C
omp
u
te
r
S
c
i
e
n
c
e
an
d
I
n
for
mati
on
T
e
c
h
n
ol
ogi
e
s
V
ol
.
7
,
N
o
.
1
,
M
a
r
c
h
20
2
6
,
p
p.
1
~
9
IS
S
N
:
2722
-
3221
,
D
O
I
:
10.
1
1591
/
c
s
i
t
.
v
7
i
1
.
pp
1
-
9
1
Jou
r
n
al
h
o
m
e
pa
ge
:
ht
t
p:
/
/
i
ae
s
pr
i
m
e
.
c
om
/
i
nd
e
x
.
php
/
c
s
i
t
Impl
e
me
n
t
a
t
i
o
n
o
f
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
Py
t
h
o
n
F
e
b
r
i
an
Wah
yu
C
h
r
i
s
tan
to
1
,
H
u
s
n
u
l
A
r
i
fi
n
1
,
C
h
r
i
s
t
i
n
e
D
e
w
i
2
,
3
,
T
e
gu
h
P
r
as
an
d
y
4
1
D
e
p
a
rt
m
e
n
t
o
f
In
fo
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
In
fo
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
Co
m
m
u
n
i
c
a
t
i
o
n
,
U
n
i
v
e
rs
i
t
a
s
S
e
m
a
ra
n
g
,
S
e
m
a
ra
n
g
,
In
d
o
n
e
s
i
a
2
D
e
p
a
rt
m
e
n
t
o
f
I
n
fo
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
In
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
S
a
t
y
a
W
a
c
a
n
a
Ch
ri
s
t
i
a
n
U
n
i
v
e
rs
i
t
y
,
S
a
l
a
t
i
g
a
,
In
d
o
n
e
s
i
a
3
S
c
h
o
o
l
o
f
In
fo
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
E
n
g
i
n
e
e
ri
n
g
a
n
d
Bu
i
l
t
E
n
v
i
ro
n
m
e
n
t
,
D
e
a
k
i
n
U
n
i
v
e
rs
i
t
y
,
M
e
l
b
o
u
rn
e
,
A
u
s
t
ra
l
i
a
4
D
e
p
a
rt
m
e
n
t
o
f
I
n
fo
rm
a
t
i
o
n
S
y
s
t
e
m
,
Bi
n
u
s
O
n
-
l
i
n
e
L
e
a
rn
i
n
g
,
Bi
n
a
N
u
s
a
n
t
a
ra
U
n
i
v
e
rs
i
t
y
,
J
a
k
a
rt
a
,
In
d
o
n
e
s
i
a
A
r
ti
c
l
e
I
n
fo
A
BS
TR
A
C
T
Ar
t
i
c
l
e
h
i
s
t
or
y
:
Re
c
e
i
v
e
d
M
a
y
18
,
2025
Re
vi
s
e
d
J
u
l
22,
202
5
A
c
c
e
pt
e
d
N
o
v
28
,
2025
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
nc
e
(
A
I
)
-
ba
s
e
d
t
e
c
hno
l
o
gy
s
ys
t
e
m
s
a
r
e
de
v
e
l
o
pi
n
g
r
a
p
i
d
l
y
.
A
l
ong
w
i
t
h
t
e
c
hn
ol
o
gi
c
a
l
d
e
ve
l
op
m
e
nt
t
he
nu
m
be
r
o
f
c
r
i
m
i
na
l
c
a
s
e
s
c
a
u
s
e
d
by
f
a
c
i
a
l
f
or
ge
r
y
i
s
a
l
s
o
gr
ow
i
ng
.
C
a
s
e
s
of
t
h
e
f
t
a
nd
hou
s
e
b
r
e
a
ki
n
g
w
i
t
h
f
a
ke
phot
os
a
r
e
a
c
o
m
m
on
pr
obl
e
m
i
n
S
e
m
a
r
a
n
g.
I
n
20
22
–
2
023
t
he
n
um
b
e
r
o
f
c
a
s
e
s
of
t
h
e
f
t
a
nd
hou
s
e
b
r
e
a
ki
ng
r
e
a
c
h
e
d
372
,
96
5
w
i
t
h
a
c
r
i
m
e
r
i
s
k
l
e
ve
l
of
137/
100
,
000
pe
opl
e
.
T
o
ove
r
c
o
m
e
t
hi
s
p
r
ob
l
e
m
t
h
e
f
a
c
i
a
l
r
e
c
o
gni
t
i
on
s
y
s
t
e
m
us
e
d
i
n
t
he
d
oor
s
e
c
ur
i
t
y
s
y
s
t
e
m
us
e
s
d
i
gi
t
a
l
i
m
a
g
e
p
r
o
c
e
s
s
i
ng
.
T
hi
s
m
e
t
h
od
w
or
ks
by
i
m
i
t
a
t
i
n
g
h
ow
n
e
r
ve
c
e
l
l
s
c
o
m
m
un
i
c
a
t
e
w
i
t
h
i
nt
e
r
c
onne
c
t
e
d
ne
ur
ons
,
or
m
o
r
e
p
r
e
c
i
s
e
l
y,
h
ow
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
ne
t
w
or
k
s
f
u
nc
t
i
on
i
n
hum
a
ns
.
A
s
t
r
a
i
n
i
ng
d
a
t
a
,
i
m
a
g
e
c
a
p
t
u
r
e
a
nd
f
a
c
i
a
l
r
e
c
ogn
i
t
i
on
a
r
e
c
a
r
r
i
e
d
out
u
s
i
ng
a
w
e
bc
a
m
a
n
d
t
he
P
y
t
ho
n
p
r
og
r
a
m
m
i
n
g
l
a
ng
ua
g
e
w
i
t
h
t
h
e
T
e
ns
o
r
F
l
ow
l
i
b
r
a
r
y.
T
h
e
i
m
a
ge
pr
oc
e
s
s
i
ng
a
l
g
or
i
t
hm
u
s
e
s
400
f
a
c
i
a
l
i
m
a
ge
s
w
i
t
h
a
n
a
c
c
ur
a
c
y
r
a
t
e
o
f
9
5%
.
H
ow
e
ve
r
f
ur
t
he
r
de
ve
l
op
m
e
nt
i
s
ne
e
d
e
d
t
o
i
m
pr
o
ve
t
he
e
f
f
i
c
i
e
nc
y
a
nd
a
c
c
u
r
a
c
y
o
f
t
h
e
s
ys
t
e
m
t
o
pr
o
duc
e
b
e
t
t
e
r
r
e
s
u
l
t
s
.
Ke
y
w
or
d
s
:
A
rt
i
fi
c
i
a
l
i
n
t
e
l
l
i
ge
nc
e
D
i
gi
t
a
l
i
m
a
ge
pro
c
e
s
s
i
n
g
E
nvi
r
onm
e
nt
a
l
s
e
c
ur
i
t
y
F
a
c
e
r
e
c
og
ni
t
i
on
T
e
ns
orF
l
ow
l
i
br
a
ry
T
hi
s
i
s
an
op
e
n
ac
c
e
s
s
ar
t
i
c
l
e
u
nde
r
t
he
C
C
B
Y
-
SA
l
i
c
e
n
s
e
.
Cor
r
e
s
pon
di
n
g
Au
t
h
or
:
F
e
bri
a
n
W
a
hyu
Chr
i
s
t
a
n
t
o
D
e
pa
r
t
m
e
nt
of
Info
rm
a
t
i
on
T
e
c
hn
ol
ogy
,
F
a
c
ul
t
y
o
f
In
form
a
t
i
on
T
e
c
hnol
ogy
a
nd
Co
m
m
uni
c
a
t
i
o
n
U
ni
ve
rs
i
t
a
s
S
e
m
a
r
a
ng
S
oe
ka
rn
o
-
H
a
t
t
a
A
r
t
e
r
i
a
l
R
oa
d
,
T
l
ogos
a
r
i
,
S
e
m
a
ra
ng
,
Indon
e
s
i
a
E
m
a
i
l
:
fe
br
i
a
n.
w
a
hyu
.
c
hr
i
s
t
a
nt
o
@
us
m
.
a
c
.
i
d
1.
I
N
TR
O
D
U
C
TI
O
N
H
om
e
s
e
c
u
ri
t
y
i
s
i
m
p
ort
a
nt
t
o
a
vo
i
d
c
ri
m
e
probl
e
m
s
s
uc
h
a
s
hous
e
ro
bbe
ry
.
A
c
c
o
rdi
ng
t
o
t
h
e
c
e
nt
ra
l
s
t
a
t
i
s
t
i
c
s
a
g
e
nc
y
of
S
e
m
a
ra
ng
c
i
t
y
,
Indon
e
s
i
a
,
c
ri
m
e
c
a
s
e
s
i
n
20
22
-
202
3
re
a
c
h
e
d
37
2,
9
65
w
i
t
h
a
r
i
s
k
l
e
ve
l
of
137/
100
,
00
0
re
s
i
d
e
n
t
s
[1
]
.
T
he
i
nc
r
e
a
s
i
ng
nu
m
be
r
o
f
t
h
e
ft
a
n
d
rob
be
ry
c
a
s
e
s
i
n
hous
i
ng
i
s
a
c
ons
i
d
e
ra
t
i
o
n
for
t
i
gh
t
e
n
i
ng
t
he
c
urr
e
n
t
s
e
c
uri
t
y
s
ys
t
e
m
.
A
l
t
hou
gh
m
os
t
ho
us
i
ng
i
s
p
rovi
de
d
w
i
t
h
c
l
os
e
d
-
c
i
r
c
ui
t
t
e
l
e
vi
s
i
on
(CCT
V
)
,
f
a
c
i
a
l
r
e
c
o
gni
t
i
on
t
e
c
hnol
o
gy
i
s
n
e
e
d
e
d
t
o
e
ns
ur
e
t
ha
t
onl
y
p
e
opl
e
w
i
t
h
a
c
c
e
s
s
a
r
e
a
l
l
ow
e
d
t
o
e
nt
e
r
t
he
hous
e
[2]
.
T
he
us
e
o
f
p
a
s
s
w
ord
-
t
ype
s
e
c
ur
i
t
y
s
uc
h
a
s
us
i
ng
l
e
t
t
e
rs
a
nd
nu
m
be
rs
of
t
e
n
r
e
s
ul
t
s
i
n
e
rrors
a
nd
i
s
vu
l
ne
r
a
b
l
e
t
o
h
a
c
k
i
ng
be
c
a
us
e
ba
s
e
d
on
CN
B
C
I
ndon
e
s
i
a
d
a
t
a
i
n
2
022
,
t
he
p
a
s
s
w
ord
h
a
c
k
i
ng
ra
t
e
i
nc
r
e
a
s
e
d
b
y
9
21
a
t
t
a
c
ks
p
e
r
s
e
c
ond
,
p
l
us
da
t
a
a
c
c
or
di
ng
t
o
t
h
e
M
i
c
ros
o
ft
D
i
g
i
t
a
l
D
e
f
e
ns
e
Re
port
s
how
s
a
n
i
nc
r
e
a
s
e
of
up
t
o
7
4%
i
n
one
ye
a
r.
T
h
e
re
fore
,
t
he
us
e
of
f
a
c
i
a
l
p
a
s
s
w
ords
i
s
t
h
e
b
e
s
t
s
ol
ut
i
on
t
o
pre
ve
n
t
hous
e
t
he
f
t
[3]
.
D
e
e
p
l
e
a
rn
i
ng
i
s
d
e
ve
l
op
e
d
us
i
n
g
a
m
a
c
hi
n
e
l
e
a
r
ni
ng
a
ppro
a
c
h
t
ha
t
ha
s
a
w
orki
n
g
pri
n
c
i
pl
e
of
a
fa
c
i
a
l
d
e
t
e
c
t
i
on
c
a
m
e
r
a
s
ys
t
e
m
w
i
t
h
a
n
a
c
c
ur
a
c
y
e
qui
va
l
e
nt
t
o
t
h
e
a
bi
l
i
t
y
of
t
h
e
h
um
a
n
bra
i
n
.
E
ve
n
t
he
a
c
c
ura
c
y
prod
uc
e
d
re
a
c
h
e
s
98
.
8%
on
a
6
4×
6
4×
3
f
a
c
e
,
bu
t
i
s
a
l
s
o
s
uppor
t
e
d
b
y
t
h
e
qua
l
i
t
y
of
t
h
e
c
a
m
e
ra
us
e
d
t
o
pro
c
e
s
s
fa
c
i
a
l
re
c
ogni
t
i
on.
It
s
i
m
pl
e
m
e
nt
a
t
i
on
us
e
s
t
he
s
i
n
gl
e
-
s
ho
t
d
e
t
e
c
t
or
(S
S
D
)
m
e
t
h
od,
w
hi
c
h
i
s
on
e
o
f
t
he
di
g
i
t
a
l
i
m
a
ge
pro
c
e
s
s
i
ng
m
e
t
hods
[4],
[5]
.
T
he
us
e
o
f
d
i
g
i
t
a
l
i
m
a
ge
pr
o
c
e
s
s
i
ng
m
e
t
ho
ds
i
s
a
m
e
t
ho
d
t
h
a
t
h
a
s
t
h
e
h
i
gh
e
s
t
a
c
c
ur
a
c
y
b
ot
h
s
t
a
t
i
s
t
i
c
a
l
l
y
a
nd
i
n
re
a
l
t
i
m
e
[6
]
.
T
h
e
re
c
o
rd
e
d
a
c
c
ur
a
c
y
l
e
v
e
l
i
s
10
0
%
w
h
e
n
t
h
e
v
i
e
w
i
n
g
a
n
g
l
e
i
s
f
a
c
i
n
g
fo
rw
a
rd
,
t
he
n
w
h
e
n
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2722
-
3221
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
,
V
o
l
.
7
,
N
o
.
1
,
M
a
rc
h
20
2
6
:
1
-
9
2
no
t
f
a
c
i
n
g
f
or
w
a
r
d
,
t
h
e
h
i
g
h
e
s
t
a
c
c
ur
a
c
y
l
e
v
e
l
i
s
8
0
%
,
b
ut
w
i
t
h
a
d
i
s
t
a
n
c
e
r
a
n
ge
of
6
0
-
2
50
c
m
f
ro
m
t
h
e
f
a
c
e
d
e
t
e
c
t
i
o
n
c
a
m
e
ra
[
7]
,
[
8]
.
R
e
a
l
-
t
i
m
e
f
a
c
i
a
l
r
e
c
o
gn
i
t
i
o
n
r
e
s
e
a
r
c
h
h
a
s
b
e
e
n
c
o
nd
u
c
t
e
d
a
nd
h
a
s
a
n
a
c
c
u
r
a
c
y
r
e
s
u
l
t
of
8
7
%
us
i
n
g
t
h
e
c
on
vo
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
rk
(
CN
N
)
m
e
t
h
o
d
w
i
t
h
37
2
d
a
t
a
po
i
n
t
s
,
i
n
c
l
u
d
i
n
g
18
6
m
a
l
e
i
m
a
g
e
d
a
t
a
a
nd
1
86
f
e
m
a
l
e
i
m
a
g
e
d
a
t
a
[9
]
,
[
10
]
.
A
no
t
h
e
r
r
e
s
e
a
r
c
h
us
e
d
1
,
10
0
i
m
a
g
e
s
,
w
i
t
h
55
0
b
e
i
ng
m
a
l
e
i
m
a
g
e
d
a
t
a
a
nd
5
5
0
f
e
m
a
l
e
i
m
a
g
e
d
a
t
a
.
P
ro
du
c
i
ng
a
n
a
c
c
u
r
a
c
y
v
a
l
u
e
o
f
90
%
f
or
a
g
e
a
n
d
9
6
%
fo
r
g
e
nd
e
r
us
i
ng
t
h
e
C
N
N
m
e
t
h
o
d
[1
1]
.
R
e
s
e
a
r
c
h
e
n
t
i
t
l
e
d
"
o
p
t
i
m
i
z
i
n
g
g
e
n
d
e
r
c
l
a
s
s
i
fi
c
a
t
i
on
a
c
c
u
r
a
c
y
i
n
f
a
c
i
a
l
i
m
a
g
e
s
us
i
ng
d
a
t
a
a
ug
m
e
nt
a
t
i
on
a
n
d
i
n
c
e
p
t
i
o
n
V
-
3
"
u
s
i
n
g
t
h
e
i
n
c
e
p
t
i
on
V
-
3
a
n
d
c
o
nv
o
l
ut
i
on
a
l
m
e
t
ho
ds
w
i
t
h
29
0
d
a
t
a
c
o
ns
i
s
t
i
n
g
of
14
5
m
e
n
a
n
d
1
45
w
o
m
e
n
p
ro
d
u
c
e
d
t
h
e
b
e
s
t
a
c
c
u
r
a
c
y
v
a
l
u
e
of
99
.
31
%
[1
2]
,
[
13
]
.
A
l
t
houg
h
fa
c
i
a
l
re
c
ogn
i
t
i
on
t
e
c
hnol
ogy
h
a
s
be
e
n
a
dv
a
nc
e
d
,
m
os
t
of
t
h
e
s
ys
t
e
m
s
c
re
a
t
e
d
a
re
l
i
m
i
t
e
d
t
o
t
he
or
e
t
i
c
a
l
va
l
i
d
a
t
i
on
or
re
l
y
on
hi
gh
-
p
e
rfor
m
a
n
c
e
G
P
U
s
.
T
he
fo
c
us
of
t
h
i
s
r
e
s
e
a
rc
h
i
s
on
t
he
e
f
fi
c
i
e
nc
y
of
l
i
m
i
t
e
d
ha
r
dw
a
r
e
a
nd
r
e
s
ourc
e
s
b
y
de
v
e
l
op
i
ng
a
l
i
gh
t
w
e
i
ght
a
nd
a
c
c
e
s
s
i
bl
e
f
a
c
i
a
l
re
c
ogn
i
t
i
on
s
ys
t
e
m
.
T
hi
s
s
ys
t
e
m
i
s
s
p
e
c
i
fi
c
a
l
l
y
d
e
s
i
gn
e
d
for
hom
e
s
e
c
uri
t
y.
T
he
di
s
t
i
ngu
i
s
hi
n
g
va
l
ue
of
t
hi
s
r
e
s
e
a
rc
h
i
s
t
h
e
i
m
p
l
e
m
e
n
t
a
t
i
o
n
of
d
i
gi
t
a
l
i
m
a
g
e
pro
c
e
s
s
i
n
g
for
a
s
e
c
uri
t
y
s
ys
t
e
m
w
i
t
h
a
h
i
gh
l
e
v
e
l
o
f
a
c
c
ur
a
c
y.
D
i
gi
t
a
l
i
m
a
g
e
proc
e
s
s
i
ng
c
a
n
i
d
e
nt
i
fy
a
nd
re
c
ogn
i
z
e
r
e
c
or
de
d
fa
c
e
s
p
re
c
i
s
e
l
y.
By
us
i
ng
t
h
i
s
s
ys
t
e
m
,
a
c
c
e
s
s
c
o
nt
ro
l
i
n
a
room
i
n
t
h
e
hous
e
c
a
n
a
vo
i
d
t
h
e
ri
s
k
of
h
a
c
ki
ng
a
nd
a
c
c
e
s
s
b
y
f
a
c
e
s
t
h
a
t
a
r
e
no
t
re
c
ogn
i
z
e
d
by
t
he
s
ys
t
e
m
,
s
o
t
ha
t
i
t
c
a
n
b
e
s
e
c
ur
e
d
[14
]
.
T
h
e
us
e
of
t
he
d
i
g
i
t
a
l
i
m
a
ge
proc
e
s
s
i
ng
m
e
t
hod
h
a
s
b
e
e
n
prov
e
n
t
o
prov
i
d
e
re
s
u
l
t
s
w
i
t
h
a
hi
gh
l
e
ve
l
of
a
c
c
ur
a
c
y
,
a
c
c
ord
i
ng
t
o
re
s
e
a
r
c
h
t
ha
t
h
a
s
be
e
n
c
on
duc
t
e
d
on
di
gi
t
a
l
i
m
a
ge
proc
e
s
s
i
ng
,
w
hi
c
h
c
a
n
re
c
ogn
i
z
e
fa
c
i
a
l
i
m
a
g
e
s
b
e
t
t
e
r
t
ha
n
o
t
he
r
m
e
t
hods
t
h
a
t
h
a
ve
b
e
e
n
t
e
s
t
e
d
[15]
.
T
he
re
fo
re
,
t
he
us
e
of
t
hi
s
m
e
t
h
od
w
i
l
l
be
ve
ry
s
u
i
t
a
bl
e
for
i
m
p
l
e
m
e
n
t
a
t
i
o
n
a
s
a
form
of
ro
om
s
e
c
ur
i
t
y
t
e
c
hno
l
ogy
t
ha
t
re
qu
i
r
e
s
va
ri
a
t
i
ons
i
n
fa
c
i
a
l
e
xp
re
s
s
i
ons
t
o
un
c
e
r
t
a
i
nt
y
i
n
c
h
a
nge
s
i
n
a
ppe
a
r
a
n
c
e
[16]
.
T
hi
s
re
s
e
a
rc
h
w
a
s
c
ond
uc
t
e
d
t
o
de
t
e
rm
i
ne
ho
w
t
he
a
ppl
i
c
a
t
i
on
of
t
he
di
gi
t
a
l
i
m
a
ge
pr
oc
e
s
s
i
n
g
m
e
t
hod
a
s
fa
c
i
a
l
re
c
ogni
t
i
on
i
n
hom
e
s
e
c
uri
t
y
s
y
s
t
e
m
s
a
nd
w
he
t
he
r
di
gi
t
a
l
i
m
a
ge
proc
e
s
s
i
ng
c
a
n
produc
e
a
good
l
e
ve
l
of
a
c
c
ura
c
y
for
hum
a
n
fa
c
i
a
l
re
c
ogni
t
i
o
n.
It
i
s
e
xpe
c
t
e
d
t
ha
t
t
hi
s
t
e
c
hnol
ogy
c
a
n
di
s
t
i
ngui
s
h
be
t
w
e
e
n
know
n
a
nd
unkno
w
n
fa
c
e
s
s
o
t
ha
t
onl
y
c
onfi
r
m
e
d
fa
c
e
s
c
a
n
be
a
ut
hori
z
e
d
t
o
e
nt
e
r
t
he
a
re
a
.
T
he
s
ys
t
e
m
doe
s
n
ot
re
qui
re
s
pe
c
i
a
l
de
vi
c
e
s
s
o
t
ha
t
i
t
i
s
a
fforda
bl
e
a
nd
i
nc
re
a
s
e
s
a
c
c
e
s
s
i
bi
l
i
t
y
i
n
i
t
s
a
ppl
i
c
a
t
i
on,
e
s
pe
c
i
a
l
l
y
i
n
re
s
i
de
nt
i
a
l
a
re
a
s
t
ha
t
re
qui
re
m
o
re
s
e
c
uri
t
y.
T
he
p
urp
os
e
o
f
t
hi
s
re
s
e
a
rc
h
i
s
t
o
i
m
pl
e
m
e
nt
a
fa
c
i
a
l
re
c
ogni
t
i
on
s
ys
t
e
m
us
i
ng
di
gi
t
a
l
i
m
a
ge
proc
e
s
s
i
n
g
a
nd
de
e
p
l
e
a
rni
ng
t
ool
s
ba
s
e
d
o
n
P
yt
ho
n
a
nd
O
pe
nCV
t
he
n
e
va
l
ua
t
e
t
he
a
c
c
ura
c
y
a
nd
rob
us
t
ne
s
s
o
f
t
he
s
y
s
t
e
m
i
n
re
a
l
-
w
orl
d
c
on
s
t
ra
i
nt
s
i
nc
l
udi
ng
l
i
g
ht
i
ng
va
ri
a
t
i
on
s
a
nd
va
ri
ou
s
fa
c
i
a
l
p
os
e
s
.
A
not
he
r
obj
e
c
t
i
ve
i
s
t
o
de
m
o
ns
t
ra
t
e
t
he
fe
a
s
i
bi
l
i
t
y
o
f
i
m
pl
e
m
e
nt
i
ng
t
he
s
ys
t
e
m
on
l
ow
-
c
os
t
ha
rd
w
a
re
fo
r
re
s
i
de
nt
i
a
l
s
e
c
uri
t
y
u
s
e
a
nd
s
y
s
t
e
m
pe
r
form
a
nc
e
w
i
l
l
be
m
e
a
s
ure
d
t
h
rou
gh
qua
nt
i
t
a
t
i
ve
m
e
t
ri
c
s
i
nc
l
udi
ng
a
c
c
ura
c
y,
pre
c
i
s
i
on,
re
c
a
l
l
,
F
1
s
c
ore
,
a
nd
c
onfu
s
i
o
n
m
a
t
ri
x
a
na
l
ys
i
s
.
2.
M
ET
H
O
D
T
he
fa
c
e
re
c
ogn
i
t
i
on
s
ys
t
e
m
us
i
ng
di
g
i
t
a
l
i
m
a
g
e
pr
oc
e
s
s
i
ng
re
q
ui
r
e
s
a
n
a
l
ys
i
s
t
o
c
o
ve
r
va
r
i
ous
va
ri
a
t
i
ons
of
hu
m
a
n
fa
c
e
s
fr
om
v
a
ri
ous
pra
c
t
i
c
a
l
c
ond
i
t
i
ons
.
T
h
e
s
e
c
ond
i
t
i
ons
m
a
y
o
c
c
ur
i
n
t
he
us
e
of
t
h
e
s
ys
t
e
m
a
nd
m
us
t
b
e
a
ddre
s
s
e
d
prop
e
r
l
y.
S
om
e
of
t
h
e
a
na
l
y
s
e
s
t
ha
t
n
e
e
d
t
o
be
c
a
rri
e
d
o
ut
b
y
di
gi
t
a
l
i
m
a
g
e
proc
e
s
s
i
ng
i
n
c
l
ud
e
da
t
a
a
n
a
l
ys
i
s
,
pro
c
e
s
s
a
na
l
ys
i
s
,
s
ys
t
e
m
d
e
s
i
gn,
a
n
d
s
ys
t
e
m
i
m
p
l
e
m
e
n
t
a
t
i
o
n.
2.
1
.
D
ata
a
n
al
ys
i
s
T
he
d
a
t
a
s
o
u
rc
e
c
on
s
i
s
t
s
o
f
a
d
a
t
a
s
e
t
o
f
h
u
m
a
n
f
a
c
i
a
l
i
m
a
g
e
s
t
r
a
i
n
e
d
t
hr
ou
g
h
i
m
a
g
e
s
a
m
p
l
e
s
w
i
t
h
v
a
r
i
o
us
po
s
e
s
,
e
x
pr
e
s
s
i
o
ns
,
l
i
g
h
t
i
n
g
,
a
n
d
d
i
ff
e
re
n
t
b
a
c
kg
r
ou
nd
s
.
T
he
p
ur
pos
e
of
t
h
i
s
v
a
r
i
a
t
i
o
n
i
s
f
or
d
i
g
i
t
a
l
i
m
a
g
e
pr
o
c
e
s
s
i
n
g
t
o
b
e
a
b
l
e
t
o
un
d
e
r
s
t
a
nd
a
nd
r
e
c
o
g
ni
z
e
r
e
g
i
s
t
e
re
d
f
a
c
e
s
f
r
o
m
v
a
ri
o
us
c
o
nd
i
t
i
o
ns
.
T
h
e
t
o
t
a
l
a
m
o
un
t
o
f
t
r
a
i
n
e
d
i
m
a
g
e
d
a
t
a
i
s
a
d
j
u
s
t
e
d
t
o
t
h
e
n
u
m
b
e
r
o
f
s
u
b
j
e
c
t
s
i
n
v
o
l
v
e
d
a
n
d
t
o
t
h
e
d
e
s
i
r
e
d
v
a
r
i
a
t
i
on
.
F
u
rt
h
e
r
m
o
re
,
t
e
s
t
i
m
a
g
e
d
a
t
a
a
nd
p
e
r
fo
r
m
a
n
c
e
t
e
s
t
s
o
f
t
r
a
i
n
e
d
d
a
t
a
a
r
e
c
a
rr
i
e
d
o
u
t
.
T
h
i
s
t
e
s
t
i
s
c
a
r
ri
e
d
o
u
t
t
o
e
v
a
l
u
a
t
e
t
h
e
r
e
l
i
a
b
i
l
i
t
y
of
t
he
s
ys
t
e
m
i
n
r
e
c
og
n
i
z
i
n
g
f
a
c
e
s
t
h
a
t
h
a
v
e
b
e
e
n
r
e
g
i
s
t
e
r
e
d
b
y
di
g
i
t
a
l
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
[
17
]
.
2.
2
.
P
r
oc
e
s
s
a
n
a
l
ys
i
s
T
hi
s
proc
e
s
s
pe
rf
orm
s
a
n
i
n
-
de
pt
h
a
na
l
ys
i
s
re
l
a
t
e
d
t
o
t
he
fa
c
e
re
c
ogni
t
i
on
proc
e
s
s
i
n
di
gi
t
a
l
i
m
a
ge
proc
e
s
s
i
ng
by
c
on
s
i
de
ri
ng
t
he
a
ppl
i
c
a
t
i
on
bui
l
t
a
nd
t
he
s
p
e
c
i
fi
c
a
t
i
ons
of
t
he
re
gi
s
t
e
re
d
da
t
a
s
e
t
.
T
he
fi
rs
t
s
t
a
ge
i
s
i
m
a
ge
a
c
qui
s
i
t
i
on,
w
he
re
da
t
a
t
ha
t
ha
s
be
e
n
e
nt
e
re
d
i
nt
o
t
he
s
ys
t
e
m
c
a
n
de
t
e
c
t
pe
opl
e
'
s
fa
c
e
s
us
i
n
g
a
re
a
l
-
t
i
m
e
c
a
m
e
ra
.
E
a
c
h
fa
c
e
de
t
e
c
t
e
d
by
t
he
s
ys
t
e
m
i
s
i
d
e
nt
i
fi
e
d
a
nd
na
m
e
d.
T
he
s
uc
c
e
s
s
o
f
t
he
s
y
s
t
e
m
c
a
n
be
i
ndi
c
a
t
e
d
by
t
he
a
ppe
a
ra
nc
e
of
a
na
m
e
on
t
he
fa
c
e
t
ha
t
ha
s
be
e
n
re
gi
s
t
e
re
d,
a
nd
t
he
c
a
m
e
ra
c
a
n
c
ons
i
s
t
e
nt
l
y
de
t
e
c
t
i
ndi
vi
dua
l
fa
c
e
s
qui
c
kl
y
a
nd
a
c
c
ura
t
e
l
y
from
va
ri
ou
s
c
ondi
t
i
on
s
[18
]
.
T
he
ne
xt
s
t
a
ge
i
s
t
he
fa
c
e
de
t
e
c
t
i
on
s
t
a
ge
,
fa
c
e
de
t
e
c
t
i
on
u
s
i
ng
di
gi
t
a
l
i
m
a
ge
proc
e
s
s
i
ng
a
s
s
i
s
t
e
d
b
y
t
he
O
pe
nC
V
l
i
bra
ry
[19
],
[20]
.
T
hi
s
proc
e
s
s
i
s
c
a
r
ri
e
d
out
t
o
fi
nd
t
he
pre
s
e
nc
e
of
a
fa
c
e
i
n
t
he
c
a
m
e
ra
fra
m
e
.
T
hi
s
fa
c
e
de
t
e
c
t
i
on
u
s
e
s
t
he
c
onc
e
pt
of
H
a
a
r
fe
a
t
u
re
s
,
i
nt
e
g
ra
l
i
m
a
ge
,
a
nd
c
a
s
c
a
de
c
l
a
s
s
i
fi
e
r
s
o
t
ha
t
t
he
fa
c
e
de
t
e
c
t
i
on
p
roc
e
s
s
ru
n
s
e
ffi
c
i
e
nt
l
y
[21
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
IS
S
N
:
2722
-
3221
Im
pl
e
m
e
nt
a
t
i
o
n
o
f
f
ac
e
r
e
c
o
gni
t
i
on
us
i
ng
P
y
t
hon
(
F
e
br
i
an
W
ahy
u
Chr
i
s
t
ant
o
)
3
T
he
t
h
i
r
d
s
t
a
g
e
i
s
p
r
e
-
pr
o
c
e
s
s
i
ng
,
w
h
i
c
h
i
s
t
h
e
p
ro
c
e
s
s
of
i
m
pr
ov
i
ng
i
m
a
ge
qu
a
l
i
t
y
b
e
f
o
re
t
h
e
n
e
xt
pr
o
c
e
s
s
i
s
c
on
t
i
n
u
e
d
.
T
h
i
s
pr
o
c
e
s
s
r
e
qu
i
r
e
s
c
ro
pp
i
ng
o
n
t
h
e
t
a
rg
e
t
f
a
c
e
on
l
y
a
nd
r
e
m
o
vi
n
g
i
r
r
e
l
e
v
a
n
t
a
r
e
a
s
,
t
h
e
n
t
h
e
i
m
a
g
e
r
e
s
i
z
i
n
g
pr
o
c
e
s
s
s
o
t
h
a
t
w
h
e
n
t
h
e
i
m
a
g
e
i
s
c
o
nv
e
r
t
e
d
t
o
g
r
a
ys
c
a
l
e
m
o
d
e
i
t
i
s
e
a
s
y
t
o
e
x
t
r
a
c
t
a
n
d
r
e
d
uc
e
no
i
s
e
a
n
d
c
o
n
t
r
a
s
t
a
d
j
us
t
m
e
n
t
s
a
n
d
w
h
e
n
c
h
a
ng
i
ng
t
he
c
ol
o
r
t
o
g
r
a
y
s
c
a
l
e
a
r
e
d
o
n
e
t
o
fo
c
us
i
n
fo
r
m
a
t
i
o
n
f
or
m
o
r
e
e
f
f
i
c
i
e
n
t
a
nd
a
c
c
ur
a
t
e
fa
c
e
r
e
c
o
g
ni
t
i
on
.
T
h
e
ne
x
t
i
s
t
he
f
e
a
t
u
r
e
e
xt
r
a
c
t
i
o
n
s
t
a
g
e
,
t
a
k
i
n
g
i
m
p
or
t
a
n
t
f
e
a
t
ur
e
s
b
a
s
e
d
on
t
h
e
r
e
g
i
s
t
e
r
e
d
d
a
t
a
t
o
d
i
s
t
i
n
gu
i
s
h
b
e
t
w
e
e
n
f
a
c
e
s
.
T
h
e
e
x
t
r
a
c
t
e
d
f
e
a
t
u
r
e
s
i
n
c
l
u
de
v
i
s
u
a
l
p
a
t
t
e
r
ns
t
h
a
t
r
e
pr
e
s
e
n
t
un
i
qu
e
f
e
a
t
u
r
e
s
o
f
t
h
e
r
e
g
i
s
t
e
r
e
d
f
a
c
e
[
22
]
.
T
h
e
f
i
n
a
l
s
t
a
g
e
i
s
f
a
c
e
m
a
t
c
hi
n
g
by
m
e
a
s
ur
i
ng
t
h
e
l
e
v
e
l
of
s
i
m
i
l
a
r
i
t
y
b
e
t
w
e
e
n
t
h
e
t
r
a
i
n
i
n
g
i
m
a
g
e
a
n
d
t
h
e
t
e
s
t
i
m
a
g
e
w
i
t
h
a
d
i
g
i
t
a
l
i
m
a
ge
p
ro
c
e
s
s
i
n
g
m
e
t
h
o
d
.
T
h
i
s
p
ro
c
e
s
s
c
o
m
p
a
r
e
s
t
h
e
c
h
a
r
a
c
t
e
ri
s
t
i
c
s
l
e
a
rn
e
d
b
y
t
h
e
s
ys
t
e
m
,
s
o
t
h
a
t
i
t
c
a
n
a
c
c
ur
a
t
e
l
y
d
e
t
e
c
t
t
h
e
v
i
s
u
a
l
s
s
e
e
n
.
2.
3
.
S
ys
te
m
d
e
s
i
gn
T
he
d
e
s
i
gn
of
a
fa
c
i
a
l
r
e
c
og
ni
t
i
on
s
ys
t
e
m
r
e
qu
i
re
s
s
e
ve
ra
l
c
ons
i
de
r
a
t
i
ons
,
s
u
c
h
a
s
s
ys
t
e
m
a
rc
h
i
t
e
c
t
ure
d
e
s
i
gn
,
a
fa
c
i
a
l
r
e
c
og
ni
t
i
on
m
ode
l
t
h
a
t
m
e
e
t
s
s
p
e
c
i
fi
c
a
t
i
o
ns
,
a
c
a
m
e
r
a
f
or
f
a
c
i
a
l
i
m
a
g
e
a
c
qu
i
s
i
t
i
on
,
s
oft
w
a
re
for
i
m
pl
e
m
e
n
t
i
ng
fa
c
i
a
l
r
e
c
og
ni
t
i
on
a
l
g
ori
t
h
m
s
,
a
nd
i
t
s
i
n
t
e
rfa
c
e
.
T
h
e
s
ys
t
e
m
de
s
i
g
n
ha
s
a
f
a
c
i
a
l
de
t
e
c
t
i
on
proc
e
s
s
s
t
a
rt
i
ng
w
i
t
h
i
m
a
g
e
i
npu
t
,
fo
l
l
o
w
e
d
b
y
a
pre
-
proc
e
s
s
i
ng
pro
c
e
s
s
.
A
f
t
e
r
t
ha
t
,
t
he
fe
a
t
ure
e
x
t
ra
c
t
i
on
proc
e
s
s
,
c
l
a
s
s
i
fi
c
a
t
i
o
n
pr
o
c
e
s
s
,
a
nd
i
m
a
ge
out
pu
t
a
re
c
a
rri
e
d
out
.
T
he
a
pp
l
i
c
a
t
i
o
n
of
fa
c
e
re
c
og
ni
t
i
on
for
h
om
e
s
e
c
ur
i
t
y
s
ys
t
e
m
s
b
e
gi
ns
by
c
a
p
t
uri
ng
f
a
c
i
a
l
i
m
a
ge
s
w
i
t
h
t
h
e
c
a
m
e
ra
a
nd
a
u
t
om
a
t
i
c
a
l
l
y
c
onv
e
rt
i
ng
t
h
e
m
f
rom
RG
B
i
m
a
g
e
s
t
o
gra
ys
c
a
l
e
i
m
a
ge
s
.
T
he
us
e
of
t
he
H
a
a
r
c
a
s
c
a
de
c
l
a
s
s
i
fi
e
r
m
e
t
h
od
t
o
de
t
e
c
t
f
a
c
e
s
c
a
p
t
ur
e
d
by
t
he
c
a
m
e
r
a
i
s
m
a
rk
e
d
by
a
bl
ue
c
i
rc
l
e
on
t
he
fa
c
e
t
ha
t
h
a
s
b
e
e
n
d
e
t
e
c
t
e
d
[23]
.
T
he
c
on
t
e
n
t
s
of
t
he
da
t
a
s
e
t
a
re
va
r
i
ous
f
a
c
i
a
l
i
m
a
g
e
s
t
ha
t
re
p
re
s
e
n
t
s
ubj
e
c
t
s
fro
m
v
a
ri
o
us
c
on
di
t
i
ons
w
he
n
t
a
ki
n
g
pi
c
t
ur
e
s
,
s
o
t
ha
t
t
h
e
s
ys
t
e
m
c
a
n
re
c
ogn
i
z
e
f
a
c
e
s
a
s
a
w
h
ol
e
,
up
t
o
v
a
ri
ous
s
i
t
ua
t
i
ons
t
h
a
t
o
c
c
ur
.
T
he
de
s
i
gn
of
t
hi
s
s
ys
t
e
m
r
e
qu
i
re
s
da
t
a
pr
e
-
pro
c
e
s
s
i
n
g
s
uc
h
a
s
c
ropp
i
ng,
r
e
s
i
z
i
ng
,
a
nd
c
on
ve
r
t
i
ng
t
o
gra
ys
c
a
l
e
.
T
hi
s
pr
oc
e
s
s
n
e
e
ds
t
o
be
do
ne
t
o
i
m
prov
e
t
h
e
a
c
c
ur
a
c
y
of
fa
c
i
a
l
r
e
c
o
gni
t
i
on
[
24]
.
T
h
e
fl
ow
of
da
t
a
s
e
t
c
re
a
t
i
on
i
s
a
s
fo
l
l
ow
s
i
n
F
i
gu
re
1.
T
he
f
a
c
e
de
t
e
c
t
e
d
by
t
h
e
c
a
m
e
r
a
w
i
l
l
be
kn
ow
n
by
i
t
s
h
i
s
t
og
r
a
m
.
T
h
e
s
ys
t
e
m
w
i
l
l
c
o
m
p
a
r
e
t
h
e
hi
s
t
o
gr
a
m
v
a
l
u
e
o
f
t
h
e
f
a
c
e
d
e
t
e
c
t
e
d
b
y
t
h
e
c
a
m
e
r
a
w
i
t
h
t
h
a
t
i
n
t
he
d
a
t
a
b
a
s
e
.
T
h
e
fa
c
e
w
i
l
l
b
e
r
e
c
og
n
i
z
e
d
i
f
i
t
s
hi
s
t
o
gr
a
m
v
a
l
u
e
i
s
m
os
t
s
i
m
i
l
a
r
t
o
t
h
e
d
a
t
a
.
B
y
a
p
p
l
y
i
ng
t
h
e
l
o
c
a
l
bi
n
a
r
y
p
a
t
t
e
rn
h
i
s
t
og
r
a
m
a
l
g
or
i
t
h
m
,
t
h
e
c
a
m
e
r
a
c
a
n
a
u
t
o
m
a
t
i
c
a
l
l
y
c
o
m
pa
r
e
h
i
s
t
o
gr
a
m
s
on
t
h
e
f
a
c
e
[2
5
]
.
T
h
e
f
a
c
e
r
e
c
o
g
ni
t
i
on
f
l
o
w
i
s
s
h
ow
n
i
n
F
i
g
ur
e
2
.
T
he
d
e
s
i
gn
of
d
i
gi
t
a
l
i
m
a
g
e
proc
e
s
s
i
ng
a
ppl
i
c
a
t
i
ons
for
fa
c
i
a
l
r
e
c
ogni
t
i
on
s
ys
t
e
m
s
h
a
s
i
m
port
a
nt
s
t
e
ps
for
i
t
s
m
a
n
a
ge
m
e
nt
,
s
uc
h
a
s
da
t
a
s
e
t
s
e
p
a
r
a
t
i
on,
p
roc
e
s
s
i
ng
l
e
a
r
ni
ng
,
pre
d
i
c
t
i
o
n,
e
va
l
ua
t
i
o
n,
a
nd
d
i
gi
t
a
l
i
m
a
g
e
proc
e
s
s
i
ng
a
r
c
hi
t
e
c
t
ur
e
de
s
i
g
n
[
26],
[27
]
.
F
i
gure
1
.
D
a
t
a
s
e
t
c
r
e
a
t
i
o
n
f
l
ow
F
i
gure
2
.
F
a
c
e
r
e
c
o
gni
t
i
on
f
l
ow
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2722
-
3221
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
,
V
o
l
.
7
,
N
o
.
1
,
M
a
rc
h
20
2
6
:
1
-
9
4
2.
4
.
S
ys
te
m
i
mp
l
e
me
n
ta
ti
on
D
a
t
a
s
e
t
s
e
pa
r
a
t
i
on
i
s
t
he
be
g
i
nn
i
ng
of
t
he
i
m
pl
e
m
e
nt
a
t
i
on
of
a
s
ys
t
e
m
c
ons
i
s
t
i
ng
of
s
e
v
e
ra
l
f
a
c
i
a
l
i
m
a
ge
s
t
ha
t
a
re
s
e
p
a
ra
t
e
d
i
nt
o
t
w
o
pa
r
t
s
,
na
m
e
l
y
t
ra
i
ni
n
g
d
a
t
a
a
nd
t
e
s
t
da
t
a
.
T
ra
i
ni
ng
d
a
t
a
w
i
l
l
be
us
e
d
t
o
t
r
a
i
n
t
he
di
gi
t
a
l
i
m
a
ge
m
ode
l
,
w
h
i
l
e
t
e
s
t
d
a
t
a
w
i
l
l
be
us
e
d
t
o
t
e
s
t
t
h
e
pe
rf
orm
a
n
c
e
of
t
h
e
t
r
a
i
n
e
d
m
o
de
l
.
T
h
e
n
t
h
e
di
gi
t
a
l
i
m
a
g
e
pro
c
e
s
s
i
n
g
p
ro
c
e
s
s
i
s
c
a
rr
i
e
d
o
ut
us
i
ng
t
r
a
i
ni
ng
d
a
t
a
t
o
t
ra
i
n
di
gi
t
a
l
i
m
a
g
e
s
.
T
he
pr
oc
e
s
s
i
nvol
ve
s
forw
a
r
d
pr
opa
g
a
t
i
on
a
n
d
b
a
c
kw
a
rd
prop
a
g
a
t
i
on
t
o
o
pt
i
m
i
z
e
m
o
de
l
p
a
ra
m
e
t
e
rs
on
f
a
c
i
a
l
p
a
t
t
e
rns
.
D
i
gi
t
a
l
i
m
a
ge
s
a
r
e
t
ra
i
ne
d
t
o
m
a
ke
pr
e
di
c
t
i
ons
o
n
n
e
w
l
y
s
e
e
n
f
a
c
i
a
l
i
m
a
g
e
s
.
T
h
e
proc
e
s
s
i
s
c
a
rr
i
e
d
out
by
c
l
a
s
s
i
fy
i
ng
pre
v
i
ous
l
y
uns
e
e
n
f
a
c
i
a
l
i
m
a
ge
s
t
ha
t
h
a
v
e
be
e
n
l
e
a
rn
e
d
fro
m
d
i
gi
t
a
l
i
m
a
ge
s
.
T
he
r
e
s
ul
t
s
w
i
l
l
l
a
t
e
r
be
us
e
d
t
o
i
de
nt
i
fy
r
e
l
a
t
e
d
i
ndi
v
i
du
a
l
s
.
E
v
a
l
u
a
t
i
on
i
s
t
h
e
fi
na
l
s
t
a
ge
t
o
m
e
a
s
ure
t
h
e
p
e
rfor
m
a
nc
e
of
t
he
di
gi
t
a
l
i
m
a
ge
m
od
e
l
.
S
o
m
e
of
t
he
e
va
l
ua
t
i
o
n
m
e
a
s
ure
s
a
re
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
on
,
r
e
c
a
l
l
,
a
nd
F
1
s
c
or
e
.
T
hi
s
e
va
l
ua
t
i
on
i
s
c
a
rr
i
e
d
o
ut
t
o
a
s
s
e
s
s
t
he
l
e
ve
l
of
s
e
ns
i
t
i
v
i
t
y
of
di
gi
t
a
l
i
m
a
ge
s
i
n
r
e
c
ogni
z
i
n
g
fa
c
e
s
a
c
c
ur
a
t
e
l
y
or
not
.
H
a
a
r
C
a
s
c
a
de
e
x
c
e
l
s
i
n
s
pe
e
d
a
nd
s
i
m
p
l
i
c
i
t
y
b
ut
m
u
l
t
i
-
t
a
s
k
c
a
s
c
a
de
d
c
onvo
l
ut
i
ona
l
ne
t
w
ork
(
M
T
CN
N
)
or
Y
O
L
O
a
re
s
up
e
r
i
or
for
c
om
p
l
e
x
a
nd
h
i
gh
-
pr
e
c
i
s
i
on
a
pp
l
i
c
a
t
i
ons
e
s
p
e
c
i
a
l
l
y
i
n
poor
l
i
gh
t
i
ng
c
ond
i
t
i
ons
,
rot
a
t
i
ons
,
or
v
a
ry
i
ng
e
xp
re
s
s
i
ons
.
3.
R
ES
U
LTS
A
N
D
D
I
S
C
U
S
S
I
O
N
T
he
ha
rdw
a
r
e
i
m
pl
e
m
e
nt
a
t
i
on
e
nv
i
ron
m
e
n
t
us
e
d
ha
s
t
h
e
fo
l
l
ow
i
ng
s
pe
c
i
f
i
c
a
t
i
ons
,
i
n
c
l
u
di
ng
p
roc
e
s
s
or
:
Int
e
l
C
e
l
e
ron
N
4020
(2C
/
2
T
,
1
.
1/
2
.
8G
H
z
,
4
M
B),
s
c
r
e
e
n
:
1
4″
H
D
(1366
×
768)
T
N
2
20ni
t
s
a
nt
i
-
gl
a
re
,
m
e
m
ory
:
4G
B
D
D
R4
-
24
00M
H
z
,
25
6G
B
S
S
D
M
.
2
22
42
P
CI
e
3
.
0×
2
N
V
M
e
s
t
or
a
ge
,
i
nt
e
gra
t
e
d
Int
e
l
U
H
D
G
ra
ph
i
c
s
,
a
nd
2
c
e
l
l
s
35
W
H
35
ba
t
t
e
ry
.
N
e
xt
i
s
t
h
e
s
of
t
w
a
r
e
i
m
p
l
e
m
e
nt
a
t
i
on
e
nv
i
ron
m
e
n
t
us
e
d
,
s
uc
h
a
s
t
h
e
progr
a
m
m
i
n
g
l
a
ng
ua
g
e
us
e
d
i
s
P
y
t
hon
3.
6
,
w
h
i
c
h
ha
s
f
l
e
x
i
bi
l
i
t
y
a
nd
m
a
ny
s
uppor
t
i
ng
l
i
bra
r
i
e
s
i
n
i
m
a
ge
proc
e
s
s
i
ng
.
P
yt
hon
h
a
s
a
n
e
a
s
y
-
to
-
und
e
rs
t
a
nd
s
ynt
a
x
a
nd
e
a
s
e
i
n
ut
i
l
i
z
i
n
g
v
a
ri
o
u
s
l
a
t
e
s
t
t
o
ol
s
a
nd
t
e
c
hn
i
qu
e
s
i
n
a
ppl
i
c
a
t
i
on
de
ve
l
op
m
e
n
t
.
T
h
e
l
i
br
a
ri
e
s
a
nd
fra
m
e
w
o
rks
us
e
d
i
n
t
hi
s
s
t
udy
a
r
e
T
e
ns
orF
l
ow
:
2
.
16
;
K
e
r
a
s
:
3
.
0
.
5;
S
c
i
k
i
t
-
L
e
a
rn:
1
.
4
.
1;
P
a
nd
a
s
:
2
.
2.
1;
O
p
e
nCV
:
4.
9
.
0
.
80
;
M
a
t
p
l
o
t
l
i
b
:
3.
8
.
3
;
a
nd
N
um
P
y
:
1.
26.
4
.
d
e
ve
l
op
m
e
n
t
t
ool
s
us
i
ng
J
upyt
e
r
N
ot
e
book
,
S
pyd
e
r,
a
nd
T
ki
n
t
e
r
.
T
he
r
i
ght
c
om
bi
na
t
i
on
o
f
progr
a
m
m
i
ng
l
a
ngu
a
ge
s
a
nd
l
i
bra
r
i
e
s
w
i
l
l
m
a
k
e
i
t
e
a
s
y
t
o
d
e
v
e
l
op
a
ppl
i
c
a
t
i
ons
w
i
t
h
s
a
t
i
s
fa
c
t
ory
a
n
d
e
f
fi
c
i
e
nt
re
s
u
l
t
s
.
Im
pl
e
m
e
n
t
a
t
i
on
of
f
a
c
i
a
l
re
c
ogn
i
t
i
on
i
s
don
e
by
s
e
pa
r
a
t
i
ng
t
he
d
a
t
a
s
e
t
a
c
c
ord
i
ng
t
o
t
he
na
m
e
t
ha
t
ha
s
be
e
n
re
gi
s
t
e
re
d
i
n
t
he
s
ys
t
e
m
.
G
rou
pi
ng
a
c
c
ord
i
ng
t
o
t
hi
s
d
a
t
a
i
s
don
e
ba
s
e
d
on
t
he
f
a
c
e
of
e
a
c
h
i
ndi
v
i
du
a
l
,
w
ho
w
i
l
l
c
r
e
a
t
e
a
fol
d
e
r
c
on
t
a
i
ni
ng
s
a
m
pl
e
i
m
a
ge
s
of
t
he
i
r
f
a
c
e
.
T
h
e
c
re
a
t
e
_d
i
re
c
t
or
y
fun
c
t
i
on
w
i
l
l
c
re
a
t
e
a
fol
d
e
r
t
h
a
t
w
i
l
l
d
i
vi
d
e
t
h
e
t
yp
e
of
fa
c
e
.
F
ur
t
h
e
r
m
ore
,
t
h
e
s
ys
t
e
m
w
i
l
l
pe
rf
orm
a
n
O
pe
nCV
f
a
c
e
de
t
e
c
t
or
us
i
ng
a
w
e
bc
a
m
.
T
he
de
t
e
c
t
e
d
i
m
a
g
e
w
i
l
l
be
s
t
o
re
d
i
n
t
he
d
i
re
c
t
ory
a
c
c
or
di
ng
t
o
t
he
n
a
m
e
re
gi
s
t
e
re
d
t
o
d
i
s
t
i
ng
ui
s
h
t
he
s
a
m
pl
e
.
A
ft
e
r
t
he
de
t
e
c
t
e
d
f
a
c
e
e
nt
e
rs
t
h
e
di
re
c
t
or
y,
t
h
e
n
e
xt
s
t
e
p
i
s
p
roc
e
s
s
i
ng
t
h
e
d
a
t
a
s
e
t
for
f
a
c
e
s
t
h
a
t
h
a
ve
be
e
n
c
a
t
e
gori
z
e
d
by
n
a
m
e
.
T
he
i
m
a
g
e
s
t
ha
t
ha
v
e
be
e
n
e
nt
e
r
e
d
a
re
c
onve
rt
e
d
t
o
g
ra
ys
c
a
l
e
t
o
re
du
c
e
t
he
d
a
t
a
di
m
e
ns
i
on
,
but
s
t
i
l
l
ge
t
t
h
e
re
q
ui
r
e
d
da
t
a
,
n
a
m
e
l
y
t
he
v
i
s
ua
l
c
h
a
ra
c
t
e
ri
s
t
i
c
s
of
t
he
f
a
c
i
a
l
i
m
a
ge
.
B
e
f
o
r
e
b
e
i
n
g
c
on
v
e
r
t
e
d
t
o
gr
a
ys
c
a
l
e
,
t
h
e
i
m
a
g
e
w
i
l
l
b
e
c
r
o
pp
e
d
s
o
t
h
a
t
o
n
l
y
t
h
e
f
a
c
e
pa
r
t
i
s
o
b
t
a
i
n
e
d
a
s
t
h
e
r
e
q
u
i
r
e
d
d
a
t
a
,
t
h
e
n
t
h
e
i
m
a
g
e
t
h
a
t
h
a
s
g
o
n
e
t
hr
o
ug
h
t
h
e
c
r
op
p
i
n
g
p
ro
c
e
s
s
w
i
l
l
be
r
e
s
i
z
e
d
t
o
10
0
×
1
0
0
p
i
x
e
l
s
s
o
t
ha
t
t
h
e
s
i
z
e
i
s
uni
for
m
a
nd
by
t
he
di
g
i
t
a
l
i
m
a
ge
m
od
e
l
.
O
nl
y
a
f
t
e
r
t
ha
t
a
re
t
he
i
m
a
g
e
s
c
on
ve
r
t
e
d
t
o
gra
ys
c
a
l
e
t
o
fa
c
i
l
i
t
a
t
e
a
na
l
ys
i
s
a
nd
e
f
fi
c
i
e
nc
y
of
t
h
e
d
i
gi
t
a
l
i
m
a
ge
m
od
e
l
,
s
o
t
ha
t
t
h
e
d
a
t
a
s
e
t
i
s
re
a
dy
t
o
b
e
us
e
d
i
n
fa
c
i
a
l
re
c
ogn
i
t
i
on,
a
s
i
n
F
i
g
ure
3.
N
e
xt
,
t
he
f
a
c
e
r
e
c
o
gni
t
i
on
s
ys
t
e
m
us
i
n
g
d
i
gi
t
a
l
i
m
a
ge
s
w
i
l
l
re
c
ogn
i
z
e
kn
ow
n
f
a
c
e
s
a
c
c
ord
i
ng
t
o
t
hos
e
r
e
g
i
s
t
e
r
e
d
i
n
t
he
O
pe
nCV
l
i
br
a
ry.
T
he
r
e
c
ogni
t
i
o
n
s
ys
t
e
m
c
a
n
d
i
r
e
c
t
l
y
us
e
t
he
c
a
m
e
ra
i
n
re
a
l
-
t
i
m
e
.
T
he
re
s
u
l
t
s
of
t
h
i
s
r
e
c
og
ni
t
i
on
w
i
l
l
s
how
t
he
n
a
m
e
o
f
t
he
re
gi
s
t
e
re
d
f
a
c
e
us
e
r
c
on
t
i
n
uous
l
y
,
a
s
i
n
F
i
gur
e
4.
T
he
c
re
a
t
i
on
o
f
t
h
e
b
a
s
i
c
c
on
c
e
p
t
of
di
g
i
t
a
l
i
m
a
ge
a
r
c
hi
t
e
c
t
ur
e
,
c
ov
e
ri
ng
t
h
e
m
a
i
n
l
a
ye
rs
i
n
t
he
form
a
t
i
on
of
di
g
i
t
a
l
i
m
a
ge
s
t
r
uc
t
ure
s
s
uc
h
a
s
c
onv
ol
u
t
i
on
a
l
l
a
ye
rs
,
pool
i
ng
l
a
y
e
rs
,
a
nd
ful
l
y
c
o
nne
c
t
e
d
l
a
ye
rs
,
i
s
c
a
r
ri
e
d
ou
t
a
t
t
h
i
s
s
t
a
ge
.
E
a
c
h
l
a
ye
r
w
i
l
l
e
x
t
ra
c
t
from
e
a
c
h
fa
c
i
a
l
re
c
ogn
i
t
i
on
f
e
a
t
ure
a
nd
c
o
m
bi
n
e
t
he
m
i
n
t
o
one
uni
t
f
or
a
c
c
ur
a
t
e
pr
e
d
i
c
t
i
on
re
s
u
l
t
s
.
T
he
f
i
rs
t
l
a
ye
r
i
s
a
c
onvo
l
ut
i
on
(Conv
2D
)
w
i
t
h
32
fi
l
t
e
rs
m
e
a
s
uri
n
g
3×
3
w
i
t
h
t
h
e
re
c
t
i
fi
e
d
l
i
n
e
a
r
un
i
t
(Re
L
U
)
a
c
t
i
va
t
i
on
fun
c
t
i
on
.
Im
a
ge
i
nput
us
e
s
a
c
o
l
or
i
m
a
g
e
w
i
t
h
di
m
e
ns
i
ons
of
1
00×
1
00
pi
x
e
l
s
.
F
ol
l
ow
e
d
b
y
a
M
a
xP
o
ol
i
ng
l
a
ye
r
(M
a
x
P
ool
i
ng
2D
)
m
e
a
s
ur
i
ng
2
×
2
t
o
r
e
du
c
e
t
he
i
m
a
ge
di
m
e
ns
i
on
.
A
ft
e
r
bo
t
h
of
t
he
s
e
t
hi
ngs
run
,
t
h
e
re
s
u
l
t
s
w
i
l
l
b
e
don
e
f
or
f
l
a
t
t
e
ni
n
g
(dl
a
t
t
e
n)
,
w
hi
c
h
c
ha
n
ge
s
t
h
e
ve
c
t
or
t
o
di
m
e
ns
i
ons
.
T
h
e
v
e
c
t
or
w
i
l
l
b
e
forw
a
rd
e
d
t
o
t
h
e
de
ns
e
l
a
y
e
r
w
i
t
h
12
8
un
i
t
s
a
nd
us
e
s
t
he
Re
L
U
a
c
t
i
v
a
t
i
on
fu
nc
t
i
on
.
T
h
e
d
e
ns
e
re
po
rt
provi
de
s
o
ut
pu
t
a
c
c
ord
i
ng
t
o
t
he
nu
m
be
r
of
fa
c
e
s
r
e
c
ogni
z
e
d
us
i
ng
t
he
so
ft
m
a
x
a
c
t
i
v
a
t
i
on
fun
c
t
i
on
t
o
produ
c
e
pr
e
di
c
t
i
on
prob
a
bi
l
i
t
i
e
s
for
e
a
c
h
c
l
a
s
s
.
T
he
d
e
s
c
r
i
pt
i
on
a
n
d
ra
t
i
on
a
l
e
for
p
a
ra
m
e
t
e
r
s
e
l
e
c
t
i
on
a
re
fr
om
32
fi
l
t
e
rs
a
nd
3
×
3
k
e
rne
l
w
i
t
h
s
m
a
l
l
s
i
z
e
a
n
d
e
ffi
c
i
e
nt
for
i
ni
t
i
a
l
f
e
a
t
ur
e
d
e
t
e
c
t
i
o
n
b
e
c
a
us
e
32
fi
l
t
e
rs
a
re
s
uffi
c
i
e
nt
for
s
m
a
l
l
d
a
t
a
s
e
t
s
.
M
a
xP
oo
l
i
ng
2×
2
c
o
m
m
onl
y
us
e
d
t
o
re
duc
e
t
h
e
s
i
z
e
of
t
he
f
e
a
t
ur
e
m
a
p
w
hi
l
e
pre
s
e
rvi
n
g
i
m
port
a
n
t
fe
a
t
ur
e
s
.
I
n
a
dd
i
t
i
on
,
Re
L
U
s
e
rve
s
a
s
a
pop
ul
a
r
a
c
t
i
va
t
i
on
func
t
i
o
n
be
c
a
us
e
i
t
a
v
o
i
ds
t
h
e
va
n
i
s
hi
n
g
gra
di
e
nt
pr
obl
e
m
a
nd
s
of
t
m
a
x
us
e
d
f
or
m
ul
t
i
c
l
a
s
s
c
l
a
s
s
i
f
i
c
a
t
i
on
i
n
t
h
e
out
p
ut
l
a
ye
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
IS
S
N
:
2722
-
3221
Im
pl
e
m
e
nt
a
t
i
o
n
o
f
f
ac
e
r
e
c
o
gni
t
i
on
us
i
ng
P
y
t
hon
(
F
e
br
i
an
W
ahy
u
Chr
i
s
t
ant
o
)
5
T
h
e
m
o
de
l
t
r
a
i
ni
ng
pro
c
e
s
s
us
e
s
t
h
e
A
da
m
op
t
i
m
i
z
a
t
i
on
a
l
gor
i
t
h
m
t
o
p
rod
uc
e
op
t
i
m
a
l
pr
e
d
i
c
t
i
o
n
prob
a
bi
l
i
t
i
e
s
.
T
h
e
w
a
y
t
h
e
A
d
a
m
m
e
t
hod
w
orks
i
s
t
o
u
pd
a
t
e
t
he
p
a
ra
m
e
t
e
rs
of
t
h
e
m
od
e
l
b
a
s
e
d
o
n
t
he
gr
a
d
i
e
n
t
a
nd
l
o
s
s
fun
c
t
i
on
,
s
o
t
h
a
t
p
e
r
i
o
di
c
a
l
l
y
,
t
he
p
e
r
for
m
a
n
c
e
o
f
t
h
e
s
ys
t
e
m
'
s
d
e
c
i
s
i
o
n
s
e
l
e
c
t
i
o
n
fro
m
i
t
s
pr
e
d
i
c
t
i
ons
be
c
o
m
e
s
b
e
t
t
e
r
[
28
]
.
T
h
e
r
e
s
ul
t
s
o
f
t
he
a
n
a
l
ys
i
s
s
ho
w
t
ha
t
t
he
e
v
a
l
u
a
t
i
o
n
m
a
t
r
i
x
o
b
t
a
i
n
e
d
i
s
a
c
c
u
r
a
t
e
t
o
h
e
l
p
de
t
e
r
m
i
ne
h
ow
w
e
l
l
t
he
m
o
de
l
m
a
t
c
h
e
s
f
a
c
i
a
l
i
m
a
ge
s
i
n
e
a
c
h
c
a
t
e
gor
y
.
T
he
n,
t
h
e
pr
e
c
i
s
i
on
e
v
a
l
ua
t
i
on
i
s
c
a
rr
i
e
d
o
ut
t
o
und
e
rs
t
a
n
d
t
he
re
l
i
a
bi
l
i
t
y
of
t
h
e
m
o
de
l
i
n
i
d
e
n
t
i
fyi
ng
f
a
c
i
a
l
i
m
a
g
e
s
f
ro
m
i
t
s
c
l
a
s
s
[29
]
.
R
e
c
a
l
l
or
s
e
ns
i
t
i
v
i
t
y
l
e
v
e
l
t
o
m
e
a
s
ur
e
t
he
p
rop
or
t
i
on
of
t
he
p
re
di
c
t
e
d
re
s
u
l
t
s
t
o
t
he
a
c
t
u
a
l
p
os
i
t
i
v
e
da
t
a
.
F
1
-
s
c
or
e
i
s
a
m
e
t
r
i
c
t
h
a
t
c
o
m
b
i
n
e
s
p
re
c
i
s
i
on
a
n
d
r
e
c
a
l
l
i
n
t
o
on
e
n
u
m
b
e
r
.
F
1
-
s
c
or
e
p
ro
vi
de
s
a
n
o
ve
rv
i
e
w
of
t
he
qu
a
l
i
t
y
of
t
he
m
o
de
pr
e
d
i
c
t
i
o
n
a
n
d
c
o
ns
i
de
rs
i
t
s
b
a
l
a
n
c
e
.
E
v
a
l
u
a
t
i
o
n
r
e
s
ul
t
s
w
i
l
l
p
rov
i
d
e
i
ns
i
g
ht
s
r
e
l
a
t
e
d
t
o
t
he
p
e
r
for
m
a
n
c
e
of
t
he
d
i
g
i
t
a
l
i
m
a
g
e
m
od
e
l
.
T
he
d
a
t
a
s
how
n
a
r
e
a
c
c
u
ra
c
y,
e
v
a
l
ua
t
i
on
m
a
t
r
i
x
,
a
nd
he
a
t
m
a
p
c
onf
us
i
on
m
a
t
r
i
x
.
F
i
gure
3
.
I
m
a
ge
da
t
a
s
e
t
F
i
gure
4
.
F
a
c
i
a
l
r
e
c
og
ni
t
i
on
pro
c
e
s
s
3.
1
.
Tr
ai
n
i
n
g
an
d
v
al
i
d
a
ti
on
ac
c
u
r
a
c
y
gr
ap
h
A
c
c
ur
a
c
y
a
nd
va
l
i
d
a
t
i
on
t
r
a
i
n
i
ng
pro
c
e
s
s
l
ooks
a
t
h
ow
w
e
l
l
t
h
e
m
od
e
l
l
e
a
r
ns
t
he
da
t
a
a
nd
ge
ne
r
a
l
i
z
e
s
t
o
t
he
t
e
s
t
da
t
a
.
Ch
a
ng
e
s
i
n
m
od
e
l
a
c
c
ur
a
c
y
a
re
m
a
d
e
a
l
o
ng
w
i
t
h
t
h
e
a
ddi
t
i
o
n
of
e
poc
hs
i
nd
i
c
a
t
e
d
by
t
he
t
r
a
i
n
i
ng
a
c
c
ura
c
y
on
t
h
e
b
l
u
e
l
i
n
e
t
o
s
how
h
ow
w
e
l
l
t
he
m
od
e
l
l
e
a
r
ns
t
he
t
r
a
i
n
i
ng
d
a
t
a
w
i
l
l
r
e
m
e
m
b
e
rs
t
he
pa
t
t
e
rns
i
n
t
h
e
da
t
a
.
T
he
or
a
ng
e
l
i
n
e
w
hi
c
h
i
s
t
he
v
a
l
i
da
t
i
on
a
c
c
ura
c
y
s
h
ow
s
how
w
e
l
l
t
h
e
m
od
e
l
ge
ne
r
a
l
i
z
e
s
ne
w
da
t
a
t
ha
t
i
s
no
t
i
n
t
h
e
t
r
a
i
n
i
ng
di
r
e
c
t
ory
t
o
a
voi
d
a
dj
us
t
i
ng
n
e
w
d
a
t
a
.
T
he
r
e
s
ul
t
s
of
t
h
e
va
l
i
da
t
i
on
t
r
a
i
n
i
ng
a
nd
va
l
i
d
a
t
i
on
a
c
c
ur
a
c
y
i
n
di
c
a
t
e
d
by
t
he
bl
u
e
a
nd
or
a
ng
e
l
i
n
e
s
a
re
de
p
i
c
t
e
d
i
n
a
c
h
a
rt
i
n
F
i
gure
5.
B
a
s
e
d
on
t
he
e
poc
h
ve
rs
us
a
c
c
ura
c
y
g
ra
ph
,
t
hi
s
m
od
e
l
a
c
hi
e
ve
s
a
l
e
ve
l
of
a
c
c
u
ra
c
y
s
t
a
b
i
l
i
t
y
re
a
c
hi
n
g
3
e
poc
hs
w
i
t
h
a
t
r
a
i
n
i
ng
a
c
c
ur
a
c
y
r
e
a
c
hi
n
g
9
5%
w
i
t
h
hi
gh
a
nd
s
t
a
bl
e
v
a
l
i
da
t
i
o
n
a
c
c
ura
c
y
.
3.
2
.
Eva
l
u
ati
on
mat
r
i
x
g
r
ap
h
i
c
S
c
ope
of
t
h
e
e
va
l
u
a
t
i
on
m
a
t
ri
x
i
s
a
c
c
u
ra
c
y,
pr
e
c
i
s
i
on
,
r
e
c
a
l
l
,
a
nd
F
1
-
s
c
ore
.
T
hi
s
e
v
a
l
ua
t
i
on
he
l
ps
t
o
fi
nd
o
ut
t
he
s
t
r
e
ngt
hs
a
nd
w
e
a
kne
s
s
e
s
of
t
he
m
o
de
l
for
c
l
us
t
e
ri
ng,
a
s
i
n
F
i
gure
6.
A
s
s
e
s
s
m
e
nt
o
f
t
h
e
e
va
l
ua
t
i
on
m
a
t
ri
x
s
how
s
a
r
a
ng
e
of
0
t
o
1
.
I
f
i
t
s
how
s
t
h
e
num
b
e
r
1,
t
he
n
t
he
p
e
rfor
m
a
n
c
e
o
f
t
he
m
od
e
l
i
s
opt
i
m
a
l
.
T
h
e
gr
a
ph
i
n
F
i
gur
e
5
s
how
s
t
h
e
m
a
xi
m
um
va
l
u
e
,
w
hi
c
h
i
s
97.
5%,
w
i
t
h
go
od
p
e
rfor
m
a
nc
e
i
n
re
c
og
ni
z
i
ng
a
nd
c
l
a
s
s
i
fy
i
ng
fa
c
i
a
l
i
m
a
g
e
s
w
i
t
h
a
hi
gh
l
e
v
e
l
i
n
e
a
c
h
e
va
l
ua
t
i
on
m
a
t
ri
x
.
F
i
gure
5
.
V
a
l
i
da
t
i
on
t
r
a
i
ni
ng
a
c
c
ura
c
y
c
h
a
rt
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2722
-
3221
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
,
V
o
l
.
7
,
N
o
.
1
,
M
a
rc
h
20
2
6
:
1
-
9
6
F
i
gure
6
.
E
va
l
ua
t
i
on
m
a
t
ri
x
gr
a
ph
i
c
3.
3
.
H
e
atm
ap
c
on
fu
s
i
on
matr
i
x
E
va
l
ua
t
i
o
n
t
a
bl
e
of
t
he
c
l
a
s
s
i
f
i
c
a
t
i
on
m
ode
l
p
e
rfor
m
a
n
c
e
i
n
t
he
row
t
a
b
l
e
i
s
t
h
e
a
c
t
ua
l
l
a
be
l
,
a
nd
t
h
e
c
ol
u
m
n
t
a
b
l
e
i
s
t
he
pr
e
di
c
t
e
d
l
a
b
e
l
.
T
he
di
s
t
ri
bu
t
i
o
n
of
m
o
de
l
pr
e
di
c
t
i
ons
i
n
c
ol
or
s
how
s
how
w
e
l
l
t
he
m
od
e
l
pre
di
c
t
s
,
or
t
he
r
e
a
re
e
rr
ors
.
T
h
e
re
a
re
fou
r
c
l
a
s
s
e
s
r
e
g
i
s
t
e
r
e
d,
n
a
m
e
l
y
F
a
di
a
,
V
i
c
ky,
A
ri
f
i
n
,
a
nd
A
i
s
ya
h
.
T
h
e
m
a
t
ri
x
s
how
s
t
he
v
a
l
u
e
of
t
h
e
nu
m
b
e
r
of
pr
e
di
c
t
i
ons
for
m
e
d
by
t
he
m
od
e
l
i
n
e
a
c
h
c
l
a
s
s
a
nd
c
om
p
a
re
d
t
o
t
he
a
c
t
ua
l
c
l
a
s
s
.
T
h
e
a
c
t
u
a
l
l
a
b
e
l
c
l
a
s
s
ha
s
4
na
m
e
s
r
e
gi
s
t
e
re
d
i
n
t
he
m
od
e
l
.
D
i
a
g
ona
l
l
y
fro
m
l
e
ft
t
o
r
i
gh
t
,
t
he
num
b
e
r
o
f
m
od
e
l
pre
di
c
t
i
o
n
v
a
l
u
e
s
i
n
pre
d
i
c
t
i
n
g
t
he
c
o
rre
c
t
l
a
be
l
.
In
t
h
e
F
a
di
a
c
l
a
s
s
,
i
t
s
how
s
6
c
orre
c
t
pre
di
c
t
i
ons
,
t
he
V
i
c
ky
c
l
a
s
s
ha
s
15
c
o
rre
c
t
pr
e
di
c
t
i
ons
,
t
he
A
ri
f
i
n
c
l
a
s
s
h
a
s
9
c
orr
e
c
t
pre
d
i
c
t
i
o
ns
,
a
nd
t
he
A
i
s
ya
h
c
l
a
s
s
h
a
s
1
0
c
orr
e
c
t
pr
e
d
i
c
t
i
ons
.
In
o
t
he
r
c
e
l
l
s
t
h
a
t
s
how
i
nc
o
rre
c
t
pr
e
di
c
t
i
ons
,
t
h
e
r
e
i
s
on
l
y
1
pre
di
c
t
i
on
e
rr
or.
T
he
c
ol
or
a
nd
s
c
a
l
e
i
n
t
he
t
a
bl
e
s
h
ow
t
ha
t
t
he
d
a
rk
c
ol
or
i
s
t
h
e
hi
gh
fr
e
qu
e
nc
y,
a
n
d
t
he
s
c
a
l
e
on
t
he
r
i
gh
t
s
h
ow
s
t
he
r
a
ng
e
of
va
l
ue
s
a
s
s
oc
i
a
t
e
d
w
i
t
h
t
h
e
m
a
t
ri
x
c
ol
o
r.
I
t
c
a
n
be
c
onc
l
ud
e
d
t
h
a
t
t
hi
s
m
ode
l
c
a
n
pr
e
di
c
t
a
c
c
u
ra
t
e
l
y
a
nd
e
ff
e
c
t
i
v
e
l
y
w
i
t
hou
t
a
ny
l
a
c
k
of
v
a
r
i
a
t
i
on
i
n
t
h
e
t
e
s
t
d
a
t
a
a
s
s
h
ow
n
i
n
F
i
gur
e
7
.
F
i
gure
7
.
H
e
a
t
m
a
p
c
onf
us
i
on
m
a
t
r
i
x
T
he
t
e
s
t
i
n
g
pro
c
e
s
s
us
e
s
a
gr
a
phi
c
a
l
us
e
r
i
nt
e
rf
a
c
e
(G
U
I)
di
s
pl
a
y
pr
ogra
m
w
i
t
h
a
n
H
T
M
L
-
ba
s
e
d
c
om
m
a
nd
s
c
ri
p
t
a
nd
i
s
c
om
pa
r
e
d
w
i
t
h
t
h
e
P
y
t
hon
l
a
ngu
a
ge
t
o
r
un
t
he
c
a
m
e
ra
a
nd
d
i
gi
t
a
l
i
m
a
ge
m
ode
l
a
l
gor
i
t
h
m
.
T
he
i
ni
t
i
a
l
s
t
e
p
i
s
t
o
e
n
t
e
r
t
he
us
e
rn
a
m
e
t
o
re
t
ri
e
v
e
fa
c
i
a
l
i
m
a
g
e
da
t
a
100
t
i
m
e
s
a
nd
t
he
n
s
a
ve
i
t
i
n
a
fol
de
r
a
c
c
or
di
ng
t
o
t
he
us
e
rna
m
e
.
T
he
n
e
x
t
s
t
e
p
i
s
t
o
t
e
s
t
t
h
e
r
e
gi
s
t
e
r
e
d
fa
c
e
de
t
e
c
t
i
on
s
ys
t
e
m
,
e
a
c
h
of
w
hi
c
h
i
s
t
e
s
t
e
d
5
t
i
m
e
s
.
B
a
s
e
d
on
t
h
e
t
e
s
t
i
ng
of
t
h
e
f
our
us
e
r
f
a
c
e
s
,
e
a
c
h
of
w
hi
c
h
w
a
s
t
e
s
t
e
d
fi
v
e
t
i
m
e
s
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
IS
S
N
:
2722
-
3221
Im
pl
e
m
e
nt
a
t
i
o
n
o
f
f
ac
e
r
e
c
o
gni
t
i
on
us
i
ng
P
y
t
hon
(
F
e
br
i
an
W
ahy
u
Chr
i
s
t
ant
o
)
7
a
c
c
um
u
l
a
t
e
d
ove
r
20
t
r
i
a
l
s
,
on
l
y
on
e
de
t
e
c
t
i
on
e
r
ror
w
a
s
fo
und,
n
a
m
e
l
y
i
n
us
e
r
V
i
c
k
y
i
n
h
e
r
t
h
i
rd
t
e
s
t
a
s
a
n
unknow
n
fa
c
e
,
a
s
i
n
T
a
b
l
e
1.
Ca
us
e
of
t
he
fa
i
l
ur
e
of
i
de
n
t
i
f
i
c
a
t
i
o
n
of
t
h
e
i
d
e
nt
i
fi
c
a
t
i
on
of
t
h
e
V
i
c
ky
us
e
r
i
s
due
t
o
l
i
ght
i
ng
t
ha
t
i
s
t
oo
bri
g
ht
or
t
o
o
d
a
rk
,
s
o
t
ha
t
fa
c
i
a
l
d
e
t
e
c
t
i
on
t
o
i
de
n
t
i
f
y
m
ov
i
ng
fa
c
e
s
h
a
s
d
i
ffi
c
ul
t
y
.
T
he
l
e
ve
l
of
a
c
c
ura
c
y
o
f
t
h
e
r
e
s
ul
t
s
of
t
hi
s
t
e
s
t
i
s
c
a
l
c
ul
a
t
e
d
us
i
ng
a
pe
rc
e
nt
a
ge
t
h
a
t
p
rodu
c
e
s
95
%
b
a
s
e
d
o
n
19
ou
t
o
f
20
s
u
c
c
e
s
s
ful
t
e
s
t
s
.
T
a
b
l
e
1
.
T
a
b
l
e
r
e
s
u
l
t
s
N
u
m
U
s
e
rn
a
m
e
T
e
s
t
i
n
g
Id
e
n
t
i
fi
c
a
t
i
o
n
r
e
s
u
l
t
s
S
t
a
t
u
s
1
F
a
d
i
a
5
t
i
m
e
s
F
a
d
i
a
5
S
u
c
c
e
s
s
fu
l
l
y
2
V
i
c
k
y
5
t
i
m
e
s
4
V
i
c
k
y
1
U
n
k
n
o
w
n
4
S
u
c
c
e
s
s
fu
l
l
y
1
F
a
i
l
e
d
3
A
ri
fi
n
5
t
i
m
e
s
A
ri
fi
n
5
S
u
c
c
e
s
s
fu
l
l
y
4
A
i
s
y
a
h
5
t
i
m
e
s
A
i
s
y
a
h
5
S
u
c
c
e
s
s
fu
l
l
y
4.
C
O
N
C
LU
S
I
O
N
T
he
c
onc
l
us
i
on
t
ha
t
c
a
n
be
dr
a
w
n
i
s
t
h
a
t
t
h
e
a
c
c
ur
a
c
y
of
t
he
di
g
i
t
a
l
i
m
a
g
e
m
o
de
l
r
e
a
c
h
e
s
a
roun
d
3
e
poc
hs
.
T
h
e
t
r
a
i
n
i
ng
a
c
c
ura
c
y
re
a
c
he
s
95%
w
i
t
h
hi
gh
a
nd
s
t
a
bl
e
va
l
i
d
a
t
i
on
a
c
c
ura
c
y.
S
o
t
ha
t
t
he
m
od
e
l
c
a
n
l
e
a
rn
p
a
t
t
e
r
ns
i
n
t
he
da
t
a
w
e
l
l
a
n
d
c
a
n
g
e
ne
r
a
l
i
z
e
t
o
t
h
e
t
e
s
t
da
t
a
.
T
h
e
m
a
xi
m
um
v
a
l
u
e
o
bt
a
i
n
e
d
i
s
97
.
5%
t
he
r
e
for
e
,
t
h
e
m
o
de
l
ha
s
s
u
c
c
e
e
d
e
d
i
n
do
i
ng
i
t
s
j
ob
i
n
re
c
ogn
i
z
i
ng
a
nd
c
l
a
s
s
i
f
yi
ng
fa
c
e
s
w
e
l
l
by
s
how
i
ng
h
i
gh
l
e
v
e
l
s
of
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
on
,
r
e
c
a
l
l
,
a
nd
F
1
s
c
ore
s
.
S
ys
t
e
m
a
n
a
l
ys
i
s
re
l
a
t
e
d
t
o
f
a
c
e
re
c
ogn
i
t
i
on
w
i
t
h
t
he
a
l
gor
i
t
h
m
m
e
t
hod
c
ondu
c
t
e
d
20
t
ri
a
l
s
w
i
t
h
4
f
a
c
e
n
a
m
e
s
,
a
s
m
a
ny
a
s
400
i
m
a
g
e
s
of
di
ff
e
r
e
nt
f
a
c
e
s
,
g
e
t
t
i
n
g
a
progra
m
a
c
c
u
ra
c
y
l
e
ve
l
of
95%
,
a
nd
f
rom
t
he
ov
e
r
a
l
l
r
e
c
ogni
t
i
on
,
t
h
e
re
w
a
s
on
l
y
1
e
rror
i
n
r
e
c
ogni
t
i
o
n.
P
e
rform
a
n
c
e
n
e
e
d
e
d
for
fur
t
he
r
d
e
v
e
l
op
m
e
nt
i
s
be
t
t
e
r
a
nd
m
ore
c
om
pl
e
x,
w
hi
c
h
r
e
qui
r
e
s
t
h
e
n
e
e
d
t
o
us
e
a
hi
ghe
r
qu
a
l
i
t
y
G
P
U
a
nd
a
hi
gh
e
r
RA
M
s
i
z
e
s
o
t
ha
t
t
he
da
t
a
s
e
t
c
a
n
b
e
e
xp
a
nde
d
a
nd
t
h
e
pr
oc
e
s
s
of
unde
rs
t
a
nd
i
ng
v
a
r
i
a
t
i
ons
be
c
om
e
s
b
e
t
t
e
r
.
T
he
fa
c
i
a
l
r
e
c
ogni
t
i
on
s
ys
t
e
m
c
a
n
a
l
s
o
be
t
e
s
t
e
d
a
g
a
i
n
w
i
t
h
c
e
rt
a
i
n
c
a
s
e
s
s
u
c
h
a
s
f
a
c
i
a
l
rot
a
t
i
on
,
fa
c
i
a
l
e
xpr
e
s
s
i
on
v
a
ri
a
t
i
ons
,
d
i
ffe
re
n
t
l
i
ght
i
ng
,
a
nd
a
g
e
.
E
dg
e
de
pl
oy
m
e
nt
opt
i
m
i
z
e
s
t
h
e
m
od
e
l
t
o
ru
n
e
ffi
c
i
e
nt
l
y
on
Ra
s
pb
e
rry
P
i
,
J
e
t
s
on
N
a
no,
a
nd
ot
h
e
rs
.
E
m
o
t
i
on
d
e
t
e
c
t
i
on
c
a
n
a
l
s
o
be
a
d
de
d
by
a
ddi
ng
a
n
e
m
ot
i
on
c
l
a
s
s
i
fi
c
a
t
i
on
m
odu
l
e
t
o
d
e
t
e
c
t
s
us
pi
c
i
o
us
e
xpr
e
s
s
i
ons
.
M
ul
t
i
-
f
a
c
e
t
ra
c
ki
n
g
w
i
t
h
ID
fo
r
c
row
d
re
c
ogn
i
t
i
on
s
c
e
n
a
ri
os
a
l
ong
w
i
t
h
s
p
oofi
ng
de
fe
ns
e
fo
r
l
i
v
e
ne
s
s
ve
r
i
fi
c
a
t
i
on
,
bl
i
nk
de
t
e
c
t
i
on
,
or
l
i
v
e
s
k
i
n
t
e
xt
ur
e
c
a
n
e
nh
a
nc
e
t
hi
s
s
ys
t
e
m
.
A
C
K
N
O
WL
E
D
G
M
EN
TS
T
he
r
e
s
e
a
rc
h
t
e
a
m
e
xt
e
nds
i
t
s
h
e
a
r
t
fe
l
t
gr
a
t
i
t
u
de
t
o
t
he
U
ni
ve
rs
i
t
a
s
S
e
m
a
ra
n
g,
S
a
t
ya
W
a
c
a
na
Chri
s
t
i
a
n
U
n
i
ve
rs
i
t
y
,
D
e
a
ki
n
U
n
i
ve
rs
i
t
y
,
a
n
d
Bi
n
a
N
us
a
n
t
a
ra
U
n
i
ve
rs
i
t
y
for
t
he
i
r
i
n
va
l
ua
b
l
e
s
upp
ort
a
nd
c
ont
r
i
bu
t
i
on
t
o
t
hi
s
re
s
e
a
r
c
h.
F
U
N
D
I
N
G
I
N
F
O
R
M
A
TI
O
N
N
o
fund
i
ng
i
s
i
nvo
l
ve
d.
A
U
TH
O
R
C
O
N
TR
I
BU
TI
O
N
S
S
TA
T
EM
EN
T
T
hi
s
j
ou
rna
l
us
e
s
t
h
e
Cont
r
i
bu
t
or
Rol
e
s
T
a
xono
m
y
(C
Re
di
T
)
t
o
r
e
c
o
gni
z
e
i
ndi
v
i
du
a
l
a
u
t
hor
c
ont
r
i
bu
t
i
ons
,
r
e
du
c
e
a
ut
hors
h
i
p
di
s
pu
t
e
s
,
a
nd
fa
c
i
l
i
t
a
t
e
c
o
l
l
a
bora
t
i
on
.
N
ame
of
A
u
th
o
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
F
e
bri
a
n
W
a
hyu
Chri
s
t
a
nt
o
✓
✓
✓
✓
✓
✓
✓
✓
H
us
nul
A
r
i
fi
n
✓
✓
✓
✓
✓
✓
Chri
s
t
i
ne
D
e
w
i
✓
✓
✓
✓
✓
✓
T
e
gu
h
P
r
a
s
a
ndy
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
ft
w
a
re
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
rm
a
l
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
s
o
u
rc
e
s
D
:
D
a
t
a
Cu
ra
t
i
o
n
O
:
W
ri
t
i
n
g
-
O
ri
g
i
n
a
l
D
ra
ft
E
:
W
ri
t
i
n
g
-
Re
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
s
u
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
rv
i
s
i
o
n
P
:
P
ro
j
e
c
t
a
d
m
i
n
i
s
t
ra
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
s
i
t
i
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2722
-
3221
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
,
V
o
l
.
7
,
N
o
.
1
,
M
a
rc
h
20
2
6
:
1
-
9
8
C
O
N
F
LI
C
T
O
F
I
N
T
ER
ES
T
S
TA
T
EM
EN
T
A
ut
hors
s
t
a
t
e
no
c
onf
l
i
c
t
of
i
n
t
e
r
e
s
t
.
D
A
TA
A
V
A
I
LA
BI
LI
TY
N
o
da
t
a
a
re
a
v
a
i
l
a
b
l
e
for
s
ha
r
i
ng
a
s
t
h
i
s
r
e
s
e
a
rc
h
di
d
n
ot
us
e
a
n
e
xt
e
rn
a
l
da
t
a
s
e
t
.
R
EF
ER
EN
C
ES
[1
]
Z
.
S
.
S
h
o
u
ra
n
,
N
.
Ro
k
h
m
a
n
,
a
n
d
T
.
K
.
P
ri
y
a
m
b
o
d
o
,
“
S
y
s
t
e
m
s
e
c
u
ri
t
y
a
w
a
re
n
e
s
s
p
l
a
n
n
i
n
g
m
o
d
e
l
u
s
i
n
g
t
h
e
o
c
t
a
v
e
m
e
t
h
o
d
a
p
p
ro
a
c
h
,
”
IJ
CCS
(In
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
Co
m
p
u
t
i
n
g
a
n
d
Cy
b
e
r
n
e
t
i
c
s
S
y
s
t
e
m
s
)
,
v
o
l
.
1
3
,
n
o
.
3
,
2
0
1
9
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
c
c
s
.
4
3
9
2
2
.
[2
]
H
.
F
i
t
ri
y
a
h
a
n
d
E
.
R
.
W
i
d
a
s
a
ri
,
“
F
a
c
e
d
e
t
e
c
t
i
o
n
o
f
t
h
e
rm
a
l
i
m
a
g
e
s
i
n
v
a
ri
o
u
s
s
t
a
n
d
i
n
g
b
o
d
y
-
p
o
s
e
u
s
i
n
g
fa
c
i
a
l
g
e
o
m
e
t
ry
,
”
IJ
CCS
(In
d
o
n
e
s
i
a
n
J
o
u
r
n
a
l
o
f
Co
m
p
u
t
i
n
g
a
n
d
Cy
b
e
r
n
e
t
i
c
s
S
y
s
t
e
m
s
)
,
v
o
l
.
1
4
,
n
o
.
4
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
c
c
s
.
5
9
6
7
2
.
[3
]
A
.
W
.
D
o
rn
,
S
.
W
e
b
b
,
a
n
d
S
.
P
â
q
u
e
t
,
“
F
ro
m
w
a
rg
a
m
i
n
g
t
o
p
e
a
c
e
g
a
m
i
n
g
:
d
i
g
i
t
a
l
s
i
m
u
l
a
t
i
o
n
s
w
i
t
h
p
e
a
c
e
k
e
e
p
e
r
ro
l
e
s
n
e
e
d
e
d
,
”
In
t
e
r
n
a
t
i
o
n
a
l
P
e
a
c
e
k
e
e
p
i
n
g
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
2
8
9
–
3
1
0
,
M
a
r.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
1
3
5
3
3
3
1
2
.
2
0
2
0
.
1
7
2
1
2
8
7
.
[4
]
A
.
V
a
t
re
s
i
a
,
R.
F
a
u
ri
n
a
,
V
.
P
u
rn
a
m
a
s
a
ri
,
a
n
d
I.
A
g
u
s
t
i
a
n
,
“
A
u
t
o
m
a
t
i
c
fi
s
h
i
d
e
n
t
i
fi
c
a
t
i
o
n
u
s
i
n
g
s
i
n
g
l
e
s
h
o
t
d
e
t
e
c
t
o
r,
”
Co
m
m
IT
J
o
u
r
n
a
l
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
1
6
7
–
1
7
4
,
J
u
n
.
2
0
2
2
,
d
o
i
:
1
0
.
2
1
5
1
2
/
c
o
m
m
i
t
.
v
1
6
i
2
.
8
1
2
6
.
[5
]
J
.
N
i
,
R
.
W
a
n
g
,
a
n
d
J
.
T
a
n
g
,
“
A
D
S
S
D
:
i
m
p
ro
v
e
d
s
i
n
g
l
e
-
s
h
o
t
d
e
t
e
c
t
o
r
w
i
t
h
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
s
m
a
n
d
d
i
l
a
t
e
d
c
o
n
v
o
l
u
t
i
o
n
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
6
,
M
a
r.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
0
6
4
0
3
8
.
[6
]
S
.
S
u
n
a
rd
i
,
A
.
F
a
d
l
i
l
,
a
n
d
D
.
P
ra
y
o
g
i
,
“
F
a
c
e
re
c
o
g
n
i
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
rn
i
n
g
a
l
g
o
ri
t
h
m
b
a
s
e
d
o
n
Ra
s
p
b
e
rry
P
i
4
b
,
”
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
In
t
e
l
l
i
g
e
n
c
e
R
e
s
e
a
r
c
h
,
v
o
l
.
IS
S
N
,
n
o
.
1
,
p
p
.
2
5
7
9
–
7
2
9
8
,
2
0
22.
[7
]
G
.
W
a
n
g
,
J
.
L
i
,
Z
.
W
u
,
J
.
X
u
,
J
.
S
h
e
n
,
a
n
d
W
.
Y
a
n
g
,
“
E
f
fi
c
i
e
n
t
F
a
c
e
:
a
n
e
ffi
c
i
e
n
t
d
e
e
p
n
e
t
w
o
rk
w
i
t
h
fe
a
t
u
re
e
n
h
a
n
c
e
m
e
n
t
fo
r
a
c
c
u
ra
t
e
fa
c
e
d
e
t
e
c
t
i
o
n
,
”
M
u
l
t
i
m
e
d
i
a
S
y
s
t
e
m
s
,
v
o
l
.
2
9
,
n
o
.
5
,
p
p
.
2
8
2
5
–
2
8
3
9
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
0
0
5
3
0
-
023
-
0
1
1
3
4
-
6.
[8
]
A
b
a
l
l
e
e
t
a
l
.
,
“
S
e
c
u
ri
t
y
m
e
a
s
u
re
s
:
e
ffe
c
t
i
v
e
n
e
s
s
o
f
t
h
e
i
n
s
t
a
l
l
a
t
i
o
n
o
f
CCT
V
c
a
m
e
ra
s
i
n
re
l
a
t
i
o
n
t
o
c
ri
m
e
p
re
v
e
n
t
i
o
n
a
s
p
e
rc
e
i
v
e
d
b
y
t
h
e
c
o
m
m
u
n
i
t
y
,
”
M
i
d
d
l
e
E
a
s
t
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
0
5
,
n
o
.
0
2
,
p
p
.
1
4
9
–
1
6
0
,
2
0
2
2
,
d
o
i
:
1
0
.
4
6
4
3
1
/
m
e
j
a
s
t
.
2
0
2
2
.
5
2
1
6
.
[9
]
I.
H
.
A
l
A
m
i
n
,
D
.
E
.
M
a
ri
n
d
a
,
E
.
W
i
n
a
rn
o
,
U
.
N
.
D
.
H
a
n
d
a
y
a
n
i
,
a
n
d
V
.
L
u
s
i
a
n
a
,
“
Re
a
l
-
t
i
m
e
d
e
t
e
c
t
i
o
n
o
f
fa
c
e
m
a
s
k
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
ra
l
n
e
t
w
o
r
k
,
”
J
u
r
n
a
l
R
E
S
T
I
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
6
9
7
–
7
0
4
,
J
u
n
.
2
0
2
3
,
d
o
i
:
1
0
.
2
9
2
0
7
/
re
s
t
i
.
v
7
i
3
.
5
0
3
6
.
[1
0
]
M
.
K
.
Be
n
k
a
d
d
o
u
r,
S
.
L
a
h
l
a
l
i
,
a
n
d
M
.
T
ra
b
e
l
s
i
,
“
H
u
m
a
n
a
g
e
a
n
d
g
e
n
d
e
r
c
l
a
s
s
i
fi
c
a
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
ra
l
n
e
t
w
o
rk
,
”
i
n
2
0
2
0
2
n
d
In
t
e
r
n
a
t
i
o
n
a
l
W
o
r
k
s
h
o
p
o
n
H
u
m
a
n
-
Ce
n
t
r
i
c
S
m
a
r
t
E
n
v
i
r
o
n
m
e
n
t
s
f
o
r
H
e
a
l
t
h
a
n
d
W
e
l
l
-
B
e
i
n
g
,
IH
S
H
2
0
2
0
,
F
e
b
.
2
0
2
1
,
p
p
.
2
1
5
–
2
2
0
.
d
o
i
:
1
0
.
1
1
0
9
/
IH
S
H
5
1
6
6
1
.
2
0
2
1
.
9
3
7
8
7
0
8
.
[1
1
]
N
.
K
a
s
h
y
a
p
,
A
.
M
a
n
n
,
a
n
d
N
.
S
h
a
rm
a
,
“
A
g
e
a
n
d
g
e
n
d
e
r
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
,
”
S
S
R
N
E
l
e
c
t
r
o
n
i
c
J
o
u
r
n
a
l
,
2
0
2
4
,
d
o
i
:
1
0
.
2
1
3
9
/
s
s
rn
.
4
9
3
1
5
3
0
.
[1
2
]
J
.
P
.
T
a
n
j
u
n
g
,
M
.
R.
F
a
l
d
i
,
H
.
S
i
t
o
m
p
u
l
,
M
.
R
i
d
h
o
,
a
n
d
J
.
P
.
A
m
b
a
ri
t
a
,
“
O
p
t
i
m
i
z
i
n
g
g
e
n
d
e
r
c
l
a
s
s
i
fi
c
a
t
i
o
n
a
c
c
u
ra
c
y
i
n
fa
c
i
a
l
i
m
a
g
e
s
u
s
i
n
g
d
a
t
a
a
u
g
m
e
n
t
a
t
i
o
n
a
n
d
i
n
c
e
p
t
i
o
n
V
-
3
,
”
S
i
n
k
r
o
n
,
v
o
l
.
8
,
n
o
.
4
,
p
p
.
2
6
2
7
–
2
6
3
4
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
3
3
3
9
5
/
s
i
n
k
ro
n
.
v
8
i
4
.
1
2
7
8
5
.
[1
3
]
S
.
M
.
D
a
n
i
y
a
l
,
A
.
M
a
s
o
o
d
,
M
.
E
b
ra
h
i
m
,
M
.
E
b
ra
h
i
m
,
S
.
H
.
A
d
i
l
,
a
n
d
K
.
R
a
z
a
,
“
A
n
i
m
p
ro
v
e
d
fa
c
e
re
c
o
g
n
i
t
i
o
n
m
e
t
h
o
d
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
ra
l
n
e
t
w
o
rk
,
”
J
o
u
r
n
a
l
o
f
In
d
e
p
e
n
d
e
n
t
S
t
u
d
i
e
s
a
n
d
R
e
s
e
a
r
c
h
Co
m
p
u
t
i
n
g
,
v
o
l
.
2
2
,
n
o
.
1
,
2
0
2
4
,
d
o
i
:
1
0
.
3
1
6
4
5
/
J
IS
RC.
2
4
.
2
2
.
1
.
1
0
.
[1
4
]
R.
M
a
t
u
l
i
o
n
y
t
e
a
n
d
M
.
Z
a
l
n
i
e
ri
u
t
e
,
T
h
e
Ca
m
b
r
i
d
g
e
h
a
n
d
b
o
o
k
o
f
f
a
c
i
a
l
r
e
c
o
g
n
i
t
i
o
n
i
n
t
h
e
m
o
d
e
r
n
s
t
a
t
e
.
Ca
m
b
ri
d
g
e
U
n
i
v
e
rs
i
t
y
P
re
s
s
,
2
0
2
4
.
d
o
i
:
1
0
.
1
0
1
7
/
9
7
8
1
0
0
9
3
2
1
2
1
1
.
[1
5
]
K
.
N
.
S
i
n
g
h
,
O
.
P
.
S
i
n
g
h
,
a
n
d
A
.
K
.
S
i
n
g
h
,
“
E
C
i
S
:
E
n
c
ry
p
t
i
o
n
p
ri
o
r
t
o
c
o
m
p
re
s
s
i
o
n
fo
r
d
i
g
i
t
a
l
i
m
a
g
e
s
e
c
u
ri
t
y
w
i
t
h
re
d
u
c
e
d
m
e
m
o
ry
,
”
Co
m
p
u
t
e
r
Co
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
3
,
p
p
.
4
1
0
–
4
1
7
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
c
o
m
.
2
0
2
2
.
0
7
.
0
4
9
.
[1
6
]
H
.
L
.
G
u
ru
ra
j
,
B.
C.
S
o
u
n
d
a
ry
a
,
S
.
P
ri
y
a
,
J
.
S
h
re
y
a
s
,
a
n
d
F
.
F
l
a
m
m
i
n
i
,
“
A
c
o
m
p
re
h
e
n
s
i
v
e
re
v
i
e
w
o
f
fa
c
e
re
c
o
g
n
i
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
t
re
n
d
s
,
a
n
d
c
h
a
l
l
e
n
g
e
s
,
”
IE
E
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
1
0
7
9
0
3
–
1
0
7
9
2
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
CCE
S
S
.
2
0
2
4
.
3
4
2
4
9
3
3
.
[1
7
]
W
.
X
u
e
,
Z
.
Z
h
e
n
g
,
F
.
L
u
,
H
.
W
e
i
,
G
.
Ch
e
n
,
a
n
d
C.
J
i
a
n
g
,
“
G
e
o
N
L
F
:
g
e
o
m
e
t
ry
g
u
i
d
e
d
p
o
s
e
-
fre
e
n
e
u
ra
l
L
i
D
A
R
fi
e
l
d
s
,
”
A
d
v
a
n
c
e
s
i
n
Ne
u
r
a
l
In
f
o
r
m
a
t
i
o
n
P
r
o
c
e
s
s
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
3
7
,
2
0
2
4
.
[1
8
]
A
.
B
.
S
h
e
t
t
y
,
Bh
o
o
m
i
k
a
,
D
e
e
k
s
h
a
,
J
.
Re
b
e
i
ro
,
a
n
d
Ra
m
y
a
s
h
re
e
,
“
F
a
c
i
a
l
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
H
a
a
r
c
a
s
c
a
d
e
a
n
d
L
BP
c
l
a
s
s
i
f
i
e
rs
,
”
G
l
o
b
a
l
T
r
a
n
s
i
t
i
o
n
s
P
r
o
c
e
e
d
i
n
g
s
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
3
3
0
–
3
3
5
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
l
t
p
.
2
0
2
1
.
0
8
.
0
4
4
.
[1
9
]
A
.
W
i
l
l
i
s
a
n
d
K
.
H
a
s
a
n
,
“
S
i
m
p
l
e
c
o
m
p
u
t
e
r
v
i
s
i
o
n
a
l
g
o
ri
t
h
m
p
ro
d
u
c
t
i
o
n
u
s
i
n
g
O
p
e
n
CV
fo
r
"
v
i
r
t
u
a
l
e
c
o
s
y
s
t
e
m
”
p
ro
j
e
c
t
,
”
IJ
NM
T
(In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ne
w
M
e
d
i
a
T
e
c
h
n
o
l
o
g
y
)
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
2
3
–
2
7
,
J
u
l
.
2
0
2
0
,
d
o
i
:
1
0
.
3
1
9
3
7
/
i
j
n
m
t
.
v
7
i
1
.
1
6
6
0
.
[2
0
]
K
.
Bu
ru
g
u
,
V
.
D
o
d
d
a
,
V
.
Ra
j
m
o
o
r,
S
.
C.
Y
e
rra
,
a
n
d
S
.
Bh
u
t
a
d
a
,
“
S
e
c
u
ri
t
y
s
u
rv
e
i
l
l
a
n
c
e
m
o
n
i
t
o
ri
n
g
s
y
s
t
e
m
u
s
i
n
g
O
p
e
n
CV
,
”
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
R
e
s
e
a
r
c
h
i
n
Co
m
p
u
t
e
r
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
r
i
n
g
a
n
d
In
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
8
,
n
o
.
3
,
p
p
.
4
0
2
–
4
0
7
,
2
0
2
2
.
[2
1
]
R.
B.
Y
.
A
l
-
K
h
a
fa
j
i
,
“
U
s
i
n
g
t
e
c
h
n
o
l
o
g
y
a
n
d
a
l
g
o
ri
t
h
m
s
fo
r
fa
c
e
d
e
t
e
c
t
i
o
n
a
n
d
re
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
i
g
i
t
a
l
i
m
a
g
e
p
ro
c
e
s
s
i
n
g
a
n
d
re
l
y
i
n
g
o
n
a
c
o
m
p
u
t
e
r
v
i
s
i
o
n
s
e
n
s
o
r,
”
J
o
u
r
n
a
l
o
f
In
f
o
r
m
a
t
i
o
n
S
y
s
t
e
m
s
E
n
g
i
n
e
e
r
i
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
,
v
o
l
.
9
,
n
o
.
1
,
J
a
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
5
2
6
7
/
i
a
d
t
.
0
7
.
1
4
3
2
8
.
[2
2
]
H
.
P
u
t
ri
e
t
a
l
.
,
“
S
e
c
u
ri
t
y
s
y
s
t
e
m
fo
r
d
o
o
r
l
o
c
k
s
u
s
i
n
g
Y
O
L
O
-
b
a
s
e
d
fa
c
e
re
c
o
g
n
i
t
i
o
n
,
”
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
In
f
o
r
m
a
t
i
c
s
V
i
s
u
a
l
i
z
a
t
i
o
n
,
v
o
l
.
9
,
n
o
.
1
,
p
p
.
2
2
4
–
2
3
0
,
J
a
n
.
2
0
2
5
,
d
o
i
:
1
0
.
6
2
5
2
7
/
j
o
i
v
.
9
.
1
.
2
4
1
0
.
[2
3
]
H
.
J
.
M
u
n
a
n
d
M
.
H
.
L
e
e
,
“
D
e
s
i
g
n
fo
r
v
i
s
i
t
o
r
a
u
t
h
e
n
t
i
c
a
t
i
o
n
b
a
s
e
d
o
n
fa
c
e
re
c
o
g
n
i
t
i
o
n
t
e
c
h
n
o
l
o
g
y
u
s
i
n
g
CCT
V
,
”
IE
E
E
A
c
c
e
s
s
,
v
o
l
.
1
0
,
p
p
.
1
2
4
6
0
4
–
1
2
4
6
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
A
CCE
S
S
.
2
0
2
2
.
3
2
2
3
3
7
4
.
[2
4
]
B.
K
o
o
d
a
l
s
a
m
y
,
M
.
B.
V
e
e
ra
y
a
n
,
a
n
d
V
.
N
a
ra
y
a
n
a
s
a
m
y
,
“
F
a
c
e
re
c
o
g
n
i
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
rn
i
n
g
,
”
E
3
S
W
e
b
o
f
Co
n
f
e
r
e
n
c
e
s
,
v
o
l
.
3
8
7
,
M
a
y
2
0
2
3
,
d
o
i
:
1
0
.
1
0
5
1
/
e
3
s
c
o
n
f/
2
0
2
3
3
8
7
0
5
0
0
1
.
[2
5
]
M
.
H
.
A
b
d
u
rra
h
m
a
n
,
H
.
A
m
ra
n
D
a
rw
i
t
o
,
a
n
d
A
.
S
a
l
e
h
,
“
F
a
c
e
re
c
o
g
n
i
t
i
o
n
s
y
s
t
e
m
fo
r
p
re
v
e
n
t
i
o
n
o
f
c
a
r
t
h
e
ft
w
i
t
h
H
a
a
r
c
a
s
c
a
d
e
a
n
d
l
o
c
a
l
b
i
n
a
ry
p
a
t
t
e
rn
h
i
s
t
o
g
ra
m
u
s
i
n
g
Ra
s
p
b
e
rr
y
P
i
,
”
E
M
IT
T
E
R
In
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
T
e
c
h
n
o
l
o
g
y
,
p
p
.
4
0
7
–
4
2
5
,
D
e
c
.
2
0
2
0
,
d
o
i
:
1
0
.
2
4
0
0
3
/
e
m
i
t
t
e
r.
v
8
i
2
.
5
3
4
.
[2
6
]
X
.
F
u
,
“
D
e
s
i
g
n
o
f
fa
c
i
a
l
re
c
o
g
n
i
t
i
o
n
s
y
s
t
e
m
b
a
s
e
d
o
n
v
i
s
u
a
l
c
o
m
m
u
n
i
c
a
t
i
o
n
e
ffe
c
t
,
”
Co
m
p
u
t
a
t
i
o
n
a
l
In
t
e
l
l
i
g
e
n
c
e
a
n
d
Ne
u
r
o
s
c
i
e
n
c
e
,
v
o
l
.
2
0
2
1
,
n
o
.
1
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
1
/
1
5
3
9
5
9
6
.
[2
7
]
X
.
L
i
u
a
n
d
R.
Y
a
o
,
“
D
e
s
i
g
n
o
f
v
i
s
u
a
l
c
o
m
m
u
n
i
c
a
t
i
o
n
t
e
a
c
h
i
n
g
s
y
s
t
e
m
b
a
s
e
d
o
n
a
rt
i
fi
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
CA
D
t
e
c
h
n
o
l
o
g
y
,
”
Co
m
p
u
t
e
r
-
A
i
d
e
d
D
e
s
i
g
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
,
n
o
.
S
1
0
,
p
p
.
9
0
–
1
0
1
,
A
p
r.
2
0
2
3
,
d
o
i
:
1
0
.
1
4
7
3
3
/
c
a
d
a
p
s
.
2
0
2
3
.
S
1
0
.
9
0
-
1
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Com
pu
t
S
c
i
Inf
T
e
c
h
nol
IS
S
N
:
2722
-
3221
Im
pl
e
m
e
nt
a
t
i
o
n
o
f
f
ac
e
r
e
c
o
gni
t
i
on
us
i
ng
P
y
t
hon
(
F
e
br
i
an
W
ahy
u
Chr
i
s
t
ant
o
)
9
[2
8
]
Y
.
S
h
a
o
e
t
a
l
.
,
“
A
n
i
m
p
ro
v
e
d
BG
E
-
A
d
a
m
o
p
t
i
m
i
z
a
t
i
o
n
a
l
g
o
ri
t
h
m
b
a
s
e
d
o
n
e
n
t
ro
p
y
w
e
i
g
h
t
i
n
g
a
n
d
a
d
a
p
t
i
v
e
g
r
a
d
i
e
n
t
s
t
ra
t
e
g
y
,
”
S
y
m
m
e
t
r
y
,
v
o
l
.
1
6
,
n
o
.
5
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
s
y
m
1
6
0
5
0
6
2
3
.
[2
9
]
N
.
X
i
a
o
,
X
.
H
u
,
X
.
L
i
u
,
a
n
d
K
.
-
C
.
T
o
h
,
“
A
d
a
m
-
fa
m
i
l
y
m
e
t
h
o
d
s
fo
r
n
o
n
s
m
o
o
t
h
o
p
t
i
m
i
z
a
t
i
o
n
w
i
t
h
c
o
n
v
e
rg
e
n
c
e
g
u
a
ra
n
t
e
e
s
,
”
J
o
u
r
n
a
l
o
f
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
R
e
s
e
a
r
c
h
,
v
o
l
.
2
5
,
p
p
.
1
-
5
3
,
2
0
2
4
.
BI
O
G
R
A
P
H
I
ES
O
F
A
U
T
H
O
R
S
F
e
b
r
i
an
Wah
y
u
C
h
r
i
s
t
an
t
o
r
e
c
e
i
v
e
d
t
he
B
.
S
.
de
g
r
e
e
i
n
I
n
f
or
m
a
t
i
c
E
n
gi
ne
e
r
i
ng
i
n
20
10
a
n
d
h
i
s
M
.
S
.
i
n
I
nf
o
r
m
a
t
i
o
n
S
ys
t
e
m
i
n
2
012
r
e
s
pe
c
t
i
ve
l
y
f
r
om
t
h
e
S
a
t
ya
W
a
c
a
n
a
C
hr
i
s
t
i
a
n
U
n
i
v
e
r
s
i
t
y
,
S
a
l
a
t
i
g
a
,
I
ndon
e
s
i
a
.
S
i
n
c
e
20
13
he
h
a
s
be
e
n
a
n
A
s
s
i
s
t
a
nt
P
r
o
f
e
s
s
o
r
a
t
t
he
I
nf
or
m
a
t
i
on
T
e
c
hn
ol
o
gy
D
e
p
a
r
t
m
e
n
t
o
f
U
ni
ve
r
s
i
t
a
s
S
e
m
a
r
a
ng
,
I
ndone
s
i
a
.
H
e
ha
s
pub
l
i
s
he
d
s
e
ve
r
a
l
j
o
ur
n
a
l
a
nd
c
o
nf
e
r
e
nc
e
a
r
t
i
c
l
e
s
i
n
h
i
s
a
r
e
a
s
a
n
d
a
c
t
i
ve
a
s
a
r
e
vi
e
w
e
r
a
nd
gu
e
s
t
e
di
t
o
r
i
n
m
a
n
y
j
o
ur
n
a
l
s
.
H
i
s
r
e
s
e
a
r
c
h
i
nt
e
r
e
s
t
s
i
nc
l
ud
e
c
o
m
pu
t
e
r
ne
t
w
o
r
ki
ng,
i
nt
e
r
ne
t
of
t
hi
ngs
,
a
n
d
so
f
t
w
a
r
e
e
ng
i
n
e
e
r
i
n
g.
H
e
c
a
n
be
c
on
t
a
c
t
e
d
a
t
e
m
a
i
l
:
f
e
b
r
i
a
n.
w
a
hy
u.
c
hr
i
s
t
a
n
t
o
@us
m
.
a
c
.
i
d
.
H
u
s
n
u
l
A
r
i
f
i
n
r
e
c
e
i
ve
d
t
he
B
a
c
h
e
l
o
r
o
f
I
nf
or
m
a
t
i
c
s
E
ng
i
ne
e
r
i
n
g
(
S
.
K
o
m
.
)
f
r
om
t
he
D
e
pa
r
t
m
e
n
t
o
f
I
n
f
or
m
a
t
i
on
T
e
c
hn
ol
o
gy
U
ni
ve
r
s
i
t
a
s
S
e
m
a
r
a
n
g,
I
ndon
e
s
i
a
i
n
2024
.
H
is
r
e
s
e
a
r
c
h
t
o
pi
c
s
i
n
c
l
u
de
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
ge
n
c
e
a
nd
ob
j
e
c
t
de
t
e
c
t
i
on
a
nd
r
e
c
ogn
i
t
i
o
n.
H
e
c
a
n
be
c
ont
a
c
t
e
d
a
t
e
m
a
i
l
:
a
r
i
f
i
n
hus
n
ul
20@
gm
a
i
l
.
c
o
m
.
C
h
r
i
s
t
i
n
e
D
e
w
i
r
e
c
e
i
v
e
d
a
B
.
S
.
D
e
g
r
e
e
f
r
om
t
he
I
nf
or
m
a
t
i
c
s
E
ngi
n
e
e
r
i
n
g
s
t
ud
y
pr
og
r
a
m
i
n
20
10,
a
nd
a
M
a
s
t
e
r
of
C
o
m
p
ut
e
r
S
c
i
e
nc
e
f
r
o
m
t
h
e
M
a
s
t
e
r
of
I
nf
or
m
a
t
i
on
S
y
s
t
e
m
s
s
t
ud
y
pr
o
gr
a
m
i
n
201
2,
bo
t
h
f
r
o
m
t
h
e
S
a
t
ya
W
a
c
a
na
C
hr
i
s
t
i
a
n
U
n
i
ve
r
s
i
t
y
,
S
a
l
a
t
i
ga
,
I
ndon
e
s
i
a
.
I
n
2021
s
he
f
i
n
i
s
h
e
d
he
r
P
h
.
D
.
a
nd
w
or
k
a
s
a
pos
t
d
oc
t
or
a
l
r
e
s
e
a
r
c
he
r
a
t
C
h
a
oy
a
ng
U
n
i
ve
r
s
i
t
y
of
T
e
c
h
nol
ogy
,
T
a
i
w
a
n
un
t
i
l
2
022
.
S
he
i
s
n
ow
a
n
A
s
s
o
c
i
a
t
e
P
r
of
e
s
s
o
r
i
n
t
he
D
e
pa
r
t
m
e
n
t
o
f
I
nf
or
m
a
t
i
on
T
e
c
hno
l
ogy
o
f
S
a
t
ya
W
a
c
a
na
C
hr
i
s
t
i
a
n
U
n
i
ve
r
s
i
t
y,
I
n
done
s
i
a
a
nd
R
e
s
e
a
r
c
h
e
r
a
t
D
e
a
ki
n
U
n
i
v
e
r
s
i
t
y,
A
u
s
t
r
a
l
i
a
.
S
he
i
s
a
c
t
i
v
e
a
s
a
r
e
v
i
e
w
e
r
a
n
d
gu
e
s
t
e
d
i
t
o
r
i
n
m
a
ny
j
our
na
l
s
.
H
e
r
c
ur
r
e
n
t
r
e
s
e
a
r
c
h
i
nt
e
r
e
s
t
s
i
n
c
l
ude
i
m
a
ge
pr
oc
e
s
s
i
ng
,
c
o
m
pu
t
e
r
vi
s
i
on
,
obj
e
c
t
d
e
t
e
c
t
i
on
a
nd
r
e
c
o
gn
i
t
i
on
,
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
ge
nc
e
,
a
nd
m
a
c
hi
ne
l
e
a
r
ni
ng.
S
h
e
c
a
n
b
e
c
on
t
a
c
t
e
d
a
t
e
m
a
i
l
:
c
.
d
e
w
i
@de
a
ki
n.
e
du
.
a
u
o
r
c
h
r
i
s
t
i
ne
.
d
e
w
i
@
uks
w
.
e
du.
T
e
gu
h
P
r
a
s
an
d
y
w
o
r
k
i
ng
a
s
a
n
O
n
l
i
ne
L
e
c
t
ur
e
r
C
oo
r
d
i
na
t
o
r
i
n
t
h
e
B
us
i
n
e
s
s
C
om
p
e
t
i
t
i
v
e
I
nt
e
l
l
i
ge
n
c
e
G
r
oup
a
t
t
h
e
I
nf
or
m
a
t
i
on
S
ys
t
e
m
D
e
pa
r
t
m
e
n
t
,
B
i
n
a
N
u
s
a
n
t
a
r
a
U
ni
ve
r
s
i
t
y,
I
ndone
s
i
a
.
G
r
a
dua
t
e
d
f
r
o
m
W
a
t
e
r
R
e
s
ou
r
c
e
s
M
a
n
a
ge
m
e
nt
,
D
i
pon
e
go
r
o
U
n
i
v
e
r
s
i
t
y
i
n
2007
.
G
r
a
dua
t
e
d
f
r
o
m
t
h
e
M
a
s
t
e
r
of
I
nf
o
r
m
a
t
i
on
S
ys
t
e
m
s
,
D
i
p
o
ne
go
r
o
U
ni
v
e
r
s
i
t
y
i
n
2
011
.
a
nd
gr
a
dua
t
e
d
f
r
o
m
I
nf
o
r
m
a
t
i
c
s
E
ng
i
ne
e
r
i
ng
,
U
ni
ve
r
s
i
t
a
s
S
e
m
a
r
a
ng
i
n
20
16.
I
nt
e
r
e
s
t
e
d
i
n
r
e
s
e
a
r
c
h
on
w
e
b
-
ba
s
e
d
a
p
pl
i
c
a
t
i
on
s
f
or
m
a
n
a
ge
m
e
nt
de
c
i
s
i
on
m
a
ki
ng.
H
e
c
a
n
be
c
ont
a
c
t
e
d
a
t
e
m
a
i
l
:
t
e
gu
h.
pr
a
s
a
n
dy@
bi
n
us
.
a
c
.
i
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.