
a
m
p
r
o
j
ec
tio
n
th
r
es
h
o
ld
in
g
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2021
:
8
1
1
-
8
2
1
816
3
.
2
.
2
.
Reg
io
n o
f
inte
re
s
t
ex
t
ra
ct
io
n ba
s
ed
o
n t
he
v
er
t
ica
l
pro
j
ec
t
io
n
I
n
th
is
s
tep
,
all
th
e
r
em
a
in
i
n
g
p
ea
k
s
in
t
h
e
p
r
o
j
ec
tio
n
h
is
to
g
r
a
m
w
ill
b
e
an
al
y
s
ed
to
f
in
d
th
e
r
eg
io
n
o
f
in
ter
est.
S
in
ce
I
n
d
o
n
esia
n
lice
n
s
e
p
late
h
as
a
b
lack
co
lo
u
r
ed
b
ac
k
g
r
o
u
n
d
w
it
h
w
h
ite
co
lo
u
r
ed
tex
t
an
d
b
o
r
d
er
,
it
m
u
s
t
y
ield
a
s
i
g
n
i
f
ica
n
t
a
m
o
u
n
t
o
f
m
a
g
n
itu
d
e
in
th
e
p
r
o
jectio
n
h
is
to
g
r
a
m
.
T
h
er
e
f
o
r
e,
th
e
r
eg
io
n
o
f
i
n
ter
es
t
s
h
o
u
ld
b
e
th
e
p
ea
k
s
w
h
ic
h
co
n
tai
n
s
a
g
lo
b
al
m
a
x
i
m
a
ac
r
o
s
s
th
e
p
r
o
j
ec
tio
n
,
an
d
an
y
o
th
er
p
ea
k
s
s
h
o
u
ld
b
e
eli
m
i
n
ated
f
r
o
m
th
e
i
m
a
g
e
to
lo
ca
lis
e
th
e
r
eg
io
n
o
f
i
n
ter
est s
ee
Fig
u
r
e
8
.
Fig
u
r
e
2
.
R
OI
b
ased
o
n
th
e
v
e
r
tical
ed
g
e
3
.
2
.
3
.
H
o
rizo
nt
a
l e
dg
e
pro
j
ec
t
io
n
Af
ter
t
h
e
r
eg
io
n
o
f
in
ter
est
h
a
s
b
ee
n
lo
ca
lis
ed
alo
n
g
th
e
v
er
tical
ed
g
e,
an
al
y
s
i
s
alo
n
g
t
h
e
h
o
r
izo
n
ta
l
ed
g
e
is
ex
ec
u
ted
to
p
r
ec
is
ely
d
etec
t
th
e
v
eh
icle
licen
s
e
p
lat
e.
T
h
e
p
r
o
ce
d
u
r
e
t
o
ca
lcu
late
th
e
h
o
r
izo
n
tal
ed
g
e
p
r
o
j
ec
tio
n
is
id
en
ticall
y
t
h
e
s
a
m
e
as
b
ef
o
r
e,
ex
ce
p
t
t
h
e
s
u
m
o
f
all
m
a
g
n
i
tu
d
e
d
if
f
er
en
ce
s
w
ill
b
e
ca
lcu
lated
b
et
w
ee
n
ev
er
y
n
ei
g
h
b
o
u
r
in
g
p
ix
el
in
t
h
e
v
er
tica
l
ax
i
s
w
it
h
i
n
s
u
ch
co
l
u
m
n
.
T
h
e
o
u
tco
m
e
f
o
r
ea
ch
p
r
o
ce
s
s
is
v
is
u
ali
s
ed
b
y
Fi
g
u
r
e
9
.
(
a)
(
b
)
(
c)
Fig
u
r
e
9
.
Ho
r
izo
n
tal
ed
g
e
p
r
o
ce
s
s
i
n
g
v
is
u
ali
s
atio
n
,
(
a)
r
o
u
g
h
h
i
s
to
g
r
a
m
p
r
o
j
ec
tio
n
,
(
b
)
lo
w
p
as
s
f
il
ter
,
(
c)
h
is
to
g
r
a
m
p
r
o
j
ec
tio
n
th
r
es
h
o
ld
in
g
3
.
2
.
4
.
Reg
io
n o
f
inte
re
s
t
ex
t
ra
ct
io
n ba
s
ed
o
n ho
rizo
nta
l pro
j
ec
t
io
n
Dif
f
er
en
t
th
a
n
b
e
f
o
r
e,
th
e
r
e
g
io
n
o
f
i
n
ter
est
i
s
a
n
al
y
s
ed
th
r
o
u
g
h
th
e
w
id
th
o
f
ea
c
h
p
ea
k
i
n
t
h
e
p
r
o
j
ec
tio
n
h
is
to
g
r
a
m
.
W
e
d
ef
i
n
e
a
t
h
r
es
h
o
ld
v
al
u
e
to
f
i
lter
o
u
t
t
h
e
p
ea
k
s
b
ased
o
n
its
w
i
d
th
.
Fo
r
ev
er
y
p
ea
k
h
av
i
n
g
a
w
id
th
les
s
t
h
an
t
h
e
t
h
r
es
h
o
ld
v
al
u
e
w
i
ll
b
e
co
n
s
id
er
ed
as
n
o
is
e
an
d
m
u
s
t
b
e
eli
m
i
n
ated
,
w
h
ile
t
h
o
s
e
ab
o
v
e
th
e
th
r
e
s
h
o
ld
v
al
u
e
w
i
ll
b
e
k
ep
t.
I
n
th
is
r
esear
c
h
,
w
e
d
ef
in
e
t
h
e
t
h
r
esh
o
ld
v
alu
e
a
s
2
5
u
n
its
s
ee
Fi
g
u
r
e
10.
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
I
n
d
o
n
esia
n
licen
s
e
p
la
te
r
ec
o
g
n
itio
n
w
ith
imp
r
o
ve
d
h
o
r
iz
o
n
t
a
l
-
ve
r
tica
l e
d
g
e
p
r
o
jectio
n
(
I
d
a
N
u
r
h
a
id
a
)
817
Fig
u
r
e
3
.
Fin
al
R
OI
3
.
2
.
5
.
L
icense pla
t
e
s
eg
m
ent
a
t
io
n
Af
ter
th
e
lice
n
s
e
p
late
h
as
b
ee
n
p
r
ec
is
el
y
lo
ca
ted
an
d
n
o
is
es
ar
e
s
u
cc
e
s
s
f
u
ll
y
r
e
m
o
v
ed
,
th
e
g
r
a
y
s
ca
led
i
m
a
g
e
in
t
h
e
f
ir
s
t
p
h
ase
w
ill
b
e
cr
o
p
p
ed
b
ased
o
n
th
e
r
eg
io
n
o
f
in
ter
est
d
ef
i
n
ed
f
r
o
m
all
o
f
t
h
e
p
r
ev
io
u
s
s
tep
s
s
ee
Fi
g
u
r
e
1
1
.
T
h
is
cr
o
p
p
e
d
im
a
g
e
w
ill t
h
e
n
b
e
p
ass
ed
f
o
r
th
e
ch
ar
ac
ter
r
ec
o
g
n
itio
n
p
h
ase.
Fig
u
r
e
4
.
C
r
o
p
p
ed
licen
s
e
p
late
3
.
3
.
Cha
ra
c
t
er
re
co
g
nitio
n
Fo
r
ch
ar
ac
ter
r
ec
o
g
n
itio
n
p
h
a
s
e,
w
e
m
o
d
i
f
y
t
h
e
f
o
n
t
te
m
p
la
te
as
r
ec
o
m
m
e
n
d
ed
b
y
Hid
a
y
atu
lla
h
[
4
]
.
I
n
s
tead
,
w
e
u
s
e
o
u
r
o
w
n
m
o
d
i
f
ied
f
o
n
t te
m
p
late.
T
h
is
d
i
f
f
er
en
ce
m
a
y
a
f
f
ec
t t
h
e
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
.
3
.
3
.
1
.
T
hresh
o
ldi
ng
(
O
t
s
u’s m
et
ho
d)
T
h
e
f
ir
s
t
s
tep
i
n
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
p
h
a
s
e
i
s
to
co
n
v
er
t
t
h
e
i
n
p
u
t
i
m
ag
e
in
to
a
b
in
ar
y
i
m
a
g
e
b
y
th
r
es
h
o
ld
in
g
.
T
h
e
m
o
s
t c
o
m
m
o
n
l
y
u
s
ed
m
eth
o
d
f
o
r
th
r
e
s
h
o
l
d
in
g
is
Ots
u
'
s
m
eth
o
d
s
in
ce
it
p
r
o
v
id
es a
d
y
n
a
m
ic
th
r
es
h
o
ld
lev
el
w
h
ic
h
ca
lc
u
lat
ed
f
r
o
m
t
h
e
i
m
ag
e
p
i
x
el
s
[
2
4
,
2
5
]
.
T
h
is
co
n
v
er
s
io
n
m
ea
n
s
t
h
at
f
o
r
ev
er
y
p
i
x
el
v
alu
e
b
elo
w
th
e
t
h
r
es
h
o
ld
lev
el
w
ill
b
e
co
n
v
er
ted
in
to
0
(
t
h
e
d
ar
k
es
t
co
lo
u
r
)
.
I
n
co
n
tr
as
t,
ev
er
y
p
i
x
el
v
alu
e
ab
o
v
e
th
e
th
r
e
s
h
o
ld
lev
e
l
w
il
l
b
e
co
n
v
er
ted
in
to
1
(
th
e
b
r
ig
h
te
s
t
co
lo
u
r
)
.
T
h
e
o
u
tco
m
e
o
f
th
i
s
co
n
v
er
s
io
n
u
s
u
al
ly
c
al
l
e
d
b
in
a
r
y
im
ag
e
s
in
c
e
i
t
c
o
n
t
ai
n
s
o
n
ly
0
s
an
d
1
s
v
al
u
e
i
n
th
e
p
ix
e
l
m
ag
n
itu
d
e
,
a
s
s
h
o
w
n
in
F
ig
u
r
e
1
2
.
(
a)
(
b
)
Fig
u
r
e
1
2
.
C
o
m
p
ar
is
o
n
b
et
w
e
en
,
(
a)
g
r
a
y
s
ca
led
i
m
ag
e
a
n
d
(
b
)
b
in
ar
y
i
m
a
g
e
3
.
3
.
2
.
Cha
ra
ct
er
c
a
nd
ida
t
e
ex
t
ra
ct
io
n
Af
ter
t
h
e
i
m
a
g
e
h
a
s
b
ee
n
co
n
v
er
ted
in
to
a
b
i
n
ar
y
i
m
a
g
e,
we
co
u
ld
q
u
ic
k
l
y
id
en
ti
f
y
an
d
e
x
tr
ac
t
all
o
f
th
e
o
b
j
ec
ts
w
it
h
i
n
th
e
i
m
ag
e
th
r
o
u
g
h
C
o
n
n
ec
ted
C
o
m
p
o
n
en
t
An
al
y
s
is
.
A
ll
o
f
t
h
e
d
etec
ted
o
b
j
ec
ts
a
r
e
co
n
s
id
er
ed
as
ch
ar
ac
ter
ca
n
d
id
ate
as
s
h
o
w
n
i
n
Fi
g
u
r
e
1
3
,
h
o
w
ev
er
,
s
o
m
e
o
f
th
e
m
ar
e
b
etter
co
n
s
id
er
ed
as
n
o
is
e.
T
h
er
ef
o
r
e,
f
u
r
t
h
er
n
o
is
e
r
em
o
v
al
s
h
o
u
ld
b
e
ex
ec
u
ted
.
Fo
r
tu
n
ate
l
y
,
C
o
n
n
ec
ted
C
o
m
p
o
n
en
t
An
al
y
s
i
s
n
o
t
o
n
l
y
d
etec
t
o
b
j
ec
ts
w
it
h
i
n
a
n
i
m
a
g
e
b
u
t
also
a
s
s
i
g
n
s
o
m
e
p
r
o
p
er
ties
to
th
e
o
b
j
ec
t
s
u
c
h
a
s
ce
n
tr
o
id
s
,
a
n
d
b
o
u
n
d
in
g
b
o
x
[
2
6
]
.
E
n
h
a
n
ci
n
g
th
e
q
u
a
lit
y
o
f
b
i
n
ar
y
i
m
a
g
e
f
o
r
p
late
i
m
a
g
e
ca
n
b
e
d
o
n
e
b
as
ed
o
n
p
r
ep
r
o
ce
s
s
ed
to
r
e
m
o
v
e
t
h
e
n
o
is
e
a
n
d
co
m
p
en
s
ate
p
o
o
r
illu
m
i
n
atio
n
[
2
7
]
.
T
h
en
,
w
e
ca
n
id
e
n
ti
f
y
th
e
p
o
s
itio
n
an
d
t
h
e
s
ize
o
f
an
o
b
j
ec
t w
h
ic
h
co
u
ld
b
e
u
s
e
f
u
l f
o
r
th
e
n
o
is
e
r
e
m
o
v
al
p
r
o
ce
s
s
.
No
is
e
r
e
m
o
v
al
p
r
o
ce
s
s
co
n
s
i
s
ts
o
f
s
e
v
er
al
s
tag
e
s
.
T
h
e
f
ir
s
t
s
tag
e
i
s
ap
p
ly
i
n
g
a
m
ed
ia
n
f
ilter
to
r
e
m
o
v
e
s
alt
a
n
d
p
ep
p
er
n
o
is
e.
T
h
e
s
ec
o
n
d
s
ta
g
e
i
s
eli
m
i
n
ati
n
g
o
b
j
ec
ts
w
h
o
s
e
s
ize
is
b
elo
w
t
h
e
d
e
f
in
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2021
:
8
1
1
-
8
2
1
818
th
r
es
h
o
ld
ac
q
u
ir
ed
f
r
o
m
t
h
e
e
q
u
atio
n
p
r
o
p
o
s
ed
b
y
[
4
]
.
T
h
e
th
ir
d
s
tag
e
is
to
eli
m
i
n
ate
o
b
j
ec
ts
w
h
ic
h
le
n
g
t
h
ex
ce
ed
1
/8
len
g
th
o
f
t
h
e
i
m
a
g
e.
Fu
r
t
h
er
m
o
r
e
,
th
e
last
s
tep
is
to
ch
ec
k
w
h
et
h
er
a
n
o
b
j
ec
t is p
ar
allel
to
th
e
o
th
er
o
b
j
ec
t
o
r
n
o
t
s
in
ce
t
h
e
ch
ar
ac
ter
s
o
n
a
lice
n
s
e
p
late
ar
e
u
s
u
all
y
n
ea
r
l
y
p
ar
allel.
Af
ter
all
o
f
th
e
l
icen
s
e
p
late
ch
ar
ac
ter
ca
n
d
id
ates
h
a
s
b
ee
n
tr
u
l
y
d
eter
m
i
n
ed
,
t
h
e
y
w
ill
b
e
cr
o
p
p
e
d
o
u
t
as
a
n
i
n
d
iv
id
u
al
c
h
ar
ac
ter
.
A
f
ter
th
at,
t
h
e
y
w
i
ll
b
e
n
o
r
m
ali
s
ed
b
y
r
esizi
n
g
t
h
e
m
i
n
to
4
2
x
2
4
p
ix
els
to
m
atc
h
t
h
e
s
ize
o
f
t
h
e
f
o
n
t
te
m
p
la
te.
T
h
is
cr
o
p
p
in
g
an
d
n
o
r
m
ali
s
atio
n
p
r
o
ce
s
s
is
r
eq
u
ir
ed
to
p
er
f
o
r
m
te
m
p
late
m
a
tch
i
n
g
.
Fig
u
r
e
5
.
T
h
e
v
is
u
ali
s
atio
n
o
f
ch
ar
ac
ter
ca
n
d
id
ate
d
etec
tio
n
3
.
3
.
3
.
T
e
m
pla
t
e
m
a
t
chi
ng
I
n
th
i
s
s
tep
,
ev
er
y
i
n
d
i
v
id
u
al
ch
ar
ac
ter
w
ill
b
e
m
atch
ed
a
g
ain
s
t
s
ets
o
f
c
h
ar
ac
ter
te
m
p
la
te
th
r
o
u
g
h
s
u
c
h
ca
lcu
latio
n
to
f
in
d
s
i
m
il
ar
it
y
b
et
w
ee
n
t
h
e
m
.
I
n
th
is
r
e
s
ea
r
ch
,
w
e
u
s
ed
th
e
n
o
r
m
alis
ed
cr
o
s
s
-
co
r
r
elatio
n
m
et
h
o
d
.
E
v
er
y
ca
lc
u
latio
n
r
es
u
lts
o
b
tain
ed
f
r
o
m
th
e
o
p
er
atio
n
w
il
l
b
e
m
ap
p
ed
in
s
id
e
an
ar
r
ay
f
o
r
th
e
v
o
tin
g
p
r
o
ce
s
s
.
T
h
e
ch
ar
ac
ter
is
r
ec
o
g
n
i
s
ed
as
s
u
c
h
s
tr
in
g
th
r
o
u
g
h
th
e
v
o
ti
n
g
p
r
o
ce
s
s
b
y
f
i
n
d
in
g
in
w
h
ic
h
te
m
p
lat
e
th
e
o
p
er
atio
n
ac
h
ie
v
ed
m
a
x
i
m
u
m
co
r
r
elatio
n
v
al
u
e.
4.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
4
.
1
.
L
icense pla
t
e
lo
ca
lis
a
t
io
n
T
o
c
o
n
d
u
ct
a
f
air
co
m
p
ar
i
s
o
n
b
et
w
ee
n
[
3
]
an
d
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
w
e
p
er
f
o
r
m
th
e
r
esear
c
h
u
s
i
n
g
th
e
s
a
m
e
s
a
m
p
le
i
m
a
g
e
s
as
u
s
ed
b
y
th
e
m
w
it
h
th
eir
p
er
m
is
s
io
n
.
T
h
e
s
a
m
p
le
co
n
s
is
t
s
o
f
8
0
im
a
g
es,
ca
p
tu
r
ed
u
s
i
n
g
v
ar
io
u
s
ca
m
er
a
co
n
f
i
g
u
r
atio
n
s
s
u
ch
as
t
h
e
c
a
m
er
a
d
is
ta
n
ce
(
b
et
w
ee
n
1
m
,
1
.
5
m
,
o
r
2
m
)
,
an
d
h
eig
h
t
(
b
et
w
ee
n
5
5
c
m
,
1
m
,
o
r
2
m
)
.
O
u
r
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
a
s
s
u
cc
es
s
f
u
ll
y
d
etec
ted
t
h
e
v
e
h
icle
lice
n
s
e
p
late
in
7
1
s
a
m
p
le
s
o
u
t
o
f
8
0
s
a
m
p
les,
w
h
i
le
[
3
]
d
etec
t
6
3
s
a
m
p
les
o
u
t
o
f
8
0
s
a
m
p
les.
B
elo
w
i
s
th
e
tab
le
o
f
co
m
p
ar
is
o
n
b
et
w
ee
n
[
3
]
an
d
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
Fig
u
r
e
1
4
p
r
esen
ts
th
e
v
is
u
ali
s
atio
n
o
f
t
h
e
s
u
cc
ess
f
u
l
d
etec
t
io
n
p
r
o
ce
s
s
f
o
r
s
o
m
e
s
a
m
p
les,
w
h
er
e
th
e
co
n
d
itio
n
i
s
n
o
t
v
er
y
o
p
ti
m
a
l.
E
v
en
t
h
o
u
g
h
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
h
o
w
s
an
i
m
p
r
o
v
e
m
e
n
t
to
t
h
e
d
etec
tio
n
ac
cu
r
ac
y
,
it
s
till
f
i
n
d
s
s
tr
u
g
g
le
s
to
d
etec
t
th
e
v
e
h
icle
l
icen
s
e
p
late
in
s
o
m
e
s
a
m
p
les.
So
m
e
f
ailed
d
etec
tio
n
ar
e
s
h
o
w
n
in
Fig
u
r
e
1
5
.
Fig
u
r
e
1
5
(
a,
b
)
s
h
o
w
s
a
n
ex
tr
e
m
e
ca
s
e
w
h
er
e
th
e
d
e
tecte
d
lice
n
s
e
p
lat
e
ar
ea
ex
ce
ed
ed
th
e
ac
tu
al
v
e
h
icle
l
icen
s
e
p
late
d
u
e
to
th
e
f
a
ilu
r
e
o
f
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
ase
to
r
ed
u
ce
th
e
o
v
er
l
y
s
at
u
r
ated
ca
r
.
T
h
is
co
n
d
itio
n
ca
u
s
ed
h
i
g
h
p
r
o
j
ec
tio
n
v
alu
e
i
n
th
e
h
is
to
g
r
a
m
an
d
co
n
f
u
s
ed
th
e
a
n
al
y
s
i
s
p
r
o
ce
s
s
.
Fig
u
r
e
1
5
(
c)
s
h
o
w
s
t
h
e
f
ailu
r
e
o
f
t
h
e
d
etec
t
io
n
d
u
e
to
th
e
u
s
ag
e
o
f
n
o
n
-
s
t
an
d
ar
d
is
ed
licen
s
e
p
late.
T
h
e
th
in
n
er
f
o
n
t
w
ill
n
o
t
p
r
o
d
u
ce
s
ig
n
if
ican
t
p
ea
k
s
in
t
h
e
p
r
o
j
ec
tio
n
h
is
to
g
r
a
m
.
T
h
er
ef
o
r
e,
p
ar
ts
o
f
t
h
e
lice
n
s
e
p
lat
e
d
id
n
o
t
ex
ce
ed
t
h
e
th
r
es
h
o
ld
v
alu
e
i
n
t
h
e
h
o
r
izo
n
t
al
p
r
o
j
ec
tio
n
an
al
y
s
is
a
n
d
g
et
eli
m
i
n
ated
f
r
o
m
th
e
r
eg
io
n
o
f
in
ter
est.
S
a
mp
l
e
I
mag
e
Pre
-
P
r
o
c
e
ssi
n
g
S
e
g
me
n
t
a
t
i
o
n
R
e
su
l
t
a
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
I
n
d
o
n
esia
n
licen
s
e
p
la
te
r
ec
o
g
n
itio
n
w
ith
imp
r
o
ve
d
h
o
r
iz
o
n
t
a
l
-
ve
r
tica
l e
d
g
e
p
r
o
jectio
n
(
I
d
a
N
u
r
h
a
id
a
)
819
Fig
u
r
e
1
4
.
(
a)
C
am
er
a
a
litt
le
h
ig
h
er
t
h
an
lice
n
s
e
p
late,
(
b
)
ca
s
e
w
ith
s
p
ec
u
lar
r
ef
lec
tio
n
Sa
m
p
le
I
m
a
g
e
P
r
e
-
P
r
o
ce
s
s
in
g
Seg
m
en
tatio
n
R
es
u
lt
a
b
c
Fig
u
r
e
1
5
.
(
a
,
b
)
licen
s
e
p
late
ar
ea
ex
ce
ed
ed
,
(
c)
licen
s
e
p
late
ar
ea
cu
t
4
.
2
.
Cha
ra
c
t
er
re
co
g
nitio
n
A
ll
o
f
th
e
7
1
s
u
cc
es
s
f
u
l
l
y
d
et
ec
ted
licen
s
e
p
lates
w
er
e
th
e
n
u
s
ed
f
o
r
f
u
r
t
h
er
p
r
o
ce
s
s
in
g
wh
ich
i
s
th
e
ch
ar
ac
ter
r
ec
o
g
n
itio
n
p
h
a
s
e.
J
ac
ca
r
d
Sim
ilar
it
y
I
n
d
ex
is
u
s
ed
to
ca
lcu
la
te
th
e
s
i
m
il
ar
it
y
b
et
w
ee
n
t
h
e
r
ec
o
g
n
is
ed
tex
t
a
n
d
th
e
ac
tu
a
l
licen
s
e
p
late.
Fro
m
t
h
e
ex
p
er
i
m
en
t,
as
s
h
o
w
n
i
n
T
ab
le
1
,
w
e
ac
h
ie
v
ed
an
av
er
ag
e
o
f
7
7
.
9
7
%
s
i
m
ilar
it
y
,
w
h
ile
[
3
]
o
b
tain
ed
an
av
er
ag
e
o
f
8
5
.
8
7
%
s
i
m
ilar
it
y
.
T
h
is
g
ap
m
i
g
h
t
b
e
ca
u
s
ed
b
y
t
h
e
p
r
esen
ce
o
f
n
o
is
e
w
h
i
ch
f
al
s
el
y
r
ec
o
g
n
is
ed
as
o
n
e
o
f
th
e
licen
s
e
p
late
ch
ar
ac
ter
s
o
r
th
e
d
is
to
r
tio
n
a
m
o
n
g
t
h
e
lice
n
s
e
p
late
c
h
ar
ac
ter
s
,
w
h
ic
h
i
m
p
lie
s
to
f
als
e
r
ec
o
g
n
itio
n
.
T
ab
le
2
s
h
o
w
s
th
e
r
es
u
lt
s
o
f
t
h
e
ch
ar
ac
ter
r
ec
o
g
n
itio
n
s
ta
g
e.
T
ab
le
1
.
T
h
e
co
m
p
ar
is
o
n
r
es
u
l
ts
in
d
etec
tio
n
ac
cu
r
ac
y
A
l
g
o
r
i
t
h
m
D
e
t
e
c
t
e
d
sam
p
l
e
(
O
u
t
o
f
8
0
sam
p
l
e
)
%
M
o
d
i
f
i
e
d
H
o
r
i
z
o
n
t
a
l
-
V
e
r
t
i
c
a
l
P
r
o
j
e
c
t
i
o
n
63
7
8
.
7
5
%
P
r
o
p
o
se
d
A
g
o
r
i
t
h
m
71
8
8
.
7
5
%
T
ab
le
2
.
T
h
e
r
esu
lts
o
f
c
h
ar
ac
t
er
r
ec
o
g
n
itio
n
N
o.
D
e
t
e
c
t
i
o
n
R
e
su
l
t
A
c
t
u
a
l
L
i
c
e
n
se
P
l
a
t
e
R
e
c
o
g
n
i
se
d
S
i
mi
l
a
r
i
t
y
(
%)
1
.
D
8
1
1
C
J
D
8
1
1
C
J
1
0
0
2
.
D
4
0
3
L
L
D
4
0
3
L
L
1
0
0
3
.
D
1
7
3
2
W
G
D
1
7
3
G
7
1
.
4
3
4
.
D
1
6
8
5
X
T
1X
2
8
.
5
7
5
.
D
1
3
1
1
G
W
-
0
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.
21
,
No
.
2
,
Feb
r
u
ar
y
2021
:
8
1
1
-
8
2
1
820
5.
CO
NCLU
SI
O
N
T
h
e
p
er
f
o
r
m
an
ce
o
f
Ho
r
izo
n
t
al
-
Ver
tical
E
d
g
e
P
r
o
jectio
n
co
u
ld
b
e
im
p
r
o
v
ed
b
y
m
o
d
i
f
y
i
n
g
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
a
s
e
to
e
n
h
an
ce
th
e
in
p
u
t
i
m
a
g
e.
Ho
r
izo
n
ta
l
-
Ver
tical
E
d
g
e
P
r
o
j
ec
tio
n
is
th
e
s
i
m
p
lest
y
e
t
ef
f
ec
tiv
e
alg
o
r
it
h
m
f
o
r
licen
s
e
p
late
d
etec
tio
n
.
S
t
ill,
it
s
u
f
f
er
s
f
r
o
m
t
h
e
s
p
ec
u
lar
r
ef
lec
tio
n
p
r
o
b
lem
b
ec
au
s
e
it
an
al
y
s
es
t
h
e
r
eg
io
n
o
f
in
ter
est
-
b
ased
o
n
t
h
e
m
a
g
n
it
u
d
e
v
alu
e
p
r
o
j
ec
tio
n
.
T
h
er
ef
o
r
e,
a
n
y
o
b
j
ec
t
w
it
h
h
i
g
h
s
atu
r
atio
n
in
ten
s
it
y
o
r
s
p
ec
u
l
ar
r
ef
lectio
n
f
r
o
m
t
h
e
v
e
h
icle
its
el
f
co
u
ld
co
n
f
u
s
e
t
h
e
an
a
l
y
s
i
s
p
r
o
ce
s
s
,
w
h
ic
h
o
f
ten
r
es
u
lt
s
i
n
m
is
d
etec
tio
n
.
Ou
r
r
esear
ch
p
r
o
p
o
s
ed
an
alg
o
r
ith
m
w
it
h
t
h
e
i
m
p
le
m
e
n
tat
io
n
to
r
ed
u
ce
s
u
c
h
p
r
o
b
lem
s
b
y
d
o
i
n
g
a
n
i
m
ag
e
e
n
h
a
n
ce
m
en
t
in
t
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
a
s
e,
w
h
ic
h
i
n
r
es
u
lt
r
e
d
u
cin
g
t
h
e
ef
f
ec
t
o
f
s
p
ec
u
lar
r
ef
lectio
n
an
d
o
b
j
ec
t
w
it
h
h
ig
h
s
at
u
r
atio
n
i
n
te
n
s
i
t
y
w
h
i
le
p
r
eser
v
i
n
g
a
n
d
en
h
a
n
cin
g
t
h
e
r
eg
io
n
o
f
in
ter
est
i
n
f
o
r
m
atio
n
.
Ou
r
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
as
p
r
o
v
en
to
b
e
ef
f
ec
ti
v
e
an
d
i
m
p
r
o
v
ed
th
e
p
er
f
o
r
m
a
n
ce
b
y
a
s
ig
n
i
f
ica
n
t
a
m
o
u
n
t,
f
r
o
m
6
3
(
7
8
.
7
5
%)
d
etec
ted
s
am
p
les
in
to
7
1
(
8
8
.
7
5
%).
T
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
p
h
ase
s
o
m
eti
m
es
s
ti
ll
f
ailed
to
r
ed
u
c
e
th
e
s
p
ec
u
lar
r
e
f
lectio
n
ef
f
ec
t
.
Fo
r
en
h
a
n
ce
m
en
t,
s
a
m
p
le
i
m
ag
e
q
u
al
it
y
s
h
o
u
ld
also
b
e
tak
en
ca
r
e,
b
l
u
r
r
y
i
m
a
g
e
an
d
a
d
ir
t
y
ca
r
co
u
ld
f
ail
t
h
e
lo
ca
lis
at
io
n
a
n
d
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
.
A
n
o
t
h
er
co
n
ce
r
n
is
t
h
at
th
is
al
g
o
r
ith
m
i
s
n
o
t
v
er
y
r
o
b
u
s
t
ag
ai
n
s
t
o
r
ien
tatio
n
ch
a
n
g
es,
an
d
d
u
e
to
th
e
li
m
ited
s
a
m
p
le
w
e
co
u
ld
n
o
t te
s
t t
h
e
alg
o
r
it
h
m
a
g
ain
s
t t
h
e
ca
s
e
w
h
e
n
th
e
ca
m
er
a
is
n
o
t p
er
p
en
d
icu
lar
to
th
e
li
ce
n
s
e
p
late.
RE
F
E
R
E
NC
E
S
[1
]
S
.
Ch
a
k
ra
b
o
rty
a
n
d
R.
P
a
re
k
h
,
“
A
n
I
m
p
ro
v
e
d
T
e
m
p
late
M
a
tch
in
g
A
lg
o
rit
h
m
f
o
r
Ca
r
L
ice
n
se
P
late
Re
c
o
g
n
it
io
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
l
ica
ti
o
n
s
,
v
o
l.
1
1
8
,
n
o
.
2
5
,
p
p
.
1
6
-
2
2
,
2
0
1
5
.
[2
]
S
u
z
h
i
Z
h
a
n
g
,
Yu
h
o
n
g
W
u
,
Ju
n
Ch
a
n
g
,
“
S
u
rv
e
y
o
f
I
m
a
g
e
R
e
c
o
g
n
it
io
n
A
lg
o
rit
h
m
s”
,
IE
EE
4
th
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Ne
two
rk
in
g
,
El
e
c
tro
n
ic a
n
d
Au
t
o
ma
ti
o
n
Co
n
tro
l
C
o
n
f
e
re
n
c
e
,
2
0
2
0
.
[3
]
S
e
rg
io
M
o
n
taz
z
o
ll
i
S
il
v
a
,
Clau
d
io
Ro
sito
Ju
n
g
,
“
Re
a
l
-
ti
m
e
li
c
e
n
se
p
late
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
u
si
n
g
d
e
e
p
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s
”
,
J
o
u
rn
a
l
o
f
Vi
s
u
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
,
2
0
2
0
.
[4
]
P
.
Hid
a
y
a
tu
ll
a
h
,
F
.
F
e
iri
z
a
l,
H.
P
e
rm
a
n
a
,
Q.
M
a
u
lu
d
d
iah
,
a
n
d
A
.
Dw
it
a
m
a
,
“
L
ice
n
se
p
late
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
f
o
r
In
d
o
n
e
sia
n
c
a
rs,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
I
n
fo
rm
a
ti
c
s
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
3
3
1
-
3
4
6
,
2
0
1
6
.
[5
]
W
.
De
v
a
p
ri
y
a
,
C.
N.
K.
B
a
b
u
,
a
n
d
T
.
S
rih
a
ri,
“
In
d
ian
L
ice
n
se
P
late
De
tec
ti
o
n
a
n
d
Re
c
o
g
n
it
io
n
Us
in
g
M
o
rp
h
o
l
o
g
ica
l
Op
e
ra
ti
o
n
a
n
d
T
e
m
p
late
M
a
tch
in
g
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
,
E
lec
trica
l,
A
u
to
m
a
ti
o
n
,
Co
n
tro
l
a
n
d
In
f
o
rm
a
ti
o
n
En
g
i
n
e
e
rin
g
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
1
0
4
9
-
1
0
5
5
,
2
0
1
5
.
[6
]
Na
ik
u
r
B.
G
o
h
il
,
“
Ca
r
L
ice
n
se
P
l
a
te De
tec
ti
o
n
”
,
S
a
c
ra
m
e
n
to
,
Ca
li
f
o
rn
ia S
tate
Un
iv
e
rsity
,
2
0
1
0
.
[7
]
Hu
i
L
i,
P
e
n
g
W
a
n
g
,
a
n
d
Ch
u
n
h
u
a
S
h
e
n
,
“
T
o
w
a
rd
En
d
-
to
-
E
n
d
Ca
r
L
ic
e
n
se
P
late
De
tec
ti
o
n
a
n
d
Re
c
o
g
n
it
io
n
W
it
h
De
e
p
Ne
u
r
a
l
Ne
tw
o
rk
s
”
,
IEE
E
T
r
a
n
sa
c
ti
o
n
s O
n
In
telli
g
e
n
t
T
r
a
n
sp
o
rta
ti
o
n
S
y
ste
ms
,
p
p
9
9
,
2
0
1
7
.
[8
]
Na
a
m
a
n
O
m
a
r,
A
b
d
u
lk
a
d
ir
S
e
n
g
u
r,
S
a
li
m
G
a
n
i
m
S
a
e
e
d
A
l
-
A
li
,
“
Ca
sc
a
d
e
d
d
e
e
p
lea
rn
i
n
g
-
b
a
se
d
e
fficie
n
t
a
p
p
ro
a
c
h
f
o
r
li
c
e
n
se
p
late
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
”
,
Ex
p
e
rt S
y
ste
ms
W
it
h
A
p
p
li
c
a
ti
o
n
s
,
2
0
2
0
.
[
9
]
Z
h
o
n
g
l
i
W
a
n
g
,
X
i
p
i
n
g
M
a
a
n
d
W
e
n
l
i
n
H
u
a
n
g
,
“
V
e
h
i
c
l
e
L
i
c
e
n
s
e
P
l
a
t
e
R
e
c
o
g
n
i
t
i
o
n
B
a
s
e
d
o
n
W
a
v
e
l
e
t
T
r
a
n
s
f
o
r
m
a
n
d
V
e
r
t
i
c
a
l
E
d
g
e
M
a
t
c
h
i
n
g
”
,
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
4
,
n
o
.
6
,
2
0
2
0
.
[1
0
]
K.
A
d
i,
A
.
P
.
W
id
o
d
o
,
C.
E
.
W
id
o
d
o
,
A
.
P
a
m
u
n
g
k
a
s,
a
n
d
A
.
B.
P
u
t
ra
n
to
,
“
A
u
to
m
a
ti
c
v
e
h
icle
c
o
u
n
ti
n
g
u
si
n
g
b
a
c
k
g
ro
u
n
d
su
b
trac
ti
o
n
m
e
th
o
d
o
n
g
ra
y
sc
a
le
i
m
a
g
e
s
a
n
d
m
o
rp
h
o
l
o
g
y
o
p
e
ra
ti
o
n
,
”
J
o
u
rn
a
l
o
f
P
h
y
si
c
s:
Co
n
fer
e
n
c
e
S
e
rie
s
,
v
o
l.
1
0
2
5
,
n
o
.
1
,
2
0
1
8
.
[1
1
]
El
e
n
a
M
e
d
v
e
d
e
v
a
,
Ig
o
r
T
ru
b
in
,
a
n
d
P
a
v
e
l
Ka
sp
e
r,
“
V
e
h
icle
L
ice
n
se
P
late
Re
c
o
g
n
it
i
o
n
Ba
se
d
o
n
E
d
g
e
De
tec
ti
o
n
”
,
Pro
c
e
e
d
in
g
o
f
th
e
2
6
th
C
o
n
fer
e
n
c
e
o
f
Fru
c
t
Asso
c
ia
ti
o
n
,
2
0
2
0
.
[1
2
]
S
.
M
a
h
a
lak
sh
m
i
a
n
d
P
.
M
.
Ka
ra
n
i,
“
S
tu
d
y
o
f
Ed
g
e
De
t
e
c
ti
o
n
T
e
c
h
n
i
q
u
e
s
in
A
u
to
m
a
ti
c
L
ice
n
se
P
late
Re
c
o
g
n
it
io
n
(AL
P
R),
”
In
ter
n
a
ti
o
n
a
l
Res
e
a
rc
h
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
4
,
n
o
.
5
,
p
p
.
1
6
5
8
-
1
6
6
1
,
2
0
1
7
.
[1
3
]
S
.
Bo
rk
e
r,
“
I
m
p
le
m
e
n
tatio
n
o
f
V
e
h
icle
L
ice
n
se
P
late
Re
c
o
g
n
it
io
n
Us
in
g
Ca
n
n
y
Ed
g
e
D
e
tec
ti
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
i
e
n
c
e
a
n
d
En
g
in
e
e
rin
g
T
e
c
h
n
o
l
o
g
y
(
IJ
CS
ET
)
,
v
o
l.
6
,
n
o
.
0
6
,
p
p
.
3
7
6
-
3
7
9
,
2
0
1
5
.
[1
4
]
Ch
e
n
,
Y,
L
u
o
,
S
.
,
“
Re
se
a
rc
h
o
n
Li
c
e
n
se
P
late
L
o
c
a
ti
o
n
in
Dif
f
e
re
n
t
S
c
e
n
e
s”
,
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
a
n
d
A
d
v
a
n
c
e
d
M
a
n
u
f
a
c
tu
rin
g
,
2
0
1
9
.
[1
5
]
Nu
rh
a
id
a
,
A
.
No
v
iy
a
n
to
,
R.
M
a
n
u
ru
n
g
,
a
n
d
A
.
M
.
A
r
y
m
u
rth
y
,
“
A
u
to
m
a
ti
c
In
d
o
n
e
sia
n
’s
Ba
ti
k
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
Us
in
g
S
IF
T
A
p
p
ro
a
c
h
,
”
Pro
c
e
d
i
a
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
5
9
,
p
p
.
5
6
7
-
5
7
6
,
2
0
1
5
.
[1
6
]
F
.
A
.
He
r
m
a
w
a
ti
a
n
d
R.
Ko
e
s
d
ij
a
rto
,
“
a
Re
a
l
-
T
i
m
e
L
ic
e
n
se
P
late
De
tec
ti
o
n
S
y
ste
m
f
o
r
P
a
rk
in
g
A
c
c
e
ss
,
”
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
t
io
n
,
Co
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l)
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
9
7
-
1
0
6
,
2
0
1
0
.
[
1
7
]
R
a
h
m
a
t
,
B
.
,
J
o
e
l
i
a
n
t
o
,
E
.
,
K
e
t
u
t
E
d
d
y
P
u
r
n
a
m
a
,
P
u
r
n
o
m
o
,
M
.
H
.
,
“
V
e
h
i
c
l
e
l
i
c
e
n
s
e
p
l
a
t
e
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
s
y
s
t
e
m
u
s
i
n
g
c
e
l
l
u
l
a
r
n
e
u
r
a
l
n
e
t
w
o
r
k
o
p
t
i
m
i
z
e
d
b
y
a
d
a
p
t
i
v
e
f
u
z
z
y
a
n
d
N
e
u
r
o
-
F
u
z
z
y
a
l
g
o
r
i
t
h
m
s
”
,
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
u
l
t
i
m
e
d
i
a
a
n
d
U
b
i
q
u
i
t
o
u
s
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
,
no.
1
2
,
p
p.
383
-
4
0
0
,
2
0
1
6
.
[1
8
]
F
it
ri
Da
m
a
y
a
n
ti
,
S
ri
He
ra
w
a
ti
,
I
m
a
m
a
h
,
F
if
in
Ay
u
M
,
A
e
ri
Ra
c
h
m
a
d
,
“
In
d
o
n
e
sia
n
li
c
e
n
se
p
late
re
c
o
g
n
it
io
n
b
a
se
d
o
n
a
re
a
f
e
a
tu
re
e
x
trac
ti
o
n
”
,
T
E
L
KOM
NIKA
(
T
e
le
c
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
t
in
g
,
E
lec
tro
n
ics
a
n
d
C
o
n
t
ro
l)
,
v
o
l
.
1
7
,
n
o.
2
,
p
p
.
6
2
0
-
6
2
7
,
2
0
1
9
.
[1
9
]
V
.
Ay
u
m
i,
L
.
M
.
R.
R
e
re
,
M
.
I.
F
a
n
a
n
y
,
a
n
d
A
.
M
.
A
r
y
m
u
rth
y
,
“
Ra
n
d
o
m
A
d
ju
st
m
e
n
t
-
Ba
se
d
Ch
a
o
ti
c
M
e
tah
e
u
rist
ic
A
lg
o
rit
h
m
s
f
o
r
I
m
a
g
e
Co
n
tras
t
En
h
a
n
c
e
m
e
n
t,
”
J
o
u
rn
a
l
o
f
a
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
t
io
n
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
6
7
-
7
6
,
2
0
1
7
.
[2
0
]
S
.
S
a
laz
a
r
-
Co
lo
re
s,
J.
M
.
Ra
m
o
s
-
A
rre
g
u
ín
,
C.
J.
Ortiz
Ech
e
v
e
rri,
E.
Ca
b
a
l
-
Ye
p
e
z
,
J.
C.
P
e
d
ra
z
a
-
Orte
g
a
,
a
n
d
J.
Ro
d
rig
u
e
z
-
Re
se
n
d
iz,
“
Im
a
g
e
d
e
h
a
z
in
g
u
sin
g
m
o
rp
h
o
l
o
g
ica
l
o
p
e
n
in
g
,
d
il
a
ti
o
n
a
n
d
G
a
u
ss
ian
f
il
terin
g
,
”
S
i
g
n
a
l
,
Ima
g
e
Vi
d
e
o
Pr
o
c
e
ss
.
,
v
o
l.
1
2
,
n
o
.
7
,
p
p
.
1
3
2
9
-
1
3
3
5
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.