T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
1
9
6
2
~
1
9
6
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i4
.
1
4
8
2
5
1962
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
Applica
tion o
f
ne
ura
l net
w
o
rk
m
et
ho
d f
o
r roa
d crac
k
dete
ction
Yus
lena
Sa
ri
,
P
ug
uh
B
u
di P
ra
k
o
s
o
,
Andrey
a
n Riz
k
y
B
a
s
k
a
ra
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
L
a
m
b
u
n
g
M
a
n
g
k
u
ra
t,
In
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
J
u
n
6
,
2019
R
ev
i
s
ed
Feb
2
7
,
2
0
2
0
A
cc
ep
ted
A
p
r
3
,
2
0
2
0
T
h
e
stu
d
y
p
re
se
n
ts
a
ro
a
d
p
a
v
e
m
e
n
t
c
ra
c
k
d
e
tec
ti
o
n
sy
ste
m
b
y
e
x
trac
ti
n
g
p
ictu
re
f
e
a
tu
re
s
th
e
n
c
las
sify
in
g
th
e
m
b
a
se
d
o
n
im
a
g
e
f
e
a
tu
re
s.
Th
e
a
p
p
li
e
d
f
e
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
is
t
h
e
g
ra
y
le
v
e
l
c
o
-
o
c
c
u
rre
n
c
e
m
a
tri
c
e
s
(GL
CM
).
T
h
is
m
e
th
o
d
e
m
p
lo
y
s
t
w
o
o
rd
e
r
m
e
a
su
re
m
e
n
ts.
T
h
e
f
irst
o
rd
e
r
u
ti
li
z
e
s
sta
ti
stica
l
c
a
lcu
latio
n
s
b
a
se
d
o
n
t
h
e
p
ix
e
l
v
a
lu
e
o
f
th
e
o
rig
in
a
l
ima
g
e
a
lo
n
e
,
su
c
h
a
s
v
a
rian
c
e
,
a
n
d
d
o
e
s
n
o
t
p
a
y
a
tt
e
n
ti
o
n
to
t
h
e
n
e
ig
h
b
o
rin
g
p
ix
e
l
re
latio
n
sh
i
p
.
I
n
th
e
se
c
o
n
d
o
rd
e
r,
th
e
re
latio
n
s
h
ip
b
e
tw
e
e
n
th
e
tw
o
p
ix
el
-
p
a
irs
o
f
th
e
o
rig
in
a
l
im
a
g
e
is
tak
e
n
in
to
a
c
c
o
u
n
t
.
In
s
p
ired
b
y
th
e
re
c
e
n
t
su
c
c
e
ss
in
im
p
le
m
e
n
ti
n
g
S
u
p
e
rv
ise
d
L
e
a
r
n
in
g
in
c
o
m
p
u
ter v
isio
n
,
th
e
a
p
p
li
e
d
m
e
th
o
d
f
o
r
c
las
si
f
ica
ti
o
n
is
a
rti
f
icia
l
n
e
u
r
a
l
n
e
tw
o
rk
(A
NN
).
Da
tas
e
ts,
w
h
ich
a
re
u
se
d
f
o
r
e
v
a
lu
a
ti
o
n
a
re
c
o
ll
e
c
ted
f
ro
m
l
o
w
-
c
o
st
s
m
a
rt
p
h
o
n
e
s.
T
h
e
re
su
lt
s
sh
o
w
th
a
t
f
e
a
tu
re
e
x
trac
ti
o
n
u
sin
g
GL
CM
c
a
n
p
ro
v
id
e
g
o
o
d
a
c
c
u
ra
c
y
th
a
t
is
e
q
u
a
l
to
9
0
%
.
K
ey
w
o
r
d
s
:
A
N
N
C
r
ac
k
d
etec
tio
n
Featu
r
e
ex
tr
ac
tio
n
GL
C
M
I
m
ag
e
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
:
P
u
g
u
h
B
u
d
i P
r
ak
o
s
o
,
Facu
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
,
U
n
i
v
e
r
s
itas
L
a
m
b
u
n
g
Ma
n
g
k
u
r
at,
I
n
d
o
n
esia
Natio
n
al
C
e
n
ter
f
o
r
Su
s
ta
in
ab
l
e
T
r
an
s
p
o
r
tatio
n
T
ec
h
n
o
lo
g
y
,
I
n
d
o
n
esia
.
E
m
ail:
p
u
g
u
h
.
p
r
ak
o
s
o
@
u
l
m
.
a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
E
v
alu
a
ti
ng
r
o
ad
q
u
alit
y
i
s
an
i
m
p
o
r
ta
n
t
ta
s
k
in
m
a
n
y
co
u
n
tr
i
es.
Fo
r
ex
a
m
p
le,
in
Fra
n
ce
,
n
at
io
n
al
r
o
ad
s
ar
e
ex
a
m
in
ed
e
v
er
y
th
r
ee
y
ea
r
s
to
esti
m
ate
r
ep
ar
atio
n
s
,
r
eq
u
ir
ed
co
n
s
tr
u
ctio
n
,
a
n
d
t
o
esti
m
a
te
q
u
al
it
y
.
T
h
ese
asp
ec
ts
ca
n
b
e
ca
lcu
la
ted
to
esti
m
ate
cr
ac
k
o
n
r
o
ad
p
av
e
m
en
t
s
u
r
f
ac
e
b
ased
o
n
co
m
p
lia
n
ce
w
ith
r
eg
u
lat
io
n
s
,
m
icr
o
te
x
t
u
r
e,
m
a
cr
o
tex
tu
r
e,
a
n
d
s
u
r
f
ac
e
d
eg
r
a
d
atio
n
.
I
n
B
an
j
ar
m
a
s
in
,
I
n
d
o
n
esia,
t
h
e
co
n
d
itio
n
o
f
s
u
b
g
r
ad
e,
w
h
ich
m
o
s
tl
y
co
n
s
is
t
s
o
f
p
ea
t
is
t
h
e
m
aj
o
r
o
r
ig
in
o
f
r
o
ad
cr
ac
k
in
g
s
.
C
o
n
s
id
er
i
n
g
th
e
v
ast
w
e
tlan
d
s
o
f
So
u
th
Kali
m
an
tan
r
ea
ch
i
n
g
382
,
2
7
2
h
a
is
a
m
aj
o
r
p
r
o
b
le
m
to
b
e
tac
k
le
d
.
A
ll
r
o
ad
ev
al
u
atio
n
in
s
p
ec
tio
n
s
i
n
I
n
d
o
n
esia
ar
e
d
o
n
e
m
a
n
u
al
l
y
,
w
h
er
ea
s
i
n
o
th
er
co
u
n
tr
ies
au
to
m
atic
s
y
s
te
m
s
h
av
e
b
ee
n
p
er
f
o
r
m
ed
w
it
h
n
o
n
-
i
n
v
a
s
i
v
e
tech
n
iq
u
e
s
s
u
ch
as i
m
a
g
e
p
r
o
ce
s
s
in
g
[1
-
3]
.
T
h
er
e
ar
e
s
ev
er
al
w
a
y
s
to
d
etec
t
r
o
ad
d
am
a
g
e
in
cl
u
d
in
g
an
al
y
zi
n
g
r
o
ad
co
n
d
itio
n
s
b
ased
o
n
i
m
ag
e
s
tak
en
o
n
t
h
e
r
o
ad
s
u
r
f
ac
e.
R
e
s
ea
r
ch
o
n
d
etec
tio
n
o
f
r
o
ad
s
u
r
f
ac
e
d
a
m
a
g
e
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
tech
n
iq
u
es
h
as
b
ee
n
ac
ti
v
el
y
ca
r
r
ied
o
u
t,
ac
h
iev
in
g
v
er
y
h
i
g
h
d
etec
tio
n
ac
cu
r
ac
y
.
Ma
n
y
s
t
u
d
ies
o
n
l
y
f
o
cu
s
o
n
d
etec
tin
g
th
e
p
r
ese
n
ce
o
r
ab
s
en
ce
o
f
d
a
m
ag
e.
Ho
w
e
v
er
,
i
n
a
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
,
w
h
e
n
r
o
ad
m
an
a
g
er
s
f
r
o
m
t
h
e
m
a
n
a
g
e
m
e
n
t
ag
e
n
c
y
n
ee
d
to
r
e
p
air
s
u
ch
d
a
m
a
g
e,
th
e
y
n
ee
d
to
clea
r
ly
u
n
d
er
s
ta
n
d
th
e
ty
p
e
o
f
d
a
m
a
g
e
to
tak
e
ef
f
ec
ti
v
e
ac
tio
n
.
I
n
ad
d
iti
o
n
,
in
m
an
y
p
r
ev
io
u
s
s
t
u
d
ies,
r
esear
ch
er
s
o
b
tain
ed
th
eir
o
w
n
d
ata
u
s
in
g
d
if
f
er
e
n
t
m
et
h
o
d
s
.
T
h
er
ef
o
r
e,
th
er
e
is
n
o
u
n
if
o
r
m
r
o
ad
d
am
a
g
e
d
ataset
av
ailab
le
o
p
en
ly
,
w
h
ich
ca
u
s
e
s
n
o
b
en
ch
m
ar
k
f
o
r
d
etec
tio
n
o
f
r
o
ad
d
am
a
g
e
[
4
,
5
]
.
T
h
i
s
r
e
s
ea
r
c
h
w
i
ll
p
r
o
p
o
s
e
a
n
in
t
el
l
ig
en
t
s
y
s
t
em
in
im
ag
e
p
r
o
c
e
s
s
in
g
t
o
d
e
t
e
c
t
c
r
a
ck
s
o
n
r
o
ad
s
u
r
f
a
c
es
.
T
o
e
x
am
in
e
r
o
a
d
i
n
f
r
as
t
r
u
ct
u
r
e
e
f
f
i
c
i
en
tly
,
es
p
e
c
i
al
ly
r
o
a
d
c
o
n
d
i
t
i
o
n
s
,
s
ev
e
r
al
m
e
th
o
d
s
u
s
i
n
g
l
a
s
e
r
t
e
ch
n
o
l
o
g
y
o
r
im
ag
e
p
r
o
c
es
s
i
n
g
h
av
e
b
e
e
n
s
tu
d
i
e
d
[6
-
9]
.
H
o
w
ev
e
r
,
th
e
t
ec
h
n
i
q
u
e
o
f
u
s
in
g
a
l
as
e
r
r
e
q
u
i
r
e
s
a
h
ig
h
c
o
s
t
[
1
0
,
1
1
]
.
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
A
p
p
lica
tio
n
o
f n
eu
r
a
l
n
etw
o
r
k
meth
o
d
fo
r
r
o
a
d
cra
ck
d
etec
tio
n
(
Yu
s
len
a
S
a
r
i
)
1963
F
u
th
e
r
m
o
r
e
,
at
a
l
o
w
e
r
c
o
s
t
,
th
e
r
e
w
e
r
e
s
ev
e
r
al
s
tu
d
i
es
u
s
in
g
c
o
m
p
u
t
e
r
v
is
i
o
n
a
p
p
r
o
a
c
h
f
o
r
s
o
l
v
in
g
th
is
p
r
o
b
l
em
i
n
1
1
y
e
a
r
s
[
1
2
-
17]
.
I
n
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
i
t
is
f
i
r
s
t
n
ec
e
s
s
ar
y
t
o
ex
t
r
a
c
t
f
e
atu
r
e
s
f
r
o
m
t
h
e
d
a
t
a
s
e
t
t
o
o
b
t
ain
q
u
an
t
it
a
t
iv
e
d
a
t
a
f
r
o
m
im
ag
e
d
a
t
a
,
th
en
t
h
e
n
ex
t
p
r
o
c
es
s
i
s
t
o
d
e
t
e
c
t
r
o
a
d
p
av
em
en
t
c
r
a
ck
s
.
R
es
e
a
r
ch
c
o
n
d
u
c
t
e
d
b
y
E
.
Z
al
a
m
a
,
G
.
J
a
im
e
,
a
n
d
R
.
M
e
d
in
a
[
4
]
d
em
o
n
s
t
r
at
e
d
th
a
t
u
s
in
g
B
an
k
G
a
b
o
r
f
i
lt
e
r
f
o
r
f
e
a
tu
r
e
e
x
t
r
a
c
ti
o
n
m
e
th
o
d
s
i
n
d
e
te
c
t
in
g
r
o
a
d
p
a
v
em
en
t
c
r
a
ck
s
,
th
e
a
c
cu
r
a
cy
o
b
t
a
i
n
e
d
is
9
0
%
.
T
h
e
B
a
n
k
G
a
b
o
r
f
i
lt
e
r
m
e
th
o
d
r
e
p
r
e
s
en
t
s
th
e
im
ag
e
i
n
a
o
n
e
-
a
n
g
l
e
o
r
i
en
t
a
ti
o
n
s
c
a
l
e
,
w
h
i
le
th
e
GL
C
M
r
e
p
r
es
en
ts
it
in
4
an
g
l
es
n
am
ely
0
0
,
4
5
0
,
90
0
,
135
0
,
s
o
th
at
th
e
e
x
tr
ac
tio
n
o
f
t
h
e
r
esu
l
tin
g
f
ea
tu
r
e
s
w
ill
r
ep
r
esen
t th
e
e
x
tr
ac
ted
i
m
a
g
e
m
o
r
e.
Fo
r
th
e
d
etec
tio
n
s
ta
g
e,
m
o
n
it
o
r
in
g
t
h
e
p
r
o
ce
s
s
is
co
n
s
id
er
ed
as
o
n
e
o
f
th
e
m
o
s
t
i
m
p
o
r
ta
n
t
tas
k
s
i
n
th
e
d
etec
tio
n
p
r
o
ce
s
s
.
Ma
n
y
r
esear
ch
er
s
u
til
ize
S
u
p
er
v
i
s
ed
L
ea
r
n
i
n
g
i
n
t
h
e
d
etec
tio
n
p
r
o
ce
s
s
,
esp
ec
iall
y
th
e
ANN
m
et
h
o
d
.
A
r
o
ad
d
etec
tio
n
s
tr
ateg
y
u
s
in
g
t
h
e
ANN
m
eth
o
d
f
o
r
th
e
clas
s
i
f
ier
w
a
s
i
n
tr
o
d
u
ce
d
b
y
M.
Mo
k
h
tar
za
d
e,
H.
E
b
ad
i,
a
n
d
M.
J
.
Vala
d
an
Z
o
ej
,
w
h
er
e
th
e
d
ataset
w
a
s
s
atell
ite
i
m
ag
er
y
[
5
]
.
R
esear
c
h
e
s
d
o
n
e
b
y
I
.
Kah
r
a
m
an
,
M.
Ka
m
il
T
u
r
an
,
an
d
I
.
R
ak
ip
Kar
as
also
ap
p
ly
ANN
in
d
etec
ti
n
g
r
o
ad
cr
ac
k
s
w
ith
r
es
u
lt
s
th
at
t
h
e
A
NN
m
et
h
o
d
is
ab
le
to
d
etec
t
r
o
ad
cr
ac
k
s
w
it
h
9
3
.
3
5
%
s
u
cc
es
s
[
1
8
]
.
R
ef
er
r
in
g
t
o
th
o
s
e
r
esear
ch
e
s
,
th
is
s
t
u
d
y
p
r
o
p
o
s
es
A
NN
m
e
th
o
d
in
d
etec
tin
g
r
o
ad
cr
ac
k
an
d
also
ap
p
lies
GL
C
M
to
e
x
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
i
m
a
g
es i
n
to
q
u
an
titati
v
e
d
ata.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
o
d
etec
t
r
o
a
d
s
u
r
f
ac
e
cr
ac
k
s
,
f
ea
t
u
r
es o
f
a
r
o
a
d
cr
ac
k
in
g
ar
e
r
eq
u
ir
ed
.
T
h
e
f
ea
tu
r
es a
r
e
s
h
a
p
e
f
ea
tu
r
e
an
d
tex
tu
r
e
f
ea
t
u
r
e,
w
h
er
e
th
e
s
e
f
ea
tu
r
e
s
ca
n
b
e
u
s
ed
to
d
is
tin
g
u
i
s
h
r
o
ad
co
n
d
itio
n
s
[
1
9
,
2
0
]
.
Fig
u
r
e
1
s
h
o
w
s
th
e
s
ta
g
es o
f
th
e
r
o
ad
s
u
r
f
ac
e
cr
ac
k
d
etec
tio
n
p
r
o
ce
s
s
.
Fu
r
t
h
er
ex
p
lan
atio
n
o
f
Fi
g
u
r
e
1
:
Fig
u
r
e
1
.
P
r
o
p
o
s
ed
r
o
ad
s
u
r
f
ac
e
cr
ac
k
d
etec
tio
n
s
ta
g
es
a.
R
o
ad
i
m
ag
e
d
ata
T
h
e
co
llected
d
ata
is
lab
elle
d
as
a
cr
ac
k
ed
r
o
ad
i
m
a
g
e.
R
o
ad
i
m
a
g
es
ar
e
tak
e
n
u
s
i
n
g
lo
w
-
co
s
t
s
m
ar
tp
h
o
n
e
ca
m
er
a,
w
h
er
e
t
h
e
d
is
ta
n
ce
b
et
w
ee
n
th
e
r
o
a
d
s
u
r
f
ac
e
a
n
d
t
h
e
ca
m
er
a
i
s
1
m
eter
in
f
r
o
n
t
o
f
th
e
ca
m
er
a.
Data
is
co
llected
f
r
o
m
s
o
m
e
r
o
ad
w
a
y
s
ec
tio
n
s
in
B
an
j
ar
m
as
in
,
w
h
ich
co
n
s
is
t
s
o
f
t
w
o
t
y
p
e
s
,
n
a
m
e
l
y
cr
ac
k
ed
r
o
ad
an
d
n
o
n
-
cr
ac
k
ed
r
o
ad
im
a
g
es.
Fi
g
u
r
e
2
p
r
esen
ts
a
n
ex
a
m
p
le
d
ata
o
f
r
o
ad
s
u
r
f
ac
e
w
it
h
cr
ac
k
s
.
b.
Data
p
re
-
p
r
o
ce
s
s
in
g
I
n
th
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
ta
g
e,
i
m
ag
e
d
ata
i
s
s
e
g
m
en
ted
f
ir
s
t.
Seg
m
en
tatio
n
i
s
t
h
e
p
r
o
ce
s
s
o
f
s
ep
ar
atin
g
o
b
j
ec
ts
co
n
tain
ed
in
an
i
m
a
g
e,
w
h
ic
h
ai
m
s
to
ea
s
e
th
e
p
r
o
ce
s
s
in
g
o
f
d
ig
ital
i
m
ag
e
o
n
ea
ch
o
b
j
ec
t.
T
h
en
th
r
esh
o
ld
i
n
g
,
w
h
ic
h
is
th
e
p
r
o
ce
s
s
o
f
ch
an
g
i
n
g
a
g
r
a
y
s
c
ale
i
m
ag
e
i
n
to
a
b
in
ar
y
o
r
b
lac
k
an
d
w
h
ite
i
m
a
g
e.
T
h
e
g
o
al
o
f
th
r
esh
o
ld
i
n
g
is
to
s
ee
clea
r
ly
w
h
ic
h
ar
ea
s
ar
e
in
clu
d
ed
in
th
e
o
b
j
ec
t
an
d
in
th
e
b
ac
k
g
r
o
u
n
d
o
f
an
i
m
a
g
e.
Nex
t
s
tep
is
m
o
r
p
h
o
lo
g
y
.
Mo
r
p
h
o
lo
g
y
is
a
d
ig
ital
i
m
ag
e
p
r
o
ce
s
s
i
n
g
tec
h
n
iq
u
e
wh
ich
u
s
e
s
s
h
ap
es
as
a
r
ef
er
en
ce
in
p
r
o
ce
s
s
i
n
g
t
h
e
i
m
a
g
e.
T
h
e
v
alu
e
o
f
e
ac
h
p
i
x
el
in
a
d
ig
ital
i
m
ag
e
i
s
o
b
tain
ed
f
r
o
m
t
h
e
r
esu
lts
o
f
a
co
m
p
ar
is
o
n
b
et
w
ee
n
th
e
co
r
r
esp
o
n
d
in
g
p
ix
e
ls
i
n
t
h
e
d
i
g
ital
i
m
a
g
e
a
n
d
th
e
ad
j
ac
en
t
p
ix
els.
Mo
r
p
h
o
lo
g
y
o
p
er
atio
n
s
d
ep
en
d
o
n
t
h
e
o
r
d
er
o
f
p
ix
el
s
a
n
d
d
o
n
o
t
p
a
y
a
tt
en
tio
n
to
th
e
v
al
u
e
o
f
p
i
x
els;
t
h
u
s
,
t
h
is
tech
n
iq
u
e
ca
n
b
e
u
s
ed
to
p
r
o
ce
s
s
b
in
ar
y
i
m
ag
e
s
an
d
g
r
a
y
s
ca
le
i
m
a
g
es.
c.
Featu
r
e
ex
tr
ac
tio
n
Featu
r
e
ex
tr
ac
tio
n
is
ap
p
lied
to
r
etr
iev
e
ass
ess
m
e
n
t
in
f
o
r
m
a
tio
n
f
r
o
m
t
h
e
an
al
y
s
is
an
d
ca
l
cu
latio
n
s
p
er
f
o
r
m
ed
o
n
d
i
g
ital
i
m
a
g
es
[
2
1
,
2
2
]
.
T
h
e
r
esu
lts
o
f
th
i
s
e
x
tr
ac
tio
n
h
a
v
e
a
s
i
g
n
if
ican
t
e
f
f
ec
t
o
n
t
h
e
r
es
u
lt
s
o
f
th
e
clas
s
if
icatio
n
la
ter
.
T
h
e
f
ea
tu
r
e
ex
tr
ac
t
io
n
p
r
o
ce
s
s
i
s
ca
r
r
ied
o
u
t
u
s
in
g
Ma
tlab
s
o
f
t
w
ar
e
,
w
h
er
e
t
h
e
G
L
C
M
m
et
h
o
d
is
ap
p
lied
in
th
e
f
e
atu
r
e
ex
tr
ac
tio
n
o
f
r
o
ad
p
av
e
m
en
t
cr
ac
k
d
etec
t
io
n
.
G
L
C
M
u
til
izes
te
x
t
u
r
e
ca
lcu
latio
n
s
in
t
h
e
s
ec
o
n
d
o
r
d
e
r
.
Me
asu
r
e
m
en
t
o
f
tex
t
u
r
es
in
t
h
e
f
ir
s
t
o
r
d
er
ass
ig
n
s
s
tati
s
tical
ca
lcu
latio
n
s
b
ased
o
n
th
e
p
i
x
el
v
al
u
e
o
f
t
h
e
o
r
ig
in
al
i
m
a
g
e,
s
u
ch
a
s
v
ar
ian
ce
,
an
d
d
o
es
n
o
t
p
a
y
at
ten
t
io
n
to
n
ei
g
h
b
o
r
in
g
p
ix
e
l
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.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
9
6
2
-
1
9
6
7
1964
r
elatio
n
s
h
ip
s
.
I
n
th
e
s
ec
o
n
d
o
r
d
er
,
th
e
r
elatio
n
s
h
ip
b
et
w
ee
n
p
air
s
o
f
t
w
o
o
r
ig
in
al
i
m
a
g
e
i
m
ag
e
s
is
tak
e
n
in
to
ac
co
u
n
t
[
2
3
]
.
Fo
r
ex
a
m
p
le,
f
(
x
,
y
)
is
a
n
i
m
ag
e
o
f
s
ize
N
x
an
d
N
y
t
h
at
h
as
p
ix
el
s
w
it
h
t
h
e
p
o
s
s
ib
ilit
y
o
f
L
lev
el
s
an
d
⃗
⃗
is
a
s
p
atial
o
f
f
s
et
d
ir
ec
tio
n
v
ec
to
r
.
(
,
)
is
d
ef
in
ed
as
th
e
n
u
m
b
er
o
f
p
ix
el
s
w
it
h
∈
1
,
.
.
,
th
at
o
cc
u
r
s
in
o
f
f
s
et
⃗
⃗
to
th
e
p
ix
els
with
v
a
lu
e
s
∈
1
,
.
.
,
,
w
h
ic
h
ca
n
b
e
s
tate
d
in
th
e
(
1
)
[
2
4
]
.
(
,
)
=
#
{
(
1
,
1
)
,
(
2
,
2
)
∈
(
,
)
×
(
,
)
|
(
1
,
1
)
=
=
(
2
−
1
,
2
−
1
)
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
⃗
}
(
1
)
I
n
th
is
ca
s
e,
o
f
f
s
et
⃗
⃗
ca
n
b
e
an
an
g
le
an
d
/o
r
d
is
tan
ce
.
Fo
r
e
x
a
m
p
le,
th
e
F
i
g
u
r
e
3
s
h
o
w
s
t
h
e
f
o
u
r
d
ir
ec
tio
n
s
f
o
r
GL
C
M.
Fig
u
r
e
2
.
R
o
ad
s
u
r
f
ac
e
cr
ac
k
i
n
g
i
m
a
g
e
Fig
u
r
e
3
.
E
x
a
m
p
le
d
ir
ec
tio
n
s
f
o
r
GL
C
M
w
it
h
a
n
g
le
s
0
0
,
4
5
0
,
9
0
0
,
d
an
1
3
5
0
d.
R
o
ad
d
etec
tio
n
R
o
a
d
c
r
a
ck
d
et
e
c
ti
o
n
c
an
b
e
d
o
n
e
af
te
r
th
e
ex
t
r
a
c
t
i
o
n
o
f
r
o
a
d
im
ag
e
f
e
a
tu
r
es
.
T
h
e
d
at
a
w
i
l
l
b
e
d
i
v
i
d
e
d
i
n
t
o
tw
o
p
a
r
t
s
,
n
am
ely
t
r
ain
in
g
d
a
t
a
an
d
te
s
tin
g
d
a
t
a
.
A
f
t
e
r
th
a
t
th
e
cl
as
s
if
i
c
a
ti
o
n
o
f
c
r
a
ck
r
o
a
d
s
an
d
g
o
o
d
r
o
a
d
s
w
il
l
b
e
ca
r
r
i
e
d
o
u
t u
s
in
g
a
m
ac
h
in
e
l
e
a
r
n
in
g
a
p
p
r
o
a
c
h
w
h
i
ch
is
a
r
tif
i
ci
a
l
n
eu
r
al
n
etw
o
r
k
(
A
NN
)
m
e
th
o
d
.
A
N
N
is
a
p
r
o
c
e
s
s
o
r
th
a
t
c
a
r
r
ie
s
o
u
t
l
a
r
g
e
-
s
c
a
l
e
d
is
t
r
i
b
u
ti
o
n
,
w
h
i
ch
h
as
a
n
at
u
r
a
l
t
en
d
en
cy
t
o
s
t
o
r
e
a
r
e
c
o
g
n
i
ti
o
n
th
at
h
as
b
e
e
n
ex
p
e
r
i
en
ce
d
,
in
o
t
h
e
r
w
o
r
d
s
A
N
N
h
as
th
e
a
b
i
l
ity
t
o
b
e
a
b
l
e
t
o
d
o
l
e
a
r
n
in
g
an
d
d
e
t
e
c
ti
o
n
o
f
an
o
b
je
c
t
[
2
5
]
.
e.
R
es
u
lt
ev
a
lu
at
io
n
an
d
v
alid
ati
o
n
In
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
e
m
e
n
t
u
s
i
n
g
co
n
f
u
s
io
n
m
atr
i
x
is
u
s
ed
to
m
ea
s
u
r
e
h
o
w
w
el
l
th
e
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
A
NN
m
et
h
o
d
is
to
r
ec
o
g
n
ize
tu
p
les f
r
o
m
d
if
f
er
e
n
t
clas
s
es.
T
P
an
d
T
N
p
r
o
v
id
e
in
f
o
r
m
atio
n
w
h
e
n
th
e
d
etec
tio
n
r
esu
lt
s
ar
e
tr
u
e,
w
h
ile
FP
an
d
FN
tell
w
h
e
n
th
e
v
a
lu
e
s
ar
e
f
alse
[
4
,
2
6
]
.
T
h
en
af
ter
th
e
co
n
f
u
s
io
n
m
atr
i
x
o
b
tain
ed
,
A
cc
u
r
ac
y
,
P
r
ec
is
io
n
a
n
d
R
ec
a
ll
v
al
u
e
ca
n
b
e
ca
lc
u
lated
.
T
h
e
A
cc
u
r
ac
y
v
alu
e
is
o
b
tain
ed
b
y
(
2
)
.
T
h
e
Pre
cisi
o
n
v
alu
e
i
s
o
b
tain
ed
b
y
(
3
)
.
T
h
e
R
ec
all
v
a
lu
e
i
s
o
b
tain
ed
b
y
(
4
)
[
2
7
,
2
8
]
:
=
+
+
+
+
100%
(
2
)
=
+
100%
(
3
)
=
+
100%
(
4
)
w
h
er
e:
T
P
is
tr
u
e
p
o
s
itiv
e
,
w
h
ic
h
i
s
th
e
a
m
o
u
n
t o
f
p
o
s
iti
v
e
d
ata
th
at
is
p
r
o
p
er
ly
clas
s
if
ied
b
y
t
h
e
s
y
s
te
m
.
T
N
is
tr
u
e
n
eg
ati
v
e,
w
h
ich
i
s
t
h
e
a
m
o
u
n
t o
f
n
e
g
ati
v
e
d
ata
th
at
is
p
r
o
p
er
ly
clas
s
if
ied
b
y
t
h
e
s
y
s
te
m
.
FN is
f
alse
n
eg
at
iv
e
,
w
h
ic
h
is
th
e
a
m
o
u
n
t o
f
n
e
g
ati
v
e
d
ata
b
u
t c
las
s
i
f
ied
in
co
r
r
ec
tl
y
b
y
t
h
e
s
y
s
te
m
.
FP
is
f
alse p
o
s
iti
v
e
,
w
h
ich
i
s
t
h
e
a
m
o
u
n
t o
f
p
o
s
itiv
e
d
ata
b
u
t
is
class
i
f
ied
i
n
co
r
r
e
ctl
y
b
y
t
h
e
s
y
s
te
m
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
3.
1.
D
a
t
a
p
ro
ce
s
s
ing
I
m
ag
e
d
a
t
a
w
il
l
b
e
c
r
o
p
p
e
d
f
i
r
s
t
t
o
u
n
if
o
r
m
a
l
l
d
a
t
a
.
T
h
e
am
o
u
n
t
o
f
d
a
t
a
is
1
0
0
,
w
h
i
ch
i
s
l
a
b
e
l
e
d
c
r
a
ck
a
n
d
n
o
_
c
r
a
c
k
.
T
h
e
d
a
ta
t
o
b
e
p
r
o
c
e
s
s
e
d
is
a
d
a
t
as
e
t
o
f
2
5
6
x
1
0
0
p
i
x
e
ls
.
T
h
e
n
f
ea
tu
r
e
ex
t
r
a
ct
i
o
n
w
il
l
b
e
p
e
r
f
o
r
m
e
d
to
a
l
l
im
ag
es
.
E
x
am
p
l
es
o
f
d
a
t
as
e
t
a
r
e
d
e
p
ic
t
e
d
in
F
ig
u
r
e
4
.
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
A
p
p
lica
tio
n
o
f n
eu
r
a
l
n
etw
o
r
k
meth
o
d
fo
r
r
o
a
d
cra
ck
d
etec
tio
n
(
Yu
s
len
a
S
a
r
i
)
1965
(
a)
(
b
)
Fig
u
r
e
4
.
E
x
a
m
p
le
o
f
d
ataset
w
it
h
(
a)
cr
ac
k
an
d
(
b
)
n
o
cr
ac
k
3.
2.
F
e
a
t
ure
e
x
t
ra
ct
io
n
Featu
r
e
e
x
tr
ac
tio
n
u
til
izes
t
h
e
g
r
a
y
le
v
el
co
-
o
cc
u
r
r
en
ce
m
atr
i
x
(
G
L
C
M)
,
w
h
ic
h
ap
p
lies
f
i
v
e
q
u
an
tit
ies,
n
a
m
e
l
y
a
n
g
u
lar
s
ec
o
n
d
m
o
m
e
n
t
(
ASM)
,
co
n
tr
ast,
i
n
v
er
s
e
d
if
f
er
e
n
t
m
o
m
e
n
t
(
I
DM
)
,
en
tr
o
p
i,
an
d
co
r
r
elatio
n
[
2
9
-
31]
.
E
x
a
m
p
les
o
f
th
e
r
es
u
lts
f
r
o
m
f
ea
t
u
r
e
ex
tr
ac
tio
n
ca
n
b
e
s
ee
n
i
n
T
ab
le
1
.
T
h
e
v
alu
e
s
f
r
o
m
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
w
ill b
e
t
h
e
in
p
u
t p
ar
a
m
eter
s
i
n
d
etec
ti
n
g
r
o
ad
cr
ac
k
s
.
T
ab
le
1
.
Data
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
r
esu
l
t
No
L
a
b
e
l
A
S
M
C
o
n
t
r
a
st
I
D
M
En
t
r
o
p
y
C
o
r
r
e
l
a
t
i
o
n
1
c
r
a
c
k
3
,
3
7
E+
1
1
1
,
7
8
E+
1
7
0
.
1
2
3
8
6
8
9
1
6
8
6
0
6
7
6
8
.
5
1
5
.
1
7
7
.
2
2
1
.
6
1
5
.
9
8
0
9
,
1
0
E+
1
1
2
c
r
a
c
k
3
,
5
4
E+
1
1
1
,
4
6
E+
1
7
0
.
1
4
8
8
2
3
3
0
9
9
9
1
5
9
5
8
.
4
1
9
.
9
8
5
.
8
9
4
.
6
0
5
.
6
4
0
9
,
1
1
E+
1
1
3
n
o
_
c
r
a
c
k
4
,
2
2
E+
1
1
1
,
5
1
E+
1
7
0
.
1
3
3
6
5
2
3
3
1
5
1
3
8
2
8
8
.
2
3
5
.
8
9
4
.
3
2
9
.
9
8
1
.
7
7
0
0
.
0
0
1
3
7
6
0
6
7
1
6
9
5
6
3
4
n
o
_
c
r
a
c
k
8
,
0
6
E+
1
1
1
,
2
5
E+
1
7
0
.
1
7
0
2
5
4
6
5
1
9
3
2
0
8
8
7
.
7
7
3
.
6
6
1
.
5
1
0
.
4
9
9
.
4
8
0
0
.
0
0
1
5
3
8
1
4
2
4
1
3
4
5
1
5
c
r
a
c
k
2
,
3
7
E+
1
1
4
,
3
7
E+
1
7
0
.
0
8
4
8
7
9
1
7
8
5
8
0
0
0
5
8
.
8
5
4
.
0
8
3
.
8
5
0
.
6
8
4
.
6
9
0
7
,
7
8
E+
1
1
3.
4.
Resul
t
a
nd
e
v
a
lua
t
io
n
B
ef
o
r
e
tr
ain
in
g
th
e
d
ata,
th
e
l
ea
r
n
in
g
r
ate
is
s
et
0
.
0
1
w
it
h
m
o
m
e
n
t
u
m
0
.
9
.
T
h
e
n
et
w
o
r
k
ar
ch
itect
u
r
e
m
o
d
el
w
h
ic
h
is
o
b
tain
ed
f
r
o
m
th
e
tr
ain
i
n
g
d
ataset
p
r
o
d
u
ce
s
a
n
et
w
o
r
k
ar
ch
itect
u
r
e
w
it
h
5
in
p
u
ts
,
n
a
m
el
y
:
ASM,
c
o
n
tr
ast,
I
DM
,
en
tr
o
p
y
,
co
r
r
e
latio
n
;
as
w
e
ll
a
s
w
i
th
5
h
id
d
en
la
y
er
s
.
T
h
e
n
et
w
o
r
k
ar
ch
itect
u
r
e
is
s
h
o
wn
in
Fi
g
u
r
e
5
.
A
s
f
o
r
th
e
w
ei
g
h
ts
o
f
h
id
d
en
la
y
er
ar
e
s
h
o
w
n
in
T
ab
le
2
.
T
h
ese
w
ei
g
h
ts
w
e
r
e
g
en
er
ated
f
r
o
m
th
e
tr
ain
i
n
g
d
ata
r
esu
lts
o
f
5
0
0
ep
o
ch
r
e
p
etitio
n
s
.
T
h
e
n
et
w
o
r
k
ar
ch
itectu
r
e
m
o
d
el
b
r
in
g
s
ab
o
u
t
t
w
o
g
r
o
u
p
s
o
f
o
u
tp
u
t,
n
a
m
el
y
cr
ac
k
a
n
d
n
o
cr
ac
k
.
T
ab
le
3
s
h
o
w
s
t
h
e
r
es
u
lti
n
g
w
ei
g
h
t
o
u
tp
u
t
s
,
m
ea
n
wh
ile
T
ab
le
4
ex
h
ib
it
s
th
e
as
s
ess
m
e
n
t r
es
u
lts
.
Fig
u
r
e
5
.
T
h
e
b
est n
et
w
o
r
k
ar
c
h
itect
u
r
e
f
r
o
m
tr
ai
n
i
n
g
d
atase
t
s
T
ab
l
e
2
.
T
h
e
w
e
ig
h
t o
f
h
id
d
en
la
y
er
H
i
d
d
e
n
L
a
y
e
r
T
h
r
e
sh
o
l
d
A
S
M
C
o
n
t
r
a
st
I
D
M
En
t
r
o
p
y
C
o
r
r
e
l
a
t
i
o
n
1
-
0
.
0
8
8
0
.
0
6
4
0
.
0
0
2
-
0
.
1
4
9
-
0
.
1
3
9
0
.
0
7
2
2
-
0
.
7
5
6
0
.
1
3
2
0
.
1
3
2
-
0
.
4
7
0
-
1
.
5
4
1
-
2
.
2
3
2
3
0
.
5
6
9
-
0
.
6
3
8
0
.
0
8
5
0
.
3
9
4
1
.
3
0
7
1
.
6
9
6
4
-
0
.
2
1
4
0
.
2
8
9
-
0
.
0
9
3
-
0
.
5
6
3
-
1
.
0
1
1
-
0
.
6
0
9
5
0
.
7
0
8
-
0
.
8
4
7
0
.
0
3
0
0
.
2
9
8
1
.
4
9
6
2
.
6
2
7
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.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
9
6
2
-
1
9
6
7
1966
T
ab
l
e
3
.
T
h
e
w
e
ig
h
t o
u
tp
u
t
O
u
t
p
u
t
L
a
y
e
r
N
o
d
e
1
N
o
d
e
2
N
o
d
e
3
N
o
d
e
4
N
o
d
e
5
T
h
r
e
sh
o
l
d
C
r
a
c
k
-
0
.
2
8
0
-
2
.
1
7
7
1
.
3
2
2
-
1
.
0
5
6
2
.
0
5
7
-
0
.
6
0
2
N
o
_
c
r
a
c
k
0
.
2
7
4
2
.
1
5
8
-
1
.
2
9
9
1
.
0
9
8
-
2
.
0
7
2
0
.
5
8
8
T
ab
l
e
4
.
T
h
e
A
s
s
e
s
s
m
e
n
t
r
es
u
l
ts
M
e
a
su
r
e
me
n
t
R
e
su
l
t
s
A
c
c
u
r
a
c
y
9
0
.
0
0
%
P
r
e
c
i
si
o
n
9
3
.
5
0
%
R
e
c
a
l
l
8
7
.
5
0
%
T
h
e
ass
ess
m
en
t
r
es
u
lts
i
n
T
a
b
le
4
d
em
o
n
s
tr
ate
th
at
A
NN
B
ac
k
p
r
o
p
ag
atio
n
m
et
h
o
d
r
e
ac
h
es
9
0
%
ac
cu
r
ac
y
f
o
r
th
e
d
etec
tio
n
o
f
r
o
ad
d
am
ag
e,
w
h
ic
h
ca
n
b
e
ca
t
eg
o
r
ized
as
h
ig
h
ac
c
u
r
ac
y
le
v
e
l.
I
t
ca
n
also
b
e
s
ee
n
th
at
th
e
p
r
ec
is
io
n
v
alu
e
i
s
h
i
g
h
er
th
an
t
h
e
ac
cu
r
ac
y
v
alu
e,
n
a
m
e
l
y
9
3
.
5
0
%.
Me
an
w
h
ile,
th
e
r
ec
all
v
alu
e
h
as
th
e
lo
w
est
v
al
u
e,
w
h
ic
h
is
8
7
.
5
0
%.
T
h
e
h
ig
h
est
ac
c
u
r
ac
y
i
s
o
b
tain
ed
w
i
th
a
v
alu
e
o
f
9
0
%.
T
h
is
is
b
ec
au
s
e
th
e
d
ata
is
w
ell
p
r
ep
ar
ed
,
an
d
th
e
d
ata
u
s
ed
is
d
ata
f
r
o
m
cr
ac
k
an
d
n
o
n
cr
ac
k
d
ata
im
a
g
es
(
g
o
o
d
asp
h
alt)
.
No
o
th
er
r
o
ad
d
am
a
g
e
d
ata
is
p
r
esen
ted
.
T
h
e
v
alu
e
o
f
p
r
ec
is
io
n
is
9
3
.
5
0
%
w
h
ic
h
i
s
h
i
g
h
er
th
a
n
th
e
ac
cu
r
ac
y
.
T
h
is
m
ea
n
s
th
at
t
h
e
ac
cu
r
ac
y
o
f
th
e
d
etec
tio
n
ar
ea
is
h
ig
h
er
th
an
th
e
ac
c
u
r
ac
y
o
f
t
h
e
d
etec
tio
n
.
T
h
e
r
ec
all
r
esu
lt
is
8
7
.
5
0
%.
th
is
r
esu
l
t
is
ca
te
g
o
r
ized
as
g
o
o
d
.
T
h
is
r
esu
lt
o
b
tain
ed
f
r
o
m
to
tal
co
r
r
ec
t
d
ata
d
etec
tio
n
ea
ch
clas
s
(
cr
ac
k
an
d
n
o
n
cr
ac
k
d
ata)
d
iv
id
ed
b
y
all
d
ata
class
i
f
ied
co
r
r
ec
tl
y
.
4.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
o
f
r
o
a
d
cr
ac
k
d
etec
tio
n
is
ab
le
to
id
en
ti
f
y
cr
ac
k
s
w
it
h
a
n
a
cc
u
r
ac
y
o
f
9
0
%.
T
h
e
i
m
ag
e
p
r
o
ce
s
s
i
n
g
tech
n
iq
u
e
ap
p
lies
f
ea
t
u
r
e
e
x
tr
ac
tio
n
u
s
i
n
g
t
h
e
G
L
C
M
m
et
h
o
d
.
T
h
is
m
eth
o
d
p
r
o
d
u
ce
s
i
m
a
g
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
f
r
o
m
f
o
u
r
a
n
g
le
s
n
a
m
el
y
0
0
,
4
5
0
,
9
0
0
,
an
d
1
3
5
0
.
T
h
e
ex
p
er
i
m
en
tal
r
esu
lt
s
d
e
m
o
n
s
tr
ate
th
at
a
s
et
o
f
4
a
n
g
le
s
,
co
n
s
is
t
in
g
o
f
p
r
o
p
er
ties
d
er
iv
ed
f
r
o
m
p
r
o
j
ec
tiv
e
in
teg
r
al
s
an
d
cr
a
ck
o
b
j
ec
t
p
r
o
p
e
r
ties
co
o
p
er
ates
to
ac
h
iev
e
th
e
m
o
s
t
ac
cu
r
ate
p
r
ed
ictio
n
.
I
n
ad
d
itio
n
,
th
e
in
cl
u
s
io
n
o
f
ch
ar
ac
t
er
is
tics
o
f
cr
ac
k
ed
o
b
j
ec
ts
s
u
c
h
as A
SM,
c
o
n
tr
ast
,
I
DM
,
en
tr
o
p
y
a
n
d
co
r
r
elatio
n
h
as
b
ee
n
p
r
o
v
en
to
p
r
o
v
id
e
m
o
r
e
in
f
o
r
m
atio
n
f
o
r
class
i
f
icatio
n
.
T
h
is
f
ac
t
is
e
x
h
ib
ited
th
r
o
u
g
h
t
h
e
g
o
o
d
ex
p
er
i
m
en
tal
r
esu
l
ts
.
A
NN
i
s
a
s
u
p
er
v
is
ed
lear
n
i
n
g
ap
p
r
o
ac
h
th
at
h
as
b
ee
n
i
m
p
le
m
en
ted
to
s
t
u
d
y
th
e
m
ap
p
in
g
f
u
n
ctio
n
b
et
w
ee
n
t
h
e
i
m
ag
e
i
n
p
u
t
an
d
o
u
tp
u
t
f
ea
tu
r
e
s
o
f
cr
ac
k
an
d
n
o
cr
ac
k
clas
s
i
f
ic
atio
n
s
.
B
ased
o
n
th
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
,
A
NN
ca
n
b
e
co
n
cl
u
d
ed
as
a
co
m
p
ete
n
t
class
i
f
icatio
n
m
e
th
o
d
.
T
h
u
s
,
t
h
e
ap
p
licatio
n
o
f
A
NN
i
n
teg
r
ate
d
w
it
h
G
L
C
M
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
e
th
o
d
is
h
ig
h
l
y
r
ec
o
m
m
e
n
d
ed
f
o
r
th
e
d
etec
tio
n
o
f
r
o
ad
p
av
em
e
n
t
cr
ac
k
s
.
Fu
tu
r
e
w
o
r
k
s
h
o
u
ld
also
in
v
e
s
ti
g
ate
th
e
ap
p
licatio
n
s
o
f
d
if
f
er
e
n
t
alg
o
r
it
h
m
s
an
d
o
th
er
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
s
in
o
r
d
er
to
im
p
r
o
v
e
p
r
ed
ictio
n
ac
cu
r
ac
y
.
L
a
s
t
b
u
t
n
o
t
least,
it
is
n
ec
ess
ar
y
to
co
llect
m
o
r
e
i
m
ag
e
d
atasets
to
im
p
r
o
v
e
th
e
ab
ilit
y
o
f
th
e
cu
r
r
en
t
r
o
ad
p
av
e
m
e
n
t
cr
ac
k
d
etec
tio
n
m
o
d
el.
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
is
p
ap
er
is
s
u
p
p
o
r
ted
b
y
US
A
I
D
t
h
r
o
u
g
h
S
u
s
tain
ab
le
Hig
h
er
E
d
u
ca
tio
n
R
esear
c
h
A
l
lian
ce
s
(
SHE
R
A
)
P
r
o
g
r
a
m
C
e
n
tr
e
f
o
r
C
o
llab
o
r
ativ
e
(
C
C
R
)
N
atio
n
al
C
e
n
ter
f
o
r
Su
s
tain
a
b
le
T
r
an
s
p
o
r
tatio
n
T
ec
h
n
o
lo
g
y
(
NC
ST
T
)
w
ith
Gr
an
t N
o
.
I
I
E
0
0
0
0
0
0
7
8
-
I
T
B
-
1.
RE
F
E
R
E
NC
E
S
[1
]
T
.
H
.
N
g
u
y
e
n
,
A
.
Z
h
u
k
o
v
,
a
n
d
T
.
L
.
N
g
u
y
e
n
,
“
O
n
r
o
a
d
d
e
f
e
c
t
s
d
e
t
e
c
t
i
o
n
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
,
”
S
u
p
p
l
e
m
e
n
t
a
r
y
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
F
i
f
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
n
a
l
y
s
i
s
o
f
I
m
a
g
e
s
,
S
o
c
i
a
l
N
e
t
w
o
r
k
s
a
n
d
T
e
x
t
s
,
p
p
.
2
6
4
–
275
,
2
0
1
6
.
[2
]
A
.
Ra
g
n
o
li
,
M
.
R.
De
Blas
ii
s,
a
n
d
A
.
Di
Be
n
e
d
e
tt
o
,
“
P
a
v
e
m
e
n
t
Distre
ss
De
tec
ti
o
n
M
e
th
o
d
s :
A
Re
v
ie
w
,
”
In
fra
stru
c
t
u
re
s
,
v
o
l.
3
,
n
o
.
5
8
,
p
p
.
1
–
1
9
,
2
0
1
8
.
[3
]
T
.
B.
J.
C
o
e
n
e
n
a
n
d
A
.
G
o
lro
o
,
“
A
re
v
ie
w
o
n
a
u
to
m
a
ted
p
a
v
e
m
e
n
t
d
istres
s
d
e
tec
ti
o
n
m
e
th
o
d
s,”
C
o
g
e
n
t
E
n
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
1
,
2
0
1
7
.
[4
]
E.
Zala
m
a
,
G
.
J
a
i
m
e
,
a
n
d
R.
M
e
d
in
a
,
“
Ro
a
d
Cra
c
k
De
tec
ti
o
n
Us
in
g
V
isu
a
l
F
e
a
t
u
re
s
Ex
trac
ted
b
y
G
a
b
o
r
F
il
ters
,
”
Co
mp
u
t
er
-
Ai
d
e
d
Civil
a
n
d
I
n
fra
st
ru
c
tu
re
En
g
in
e
e
rin
g
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
3
4
2
–
3
5
8
,
2
0
1
4
.
[5
]
M
.
M
o
k
h
tarz
a
d
e
,
H.
Eb
a
d
i,
a
n
d
M
.
J.
V
a
lad
a
n
Z
o
e
j,
“
Op
ti
m
iza
ti
o
n
o
f
ro
a
d
d
e
tec
ti
o
n
f
ro
m
h
ig
h
-
re
s
o
lu
ti
o
n
sa
telli
t
e
im
a
g
e
s
u
sin
g
tex
tu
re
p
a
ra
m
e
ter
s i
n
n
e
u
ra
l
n
e
tw
o
rk
c
las
si
f
iers
,
”
Ca
n
a
d
ia
n
J
o
u
r
n
a
l
o
f
Rem
o
te S
e
n
si
n
g
,
v
o
l.
3
3
,
n
o
.
6
,
p
p
.
4
8
1
–
4
9
1
,
2
0
0
7
.
[6
]
Z.
F
a
n
,
S
.
M
e
m
b
e
r,
Y.
W
u
,
J.
L
u
,
a
n
d
W
.
L
i,
“
Ba
se
d
o
n
S
tru
c
tu
re
d
P
re
d
ictio
n
w
it
h
t
h
e
C
o
n
v
o
lu
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
,
”
a
rX
iv
:1
8
0
2
.
0
2
2
0
8
,
p
p
.
1
–
9
,
2
0
1
8
.
[7
]
K.
Ku
b
o
,
“
P
a
v
e
m
e
n
t
M
a
in
ten
a
n
c
e
in
Ja
p
a
n
,
”
R
o
a
d
C
o
n
fer
e
n
c
e
2
0
1
7
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
,
2
0
1
7
.
[8
]
Cro
ss
-
m
in
isteria
l
S
trate
g
ic
In
n
o
v
a
ti
o
n
P
ro
m
o
ti
o
n
P
ro
g
ra
m
,
“
In
f
ra
stru
c
tu
re
M
a
in
ten
a
n
c
e
,
Re
n
o
v
a
ti
o
n
a
n
d
M
a
n
a
g
e
m
e
n
t
-
In
tro
d
u
c
t
io
n
;
T
h
e
R&
D
P
r
o
jec
t
o
f
In
f
ra
stru
c
tu
re
,
”
2
0
1
7
.
[
On
l
i
n
e
]
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
jst.
g
o
.
jp
/sip
/
d
l/
k
0
7
/p
a
m
p
h
let_
2
0
1
7
_
e
n
.
p
d
f
[9
]
S
.
C.
Ra
d
o
p
o
u
lo
u
a
n
d
I.
Bril
a
k
is,
“
I
m
p
ro
v
in
g
ro
a
d
a
ss
e
t
c
o
n
d
i
ti
o
n
m
o
n
it
o
rin
g
,
”
T
r
a
n
sp
o
rta
t
io
n
Res
e
a
rc
h
Pro
c
e
d
i
a
,
v
o
l.
1
4
,
p
p
.
3
0
0
4
–
3
0
1
2
,
2
0
1
6
.
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
A
p
p
lica
tio
n
o
f n
eu
r
a
l
n
etw
o
r
k
meth
o
d
fo
r
r
o
a
d
cra
ck
d
etec
tio
n
(
Yu
s
len
a
S
a
r
i
)
1967
[1
0
]
C.
C.
G
u
,
H.
Ch
e
n
g
,
K.
J.
W
u
,
L
.
J
.
Zh
a
n
g
,
a
n
d
X
.
P
.
G
u
a
n
,
“
A
Hig
h
P
re
c
isio
n
L
a
se
r
-
Ba
s
e
d
A
u
to
f
o
c
u
s
M
e
th
o
d
Us
in
g
Bias
e
d
Im
a
g
e
P
lan
e
f
o
r
M
icro
sc
o
p
y
,
”
J
o
u
rn
a
l
o
f
S
e
n
so
rs
,
v
o
l
.
2
0
1
8
,
2
0
1
8
.
[1
1
]
H.
M
.
S
h
e
h
a
ta,
Y.
S
.
M
o
h
a
m
e
d
,
M
.
A
b
d
e
ll
a
ti
f
,
a
n
d
T
.
H.
A
wa
d
,
“
De
p
th
e
stim
a
ti
o
n
o
f
ste
e
l
c
ra
c
k
s
u
sin
g
las
e
r
a
n
d
im
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s,”
Al
e
x
a
n
d
ria
En
g
in
e
e
rin
g
J
o
u
rn
a
l
,
v
o
l.
5
7
,
n
o
.
4
,
p
p
.
2
7
1
3
–
2
7
1
8
,
2
0
1
8
.
[1
2
]
S
.
A
g
ra
wa
l
a
n
d
P
.
Na
tu
,
“
S
e
g
m
e
n
tatio
n
o
f
M
o
v
in
g
Ob
jec
ts
u
sin
g
Nu
m
e
ro
u
s
Ba
c
k
g
ro
u
n
d
S
u
b
trac
ti
o
n
M
e
t
h
o
d
s
f
o
r
S
u
rv
e
il
lan
c
e
A
p
p
li
c
a
ti
o
n
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Exp
l
o
rin
g
En
g
i
n
e
e
rin
g
(
IJ
IT
EE
)
,
v
o
l.
9
,
n
o
.
3
,
p
p
.
2
5
5
3
–
2
5
6
3
,
2
0
2
0
.
[1
3
]
L
.
Zh
a
n
g
,
F
.
Ya
n
g
,
Y.
Da
n
iel
Zh
a
n
g
,
a
n
d
Y.
J
.
Zh
u
,
“
Ro
a
d
c
ra
c
k
d
e
tec
ti
o
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
,
”
2
0
1
6
IE
EE
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Im
a
g
e
Pr
o
c
e
ss
in
g
(
ICIP)
,
p
p
.
3
7
0
8
–
3
7
1
2
,
2
0
1
6
.
[1
4
]
M
.
Qu
i
n
tan
a
,
J.
T
o
rre
s,
a
n
d
J.
M
.
M
e
n
é
n
d
e
z
,
“
A
si
m
p
li
f
ied
c
o
m
p
u
ter
v
isio
n
sy
ste
m
f
o
r
ro
a
d
su
rf
a
c
e
in
sp
e
c
ti
o
n
a
n
d
m
a
in
ten
a
n
c
e
,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
In
telli
g
e
n
t
T
ra
n
sp
o
rt
a
ti
o
n
S
y
st
e
ms
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
6
0
8
–
6
1
9
,
2
0
1
6
.
[1
5
]
M
.
M
.
Na
d
d
a
f
-
S
h
,
S
.
Ho
ss
e
in
i,
J.
Zh
a
n
g
,
N.
A
.
Bra
k
e
,
a
n
d
H.
Zarg
a
rz
a
d
e
h
,
“
Re
a
l
-
T
i
m
e
Ro
a
d
Cra
c
k
M
a
p
p
i
n
g
Us
in
g
a
n
Op
ti
m
ize
d
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
r
a
l
Ne
tw
o
rk
,
”
Co
mp
lex
it
y
,
v
o
l.
2
0
1
9
,
2
0
1
9
.
[1
6
]
S
.
Ch
a
m
b
o
n
a
n
d
J.
M
.
M
o
l
iar
d
,
“
A
u
to
m
a
ti
c
ro
a
d
p
a
v
e
m
e
n
t
a
ss
e
ss
m
e
n
t
w
it
h
im
a
g
e
p
ro
c
e
ss
in
g
:
Re
v
ie
w
a
n
d
c
o
m
p
a
riso
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ge
o
p
h
y
sic
s
,
v
o
l.
2
0
1
1
,
2
0
1
1
.
[1
7
]
B.
F
.
S
p
e
n
c
e
r,
V.
Ho
sk
e
re
,
a
n
d
Y.
Na
ra
z
a
k
i,
“
A
d
v
a
n
c
e
s
in
Co
m
p
u
ter
V
isio
n
-
Ba
se
d
Civ
il
I
n
f
ra
stru
c
tu
re
In
sp
e
c
ti
o
n
a
n
d
M
o
n
i
to
ri
n
g
,
”
En
g
in
e
e
rin
g
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
1
9
9
–
2
2
2
,
2
0
1
9
.
[1
8
]
I.
Ka
h
ra
m
a
n
,
M
.
Ka
m
il
T
u
ra
n
,
a
n
d
I.
Ra
k
ip
Ka
ra
s,
“
Ro
a
d
De
tec
ti
o
n
f
ro
m
Hig
h
S
a
telli
te
Im
a
g
e
s
Us
in
g
Ne
u
ra
l
Ne
tw
o
rk
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
M
o
d
e
li
n
g
a
n
d
Op
ti
miz
a
ti
o
n
,
v
o
l.
5
,
n
o
.
4
,
p
p
.
3
0
4
–
3
0
7
,
2
0
1
5
.
[1
9
]
J.
Zh
a
o
,
H.
W
u
,
a
n
d
L
.
Ch
e
n
,
“
Ro
a
d
S
u
rf
a
c
e
S
tate
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
S
V
M
Op
ti
m
iza
ti
o
n
a
n
d
Im
a
g
e
S
e
g
m
e
n
tatio
n
P
r
o
c
e
ss
in
g
,
”
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
d
T
ra
n
s
p
o
rt
a
ti
o
n
,
v
o
l.
2
0
1
7
,
n
o
.
6
,
2
0
1
7
.
[2
0
]
Y
.
S
a
r
i
,
P
.
B
.
P
r
a
k
o
s
o
,
a
n
d
A
.
R
.
B
a
sk
a
ra
,
“
R
o
a
d
C
ra
c
k
De
t
e
c
t
i
o
n
u
s
i
n
g
S
u
p
p
o
r
t
Ve
c
t
o
r
M
a
c
h
i
n
e
(
S
VM
)
a
n
d
O
T
S
U
A
lg
o
r
i
t
h
m
,
”
2
0
1
9
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
E
l
e
c
tr
i
c
Ve
h
i
c
u
l
a
r
T
e
c
h
n
o
l
o
g
y
(
I
C
E
V
T
)
,
p
p
.
3
4
9
–
3
5
4
,
2
0
1
9
.
[2
1
]
S
.
J
a
y
a
a
n
d
M
.
L
a
t
h
a
,
“
D
ia
g
n
o
s
i
s o
f
Ce
rv
i
c
a
l
c
a
n
c
e
r
u
s
i
n
g
CL
A
H
E
a
n
d
S
G
L
D
M
o
n
RG
B
P
a
p
sm
e
a
r
Im
a
g
e
s
t
h
r
o
u
g
h
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
E
x
p
l
o
r
i
n
g
E
n
g
i
n
e
e
r
i
n
g
(
I
J
I
T
E
E
)
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
5
3
0
–
5
3
4
,
2
0
1
9
.
[2
2
]
M
.
M
a
lath
y
,
C.
Ra
ji
n
ik
a
n
t
h
,
V
.
M
o
h
a
n
,
a
n
d
T
.
Yu
v
a
ra
ja,
“
H
y
b
rid
Ti
le
Ba
se
d
F
e
a
tu
re
Ex
trac
ti
o
n
a
n
d
S
u
p
p
o
rt
V
e
c
t
o
r
M
a
c
h
in
e
Ba
se
C
o
n
ten
t
-
Ba
se
d
Im
a
g
e
Re
tri
e
v
a
l
S
y
ste
m
f
o
r
M
e
d
ica
l
A
p
p
li
c
a
ti
o
n
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Rec
e
n
t
T
e
c
h
n
o
l
o
g
y
a
n
d
E
n
g
i
n
e
e
rin
g
(
IJ
R
T
E)
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
3
3
0
5
–
33
1
0
,
2
0
1
9
.
[2
3
]
M
.
Ha
ll
-
b
e
y
e
r,
“
GL
CM
T
e
x
tu
re
:
A
T
u
to
rial
,
”
Un
iv
e
rsity
o
f
Ca
l
g
a
r
y
, C
a
l
g
a
r
y
,
Ca
n
a
d
a
,
2
0
1
8
.
[2
4
]
E
.
K
.
S
h
a
rm
a
,
E
.
P
r
iy
a
n
k
a
,
E
.
A
.
K
a
l
s
h
,
a
n
d
E
.
K
.
S
a
i
n
i
,
“
G
L
C
M
a
n
d
i
t
s
F
e
a
t
u
r
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
R
e
s
e
a
rc
h
i
n
E
l
e
c
t
r
o
n
i
c
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
E
n
g
i
n
e
e
r
i
n
g
(
I
J
A
R
E
CE
)
,
v
o
l
.
4
,
n
o
.
8
,
p
p
.
2
1
8
0
–
2
1
8
2
,
2
0
1
5
.
[2
5
]
J.
G
u
,
Z.
W
a
n
g
,
J.
Ku
e
n
,
L
.
M
a
,
A
.
S
h
a
h
ro
u
d
y
,
a
n
d
B.
S
h
u
a
i,
e
t
a
l.
,
“
Re
c
e
n
t
A
d
v
a
n
c
e
s
in
Co
n
v
o
l
u
ti
o
n
a
l
Ne
u
ra
l
Ne
tw
o
rk
s,”
P
a
tt
e
rn
Re
c
o
g
n
i
ti
o
n
,
v
o
l.
7
7
,
p
p
.
3
5
4
-
3
7
7
,
2
0
18
.
[2
6
]
A
.
Ja
z
a
y
e
ri,
H.
Ca
i,
J.
Y.
Zh
e
n
g
,
a
n
d
M
.
T
u
c
e
r
y
a
n
,
“
V
e
h
icle
d
e
tec
ti
o
n
a
n
d
trac
k
in
g
in
c
a
r
v
id
e
o
b
a
se
d
o
n
m
o
ti
o
n
m
o
d
e
l,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
telli
g
e
n
t
T
ra
n
sp
o
rt
a
ti
o
n
S
y
ste
ms
,
v
o
l.
1
2
,
n
o
.
2
,
p
p
.
5
83
–
5
9
5
,
2
0
1
1
.
[2
7
]
R.
S
.
De
w
i,
W
.
Bij
k
e
r,
a
n
d
A
.
S
tein
,
“
C
o
m
p
a
rin
g
f
u
z
z
y
se
ts
a
n
d
ra
n
d
o
m
se
ts
to
m
o
d
e
l
th
e
u
n
c
e
rtain
ty
o
f
f
u
z
z
y
sh
o
re
li
n
e
s,”
Rem
o
te
S
e
n
si
n
g
,
v
o
l.
9
,
n
o
.
9
,
p
p
.
1
–
2
0
,
2
0
1
7
.
[2
8
]
F
o
rty
-
n
in
th
M
e
e
ti
n
g
o
f
th
e
Co
u
n
c
il
S
o
u
t
h
e
a
st
A
sia
n
F
ish
e
ries
De
v
e
lo
p
m
e
n
t
Ce
n
ter,
“
M
e
e
ti
n
g
a
g
re
e
d
th
a
t
th
e
S
EA
S
OFIA
c
o
u
ld
b
e
p
u
b
li
sh
e
d
o
n
a
re
g
u
lar
b
a
sis,”
S
o
u
th
e
a
st
Asia
n
S
ta
te
Of
Fi
sh
e
rie
s
An
d
Aq
u
a
c
u
lt
u
r
e
(
S
EA
S
OFIA
),
2
0
1
7
.
[2
9
]
D.
A
.
G
u
stian
,
N.
L
.
Ro
h
m
a
h
,
G
.
F
.
S
h
i
d
ik
,
A
.
Z.
F
a
n
a
n
i,
R.
A
.
P
ra
m
u
n
e
n
d
a
r,
a
n
d
P
u
ji
o
n
o
,
“
Clas
sif
i
c
a
ti
o
n
o
f
T
ro
so
F
a
b
ric
Us
in
g
S
V
M
-
RBF
M
u
lt
i
-
c
l
a
ss
M
e
th
o
d
w
it
h
GL
CM
a
n
d
P
CA
F
e
a
tu
re
Ex
trac
ti
o
n
,
”
2
0
1
9
In
ter
n
a
ti
o
n
a
l
S
e
min
a
r
o
n
A
p
p
li
c
a
ti
o
n
fo
r
T
e
c
h
n
o
lo
g
y
o
f
In
fo
rm
a
t
io
n
a
n
d
Co
mm
u
n
ica
ti
o
n
(
iS
e
ma
n
ti
c
)
,
p
p
.
7
–
11
,
2
0
1
9
.
[3
0
]
E.
E
.
L
a
v
in
d
i,
E.
J.
Ku
su
m
a
,
G
.
F
.
S
h
id
ik
,
R.
A
.
P
ra
m
u
n
e
n
d
a
r,
A
.
Z.
F
a
n
a
n
i
,
a
n
d
P
u
ji
o
n
o
,
“
Ne
u
ra
l
Ne
t
w
o
rk
b
a
se
d
o
n
GL
CM
,
a
n
d
CIE
L*
a
*
b
*
Co
lo
r
S
p
a
c
e
to
Clas
sify
T
o
m
a
to
e
s
M
a
tu
rit
y
,
”
2
0
1
9
I
n
ter
n
a
t
io
n
a
l
S
e
min
a
r
o
n
A
p
p
li
c
a
ti
o
n
fo
r T
e
c
h
n
o
l
o
g
y
o
f
In
fo
rm
a
t
io
n
a
n
d
Co
mm
u
n
ica
t
io
n
(
iS
e
ma
n
ti
c
)
,
p
p
.
1
–
6
,
2
0
1
9
.
[3
1
]
Y.
S
a
ri,
M
.
A
lk
a
ff
,
a
n
d
R.
A
.
P
ra
m
u
n
e
n
d
a
r,
“
Clas
sif
ica
ti
o
n
o
f
C
o
a
sta
l
a
n
d
In
lan
d
Ba
ti
k
u
sin
g
G
L
C
M
a
n
d
Ca
n
b
e
rr
a
Dista
n
c
e
,
”
AIP
Co
n
fer
e
n
c
e
Pro
c
e
e
d
in
g
s
,
v
o
l.
1
9
7
7
,
n
o
.
1
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.