T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n Co
m
pu
t
i
ng
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
,
p
p
.
620
~
634
I
SS
N:
1
6
9
3
-
6
9
3
0
,
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
K
A
.
v
2
4
i
2
.
27502
620
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Identifica
tion o
f
p
a
leo
g
ra
phic curva
ture
using
s
k
el
et
o
niz
a
tion
a
nd key po
int
det
ection
F
a
dh
ila
t
ul F
it
riy
a
h
1
,
Dia
n Andria
na
2
,
M
uh
a
m
m
a
d
Z
ulh
a
j
Alia
ns
y
a
h
3
,
L
u
km
a
n H
a
k
i
m
1
,
M
uh
a
mm
a
d
F
a
is
ho
l A
m
rullo
h
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
E
n
g
i
n
e
e
r
i
n
g
,
F
a
c
u
l
t
y
o
f
En
g
i
n
e
e
r
i
n
g
,
U
n
i
v
e
r
si
t
a
s Yu
d
h
a
r
t
a
P
a
s
u
r
u
a
n
,
P
a
su
r
u
a
n
,
I
n
d
o
n
e
si
a
2
R
e
se
a
r
c
h
C
e
n
t
e
r
f
o
r
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
y
b
e
r
-
S
e
c
u
r
i
t
y
,
N
a
t
i
o
n
a
l
R
e
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
A
g
e
n
c
y
(
B
R
I
N
)
,
B
a
n
d
u
n
g
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
t
me
n
t
o
f
D
a
t
a
S
c
i
e
n
c
e
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s
P
e
mb
a
n
g
u
n
a
n
N
a
si
o
n
a
l
V
e
t
e
r
a
n
Jaw
a
T
i
mu
r
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
25
,
2025
R
ev
i
s
ed
Dec
27
,
2
0
2
5
A
cc
ep
ted
J
an
3
0
,
2
0
2
6
Ja
w
i
sc
rip
t
re
p
re
se
n
ts
a
v
it
a
l
c
o
m
p
o
n
e
n
t
o
f
th
e
Isla
m
ic
in
tellec
tu
a
l
h
e
rit
a
g
e
o
f
th
e
Nu
sa
n
tara
,
p
re
se
rv
e
d
a
c
ro
ss
n
u
m
e
ro
u
s
c
las
sic
a
l
m
a
n
u
sc
rip
ts.
A
p
rim
a
r
y
c
h
a
ll
e
n
g
e
in
d
ig
it
izin
g
t
h
e
se
d
o
c
u
m
e
n
ts
is
c
h
a
ra
c
ter
se
g
m
e
n
tatio
n
,
p
a
rti
c
u
larly
w
h
e
r
e
h
a
n
d
w
rit
ten
c
h
a
ra
c
t
e
rs
c
o
n
n
e
c
t
w
it
h
o
u
t
d
isti
n
c
t
b
o
u
n
d
a
ries
.
T
h
is
re
se
a
rc
h
p
ro
p
o
se
s
a
s
k
e
leto
n
iza
ti
o
n
-
b
a
se
d
se
g
m
e
n
tatio
n
m
e
th
o
d
to
a
d
d
re
ss
t
h
is
issu
e
,
u
t
il
i
z
in
g
a
d
a
tas
e
t
f
ro
m
1
7
p
a
g
e
s
o
f
th
e
“
Kitab
S
y
a
ir
P
e
ra
h
u
”
m
a
n
u
sc
rip
t
c
o
n
tai
n
in
g
2
6
9
tes
t
c
h
a
ra
c
ters
.
T
h
e
p
re
-
p
ro
c
e
ss
in
g
s
tag
e
in
v
o
lv
e
s
g
ra
y
s
c
a
le
c
o
n
v
e
rsio
n
,
b
in
a
riza
ti
o
n
,
a
n
d
n
o
ise
re
m
o
v
a
l
th
r
o
u
g
h
c
o
n
n
e
c
ted
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(CCA
).
T
h
e
se
g
m
e
n
tatio
n
p
r
o
c
e
ss
th
e
n
in
teg
ra
tes
sk
e
leto
n
stru
c
tu
re
s,
c
e
n
tro
i
d
p
o
siti
o
n
i
n
g
,
i
n
ters
e
c
ti
o
n
p
o
in
ts,
a
n
d
lo
o
p
d
e
tec
ti
o
n
.
Ev
a
lu
a
ti
o
n
re
su
lt
s
sh
o
w
th
e
s
y
ste
m
su
c
c
e
ss
f
u
ll
y
id
e
n
ti
f
ied
1
8
7
o
u
t
o
f
2
6
9
c
h
a
ra
c
ters
,
a
c
h
iev
in
g
a
n
a
c
c
u
ra
c
y
o
f
0
.
8
0
1
,
a
p
r
e
c
isio
n
o
f
0
.
8
9
5
,
a
re
c
a
ll
o
f
8
6
.
3
8
%
,
a
n
d
a
n
F
1
-
sc
o
re
o
f
8
8
.
9
1
%
.
W
h
il
e
t
h
e
se
re
su
lt
s
d
e
m
o
n
stra
te
th
e
m
e
th
o
d
’
s
e
ff
e
c
ti
v
e
n
e
ss
,
th
e
sm
a
ll
d
a
tas
e
t
f
ro
m
a
sin
g
le
m
a
n
u
sc
rip
t
li
m
it
s
it
s
g
e
n
e
ra
li
z
a
b
il
it
y
.
Ne
v
e
rth
e
les
s,
th
is
st
u
d
y
e
sta
b
li
sh
e
s
a
f
o
u
n
d
a
ti
o
n
a
l
ste
p
to
w
a
rd
a
n
a
u
t
o
m
a
ted
Ja
w
i
i
m
a
g
e
-
p
ro
c
e
ss
in
g
s
y
ste
m
a
n
d
th
e
d
ig
it
a
l
p
re
se
rv
a
ti
o
n
o
f
Isla
m
i
c
Nu
sa
n
tara
li
tera
c
y
,
c
o
n
tri
b
u
ti
n
g
a
tailo
re
d
sk
e
leto
n
iza
ti
o
n
-
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
Ja
w
i
sc
rip
t.
K
ey
w
o
r
d
s
:
Ak
s
ar
a
J
a
w
i
C
o
n
n
ec
ted
co
m
p
o
n
en
t
Ke
y
p
o
in
ts
Ma
n
u
s
cr
ip
t
P
aleo
g
r
ap
h
y
Seg
m
en
tatio
n
Sk
eleto
n
izatio
n
T
h
is i
s
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
:
Mu
h
a
m
m
ad
Fai
s
h
o
l
Am
r
u
l
lo
h
Dep
ar
t
m
en
t o
f
I
n
f
o
r
m
atic
s
E
n
g
in
ee
r
i
n
g
,
Facu
lt
y
o
f
E
n
g
i
n
ee
r
in
g
,
U
n
i
v
er
s
ita
s
Yu
d
h
ar
ta
P
asu
r
u
a
n
J
l.
Yu
d
h
ar
ta
No
.
7
,
Kem
b
a
n
g
K
u
n
in
g
,
Se
n
g
o
n
ag
u
n
g
,
P
u
r
w
o
s
ar
i,
P
asu
r
u
a
n
,
E
ast J
av
a
6
7
1
6
2
,
I
n
d
o
n
esia
E
m
ail:
f
ais
h
o
l
@
y
u
d
h
ar
ta.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
u
r
ats
Nu
s
a
n
tar
a
r
ef
er
s
to
t
h
e
I
s
la
m
ic
i
n
tellect
u
al
h
er
ita
g
e
p
r
eser
v
ed
in
m
a
n
u
s
cr
ip
ts
w
r
itte
n
i
n
ad
ap
ted
A
r
ab
ic
s
cr
ip
ts
,
n
o
tab
l
y
P
eg
o
n
an
d
J
a
w
i
[
1
]
,
[
2
]
.
E
t
y
m
o
lo
g
icall
y
,
tu
r
at
s
(
f
r
o
m
th
e
r
o
o
t
w
a
-
ra
-
t
s
a)
d
en
o
tes
in
h
er
ited
k
n
o
w
led
g
e
tr
an
s
m
itted
ac
r
o
s
s
g
e
n
er
ati
o
n
s
[
3
]
.
B
ey
o
n
d
m
er
e
ad
o
p
tio
n
,
J
a
w
i
s
cr
ip
t
r
ep
r
esen
ts
a
s
o
p
h
is
ticated
p
h
o
n
o
lo
g
ical
ad
j
u
s
t
m
e
n
t
o
f
A
r
a
b
ic
letter
f
o
r
m
s
to
s
u
it
r
eg
io
n
al
lan
g
u
ag
e
s
w
h
il
e
m
ai
n
tai
n
in
g
co
m
p
le
x
cu
r
s
iv
e
ch
ar
ac
ter
is
tic
s
[
4
]
-
[
7
]
.
Desp
ite
its
h
is
to
r
ical
s
i
g
n
i
f
ica
n
ce
,
th
e
d
ig
italizatio
n
o
f
J
a
w
i
m
an
u
s
cr
ip
t
s
r
e
m
ai
n
s
c
h
alle
n
g
in
g
[
8
]
.
A
m
aj
o
r
h
u
r
d
le
lies
in
ch
ar
ac
ter
s
eg
m
en
ta
tio
n
w
it
h
i
n
o
p
tical
ch
ar
ac
ter
r
ec
o
g
n
itio
n
(
OC
R
)
p
ip
elin
es,
as
J
a
w
i
i
s
in
h
er
e
n
tl
y
c
u
r
s
i
v
e
an
d
co
n
tex
t
-
s
e
n
s
iti
v
e
[
9
]
,
[
1
0
]
.
Un
lik
e
L
atin
tex
t,
J
a
w
i
ch
ar
ac
ter
s
ch
a
n
g
e
s
h
ap
e
b
ased
o
n
th
eir
p
o
s
itio
n
in
itial,
m
ed
ial,
o
r
f
in
a
l
an
d
co
n
n
ec
t
th
r
o
u
g
h
s
h
ar
ed
s
tr
o
k
es,
o
f
te
n
lac
k
i
n
g
cle
ar
b
o
u
n
d
ar
ies
[
1
1
]
-
[
1
3
]
.
T
h
ese
tr
aits
,
co
u
p
led
with
n
o
n
-
u
n
if
o
r
m
d
iacr
itics
,
h
a
n
d
w
r
i
tin
g
v
ar
iab
ilit
y
,
a
n
d
t
h
e
s
ca
r
cit
y
o
f
J
a
w
i
-
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f p
a
le
o
g
r
a
p
h
ic
cu
r
va
tu
r
e
u
s
in
g
s
ke
leto
n
iz
a
tio
n
a
n
d
ke
y
p
o
in
t d
etec
tio
n
(
F
a
d
h
ila
tu
l F
itr
iya
h
)
621
s
p
ec
if
ic
d
atase
ts
,
m
ak
e
s
eg
m
en
tatio
n
a
co
m
p
lex
y
et
v
ital
t
ask
f
o
r
th
e
d
i
g
ital
p
r
eser
v
at
io
n
o
f
Ma
la
y
-
I
s
la
m
i
c
m
an
u
s
cr
ip
ts
[
1
4
]
-
[
2
0
]
.
P
r
ev
io
u
s
s
e
g
m
en
ta
tio
n
s
tu
d
ie
s
h
a
v
e
p
r
i
m
ar
il
y
f
o
cu
s
ed
o
n
A
r
ab
ic
s
cr
ip
t.
Sea
m
ca
r
v
in
g
ap
p
r
o
ac
h
es
ca
n
h
an
d
le
to
u
c
h
i
n
g
ch
ar
ac
ter
s
b
u
t
ar
e
h
ig
h
l
y
s
en
s
iti
v
e
to
n
o
is
e
an
d
im
a
g
e
q
u
alit
y
[
2
1
]
.
Mo
r
p
h
o
lo
g
ical
an
d
co
n
n
ec
ted
co
m
p
o
n
e
n
t
-
b
ased
m
e
th
o
d
s
p
er
f
o
r
m
w
ell
o
n
s
tr
u
ctu
r
ed
tex
t
b
u
t
s
tr
u
g
g
l
e
w
it
h
h
a
n
d
w
r
itte
n
d
o
cu
m
en
ts
d
u
e
to
t
h
eir
co
m
p
l
ex
it
y
a
n
d
in
p
u
t
d
ep
en
d
en
c
y
[
2
2
]
.
Hy
b
r
id
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
co
m
b
in
in
g
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
(
C
NNs
)
w
it
h
t
h
i
n
n
i
n
g
o
r
s
eg
m
en
tatio
n
h
y
p
o
t
h
esi
s
g
r
ap
h
s
ac
h
ie
v
e
h
i
g
h
ac
cu
r
ac
y
b
u
t
r
eq
u
ir
e
lar
g
e
a
n
n
o
tated
d
atasets
a
n
d
in
v
o
l
v
e
s
ig
n
if
ica
n
t
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
[
2
3
]
.
A
s
u
m
m
ar
y
o
f
r
ep
r
ese
n
tati
v
e
s
e
g
m
e
n
tat
io
n
an
d
r
ec
o
g
n
itio
n
ap
p
r
o
ac
h
es,
th
eir
d
at
asets
,
s
tr
e
n
g
t
h
s
,
li
m
itatio
n
s
,
an
d
r
elev
an
ce
to
J
a
w
i scr
ip
t is
p
r
esen
ted
in
T
ab
le
1
.
R
esear
ch
ex
p
lici
tl
y
tar
g
et
in
g
J
a
w
i
s
cr
ip
t
r
e
m
ai
n
s
li
m
ited
.
E
x
is
ti
n
g
w
o
r
k
s
lar
g
el
y
f
o
c
u
s
o
n
is
o
lated
ch
ar
ac
ter
r
ec
o
g
n
i
tio
n
u
s
i
n
g
Fre
e
m
a
n
ch
a
in
co
d
e
co
m
b
i
n
ed
w
it
h
r
u
le
-
b
ased
class
if
ier
s
o
r
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
s
(
SVMs)
,
r
ep
o
r
tin
g
h
ig
h
ac
c
u
r
ac
y
u
n
d
er
co
n
tr
o
lled
co
n
d
itio
n
s
[
2
4
]
,
[
2
5
]
.
H
o
w
ev
er
,
t
h
es
e
a
p
p
r
o
a
ch
es
d
o
n
o
t
a
d
d
r
e
s
s
th
e
s
eg
m
en
t
a
ti
o
n
o
f
c
o
n
n
ec
t
e
d
h
an
d
w
r
i
tt
en
ch
ar
a
c
t
e
r
s
i
n
a
u
th
en
t
i
c
m
an
u
s
c
r
i
p
t
s
e
t
tin
g
s
.
T
ab
le
1
.
R
elate
d
r
esear
ch
R
e
f
e
r
e
n
c
e
M
e
t
h
o
d
D
a
t
a
se
t
S
t
r
e
n
g
t
h
s
L
i
mi
t
a
t
i
o
n
s
R
e
l
e
v
a
n
c
e
t
o
J
a
w
i
[
2
1
]
S
e
a
m c
a
r
v
i
n
g
I
s
l
a
mi
c
E
d
u
c
a
t
i
o
n
a
l
,
S
c
i
e
n
t
i
f
i
c
a
n
d
C
u
l
t
u
r
a
l
O
r
g
a
n
i
z
a
t
i
o
n
–
A
r
a
b
i
c
D
a
t
a
b
a
se
(
I
ES
K
-
A
r
D
B
,
I
n
st
i
t
u
t
f
ü
r
N
a
c
h
r
i
c
h
t
e
n
t
e
c
h
n
i
k
/
É
c
o
l
e
N
a
t
i
o
n
a
l
e
d
’
I
n
g
é
n
i
e
u
r
s d
e
T
u
n
i
s (A
r
a
b
i
c
H
a
n
d
w
r
i
t
t
e
n
W
o
r
d
D
a
t
a
b
a
se
)
(
I
F
N
/
EN
I
T
)
H
a
n
d
l
e
s
t
o
u
c
h
i
n
g
c
h
a
r
a
c
t
e
r
s
N
o
i
se
-
se
n
si
t
i
v
e
;
e
n
e
r
g
y
-
d
e
p
e
n
d
e
n
t
A
r
a
b
i
c
-
o
n
l
y
[
2
2
]
M
o
r
p
h
o
l
o
g
i
c
a
l
+
C
C
a
n
a
l
y
si
s
A
r
a
b
i
c
h
a
n
d
w
r
i
t
t
e
n
d
o
c
s
Ef
f
e
c
t
i
v
e
f
o
r
st
r
u
c
t
u
r
e
d
t
e
x
t
Q
u
a
l
i
t
y
-
se
n
si
t
i
v
e
;
mu
l
t
i
-
s
t
a
g
e
A
r
a
b
i
c
-
o
n
l
y
[
2
3
]
C
N
N
+
S
H
G
+
t
h
i
n
n
i
n
g
A
r
a
b
i
c
h
a
n
d
w
r
i
t
t
e
n
H
i
g
h
a
c
c
u
r
a
c
y
;
c
o
n
f
i
d
e
n
c
e
-
b
a
se
d
C
o
mp
l
e
x
;
d
a
t
a
-
d
e
p
e
n
d
e
n
t
A
r
a
b
i
c
-
o
n
l
y
[
2
4
]
F
C
C
+
r
e
g
u
l
a
r
e
x
p
r
e
ssi
o
n
+
D
e
c
i
si
o
n
t
r
e
e
I
so
l
a
t
e
d
Jaw
i
(
l
i
v
e
w
r
i
t
i
n
g
,
1
0
u
se
r
s)
)
R
e
a
l
-
t
i
me
;
r
e
l
i
a
b
l
e
(
=
0
.
8
3
9
)
I
so
l
a
t
e
d
o
n
l
y
;
A
n
d
r
o
i
d
-
o
n
l
y
Jaw
i
-
sp
e
c
i
f
i
c
(
i
so
l
a
t
e
d
)
[
2
5
]
F
C
C
+
S
V
M
+
d
e
c
i
si
o
n
r
u
l
e
s
I
so
l
a
t
e
d
h
a
n
d
w
r
i
t
t
e
n
J
a
w
i
H
i
g
h
a
c
c
u
r
a
c
y
(
9
2
.
8
6
%)
S
i
mi
l
a
r
-
sh
a
p
e
c
o
n
f
u
s
i
o
n
Jaw
i
-
sp
e
c
i
f
i
c
(
i
so
l
a
t
e
d
)
T
h
i
s
w
o
r
k
S
k
e
l
e
t
o
n
i
z
a
t
i
o
n
+
k
e
y
p
o
i
n
t
d
e
t
e
c
t
i
o
n
Jaw
i
man
u
scr
i
p
t
“
S
y
a
i
r
P
e
r
a
h
u
”
L
i
g
h
t
w
e
i
g
h
t
;
i
n
t
e
r
p
r
e
t
a
b
l
e
;
r
o
b
u
st
Er
r
o
r
s o
n
c
o
mp
l
e
x
l
i
g
a
t
u
r
e
s
Jaw
i
man
u
scr
i
p
t
Ho
w
e
v
er
,
m
o
s
t
o
f
th
ese
s
t
u
d
ies
r
e
m
ain
li
m
ited
to
th
e
s
tan
d
ar
d
A
r
ab
ic
s
cr
ip
t
an
d
h
av
e
n
o
t
b
ee
n
s
p
ec
if
icall
y
ap
p
lied
to
J
aw
i,
w
h
ic
h
ex
h
ib
its
d
is
ti
n
ct
s
tr
u
c
tu
r
al
co
m
p
lex
ities
an
d
ch
ar
ac
ter
v
ar
iatio
n
s
.
On
e
o
f
p
r
im
ar
y
ch
a
llen
g
e
s
in
J
a
w
i
s
cr
ip
t
s
eg
m
en
ta
tio
n
i
s
t
h
e
p
r
o
ce
s
s
o
f
s
eg
m
e
n
ts
o
f
co
n
n
ec
te
d
ch
ar
ac
ter
s
,
w
h
o
s
e
lig
at
u
r
e
s
tr
u
ctu
r
e
s
ar
e
o
f
ten
ir
r
eg
u
lar
a
n
d
h
i
g
h
l
y
v
ar
iab
le.
T
h
er
ef
o
r
e,
th
er
e
is
a
n
ee
d
f
o
r
a
n
ap
p
r
o
ac
h
ca
p
ab
le
o
f
ac
cu
r
atel
y
id
en
ti
f
y
in
g
c
h
ar
ac
ter
b
o
u
n
d
ar
ies ev
e
n
u
n
d
er
co
m
p
lex
co
n
n
ec
tio
n
p
atter
n
s
.
C
o
m
p
ar
ed
w
ith
ex
i
s
ti
n
g
ap
p
r
o
ac
h
es,
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
f
f
er
s
a
li
g
h
t
w
ei
g
h
t
a
n
d
i
n
t
er
p
r
etab
le
alter
n
ati
v
e
f
o
r
J
a
w
i
c
h
ar
ac
ter
s
eg
m
e
n
tatio
n
.
Mo
r
p
h
o
lo
g
y
-
b
ased
m
et
h
o
d
s
p
er
f
o
r
m
w
ell
o
n
p
r
in
ted
te
x
t
b
u
t
s
tr
u
g
g
le
w
it
h
ir
r
e
g
u
lar
h
an
d
w
r
itte
n
li
g
atu
r
e
s
[
2
2
]
,
w
h
ile
s
ea
m
ca
r
v
i
n
g
ap
p
r
o
ac
h
es
ar
e
h
ig
h
l
y
s
e
n
s
iti
v
e
to
n
o
is
e
an
d
i
m
a
g
e
d
eg
r
ad
atio
n
[
2
1
]
.
C
NN
-
b
ased
m
et
h
o
d
s
r
eq
u
ir
e
lar
g
e
an
n
o
tated
d
atasets
an
d
p
r
o
v
id
e
lim
ited
in
ter
p
r
etab
ilit
y
,
w
h
ic
h
is
i
m
p
r
ac
tical
f
o
r
J
a
w
i
m
an
u
s
cr
ip
ts
[
2
3
]
,
[
2
6
]
.
I
n
co
n
tr
ast,
t
h
is
s
t
u
d
y
e
m
p
lo
y
s
s
k
eleto
n
izatio
n
an
d
k
e
y
p
o
i
n
t
d
etec
tio
n
u
s
i
n
g
i
n
ter
s
ec
tio
n
,
lo
o
p
,
an
d
ce
n
tr
o
id
cu
es
to
r
o
b
u
s
tl
y
s
e
g
m
e
n
t
ch
ar
ac
ter
s
in
s
m
a
ll a
n
d
n
o
i
s
y
m
an
u
s
cr
ip
t d
atasets
.
T
h
er
ef
o
r
e,
an
alter
n
ati
v
e
s
eg
m
en
tatio
n
s
tr
ate
g
y
is
r
eq
u
ir
e
d
th
at
i
s
li
g
h
t
w
eig
h
t,
i
n
ter
p
r
etab
le,
an
d
ef
f
ec
tiv
e
o
n
s
m
all,
n
o
is
y
d
at
asets
.
T
h
is
s
t
u
d
y
p
r
o
p
o
s
es
a
s
k
eleto
n
izatio
n
-
b
ased
s
e
g
m
en
tatio
n
m
e
th
o
d
th
at
in
te
g
r
ates
co
n
n
ec
ted
co
m
p
o
n
en
t
an
al
y
s
is
(
C
C
A
)
w
it
h
k
e
y
p
o
in
t
d
etec
tio
n
,
in
cl
u
d
in
g
ce
n
tr
o
id
s
,
in
ter
s
ec
t
io
n
p
o
in
ts
,
an
d
lo
o
p
s
,
to
id
en
tify
c
h
ar
ac
ter
b
o
u
n
d
ar
ies
w
it
h
i
n
co
m
p
lex
li
g
at
u
r
es.
B
e
y
o
n
d
i
m
p
r
o
v
in
g
s
e
g
m
en
ta
tio
n
ac
cu
r
ac
y
,
t
h
e
m
et
h
o
d
e
m
p
h
a
s
i
ze
s
p
alae
o
g
r
ap
h
ic
c
u
r
v
at
u
r
e
c
h
ar
ac
ter
is
tic
s
o
f
J
a
w
i
s
cr
ip
t
as
s
tr
u
ct
u
r
al
c
u
es
f
o
r
ch
ar
ac
ter
is
o
latio
n
,
s
u
p
p
o
r
tin
g
m
an
u
s
cr
ip
t r
etr
iev
a
l a
n
d
d
ig
it
al
p
r
eser
v
atio
n
o
f
I
s
la
m
ic
N
u
s
an
tar
a
h
er
ita
g
e.
2.
M
E
T
H
O
D
I
n
th
i
s
r
esear
ch
,
a
J
a
w
i
s
cr
ip
t
letter
s
eg
m
e
n
tatio
n
m
et
h
o
d
is
p
r
o
p
o
s
ed
th
at
in
te
g
r
ated
s
k
ele
to
n
izatio
n
tech
n
iq
u
e
to
ex
tr
ac
t
th
e
b
asic
s
tr
u
ctu
r
e
o
f
ch
ar
ac
ter
s
tr
o
k
es
C
C
A
to
id
en
tif
ied
co
n
n
ec
ted
ar
ea
in
an
im
a
g
e,
an
d
b
o
u
n
d
in
g
b
o
x
as
th
e
s
p
ati
al
b
o
u
n
d
ar
ies
o
f
ea
ch
co
m
p
o
n
en
t
an
al
y
s
ed
[
2
7
]
.
T
h
i
s
r
es
e
a
r
c
h
is
co
m
p
o
s
ed
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
6
2
0
-
634
622
s
ev
e
r
a
l
m
ai
n
s
te
p
s
,
in
cl
u
d
e
p
r
e
-
p
r
o
c
e
s
s
in
g
,
s
k
e
l
e
t
o
n
i
za
t
i
o
n
,
CCA
,
b
o
u
n
d
in
g
b
o
x
d
ef
in
i
t
i
o
n
,
an
d
c
h
a
r
a
c
t
e
r
s
eg
m
en
t
a
ti
o
n
b
a
s
e
d
o
n
th
e
k
ey
p
o
i
n
ts
i
d
en
t
if
ic
a
t
i
o
n
.
T
h
e
o
v
er
all
f
lo
w
o
f
t
h
e
c
h
ar
ac
ter
s
eg
m
en
tatio
n
p
r
o
ce
s
s
i
n
th
is
r
esear
c
h
is
r
ep
r
esen
ted
i
n
Fig
u
r
e
1
.
Fig
u
r
e
1
.
Flo
w
o
f
r
esear
c
h
2
.
1
.
Da
t
a
s
et
T
h
e
d
ataset
co
n
s
i
s
ts
o
f
s
ca
n
n
e
d
p
ag
es
o
f
th
e
“
Kitab
S
y
air
P
er
ah
u
”
m
a
n
u
s
c
r
ip
t
w
r
itte
n
i
n
J
a
w
i
s
cr
ip
t
[
2
8
]
.
T
h
e
s
ca
n
n
in
g
p
r
o
ce
s
s
w
as
co
n
d
u
cted
b
y
th
e
R
esear
ch
C
e
n
ter
f
o
r
A
r
ti
f
icia
l
I
n
telli
g
en
ce
a
n
d
C
y
b
er
s
ec
u
r
it
y
,
Natio
n
al
R
ese
ar
ch
an
d
I
n
n
o
v
atio
n
Ag
e
n
c
y
(
B
R
I
N)
.
T
h
e
m
an
u
s
cr
ip
t
co
m
p
r
is
es
1
7
p
ag
es
in
P
NG
f
o
r
m
at.
Gr
o
u
n
d
tr
u
t
h
la
b
elin
g
w
a
s
p
er
f
o
r
m
ed
in
d
ep
e
n
d
en
tl
y
b
y
f
o
u
r
s
a
n
tr
i
p
r
o
f
ici
en
t
in
J
a
w
i
r
ea
d
in
g
.
Dis
ag
r
ee
m
e
n
ts
a
m
o
n
g
an
n
o
ta
tio
n
s
w
er
e
r
eso
lv
ed
th
r
o
u
g
h
co
n
s
en
s
u
s
d
is
c
u
s
s
io
n
s
f
ac
ilit
a
ted
b
y
th
e
T
u
r
ats
Div
i
s
io
n
o
f
U
n
i
v
er
s
ita
s
Yu
d
h
ar
ta
P
asu
r
u
an
,
w
h
ic
h
also
co
n
d
u
cted
f
i
n
al
v
alid
atio
n
.
T
h
is
p
r
o
ce
s
s
en
s
u
r
ed
b
o
th
tech
n
ical
ac
cu
r
ac
y
a
n
d
co
n
s
is
t
en
c
y
w
i
th
t
u
r
ats
s
ch
o
lar
s
h
ip
.
A
s
a
m
p
le
li
n
e
i
m
ag
e
i
s
s
h
o
w
n
in
Fi
g
u
r
e
2
.
Fig
u
r
e
2
.
L
in
e
e
x
ce
r
p
t f
r
o
m
“
Kitab
S
y
air
P
er
ah
u
”
p
ag
e
0
4
li
n
e
1
5
2
.
2
.
P
re
-
p
ro
ce
s
s
ing
P
r
e
-
p
r
o
ce
s
s
in
g
b
eg
i
n
s
w
it
h
R
GB
-
to
-
g
r
a
y
s
ca
le
co
n
v
er
s
io
n
t
o
r
ed
u
ce
i
m
a
g
e
co
m
p
lex
i
t
y
,
f
o
llo
w
ed
b
y
b
in
ar
izatio
n
u
s
i
n
g
Ots
u
’
s
t
h
r
es
h
o
ld
in
g
m
et
h
o
d
[
2
9
]
-
[
3
3
]
.
Ots
u
’
s
m
eth
o
d
au
to
m
atica
ll
y
d
ete
r
m
in
e
s
t
h
e
o
p
ti
m
al
th
r
es
h
o
ld
b
y
m
a
x
i
m
izin
g
b
et
w
ee
n
-
clas
s
v
ar
ia
n
ce
,
en
ab
lin
g
clea
r
s
ep
ar
atio
n
b
et
w
ee
n
f
o
r
eg
r
o
u
n
d
tex
t
a
n
d
b
ac
k
g
r
o
u
n
d
.
T
h
e
b
in
ar
izatio
n
p
r
o
ce
s
s
is
d
ef
in
ed
as
:
(
,
)
=
{
1
(
ℎ
)
,
(
,
)
≥
0
(
)
,
(
,
)
<
(
1
)
(
,
)
is
b
in
ar
izatio
n
r
es
u
lt
at
p
ix
e
l
co
o
r
d
in
ates
(
,
)
,
(
,
)
in
ten
s
it
y
v
al
u
e
at
th
e
p
ix
el
p
o
s
itio
n
(
,
)
i
n
th
e
g
r
a
y
s
ca
le
i
m
a
g
e,
an
d
is
th
e
th
r
esh
o
ld
co
m
p
u
ted
u
s
in
g
Ot
s
u
’
s
cr
iter
io
n
.
2
.
3
.
CCA
Af
ter
b
in
ar
izatio
n
,
C
C
A
is
ap
p
lied
to
r
em
o
v
e
n
o
is
e
an
d
id
en
ti
f
y
r
elev
a
n
t
ch
ar
ac
ter
co
m
p
o
n
en
t
s
b
ased
o
n
8
-
n
ei
g
h
b
o
r
h
o
o
d
co
n
n
ec
ti
v
it
y
.
C
o
m
p
o
n
e
n
t
s
ar
e
class
i
f
ied
ac
co
r
d
in
g
to
ar
ea
th
r
es
h
o
ld
s
:
co
m
p
o
n
e
n
t
s
lar
g
er
th
a
n
5
0
p
ix
els
ar
e
co
n
s
i
d
er
ed
m
ai
n
s
tr
o
k
e
s
,
w
h
ile
co
m
p
o
n
en
ts
b
et
w
ee
n
5
an
d
5
0
p
ix
els
ar
e
r
etai
n
ed
as
p
o
ten
tial
d
iacr
itics
if
lo
ca
ted
n
ea
r
th
e
m
ai
n
s
tr
o
k
e.
S
m
aller
o
r
d
is
tan
t
co
m
p
o
n
e
n
ts
ar
e
d
is
ca
r
d
ed
as
n
o
is
e.
T
h
is
f
ilter
i
n
g
s
tep
p
r
eser
v
e
s
ess
e
n
ti
al
ch
ar
ac
ter
s
tr
u
ctu
r
e
s
f
o
r
f
u
r
t
h
er
an
al
y
s
is
.
T
h
e
co
m
p
o
n
e
n
t
l
ab
elin
g
r
u
le
ca
n
b
e
ex
p
r
ess
ed
as
i
n
(
2
)
.
=
{
,
≤
,
≥
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f p
a
le
o
g
r
a
p
h
ic
cu
r
va
tu
r
e
u
s
in
g
s
ke
leto
n
iz
a
tio
n
a
n
d
ke
y
p
o
in
t d
etec
tio
n
(
F
a
d
h
ila
tu
l F
itr
iya
h
)
623
is
th
e
lab
el
ca
te
g
o
r
y
f
o
r
co
m
p
o
n
en
t
,
r
ep
r
esen
ts
t
h
e
co
m
p
o
n
en
t
ar
ea
,
is
th
e
ar
ea
th
r
es
h
o
ld
,
e.
g
.
50
.
A
co
m
p
o
n
e
n
t
is
co
n
s
id
er
ed
a
m
ain
s
tr
o
k
e
if
it
is
a
s
s
u
m
ed
to
b
e
p
ar
t
o
f
th
e
ch
ar
ac
ter
,
w
h
i
le
d
iacr
itics
r
ef
er
to
s
m
al
l c
o
m
p
o
n
en
t
s
s
u
c
h
as d
o
ts
o
r
h
ar
ak
at.
2
.
4
.
B
o
un
din
g
b
ox
I
n
th
i
s
s
tep
,
th
e
s
y
s
te
m
id
en
t
i
f
ied
ch
ar
ac
ter
co
m
p
o
n
en
ts
u
s
i
n
g
b
o
u
n
d
in
g
b
o
x
an
al
y
s
i
s
d
er
iv
ed
f
r
o
m
th
e
C
C
A
r
es
u
lts
,
w
h
ic
h
is
u
s
ed
to
d
eter
m
in
e
th
e
b
o
u
n
d
ar
i
es
o
f
ea
c
h
o
b
j
ec
t
in
th
e
i
m
a
g
e
[
3
4
]
,
[
3
5
]
.
L
ar
g
e
co
m
p
o
n
e
n
t
s
o
r
th
o
s
e
w
it
h
a
v
er
tical
asp
ec
t
r
atio
ar
e
ass
u
m
e
d
to
b
e
m
ain
s
tr
o
k
es,
w
h
ile
s
m
aller
co
m
p
o
n
e
n
t
s
th
at
d
o
n
o
t
m
ee
t t
h
ese
cr
iter
ia
ar
e
co
n
s
id
e
r
ed
as d
iacr
itic c
an
d
id
ates
[
3
6
]
.
T
o
ass
o
ciate
d
iacr
itics
w
ith
th
eir
co
r
r
esp
o
n
d
in
g
m
ai
n
ch
ar
ac
ter
s
,
th
e
E
u
clid
ea
n
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
ce
n
tr
o
id
o
f
a
s
m
al
l
co
m
p
o
n
e
n
t
an
d
t
h
e
ce
n
tr
o
id
o
f
th
e
n
e
ar
est
m
ain
s
tr
o
k
e
is
ca
lcu
late
d
.
T
h
e
d
is
tan
ce
is
d
ef
in
ed
as
i
n
(
3
)
:
=
√
(
−
)
2
+
(
−
)
2
(
3
)
is
t
h
e
E
u
c
li
d
e
an
d
i
s
t
an
ce
b
e
tw
ee
n
d
ia
c
r
i
ti
c
c
o
m
p
o
n
en
t
an
d
m
a
in
s
t
r
o
k
e
,
(
,
)
a
r
e
t
h
e
c
en
t
r
o
id
c
o
o
r
d
i
n
a
t
es
o
f
d
i
ac
r
i
t
ic
c
o
m
p
o
n
en
t
,
an
d
(
,
)
a
r
e
t
h
e
c
en
t
r
o
i
d
c
o
o
r
d
i
n
a
t
es
o
f
m
ai
n
s
t
r
o
k
e
c
o
m
p
o
n
e
n
t
.
A
s
m
a
l
l
c
o
m
p
o
n
en
t
is
a
s
s
o
c
ia
t
e
d
w
i
th
a
m
a
in
s
t
r
o
k
e
as
a
d
ia
c
r
it
i
c
if
i
ts
c
en
t
r
o
i
d
l
i
es
w
ith
in
6
0
p
i
x
el
s
o
f
t
h
e
m
a
in
s
t
r
o
k
e
’
s
c
en
t
r
o
i
d
.
Fu
r
th
e
r
m
o
r
e
,
t
h
e
v
e
r
t
i
c
al
p
o
s
i
t
i
o
n
o
f
th
e
d
i
ac
r
i
t
i
c
c
en
t
r
o
i
d
r
e
l
at
iv
e
t
o
t
h
e
m
a
i
n
s
t
r
o
k
e
c
e
n
t
r
o
i
d
i
s
u
s
e
d
t
o
d
e
t
e
r
m
in
e
w
h
e
th
e
r
i
t
i
s
l
o
c
at
e
d
a
b
o
v
e
o
r
b
e
l
o
w
m
a
in
s
t
r
o
k
e
[
3
7
]
.
T
h
is
class
i
f
icatio
n
ca
n
b
e
as i
n
(
4
)
:
=
{
A
b
ove
<
B
e
l
ow
>
(
4
)
is
t
h
e
lab
el
ca
te
g
o
r
y
f
o
r
co
m
p
o
n
en
t
,
is
t
h
e
v
er
tical
co
o
r
d
in
ate
o
f
th
e
d
iacr
itic
ce
n
tr
o
id
,
is
th
e
v
er
tical
co
o
r
d
in
ate
o
f
th
e
m
ai
n
s
tr
o
k
e
ce
n
tr
o
id
.
I
f
(
<
)
,
th
e
d
iacr
itic
is
lo
ca
ted
ab
o
v
e
th
e
m
ai
n
s
tr
o
k
e,
an
d
(
>
)
,
th
e
d
iacr
itic
is
lo
ca
ted
b
elo
w
th
e
m
ai
n
s
tr
o
k
e.
I
t
is
i
m
p
o
r
tan
t
to
n
o
te
th
at
i
n
th
e
d
ig
ital
i
m
a
g
e
co
o
r
d
in
ate
s
y
s
te
m
,
th
e
o
r
ig
in
p
o
in
t
(
0
,
0
)
is
lo
ca
ted
a
t
th
e
to
p
-
lef
t
co
r
n
er
,
s
o
s
m
alle
r
v
alu
e
s
in
d
icate
h
ig
h
er
p
o
s
itio
n
s
i
n
t
h
e
i
m
ag
e.
T
h
is
m
a
k
es
ce
n
tr
o
id
co
m
p
ar
is
o
n
a
r
eliab
le
m
et
h
o
d
f
o
r
d
is
ti
n
g
u
i
s
h
in
g
d
iacr
itic
s
pos
itio
n
ed
ab
o
v
e
o
r
b
elo
w
th
e
m
ain
s
tr
o
k
e.
2
.
5
.
Sk
elet
o
niza
t
io
n
Sk
eleto
n
izatio
n
i
s
ap
p
lied
to
th
e
m
a
in
s
tr
o
k
e
co
m
p
o
n
e
n
ts
to
r
ed
u
ce
s
tr
o
k
e
th
ic
k
n
es
s
to
a
o
n
e
-
p
i
x
el
-
w
id
e
r
ep
r
esen
tatio
n
w
h
i
le
p
r
eser
v
i
n
g
to
p
o
lo
g
ical
s
tr
u
ctu
r
e
[
3
8
]
-
[
4
1
]
.
T
h
is
s
tep
s
i
m
p
li
f
i
es
ch
ar
ac
ter
s
h
ap
es
an
d
f
ac
il
itates
k
e
y
p
o
i
n
t
d
e
tectio
n
w
it
h
o
u
t
lo
s
i
n
g
e
s
s
e
n
tial
p
alae
o
g
r
ap
h
ic
f
ea
tu
r
es
[
4
2
]
-
[
4
4
]
.
T
w
o
s
k
eleto
n
izatio
n
alg
o
r
ith
m
s
Z
h
an
g
S
u
en
an
d
L
ee
w
er
e
ev
alu
a
ted
.
T
h
e
Z
h
an
g
Su
e
n
alg
o
r
ith
m
,
a
t
w
o
-
s
u
b
iter
atio
n
th
in
n
i
n
g
m
e
th
o
d
,
w
a
s
s
elec
ted
d
u
e
to
it
s
ef
f
ici
en
c
y
in
p
r
eser
v
in
g
co
n
n
ec
t
iv
i
t
y
a
n
d
m
i
n
i
m
iz
i
n
g
s
p
u
r
io
u
s
b
r
an
c
h
es
[
4
5
]
,
[
4
6
]
.
T
h
e
s
k
eleto
n
izat
io
n
p
r
o
ce
s
s
ca
n
b
e
m
at
h
e
m
a
ticall
y
ex
p
r
ess
e
d
as:
(
)
=
{
∈
|
∈
me
d
ia
l
a
xis
(
)
∧
(
\
{
}
)
r
e
ma
in
s
c
on
n
e
c
te
d
}
(
5
)
(
)
is
th
e
b
i
n
ar
y
o
b
j
ec
t,
r
ep
r
esen
ts
a
p
i
x
el
i
n
o
b
j
ec
t
,
m
ed
ial
a
x
is
(
)
d
en
o
tes
t
h
e
m
ed
ial
a
x
i
s
o
f
o
b
j
ec
t
.
(
)
is
th
e
s
et
o
f
p
i
x
e
ls
i
n
o
b
j
ec
t
th
at
lie
o
n
t
h
e
m
ed
ial
a
x
is
a
n
d
ca
n
b
e
d
elet
ed
w
it
h
o
u
t
b
r
ea
k
in
g
o
b
j
ec
t
co
n
n
ec
tiv
it
y
.
T
h
is
d
ef
in
i
tio
n
f
o
r
m
s
th
e
f
o
u
n
d
atio
n
o
f
t
h
e
s
k
eleto
n
izatio
n
p
r
o
ce
s
s
,
en
s
u
r
i
n
g
th
at
t
h
e
to
p
o
lo
g
ical
s
tr
u
ct
u
r
e
o
f
ch
ar
ac
ter
s
i
s
p
r
eser
v
ed
.
I
n
th
e
Z
h
a
n
g
-
S
u
en
al
g
o
r
ith
m
,
a
p
ix
el
is
d
elete
d
if
i
t
s
atis
f
ies
th
e
f
o
llo
w
i
n
g
co
n
d
iti
o
n
s
.
T
h
ese
co
n
d
itio
n
s
en
s
u
r
e
th
at
t
h
e
s
k
eleto
n
r
e
m
ai
n
s
o
n
e
p
ix
el
w
id
e
w
h
i
le
p
r
eser
v
in
g
co
n
n
ec
ti
v
it
y
.
Dele
te
p
ix
el
if
:
−
2
≤
N
(
)
≤
6
N
(
)
=
n
u
m
b
er
o
f
8
n
eig
h
b
o
r
s
o
f
p
ix
el
−
Z
(
)
=
1
Z
(
)
=
n
u
m
b
er
o
f
tr
an
s
itio
n
s
f
r
o
m
0
to
1
in
th
e
clo
ck
w
i
s
e
o
r
d
er
o
f
t
h
e
8
n
eig
h
b
o
r
s
−
2
.
4
.
6
=
0
s
tep
1
−
2
.
4
.
6
=
0
s
tep
2
2
.
4
.
6
=
p
o
s
itio
n
o
f
th
e
p
i
x
el
’
s
n
e
ig
h
b
o
r
s
in
th
e
clo
ck
w
is
e
d
ir
ec
tio
n
T
o
s
tr
en
g
t
h
en
t
h
e
j
u
s
tific
atio
n
f
o
r
th
e
ch
o
s
en
m
et
h
o
d
,
a
co
m
p
ar
at
iv
e
ev
a
lu
atio
n
w
as
also
co
n
d
u
cted
u
s
i
n
g
th
e
L
ee
alg
o
r
it
h
m
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
Z
h
a
n
g
-
S
u
en
an
d
L
ee
s
k
eleto
n
izatio
n
w
as
q
u
an
titati
v
el
y
ass
es
s
ed
u
s
i
n
g
th
r
ee
m
etr
ic
s
:
ex
ec
u
t
io
n
ti
m
e,
n
u
m
b
er
o
f
s
p
u
r
io
u
s
b
r
an
c
h
es,
an
d
p
ix
el
r
ed
u
ctio
n
r
atio
(
P
R
R
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
6
2
0
-
634
624
T
h
is
co
m
p
ar
is
o
n
p
r
o
v
id
es
a
co
m
p
r
e
h
en
s
iv
e
b
as
is
f
o
r
s
elec
ti
n
g
t
h
e
m
o
s
t
s
u
itab
le
al
g
o
r
ith
m
f
o
r
J
a
w
i
c
h
ar
ac
ter
s
eg
m
e
n
tatio
n
i
n
t
h
is
r
esear
c
h
.
2
.
6
.
K
ey
po
int
d
et
ec
t
io
n
Af
ter
s
k
eleto
n
izatio
n
o
f
th
e
m
ai
n
s
tr
o
k
e
s
,
s
tr
u
c
tu
r
al
k
e
y
p
o
in
ts
ar
e
ex
tr
ac
ted
to
s
u
p
p
o
r
t
d
etailed
s
h
ap
e
an
al
y
s
is
a
n
d
w
r
i
tin
g
d
ir
ec
tio
n
d
etec
tio
n
.
T
h
e
d
etec
ted
k
e
y
p
o
in
t
s
in
cl
u
d
e
s
tar
t
p
o
in
ts
,
en
d
p
o
in
t
s
,
in
ter
s
ec
tio
n
p
o
in
ts
,
t
u
r
n
p
o
in
t
s
,
ce
n
tr
o
id
p
o
in
ts
,
an
d
lo
o
p
.
T
h
eir
d
ef
in
itio
n
s
ar
e
as
in
:
2
.
6
.
1
.
Sta
rt
p
o
int
T
h
e
s
k
eleto
n
p
o
in
t
w
i
th
o
n
e
ac
tiv
e
n
ei
g
h
b
o
r
in
th
e
3
×3
w
i
n
d
o
w
an
d
lo
ca
ted
at
th
e
to
p
-
r
ig
h
t
p
o
s
itio
n
(
m
ax
i
m
u
m
co
l
u
m
n
v
al
u
e
an
d
m
i
n
i
m
u
m
r
o
w
v
al
u
e)
is
d
ef
in
e
d
as
th
e
s
tar
t
p
o
in
t.
T
h
is
p
o
in
t
is
s
elec
ted
b
ec
au
s
e
it
r
ep
r
esen
ts
th
e
n
atu
r
al
wr
itin
g
d
ir
ec
tio
n
o
f
A
r
ab
ic
o
r
J
aw
i
s
cr
ip
t,
w
h
ic
h
b
eg
i
n
s
f
r
o
m
th
e
r
ig
h
t.
Ma
th
e
m
atica
ll
y
,
th
e
d
e
f
i
n
itio
n
ca
n
b
e
f
o
r
m
u
lated
as
in
:
(
)
=
1
(
6
)
=
(
(
)
−
(
)
|
(
)
=
1
)
(7
)
is
a
s
k
eleto
n
p
ix
el,
(
)
r
ep
r
ese
n
ts
th
e
n
u
m
b
er
o
f
co
n
n
ec
ted
n
eig
h
b
o
r
s
o
f
p
ix
el
an
d
(
)
−
(
)
ar
e
th
e
an
d
co
o
r
d
in
ate
v
al
u
es
o
f
p
i
x
el
in
th
e
i
m
a
g
e
c
o
o
r
d
in
ate
s
y
s
te
m
.
A
p
ix
e
l
i
s
d
ef
in
ed
as
a
s
tar
tin
g
p
o
in
t
if
it
is
an
en
d
p
o
in
t,
i.e
.
,
co
n
n
ec
ted
to
o
n
l
y
o
n
e
n
eig
h
b
o
r
in
th
e
s
k
eleto
n
g
r
ap
h
(
(
)
=
1
)
.
Am
o
n
g
all
s
u
c
h
p
ix
els,
th
e
o
n
e
w
ith
t
h
e
lar
g
est
(
−
)
v
alu
e
is
ch
o
s
en
as
t
h
e
to
p
-
r
ig
h
t
p
o
s
itio
n
f
o
r
tr
av
er
s
al.
2
.
6
.
2
.
E
nd
p
o
int
A
s
k
eleto
n
p
ix
el
w
it
h
o
n
e
a
ctiv
e
n
e
ig
h
b
o
r
,
lo
ca
ted
at
th
e
f
ar
lef
t
(
m
in
i
m
u
m
co
l
u
m
n
v
alu
e)
a
n
d
b
o
tto
m
(
m
a
x
i
m
u
m
r
o
w
v
alu
e)
,
is
d
ef
in
ed
as
th
e
en
d
p
o
in
t.
T
h
is
p
o
in
t
in
d
icate
s
th
e
g
eo
m
etr
ic
ter
m
i
n
atio
n
o
f
th
e
ch
ar
ac
ter
s
h
ap
e.
Ma
th
e
m
at
icall
y
,
t
h
e
d
ef
i
n
itio
n
ca
n
b
e
f
o
r
m
u
la
ted
as
in
:
(
)
=
1
(
8
)
=
(
(
)
−
(
)
|
(
)
=
1
)
(
9
)
As
w
it
h
t
h
e
s
tar
t
p
o
in
t,
t
h
e
en
d
p
o
in
t
i
s
also
a
p
i
x
el
th
at
is
co
n
n
ec
ted
to
o
n
l
y
o
n
e
n
eig
h
b
o
r
(
(
)
=
1
)
.
T
h
e
d
if
f
er
en
ce
f
r
o
m
t
h
e
s
ta
r
t
p
o
in
t
is
th
at
th
e
en
d
p
o
in
t
is
lo
ca
ted
at
th
e
b
o
tto
m
-
le
f
t
o
f
t
h
e
s
k
eleto
n
,
d
eter
m
i
n
ed
b
y
a
s
m
a
ll
(
lef
t
m
o
s
t)
an
d
lar
g
e
(
lo
w
es
t)
.
2
.
6
.
3
.
I
nte
rsect
io
n
p
o
int
A
s
k
eleto
n
p
i
x
el
w
ith
t
h
r
ee
o
r
m
o
r
e
ac
tiv
e
n
eig
h
b
o
r
s
is
d
ef
i
n
e
d
as
an
in
ter
s
ec
t
io
n
p
o
in
t.
T
h
is
p
o
in
t
r
ep
r
esen
ts
b
r
an
ch
in
g
i
n
th
e
ch
ar
ac
ter
s
tr
u
ct
u
r
e,
w
h
ic
h
is
t
y
p
ical
in
co
m
p
le
x
o
r
cu
r
v
ed
s
h
ap
es.
Ma
th
e
m
atica
ll
y
,
th
e
d
e
f
i
n
itio
n
ca
n
b
e
ex
p
r
ess
ed
as
(
1
0
)
.
(
)
≥
3
(
1
0
)
An
i
n
ter
s
ec
tio
n
p
o
in
t
h
a
s
h
i
g
h
co
n
n
ec
tiv
it
y
,
a
s
it
is
co
n
n
e
cted
to
th
r
ee
o
r
m
o
r
e
n
ei
g
h
b
o
r
in
g
p
ix
el
s
i
n
th
e
s
k
eleto
n
g
r
ap
h
.
2
.
6
.
4
.
T
urn
p
o
int
A
s
k
e
leto
n
p
i
x
el
w
it
h
o
n
e
h
o
r
izo
n
tal
n
eig
h
b
o
r
an
d
o
n
e
v
er
t
ical
n
ei
g
h
b
o
r
is
d
ef
i
n
ed
as
a
t
u
r
n
p
o
in
t.
T
h
is
p
o
in
t
co
r
r
esp
o
n
d
s
to
a
s
h
ar
p
ch
an
g
e
i
n
d
ir
ec
tio
n
,
t
y
p
i
ca
ll
y
clo
s
e
to
a
9
0
°
an
g
le,
a
n
d
is
o
f
ten
f
o
u
n
d
i
n
cu
r
v
ed
o
r
an
g
u
lar
ch
ar
ac
ter
s
.
Ma
th
e
m
atica
ll
y
,
a
tu
r
n
p
o
in
t c
an
b
e
d
ef
in
ed
as
(
1
1
)
.
=
−
1
(
(
−
−
1
)
∙
(
+
1
−
)
‖
−
−
1
‖
‖
+
1
−
‖
)
(
1
1
)
I
f
−
1
,
,
+
1
ar
e
th
r
ee
co
n
s
ec
u
ti
v
e
p
ix
els
alo
n
g
t
h
e
s
k
eleto
n
p
at
h
,
th
e
n
p
ix
el
is
co
n
s
id
er
ed
a
tu
r
n
p
o
in
t i
f
:
>
ℎ
ℎ
(
1
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f p
a
le
o
g
r
a
p
h
ic
cu
r
va
tu
r
e
u
s
in
g
s
ke
leto
n
iz
a
tio
n
a
n
d
ke
y
p
o
in
t d
etec
tio
n
(
F
a
d
h
ila
tu
l F
itr
iya
h
)
625
w
h
er
e
ℎ
ℎ
is
a
p
r
ed
ef
in
ed
t
h
r
es
h
o
ld
an
g
le
(
co
m
m
o
n
l
y
b
et
w
ee
n
30
°
an
d
60
°)
u
s
ed
to
d
etec
t
s
i
g
n
i
f
ica
n
t
cu
r
v
at
u
r
e
ch
a
n
g
e
s
.
2
.
6
.
5
.
Cent
ro
id
p
o
int
T
h
e
ce
n
tr
o
id
p
o
in
t
r
ep
r
esen
ts
th
e
av
er
a
g
e
p
o
s
itio
n
o
f
al
l
s
k
eleto
n
p
ix
els
w
it
h
i
n
a
ch
ar
ac
ter
’
s
b
o
u
n
d
in
g
b
o
x
.
I
t
s
er
v
es
as
a
g
lo
b
al
d
escr
ip
to
r
o
f
th
e
ch
ar
ac
ter
’
s
p
o
s
itio
n
an
d
is
also
u
s
ed
to
estab
lis
h
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
t
h
e
m
ai
n
s
tr
o
k
e
a
n
d
its
d
iacr
itics
.
M
ath
e
m
atica
ll
y
,
if
t
h
er
e
ar
e
s
k
eleto
n
p
o
in
ts
,
t
h
e
ce
n
tr
o
id
co
o
r
d
in
ates c
an
b
e
co
m
p
u
ted
as:
=
1
∑
,
=
1
∑
=
1
=
1
(
1
3
)
an
d
ar
e
th
e
ce
n
tr
o
id
co
o
r
d
in
ates
r
ep
r
esen
tin
g
t
h
e
av
er
a
g
e
an
d
p
o
s
itio
n
s
o
f
all
s
k
elet
o
n
p
ix
els
,
an
d
ar
e
th
e
an
d
co
o
r
d
in
ate
v
alu
es
o
f
t
h
e
-
th
s
k
eleto
n
p
i
x
el
in
t
h
e
i
m
a
g
e
co
o
r
d
in
ate
s
y
s
te
m
.
T
h
u
s
,
th
e
ce
n
tr
o
id
is
d
ef
in
ed
as
=
(
,
)
.
T
h
is
p
o
in
t
ca
n
b
e
u
s
ed
to
n
o
r
m
alize
t
h
e
p
o
s
itio
n
o
f
ea
c
h
c
h
ar
ac
ter
an
d
as a
f
ea
t
u
r
e
in
d
eter
m
in
i
n
g
r
elativ
e
p
o
s
itio
n
s
o
r
f
o
r
ch
ar
ac
ter
class
i
f
icatio
n
.
2
.
6
.
6
.
L
o
o
p
A
s
k
eleto
n
lo
o
p
is
d
ef
i
n
ed
a
s
a
clo
s
ed
c
y
cle
d
etec
ted
i
n
t
h
e
c
h
ar
ac
ter
s
k
eleto
n
g
r
ap
h
.
T
o
en
s
u
r
e
ac
cu
r
ac
y
,
th
e
s
y
s
te
m
ap
p
lies
a
f
ilter
in
g
p
r
o
ce
s
s
th
at
d
is
ti
n
g
u
is
h
es
tr
u
e
lo
o
p
f
r
o
m
n
o
is
e
o
r
s
m
all
tu
r
n
s
.
E
ac
h
c
y
cle
is
ev
a
lu
ated
u
s
i
n
g
t
h
e
C
o
n
v
e
x
Hu
l
l
m
et
h
o
d
,
an
d
o
n
l
y
th
o
s
e
w
it
h
a
s
u
f
f
icie
n
tl
y
lar
g
e
ar
ea
ar
e
class
if
ied
as v
alid
lo
o
p
.
Ma
th
e
m
at
icall
y
,
lo
o
p
id
en
tif
icatio
n
ca
n
b
e
ex
p
r
ess
ed
as:
=
{
ℎ
∈
_
(
)
|
(
(
ℎ
)
)
>
}
(
1
4
)
is
th
e
s
k
e
leto
n
g
r
ap
h
r
ep
r
esen
t
in
g
t
h
e
co
n
n
ec
t
iv
i
t
y
o
f
p
ix
el
s
,
ℎ
is
a
A
cy
c
le
(
clo
s
ed
p
ath
)
ex
tr
ac
ted
f
r
o
m
t
h
e
c
y
cle
b
as
is
o
f
g
r
ap
h
,
an
d
_
(
)
d
en
o
tes
th
e
s
et
o
f
all
f
u
n
d
am
e
n
tal
c
y
cle
s
in
t
h
e
s
k
eleto
n
g
r
ap
h
.
(
ℎ
)
r
e
p
r
e
s
e
n
t
s
th
e
c
o
n
v
e
x
h
u
l
l
f
o
r
m
e
d
b
y
th
e
p
ix
e
l
s
b
e
l
o
n
g
in
g
t
o
cy
c
l
e
ℎ
,
a
n
d
(
(
ℎ
)
)
i
s
th
e
a
r
e
a
en
cl
o
s
e
d
b
y
th
e
c
o
n
v
ex
h
u
l
l
o
f
cy
c
le
ℎ
.
is
th
e
m
in
im
u
m
a
r
e
a
th
r
esh
o
l
d
u
s
e
d
t
o
f
i
l
te
r
o
u
t
s
m
al
l
o
r
n
o
i
s
y
cy
c
le
s
,
an
d
L
oop
i
s
th
e
s
e
t
o
f
v
a
li
d
lo
o
p
w
h
o
s
e
a
r
e
a
s
ex
ce
e
d
th
e
th
r
e
s
h
o
l
d
.
W
h
er
e
d
en
o
tes
th
e
s
et
o
f
v
alid
lo
o
p
,
r
e
p
r
esen
ts
a
cy
c
le
f
r
o
m
_
(
)
,
an
d
is
th
e
m
i
n
i
m
u
m
ar
ea
th
r
es
h
o
ld
(
s
et
to
1
.
5
in
th
is
s
t
u
d
y
)
.
C
y
cles
w
it
h
an
ar
ea
g
r
ea
ter
th
a
n
ar
e
r
etain
ed
as
v
alid
lo
o
p
,
w
h
ile
s
m
aller
o
n
es
ar
e
d
is
ca
r
d
ed
as
n
o
is
e.
T
h
is
ap
p
r
o
a
ch
en
s
u
r
es
t
h
at
o
n
l
y
lo
o
p
r
ef
l
ec
tin
g
tr
u
e
cir
cu
lar
ch
ar
ac
ter
s
tr
u
ct
u
r
es a
r
e
p
r
eser
v
ed
in
t
h
e
an
al
y
s
is
.
2
.
7
.
Cha
ra
c
t
er
s
eg
m
ent
a
t
io
n
C
h
ar
ac
ter
s
e
g
m
e
n
tatio
n
w
as
p
er
f
o
r
m
ed
a
f
ter
id
en
tify
i
n
g
k
e
y
p
o
in
t
s
in
th
e
s
k
eleto
n
s
tr
u
ctu
r
e,
u
s
in
g
th
r
ee
ap
p
r
o
ac
h
es
:
c
h
ar
ac
ter
s
e
g
m
e
n
tat
io
n
i
s
co
n
d
u
c
ted
af
ter
s
k
eleto
n
-
b
a
s
ed
k
e
y
p
o
i
n
t
e
x
tr
a
ctio
n
u
s
i
n
g
a
th
r
ee
-
s
tag
e
s
tr
ateg
y
.
First,
co
n
n
ec
te
d
co
m
p
o
n
e
n
t
lab
elin
g
(
C
C
L
)
is
ap
p
lied
to
d
ir
ec
tly
s
eg
m
e
n
t
i
s
o
lated
ch
ar
ac
ter
s
,
w
it
h
ce
n
tr
o
id
s
u
s
ed
to
g
u
id
e
cr
o
p
p
in
g
an
d
ass
o
ciate
d
iacr
it
ics
w
it
h
th
e
m
a
in
s
tr
o
k
e.
Sec
o
n
d
,
f
o
r
c
o
n
n
ec
ted
co
m
p
o
n
e
n
t
s
,
s
k
eleto
n
in
ter
s
e
ctio
n
p
o
in
ts
ar
e
em
p
lo
y
ed
as
s
tr
u
ctu
r
al
cu
t
c
u
es,
w
ith
cu
t
s
ap
p
lied
o
n
e
p
ix
el
b
ef
o
r
e
th
e
in
ter
s
ec
tio
n
to
p
r
es
er
v
e
s
tr
o
k
e
co
n
ti
n
u
it
y
.
T
h
ir
d
,
lo
o
p
(
cl
o
s
ed
-
p
ath
)
an
al
y
s
i
s
is
i
n
teg
r
ated
to
r
eso
lv
e
a
m
b
ig
u
itie
s
i
n
m
u
lti
-
c
h
ar
ac
ter
co
n
n
ec
tio
n
s
:
cr
o
p
p
in
g
i
s
ad
j
u
s
ted
r
elativ
e
to
th
e
in
ter
s
ec
tio
n
p
o
s
itio
n
d
ep
en
d
in
g
o
n
lo
o
p
lo
ca
tio
n
,
d
o
u
b
le
cu
ts
ar
e
ap
p
lied
f
o
r
th
r
ee
-
ch
ar
ac
ter
co
n
n
ec
tio
n
s
,
an
d
co
m
p
o
n
en
t
s
w
ith
o
u
t
lo
o
p
s
an
d
w
it
h
o
n
l
y
t
w
o
en
d
p
o
in
ts
ar
e
r
etain
ed
as
s
in
g
le
ch
ar
ac
ter
s
.
T
h
is
co
m
b
i
n
ed
s
tr
ateg
y
en
ab
le
s
ac
cu
r
ate
an
d
co
n
tex
t
-
a
w
ar
e
s
e
g
m
e
n
tati
o
n
o
f
co
m
p
lex
h
a
n
d
w
r
it
ten
J
a
w
i c
h
ar
ac
ter
s
.
W
h
ile
t
h
ese
s
eg
m
e
n
tatio
n
m
et
h
o
d
s
(
e.
g
.
,
co
n
n
ec
ted
co
m
p
o
n
en
t,
s
k
eleto
n
izatio
n
,
a
n
d
k
e
y
p
o
in
t
de
tectio
n
)
ar
e
n
o
t
en
tire
l
y
n
e
w
,
th
e
n
o
v
elt
y
o
f
th
i
s
w
o
r
k
li
es
in
th
eir
ad
ap
tatio
n
to
th
e
J
a
w
i
s
cr
ip
t.
P
r
ev
io
u
s
s
tu
d
ie
s
h
av
e
p
r
o
v
id
ed
i
m
p
o
r
tan
t
in
s
i
g
h
t
s
in
to
A
r
ab
ic
s
cr
ip
t
s
eg
m
en
ta
tio
n
,
b
u
t
th
e
y
r
e
m
ai
n
lar
g
el
y
li
m
ited
to
s
tan
d
ar
d
A
r
ab
ic
an
d
h
a
v
e
n
o
t
b
ee
n
s
p
e
cif
icall
y
ap
p
lied
to
J
a
w
i.
T
h
e
J
a
w
i
s
cr
ip
t
in
tr
o
d
u
ce
s
d
is
tin
ct
s
tr
u
ctu
r
a
l
co
m
p
le
x
itie
s
:
it
s
ch
ar
ac
ter
s
ex
h
ib
it
m
o
r
e
in
tr
icate
s
tr
u
ct
u
r
es,
d
iacr
itic
p
lace
m
e
n
t
d
i
f
f
er
s
,
h
a
n
d
w
r
iti
n
g
th
ic
k
n
e
s
s
v
ar
ies
co
n
s
id
er
ab
l
y
,
an
d
li
g
at
u
r
es
ar
e
o
f
te
n
ir
r
eg
u
lar
.
T
h
ese
ch
ar
a
cter
is
t
ics
m
a
k
e
th
e
s
e
g
m
e
n
tatio
n
o
f
co
n
n
ec
ted
ch
ar
ac
ter
s
p
ar
tic
u
lar
l
y
ch
alle
n
g
i
n
g
,
t
h
er
eb
y
r
e
q
u
ir
in
g
a
m
o
r
e
r
o
b
u
s
t
an
d
ad
ap
tiv
e
ap
p
r
o
ac
h
to
ac
cu
r
atel
y
id
e
n
ti
f
y
c
h
ar
ac
ter
b
o
u
n
d
ar
ies
u
n
d
er
co
m
p
lex
co
n
d
itio
n
s
.
A
lt
h
o
u
g
h
t
h
is
r
e
s
ea
r
ch
f
o
cu
s
e
s
o
n
c
h
ar
ac
ter
s
eg
m
e
n
tatio
n
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
ca
n
b
e
in
te
g
r
ated
in
to
a
co
m
p
lete
OC
R
w
o
r
k
f
lo
w
.
Se
g
m
en
ted
ch
ar
ac
ter
s
s
er
v
e
as
i
n
p
u
t
f
o
r
later
s
tag
e
s
s
u
ch
a
s
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
class
if
icatio
n
,
an
d
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
,
en
ab
li
n
g
th
e
r
ec
o
g
n
itio
n
o
f
P
eg
o
n
s
cr
ip
t
in
h
is
to
r
ica
l
m
an
u
s
cr
ip
ts
.
T
h
is
i
n
te
g
r
atio
n
h
ig
h
li
g
h
ts
th
e
p
r
ac
tical
ap
p
licatio
n
o
f
s
eg
m
e
n
tatio
n
m
et
h
o
d
s
in
b
r
o
ad
er
OC
R
s
y
s
te
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
6
2
0
-
634
626
2.
8
.
E
v
a
lua
t
i
o
n
T
h
is
ev
alu
a
tio
n
s
ta
g
e
w
as
co
n
d
u
cted
to
m
ea
s
u
r
e
h
o
w
w
e
ll
t
h
e
s
e
g
m
e
n
tatio
n
m
e
th
o
d
s
ep
ar
ated
J
aw
i
ch
ar
ac
ter
s
co
r
r
ec
tl
y
.
T
h
e
e
v
alu
atio
n
w
as
ca
r
r
ied
o
u
t
b
y
co
m
p
ar
in
g
t
h
e
a
u
to
m
at
ic
s
eg
m
e
n
tat
io
n
r
es
u
lt
s
g
en
er
ated
b
y
th
e
s
y
s
te
m
w
it
h
th
e
m
a
n
u
all
y
d
ef
i
n
ed
g
r
o
u
n
d
tr
u
th
d
ata.
T
h
is
p
r
o
ce
s
s
u
s
ed
s
ev
er
al
s
tan
d
ar
d
ev
alu
a
tio
n
m
etr
ics i
n
t
h
e
f
ield
o
f
p
atter
n
r
ec
o
g
n
i
tio
n
,
n
a
m
el
y
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
[
4
7
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
P
re
-
p
ro
ce
s
s
ing
Fig
u
r
e
s
3
(
a)
to
(
c)
illu
s
tr
ates
t
h
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tag
e
s
,
in
c
lu
d
in
g
g
r
a
y
s
ca
le
co
n
v
er
s
io
n
,
t
h
r
esh
o
ld
in
g
,
an
d
n
o
is
e
r
e
m
o
v
al
u
s
i
n
g
C
C
A
.
T
h
ese
s
tep
s
ef
f
ec
ti
v
el
y
en
h
a
n
ce
f
o
r
eg
r
o
u
n
d
-
b
ac
k
g
r
o
u
n
d
s
ep
ar
atio
n
an
d
p
r
o
v
id
e
a
clea
n
b
as
is
f
o
r
s
e
g
m
en
tatio
n
.
Ho
w
ev
er
,
s
o
m
e
d
iac
r
itics
ar
e
r
e
m
o
v
ed
d
u
r
i
n
g
C
C
A
d
u
e
to
t
h
eir
s
m
all
s
ize
an
d
s
p
atial
s
ep
ar
atio
n
r
ese
m
b
lin
g
n
o
is
e,
w
h
ich
af
f
ec
t
s
ch
ar
ac
ter
s
th
at
r
el
y
o
n
d
o
t
p
atte
r
n
s
.
T
h
is
li
m
itatio
n
in
d
icate
s
t
h
at
f
ix
ed
th
r
e
s
h
o
ld
s
etti
n
g
s
ar
e
n
o
t
f
u
ll
y
al
ig
n
ed
w
it
h
J
a
w
i
p
aleo
g
r
ap
h
ic
ch
ar
ac
ter
is
tics
,
s
u
g
g
e
s
ti
n
g
th
e
n
ee
d
f
o
r
ad
ap
tiv
e
d
iacr
itic
-
p
r
eser
v
atio
n
s
tr
ate
g
ies to
i
m
p
r
o
v
e
s
eg
m
e
n
tatio
n
co
n
s
i
s
te
n
c
y
.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
Step
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
:
(
a)
g
r
a
y
s
ca
le
i
m
a
g
e
r
esu
lt,
(
b
)
t
h
r
esh
o
ld
in
g
i
m
a
g
e
r
es
u
lt,
an
d
(
c)
c
lean
ed
th
r
es
h
o
ld
in
g
i
m
a
g
e
r
es
u
lt
3
.
2
.
B
o
un
din
g
b
ox
B
o
u
n
d
in
g
b
o
x
an
al
y
s
i
s
s
u
cc
ess
f
u
l
l
y
d
is
ti
n
g
u
is
h
es
m
ain
s
tr
o
k
es
an
d
d
iacr
itics
,
as
v
i
s
u
alize
d
i
n
Fig
u
r
e
4
,
p
r
eser
v
in
g
th
e
ir
s
p
atial
r
elatio
n
s
h
ip
s
,
w
h
ich
a
r
e
cr
itical
f
o
r
J
a
w
i
r
ec
o
g
n
it
io
n
.
Nev
er
t
h
eles
s
,
d
iacr
itics
lo
ca
ted
f
ar
f
r
o
m
t
h
e
m
ai
n
s
tr
o
k
e
ar
e
s
o
m
e
ti
m
es
m
i
s
class
if
ied
as
n
o
is
e
o
r
in
co
r
r
ec
tl
y
as
s
o
ciate
d
d
u
e
to
o
v
er
lap
p
in
g
s
tr
o
k
es.
T
h
is
li
m
itatio
n
r
ed
u
ce
s
s
e
g
m
en
tat
io
n
ac
cu
r
ac
y
f
o
r
d
o
t
-
s
e
n
s
it
iv
e
c
h
ar
ac
ter
s
.
A
d
ap
tiv
e
d
is
tan
ce
t
h
r
es
h
o
ld
s
n
o
r
m
alize
d
to
ch
ar
ac
ter
s
ize
a
n
d
th
e
i
n
co
r
p
o
r
atio
n
o
f
J
a
w
i
-
s
p
ec
if
ic
l
in
g
u
i
s
tic
r
u
les
ar
e
r
ec
o
m
m
e
n
d
ed
to
i
m
p
r
o
v
e
r
o
b
u
s
t
n
es
s
ac
r
o
s
s
h
a
n
d
w
r
iti
n
g
s
t
y
les an
d
m
a
n
u
s
cr
ip
t q
u
a
li
t
y
v
ar
iatio
n
s
.
Fig
u
r
e
4
.
Vis
u
al
izatio
n
o
f
d
iac
r
itics
an
d
m
a
in
s
tr
o
k
es
3
.
3
.
Sk
elet
o
niza
t
io
n
T
h
e
s
k
eleto
n
izatio
n
r
esu
l
ts
ar
e
p
r
esen
ted
in
Fig
u
r
e
5
,
co
m
p
ar
in
g
th
e
Z
h
an
g
-
S
u
en
a
n
d
L
ee
(
1
9
9
4
)
alg
o
r
ith
m
s
.
Z
h
a
n
g
-
Su
e
n
Fi
g
u
r
e
5
(
a
)
p
r
o
d
u
ce
s
th
in
s
k
eleto
n
s
an
d
p
r
eser
v
es
m
ai
n
s
tr
o
k
e
s
tr
u
ctu
r
e
s
ef
f
icien
tl
y
,
b
u
t
in
tr
o
d
u
ce
s
e
x
ce
s
s
i
v
e
b
r
an
ch
es
t
h
at
i
n
cr
ea
s
e
v
i
s
u
a
l
r
o
u
g
h
n
e
s
s
.
I
n
co
n
tr
ast,
th
e
L
ee
al
g
o
r
ith
m
F
ig
u
r
e
5
(
b
)
g
en
er
ate
s
s
m
o
o
th
er
s
k
e
leto
n
s
w
ith
f
e
w
er
b
r
an
ch
e
s
,
alt
h
o
u
g
h
s
o
m
e
f
in
e
s
tr
u
ctu
r
al
d
etails
ar
e
lo
s
t
d
u
e
t
o
o
v
er
s
i
m
p
li
f
ica
tio
n
.
(
a)
(
b
)
Fig
u
r
e
5
.
Step
o
f
s
k
eleto
n
izati
o
n
:
(
a)
Z
h
a
n
g
-
Su
e
n
s
k
eleto
n
iz
atio
n
alg
o
r
it
h
m
a
n
d
(
b
)
L
ee
9
4
s
k
eleto
n
izatio
n
alg
o
r
ith
m
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f p
a
le
o
g
r
a
p
h
ic
cu
r
va
tu
r
e
u
s
in
g
s
ke
leto
n
iz
a
tio
n
a
n
d
ke
y
p
o
in
t d
etec
tio
n
(
F
a
d
h
ila
tu
l F
itr
iya
h
)
627
Qu
a
n
titati
v
e
r
es
u
lt
s
i
n
T
ab
le
2
s
h
o
w
t
h
at
Z
h
an
g
-
S
u
e
n
ac
h
ie
v
es
f
a
s
ter
p
r
o
ce
s
s
in
g
t
i
m
e
(
0
.
2
8
m
s
)
t
h
a
n
L
ee
(
0
.
7
0
m
s
)
,
b
u
t
p
r
o
d
u
ce
s
m
o
r
e
e
x
ce
s
s
i
v
e
b
r
an
ch
e
s
(
3
5
v
s
.
2
7
)
.
B
o
th
m
et
h
o
d
s
y
ie
ld
id
en
tical
P
R
R
v
al
u
e
s
o
f
3
1
%.
T
h
is
in
d
icate
s
a
clea
r
tr
ad
e
-
o
f
f
b
et
w
ee
n
s
tr
u
ct
u
r
al
d
etail
p
r
eser
v
atio
n
an
d
s
k
eleto
n
s
m
o
o
t
h
n
e
s
s
.
C
o
n
s
id
er
in
g
its
ef
f
icie
n
c
y
an
d
co
m
p
ar
ab
le
P
R
R
,
Z
h
a
n
g
-
Su
e
n
w
as
s
elec
ted
a
s
t
h
e
p
r
ef
er
r
ed
m
eth
o
d
,
w
it
h
t
h
e
ac
k
n
o
w
led
g
m
e
n
t
t
h
at
b
r
an
ch
-
p
r
u
n
i
n
g
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
is
r
eq
u
ir
ed
to
m
iti
g
ate
n
o
is
e
a
n
d
p
r
ev
en
t
s
e
g
m
e
n
tatio
n
er
r
o
r
s
.
Fu
tu
r
e
w
o
r
k
s
h
o
u
ld
i
n
v
esti
g
ate
ad
ap
ti
v
e
o
r
h
y
b
r
id
s
k
eleto
n
iza
tio
n
s
tr
ateg
ie
s
to
b
a
lan
ce
e
f
f
icien
c
y
a
n
d
s
tr
u
ct
u
r
al
f
id
eli
t
y
f
o
r
J
a
w
i c
h
a
r
ac
ter
r
ec
o
g
n
itio
n
.
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
s
k
elet
o
n
izatio
n
al
g
o
r
ith
m
s
A
l
g
o
r
i
t
h
m
P
r
o
c
e
ssi
n
g
t
i
me
(
ms)
Ex
c
e
ssi
v
e
b
r
a
n
c
h
e
s
P
R
R
(
%)
N
o
t
e
s
Z
h
a
n
g
-
S
u
e
n
0
.
2
8
35
31
F
a
st
e
r
,
b
u
t
g
e
n
e
r
a
t
e
s mo
r
e
n
o
i
se
/
b
r
a
n
c
h
e
s
L
e
e
(
1
9
9
4
)
0
.
7
0
27
31
C
l
e
a
n
e
r
sk
e
l
e
t
o
n
,
b
u
t
sl
o
w
e
r
a
n
d
l
o
se
s d
e
t
a
i
l
s
3
.
4
.
K
ey
po
int
det
ec
t
io
n
Ke
y
p
o
in
t
d
etec
tio
n
r
esu
lts
s
h
o
w
n
in
Fig
u
r
e
6
d
em
o
n
s
tr
ate
r
eliab
le
id
en
tif
icat
io
n
o
f
s
tar
t
p
o
in
ts
,
en
d
p
o
in
ts
,
ce
n
tr
o
id
s
,
an
d
i
n
ter
s
ec
tio
n
s
,
e
f
f
ec
ti
v
el
y
s
u
p
p
o
r
tin
g
c
h
ar
ac
ter
s
e
g
m
e
n
tat
io
n
.
Ho
w
e
v
er
,
tu
r
n
p
o
in
t
s
ar
e
n
o
t
s
u
cc
es
s
f
u
l
l
y
d
etec
ted
,
as
cu
r
v
ed
s
tr
o
k
e
s
ar
e
o
f
ten
m
is
in
ter
p
r
eted
as
in
ter
s
ec
tio
n
s
.
I
n
p
r
ac
tice,
th
is
li
m
ita
tio
n
h
a
s
m
i
n
i
m
al
i
m
p
ac
t
o
n
s
eg
m
e
n
tatio
n
r
eliab
ilit
y
b
ec
au
s
e
s
e
g
m
e
n
tat
io
n
d
ec
is
io
n
s
p
r
im
ar
il
y
r
el
y
o
n
in
ter
s
ec
tio
n
an
d
ce
n
tr
o
id
p
o
i
n
ts
r
ath
er
th
a
n
tu
r
n
p
o
in
t
s
.
No
ex
p
licit
co
r
r
e
ctio
n
s
tr
at
eg
y
w
a
s
ap
p
lied
at
th
is
s
tag
e;
i
n
s
tead
,
s
eg
m
e
n
tatio
n
r
o
b
u
s
tn
ess
w
as
m
ain
tain
ed
b
y
p
r
io
r
itizin
g
s
tab
le
k
e
y
p
o
in
ts
an
d
ex
cl
u
d
in
g
a
m
b
ig
u
o
u
s
tu
r
n
-
p
o
in
t
d
etec
tio
n
s
.
T
h
is
li
m
itatio
n
in
d
icate
s
th
at
th
e
cu
r
r
en
t
r
u
le
-
b
ased
ap
p
r
o
ac
h
is
in
s
u
f
f
icie
n
t
to
ca
p
tu
r
e
cu
r
v
at
u
r
e
v
ar
iat
io
n
s
.
Fu
t
u
r
e
i
m
p
r
o
v
e
m
e
n
ts
s
h
o
u
ld
in
co
r
p
o
r
ate
cu
r
v
atu
r
e
-
s
e
n
s
iti
v
e
an
al
y
s
is
o
r
d
ata
-
d
r
iv
en
m
eth
o
d
s
to
en
h
a
n
ce
th
e
d
etec
tio
n
o
f
d
ir
ec
tio
n
al
ch
a
n
g
es in
J
a
w
i c
h
ar
ac
ter
s
tr
o
k
e
s
.
Fig
u
r
e
6
.
Ke
y
p
o
in
t d
etec
tio
n
r
esu
lt
s
f
o
r
th
e
w
o
r
d
“
ير
ي
د
”
3
.
5
.
Cha
ra
c
t
er
s
eg
m
ent
a
t
io
n
I
n
th
e
c
h
ar
ac
ter
s
e
g
m
en
ta
tio
n
s
ec
tio
n
,
th
e
ch
ar
ac
ter
s
i
n
t
h
e
f
ig
u
r
e
ar
e
ar
r
an
g
ed
ac
co
r
d
in
g
to
t
h
e
n
atu
r
al
J
a
w
i
r
ea
d
in
g
d
ir
ec
tio
n
,
f
r
o
m
r
ig
h
t
to
le
f
t.
Ho
w
e
v
er
,
th
e
s
u
b
f
i
g
u
r
e
lab
els
f
o
llo
w
t
h
e
s
ta
n
d
ar
d
j
o
u
r
n
al
co
n
v
e
n
tio
n
o
f
lef
t
-
to
-
r
ig
h
t o
r
d
er
in
g
.
3
.
5
.
1
.
B
a
s
ed
o
n
ce
ntr
o
id o
f
CCL
T
h
is
s
ec
tio
n
p
r
ese
n
ts
th
e
s
eg
m
en
tatio
n
r
es
u
lt
s
o
b
tain
ed
u
s
in
g
C
C
L
.
T
h
e
m
et
h
o
d
is
d
esig
n
ed
to
s
ep
ar
ate
in
d
iv
id
u
al
J
a
w
i
c
h
ar
a
cter
s
b
y
id
en
ti
f
y
i
n
g
co
m
p
o
n
e
n
ts
w
it
h
o
u
t
s
tr
u
ct
u
r
al
co
n
n
ec
t
io
n
s
a
n
d
ex
tr
ac
ti
n
g
th
e
m
as
s
in
g
le
u
n
its
.
T
o
im
p
r
o
v
e
s
eg
m
en
ta
tio
n
co
n
s
is
ten
c
y
,
th
e
ce
n
tr
o
id
o
f
ea
ch
co
n
n
ec
ted
co
m
p
o
n
e
n
t,
r
ep
r
esen
tin
g
it
s
s
p
atial
ce
n
ter
o
f
m
a
s
s
,
w
a
s
u
s
ed
as
a
r
ef
er
e
n
ce
.
T
h
is
allo
w
s
t
h
e
s
y
s
te
m
t
o
s
ep
ar
ate
th
e
m
a
in
s
tr
o
k
es
f
r
o
m
d
iacr
itical
ele
m
e
n
ts
s
u
ch
as
d
o
ts
o
r
h
ar
ak
at
m
o
r
e
p
r
ec
is
el
y
.
Fig
u
r
e
7
(
a)
s
h
o
w
s
ya
’
,
Fig
u
r
e
7
(
b
)
s
h
o
w
s
ya
’
an
d
r
a
’
,
an
d
Fig
u
r
e
7
(
c)
s
h
o
w
s
dal
.
T
h
ese
ex
a
m
p
l
es
d
e
m
o
n
s
tr
ate
th
at
C
C
L
p
er
f
o
r
m
s
ef
f
ec
ti
v
el
y
o
n
is
o
lated
co
m
p
o
n
en
t
s
w
it
h
n
o
s
tr
u
ctu
r
al
o
v
er
lap
.
As
s
h
o
w
n
in
Fig
u
r
e
7
,
s
in
g
le
ch
ar
ac
ter
s
w
er
e
s
e
g
m
en
ted
c
o
r
r
ec
tly
w
h
en
t
h
eir
s
tr
u
ctu
r
es
w
er
e
n
o
t
co
n
n
ec
ted
,
d
e
m
o
n
s
tr
atin
g
t
h
e
ef
f
ec
t
iv
e
n
es
s
o
f
C
C
L
in
h
a
n
d
lin
g
is
o
lated
s
tr
o
k
e
s
.
Ho
w
ev
er
,
s
eg
m
e
n
tatio
n
f
ail
u
r
es
w
er
e
o
b
s
er
v
ed
in
tig
h
tl
y
co
n
n
ec
ted
ch
ar
ac
ter
s
,
s
u
ch
as
ya
’
an
d
r
a
’
(
Fig
u
r
e
7
(
b)
)
,
w
h
er
e
ad
j
ac
en
t
ce
n
tr
o
id
s
w
er
e
to
o
clo
s
e,
ca
u
s
i
n
g
t
h
e
s
y
s
te
m
to
i
n
ter
p
r
et
m
u
lt
ip
le
ch
ar
ac
ter
s
as a
s
i
n
g
le
u
n
it.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
24
,
No
.
2
,
A
p
r
il
20
26
:
6
2
0
-
634
628
(
a)
(
b
)
(
c)
Fig
u
r
e
7
.
Step
o
f
s
eg
m
e
n
tatio
n
: (
a)
r
esu
lt
s
o
f
ya
’
ch
ar
ac
ter
s
eg
m
e
n
tat
io
n
,
(
b
)
r
esu
lts
o
f
ya
’
an
d
r
a
’
ch
ar
ac
ter
s
eg
m
e
n
tatio
n
,
a
n
d
(
c)
r
esu
lts
o
f
d
al
ch
ar
ac
ter
s
eg
m
e
n
tatio
n
T
h
is
h
i
g
h
li
g
h
t
s
a
f
u
n
d
a
m
e
n
tal
li
m
itatio
n
o
f
ce
n
tr
o
id
-
b
ased
s
eg
m
e
n
tatio
n
:
it
s
lac
k
o
f
d
is
c
r
i
m
i
n
ati
v
e
p
o
w
er
in
d
ea
li
n
g
w
i
th
t
h
e
ir
r
eg
u
lar
s
p
ac
i
n
g
a
n
d
co
m
p
le
x
lig
at
u
r
es
o
f
J
a
w
i
s
cr
ip
t.
T
o
ad
d
r
ess
th
is
,
m
o
r
e
co
n
tex
t
-
a
w
ar
e
s
tr
ate
g
ies
ar
e
r
eq
u
ir
ed
.
Po
ten
tial
i
m
p
r
o
v
e
m
en
t
s
in
cl
u
d
e
n
o
r
m
alizi
n
g
ce
n
tr
o
id
d
is
tan
ce
s
r
elativ
e
to
ch
ar
ac
ter
s
ize
o
r
in
teg
r
ati
n
g
ad
d
itio
n
al
h
eu
r
i
s
tics
,
s
u
c
h
as
s
k
eleto
n
-
b
a
s
ed
in
ter
s
ec
t
io
n
p
o
in
ts
,
to
g
u
id
e
m
o
r
e
ac
cu
r
ate
s
eg
m
e
n
tatio
n
.
3
.
5
.
2
.
B
a
s
ed
o
n
ce
ntr
o
id f
ro
m
C
CL
a
nd
i
nte
rsect
io
n po
i
nts
De
s
p
ite
th
e
o
b
s
er
v
ed
i
m
p
r
o
v
e
m
en
ts
,
s
e
g
m
en
tatio
n
er
r
o
r
s
p
er
s
is
t
in
co
m
p
le
x
c
h
ar
ac
ter
s
tr
u
ct
u
r
es.
Fig
u
r
es
8
(
a)
to
(
d
)
s
h
o
w
t
h
e
r
esu
lt
s
o
f
c
h
ar
ac
ter
s
eg
m
e
n
tatio
n
u
s
in
g
ce
n
tr
o
id
in
f
o
r
m
atio
n
f
r
o
m
C
C
L
co
m
b
i
n
ed
w
it
h
s
k
eleto
n
i
n
ter
s
ec
tio
n
p
o
in
ts
f
o
r
d
if
f
er
e
n
t
J
aw
i
c
h
ar
ac
ter
s
.
I
n
Fi
g
u
r
es
8
(
a)
an
d
(
b
)
,
ch
ar
ac
ter
s
w
it
h
s
er
r
ated
o
r
h
ig
h
l
y
cu
r
v
e
d
s
tr
o
k
es
(
e.
g
.
,
ya
a
n
d
ra
)
ex
h
ib
i
t
o
v
er
-
s
e
g
m
en
ta
tio
n
,
a
s
m
u
ltip
le
ce
n
tr
o
id
an
d
in
ter
s
ec
tio
n
p
o
in
t
s
ar
e
g
e
n
er
ated
alo
n
g
ir
r
eg
u
lar
s
k
eleto
n
p
ath
s
.
C
o
n
v
er
s
el
y
,
Fi
g
u
r
e
s
8
(
c)
an
d
(
d
)
illu
s
tr
at
e
ca
s
es
w
h
er
e
s
m
o
o
t
h
er
lig
at
u
r
es
(
e.
g
.
,
ya
an
d
dal
)
lea
d
t
o
u
n
d
er
-
s
e
g
m
e
n
tatio
n
d
u
e
to
w
ea
k
o
r
m
is
s
i
n
g
in
ter
s
ec
tio
n
p
o
in
ts
in
th
e
s
k
ele
to
n
r
ep
r
esen
tatio
n
.
T
h
ese
r
esu
lts
in
d
icate
th
at
th
e
e
f
f
ec
t
iv
e
n
ess
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
is
h
i
g
h
l
y
s
en
s
iti
v
e
t
o
s
k
eleto
n
q
u
alit
y
a
n
d
r
esid
u
a
l
n
o
is
e,
w
h
ic
h
d
ir
ec
tl
y
in
f
l
u
en
ce
th
e
ac
c
u
r
ac
y
o
f
ce
n
tr
o
id
d
etec
tio
n
an
d
in
ter
s
ec
tio
n
p
o
in
t e
x
tr
ac
tio
n
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
8
.
Step
o
f
s
eg
m
e
n
tatio
n
:
(
a)
r
esu
lt
s
o
f
ya
’
ch
ar
ac
ter
s
eg
m
e
n
tat
io
n
,
(
b
)
r
esu
lts
o
f
r
a
’
ch
ar
ac
ter
s
eg
m
e
n
tatio
n
,
(
c)
r
esu
l
ts
o
f
ya
’
ch
ar
ac
ter
s
eg
m
en
ta
tio
n
a
n
d
(
d
)
r
esu
lts
o
f
dal
ch
ar
ac
ter
s
eg
m
en
tatio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f p
a
le
o
g
r
a
p
h
ic
cu
r
va
tu
r
e
u
s
in
g
s
ke
leto
n
iz
a
tio
n
a
n
d
ke
y
p
o
in
t d
etec
tio
n
(
F
a
d
h
ila
tu
l F
itr
iya
h
)
629
3
.
5
.
3
.
B
a
s
ed
o
n c
ent
ro
id f
ro
m
C
CL
,
inte
r
s
ec
t
io
n po
ints,
a
nd
lo
o
p
T
o
f
u
r
th
er
ad
d
r
ess
co
n
n
ec
ted
ch
ar
ac
ter
s
,
lo
o
p
f
ea
tu
r
es
w
er
e
in
te
g
r
ated
w
it
h
ce
n
tr
o
id
an
d
in
ter
s
ec
tio
n
in
f
o
r
m
atio
n
.
As
s
h
o
w
n
i
n
Fi
g
u
r
e
s
9
an
d
1
0
,
th
is
ap
p
r
o
ac
h
i
m
p
r
o
v
e
s
s
e
g
m
e
n
tatio
n
ac
c
u
r
ac
y
f
o
r
ch
ar
ac
ter
s
w
it
h
lo
o
p
s
tr
u
ct
u
r
es
(
e.
g
.
,
ba
’
,
ha
’
)
,
o
u
tp
er
f
o
r
m
i
n
g
th
e
p
r
ev
io
u
s
m
eth
o
d
s
i
n
h
a
n
d
lin
g
co
m
p
lex
s
h
ap
es.
Nev
er
th
e
less
,
li
m
itatio
n
s
r
e
m
a
in
f
o
r
ch
ar
ac
ter
s
w
it
h
m
u
l
tip
le
lo
o
p
s
o
r
clo
s
el
y
lo
ca
ted
i
n
ter
s
ec
tio
n
s
,
a
s
w
ell
a
s
f
o
r
s
eq
u
en
ce
s
o
f
t
h
r
ee
co
n
n
ec
ted
ch
ar
ac
ter
s
(
e.
g
.
,
m
i
m
-
n
u
n
-
w
a
w
)
,
w
h
er
e
in
co
r
r
ec
t
cu
t
p
lace
m
e
n
t
m
a
y
ca
u
s
e
s
tr
u
ct
u
r
al
lo
s
s
.
T
h
ese
f
i
n
d
in
g
s
in
d
icate
th
at
f
ix
ed
cu
t
tin
g
r
u
l
es
ar
e
s
till
in
s
u
f
f
icie
n
t
f
o
r
h
i
g
h
l
y
co
m
p
le
x
J
a
w
i
h
an
d
w
r
iti
n
g
.
Fu
t
u
r
e
i
m
p
r
o
v
e
m
en
ts
s
h
o
u
ld
in
co
r
p
o
r
ate
ad
a
p
tiv
e
in
ter
s
ec
t
io
n
f
il
ter
in
g
,
b
r
an
ch
p
r
u
n
in
g
,
an
d
J
a
w
i
-
s
p
ec
i
f
ic
lin
g
u
is
tic
co
n
s
tr
ain
ts
to
e
n
h
a
n
ce
s
e
g
m
en
ta
tio
n
r
o
b
u
s
tn
es
s
.
T
h
e
s
eg
m
en
tatio
n
r
esu
lts
f
o
r
ch
ar
ac
ter
s
w
i
th
lo
o
p
s
tr
u
ctu
r
es
ar
e
s
h
o
w
n
i
n
Fig
u
r
es
1
0
(
a
)
an
d
(
b
)
.
Fig
u
r
e
1
0
(
a)
s
h
o
w
s
ha
’
,
an
d
F
ig
u
r
e
1
0
(
b
)
s
h
o
w
s
ba
’
.
T
h
ese
ex
a
m
p
le
s
d
e
m
o
n
s
tr
ate
th
at
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
p
er
f
o
r
m
s
ef
f
ec
t
iv
el
y
f
o
r
b
o
th
in
d
ep
en
d
en
t
a
n
d
co
n
n
ec
ted
ch
ar
ac
ter
s
w
it
h
lo
o
p
s
tr
u
ctu
r
e
s
.
C
o
m
p
ar
ed
to
th
e
t
w
o
p
r
ev
io
u
s
ap
p
r
o
ac
h
es,
th
is
m
et
h
o
d
p
r
o
v
id
es
i
m
p
r
o
v
ed
s
eg
m
en
ta
tio
n
ac
cu
r
ac
y
,
p
ar
ticu
lar
l
y
i
n
d
is
tin
g
u
is
h
i
n
g
c
h
ar
ac
ter
s
w
it
h
co
m
p
le
x
s
h
ap
es.
Desp
ite
it
s
ad
v
a
n
ce
m
e
n
t
s
,
th
e
cu
r
r
en
t
s
eg
m
e
n
tatio
n
m
e
th
o
d
f
ac
es
s
tr
u
c
tu
r
al
c
h
alle
n
g
e
s
,
p
ar
ticu
lar
l
y
w
it
h
c
h
ar
ac
ter
s
f
ea
t
u
r
in
g
d
o
u
b
le
lo
o
p
s
o
r
in
ter
s
ec
tio
n
s
lo
ca
ted
v
er
y
clo
s
e
to
a
lo
o
p
,
s
u
ch
as
h
a
’
o
r
m
i
m
.
I
n
th
ese
in
s
ta
n
ce
s
,
cu
tt
in
g
r
u
les
o
f
ten
d
a
m
ag
e
t
h
e
lo
o
p
a
r
ea
,
lead
in
g
to
s
tr
u
ctu
r
al
d
eg
r
ad
atio
n
.
Si
m
i
lar
l
y
,
i
n
co
m
p
le
x
s
eq
u
e
n
ce
s
l
ik
e
mim
-
nun
-
w
a
w
,
th
e
s
y
s
te
m
o
cc
as
io
n
all
y
f
a
ils
to
p
o
s
itio
n
c
u
t
p
o
in
ts
ac
c
u
r
atel
y
,
ca
u
s
i
n
g
th
e
m
id
d
le
ch
ar
ac
ter
(
nun
)
to
b
e
lo
s
t
o
r
in
co
r
r
ec
tl
y
m
er
g
ed
.
T
o
o
v
er
co
m
e
th
ese
li
m
itatio
n
s
an
d
e
n
h
a
n
ce
r
o
b
u
s
t
n
es
s
ag
a
in
s
t
t
h
e
h
ig
h
v
ar
iab
ilit
y
o
f
J
a
w
i
s
cr
i
p
t,
f
u
t
u
r
e
r
ef
i
n
e
m
en
ts
s
h
o
u
ld
f
o
cu
s
o
n
ad
ap
tiv
e
in
ter
s
ec
tio
n
f
ilter
i
n
g
,
s
k
eleto
n
b
r
an
ch
p
r
u
n
i
n
g
,
an
d
th
e
i
n
teg
r
at
io
n
o
f
lin
g
u
i
s
tic
r
u
le
s
to
b
etter
p
r
eser
v
e
ch
ar
ac
ter
in
te
g
r
it
y
.
Fig
u
r
e
9
.
T
h
e
r
esu
lt o
f
v
i
s
u
al
i
za
tio
n
o
f
ch
ar
ac
ter
s
e
g
m
en
tati
o
n
th
at
h
as lo
o
p
p
ar
t
ba
’
an
d
ha
’
(
a)
(
b
)
Fig
u
r
e
1
0
.
Step
o
f
s
eg
m
en
ta
ti
o
n
:
(
a)
r
esu
lts
o
f
ha
’
ch
ar
ac
ter
s
eg
m
en
tatio
n
a
n
d
(
b
)
r
esu
lts
o
f
ba
’
ch
ar
ac
ter
s
eg
m
e
n
tatio
n
3
.
6
.
E
v
a
lua
t
i
o
n
T
h
e
ev
alu
atio
n
s
tag
e
f
o
cu
s
ed
o
n
co
m
p
ar
i
n
g
t
h
e
s
y
s
te
m
’
s
ch
ar
ac
ter
s
eg
m
e
n
tatio
n
r
es
u
lt
s
ag
ai
n
s
t
a
m
an
u
all
y
v
er
i
f
ied
g
r
o
u
n
d
tr
u
th
(
GT
)
f
r
o
m
th
e
“
Kitab
S
y
air
P
er
ah
u
”
m
a
n
u
s
cr
ip
t.
Usi
n
g
a
s
a
m
p
le
o
f
1
0
m
an
u
s
cr
ip
t
lin
e
s
,
th
e
an
a
l
y
s
is
w
as
co
n
d
u
cted
o
n
a
p
er
-
li
n
e
(
r
as
m
)
b
asis
to
en
s
u
r
e
ac
cu
r
a
c
y
.
Fro
m
a
to
tal
o
f
2
6
9
g
r
o
u
n
d
-
tr
u
t
h
ch
ar
ac
ter
s
,
t
h
e
s
y
s
te
m
g
e
n
er
ated
2
3
6
s
eg
m
en
ts
,
o
f
w
h
ich
1
8
7
w
er
e
tr
u
e
p
o
s
itiv
es
(
T
P).
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.