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
.
3
5
6
~
3
6
2
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
1
.
p
p
356
-
3
6
2
35
6
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
Struct
uring
Ele
ments o
f
H
i
t
o
r Mis
s to Identi
fy Pat
te
rn
o
f
Bench
m
a
r
k
La
tin
Alp
ha
bets S
tr
o
k
es
No
rz
eha
n Sa
k
a
m
a
t
1
,
No
o
r
E
la
iza
Abd K
ha
lid
2
,
I
n
da
I
s
ha
da
h Na
zr
ul Az
ha
2
1
Ce
n
tre o
f
F
o
u
n
d
a
ti
o
n
S
t
u
d
ies
,
U
n
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
R
A
,
Ca
wa
n
g
a
n
S
e
lan
g
o
r
,
Ka
m
p
u
s De
n
g
k
il
,
S
e
lan
g
o
r
Da
ru
l
E
h
sa
n
,
M
a
lay
sia
2
F
a
c
u
lt
y
o
f
Co
m
p
u
ter an
d
M
a
th
e
m
a
ti
c
a
l
S
c
ien
c
e
s
,
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
A
RA
,
M
a
la
y
sia
Ca
wa
n
g
a
n
S
e
lan
g
o
r
,
Ka
m
p
u
s S
h
a
h
A
la
m
,
S
e
lan
g
o
r
Da
ru
l
Eh
sa
n
,
M
a
la
y
sia
Art
icl
e
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
,
2
0
1
8
R
ev
i
s
ed
J
u
l 1
0
,
2
0
1
8
A
cc
ep
ted
Ju
l 2
5
,
2
0
1
8
Id
e
n
ti
f
ica
ti
o
n
o
f
f
e
a
tu
re
s
in
c
o
rr
e
c
t
a
lp
h
a
b
e
t
stro
k
e
f
o
rm
a
ti
o
n
is
a
p
rim
a
r
y
f
a
c
to
r
in
a
c
k
n
o
w
led
g
in
g
h
a
n
d
w
rit
in
g
leg
ib
il
it
y
.
Hit
–
or
-
M
iss
tran
sf
o
r
m
is
a
m
o
rp
h
o
lo
g
y
o
p
e
ra
to
r
t
h
a
t
is
o
f
ten
a
p
p
l
ied
t
o
i
d
e
n
ti
f
y
g
e
o
m
e
tri
c
f
e
a
tu
re
s.
Id
e
n
ti
f
y
in
g
th
e
c
o
rre
c
t
stru
c
tu
rin
g
e
le
m
e
n
ts
(S
Es)
p
ro
v
id
e
s
a
g
o
o
d
g
e
o
m
e
tri
c
f
e
a
tu
re
e
x
tra
c
ti
o
n
.
T
h
e
re
f
o
re
th
is
re
se
a
r
c
h
p
ro
p
o
se
s
to
id
e
n
ti
fy
g
e
n
e
ric
S
Es
re
p
re
se
n
ti
n
g
a
lp
h
a
b
e
t
stro
k
e
s.
T
h
e
h
a
n
d
w
rit
in
g
f
o
n
t
u
se
d
is
S
y
a
z
a
li
n
a
8
3
v
3
w
h
ich
is
p
o
p
u
larly
u
se
in
tea
c
h
in
g
w
rit
in
g
f
o
r
lo
w
e
r
p
ri
m
a
r
y
s
c
h
o
o
l
c
h
il
d
re
n
in
M
a
lay
si
a
.
T
h
e
m
e
th
o
d
o
lo
g
y
c
o
n
sists
o
f
f
o
u
r
p
h
a
se
s
w
h
ich
a
re
a
lp
h
a
b
e
t
se
lec
ti
o
n
;
im
a
g
e
p
re
-
p
ro
c
e
ss
in
g
;
m
a
n
u
a
l
m
e
a
su
re
m
e
n
t
a
n
d
h
i
t
o
r
m
iss
a
lg
o
rit
h
m
w
it
h
sin
g
le
a
n
d
v
a
rio
u
s
c
o
m
b
in
a
ti
o
n
o
f
2
x
2
,
3
x
3
a
n
d
5
x
5
S
E
w
in
d
o
w
siz
e
;
a
n
d
S
Es
p
e
rf
o
rm
a
n
c
e
u
sin
g
P
e
a
rso
n
c
o
rre
la
ti
o
n
.
T
h
e
c
o
m
b
in
a
ti
o
n
o
f
h
o
rizo
n
tal
a
n
d
v
e
rti
c
a
l,
rig
h
t
d
iag
o
n
a
l
a
n
d
lef
t
d
ia
g
o
n
a
l
S
Es
p
e
rf
o
r
m
s
w
e
ll
w
it
h
v
e
r
y
stro
n
g
c
o
rre
lat
io
n
i
n
d
e
tec
ti
n
g
S
im
p
le
S
traig
h
t
L
in
e
(S
S
L
),
Co
m
p
lex
S
traig
h
t
L
in
e
(CS
L
)
,
Cu
rv
e
L
in
e
(CL
)
a
n
d
Co
m
b
in
a
ti
o
n
o
f
Cu
rv
e
L
in
e
a
n
d
S
im
p
le
S
traig
h
t
L
in
e
(CL
S
S
L
)
b
a
se
d
o
n
Ev
a
n
‘s
c
o
rre
latio
n
g
u
id
e
.
K
ey
w
o
r
d
s
:
Han
d
w
r
iti
n
g
s
tr
o
k
e
Mo
r
p
h
o
lo
g
y
Hit o
r
m
is
s
Stru
ct
u
r
in
g
el
e
m
en
t
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
:
No
r
ze
h
an
Sa
k
a
m
at
,
C
en
tr
e
o
f
Fo
u
n
d
atio
n
St
u
d
ies
,
Un
i
v
er
s
iti T
ek
n
o
lo
g
i M
A
R
A
,
C
a
w
an
g
a
n
Sela
n
g
o
r
,
Ka
m
p
u
s
Den
g
k
il
,
Selan
g
o
r
Dar
u
l E
h
s
an
,
Ma
la
y
s
ia
.
E
m
ail:
n
o
r
ze
h
an
0
1
2
@
s
ala
m
.
u
it
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Ass
es
s
i
n
g
h
an
d
w
r
it
in
g
in
L
ati
n
alp
h
ab
ets
i
n
v
o
l
v
es
a
n
al
y
zin
g
th
e
co
m
p
o
s
i
tio
n
o
f
co
r
r
ec
t
g
eo
m
etr
i
c
ch
ar
ac
ter
s
tr
o
k
es.
E
ac
h
alp
h
a
b
et
s
tr
o
k
e
p
atter
n
s
f
o
r
m
atio
n
h
as
a
s
p
ec
i
f
ic
d
ir
ec
tio
n
a
n
d
s
eq
u
en
ce
,
len
g
t
h
a
n
d
cu
r
v
at
u
r
e;
r
elati
v
e
to
t
h
e
s
u
b
s
eq
u
en
t
s
tr
o
k
es
in
a
n
alp
h
ab
et.
I
n
o
r
d
er
to
f
ac
ilit
ate
teac
h
i
n
g
an
d
lear
n
i
n
g
,
w
o
r
d
p
r
o
ce
s
s
o
r
s
f
o
n
ts
ar
e
u
s
ed
to
cr
ea
te
th
e
r
elev
an
t
m
ater
ial
s
f
o
r
th
is
m
atter
.
Fo
n
ts
li
k
e
C
o
m
ic
San
s
Ms,
S
y
az
ali
n
a8
3
v
3
,
C
en
t
u
r
y
Go
t
h
i
c,
T
w
C
en
MT
,
T
w
C
e
n
MT
C
o
n
d
en
s
ed
,
T
w
C
e
n
MT
C
o
n
d
en
s
ed
E
x
tr
a
B
o
ld
an
d
P
r
im
eti
m
e
ar
e
r
ec
o
m
m
e
n
d
ed
b
y
a
g
r
o
u
p
o
f
Ma
la
y
s
ia
n
teac
h
er
in
f
ac
i
litati
n
g
teac
h
i
n
g
an
d
lear
n
i
n
g
[
1
]
.
S
y
az
ali
n
a8
3
v
3
f
o
n
t
w
as
cr
ea
t
ed
b
y
a
p
r
i
m
ar
y
s
c
h
o
o
l
teac
h
er
an
d
d
esi
g
n
ed
b
ased
o
n
p
r
in
ted
Ma
la
y
s
ia
n
tex
t
b
o
o
k
[
2
]
.
T
h
ese
f
o
n
t
s
tr
o
k
e
f
o
r
m
at
io
n
s
ar
e
f
r
eq
u
e
n
tl
y
u
s
ed
to
teac
h
lev
e
l
o
n
e
p
r
i
m
ar
y
s
ch
o
o
l
ch
ild
r
en
a
g
ed
s
ix
y
ea
r
s
o
ld
.
Ma
n
y
atte
m
p
ts
h
av
e
b
ee
n
m
ad
e
to
au
to
m
atic
all
y
id
en
ti
f
y
co
r
r
ec
t
letter
f
o
r
m
atio
n
to
s
p
ee
d
u
p
th
e
as
s
ess
m
e
n
t p
r
o
ce
s
s
.
Var
io
u
s
m
et
h
o
d
s
an
d
ap
p
r
o
ac
h
es
h
a
v
e
b
ee
n
u
s
ed
to
r
ec
o
g
n
ize
th
e
co
r
r
ec
tn
ess
o
f
t
h
e
h
an
d
w
r
itte
n
f
o
r
m
atio
n
t
h
r
o
u
g
h
s
tr
o
k
e
p
a
tter
n
d
ec
o
m
p
o
s
itio
n
s
u
c
h
as
p
atter
n
r
ec
o
g
n
itio
n
,
A
r
ti
f
ici
al
n
e
u
r
al
n
et
w
o
r
k
,
ev
o
lu
tio
n
ar
y
al
g
o
r
ith
m
s
a
n
d
m
o
r
p
h
o
lo
g
y
al
g
o
r
ith
m
s
.
P
atter
n
r
ec
o
g
n
it
io
n
b
ased
m
et
h
o
d
s
ar
e
p
o
p
u
lar
in
s
o
lv
i
n
g
p
r
o
b
le
m
s
r
elate
d
to
id
en
ti
f
icatio
n
o
f
tex
t,
n
u
m
b
er
s
o
r
i
m
ag
e.
I
n
te
x
t
s
t
u
d
ies
ar
ea
s
,
it
is
w
id
el
y
u
s
ed
in
id
en
ti
f
icatio
n
o
f
s
h
ap
es
a
n
d
s
tr
o
k
es
i
n
L
ati
n
alp
h
ab
et
s
[
3
-
4
]
,
C
h
i
n
e
s
e
s
tr
o
k
e
s
[
5
]
,
Gu
r
u
m
u
k
h
i
[
6
-
8
]
an
d
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
S
tr
u
ctu
r
in
g
E
leme
n
ts
o
f H
it o
r
Mis
s
to
I
d
en
tify P
a
tte
r
n
o
f B
en
ch
ma
r
k
La
tin
A
lp
h
a
b
ets…
(
N
o
r
z
eh
a
n
S
a
k
a
ma
t
)
357
Ar
ab
ic
ch
ar
ac
ter
s
[
9
-
1
0
]
.
C
h
ai
n
co
d
e
w
er
e
ap
p
lied
b
y
[
11
-
1
3
]
o
n
h
an
d
w
r
itte
n
A
r
ab
ic
alp
h
ab
et
to
d
etec
t
o
r
d
er
,
to
tal,
lik
en
e
s
s
a
n
d
d
ir
ec
tio
n
o
f
s
tr
o
k
es.
C
h
ai
n
co
d
es
wer
e
also
u
s
ed
to
co
m
p
ar
es
s
tr
o
k
e
f
o
r
m
atio
n
o
f
h
an
d
w
r
itte
n
L
ati
n
alp
h
ab
ets
to
co
n
v
e
n
tio
n
al
r
u
les
o
f
alp
h
ab
et
f
o
r
m
atio
n
tau
g
h
t
i
n
s
ch
o
o
l
[
3
]
.
Ho
w
e
v
er
,
ch
ai
n
co
d
e
ar
e
f
o
u
n
d
to
b
e
s
u
s
ce
p
tib
le
to
n
o
is
e
an
d
d
e
m
a
n
d
h
i
g
h
m
e
m
o
r
y
an
d
p
r
o
ce
s
s
i
n
g
p
o
w
er
[
1
4
]
.
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
(
ANN)
b
ased
m
et
h
o
d
is
an
o
t
h
er
h
an
d
w
r
iti
n
g
ass
e
s
s
m
e
n
t
m
eth
o
d
u
s
ed
b
y
r
esear
ch
er
s
.
A
NN
is
a
co
m
p
u
t
atio
n
al
m
o
d
el
t
h
at
r
ep
licate
th
e
ca
p
ab
ilit
y
o
f
h
u
m
an
b
r
ain
s
n
eu
r
al
n
et
w
o
r
k
s
to
lear
n
an
d
r
elea
r
n
a
s
its
n
e
u
r
al
n
et
w
o
r
k
c
h
a
n
g
e
s
b
ased
o
n
i
n
p
u
t
f
ed
an
d
o
u
tp
u
t
p
r
o
d
u
ce
d
.
I
t
w
as
ap
p
lied
i
n
an
al
y
z
in
g
p
er
s
o
n
a
lit
y
o
f
a
p
er
s
o
n
b
ased
o
n
o
f
f
li
n
e
h
a
n
d
w
r
it
ten
s
m
al
l
lette
r
‗
t
‘
[
1
5
-
16]
an
d
to
ass
es
s
c
h
ild
r
en
h
an
d
w
r
iti
n
g
b
ased
o
n
th
e
t
y
p
o
lo
g
y
o
f
s
tr
o
k
e
t
y
p
e,
s
eq
u
e
n
ce
s
,
a
n
d
d
ir
ec
tio
n
o
f
L
ati
n
alp
h
ab
et
f
o
r
m
atio
n
[
1
7
-
1
8
]
.
T
h
e
s
tr
o
k
es
ar
e
class
i
f
ied
i
n
to
th
r
ee
t
y
p
e
s
o
f
s
tr
o
k
e
p
atter
n
s
w
h
ic
h
ar
e
s
tr
ai
g
h
t
lin
e,
co
m
p
le
x
s
tr
aig
h
t
li
n
e
a
n
d
cu
r
v
e.
E
ac
h
s
tr
o
k
e
w
o
u
ld
h
a
v
e
i
ts
o
w
n
r
an
g
e
o
f
B
P
NN
n
e
u
r
o
n
v
al
u
e.
T
h
e
test
e
d
h
an
d
w
r
iti
n
g
v
alu
e
s
w
ill
th
e
n
b
e
co
m
p
ar
ed
to
B
P
NN
n
eu
r
o
n
v
al
u
e
o
f
r
ef
er
en
ce
a
lp
h
ab
et
[
1
7
]
.
I
n
an
o
th
er
r
esear
ch
,
B
P
NN
v
al
u
es
an
d
c
o
r
r
elatio
n
an
al
y
s
i
s
m
et
h
o
d
s
wer
e
u
s
ed
to
a
n
al
y
ze
t
h
e
ac
c
u
r
ac
y
o
f
s
i
x
co
m
p
le
x
s
tr
aig
h
t
li
n
e
L
ati
n
alp
h
ab
et
f
o
r
m
at
io
n
s
.
B
P
NN
ar
e
k
n
o
w
n
f
o
r
its
ac
c
u
r
ac
y
an
d
v
er
s
atil
i
t
y
,
t
h
e
ac
cu
r
ac
y
o
f
B
P
NN
d
ep
en
d
s
o
n
n
u
m
b
er
s
o
f
tr
ain
d
ata
f
ed
.
T
h
e
h
i
g
h
er
t
h
e
v
o
lu
m
e
o
f
tr
ai
n
i
n
g
d
ata
i
s
s
u
p
p
lies
to
B
P
NN,
t
h
e
m
o
r
e
ac
c
u
r
ate
th
e
r
es
u
lt
w
i
ll b
e.
Ho
w
ev
er
,
d
u
e
to
t
h
ese
f
ac
ts
,
it
w
a
s
d
is
co
v
er
ed
th
at
B
P
NN
is
ti
m
e
-
co
n
s
u
m
in
g
d
u
e
to
th
e
n
ee
d
s
to
tr
ain
lo
ts
o
f
d
ata
an
d
co
m
p
le
x
it
y
o
f
p
r
o
ce
s
s
i
n
g
[
1
8
]
.
E
v
o
lu
tio
n
ar
y
al
g
o
r
ith
m
(
E
A
)
b
ased
tech
n
iq
u
es
w
h
ic
h
w
er
e
in
s
p
ir
e
d
f
r
o
m
t
h
e
b
io
lo
g
ical
ev
o
lu
t
io
n
s
ar
e
also
u
s
ed
in
d
etec
tin
g
alp
h
ab
et
s
tr
o
k
es.
Gen
etic
A
l
g
o
r
ith
m
(
G
A
)
is
o
n
e
o
f
th
e
w
id
el
y
ap
p
lied
E
A
t
ec
h
n
iq
u
es
ar
e
b
ased
o
n
th
e
ev
o
lu
tio
n
ar
y
id
ea
s
o
f
n
atu
r
al
s
elec
tio
n
an
d
g
e
n
etics.
I
t
w
a
s
u
s
ed
to
d
etec
t
an
d
e
x
t
r
ac
t
h
an
d
w
r
i
ti
n
g
s
tr
o
k
es
a
n
d
f
ea
tu
r
es
[
1
9
]
u
s
i
n
g
th
e
co
n
ce
p
t
o
f
f
it
n
es
s
f
u
n
cti
o
n
.
G
A‘
s
p
atter
n
r
ec
o
g
n
itio
n
r
esu
lt
is
h
i
g
h
l
y
d
ep
en
d
en
t
o
n
f
i
tn
e
s
s
f
u
n
c
tio
n
d
esig
n
.
P
o
o
r
d
esig
n
o
f
f
it
n
es
s
f
u
n
ctio
n
w
ill r
es
u
lt i
n
i
n
ef
f
icie
n
t o
r
in
co
m
p
r
eh
e
n
s
ib
le
r
ec
o
g
n
itio
n
p
r
o
d
u
ct.
I
n
g
e
n
er
al
m
o
r
p
h
o
lo
g
y
m
ea
n
s
t
h
e
s
t
u
d
y
o
f
a
p
ar
ticu
lar
f
o
r
m
,
s
h
ap
e,
o
r
s
tr
u
ct
u
r
e.
C
o
n
v
e
x
a
n
d
co
n
ca
v
e
h
u
ll
s
ar
e
u
s
ef
u
l
m
o
r
p
h
o
lo
g
y
co
n
ce
p
ts
u
s
ed
f
o
r
a
w
id
e
v
ar
iet
y
o
f
ap
p
licatio
n
ar
ea
s
,
s
u
c
h
as
p
atter
n
r
ec
o
g
n
itio
n
,
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
,
s
tati
s
tic
s
,
an
d
clas
s
i
f
icatio
n
tas
k
s
.
Ho
w
e
v
er
,
it
w
a
s
d
is
co
v
er
ed
th
at
co
n
v
ex
h
u
l
l
co
u
ld
n
o
t
co
m
p
r
eh
e
n
s
i
v
el
y
id
e
n
ti
f
y
th
e
g
eo
m
etr
ical
f
ea
t
u
r
es
o
f
a
s
h
ap
e
[
5
]
.
I
n
ce
r
tain
ap
p
licatio
n
it
d
o
es
n
o
t
f
u
ll
y
r
e
f
lect
t
h
e
g
eo
m
e
tr
ical
ch
ar
ac
ter
is
t
ics
o
f
a
d
ataset
s
in
ce
it
d
o
esn
‘
t
f
o
llo
w
t
h
e
p
at
h
o
f
th
e
o
u
ter
m
o
s
t
p
o
in
ts
.
T
o
o
v
er
co
m
e
th
e
d
r
aw
b
ac
k
o
f
co
n
v
e
x
h
u
ll
al
g
o
r
ith
m
,
co
n
ca
v
e
h
u
ll
al
g
o
r
ith
m
w
a
s
in
tr
o
d
u
ce
d
.
T
h
e
co
n
ca
v
e
h
u
ll
ap
p
r
o
ac
h
is
a
m
o
r
e
ad
v
a
n
ce
d
ap
p
r
o
ac
h
u
s
ed
to
ca
p
tu
r
e
th
e
ex
ac
t
s
h
ap
e
o
f
th
e
s
u
r
f
ac
e
o
f
a
d
ataset;
n
ev
er
t
h
eles
s
,
f
o
r
m
u
lat
in
g
t
h
e
s
e
t
o
f
co
n
ca
v
e
h
u
ll
i
s
d
if
f
ic
u
lt
[
2
0
]
.
B
o
u
n
d
ar
ies
e
x
tr
ac
tio
n
,
Hit
-
or
-
M
is
s
T
r
an
s
f
o
r
m
(
HM
T
)
an
d
r
eg
io
n
f
ill
in
g
ar
e
o
th
er
ex
a
m
p
l
es
o
f
w
id
el
y
u
s
ed
ap
p
licati
o
n
o
f
m
o
r
p
h
o
lo
g
y
alg
o
r
ith
m
s
[
2
1
-
2
2
]
.
T
h
e
HM
T
is
a
f
u
n
d
a
m
en
ta
l
o
p
er
atio
n
o
n
b
in
ar
y
i
m
ag
e
s
w
h
ic
h
h
a
s
b
ee
n
w
id
el
y
u
s
ed
f
o
r
4
0
y
ea
r
s
[
2
3
]
.
HM
T
is
a
w
ell
-
k
n
o
w
n
m
o
r
p
h
o
lo
g
ical
tr
an
s
f
o
r
m
th
at
p
r
o
v
id
es
a
n
e
x
tr
e
m
e
l
y
p
o
w
er
f
u
l
s
et
o
f
to
o
ls
f
o
r
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
T
h
e
in
p
u
t
o
f
HM
T
ar
e
b
in
ar
y
i
m
a
g
es
a
n
d
a
s
p
ec
if
ica
ll
y
d
es
ig
n
ed
te
m
p
late
ca
lled
s
tr
u
ct
u
r
in
g
ele
m
e
n
t
(
SE)
.
Str
u
ctu
r
i
n
g
ele
m
en
t
s
(
SE)
is
a
p
r
e
-
d
ef
in
ed
te
m
p
late
u
s
ed
to
id
en
tify
g
r
o
u
p
s
o
f
co
n
n
ec
ted
p
i
x
els
th
a
t
co
m
p
l
y
w
it
h
ce
r
tai
n
g
eo
m
etr
ic
p
r
o
p
e
r
ties
o
f
th
e
a
n
al
y
ze
d
b
i
n
ar
y
i
m
ag
e
s
b
ased
o
n
it
s
f
o
r
eg
r
o
u
n
d
an
d
b
ac
k
g
r
o
u
n
d
.
T
h
e
ac
cu
r
ac
y
o
f
t
h
i
s
al
g
o
r
ith
m
i
s
g
r
ea
tl
y
d
ep
en
d
en
t
o
n
its
s
h
ap
e
a
n
d
s
ize
o
f
t
h
e
SE.
[
2
4
]
T
h
u
s
th
is
s
tu
d
y
i
s
co
n
d
u
cted
w
it
h
th
e
p
u
r
p
o
s
e
o
f
s
ee
k
in
g
f
o
r
th
e
ap
p
r
o
p
r
iate
g
en
er
al
SE
d
ec
o
m
p
o
s
itio
n
o
f
HM
T
th
at
c
an
ac
cu
r
atel
y
ex
tr
ac
t a
n
d
r
ec
o
g
n
ized
L
ati
n
alp
h
ab
et
i
m
ag
e
s
.
2.
RE
L
AT
E
D
WO
RK
S
C
h
ea
e
t
al
[
3
]
ex
p
r
ess
ed
t
h
a
t
L
at
in
a
lp
h
ab
ets
ar
e
co
m
b
i
n
atio
n
o
f
s
tr
o
k
e
p
atter
n
s
ca
te
g
o
r
ized
as
s
i
m
p
le
s
tr
ai
g
h
t
lin
e
s
,
co
m
p
le
x
s
tr
aig
h
t
li
n
es
a
n
d
cu
r
v
e
li
n
es.
L
a
tin
alp
h
ab
ets
f
o
r
m
a
ti
o
n
ar
e
m
ad
e
u
p
o
f
s
i
m
p
le
s
t
o
f
ele
m
e
n
t
s
w
h
ic
h
ar
e
o
n
e
o
r
m
o
r
e
s
tr
aig
h
t
li
n
es
c
o
m
p
r
i
s
in
g
o
f
v
er
tica
l,
h
o
r
izo
n
tal
o
r
d
iag
o
n
al
lin
es
to
a
m
o
r
e
co
m
p
lex
c
u
r
v
e
li
n
e
s
co
m
p
r
is
i
n
g
o
f
a
w
h
o
le
cir
cl
e
o
r
s
em
i
-
cir
cle.
Fi
f
tee
n
L
ati
n
alp
h
ab
et
co
m
p
r
is
e
s
o
f
ar
e
s
in
g
le
d
ir
ec
tio
n
al
s
tr
a
ig
h
t
li
n
e
s
co
n
s
is
tin
g
o
f
a
co
m
b
in
at
io
n
o
f
h
o
r
izo
n
tal
(
|
)
,
v
er
tical
(
_
)
o
r
d
iag
o
n
al(
/
an
d
\
)
.
T
h
ese
ca
n
f
u
r
t
h
er
b
e
d
i
v
id
ed
in
to
t
w
o
g
r
o
u
p
s
t
h
at
i
s
s
i
m
p
le
s
tr
ai
g
h
t li
n
es (
A
,
E
,
F,
H,
I
,
K,
M,
N,
T
,
X,
Y)
an
d
co
m
p
lex
s
tr
ai
g
h
t
li
n
es
w
h
ich
co
m
b
i
n
es
t
w
o
o
r
m
o
r
e
co
m
p
le
x
li
n
e
s
w
it
h
i
n
o
n
e
s
in
g
le
s
tr
o
k
e
(
L
,
V
,
W
,
o
r
Z
)
.
T
h
r
ee
l
etter
s
ar
e
m
ad
e
u
p
en
tire
l
y
o
f
cu
r
v
ed
lin
e
s
w
h
ich
ar
e
C
,
O,
S.
L
etter
s
s
u
c
h
as
B
,
D,
J
,
P
,
R
,
U
ar
e
co
n
s
tr
u
cted
f
r
o
m
s
tr
aig
h
t li
n
es a
n
d
cu
r
v
es,
o
r
s
e
m
i
-
c
ir
cles (
b
o
w
l
s
)
co
n
n
e
cted
in
v
ar
io
u
s
w
a
y
.
Fin
all
y
,
t
w
o
letter
s
G
an
d
Q
ar
e
ess
en
tial
l
y
cir
c
u
lar
,
b
u
t
co
n
s
is
t
o
f
s
h
o
r
t
b
ar
o
r
s
p
u
r
(
s
tr
aig
h
t
o
r
cu
r
led
)
to
d
if
f
er
e
n
tiate
t
h
e
m
f
r
o
m
s
i
m
ila
r
cu
r
v
ed
letter
s
w
h
ich
i
s
C
a
n
d
O
r
esp
ec
tiv
el
y
.
HM
T
is
ca
p
ab
le
o
f
id
en
ti
f
y
i
n
g
ce
r
tain
g
eo
m
etr
ic
p
r
o
p
er
ties
b
ased
o
n
r
elati
v
e
o
r
d
er
in
g
o
f
p
ix
el
v
alu
e
s
k
n
o
w
n
a
s
s
tr
u
ct
u
r
in
g
e
le
m
e
n
ts
.
T
h
e
s
tr
u
ct
u
r
in
g
ele
m
en
ts
ar
e
r
ep
r
ese
n
ted
as
a
s
m
al
l
m
atr
i
x
o
f
p
ix
el
s
,
ea
ch
w
i
th
a
v
al
u
e
o
f
1
o
r
0
.
T
h
e
d
i
m
e
n
s
io
n
s
o
f
th
e
m
atr
ix
d
eter
m
i
n
e
t
h
e
o
v
er
all
s
ize
o
f
th
e
s
tr
u
ct
u
r
in
g
ele
m
e
n
t,
a
n
d
it
s
s
h
ap
e
is
d
eter
m
i
n
ed
b
y
th
e
p
atter
n
o
f
o
n
es
a
n
d
ze
r
o
s
.
U
s
u
al
l
y
HM
T
u
s
e
s
t
h
e
f
i
x
ed
SE
p
air
in
th
e
g
lo
b
al
i
m
a
g
e,
a
n
d
o
n
l
y
e
x
tr
ac
ts
t
h
e
o
b
j
ec
t
o
f
th
e
s
a
m
e
s
ize
an
d
s
h
ap
e
o
n
th
e
f
o
r
eg
r
o
u
n
d
i
m
ag
e.
So
m
e
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
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
3
5
6
–
362
358
r
esear
ch
er
s
m
atc
h
ed
SE
as
‗
f
its
‘
w
h
ile
o
th
er
s
as
‗
h
its
‘
[
2
5
]
.
HM
T
h
as
b
ee
n
u
s
ed
to
r
ec
o
g
n
ize
h
a
n
d
w
r
itte
n
B
en
g
ali
n
u
m
er
als
[
2
6
-
27]
an
d
th
e
s
tu
d
y
‘
s
r
es
u
lts
in
an
ac
c
u
r
ac
y
o
f
m
o
r
e
t
h
an
9
6
% r
ec
o
g
n
i
tio
n
f
o
r
m
o
s
t o
f
t
h
e
n
u
m
er
als.
T
h
e
p
r
o
g
r
a
m
s
h
o
wn
an
ac
ce
ler
ated
av
er
a
g
e
ti
m
e
tak
en
b
y
th
e
p
r
o
g
r
a
m
to
id
e
n
ti
f
y
ea
c
h
n
u
m
er
al
ev
en
f
o
r
a
v
er
y
lo
w
-
s
p
ec
co
m
p
u
ter
.
E
u
g
e
n
e
a
n
d
E
d
w
ar
d
[
2
8
]
d
ev
elo
p
ed
a
class
o
f
s
tr
u
ct
u
r
in
g
-
ele
m
en
t
p
air
s
f
o
r
s
e
g
m
en
tat
io
n
-
f
r
ee
ch
ar
ac
t
er
r
ec
o
g
n
itio
n
v
ia
th
e
m
o
r
p
h
o
lo
g
ical
H
MT
f
o
r
r
ec
o
g
n
izi
n
g
C
o
u
r
ier
f
o
n
t.
B
o
th
h
it
an
d
m
i
s
s
s
tr
u
ct
u
r
in
g
ele
m
e
n
ts
ar
e
s
elec
ted
s
o
th
at
th
e
h
i
t
-
or
-
m
is
s
tr
an
s
f
o
r
m
ca
n
b
e
ap
p
lied
ac
r
o
s
s
th
e
test
i
m
a
g
e
w
i
th
o
u
t
p
r
io
r
s
eg
m
en
t
atio
n
.
A
lt
h
o
u
g
h
th
e
y
u
s
e
s
b
asic
HM
T
m
eth
o
d
,
it
w
a
s
p
r
o
v
en
to
ac
h
ie
v
e
h
i
g
h
r
ates o
f
ac
cu
r
ac
y
o
n
tex
t a
n
d
v
er
y
r
o
b
u
s
t
w
it
h
r
esp
ec
t to
th
e
t
h
r
es
h
o
ld
lev
el
f
o
r
th
e
i
n
p
u
t g
r
a
y
-
s
ca
le
d
ata.
No
liter
atu
r
e
o
n
f
in
d
i
n
g
th
e
ap
p
r
o
p
r
iate
g
en
er
al
SE
d
ec
o
m
p
o
s
itio
n
w
as
f
o
u
n
d
h
o
w
e
v
er
th
er
e
ar
e
s
ev
er
al
liter
at
u
r
es
d
escr
ib
e
S
E
o
n
v
ar
io
u
s
u
s
ag
e
f
o
r
i
m
a
g
e
r
ec
o
g
n
itio
n
.
Do
h
et
al
[
2
9
]
s
tu
d
ies
t
h
e
ch
o
ice
o
f
SEs
f
o
r
th
e
r
ec
o
g
n
itio
n
o
f
a
class
o
f
v
ar
io
u
s
o
b
j
ec
ts
.
T
h
ey
s
tar
t
f
r
o
m
t
w
o
s
e
ts
:
a
s
et
o
f
h
it
SEs
th
a
t
f
it
t
h
e
o
b
j
ec
ts
to
b
e
r
ec
o
g
n
ized
an
d
a
s
et
o
f
m
is
s
SE
s
t
h
at
f
it
t
h
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
r
esear
ch
r
esu
l
tin
g
o
n
u
s
i
n
g
s
y
n
t
h
etic
h
it
SE
co
m
p
o
s
ed
o
f
th
e
in
ter
s
ec
tio
n
o
f
all
h
it
SE
s
an
d
a
s
y
n
t
h
etic
m
is
s
SE
co
m
p
o
s
ed
o
f
th
e
u
n
io
n
o
f
all
m
i
s
s
SE
s
f
o
r
b
etter
r
ec
o
g
n
it
io
n
o
f
d
iv
er
s
e
o
b
j
ec
ts
.
Z
h
ao
an
d
Dau
t
[
3
0
]
p
r
esen
t
a
tech
n
iq
u
e
w
h
ich
u
s
es
u
p
p
er
an
d
lo
w
er
b
o
u
n
d
s
to
d
eter
m
i
n
e
t
h
e
SEs
f
o
r
u
s
e
i
n
t
h
e
HM
T
u
s
i
n
g
a
p
r
io
r
i
k
n
o
wled
g
e
ed
g
e
o
f
th
e
s
h
ap
es
to
b
e
d
etec
ted
.
T
h
is
tech
n
iq
u
e
u
s
es
t
h
e
s
k
ele
to
n
s
o
f
b
o
th
th
e
o
b
j
ec
t
to
b
e
r
ec
o
g
n
ized
a
n
d
it
s
co
m
p
le
m
e
n
t a
s
SE
s
.
3.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
m
et
h
o
d
o
lo
g
ical
ap
p
r
o
ac
h
tak
e
n
in
th
is
s
t
u
d
y
co
n
s
i
s
t
o
f
f
o
u
r
p
h
ase
as
s
h
o
w
n
in
Fi
g
u
r
e
1
.
T
h
e
in
itial
p
h
ase
is
t
h
e
alp
h
ab
et
s
e
lectio
n
b
ased
o
n
co
m
p
lex
i
t
y
o
f
s
tr
o
k
e
f
o
r
m
atio
n
.
T
h
ese
in
v
o
lv
es
s
e
lecti
n
g
ei
g
h
t
L
ati
n
alp
h
ab
ets
d
i
v
id
ed
in
to
f
o
u
r
b
ased
o
n
th
eir
co
m
p
le
x
it
y
.
T
h
ese
g
r
o
u
p
s
ar
e
Si
m
p
le
S
tr
aig
h
t
L
i
n
e
(
SS
L
)
,
C
u
r
v
e
L
in
e
(
C
L
)
,
C
o
m
p
lex
Stra
ig
h
t
L
i
n
e
(
C
S
L
)
an
d
C
o
m
b
in
at
io
n
o
f
C
o
m
p
le
x
Stra
i
g
h
t
L
in
e
a
n
d
Si
m
p
le
Stra
ig
h
t
L
in
e
(
C
C
S
L
)
.
P
h
ase
t
w
o
is
i
m
ag
e
p
r
e
-
pr
o
ce
s
s
i
n
g
.
T
h
ese
co
m
p
r
is
es
o
f
t
w
o
p
r
o
ce
s
s
es
w
h
ich
ar
e
b
in
ar
izatio
n
an
d
th
i
n
n
i
n
g
.
P
h
ase
th
r
ee
is
s
h
ap
e
r
ec
o
g
n
i
tio
n
co
n
s
i
s
ti
n
g
o
f
t
w
o
p
r
o
ce
s
s
w
h
ic
h
ar
e
m
a
n
u
al
m
ea
s
u
r
e
m
e
n
t
an
d
h
i
t
o
r
m
is
s
alg
o
r
ith
m
.
Fi
n
al
p
h
ase
is
p
er
f
o
r
m
a
n
ce
ev
al
u
atio
n
.
T
h
e
p
e
r
f
o
r
m
a
n
ce
o
f
v
ar
io
u
s
SE
te
m
p
late
s
ize
t
h
at
m
o
s
t a
p
p
r
o
p
r
iately
d
escr
ib
e
th
e
ch
o
s
e
n
L
a
tin
alp
h
ab
et
s
tr
o
k
e
f
o
r
m
at
io
n
ar
e
ev
alu
a
ted
.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
f
o
r
Sel
ec
tin
g
A
p
p
r
o
p
r
iate
Gen
er
al
SE
Dec
o
m
p
o
s
it
io
n
3
.
1
Alph
a
bet
Select
io
n B
a
s
ed
o
n
Co
m
p
lex
it
y
o
f
Str
o
k
e
F
o
r
ma
t
io
n
L
ati
n
alp
h
ab
et
co
m
p
r
is
e
s
o
f
t
w
e
n
t
y
s
i
x
letter
s
an
d
co
m
p
o
s
ed
o
f
t
w
o
m
ai
n
s
tr
o
k
e
s
f
o
r
m
a
tio
n
,
w
h
ic
h
ar
e
s
tr
aig
h
t
li
n
e
an
d
cu
r
v
e
li
n
es.
I
n
th
is
s
t
u
d
y
,
u
p
p
er
ca
s
e
l
etter
s
ar
e
g
r
o
u
p
ed
in
to
f
o
u
r
ca
teg
o
r
ies
o
f
s
tr
o
k
e
p
atter
n
s
w
h
ic
h
ar
e
Si
m
p
le
St
r
aig
h
t
L
in
e
(
SS
L
)
,
C
u
r
v
e
L
i
n
es
(
C
L
)
,
C
o
m
p
le
x
Stra
i
g
h
t
L
in
e
(
C
S
L
)
[
3
]
an
d
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
S
tr
u
ctu
r
in
g
E
leme
n
ts
o
f H
it o
r
Mis
s
to
I
d
en
tify P
a
tte
r
n
o
f B
en
ch
ma
r
k
La
tin
A
lp
h
a
b
ets…
(
N
o
r
z
eh
a
n
S
a
k
a
ma
t
)
359
co
m
b
i
n
atio
n
o
f
t
h
e
t
h
r
ee
s
tr
o
k
es
(
C
L
S
S
L
)
.
T
w
o
alp
h
ab
ets
a
r
e
s
elec
ted
f
r
o
m
ea
c
h
ca
te
g
o
r
y
i
n
t
h
i
s
s
tu
d
y
.
T
h
e
s
elec
ted
alp
h
ab
ets ar
e
d
ep
icted
in
T
ab
le
1
ac
co
r
d
in
g
to
th
eir
co
m
p
le
x
it
y
.
T
ab
le
1
.
Stro
k
e
P
atter
n
an
d
Selecte
d
A
lp
h
ab
et
s
S
t
r
o
k
e
P
a
t
t
e
r
n
A
l
p
h
a
b
e
t
s(
S
y
a
z
a
l
i
n
a
3
v
3
)
S
i
mp
l
e
S
t
r
a
i
g
h
t
L
i
n
e
(
S
S
L
)
A
E
C
u
r
v
e
L
i
n
e
s(
C
L
)
C
J
C
o
mp
l
e
x
S
t
r
a
i
g
h
t
L
i
n
e
(
C
S
L
)
L
V
C
o
mb
i
n
a
t
i
o
n
o
f
S
S
L
,
C
L
a
n
d
C
S
L
(
C
L
S
S
L
)
B
G
A
lp
h
ab
et
A
a
n
d
E
ar
e
s
elec
ted
to
r
e
p
r
esen
t
SS
L
,
C
an
d
J
r
e
p
r
esen
t
C
L
,
L
a
n
d
V
r
ep
r
esen
t
C
S
L
an
d
B
an
d
G
r
ep
r
esen
t CLSS
L
.
3
.
2
P
re
-
pro
ce
s
s
ing
T
h
is
s
ec
tio
n
d
is
c
u
s
s
ed
o
n
t
h
e
i
m
a
g
e
p
r
e
-
p
r
o
ce
s
s
in
g
ta
s
k
as
in
Fi
g
u
r
e
2
.
I
n
t
h
is
p
r
o
ce
s
s
,
th
e
e
ig
h
t
alp
h
ab
ets
ar
e
cr
o
p
p
ed
an
d
s
av
ed
in
j
p
eg
f
o
r
m
at.
T
h
e
cu
r
r
en
t
j
p
eg
f
o
r
m
at
s
h
o
w
s
th
at
th
e
i
m
a
g
es
ar
e
i
n
g
r
a
y
s
ca
le
f
o
r
m
at.
I
n
o
r
d
er
to
in
cr
ea
s
e
id
en
t
if
ica
tio
n
ac
c
u
r
ac
y
o
f
th
e
a
lp
h
ab
et
s
tr
o
k
e
s
,
th
e
i
m
a
g
es
ar
e
co
n
v
er
ted
to
b
in
ar
y
f
o
r
m
at
an
d
t
h
in
n
i
n
g
o
p
er
atio
n
r
esp
ec
ti
v
el
y
.
Fig
u
r
e
2
.
P
r
e
-
p
r
o
ce
s
s
in
g
T
h
e
b
in
ar
izatio
n
p
r
o
ce
s
s
co
n
v
er
ts
th
e
g
r
e
y
le
v
el
i
m
ag
e
to
b
lack
an
d
w
h
ite
i
m
a
g
es
to
m
in
i
m
ize
t
h
e
in
tr
a
-
c
lass
v
ar
ia
n
ce
.
Ot
s
u
‘
s
t
h
r
esh
o
ld
in
g
m
et
h
o
d
w
as
s
elec
t
ed
.
Nex
t
i
s
t
h
e
m
o
r
p
h
o
lo
g
ical
th
i
n
n
in
g
p
r
o
ce
s
s
to
r
ed
u
ce
th
e
alp
h
ab
et
i
m
ag
e
to
a
s
in
g
le
p
ix
el
t
h
ic
k
n
e
s
s
.
T
h
is
r
ed
u
ce
s
th
e
p
r
o
ce
s
s
i
n
g
ti
m
e
a
s
w
ell
a
s
r
e
m
o
v
e
t
h
e
p
o
s
s
ib
ilit
y
o
f
d
etec
tin
g
f
a
ls
e
tr
iv
ial
d
etail
s
[
3
1
]
Fig
u
r
e
3
s
h
o
w
s
th
e
r
es
u
l
t o
f
b
in
ar
izatio
n
a
n
d
th
i
n
n
in
g
.
Fig
u
r
e
3
.
B
in
ar
izatio
n
an
d
T
h
in
n
i
n
g
o
f
t
h
e
T
est I
m
a
g
e
3
.
3
Sh
a
pe
Rec
o
g
nitio
n
T
h
is
p
h
ase
co
n
s
is
t
s
o
f
a
t
w
o
m
ai
n
p
r
o
ce
s
s
w
h
ic
h
is
m
a
n
u
a
l
m
ea
s
u
r
e
m
en
t
a
n
d
u
ti
lizatio
n
o
f
h
it
o
r
m
is
s
alg
o
r
it
h
m
.
3
.
3
.
1
.
M
a
nu
a
l
M
ea
s
ure
m
e
nt
T
h
e
m
a
n
u
al
m
ea
s
u
r
e
m
e
n
t
w
a
s
d
o
n
e
b
y
u
s
i
n
g
a
r
u
ler
.
T
h
e
b
in
ar
ize
i
m
a
g
e
o
f
th
e
ei
g
h
t
al
p
h
ab
ets
ar
e
p
r
in
ted
an
d
ev
er
y
s
tr
o
k
e
a
r
e
m
ea
s
u
r
ed
in
ce
n
ti
m
eter
s
.
T
h
e
s
tr
o
k
es
ar
e
m
ea
s
u
r
ed
as
v
er
tical,
h
o
r
izo
n
tal,
lef
t
an
d
r
ig
h
t
d
iag
o
n
a
l.
T
h
ese
s
tr
o
k
e
m
ea
s
u
r
e
m
e
n
t
s
ar
e
r
ec
o
r
d
ed
in
a
f
o
r
m
o
f
tab
le.
T
ab
le
2
s
h
o
w
s
t
h
e
m
a
n
u
a
l
m
ea
s
u
r
e
m
e
n
t
v
al
u
e:
T
ab
le
2
.
Ma
n
u
al
Me
asu
r
e
m
e
n
t
(
cm
)
Gre
y
S
c
a
l
e
Alp
hab
e
t
I
ma
g
e
Bi
n
a
r
i
z
a
t
i
o
n
(
Ot
su’
s
M
e
t
ho
d
)
Thi
n
n
i
n
g
Pro
c
e
ss
Alp
hab
e
t
s
’Sk
e
l
e
t
o
n
I
m
a
g
e
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
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
3
5
6
–
362
360
L
i
n
e
C
a
t
e
g
o
r
y
A
l
p
h
a
b
e
t
M
a
n
u
a
l
M
e
a
s
u
r
e
me
n
t
(
c
m)
T
o
t
a
l
S
t
r
o
k
e
|
S
t
r
o
k
e
s
-
S
t
r
o
k
e
s /
S
t
r
o
k
e
s
\
S
i
mp
l
e
S
t
r
a
i
g
h
t
L
i
n
e
(
S
S
L
)
A
0
4
7
.
8
7
.
8
1
9
.
6
E
7
.
2
1
1
.
6
0
0
1
8
.
8
C
u
r
v
e
L
i
n
e
(
C
L
)
C
2
.
5
4
.
9
3
.
4
3
.
9
1
4
.
7
J
6
4
.
4
1
.
5
2
1
3
.
9
C
o
mp
l
e
x
S
t
r
a
i
g
h
t
L
i
n
e
L
6
.
8
3
.
4
0
0
1
0
.
2
V
0
0
7
.
6
7
.
6
1
5
.
2
C
o
mb
i
n
a
t
i
o
n
o
f
S
S
L
a
n
d
C
L
B
6
.
5
7
.
9
3
.
6
3
.
6
2
1
.
6
G
6
.
5
7
.
3
4
.
5
3
.
7
22
3
.
3
.
2
.
H
it
o
r
M
is
s
T
ra
ns
f
o
r
m
A
lg
o
rit
h
m
T
h
e
ef
f
ec
ti
v
e
n
es
s
o
f
HM
T
d
etec
tio
n
h
ea
v
il
y
d
ep
en
d
o
n
d
esi
g
n
o
f
SE
.
T
h
e
d
esi
g
n
o
f
SE
m
u
s
t c
o
m
p
l
y
w
it
h
t
h
e
s
tr
u
ctu
r
e
o
f
t
h
e
o
b
j
ec
t th
at
ar
e
to
b
e
d
etec
ted
.
1)
Stru
ct
u
r
in
g
E
le
m
en
t D
esi
g
n
T
h
er
e
ar
e
tw
o
m
ai
n
ch
ar
ac
ter
is
tics
t
h
at
ar
e
d
ir
ec
tl
y
r
elate
d
to
SE
th
at
i
s
s
h
ap
e
an
d
s
ize.
Sh
ap
e
i
s
cr
u
cial
f
o
r
r
ec
o
g
n
izi
n
g
o
b
j
ec
t
w
h
ile
s
ize
i
s
i
m
p
er
ativ
e
to
s
et
th
e
o
b
s
er
v
at
io
n
s
ca
le
a
n
d
cr
iter
ia
to
d
if
f
er
e
n
tiat
e
i
m
a
g
e
o
b
j
ec
t a
s
w
e
ll a
s
f
ea
tu
r
es.
As
s
tated
i
n
t
h
e
li
ter
atu
r
e
[
3
]
,
m
o
s
t
L
ati
n
alp
h
ab
ets
s
tr
o
k
es
co
n
s
is
ts
o
f
a
co
m
b
i
n
atio
n
o
f
h
o
r
izo
n
tal
(
|
)
,
v
er
tical
(
_
)
o
r
d
iag
o
n
al
lin
es(
/
a
n
d
\
)
.
T
h
u
s
t
h
e
SE
ar
e
d
esig
n
ac
co
r
d
in
g
l
y
i
n
a
2
x
2
,
3
x
3
an
d
5
x
5
m
atr
i
x
s
ize
t
h
at
r
ep
r
esen
t
s
h
o
r
izo
n
tal,
v
e
r
tical,
le
f
t
d
ia
g
o
n
a
l
an
d
r
ig
h
t
d
iag
o
n
al
s
tr
o
k
e
s
.
T
h
ese
SE
ar
e
ap
p
ly
w
it
h
t
h
e
HM
T
alg
o
r
ith
m
w
h
er
e
th
e
h
it
co
u
n
t
i
s
co
r
r
elate
d
w
it
h
th
e
co
u
n
t
f
r
o
m
t
h
e
m
an
u
al
m
ea
s
u
r
e
m
en
t.
B
ased
o
n
[
3
]
,
th
e
SE
p
atter
n
ar
e
d
esig
n
to
b
e
h
o
r
izo
n
tal,
v
er
tical,
lef
t
d
iag
o
n
al
a
n
d
r
ig
h
t
d
ia
g
o
n
al.
T
h
e
d
esig
n
s
ar
e
s
h
o
w
n
i
n
T
ab
le
3
.
T
ab
le
3
.
Stru
ctu
r
in
g
E
le
m
en
t
Sh
ap
e
an
d
Size
S
t
r
u
c
t
u
r
i
n
g
El
e
me
n
t
s Si
z
e
S
t
r
u
c
t
u
r
i
n
g
El
e
me
n
t
S
h
a
p
e
5
x
5
3
x
3
2
x
2
2)
C
o
u
n
ti
n
g
s
tr
o
k
e
u
s
i
n
g
Hi
ts
A
l
g
o
r
ith
m
T
h
e
h
it
p
r
o
ce
s
s
w
ill
m
a
tch
it
to
th
e
in
ten
d
ed
p
ix
els
(
1
s
)
,
w
h
ic
h
r
ep
r
esen
ted
th
e
s
tr
o
k
e
i
m
a
g
e,
an
d
r
e
m
o
v
e
u
n
w
a
n
ted
p
ix
el
s
(
0
s
)
o
f
t
h
e
s
tr
u
ct
u
r
e
t
h
at
it
w
a
n
t
t
o
m
i
s
s
.
H
it
o
r
m
is
s
al
g
o
r
ith
m
ar
e
ex
ec
u
ted
u
s
i
n
g
th
e
SEs i
n
tab
le
2
.
On
l
y
th
e
h
it
s
w
h
er
e
t
h
e
SE
f
u
ll
y
m
a
tch
ed
t
h
e
o
b
j
ec
t stru
ctu
r
e
ar
e
co
u
n
ted
.
Hit o
r
m
is
s
al
g
o
r
ith
m
s
ar
e
f
o
r
m
u
lated
u
s
in
g
t
h
e
f
o
llo
w
i
n
g
s
f
o
r
m
u
la:
A
∗
B
=
(
A
ª
X)
∩
[
A
c
ª
(
W
−
X)
]
B
d
en
o
tes th
e
s
et
co
m
p
o
s
ed
o
f
X
an
d
its
b
ac
k
g
r
o
u
n
d
,
t
h
e
m
a
tch
/
h
it (
o
r
s
et
o
f
m
atc
h
e
s
/h
i
ts
)
o
f
B
in
A
,
X
is
s
et
f
o
r
m
ed
f
r
o
m
ele
m
en
t
s
o
f
B
ass
o
ciate
d
w
i
th
an
o
b
ject
w
h
i
le
(
W
–
X)
ar
e
s
et
f
o
r
m
ed
f
r
o
m
ele
m
e
n
ts
o
f
B
as
s
o
ciate
d
w
i
th
th
e
co
r
r
esp
o
n
d
in
g
b
ac
k
g
r
o
u
n
d
.
I
n
itiall
y
o
n
l
y
t
h
e
Se
o
f
th
e
s
a
m
e
w
in
d
o
w
s
ize
ar
e
ex
ec
u
ted
o
n
all
th
e
s
elec
ted
alp
h
ab
ets
.
L
ater
,
a
co
m
b
i
n
atio
n
o
f
d
if
f
er
en
t
s
ize
w
i
n
d
o
w
s
ar
e
test
ed
.
T
o
av
o
id
th
e
d
if
f
er
e
n
tiatio
n
f
o
r
th
e
d
if
f
er
e
n
t
s
ize
s
th
e
r
esu
lt
s
ar
e
ca
lcu
lated
b
ased
o
n
p
er
ce
n
tag
e
o
f
t
h
e
to
tal
co
u
n
ts
.
3
.
4
Co
rr
ela
t
io
n bet
w
ee
n H
M
T
a
nd
M
a
nu
a
l
M
ea
s
ure
m
ent
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
S
tr
u
ctu
r
in
g
E
leme
n
ts
o
f H
it o
r
Mis
s
to
I
d
en
tify P
a
tte
r
n
o
f B
en
ch
ma
r
k
La
tin
A
lp
h
a
b
ets…
(
N
o
r
z
eh
a
n
S
a
k
a
ma
t
)
361
T
h
e
co
llectio
n
s
o
f
r
es
u
lt
s
ar
e
co
r
r
elate
d
ag
ain
s
t
t
h
e
m
a
n
u
a
l
m
ea
s
u
r
e
m
e
n
ts
.
P
ea
r
s
o
n
co
r
r
elatio
n
i
s
u
s
ed
to
ass
ess
t
h
e
lin
ea
r
it
y
o
f
th
e
r
esu
l
ts
.
T
h
e
ass
ess
m
e
n
t
is
d
o
n
e
b
y
an
al
y
zi
n
g
t
h
e
s
tr
en
g
t
h
o
f
th
e
co
r
r
elatio
n
co
ef
f
icie
n
t.
T
h
e
s
tr
o
n
g
er
t
h
e
c
o
r
r
elatio
n
th
e
b
etter
th
e
o
b
j
ec
t
d
escr
ip
tio
n
.
T
h
is
co
r
r
elatio
n
is
b
ased
o
n
E
v
a
n
s
co
r
r
elatio
n
g
u
id
e
[
32]
a
s
s
h
o
wn
in
T
ab
le
4
.
T
ab
le
4
.
E
v
an
s
C
o
r
r
elatio
n
G
u
id
e
C
o
r
r
e
l
a
t
i
o
n
V
a
l
u
e
D
e
scri
p
t
i
o
n
0
.
0
0
-
0
.
1
9
V
e
r
y
W
e
a
k
0
.
2
0
-
0
.
3
9
W
e
a
k
0
.
4
0
-
0
.
5
9
M
o
d
e
r
a
t
e
0
.
6
0
-
0
.
7
9
S
t
r
o
n
g
0
.
8
0
-
1
.
0
0
V
e
r
y
S
t
r
o
n
g
4.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
w
o
SE
s
ar
e
f
o
u
n
d
to
b
e
th
e
m
o
s
t
f
itt
in
g
te
m
p
late:
5
x
5
w
i
t
h
3
x
3
an
d
5
x
5
w
i
th
2
x
2
.
T
h
e
y
p
r
o
d
u
ce
d
th
e
s
a
m
e
s
co
r
e
f
o
r
co
ef
f
icie
n
t
co
r
r
elatio
n
o
f
all
letter
s
ex
ce
p
t
f
o
r
th
e
co
r
r
elatio
n
o
f
let
ter
G,
w
h
ic
h
is
s
li
g
h
tl
y
d
if
f
er
e
n
t a
s
5
x
5
w
it
h
3
x
3
v
al
u
e
is
r
=
0
.
5
9
a
nd
5
x
5
w
it
h
2
x
2
v
alu
e
o
f
r
=0
.
6
0
.
5.
CO
NCLU
SI
O
N
T
h
is
s
t
u
d
y
d
is
c
u
s
s
es
o
n
ap
p
l
y
in
g
m
o
r
p
h
o
lo
g
y
h
it
a
n
d
m
i
s
s
al
g
o
r
ith
m
i
n
e
x
tr
ac
ti
n
g
an
alp
h
ab
et
i
m
a
g
e.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
d
ep
icts
th
at
it
is
s
u
cc
e
s
s
f
u
l
in
d
eter
m
i
n
i
n
g
t
h
e
m
o
s
t
ap
p
r
o
p
r
iate
SE
f
o
r
f
ea
tu
r
e
ex
tr
ac
t
io
n
p
u
r
p
o
s
es.
B
ased
o
n
th
e
ex
p
er
i
m
en
t,
th
e
co
m
b
i
n
ati
o
n
o
f
s
m
all
s
ize
SE
A
n
d
lar
g
e
s
ize
SE
ar
e
m
o
s
t
a
p
p
r
o
p
r
iate
f
o
r
d
etec
tin
g
t
h
e
s
t
r
o
k
es
co
m
p
o
s
itio
n
o
f
alp
h
ab
ets
i
m
ag
e.
B
ased
o
n
th
e
co
n
d
u
cted
e
m
p
i
r
ical
ex
p
er
i
m
e
n
ts
,
2
x
2
SE
ar
e
b
est
f
o
r
ex
tr
ac
tio
n
f
o
r
d
iag
o
n
al
s
tr
o
k
es
li
n
e
a
n
d
5
x
5
SE
f
o
r
b
est
f
o
r
e
x
tr
ac
ti
n
g
b
o
th
v
er
tical
s
tr
o
k
e
s
a
n
d
h
o
r
i
zo
n
tal
s
tr
o
k
es.
T
h
e
co
m
b
i
n
ed
SE
w
il
l
b
e
u
s
ed
i
n
f
u
tu
r
e
s
tu
d
ie
s
f
o
r
d
etec
tin
g
co
r
r
ec
t
h
an
d
w
r
iti
n
g
s
tr
o
k
e
s
an
d
leg
ib
ilit
y
o
f
h
a
n
d
w
r
i
tin
g
s
in
L
ati
n
alp
h
ab
et
a
m
o
n
g
ch
i
ld
r
en
in
lo
w
er
p
r
i
m
ar
y
s
ch
o
o
l.
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
b
y
t
h
e
U
n
i
v
er
s
iti
T
ek
n
o
lo
g
i
M
AR
A
,
I
n
s
t
itu
te
o
f
R
e
s
ea
r
ch
Ma
n
a
g
e
m
e
n
t
&
I
n
n
o
v
a
tio
n
(
6
0
0
-
I
R
MI
/MY
R
A
5
/3
/L
E
ST
A
R
I
(
0
7
0
/2
0
1
7
)
)
.
RE
F
E
R
E
NC
E
S
[1
]
.
Isn
e
n
,
M
o
h
d
S
u
h
a
im
in
.
―
Him
p
u
n
a
n
T
e
rb
a
ik
Je
n
is
T
u
li
sa
n
(F
o
n
t)
Ya
n
g
M
e
n
a
rik
Da
n
S
e
su
a
i
Un
t
u
k
M
u
ri
d
S
e
k
o
lah
Re
n
d
a
h
‖
.
S
istem
Gu
ru
O
n
li
n
e
,
4
F
e
b
.
2
0
1
8
[2
]
.
A
z
m
a
n
.
S
u
laim
a
n
.
―
F
o
n
t
Ya
n
g
S
e
su
a
i
Un
tu
k
Ujia
n
d
a
n
P
e
p
e
rik
sa
a
n
‖
.
Bl
o
g
Cikg
u
Azma
n
,
1
9
F
e
b
2
0
1
8
[3
]
.
Ne
o
CC,
S
u
EL
M
,
Kh
a
li
d
P
I,
Ye
o
n
g
CF
.
―
M
e
th
o
d
to
De
term
in
e
Ha
n
d
w
rit
in
g
S
tro
k
e
Ty
p
e
s
a
n
d
Dire
c
ti
o
n
s
f
o
r
Early
D
e
tec
ti
o
n
o
f
Ha
n
d
w
rit
in
g
Diff
icu
lt
y
‖
.
Pro
c
e
d
ia
En
g
i
n
e
e
rin
g
.
2
0
1
2
;
4
1
:
1
8
2
4
–
9.
[4
]
.
Ho
m
e
n
d
a
W
,
Ja
strz
e
b
s
k
a
A
,
Was
z
k
ie
w
i
c
z
P
,
Zaw
a
d
z
k
a
A
.
―
P
a
tt
e
rn
Re
c
o
g
n
it
i
o
n
w
it
h
Re
jec
ti
o
n
‖
.
C
o
mp
u
ter
In
fo
rm
a
t
io
n
S
y
ste
ms
a
n
d
I
n
d
u
stri
a
l
M
a
n
a
g
e
me
n
t
L
e
c
tu
re
No
tes
i
n
Co
mp
u
ter
S
c
ien
c
e
.
2
0
1
6
;:
5
8
9
–
6
0
2
.
[5
]
.
Ch
e
n
,
Y.
D.
Jh
e
n
g
a
n
d
L
.
F
.
L
in
.
―
Co
m
p
u
ter
-
b
a
se
d
A
ss
e
ss
m
e
n
t
f
o
r
th
e
S
tro
k
e
Ord
e
r
o
f
Ch
i
n
e
se
Ch
a
ra
c
ters
W
rit
in
g
‖
.
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
n
o
v
a
ti
v
e
Co
mp
u
ti
n
g
.
2
0
0
7
;1
6
0
.
-
2
[6
]
.
Ka
u
r
H,
Ra
n
i
S
.
―
Ha
n
d
w
rit
te
n
G
u
ru
m
u
k
h
i
Ch
a
ra
c
ter
Re
c
o
g
n
it
io
n
Us
in
g
Co
n
v
o
l
u
ti
o
n
Ne
u
ra
l
Ne
t
w
o
rk
‖
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
Res
e
a
rc
h
.
2
0
1
7
;1
3
(5
):
9
3
3
-
4
3
.
[7
]
.
G
o
y
a
l
G
,
L
u
th
ra
R.
―
Ne
u
ra
l
n
e
tw
o
rk
B
a
se
d
a
p
p
ro
a
c
h
f
o
r
I
m
a
g
e
S
k
e
leto
n
iza
ti
o
n
o
n
G
u
ru
m
u
k
h
i
Ch
a
ra
c
ter
s
‖
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
De
v
e
lo
p
me
n
t
a
n
d
Res
e
a
rc
h
.
2
0
1
5
;3
(
2
):1
3
2
5
-
9.
[8
]
.
Ka
u
r
A
,
S
in
g
h
P
,
Ra
n
i
S
.
―
S
e
g
m
e
n
tatio
n
o
f
Bro
k
e
n
a
n
d
Iso
late
d
c
h
a
ra
c
ters
in
Ha
n
d
w
rit
ten
G
u
ru
m
u
k
h
i
W
o
rd
u
sin
g
Ne
ig
h
b
o
rin
g
P
ix
e
l
T
e
c
h
n
iq
u
e
‖
.
T
ra
n
sa
c
ti
o
n
s
o
n
Ne
tw
o
rk
s a
n
d
C
o
m
mu
n
ica
ti
o
n
s
.
2
0
1
5
;3
(
2
):3
6
.
[9
]
.
Ra
b
i
M
,
Am
ro
u
c
h
M
,
M
a
h
a
n
i
Z
,
M
a
m
m
a
ss
D.
―
R
e
c
o
g
n
it
io
n
o
f
c
u
rsiv
e
A
r
a
b
ic
h
a
n
d
w
rit
ten
tex
t
u
sin
g
e
m
b
e
d
d
e
d
train
in
g
b
a
se
d
o
n
HMM
s
‖
.
2
0
1
6
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
E
n
g
i
n
e
e
rin
g
&
M
IS
(
ICEM
IS
)
.
2
0
1
6
.
[1
0
]
.
M
e
tw
a
ll
y
A
H,
Kh
a
li
l
M
I,
A
b
b
a
s
HM.
―
Off
li
n
e
A
ra
b
ic
h
a
n
d
w
rit
in
g
re
c
o
g
n
it
io
n
u
si
n
g
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
ls
a
n
d
P
o
st
-
Re
c
o
g
n
it
i
o
n
L
e
x
ico
n
M
a
tc
h
in
g
‖
.
1
2
th
In
ter
n
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
o
n
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
a
n
d
S
y
ste
ms
(
ICCES
)
.
2
0
1
7
.
[1
1
]
.
El
-
S
a
wy
A
,
El
-
Ba
k
r
y
H,
L
o
e
y
M
.
―
CNN
f
o
r
Ha
n
d
w
rit
ten
A
ra
b
ic
D
ig
it
s
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
L
e
Ne
t
-
5
‖.
A
d
v
a
n
c
e
s
in
In
telli
g
e
n
t
S
y
ste
ms
a
n
d
Co
m
p
u
ti
n
g
Pro
c
e
e
d
i
n
g
s o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
In
te
ll
ig
e
n
t
S
y
ste
ms
a
n
d
In
f
o
rm
a
ti
c
s
2
0
1
6
.
2
0
1
6
;:
5
6
6
–
7
5
.
[1
2
]
.
Nu
ru
l
H
u
sn
i
n
a
Hu
sa
in
,
N
o
riza
n
M
a
t
Dia
h
,
Ha
sliza
tu
l
M
o
h
a
m
e
d
Ha
n
u
m
.
―
Th
e
Re
lev
a
n
c
e
o
f
F
re
e
m
a
n
Ch
a
in
Co
d
e
f
o
r
Co
p
y
in
g
A
c
ti
v
it
ies
‖
.
IEE
E
Co
n
fer
e
n
c
e
o
n
e
-
L
e
a
rn
in
g
,
e
-
M
a
n
a
g
e
me
n
t
a
n
d
e
-
S
e
rv
ice
s
.
2
0
1
7
.
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
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
3
5
6
–
362
362
[1
3
]
.
Na
z
S
,
A
h
m
e
d
S
B,
A
h
m
a
d
R,
Ra
z
z
a
k
M
I.
―
A
ra
b
ic
S
c
rip
t
b
a
se
d
Dig
it
Re
c
o
g
n
i
ti
o
n
S
y
ste
m
s
‖
.
In
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Rec
e
n
t
A
d
v
a
n
c
e
s
i
n
Co
m
p
u
ter
S
y
ste
ms
(
RA
CS
)
2
0
1
6
;:
6
7
-
7
3
.
[1
4
]
.
S
leit,
A
.
T
.
,
Ja
b
a
y
,
R.
O.
―
A
C
h
a
in
Co
d
e
A
p
p
ro
a
c
h
f
o
r
Re
c
o
g
n
izin
g
Ba
sic
S
h
a
p
e
s
‖
.
In
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
Co
ll
e
g
e
Un
ive
rs
it
y
Of
J
o
r
d
a
n
,
A
mm
a
n
,
J
o
r
d
a
n
.
2
0
0
6
.
[1
5
]
.
M
u
talib
,
S
.
,
A
b
d
u
l
Ra
h
m
a
n
,
S
.
,
Yu
so
f
f
,
M
.
,
&
M
o
h
a
m
e
d
,
―
A
.
P
e
rso
n
a
li
ty
A
n
a
l
y
sis
Ba
se
d
On
L
e
tt
e
r
‗t‘
Us
in
g
Ba
c
k
P
r
o
p
a
g
a
ti
o
n
Ne
u
ra
l
Ne
tw
o
rk
‖
.
Pro
c
e
e
d
in
g
s
o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
a
n
d
In
fo
rm
a
t
ics
.
2
0
0
7
.
[1
6
]
.
Am
ro
u
c
h
M
,
Ra
b
i
M
.
―
De
e
p
N
e
u
ra
l
Ne
tw
o
rk
s
F
e
a
tu
re
s
f
o
r
A
r
a
b
ic
Ha
n
d
w
rit
in
g
Re
c
o
g
n
it
i
o
n
‖
.
In
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
S
e
rv
ice
s a
n
d
S
y
ste
ms
.
2
0
1
7
;:
1
3
8
-
1
4
9
.
[1
7
]
.
S
a
k
a
m
a
t
N,
Is
m
a
il
A
,
Kh
a
li
d
NE,
Zah
id
in
NA
,
L
a
ti
f
R
A
.
―
Co
rr
e
c
t
Latin
A
lp
h
a
b
e
t
F
o
rm
a
ti
o
n
A
ss
e
ss
m
e
n
t
u
sin
g
Ne
u
ro
n
V
a
l
u
e
s
‖
.
Co
n
tr
o
l
a
n
d
S
y
s
tem
Gr
a
d
u
a
te R
e
se
a
rc
h
Co
ll
o
q
u
i
u
m (
ICS
GRC)
,
2
0
1
6
;:
4
0
-
4
5
.
[1
8
]
.
N.,
Kh
a
li
d
,
N.
E
.
A
.
,
Ism
a
il
,
A
.
,
S
a
k
a
m
a
t,
N.,
&
Latif
,
R.
A
.
―
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
Us
in
g
P
e
a
rso
n
Co
rre
latio
n
o
n
Ne
u
ro
n
V
a
l
u
e
s
‖
.
In
Co
n
tro
l
a
n
d
S
y
ste
m Gra
d
u
a
te R
e
se
a
rc
h
Co
ll
o
q
u
i
u
m (
ICS
GRC)
,
2
0
1
6
;:
4
6
-
5
1
.
[1
9
]
.
Ba
i
H,
Zh
a
n
g
X
.
―
A
M
e
th
o
d
o
f
M
a
tch
in
g
S
tro
k
e
s
Ba
se
d
o
n
G
e
n
e
ti
c
A
lg
o
rit
h
m
‖
.
2
0
1
6
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
a
n
d
Ima
g
e
Pro
c
e
ss
in
g
(
ICS
IP)
.
2
0
1
6
[2
0
]
.
P
a
rk
,
J.
S
.
,
&
Oh
,
S
.
J.
―
A
Ne
w
Co
n
c
a
v
e
Hu
ll
A
lg
o
rit
h
m
a
n
d
Co
n
c
a
v
e
n
e
ss
M
e
a
su
re
f
o
r
N
-
Di
m
e
n
sio
n
a
l
Da
tas
e
ts
‖
.
J
o
u
rn
a
l
o
f
In
fo
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
.
2
0
1
2
;:
5
8
7
-
6
0
0
.
[2
1
]
.
G
o
n
z
a
lez
,
R.
C.
,
&
W
o
o
d
s,
R
.
E.
―
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
‖
.
2
n
d
Ed
it
i
o
n
.
Pre
n
ti
c
e
-
Ha
ll
.
2
0
0
2
.
[2
2
]
.
Ib
ra
h
e
m
,
W
.
N.
―
T
h
e
Hit
-
or
-
M
iss T
ra
n
s
f
o
rm
a
ti
o
n
‖
.
2
0
1
3
.
[2
3
]
.
Na
e
g
e
l,
B.
,
P
a
ss
a
t,
N.,
&
R
o
n
se
,
C.
―
G
re
y
-
lev
e
l
Hit
-
or
-
M
iss
T
ra
n
s
f
o
r
m
s
—
P
a
rt
I:
Un
if
ied
T
h
e
o
ry
‖
.
Pa
tt
e
rn
Rec
o
g
n
it
io
n
.
2
0
0
7
;:
6
3
5
-
6
4
7
.
[2
4
]
.
El
ra
ju
b
i
,
O.
M
.
,
El
-
F
e
g
h
i,
I.
,
S
a
g
h
a
y
e
r,
M
.
A
.
B.
―
Hit
-
or
-
M
iss
T
ra
n
sf
o
rm
a
s
a
T
o
o
l
f
o
r
S
im
il
a
r
S
h
a
p
e
De
tec
ti
o
n
‖
.
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
,
Co
n
tr
o
l,
Q
u
a
n
tu
m
a
n
d
I
n
fo
rm
a
ti
o
n
En
g
in
e
e
rin
g
.
2
0
1
4
.
[2
5
]
.
N.
Eff
o
rd
.
―
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
,
a
P
ra
c
ti
c
a
l
In
tro
d
u
c
ti
o
n
Us
in
g
Ja
v
a
‖
.
Pea
rs
o
n
Ed
u
c
a
t
io
n
L
i
mited
,
Ad
d
iso
n
W
e
sle
y
,
2
0
0
9
.
[2
6
]
.
V
V
ij
a
y
a
Ku
m
a
r,
A
S
rik
rish
n
a
,
B
Ra
v
e
e
n
d
ra
Ba
b
u
a
n
d
M
Ra
d
h
ik
a
M
a
n
i,
S
a
d
h
a
n
.
―
Clas
sif
ica
ti
o
n
a
n
d
Re
c
o
g
n
it
i
o
n
o
f
Ha
n
d
w
rit
ten
Dig
it
s b
y
Us
in
g
M
a
th
e
m
a
ti
c
a
l
M
o
rp
h
o
l
o
g
y
‖
.
2
0
1
0
;:
4
1
9
–
4
2
6
.
[2
7
]
.
Da
s,
P
.
,
Da
sg
u
p
ta,
T
.
,
Bh
a
tt
a
c
h
a
r
y
a
,
S
.
―
A
No
v
e
l
S
c
h
e
m
e
F
o
r
Be
n
g
a
li
Ha
n
d
w
rit
in
g
Re
c
o
g
n
it
io
n
Ba
se
d
O
n
M
o
rp
h
o
l
o
g
ica
l
Op
e
ra
ti
o
n
s
W
it
h
A
d
a
p
ti
v
e
A
u
to
-
G
e
n
e
ra
ted
S
tru
c
tu
ri
n
g
El
e
m
e
n
ts
‖
.
Co
n
tro
l,
I
n
stru
me
n
ta
ti
o
n
,
En
e
rg
y
&
Co
mm
u
n
ica
ti
o
n
(
CIEC)
.
2
0
1
6
;:
2
1
1
-
2
1
5
.
[2
8
]
.
Eu
g
e
n
e
J Kra
u
s,
Ed
w
a
rd
R
Do
u
g
h
e
rty
.
―
S
e
g
m
e
n
tatio
n
-
F
re
e
M
o
r
p
h
o
lo
g
ica
l
Ch
a
ra
c
ter Rec
o
g
n
it
io
n
‖
.
1
9
9
4
;:
1
4
–
23
[2
9
]
.
Y.
Do
h
,
J.
Kim
,
J.
Ki
m
,
S
.
Ki
m
,
M
.
A
la
m
.
―
Ne
w
M
o
rp
h
o
lo
g
ica
l
De
tec
ti
o
n
A
lg
o
rit
h
m
Ba
se
d
On
T
h
e
Hit
-
M
iss
T
ra
n
s
f
o
r
m
‖
.
Op
t.
En
g
.
2
0
0
2
;
:
2
6
–
31.
[3
0
]
.
D.
Zh
a
o
a
n
d
D.
G
.
Da
u
t,
―
M
o
r
p
h
o
l
o
g
ica
l
Hit
-
or
-
M
iss
T
ra
n
s
f
o
r
m
a
ti
o
n
f
o
r
s
h
a
p
e
re
c
o
g
n
it
i
o
n
‖
,
J.
Vi
su
a
l
Co
mm
u
n
.
Ima
g
e
Rep
re
se
n
t
.
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
2
3
0
--
2
4
3
,
S
e
p
t.
1
9
9
1
[3
1
]
.
W
e
n
,
C.
,
A
o
,
G
.
,
T
ian
,
Y.
―
A
th
in
n
i
n
g
m
e
th
o
d
f
o
r
f
in
g
e
rp
rin
t
im
a
g
e
b
a
se
d
o
n
Hit
-
M
iss
T
ra
n
sf
o
r
m
a
ti
o
n
‖
.
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
A
u
to
m
a
ti
o
n
E
n
g
in
e
e
rin
g
(
CS
AE
)
.
2
0
1
1
:
2
2
5
-
2
2
8
.
[3
2
]
.
Ev
a
n
s,
J.
D.
―
S
traig
h
t
F
o
rw
a
rd
S
tatist
ics
F
o
r
T
h
e
Be
h
a
v
io
ra
l
S
c
ien
c
e
s
‖
.
Pa
c
if
ic
Gr
o
v
e
,
C
A
:
Bro
o
k
s/Co
le
P
u
b
l
ish
i
n
g
.
1
9
9
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.