I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
,
p
p
.
4
5
3
3
~
4
5
4
0
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
6
.
p
p
4
5
3
3
-
4
5
4
0
4533
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Co
mputer
v
isio
n
sy
ndro
me
prev
en
tion: de
tec
tion o
f
ex
press
io
n
a
nd eye dista
nce
with
mo
ni
tor scre
ens
Auf
a
cla
v
Z
a
t
u K
us
um
a
F
risk
y
,
E
la
ng
Ar
k
a
na
ufa
Azr
ien
,
Ra
den Sum
iha
rt
o
,
Sri H
a
rt
a
t
i
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
El
e
c
t
r
o
n
i
c
s
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
ma
t
i
c
s
,
U
n
i
v
e
r
s
i
t
a
s Ga
d
j
a
h
M
a
d
a
,
Y
o
g
y
a
k
a
r
t
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
9
,
2
0
2
4
R
ev
is
ed
Sep
2
8
,
2
0
2
5
Acc
ep
ted
Oct
1
8
,
2
0
2
5
Co
m
p
u
ter
v
isio
n
s
y
n
d
ro
m
e
(CV
S
)
is
a
v
isio
n
-
re
late
d
c
o
m
p
lai
n
t
c
a
u
se
d
b
y
c
o
m
p
u
ter
u
sa
g
e
.
CVS
c
a
n
b
e
a
n
a
ly
z
e
d
th
r
o
u
g
h
fa
c
ial
e
x
p
re
ss
io
n
s
d
e
tec
ted
b
y
a
c
a
m
e
ra
.
Ex
p
re
ss
io
n
d
e
tec
ti
o
n
is
c
a
teg
o
rize
d
in
to
tw
o
g
r
o
u
p
s:
sa
fe
a
n
d
d
a
n
g
e
ro
u
s.
Th
e
sa
fe
c
a
teg
o
r
y
c
o
m
p
rise
s
h
a
p
p
y
,
n
e
u
tral,
d
isg
u
ste
d
,
sa
d
,
a
n
g
ry
,
a
n
d
su
r
p
rise
d
,
wh
il
e
th
e
d
a
n
g
e
ro
u
s
c
a
teg
o
r
y
in
c
l
u
d
e
s
sa
d
a
n
d
fe
a
rfu
l
e
m
o
ti
o
n
s.
T
h
is d
iv
isio
n
is
b
a
se
d
o
n
th
e
sim
il
a
rit
y
o
f
CVS
sy
m
p
to
m
s
to
fa
c
ial
e
m
o
ti
o
n
c
h
a
ra
c
teristics
.
Ad
d
it
i
o
n
a
ll
y
,
a
n
a
d
d
it
io
n
a
l
fe
a
tu
re
is
imp
lem
e
n
ted
to
d
e
tec
t
t
h
e
d
istan
c
e
b
e
twe
e
n
th
e
sc
re
e
n
a
n
d
t
h
e
u
se
r'
s
e
y
e
s
u
sin
g
th
e
F
a
c
e
M
e
sh
M
o
d
u
le
t
o
p
re
v
e
n
t
t
h
e
u
se
r'
s
e
y
e
s
fro
m
g
e
tt
i
n
g
t
o
o
c
l
o
se
to
t
h
e
sc
re
e
n
.
Bo
th
d
e
tec
ti
o
n
s
will
p
ro
v
i
d
e
wa
rn
in
g
n
o
ti
f
ica
ti
o
n
s
w
h
e
n
a
d
a
n
g
e
ro
u
s
c
a
teg
o
ry
e
x
p
re
ss
io
n
is
d
e
tec
ted
≥
7
0
%
e
v
e
ry
m
i
n
u
te,
a
n
d
wh
e
n
th
e
d
istan
c
e
b
e
twe
e
n
th
e
sc
re
e
n
a
n
d
th
e
e
y
e
s
is
≤4
0
c
m
.
No
ti
fica
ti
o
n
s
i
n
th
is
p
r
o
g
ra
m
u
se
th
e
Tk
in
ter
li
b
ra
ry
a
s
a
g
ra
p
h
ica
l
u
se
r
in
terfa
c
e
(
G
UI
)
m
e
s
sa
g
e
b
o
x
.
I
n
th
is
re
se
a
rc
h
,
fa
c
ial
e
x
p
re
ss
io
n
s
a
re
d
e
tec
ted
u
sin
g
th
e
Ca
sc
a
d
e
Clas
sifier
fo
r
fa
c
e
d
e
tec
ti
o
n
a
n
d
t
h
e
e
x
trem
e
in
c
e
p
ti
o
n
(Xc
e
p
ti
o
n
)
a
s
t
h
e
fa
c
ial
e
x
p
re
ss
io
n
c
las
sifier.
Th
e
re
su
lt
s
o
f
e
x
p
re
ss
io
n
d
e
tec
ti
o
n
a
c
h
ie
v
e
d
a
n
a
c
c
u
ra
c
y
o
f
9
4
%
,
a
n
F
1
-
sc
o
re
o
f
9
4
%
,
p
re
c
isio
n
o
f
9
5
%
,
a
n
d
re
c
a
ll
o
f
9
4
%
.
K
ey
w
o
r
d
s
:
C
ascad
e
class
if
ier
C
o
m
p
u
ter
v
is
io
n
s
y
n
d
r
o
m
e
Face
m
esh
m
o
d
u
le
T
k
in
ter
Xce
p
tio
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
:
Au
f
ac
lav
Z
atu
Ku
s
u
m
a
Frisk
y
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
lectr
o
n
ics,
Facu
lty
o
f
Scien
ce
an
d
Ma
th
e
m
atics
Un
iv
er
s
itas
Gad
jah
Ma
d
a
Slem
an
,
Sp
ec
ial
R
eg
io
n
o
f
Y
o
g
y
ak
ar
ta,
I
n
d
o
n
esia
E
m
ail: a
u
f
ac
lav
@
u
g
m
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
o
m
p
u
ter
v
is
io
n
s
y
n
d
r
o
m
e
(
C
VS)
r
ef
er
s
to
a
co
llectio
n
o
f
v
is
u
al
an
d
m
u
s
cu
lo
s
k
eleta
l
s
y
m
p
to
m
s
th
at
ar
is
e
f
r
o
m
p
r
o
lo
n
g
ed
e
x
p
o
s
u
r
e
to
d
ig
ital scr
ee
n
s
,
s
u
ch
a
s
co
m
p
u
ter
s
,
m
o
b
ile
p
h
o
n
es,
a
n
d
tab
lets
[
1
]
.
W
ith
in
cr
ea
s
in
g
d
ig
ital
r
elian
ce
in
d
aily
life
,
C
VS
h
as
b
ec
o
m
e
a
s
i
g
n
if
ican
t
p
u
b
lic
h
ea
lth
co
n
ce
r
n
,
af
f
ec
tin
g
v
is
io
n
,
co
m
f
o
r
t,
an
d
p
r
o
d
u
ctiv
ity
[
2
]
.
T
h
e
Am
er
ican
Op
to
m
etr
ic
Ass
o
ciatio
n
r
ec
o
m
m
e
n
d
s
m
ain
t
ain
in
g
a
4
0
–
7
6
c
m
v
iewin
g
d
is
tan
ce
to
m
in
im
ize
ey
e
s
tr
ain
[
3
]
.
A
m
eth
o
d
f
o
r
d
etec
tin
g
C
VS
u
tili
ze
s
f
ac
ial
r
ec
o
g
n
itio
n
d
ir
ec
tly
lin
k
ed
to
th
e
la
p
t
o
p
.
Facial
ex
p
r
ess
io
n
s
ar
e
k
n
o
wn
to
co
n
v
ey
u
p
t
o
5
5
%
o
f
c
o
m
m
u
n
icativ
e
in
f
o
r
m
atio
n
,
co
m
p
ar
ed
to
4
5
%
f
r
o
m
s
p
o
k
en
an
d
au
d
ib
le
cu
es
[
4
]
.
T
h
e
s
y
s
tem
id
en
tifie
s
an
d
p
r
o
ce
s
s
es
f
ac
ial
f
ea
tu
r
es,
wh
ich
ar
e
th
en
f
ilter
e
d
an
d
class
if
ied
b
ased
o
n
p
r
e
-
t
r
ain
e
d
d
ata
to
r
ec
o
g
n
ize
e
m
o
tio
n
al
s
tates
[
5
]
.
Ad
d
itio
n
ally
,
th
e
d
is
tan
ce
b
etwe
en
th
e
ey
es a
n
d
th
e
s
cr
ee
n
ca
n
b
e
ac
c
u
r
ately
m
ea
s
u
r
ed
u
s
in
g
o
n
ly
a
ca
m
er
a.
Sev
er
al
s
tu
d
ies
h
av
e
i
n
v
esti
g
ated
ad
v
a
n
ce
d
m
et
h
o
d
s
to
m
itig
ate
C
VS,
p
ar
ticu
lar
ly
th
r
o
u
g
h
ey
e
-
b
lin
k
d
etec
tio
n
an
d
f
ac
ial
ex
p
r
ess
io
n
r
ec
o
g
n
itio
n
(
FER).
L
ap
a
et
a
l
.
[
6
]
p
r
o
p
o
s
ed
a
r
ea
l
-
ti
m
e
C
VS
d
etec
tio
n
ap
p
r
o
ac
h
u
s
in
g
ey
e
-
b
lin
k
in
g
as
a
p
r
im
ar
y
in
d
icato
r
,
b
u
t
its
r
eliab
ilit
y
was
af
f
ec
ted
b
y
f
ac
to
r
s
s
u
ch
as
ag
e,
g
en
d
er
,
a
n
d
lig
h
tin
g
c
o
n
d
itio
n
s
.
I
n
co
n
tr
ast,
Me
d
eir
o
s
et
a
l
.
[
7
]
in
tr
o
d
u
ce
d
a
m
ac
h
i
n
e
lear
n
in
g
-
b
ased
m
et
h
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
3
3
-
4
5
4
0
4534
to
id
en
tify
ey
e
b
lin
k
s
in
in
d
iv
i
d
u
als
with
C
VS.
T
h
eir
s
tu
d
y
e
m
p
h
asized
th
at,
alth
o
u
g
h
ey
e
-
b
lin
k
d
etec
tio
n
is
a
u
s
ef
u
l
f
ea
tu
r
e,
it
is
in
s
u
f
f
ici
en
t
in
is
o
latio
n
f
o
r
p
r
ec
is
e
C
VS
ev
alu
atio
n
.
T
h
ey
r
ec
o
m
m
en
d
ed
i
n
teg
r
atin
g
ey
e
-
b
lin
k
d
etec
tio
n
with
a
d
d
i
tio
n
al
f
ac
ial
p
ar
am
eter
s
,
s
u
c
h
as
FER
,
to
ac
h
ie
v
e
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
ac
cu
r
ate
ass
ess
m
en
t.
B
u
ild
in
g
o
n
th
is
,
Mu
tan
u
et
a
l
.
[
8
]
d
ev
elo
p
e
d
a
s
elf
-
ad
ju
s
tin
g
F
E
R
-
b
ased
s
y
s
tem
to
d
etec
t
ey
e
s
tr
ain
a
n
d
r
e
d
u
ce
v
is
u
al
d
is
co
m
f
o
r
t,
b
u
t
th
eir
7
7
%
class
if
icatio
n
ac
cu
r
ac
y
h
ig
h
lig
h
ted
th
e
n
ee
d
f
o
r
b
etter
f
ea
tu
r
e
r
ep
r
esen
tatio
n
a
n
d
tr
ain
in
g
d
iv
e
r
s
ity
.
T
h
ese
s
tu
d
ies
s
u
g
g
est
th
at
wh
ile
in
d
iv
id
u
al
f
ea
tu
r
es
o
f
f
er
s
o
m
e
in
s
ig
h
t,
an
in
teg
r
ated
ap
p
r
o
ac
h
c
o
m
b
in
i
n
g
m
u
ltip
le
f
a
cial
cu
es is
m
o
r
e
p
r
o
m
is
in
g
f
o
r
r
o
b
u
s
t a
n
d
r
eliab
le
C
VS d
etec
tio
n
.
I
n
a
d
d
i
t
i
o
n
t
o
t
h
es
e
s
t
u
d
i
es
,
t
h
i
s
r
es
e
a
r
c
h
is
i
n
s
p
i
r
e
d
b
y
a
d
v
an
c
e
m
e
n
t
s
i
n
d
r
i
v
e
r
f
a
t
i
g
u
e
d
ete
c
t
i
o
n
t
h
a
t
h
i
g
h
l
i
g
h
t
t
h
e
n
e
e
d
t
o
c
o
m
b
i
n
e
m
u
l
t
i
p
l
e
f
a
ci
a
l
f
ea
t
u
r
e
s
.
S
u
n
e
t
a
l
.
[
9
]
p
r
o
p
o
s
e
d
a
m
u
l
t
i
-
s
t
r
e
a
m
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
i
n
t
e
g
r
a
ti
n
g
b
o
t
h
g
l
o
b
a
l
a
n
d
l
o
c
a
l
f
a
c
ia
l
f
e
at
u
r
e
s
t
o
e
n
h
a
n
c
e
f
a
ti
g
u
e
d
e
t
ec
t
i
o
n
p
e
r
f
o
r
m
a
n
c
e
,
p
a
r
t
i
c
u
l
a
r
l
y
u
n
d
e
r
l
o
w
-
q
u
a
l
i
t
y
in
p
u
t
s
,
t
h
o
u
g
h
t
h
e
i
r
m
o
d
e
l
s
t
i
l
l
l
a
c
k
e
d
t
e
m
p
o
r
a
l
c
o
n
t
e
x
t
.
B
al
a
s
u
n
d
a
r
a
m
e
t
a
l
.
[
1
0
]
em
p
h
asized
in
co
r
p
o
r
atin
g
f
ac
i
al
g
estu
r
es
s
u
ch
as
y
awn
in
g
to
im
p
r
o
v
e
r
eliab
ilit
y
.
Similar
ly
,
Z
h
ao
et
a
l
.
[
1
1
]
d
em
o
n
s
tr
ated
t
h
at
f
u
s
in
g
ey
e
an
d
m
o
u
th
f
ea
tu
r
es
im
p
r
o
v
es
ac
cu
r
ac
y
s
ig
n
if
ican
tly
;
h
o
we
v
er
,
th
eir
ap
p
r
o
ac
h
ca
n
s
till
b
e
en
h
an
ce
d
o
p
tim
izi
n
g
r
ea
l
-
tim
e
p
er
f
o
r
m
an
ce
f
o
r
d
ep
lo
y
m
e
n
t in
s
af
ety
-
c
r
itical
s
y
s
tem
s
.
T
h
is
s
tu
d
y
p
r
o
p
o
s
es
a
C
VS
p
r
ev
en
tio
n
s
y
s
tem
th
at
in
teg
r
ates
FER
w
ith
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
m
ea
s
u
r
em
en
t.
T
h
e
s
y
s
tem
aler
ts
u
s
er
s
wh
en
th
eir
ey
e
d
is
tan
ce
f
alls
u
n
d
er
4
0
cm
a
n
d
class
if
ies
ex
p
r
ess
io
n
s
as
eith
er
"
s
af
e"
o
r
"
d
an
g
er
o
u
s
"
,
if
a
"d
an
g
e
r
o
u
s
"
ex
p
r
ess
io
n
a
p
p
ea
r
s
with
o
v
e
r
7
0
%
ce
r
tain
ty
with
in
a
m
in
u
te,
th
e
s
y
s
tem
is
s
u
e
s
a
war
n
in
g
.
T
h
is
ap
p
r
o
ac
h
le
v
er
ag
es
a
r
eg
u
lar
ized
ex
tr
em
e
in
ce
p
tio
n
(
X
ce
p
tio
n
)
m
o
d
el
with
ex
tr
a
tr
ain
in
g
d
ata
an
d
a
s
tep
d
ec
ay
lear
n
in
g
r
ate
to
e
n
h
an
ce
r
ec
o
g
n
itio
n
ac
c
u
r
ac
y
.
2.
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
tu
d
y
d
ev
elo
p
ed
a
s
y
s
tem
to
d
etec
t
wea
r
in
ess
in
lap
t
o
p
u
s
er
s
b
y
an
aly
zin
g
f
ac
ial
ex
p
r
ess
io
n
s
an
d
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
to
m
itig
ate
C
VS.
T
h
e
s
y
s
tem
e
m
p
lo
y
s
th
e
Xce
p
tio
n
ar
ch
itec
tu
r
e
[
9
]
,
tr
ain
ed
o
n
FER2
0
1
3
,
C
K+
,
an
d
e
x
ten
d
ed
an
d
au
g
m
en
te
d
Go
o
g
le
FER
d
atasets
,
to
class
if
y
em
o
tio
n
s
in
to
s
ev
e
n
ca
teg
o
r
ies.
Facial
d
etec
tio
n
is
p
er
f
o
r
m
ed
u
s
in
g
th
e
Vio
la
-
J
o
n
es
m
eth
o
d
with
th
e
C
ascad
eCl
as
s
if
ier
alg
o
r
ith
m
[
1
0
]
.
Fear
an
d
s
ad
n
ess
ar
e
cl
ass
if
ied
as
"
d
an
g
er
o
u
s
(
b
a
h
a
ya
)
"
,
wh
ile
o
th
e
r
ex
p
r
ess
io
n
s
ar
e
"
sa
f
e
(
am
an
)
"
,
with
a
war
n
in
g
tr
ig
g
er
e
d
i
f
"
d
an
g
er
o
u
s
"
ex
p
r
ess
io
n
s
ex
ce
e
d
7
0
%
[
1
2
]
.
T
h
e
s
y
s
tem
co
n
tin
u
o
u
s
ly
m
o
n
ito
r
s
u
s
er
b
eh
av
i
o
r
,
p
r
o
ce
s
s
in
g
f
ac
i
al
ex
p
r
ess
io
n
d
ata
i
n
r
ea
l
-
tim
e
to
p
r
o
v
id
e
i
m
m
ed
iate
aler
ts
an
d
en
c
o
u
r
a
g
e
s
af
e
p
o
s
tu
r
e
[
1
3
]
.
Ad
d
itio
n
ally
,
it
m
ea
s
u
r
es
th
e
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
u
s
in
g
f
o
ca
l
len
g
th
c
alcu
latio
n
s
,
is
s
u
in
g
war
n
in
g
s
wh
en
th
e
d
is
tan
ce
is
4
0
cm
o
r
less
.
Fig
u
r
e
1
illu
s
tr
a
tes th
e
s
y
s
tem
'
s
wo
r
k
f
lo
w.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
am
s
y
s
te
m
2
.
1
.
Da
t
a
s
et
d
escript
io
n
E
k
m
a
n
[
1
4
]
i
d
e
n
ti
f
i
es h
a
p
p
i
n
e
s
s
,
a
n
g
e
r
,
d
is
g
u
s
t,
f
ea
r
,
s
a
d
n
es
s
,
a
n
d
s
u
r
p
r
is
e
as
t
h
e
f
u
n
d
a
m
e
n
ta
l h
u
m
an
em
o
ti
o
n
s
.
T
h
e
s
t
u
d
y
u
ti
liz
e
d
m
u
lti
p
l
e
d
atas
ets
o
f
f
a
ce
e
m
o
ti
o
n
s
f
o
r
tr
ai
n
i
n
g
,
i
n
c
lu
d
i
n
g
FE
R
2
0
1
3
(
tr
ai
n
i
n
g
d
ata
)
[
1
5
]
,
C
K+
[
1
6
]
,
an
d
e
x
te
n
d
e
d
an
d
a
u
g
m
e
n
t
e
d
G
o
o
g
le
F
E
R
[
1
7
]
.
T
h
e
F
E
R
2
0
1
3
d
at
aset
c
o
n
s
is
te
d
o
f
3
5
,
8
8
7
g
r
a
y
s
ca
le
p
h
o
t
o
g
r
a
p
h
s
ca
t
eg
o
r
iz
e
d
in
to
s
e
v
en
em
o
ti
o
n
a
l
c
ate
g
o
r
ies
.
Ad
d
i
ti
o
n
all
y
,
th
e
C
K
a
n
d
e
x
te
n
d
e
d
,
an
d
au
g
m
e
n
t
ed
G
o
o
g
l
e
F
E
R
d
atas
ets
w
er
e
i
n
c
l
u
d
ed
i
n
t
h
e
t
r
ain
in
g
d
ata
,
r
es
u
l
ti
n
g
i
n
a
t
o
tal
o
f
6
7
,
8
8
1
im
a
g
es
.
T
h
e
FER
2
0
1
3
(
p
u
b
l
ic
t
est
)
d
atas
et
is
u
ti
liz
ed
f
o
r
v
ali
d
a
ti
o
n
p
u
r
p
o
s
es,
wh
er
ea
s
th
e
FER
2
0
1
3
(
p
r
i
v
ate
t
est
)
d
at
ase
t is
e
m
p
l
o
y
e
d
f
o
r
t
esti
n
g
.
T
h
e
d
i
m
e
n
s
i
o
n
s
o
f
ea
c
h
i
m
a
g
e
i
n
t
h
e
c
o
ll
ec
t
io
n
a
r
e
4
8
b
y
4
8
p
ix
els
.
2
.
2
.
Ca
t
eg
o
rize
e
x
press
io
n
Acc
o
r
d
in
g
to
th
e
d
ataset,
s
ev
en
em
o
tio
n
al
ty
p
es
wo
u
ld
b
e
r
ec
lass
if
ied
in
to
two
g
r
o
u
p
s
:
s
af
e
an
d
d
an
g
er
o
u
s
.
T
h
e
s
af
e
g
r
o
u
p
co
m
p
r
is
ed
em
o
tio
n
s
s
u
c
h
as
a
n
g
r
y
,
d
is
g
u
s
t,
h
a
p
p
y
,
n
eu
tr
al,
an
d
s
u
r
p
r
is
e
wh
ile
th
e
d
an
g
er
o
u
s
g
r
o
u
p
co
n
s
is
ted
s
o
lely
o
f
s
ad
an
d
f
ea
r
.
T
h
e
c
ateg
o
r
y
is
d
e
r
iv
ed
f
r
o
m
th
e
p
ar
allels
o
b
s
er
v
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
o
mp
u
ter visi
o
n
s
yn
d
r
o
me
p
r
ev
en
tio
n
:
d
etec
tio
n
o
f e
x
p
r
ess
i
o
n
a
n
d
…
(
A
u
fa
cla
v
Za
tu
K
u
s
u
ma
F
r
is
ky
)
4535
b
etwe
en
th
e
s
y
m
p
to
m
s
o
f
C
VS
an
d
f
ac
ial
em
o
tio
n
al
tr
aits
.
C
VS
s
y
m
p
to
m
s
en
co
m
p
ass
b
lu
r
r
in
g
o
f
v
is
io
n
,
b
u
r
n
in
g
,
d
o
u
b
le
v
is
io
n
,
ey
e
p
ain
,
wate
r
in
g
e
y
s
,
an
d
m
u
ltip
le
s
y
m
to
m
p
s
[
1
]
.
C
o
n
v
er
s
ely
,
th
e
d
is
p
lay
o
f
s
ad
an
d
f
ea
r
is
ch
ar
ac
ter
ized
b
y
a
lack
o
f
f
o
cu
s
an
d
a
f
ix
e
d
g
az
e
[
1
4
]
.
Hen
ce
,
th
e
class
if
icatio
n
o
f
s
ad
an
d
f
ea
r
as
a
ca
teg
o
r
y
o
f
“
d
an
g
er
o
u
s
”
is
b
ased
o
n
th
eir
r
esem
b
lan
ce
to
t
h
e
s
y
m
p
to
m
s
o
f
C
VS
.
2
.
3
.
T
ra
ini
ng
m
o
del sy
s
t
em
T
h
e
tr
ain
in
g
m
o
d
el
em
p
l
o
y
ed
in
th
is
s
y
s
tem
is
b
a
s
ed
o
n
r
e
g
u
lar
ized
Xce
p
tio
n
f
o
r
FER
with
ex
tr
a
tr
ain
in
g
d
ata
an
d
s
tep
d
ec
ay
l
ea
r
n
in
g
r
ate
[
1
8
]
.
T
h
is
m
o
d
el
u
tili
ze
s
a
r
eg
u
lar
ized
Xce
p
tio
n
ar
ch
itectu
r
e,
d
ata
au
g
m
en
tatio
n
,
an
d
a
s
tep
d
e
ca
y
lear
n
in
g
r
ate
t
o
en
h
an
ce
its
ac
cu
r
ac
y
.
Usi
n
g
th
e
FE
R
2
0
2
3
,
C
K+
,
an
d
ex
ten
d
ed
an
d
au
g
m
en
te
d
Go
o
g
le
FER
d
ata
s
ets,
th
e
m
o
d
el
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
4
.
3
4
%,
s
u
r
p
ass
in
g
th
e
r
esu
lts
o
f
p
r
ev
io
u
s
s
tu
d
ies,
as sh
o
wn
in
T
ab
le
1
.
At
th
e
b
e
g
in
n
in
g
o
f
th
e
tr
a
in
in
g
p
r
o
ce
s
s
,
th
e
p
r
o
g
r
am
in
g
ests
d
atasets
th
at
in
clu
d
e
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
d
ata.
T
h
e
d
ata
u
n
d
er
g
o
es
p
r
ep
r
o
ce
s
s
in
g
,
wh
ich
in
clu
d
es
n
o
r
m
aliza
tio
n
an
d
d
ata
au
g
m
en
tatio
n
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
is
th
en
u
s
ed
in
th
e
tr
ain
in
g
p
h
ase
with
th
e
r
e
g
u
lar
ized
Xce
p
tio
n
ar
ch
itectu
r
e,
em
p
lo
y
in
g
th
e
s
tep
d
ec
ay
a
p
p
r
o
ac
h
th
at
a
d
j
u
s
ts
th
e
lear
n
in
g
r
ate
at
s
p
e
cif
ic
ep
o
ch
s
.
Up
o
n
co
m
p
letio
n
o
f
th
e
tr
ain
in
g
p
r
o
ce
d
u
r
e,
th
e
f
in
alize
d
m
o
d
el
will
b
e
ev
alu
ated
to
ass
e
s
s
it
s
p
er
f
o
r
m
an
ce
.
T
h
e
s
y
s
tem
ar
ch
itectu
r
e
is
illu
s
tr
ated
in
Fig
u
r
e
2
.
T
ab
le
1
.
T
h
e
co
m
p
ar
is
o
n
o
f
ac
cu
r
ac
y
f
o
r
ea
ch
m
o
d
el
R
e
f
e
r
e
n
c
e
s
M
e
t
h
o
d
A
c
c
u
r
a
c
y
(
%)
Jay
m
o
n
e
t
a
l
.
[
1
9
]
S
i
mp
l
e
C
N
N
m
o
d
e
l
54
G
u
n
a
w
a
n
e
t
a
l
.
[
2
0
]
C
o
n
v
N
e
t
mo
d
e
l
5
7
.
4
Jay
m
o
n
e
t
a
l
.
[
1
9
]
I
n
c
e
p
t
i
o
n
mo
d
e
l
6
1
.
4
2
Jay
m
o
n
e
t
a
l
.
[
1
9
]
X
c
e
p
t
i
o
n
m
o
d
e
l
6
5
.
2
V
i
g
n
e
s
h
e
t
a
l
.
[
2
1
]
S
e
g
m
e
n
t
a
t
i
o
n
V
G
G
-
19
7
5
.
9
7
Zh
a
n
g
e
t
a
l
.
[
2
2
]
C
N
N
+
i
m
a
g
e
e
d
g
e
c
o
mp
u
t
i
n
g
(
F
ER
2
0
1
3
+
LFW
D
a
t
a
set
)
8
8
.
5
6
D
e
b
n
a
t
h
e
t
a
l
.
[
2
3
]
F
u
ssi
o
n
f
e
a
t
u
r
e
s (
C
N
N
+
LB
P
+
O
R
B
)
+
C
o
n
v
N
e
t
9
1
.
0
1
A
z
r
i
e
n
e
t
a
l
.
[
1
8
]
R
e
g
u
l
a
r
i
z
e
d
X
c
e
p
t
i
o
n
f
o
r
F
ER
w
i
t
h
e
x
t
r
a
t
r
a
i
n
i
n
g
d
a
t
a
a
n
d
s
t
e
p
d
e
c
a
y
l
e
a
r
n
i
n
g
r
a
t
e
9
4
.
3
4
Fig
u
r
e
2
.
T
h
e
s
tag
es o
f
th
e
s
y
s
tem
f
o
r
tr
ain
i
n
g
m
eth
o
d
2
.
4
.
So
f
t
wa
re
s
y
s
t
em
T
h
e
s
o
f
twar
e
s
y
s
tem
s
im
u
ltan
eo
u
s
ly
p
e
r
f
o
r
m
s
f
ac
ial
ex
p
r
ess
io
n
id
en
tific
atio
n
an
d
s
cr
ee
n
-
to
-
ey
e
d
is
tan
ce
m
ea
s
u
r
em
en
t.
E
x
p
r
e
s
s
io
n
d
etec
tio
n
u
s
es
C
ascad
eCl
as
s
if
ier
with
a
6
0
-
s
ec
o
n
d
tim
er
,
class
if
y
in
g
em
o
tio
n
s
as
"saf
e"
o
r
"d
a
n
g
er
o
u
s
.
"
I
f
"d
an
g
er
o
u
s
"
ex
p
r
ess
i
o
n
s
r
ea
ch
7
0
%,
a
war
n
i
n
g
a
p
p
ea
r
s
,
an
d
th
e
u
s
er
ca
n
p
r
ess
'
o
k
'
to
co
n
tin
u
e.
Dis
tan
ce
m
ea
s
u
r
em
en
t
u
tili
ze
s
t
h
e
ca
lib
r
ated
f
o
ca
l
len
g
th
v
alu
e,
ca
lcu
lated
u
s
in
g
(
1
)
[
2
4
]
,
wh
er
e
‘
d
’
r
e
p
r
esen
ts
th
e
d
etec
ted
s
cr
ee
n
-
to
-
e
y
e
d
is
t
an
ce
.
T
h
e
eq
u
ati
o
n
r
eq
u
ir
es
ac
tu
al
p
u
p
il
d
is
tan
ce
(
W
)
,
f
o
ca
l
le
n
g
th
(
f
)
,
an
d
r
e
al
-
tim
e
ey
e
d
is
tan
ce
(
w)
d
etec
ted
v
ia
Face
Me
s
h
Mo
d
u
le.
A
war
n
in
g
tr
i
g
g
er
s
if
th
e
d
is
tan
ce
is
≤
4
0
cm
,
r
eq
u
ir
in
g
u
s
er
co
n
f
ir
m
atio
n
to
p
r
o
ce
e
d
.
d
=(
W
.
f
)
/w
(
1
)
2
.
5
.
Ca
lib
ra
t
i
o
n
s
y
s
t
em
T
h
e
ca
lib
r
atio
n
s
y
s
tem
d
eter
m
in
es
th
e
f
o
ca
l
len
g
th
,
w
h
ich
is
th
en
u
s
ed
to
co
m
p
u
te
t
h
e
d
is
tan
ce
b
etwe
en
th
e
s
cr
ee
n
an
d
th
e
ey
e.
T
h
is
p
r
o
ce
s
s
em
p
lo
y
s
th
e
Face
Me
s
h
Mo
d
u
le
f
r
o
m
Me
d
ia
P
ip
e
to
o
b
tain
p
r
ec
is
e
ey
e
co
o
r
d
i
n
ates.
Me
d
iaPip
e
f
ac
e
m
esh
is
a
r
ea
l
-
tim
e
s
y
s
tem
th
at
m
ap
s
4
6
8
3
D
f
ac
ial
lan
d
m
ar
k
s
[
2
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
3
3
-
4
5
4
0
4536
T
h
e
s
y
s
tem
ca
lcu
lates
th
e
f
o
c
al
len
g
th
u
s
in
g
(
2
)
,
w
h
er
e
f
r
e
p
r
esen
ts
th
e
f
o
ca
l
le
n
g
th
,
w
is
th
e
i
n
ter
-
p
u
p
illar
y
d
is
tan
ce
(
I
PD)
d
etec
ted
b
y
th
e
ca
m
er
a,
D
is
th
e
d
is
tan
ce
f
r
o
m
th
e
m
o
n
ito
r
to
th
e
ey
e,
a
n
d
W
is
th
e
ac
tu
al
I
PD.
=
(
.
)
/
(
2
)
T
h
e
ca
lib
r
atio
n
p
r
o
ce
s
s
b
eg
in
s
b
y
s
ettin
g
r
ef
er
e
n
ce
v
alu
es:
th
e
ac
tu
al
p
u
p
il
d
is
tan
ce
(
W
)
an
d
th
e
m
ea
s
u
r
ed
s
cr
ee
n
-
to
-
ey
e
d
is
tan
ce
(
D)
.
T
h
e
s
y
s
tem
th
en
d
etec
ts
th
e
I
PD
(
w)
u
s
in
g
Face
Me
s
h
Mo
d
u
le.
W
ith
th
ese
th
r
ee
p
ar
am
eter
s
,
th
e
f
o
c
al
len
g
th
is
co
m
p
u
ted
f
o
r
ac
cu
r
ate
d
is
tan
ce
esti
m
atio
n
.
2
.
6
.
No
t
if
ica
t
io
n
I
n
th
is
s
tu
d
y
,
we
u
tili
ze
th
e
T
k
in
ter
m
o
d
u
le
.
T
k
in
ter
is
a
Py
th
o
n
p
ac
k
a
g
e
th
at
f
ac
ilit
ates
t
h
e
cr
ea
tio
n
o
f
p
r
o
g
r
am
s
with
a
g
r
ap
h
ical
u
s
er
in
ter
f
ac
e
(
GUI
)
.
T
h
e
G
UI
allo
ws
u
s
er
s
to
in
ter
ac
t
with
th
e
ap
p
licatio
n
th
r
o
u
g
h
v
is
u
al
elem
en
ts
s
u
ch
as
ico
n
im
ag
es.
T
h
is
m
o
d
u
le
o
f
f
er
s
a
r
an
g
e
o
f
GUI
f
u
n
ctio
n
alities
,
in
clu
d
in
g
a
n
o
tific
atio
n
ca
p
a
b
ilit
y
[
2
6
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
g
r
am
was
ev
alu
ated
u
n
d
er
two
d
is
tin
ct
lig
h
tin
g
co
n
d
itio
n
s
,
4
0
lu
x
an
d
2
,
1
3
0
l
u
x
,
to
ass
ess
it
s
p
er
f
o
r
m
an
ce
i
n
lo
w
-
lig
h
t
an
d
h
ig
h
-
lig
h
t
en
v
i
r
o
n
m
e
n
ts
.
Dif
f
e
r
en
ce
s
in
illu
m
i
n
atio
n
ca
n
s
u
b
s
tan
tially
af
f
ec
t
th
e
ac
cu
r
ac
y
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
as
in
s
u
f
f
icien
t
lig
h
tin
g
m
ay
o
b
s
cu
r
e
f
ac
ial
d
etails.
Oth
er
wis
e,
ex
ce
s
s
iv
e
b
r
ig
h
tn
ess
ca
n
in
tr
o
d
u
ce
o
v
er
e
x
p
o
s
u
r
e
[
2
7
]
.
3
.
1
.
Resul
t
f
o
r
f
irst
co
nd
it
io
n
T
h
e
f
ir
s
t
test
wa
s
co
n
d
u
cted
u
n
d
er
4
0
lu
x
lig
h
t
in
ten
s
ity
to
ev
alu
ate
ex
p
r
ess
io
n
class
if
icatio
n
an
d
s
cr
ee
n
-
to
-
ey
e
d
is
tan
ce
d
etec
tio
n
.
Par
am
eter
s
in
clu
d
ed
m
o
n
ito
r
lu
m
in
an
ce
(
5
0
%
o
r
1
0
0
%)
an
d
s
cr
ee
n
d
is
tan
ce
(
5
0
cm
o
r
7
6
cm
)
.
T
h
e
s
y
s
tem
s
u
cc
ess
f
u
lly
id
en
tifie
d
“
s
af
e”
ex
p
r
ess
io
n
s
wh
en
th
ey
r
em
ain
ed
u
n
d
e
r
7
0
%
with
in
o
n
e
m
in
u
te
an
d
is
s
u
ed
a
n
o
tific
atio
n
f
o
r
“
d
an
g
e
r
o
u
s
”
ex
p
r
ess
io
n
s
wh
en
th
e
y
r
ea
c
h
ed
7
0
%
o
r
m
o
r
e.
Fo
r
s
cr
ee
n
-
to
-
e
y
e
d
is
tan
ce
,
t
h
e
s
y
s
tem
co
r
r
ec
tly
tr
ig
g
er
ed
al
er
ts
wh
en
th
e
d
is
tan
ce
was
≤
4
0
cm
an
d
r
e
f
r
ain
ed
f
r
o
m
n
o
tify
in
g
w
h
en
it
ex
ce
ed
ed
4
0
c
m
.
T
h
e
r
esu
lts
r
e
m
ain
ed
co
n
s
is
ten
t
ac
r
o
s
s
all
co
n
d
itio
n
s
.
T
ab
le
2
p
r
esen
ts
th
e
o
u
tco
m
es f
o
r
e
x
p
r
ess
io
n
d
etec
tio
n
an
d
d
is
tan
ce
m
ea
s
u
r
em
en
t.
3
.
2
.
Resul
t
s
f
o
r
s
ec
o
nd
co
nd
it
io
n
T
h
e
s
ec
o
n
d
test
,
co
n
d
u
cted
u
n
d
er
2
,
1
3
0
lu
x
lig
h
tin
g
,
ev
alu
ated
ex
p
r
ess
io
n
class
if
i
ca
tio
n
an
d
s
cr
ee
n
-
to
-
ey
e
d
is
tan
ce
d
etec
ti
o
n
u
s
in
g
th
e
s
am
e
m
o
n
ito
r
l
u
m
in
an
ce
(
5
0
%
o
r
1
0
0
%)
an
d
s
cr
ee
n
p
r
o
x
im
ity
(
5
0
cm
to
7
6
cm
)
.
T
h
e
s
y
s
tem
s
u
cc
ess
f
u
lly
is
s
u
ed
n
o
tific
a
tio
n
s
wh
en
“
d
a
n
g
er
o
u
s
”
ex
p
r
e
s
s
io
n
s
r
ea
ch
ed
7
0
%
with
in
o
n
e
m
in
u
te.
Fo
r
s
cr
ee
n
-
to
-
ey
e
d
is
tan
ce
,
aler
ts
wer
e
co
r
r
ec
tly
tr
i
g
g
er
ed
at
≤
4
0
c
m
an
d
s
u
p
p
r
ess
ed
b
ey
o
n
d
4
0
cm
.
T
h
e
s
y
s
tem
p
er
f
o
r
m
ed
co
n
s
is
ten
tly
ac
r
o
s
s
all
co
n
d
itio
n
s
.
T
ab
le
3
p
r
es
en
ts
th
e
r
esu
lts
f
o
r
ex
p
r
ess
io
n
r
ec
o
g
n
itio
n
a
n
d
d
is
tan
ce
m
ea
s
u
r
em
en
t.
3
.
3
.
Dis
cus
s
io
n
T
h
e
r
esu
lts
s
h
o
w
th
at
b
o
t
h
t
h
e
f
ac
ial
r
ec
o
g
n
itio
n
s
y
s
tem
an
d
th
e
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
d
etec
tio
n
s
y
s
tem
p
er
f
o
r
m
e
d
s
u
cc
ess
f
u
lly
u
n
d
e
r
all
test
ed
co
n
d
itio
n
s
,
in
clu
d
in
g
v
ar
iatio
n
s
in
am
b
ien
t
lig
h
tin
g
,
s
cr
ee
n
b
r
ig
h
tn
ess
,
a
n
d
v
iewin
g
d
is
tan
ce
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
t
h
at
th
e
s
y
s
tem
is
r
o
b
u
s
t
a
n
d
a
d
ap
tab
le
t
o
d
if
f
er
en
t
en
v
ir
o
n
m
en
tal
s
ettin
g
s
.
Pre
v
io
u
s
s
tu
d
ies
in
d
icate
th
at
ex
tr
em
e
lig
h
tin
g
co
n
d
itio
n
s
ca
n
af
f
ec
t
f
ac
ial
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
d
u
e
to
co
n
tr
ast
r
ed
u
ctio
n
a
n
d
g
lar
e
[
2
8
]
.
Ho
wev
e
r
,
o
u
r
s
y
s
tem
m
ain
tain
ed
s
tab
le
ac
cu
r
ac
y
ac
r
o
s
s
b
o
th
d
im
an
d
b
r
ig
h
t
e
n
v
ir
o
n
m
en
ts
.
Similar
ly
,
s
cr
ee
n
b
r
ig
h
tn
ess
v
ar
iatio
n
s
,
wh
ich
ar
e
o
f
ten
ass
o
ciate
d
with
ch
an
g
es
in
v
is
u
al
ad
ap
tatio
n
an
d
c
o
n
tr
a
s
t
s
en
s
i
tiv
ity
[
2
9
]
,
d
id
n
o
t
i
m
p
ac
t
r
ec
o
g
n
itio
n
p
er
f
o
r
m
an
ce
,
f
u
r
th
er
d
em
o
n
s
tr
atin
g
th
e
s
y
s
tem
's
r
eliab
ilit
y
.
Viewin
g
d
is
tan
ce
,
an
o
th
er
im
p
o
r
tan
t
f
ac
to
r
in
im
ag
e
clar
ity
[
3
0
]
,
also
d
id
n
o
t
af
f
ec
t
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
,
as
th
e
s
y
s
tem
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ized
f
ac
es
at
b
o
th
5
0
cm
a
n
d
7
6
cm
d
is
tan
ce
s
.
Alth
o
u
g
h
th
is
s
tu
d
y
f
o
c
u
s
ed
o
n
en
v
ir
o
n
m
e
n
tal
f
ac
to
r
s
,
o
n
e
o
f
th
e
m
ajo
r
ch
allen
g
es
in
f
ac
ial
r
ec
o
g
n
itio
n
an
d
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
m
ea
s
u
r
em
en
t
is
th
e
p
r
esen
ce
o
f
ad
d
itio
n
al
v
ar
iab
les
s
u
ch
as
th
e
u
s
e
o
f
g
lass
es,
co
n
tact
len
s
e
s
,
o
r
r
ef
r
ac
tiv
e
er
r
o
r
s
.
Prio
r
r
esear
ch
s
u
g
g
ests
th
at
g
las
s
es
an
d
o
cc
lu
s
io
n
s
ca
u
s
ed
b
y
ey
ewe
ar
ca
n
af
f
ec
t
d
etec
tio
n
ac
cu
r
ac
y
[
3
1
]
.
T
h
is
f
ac
to
r
was
n
o
t
ex
p
licitly
ex
am
in
ed
in
th
is
s
tu
d
y
,
as
th
e
ev
alu
atio
n
was
lim
ited
to
v
ar
i
atio
n
s
in
lig
h
tin
g
c
o
n
d
itio
n
s
.
Ho
wev
er
,
f
u
t
u
r
e
r
esear
ch
co
u
l
d
ex
p
lo
r
e
its
im
p
ac
t
f
u
r
th
er
t
o
ass
ess
wh
eth
er
th
e
s
y
s
tem
’
s
r
o
b
u
s
tn
ess
ex
ten
d
s
b
e
y
o
n
d
t
h
e
test
ed
p
ar
am
eter
s
.
Pre
v
io
u
s
s
tu
d
ies
h
av
e
s
h
o
wn
t
h
at
lig
h
tin
g
c
o
n
d
itio
n
s
ca
n
s
ig
n
if
ican
tly
im
p
ac
t
e
y
e
d
etec
tio
n
ac
cu
r
ac
y
[
3
2
]
.
Ho
we
v
er
,
d
esp
ite
th
ese
p
o
ten
tial
ch
allen
g
es,
th
e
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
d
etec
tio
n
s
y
s
tem
in
th
is
s
tu
d
y
p
er
f
o
r
m
ed
r
eliab
ly
u
n
d
er
all
test
ed
co
n
d
itio
n
s
.
T
h
is
co
n
s
is
t
en
cy
s
u
g
g
ests
th
at
ad
v
an
ce
m
en
ts
in
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
h
av
e
im
p
r
o
v
ed
a
d
ap
tab
ilit
y
,
m
itig
atin
g
th
e
ad
v
er
s
e
ef
f
ec
ts
o
f
lig
h
tin
g
,
s
cr
ee
n
b
r
ig
h
tn
ess
,
an
d
v
iewin
g
d
is
tan
ce
o
b
s
er
v
ed
in
ea
r
lier
r
esear
ch
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
o
mp
u
ter visi
o
n
s
yn
d
r
o
me
p
r
ev
en
tio
n
:
d
etec
tio
n
o
f e
x
p
r
ess
i
o
n
a
n
d
…
(
A
u
fa
cla
v
Za
tu
K
u
s
u
ma
F
r
is
ky
)
4537
Ov
er
all,
th
e
f
in
d
in
g
s
co
n
f
ir
m
th
at
th
e
test
ed
s
y
s
tem
r
em
ain
s
ef
f
ec
tiv
e
ac
r
o
s
s
v
ar
y
in
g
c
o
n
d
itio
n
s
,
s
u
p
p
o
r
tin
g
its
p
r
ac
tical
ap
p
licatio
n
in
d
iv
er
s
e
s
ettin
g
s
.
Fu
tu
r
e
s
tu
d
ies
co
u
ld
f
u
r
th
er
ex
p
lo
r
e
th
e
im
p
ac
t
o
f
ad
d
itio
n
al
f
ac
to
r
s
,
s
u
ch
as
e
y
ewe
ar
an
d
r
ef
r
ac
tiv
e
co
n
d
itio
n
s
,
to
r
ef
i
n
e
its
p
er
f
o
r
m
an
ce
in
b
r
o
ad
er
u
s
er
s
ce
n
ar
io
s
.
Ad
d
itio
n
ally
,
co
n
s
id
er
in
g
p
r
o
lo
n
g
ed
s
cr
ee
n
ex
p
o
s
u
r
e,
estab
lis
h
ed
g
u
id
elin
es
s
u
ch
as
th
e
2
0
-
20
-
2
0
r
u
le
h
a
v
e
b
e
en
r
ec
o
m
m
e
n
d
e
d
to
r
ed
u
ce
v
is
u
al
s
tr
ain
an
d
im
p
r
o
v
e
ey
e
h
ea
lth
[
3
1
]
.
Stu
d
ies
s
u
g
g
est
th
at
f
o
llo
win
g
th
ese
g
u
id
elin
es
ca
n
h
elp
allev
iate
d
i
g
ital
ey
e
s
tr
ain
s
y
m
p
to
m
s
an
d
m
ain
tain
v
is
u
al
co
m
f
o
r
t
d
u
r
in
g
ex
ten
d
ed
s
cr
ee
n
u
s
e.
I
n
teg
r
a
tin
g
th
ese
p
r
ev
e
n
tiv
e
m
ea
s
u
r
es
in
to
f
u
tu
r
e
r
esear
ch
co
u
ld
p
r
o
v
id
e
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
ev
alu
atio
n
o
f
u
s
er
well
-
b
ein
g
in
p
r
o
l
o
n
g
e
d
u
s
ag
e
s
ce
n
ar
io
s
.
T
ab
le
2
.
R
ec
o
g
n
ize
test
f
o
r
f
ir
s
t c
o
n
d
itio
n
T
ab
le
3
.
R
ec
o
g
n
ize
test
f
o
r
s
e
co
n
d
c
o
n
d
itio
n
R
e
c
o
g
n
i
z
e
t
e
st
LI
ED
P
r
o
g
r
a
m
R
e
s
u
l
t
R
e
c
o
g
n
i
z
e
t
e
st
LI
ED
P
r
o
g
r
a
m
R
e
s
u
l
t
S
a
f
e
5
0
%
50
cm
S
u
c
c
e
ss
S
a
f
e
5
0
%
50
cm
S
u
c
c
e
ss
S
a
f
e
5
0
%
76
cm
S
u
c
c
e
ss
S
a
f
e
5
0
%
76
cm
S
u
c
c
e
ss
S
a
f
e
1
0
0
%
50
cm
S
u
c
c
e
ss
S
a
f
e
1
0
0
%
50
cm
S
u
c
c
e
ss
S
a
f
e
1
0
0
%
76
cm
S
u
c
c
e
ss
S
a
f
e
1
0
0
%
76
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
5
0
%
50
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
5
0
%
50
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
5
0
%
76
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
5
0
%
76
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
1
0
0
%
50
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
1
0
0
%
50
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
1
0
0
%
76
cm
S
u
c
c
e
ss
D
a
n
g
e
r
o
u
s
1
0
0
%
76
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
5
0
%
40
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
5
0
%
40
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
5
0
%
60
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
5
0
%
60
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
1
0
0
%
40
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
1
0
0
%
40
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
1
0
0
%
60
cm
S
u
c
c
e
ss
S
c
r
e
e
n
-
to
-
e
y
e
D
i
st
a
n
c
e
1
0
0
%
60
cm
S
u
c
c
e
ss
4.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ef
f
ec
tiv
ely
class
if
ies
f
ac
ial
ex
p
r
ess
io
n
s
as
eith
er
"
s
af
e"
o
r
"
d
an
g
e
r
o
u
s
"
an
d
is
s
u
es
war
n
in
g
s
wh
en
a
"d
an
g
er
o
u
s
"
ex
p
r
ess
io
n
ap
p
ea
r
s
with
7
0
%
ce
r
tain
ty
.
Ad
d
itio
n
ally
,
th
e
ey
e
-
to
-
s
cr
ee
n
d
is
tan
ce
d
etec
tio
n
aler
ts
u
s
er
s
wh
en
th
eir
v
iewin
g
d
is
tan
ce
f
alls
u
n
d
er
4
0
c
m
,
ac
co
u
n
tin
g
f
o
r
v
ar
iatio
n
s
in
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
3
3
-
4
5
4
0
4538
lig
h
tin
g
co
n
d
itio
n
s
.
W
h
ile
th
is
ap
p
r
o
ac
h
en
h
a
n
ce
s
C
VS
p
r
ev
en
tio
n
,
f
u
r
th
er
r
esear
ch
is
r
eq
u
ir
e
d
to
r
ef
in
e
s
y
m
p
to
m
tim
in
g
d
etec
tio
n
,
in
t
eg
r
ate
f
atig
u
e
-
r
elate
d
f
ac
ial
ex
p
r
ess
io
n
s
,
an
d
ex
p
lo
r
e
p
o
ten
ti
al
co
r
r
elatio
n
s
with
o
cu
lar
d
is
o
r
d
e
r
s
.
I
m
p
lem
e
n
tin
g
p
r
e
v
en
tiv
e
m
ea
s
u
r
es
s
u
ch
as
th
e
2
0
-
20
-
2
0
r
u
le
r
em
ain
s
b
en
ef
icial.
Fu
tu
r
e
s
tu
d
ies
co
u
ld
im
p
r
o
v
e
s
y
s
te
m
ad
ap
tab
ilit
y
b
y
lev
e
r
ag
in
g
d
iv
er
s
e
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
s
to
en
h
an
ce
ac
cu
r
ac
y
an
d
u
s
ab
ilit
y
ac
r
o
s
s
d
if
f
er
en
t e
n
v
ir
o
n
m
en
ts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
wo
r
k
was
s
u
p
p
o
r
ted
b
y
th
e
Pu
b
licatio
n
Fu
n
d
in
g
Yea
r
2
0
2
4
th
e
Do
cto
r
al
C
o
m
p
eten
cy
I
m
p
r
o
v
em
en
t
Pr
o
g
r
am
in
2
0
2
4
(
4
3
2
/UN1
.
P1
/KPT/HUK
OR
/2
0
2
4
)
b
y
Un
iv
er
s
itas
Gad
jah
Ma
d
a.
T
h
is
wo
r
k
also
p
ar
tially
s
u
p
p
o
r
te
d
b
y
T
y
p
e
C
Fu
n
d
in
g
b
y
Dep
a
r
tm
en
t o
f
C
o
m
p
u
ter
Scien
ce
an
d
E
lec
tr
o
n
ics,
Un
iv
e
r
s
itas
Gad
jah
Ma
d
a
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Au
f
ac
lav
Z
atu
Ku
s
u
m
a
Frisk
y
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
E
l
a
n
g
A
r
k
a
n
a
u
f
a
A
z
r
i
e
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
ad
en
Su
m
ih
ar
to
✓
✓
✓
✓
Sri
Har
tati
✓
✓
✓
✓
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
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
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
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
u
s
ed
i
n
th
is
s
tu
d
y
ar
e
p
u
b
licly
ac
ce
s
s
ib
le.
T
h
e
FER2
0
1
3
d
ataset
ca
n
b
e
o
b
ta
in
ed
f
r
o
m
Kag
g
le
at
h
ttp
s
://www.
k
ag
g
le.
co
m
/c/ch
allen
g
es
-
in
-
r
ep
r
esen
tatio
n
-
lear
n
in
g
-
f
ac
ial
-
ex
p
r
ess
io
n
-
r
ec
o
g
n
itio
n
-
ch
allen
g
e/d
ata.
T
h
e
C
K+
ca
n
b
e
ac
ce
s
s
ed
at
h
tt
p
s
://d
o
i.o
r
g
/1
0
.
1
1
0
9
/C
VPR
W
.
2
0
1
0
.
5
5
4
3
2
6
2
.
Ad
d
itio
n
ally
,
th
e
ex
ten
d
e
d
a
n
d
a
u
g
m
en
ted
G
o
o
g
le
FER
d
ataset
is
av
ailab
le
o
n
Kag
g
le
at
h
ttp
s
://www.
k
ag
g
le.
co
m
/d
atasets
/p
r
ajwa
ls
o
o
d
/g
o
o
g
le
-
f
e
r
-
im
ag
e
-
f
o
r
m
at/d
ata.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
A
l
a
mr
i
e
t
a
l
.
,
“
C
o
m
p
u
t
e
r
v
i
s
i
o
n
s
y
n
d
r
o
me:
S
y
m
p
t
o
ms,
r
i
sk
f
a
c
t
o
r
s,
a
n
d
p
r
a
c
t
i
c
e
s,”
J
o
u
r
n
a
l
o
f
F
a
m
i
l
y
M
e
d
i
c
i
n
e
a
n
d
Pr
i
m
a
r
y
C
a
r
e
,
v
o
l
.
1
1
,
n
o
.
9
,
p
p
.
5
1
1
0
–
5
1
1
5
,
2
0
2
2
,
d
o
i
:
1
0
.
4
1
0
3
/
j
f
mp
c
.
j
f
m
p
c
_
1
6
2
7
_
2
1
.
[
2
]
M
a
r
v
i
t
a
,
N
.
W
i
d
a
j
a
t
i
,
S
.
N
.
R
a
ma
d
h
a
n
i
,
a
n
d
V
.
W
.
H
a
n
d
a
y
a
n
i
,
“
F
a
c
t
o
r
s rel
a
t
e
d
t
o
c
o
m
p
u
t
e
r
v
i
si
o
n
sy
n
d
r
o
m
e
(
C
V
S
)
c
o
mp
l
a
i
n
t
s
i
n
p
r
o
g
r
a
mm
e
r
s
d
u
r
i
n
g
t
h
e
c
o
v
i
d
-
1
9
p
a
n
d
e
m
i
c
,
”
J
o
u
r
n
a
l
o
f
V
o
c
a
t
i
o
n
a
l
H
e
a
l
t
h
S
t
u
d
i
e
s
,
v
o
l
.
8
,
n
o
.
2
,
p
p
.
9
1
–
9
7
,
2
0
2
4
,
d
o
i
:
1
0
.
2
0
4
7
3
/
j
v
h
s
.
v
8
.
i
2
.
2
0
2
4
.
9
1
-
9
7
.
[
3
]
K
.
K
a
u
r
e
t
a
l
.
,
“
D
i
g
i
t
a
l
e
y
e
s
t
r
a
i
n
-
a
c
o
m
p
r
e
h
e
n
si
v
e
r
e
v
i
e
w
,
”
O
p
h
t
h
a
l
m
o
l
o
g
y
a
n
d
T
h
e
r
a
p
y
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
1
6
5
5
–
1
6
8
0
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
0
1
2
3
-
022
-
0
0
5
4
0
-
9.
[
4
]
F
.
Zh
a
o
,
A
.
W
o
o
d
,
B
.
M
u
t
l
u
,
a
n
d
P
.
N
i
e
d
e
n
t
h
a
l
,
“
F
a
c
e
s
sy
n
c
h
r
o
n
i
z
e
w
h
e
n
c
o
mm
u
n
i
c
a
t
i
o
n
t
h
r
o
u
g
h
s
p
o
k
e
n
l
a
n
g
u
a
g
e
i
s
p
r
e
v
e
n
t
e
d
,
”
Em
o
t
i
o
n
,
v
o
l
.
2
3
,
n
o
.
1
,
p
p
.
8
7
–
9
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
7
/
e
mo
0
0
0
0
7
9
9
.
[
5
]
C
.
Ja
i
n
,
K
.
S
a
w
a
n
t
,
M
.
R
e
h
m
a
n
,
a
n
d
R
.
K
u
m
a
r
,
“
Em
o
t
i
o
n
d
e
t
e
c
t
i
o
n
a
n
d
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
u
si
n
g
f
a
c
i
a
l
f
e
a
t
u
r
e
s,
”
3
rd
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
a
n
d
W
o
r
k
sh
o
p
s
o
n
Re
c
e
n
t
A
d
v
a
n
c
e
s
a
n
d
I
n
n
o
v
a
t
i
o
n
s
i
n
E
n
g
i
n
e
e
r
i
n
g
,
I
C
RAIE
2
0
1
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
A
I
E.
2
0
1
8
.
8
7
1
0
4
0
6
.
[
6
]
I
.
La
p
a
,
S
.
F
e
r
r
e
i
r
a
,
C
.
M
a
t
e
u
s,
N
.
R
o
c
h
a
,
a
n
d
M
.
A
.
R
o
d
r
i
g
u
e
s
,
“
R
e
a
l
-
t
i
me
b
l
i
n
k
d
e
t
e
c
t
i
o
n
a
s
a
n
i
n
d
i
c
a
t
o
r
o
f
c
o
m
p
u
t
e
r
v
i
s
i
o
n
sy
n
d
r
o
me
i
n
r
e
a
l
-
l
i
f
e
s
e
t
t
i
n
g
s:
a
n
e
x
p
l
o
r
a
t
o
r
y
s
t
u
d
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
v
i
r
o
n
m
e
n
t
a
l
Re
se
a
rc
h
a
n
d
P
u
b
l
i
c
H
e
a
l
t
h
,
v
o
l
.
2
0
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
i
j
e
r
p
h
2
0
0
5
4
5
6
9
.
[
7
]
P
.
A
.
d
e
L.
M
e
d
e
i
r
o
s
e
t
a
l
.
,
“
Ef
f
i
c
i
e
n
t
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
v
o
l
u
n
t
e
e
r
e
y
e
-
b
l
i
n
k
d
e
t
e
c
t
i
o
n
i
n
r
e
a
l
-
t
i
me
u
si
n
g
w
e
b
c
a
m
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
8
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
6
0
7
3
.
[
8
]
L.
M
u
t
a
n
u
,
J.
G
o
h
i
l
,
a
n
d
K
.
G
u
p
t
a
,
“
V
i
s
i
o
n
-
a
u
t
o
c
o
r
r
e
c
t
:
a
s
e
l
f
-
a
d
a
p
t
i
n
g
a
p
p
r
o
a
c
h
t
o
w
a
r
d
s
r
e
l
i
e
v
i
n
g
e
y
e
-
st
r
a
i
n
u
si
n
g
f
a
c
i
a
l
-
e
x
p
r
e
ss
i
o
n
r
e
c
o
g
n
i
t
i
o
n
,
”
S
o
f
t
w
a
r
e
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
1
9
7
–
2
1
7
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
o
f
t
w
a
r
e
2
0
2
0
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
C
o
mp
u
ter visi
o
n
s
yn
d
r
o
me
p
r
ev
en
tio
n
:
d
etec
tio
n
o
f e
x
p
r
ess
i
o
n
a
n
d
…
(
A
u
fa
cla
v
Za
tu
K
u
s
u
ma
F
r
is
ky
)
4539
[
9
]
Z.
S
u
n
,
Y
.
M
i
a
o
,
J.
Y
.
J
e
o
n
,
Y
.
K
o
n
g
,
a
n
d
G
.
P
a
r
k
,
“
F
a
c
i
a
l
f
e
a
t
u
r
e
f
u
si
o
n
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
d
r
i
v
e
r
f
a
t
i
g
u
e
d
e
t
e
c
t
i
o
n
,
”
E
n
g
i
n
e
e
r
i
n
g
Ap
p
l
i
c
a
t
i
o
n
s
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
3
.
1
0
6
9
8
1
.
[
1
0
]
A
.
B
a
l
a
su
n
d
a
r
a
m
,
S
.
A
s
h
o
k
k
u
m
a
r
,
D
.
K
o
t
h
a
n
d
a
r
a
ma
n
,
S
.
K
o
r
a
,
E.
S
u
d
a
r
s
h
a
n
,
a
n
d
A
.
H
a
r
sh
a
v
e
r
d
h
a
n
,
“
C
o
mp
u
t
e
r
v
i
s
i
o
n
b
a
se
d
f
a
t
i
g
u
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
f
a
c
i
a
l
p
a
r
a
met
e
r
s,”
I
O
P
C
o
n
f
e
re
n
c
e
S
e
ri
e
s:
M
a
t
e
ri
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
8
1
,
n
o
.
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
7
-
8
9
9
X
/
9
8
1
/
2
/
0
2
2
0
0
5
.
[
1
1
]
G
.
Z
h
a
o
,
Y
.
H
e
,
H
.
Y
a
n
g
,
a
n
d
Y
.
Ta
o
,
“
R
e
se
a
r
c
h
o
n
f
a
t
i
g
u
e
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
v
i
su
a
l
f
e
a
t
u
r
e
s,
”
I
ET
I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
v
o
l
.
1
6
,
n
o
.
4
,
p
p
.
1
0
4
4
–
1
0
5
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
4
9
/
i
p
r
2
.
1
2
2
0
7
.
[
1
2
]
Y
.
H
.
C
h
i
n
,
S
.
H
.
L
i
n
,
C
.
H
.
Li
n
,
E.
S
i
a
h
a
a
n
,
A
.
F
r
i
s
k
y
,
a
n
d
J
.
C
.
W
a
n
g
,
“
Emo
t
i
o
n
p
r
o
f
i
l
e
-
b
a
s
e
d
mu
si
c
r
e
c
o
m
men
d
a
t
i
o
n
,
”
2
0
1
4
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
U
b
i
-
Me
d
i
a
C
o
m
p
u
t
i
n
g
a
n
d
Wo
r
k
s
h
o
p
s
,
p
p
.
1
1
1
–
1
1
4
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
U
-
M
E
D
I
A
.
2
0
1
4
.
3
2
.
[
1
3
]
S
.
F
a
k
h
a
r
e
t
a
l
.
,
“
S
m
a
r
t
c
l
a
ssr
o
o
m
m
o
n
i
t
o
r
i
n
g
u
si
n
g
n
o
v
e
l
r
e
a
l
-
t
i
me
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
r
e
c
o
g
n
i
t
i
o
n
sy
st
e
m,”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
2
3
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
2
3
1
2
1
3
4
.
[
1
4
]
P
.
Ek
m
a
n
,
“
A
r
e
t
h
e
r
e
b
a
si
c
e
m
o
t
i
o
n
s
?
,
”
Psy
c
h
o
l
o
g
i
c
a
l
R
e
v
i
e
w
,
v
o
l
.
9
9
,
n
o
.
3
,
p
p
.
5
5
0
–
5
5
3
,
1
9
9
2
,
d
o
i
:
1
0
.
1
0
3
7
/
0
0
3
3
-
2
9
5
X
.
9
9
.
3
.
5
5
0
.
[
1
5
]
Y
.
K
h
a
i
r
e
d
d
i
n
a
n
d
Z
.
C
h
e
n
,
“
F
a
c
i
a
l
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
:
st
a
t
e
o
f
t
h
e
a
r
t
p
e
r
f
o
r
man
c
e
o
n
F
E
R
2
0
1
3
,
”
a
r
Xi
v
:
2
1
0
5
.
0
3
5
8
8
,
2
0
2
1
.
[
1
6
]
P
.
L
u
c
e
y
,
J.
F
.
C
o
h
n
,
T
.
K
a
n
a
d
e
,
J
.
S
a
r
a
g
i
h
,
Z.
A
mb
a
d
a
r
,
a
n
d
I
.
M
a
t
t
h
e
w
s,
“
Th
e
e
x
t
e
n
d
e
d
C
o
h
n
-
K
a
n
a
d
e
d
a
t
a
s
e
t
(
C
K
+
)
:
a
c
o
m
p
l
e
t
e
d
a
t
a
se
t
f
o
r
a
c
t
i
o
n
u
n
i
t
a
n
d
e
mo
t
i
o
n
-
s
p
e
c
i
f
i
e
d
e
x
p
r
e
ss
i
o
n
,
”
2
0
1
0
I
EEE
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
a
n
d
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
-
W
o
r
k
sh
o
p
s
(
C
VPR
W
2
0
1
0
)
,
p
p
.
9
4
–
1
0
1
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/
C
V
P
R
W
.
2
0
1
0
.
5
5
4
3
2
6
2
.
[
1
7
]
P
.
S
o
o
d
,
“
E
x
t
e
n
d
e
d
a
n
d
a
u
g
me
n
t
e
d
g
o
o
g
l
e
F
E
R
,
”
K
a
g
g
l
e
.
2
0
2
1
.
A
c
c
e
sse
d
:
D
e
c
.
0
8
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
d
a
t
a
se
t
s/
p
r
a
j
w
a
l
so
o
d
/
g
o
o
g
l
e
-
f
e
r
-
i
ma
g
e
-
f
o
r
ma
t
/
d
a
t
a
[
1
8
]
E.
A
.
A
z
r
i
e
n
,
S
.
H
a
r
t
a
t
i
,
a
n
d
A
.
Z.
K
.
F
r
i
sk
y
,
“
R
e
g
u
l
a
r
i
z
e
d
X
c
e
p
t
i
o
n
f
o
r
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
e
x
t
r
a
t
r
a
i
n
i
n
g
d
a
t
a
a
n
d
st
e
p
d
e
c
a
y
l
e
a
r
n
i
n
g
r
a
t
e
,
”
I
AE
S
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
4
7
0
3
–
4
7
1
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
a
i
.
v
1
3
.
i
4
.
p
p
4
7
0
3
-
4
7
1
0
.
[
1
9
]
N
.
Jay
m
o
n
,
S
.
N
a
g
d
e
o
t
e
,
A
.
Y
a
d
a
v
,
a
n
d
R
.
R
o
d
r
i
g
u
e
s,
“
R
e
a
l
t
i
m
e
e
m
o
t
i
o
n
d
e
t
e
c
t
i
o
n
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
1
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
s
i
n
E
l
e
c
t
ri
c
a
l
,
C
o
m
p
u
t
i
n
g
,
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
i
e
s
,
(
I
C
AEC
T
)
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
E
C
T4
9
1
3
0
.
2
0
2
1
.
9
3
9
2
5
8
4
.
[
2
0
]
T.
S
.
G
u
n
a
w
a
n
e
t
a
l
.
,
“
D
e
v
e
l
o
p
m
e
n
t
o
f
v
i
d
e
o
-
b
a
s
e
d
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
w
i
t
h
G
o
o
g
l
e
C
o
l
a
b
,
”
T
e
l
k
o
m
n
i
k
a
(
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
C
o
m
p
u
t
i
n
g
El
e
c
t
r
o
n
i
c
s
a
n
d
C
o
n
t
r
o
l
)
,
v
o
l
.
1
8
,
n
o
.
5
,
p
p
.
2
4
6
3
–
2
4
7
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
2
9
2
8
/
TEL
K
O
M
N
I
K
A
.
v
1
8
i
5
.
1
6
7
1
7
.
[
2
1
]
S
.
V
i
g
n
e
s
h
,
M
.
S
a
v
i
t
h
a
d
e
v
i
,
M
.
S
r
i
d
e
v
i
,
a
n
d
R
.
S
r
i
d
h
a
r
,
“
A
n
o
v
e
l
f
a
c
i
a
l
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
m
o
d
e
l
u
s
i
n
g
s
e
g
m
e
n
t
a
t
i
o
n
V
G
G
-
19
a
r
c
h
i
t
e
c
t
u
r
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
4
,
p
p
.
1
7
7
7
–
1
7
8
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
8
7
0
-
023
-
01184
-
z.
[
2
2
]
H
.
Z
h
a
n
g
,
A
.
J
o
l
f
a
e
i
,
a
n
d
M
.
A
l
a
z
a
b
,
“
A
f
a
c
e
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
m
e
t
h
o
d
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
i
ma
g
e
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
5
9
0
8
1
–
1
5
9
0
8
9
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
4
9
7
4
1
.
[
2
3
]
T.
D
e
b
n
a
t
h
,
M
.
M
.
R
e
z
a
,
A
.
R
a
h
ma
n
,
A
.
B
e
h
e
s
h
t
i
,
S
.
S
.
B
a
n
d
,
a
n
d
H
.
A
l
i
n
e
j
a
d
-
R
o
k
n
y
,
“
F
o
u
r
-
l
a
y
e
r
C
o
n
v
N
e
t
t
o
f
a
c
i
a
l
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
mi
n
i
mal
e
p
o
c
h
s
a
n
d
t
h
e
si
g
n
i
f
i
c
a
n
c
e
o
f
d
a
t
a
d
i
v
e
r
si
t
y
,
”
S
c
i
e
n
t
i
f
i
c
Re
p
o
rt
s
,
v
o
l
.
1
2
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
3
8
/
s
4
1
5
9
8
-
0
2
2
-
1
1
1
7
3
-
0.
[
2
4
]
S
.
A
.
H
u
ssa
i
n
,
W
a
se
e
mu
l
l
a
h
,
a
n
d
N
.
A
.
K
h
a
n
,
“
F
a
c
e
-
to
-
c
a
mera
d
i
s
t
a
n
c
e
e
st
i
mat
i
o
n
u
si
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
,
”
3
rd
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
S
o
f
t
w
a
r
e
E
n
g
i
n
e
e
r
i
n
g
(
I
C
O
N
I
C
S
)
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
N
I
C
S
5
6
7
1
6
.
2
0
2
2
.
1
0
1
0
0
6
1
8
.
[
2
5
]
M
.
M
e
g
h
a
n
a
,
M
.
V
a
sa
v
i
,
a
n
d
D
.
S
h
r
a
v
a
n
i
,
“
F
a
c
i
a
l
l
a
n
d
mar
k
d
e
t
e
c
t
i
o
n
w
i
t
h
m
e
d
i
a
p
i
p
e
&
c
r
e
a
t
i
n
g
a
n
i
ma
t
e
d
sn
a
p
c
h
a
t
f
i
l
t
e
r
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
Fo
r
I
n
n
o
v
a
t
i
v
e
En
g
i
n
e
e
ri
n
g
a
n
d
M
a
n
a
g
e
m
e
n
t
R
e
se
a
rc
h
,
p
p
.
9
8
–
1
0
7
,
2
0
2
2
,
d
o
i
:
1
0
.
4
8
0
4
7
/
i
j
i
e
mr
/
v
1
1
/
i
0
6
/
1
0
.
[
2
6
]
D
.
B
.
B
e
n
i
z
a
n
d
A
.
M
.
Es
p
i
n
d
o
l
a
,
“
U
si
n
g
t
k
i
n
t
e
r
o
f
p
y
t
h
o
n
t
o
c
r
e
a
t
e
g
r
a
p
h
i
c
a
l
u
ser
i
n
t
e
r
f
a
c
e
(
G
U
I
)
f
o
r
scri
p
t
s
i
n
LN
LS,”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
1
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
W
o
rks
h
o
p
o
n
Pe
rs
o
n
a
l
C
o
m
p
u
t
e
rs
a
n
d
P
a
rt
i
c
l
e
A
c
c
e
l
e
r
a
t
o
r
C
o
n
t
ro
l
s
(
P
C
a
PAC
)
,
p
p
.
5
6
–
5
8
,
2
0
1
6
.
[
2
7
]
A
.
Z.
K
.
F
r
i
s
k
y
,
A
.
H
a
r
j
o
k
o
,
L.
A
w
a
l
u
d
i
n
,
S
.
Z
a
mb
a
n
i
n
i
,
a
n
d
R
.
S
a
b
l
a
t
n
i
g
,
“
I
n
v
e
st
i
g
a
t
i
o
n
o
f
si
n
g
l
e
i
ma
g
e
d
e
p
t
h
p
r
e
d
i
c
t
i
o
n
u
n
d
e
r
d
i
f
f
e
r
e
n
t
l
i
g
h
t
i
n
g
c
o
n
d
i
t
i
o
n
s,
”
J
o
u
rn
a
l
o
n
C
o
m
p
u
t
i
n
g
a
n
d
C
u
l
t
u
r
a
l
H
e
ri
t
a
g
e
,
v
o
l
.
1
4
,
n
o
.
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
4
6
5
7
4
2
.
[
2
8
]
D
.
Ji
r
a
k
,
A
.
S
c
i
u
t
t
i
,
P
.
B
a
r
r
o
s,
a
n
d
F
.
R
e
a
,
“
I
a
m
o
n
l
y
h
a
p
p
y
w
h
e
n
t
h
e
r
e
i
s l
i
g
h
t
:
t
h
e
i
mp
a
c
t
o
f
e
n
v
i
r
o
n
me
n
t
a
l
c
h
a
n
g
e
s o
n
a
f
f
e
c
t
i
v
e
f
a
c
i
a
l
e
x
p
r
e
ss
i
o
n
s
r
e
c
o
g
n
i
t
i
o
n
,
”
a
rXi
v
:
2
2
1
0
.
1
7
4
2
1
,
2
0
2
2
.
[
2
9
]
P
.
Ti
a
n
e
t
a
l
.
,
“
Ef
f
e
c
t
s
o
f
p
a
r
a
d
i
g
m
c
o
l
o
r
a
n
d
scre
e
n
b
r
i
g
h
t
n
e
ss
o
n
v
i
s
u
a
l
f
a
t
i
g
u
e
i
n
l
i
g
h
t
e
n
v
i
r
o
n
me
n
t
o
f
n
i
g
h
t
b
a
s
e
d
o
n
e
y
e
t
r
a
c
k
e
r
a
n
d
EEG
a
c
q
u
i
si
t
i
o
n
e
q
u
i
p
me
n
t
,
”
S
e
n
s
o
rs
,
v
o
l
.
2
2
,
n
o
.
1
1
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
2
1
1
4
0
8
2
.
[
3
0
]
A
.
G
e
r
h
a
r
d
ss
o
n
,
L
.
H
ö
g
m
a
n
,
a
n
d
H
.
F
i
sc
h
e
r
,
“
V
i
e
w
i
n
g
d
i
st
a
n
c
e
m
a
t
t
e
r
t
o
p
e
r
c
e
i
v
e
d
i
n
t
e
n
si
t
y
o
f
f
a
c
i
a
l
e
x
p
r
e
ssi
o
n
s,”
Fr
o
n
t
i
e
rs
i
n
Psy
c
h
o
l
o
g
y
,
v
o
l
.
6
,
2
0
1
5
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
sy
g
.
2
0
1
5
.
0
0
9
4
4
.
[
3
1
]
G
.
K
i
m,
S
.
H
.
S
e
o
n
g
,
S
.
S
.
H
o
n
g
,
a
n
d
E.
C
h
o
i
,
“
I
mp
a
c
t
o
f
f
a
c
e
mas
k
s
a
n
d
su
n
g
l
a
sse
s
o
n
e
m
o
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
i
n
S
o
u
t
h
K
o
r
e
a
n
s,
”
PLo
S
O
N
E
,
v
o
l
.
1
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
6
3
4
6
6
.
[
3
2
]
C
.
Ju
n
g
,
T.
S
u
n
,
a
n
d
L.
J
i
a
o
,
“
E
y
e
d
e
t
e
c
t
i
o
n
u
n
d
e
r
v
a
r
y
i
n
g
i
l
l
u
mi
n
a
t
i
o
n
u
s
i
n
g
t
h
e
r
e
t
i
n
e
x
t
h
e
o
r
y
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
1
1
3
,
p
p
.
1
3
0
–
1
3
7
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m
.
2
0
1
3
.
0
1
.
0
3
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Aufa
c
la
v
Za
tu
K
u
s
u
m
a
Frisky
re
c
e
iv
e
d
th
e
b
a
c
h
e
l
o
r
d
e
g
re
e
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
El
e
c
tro
n
ics
,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
t
u
ra
l
S
c
ien
c
e
s
fr
o
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
in
2
0
1
2
a
n
d
M
.
S
c
.
d
e
g
re
e
i
n
De
p
a
rtme
n
t
o
f
C
o
m
p
u
te
r
S
c
ien
c
e
a
n
d
In
fo
rm
a
ti
o
n
E
n
g
i
n
e
e
rin
g
fr
o
m
Na
ti
o
n
a
l
Ce
n
tral
U
n
iv
e
rsity
,
Taiwa
n
in
2
0
1
5
.
He
g
ra
d
u
a
ted
a
s
a
Do
c
to
ra
l
S
t
u
d
e
n
t
a
t
Co
m
p
u
ter
Visio
n
Lab
,
In
st
it
u
t
e
o
f
Visu
a
l
Co
m
p
u
ti
n
g
a
n
d
Hu
m
a
n
-
Ce
n
tere
d
Tec
h
n
o
l
o
g
y
,
T
U
Wi
e
n
,
Au
stria,
i
n
2
0
2
3
.
His
re
se
a
rc
h
in
tere
st
s
i
n
c
lu
d
e
c
o
m
p
u
ter
v
isio
n
,
m
a
c
h
in
e
v
isio
n
,
sin
g
le
ima
g
e
re
c
o
n
stru
c
ti
o
n
,
a
n
d
it
s
a
p
p
li
c
a
ti
o
n
s
in
c
u
lt
u
ra
l
h
e
rit
a
g
e
p
re
se
rv
a
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
u
fa
c
lav
@
u
g
m
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
4
,
No
.
6
,
Dec
em
b
er
2
0
2
5
:
4
5
3
3
-
4
5
4
0
4540
Ela
n
g
Ar
k
a
n
a
u
fa
Az
r
ien
g
ra
d
u
a
ted
wit
h
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
d
e
g
re
e
in
De
p
a
rtme
n
t
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
n
d
El
e
c
tro
n
ics
,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
in
2
0
2
4
.
Cu
rre
n
tl
y
,
h
e
is
o
n
e
o
f
th
e
re
se
a
rc
h
e
rs
in
th
e
El
e
c
tro
n
ics
a
n
d
I
n
stru
m
e
n
tati
o
n
S
tu
d
ies
P
ro
g
ra
m
a
t
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
His
m
a
in
re
se
a
rc
h
f
o
c
u
se
s
o
n
m
a
c
h
in
e
lea
rn
i
n
g
a
n
d
c
o
m
p
u
ter
v
isio
n
.
Wi
t
h
k
n
o
wle
d
g
e
in
b
o
th
f
ield
s,
h
e
e
n
g
a
g
e
s
in
re
se
a
rc
h
a
ime
d
a
t
g
a
in
in
g
in
-
d
e
p
t
h
u
n
d
e
rsta
n
d
i
n
g
a
n
d
d
e
v
e
l
o
p
in
g
p
ra
c
ti
c
a
l
so
lu
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
e
lan
g
.
a
rk
a
n
a
u
fa
.
a
z
rien
@g
m
a
il
.
c
o
m
or
e
lan
g
.
a
rk
a
n
a
u
fa
.
a
z
rien
@m
a
il
.
u
g
m
.
a
c
.
id
.
Ra
d
e
n
S
u
m
ih
a
r
t
o
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r'
s
d
e
g
re
e
i
n
P
h
y
sic
s
fro
m
Un
i
v
e
rsitas
G
a
d
jah
M
a
d
a
,
In
d
o
n
e
sia
,
i
n
2
0
0
2
a
n
d
h
is
m
a
ste
r’s
d
e
g
re
e
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
I
n
d
o
n
e
sia
,
in
2
0
0
7
.
He
is
c
u
rre
n
tl
y
a
l
e
c
tu
re
r
a
t
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
lec
tro
n
ic
s,
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
n
a
n
o
sa
telli
te
,
UA
V,
p
a
ra
ll
e
l
p
r
o
c
e
ss
in
g
,
se
n
s
o
r
n
e
two
rk
s,
a
n
d
g
ri
d
sy
ste
m
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
r_
s
u
m
ih
a
rto
@u
g
m
.
a
c
.
i
d
.
S
r
i
H
a
r
ta
ti
c
u
rre
n
tl
y
h
o
ld
s
th
e
p
o
si
ti
o
n
o
f
l
e
c
tu
re
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
El
e
c
tro
n
ics
a
t
th
e
F
a
c
u
lt
y
o
f
M
a
th
e
m
a
ti
c
s
a
n
d
Na
tu
ra
l
S
c
ien
c
e
s,
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
(UG
M
).
S
h
e
e
a
rn
e
d
h
e
r
m
a
ste
r'
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
th
e
Un
iv
e
rsit
y
o
f
Ne
w
Bru
n
sw
ick
,
Ca
n
a
d
a
,
d
u
ri
n
g
th
e
p
e
ri
o
d
o
f
S
e
p
tem
b
e
r
1
9
8
8
t
o
Oc
to
b
e
r
1
9
9
0
.
Wi
t
h
a
p
r
o
fo
u
n
d
a
c
a
d
e
m
ic
b
a
c
k
g
ro
u
n
d
,
s
h
e
h
a
s
b
e
e
n
a
c
ti
v
e
ly
c
o
n
tri
b
u
t
in
g
t
o
th
e
f
ield
s
o
f
c
o
m
p
u
ter
sc
ien
c
e
,
c
o
m
p
u
ter
re
a
so
n
in
g
,
a
n
d
a
rti
ficia
l
in
tell
ig
e
n
c
e
.
He
r
d
e
d
ica
ti
o
n
i
s
re
flec
ted
in
h
e
r
e
x
ten
si
v
e
p
u
b
li
c
a
ti
o
n
re
c
o
r
d
,
b
o
a
sti
n
g
1
1
4
a
rti
c
l
e
s
in
re
p
u
tab
le
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sh
a
rtati@u
g
m
.
a
c
.
id
.
Evaluation Warning : The document was created with Spire.PDF for Python.