I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
1
6
5
~
5
1
7
5
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
6
.
pp
5
1
6
5
-
5175
5165
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Ins
ig
ht
o
n f
a
ce
livenes
s det
ection:
A
sy
ste
m
a
tic
li
terat
ure re
v
iew
E
na
s
A.
Ra
hee
m
1
,
S
ha
rif
a
h M
um
t
a
za
h Sy
ed
Ah
m
a
d
2
,
W
a
n Az
izun Wa
n Ad
na
n
3
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Un
iv
e
rsity
o
f
T
e
c
h
n
o
lo
g
y
,
Ira
q
2
,
3
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter an
d
C
o
m
m
u
n
ica
ti
o
n
S
y
ste
m
s,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
P
u
tra M
a
lay
sia
(UP
M
)
,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
21
,
2
0
1
8
R
ev
i
s
ed
J
u
l 1
7
,
2
0
1
9
A
cc
ep
ted
J
u
l 2
9
,
2
0
1
9
T
o
re
v
ie
w
re
se
a
r
c
h
e
r‟s
a
tt
e
m
p
ts
in
re
sp
o
n
se
to
t
h
e
p
r
o
b
lem
o
f
sp
o
o
f
in
g
a
n
d
li
v
e
n
e
ss
d
e
tec
ti
o
n
,
m
a
p
p
in
g
th
e
r
e
se
a
rc
h
o
v
e
rv
i
e
w
f
ro
m
th
e
li
tera
t
u
re
su
rv
e
y
in
to
a
su
it
a
b
le
tax
o
n
o
m
y
,
e
x
p
lo
rin
g
t
h
e
b
a
sic
p
ro
p
e
rti
e
s
o
f
th
e
f
ield
,
m
o
ti
v
a
ti
o
n
o
f
u
sin
g
li
v
e
n
e
ss
d
e
tec
ti
o
n
m
e
th
o
d
s
i
n
f
a
c
e
re
c
o
g
n
it
io
n
,
a
n
d
P
r
o
b
lem
s
th
a
t
m
a
y
re
stra
in
th
e
a
d
v
a
n
tag
e
s.
We
p
re
se
n
ted
a
su
b
je
c
ted
se
a
rc
h
o
n
f
a
c
e
re
c
o
g
n
it
io
n
w
it
h
li
v
e
n
e
s
s
d
e
tec
ti
o
n
a
n
d
it
s
s
y
n
o
n
y
m
s
in
f
o
u
r
m
a
in
d
a
tab
a
se
s:
Web
o
f
sc
i
e
n
c
e
,
S
c
ie
n
c
e
Dire
c
t,
S
c
o
p
u
s
a
n
d
IEE
E
Xp
lo
re
.
W
e
b
e
li
e
v
e
th
a
t
th
e
se
d
a
tab
a
se
s
a
re
w
id
e
l
y
in
c
lu
siv
e
e
n
o
u
g
h
t
o
c
o
v
e
r
th
e
li
tera
tu
re
.
T
h
e
f
in
a
l
n
u
m
b
e
r
o
f
a
rti
c
les
c
o
n
sid
e
re
d
is
6
5
a
rti
c
les
.
4
o
f
th
e
m
w
h
e
re
r
e
v
ie
w
a
n
d
su
rv
e
y
a
rti
c
le
s
th
a
t
d
e
sc
rib
e
d
a
g
e
n
e
ra
l
o
v
e
rv
iew
a
b
o
u
t
li
v
e
n
e
ss
d
e
tec
ti
o
n
a
n
d
a
n
t
i
-
sp
o
o
f
in
g
m
e
th
o
d
s.
S
in
c
e
2
0
1
2
,
a
n
d
d
e
sp
it
e
o
f
lea
v
in
g
so
m
e
a
re
a
s
u
n
e
sta
b
li
sh
e
d
a
n
d
n
e
e
d
s
m
o
re
a
tt
e
n
ti
o
n
,
re
se
a
rc
h
e
rs
tri
e
d
to
k
e
e
p
trac
k
o
f
li
v
e
n
e
ss
d
e
tec
ti
o
n
i
n
se
v
e
ra
l
w
a
y
s.
No
m
a
tt
e
r
w
h
a
t
th
e
ir
c
a
teg
o
r
y
is,
a
rti
c
le
s
c
o
n
c
e
n
trate
d
o
n
c
h
a
ll
e
n
g
e
s
th
a
t
f
a
c
e
s
th
e
f
u
ll
u
ti
li
ty
o
f
a
n
ti
-
sp
o
o
f
in
g
m
e
th
o
d
s
a
n
d
re
c
o
m
m
e
n
d
e
d
so
m
e
so
lu
ti
o
n
s
t
o
o
v
e
rc
o
m
e
th
e
s
e
c
h
a
ll
e
n
g
e
s.
In
th
is
p
a
p
e
r,
d
if
f
e
re
n
t
ty
p
e
s
o
f
li
v
e
n
e
s
s
d
e
tec
ti
o
n
a
n
d
f
a
c
e
a
n
ti
-
sp
o
o
f
in
g
tec
h
n
i
q
u
e
s are
in
v
e
stig
a
ted
to
k
e
e
p
r
e
se
a
rc
h
e
rs u
p
d
a
ted
with
w
h
a
t
is
b
e
in
g
d
e
v
e
lo
p
e
d
in
th
is
f
ield
.
K
ey
w
o
r
d
s
:
An
ti
-
s
p
o
o
f
i
n
g
B
io
m
etr
ic
Face
liv
e
n
es
s
d
etec
tio
n
S
y
s
te
m
a
tic
liter
at
u
r
e
r
ev
ie
w
T
ax
o
n
o
m
y
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
E
n
as
A
.
R
a
h
ee
m
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
an
d
C
o
m
m
u
n
ica
tio
n
S
y
s
te
m
s
,
Facu
lt
y
o
f
E
n
g
i
n
ee
r
i
n
g
,
Un
i
v
er
s
iti P
u
tr
a
Ma
la
y
s
ia
(
UP
M)
,
Selan
g
o
r
,
4
3
4
0
0
,
Ma
lay
s
ia
.
E
m
ail:
al
k
i
n
an
y
.
en
a
s
9
1
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
B
io
m
etr
ic
s
is
a
m
u
ltid
is
cip
li
n
ar
y
f
ield
in
v
o
l
v
ed
w
i
th
m
ea
s
u
r
i
n
g
a
n
d
m
ap
p
in
g
s
p
ec
i
f
ic
b
io
lo
g
ical
tr
aits
,
e.
g
.
f
i
n
g
er
p
r
in
t
s
,
f
ac
e,
p
al
m
v
ei
n
s
,
etc.
to
b
e
u
s
ed
as
an
in
d
i
v
id
u
alize
d
r
ec
o
g
n
itio
n
c
o
d
e
[
1
]
.
B
io
m
etr
ic
tr
aits
ca
n
b
e
class
i
f
ied
in
to
t
w
o
g
r
o
u
p
s
t
h
at
ar
e
p
h
y
s
ica
l
tr
aits
s
u
c
h
as
af
o
r
e
m
e
n
tio
n
ed
ex
a
m
p
le
s
an
d
b
eh
av
io
r
al
tr
aits
s
u
ch
a
s
s
i
g
n
atu
r
e,
v
o
ice
an
d
k
e
y
s
tr
o
k
e
s
.
B
io
m
etr
ic
is
e
s
s
e
n
tial
f
o
r
a
w
id
e
r
a
n
g
e
o
f
tech
n
o
lo
g
ies.
Ho
w
ev
er
,
o
n
e
o
f
th
e
m
a
in
o
b
s
tacle
s
f
ac
in
g
b
i
o
m
e
tr
ic
r
ec
o
g
n
itio
n
s
y
s
te
m
s
i
s
f
r
au
d
u
len
t
id
en
tit
y
w
h
ic
h
is
co
n
ce
p
tu
a
ll
y
r
ef
er
r
ed
as
a
s
p
o
o
f
i
n
g
attac
k
.
B
r
o
ad
ly
,
t
w
o
t
y
p
es
o
f
attac
k
s
ca
n
b
e
co
n
s
id
er
ed
:
in
d
ir
ec
t
an
d
d
ir
ec
t
attac
k
s
.
I
n
d
ir
ec
t
att
ac
k
s
ar
e
i
m
p
le
m
e
n
ted
i
n
s
id
e
t
h
e
s
y
s
te
m
,
i
n
tr
u
d
ed
b
y
h
ac
k
er
s
o
r
i
n
tr
u
d
er
s
,
e.
g
.
b
y
ta
m
p
er
in
g
t
h
e
f
ea
t
u
r
e
ex
tr
ac
to
r
(
i.e
.
m
atch
er
)
,
o
r
b
y
p
er
f
o
r
m
i
n
g
m
o
d
if
icatio
n
s
to
th
e
te
m
p
late
d
atab
ase.
I
n
d
ir
ec
t
attac
k
s
ca
n
b
e
p
r
ec
lu
d
ed
b
y
v
ar
io
u
s
m
ea
s
u
r
es
i
n
clu
d
i
n
g
b
u
t
n
o
t
li
m
ited
to
an
ti
-
v
ir
u
s
s
o
f
t
w
ar
e,
f
ir
e
w
all
s
,
en
cr
y
p
tio
n
a
n
d
in
tr
u
s
io
n
d
etec
tio
n
.
Dir
ec
t
attac
k
s
o
n
th
e
o
th
er
h
an
d
,
ar
e
ca
r
r
i
ed
o
u
t
at
th
e
s
en
s
o
r
lev
el
o
u
t
s
id
e
th
e
d
ig
ita
l
li
m
i
ts
o
f
th
e
s
y
s
te
m
a
n
d
th
er
e
f
o
r
e,
n
o
m
ec
h
a
n
i
s
m
s
f
o
r
d
ig
ital
p
r
o
tectio
n
ca
n
b
e
u
s
ed
to
an
ticip
ate
it
[
1
]
.
L
i
v
en
e
s
s
d
etec
tio
n
i
s
a
m
aj
o
r
ar
ea
o
f
i
n
ter
es
t
w
it
h
in
th
e
f
ie
ld
o
f
b
io
m
etr
ic
th
at
en
co
m
p
as
s
es
a
p
r
o
ce
s
s
o
f
v
er
if
y
i
n
g
w
h
et
h
er
t
h
e
b
io
m
etr
ic
b
ein
g
ca
p
t
u
r
ed
b
y
t
h
e
r
ec
o
g
n
itio
n
s
y
s
te
m
i
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
6
5
-
5
1
7
5
5166
g
en
u
i
n
e
(
i.e
.
ali
v
e)
o
r
h
as
b
ee
n
m
i
m
ick
ed
b
y
in
tr
u
d
er
s
t
o
h
av
e
a
n
u
n
a
u
t
h
o
r
ized
ac
ce
s
s
to
t
h
e
b
io
m
etr
ic
s
y
s
te
m
.
I
n
t
h
e
liter
at
u
r
e
o
n
li
v
e
n
ess
d
etec
tio
n
,
t
h
e
r
elati
v
e
i
m
p
o
r
ta
n
ce
o
f
f
ac
e
li
v
e
n
ess
d
etec
tio
n
h
as
b
ee
n
s
u
b
j
ec
t
to
co
n
s
id
er
ab
le
d
is
cu
s
s
io
n
.
I
n
th
is
ar
ticle
w
e
p
r
o
v
i
d
e
a
r
ev
ie
w
o
f
t
h
e
s
tate
-
of
-
t
h
e
-
ar
t
an
t
i
-
s
p
o
o
f
in
g
d
etec
tio
n
tech
n
iq
u
e
s
f
o
r
f
ac
i
al
b
io
m
e
tr
ics.
Face
a
n
ti
-
s
p
o
o
f
i
n
g
tec
h
n
iq
u
e
s
r
eq
u
ir
es
a
g
en
u
i
n
e
p
h
o
to
g
r
ap
h
,
r
ec
o
r
d
e
d
v
id
eo
o
r
d
u
m
m
y
ev
i
d
en
ce
etc.
to
b
e
p
r
esen
t
a
t
t
h
e
s
en
s
o
r
(
i.e
.
ca
m
er
a)
.
P
h
o
to
g
r
ap
h
s
g
en
er
all
y
lac
k
s
th
e
3
D
in
f
o
r
m
at
io
n
‟
s
a
n
d
p
r
o
v
id
es
less
p
h
y
s
io
lo
g
ical
e
v
i
d
en
ce
s
th
a
n
v
id
eo
s
ca
n
p
r
o
v
id
e.
T
h
is
ca
n
b
e
ex
p
lo
ited
in
li
v
en
e
s
s
d
etec
tio
n
a
s
a
li
m
itatio
n
o
f
s
ta
tic
i
m
ag
es.
Ho
w
e
v
er
,
v
id
eo
s
ca
p
t
u
r
ed
b
y
h
ig
h
q
u
alit
y
ca
m
er
as
ca
n
b
e
also
a
ch
a
llen
g
in
g
s
p
o
o
f
in
g
attac
k
as
th
e
y
p
r
o
v
id
e
a
s
tr
o
n
g
s
ig
n
f
o
r
v
ital
it
y
t
h
r
o
u
g
h
m
o
tio
n
.
Du
m
m
y
m
o
d
el
s
o
n
th
e
o
th
er
h
an
d
ca
n
b
e
a
th
r
ea
t
to
f
ac
ial
b
io
m
etr
ic
s
y
s
te
m
co
n
tain
in
g
3
D
in
f
o
r
m
atio
n
t
h
a
t
s
tatic
i
m
a
g
es a
n
d
v
id
eo
s
d
o
n
o
t p
r
o
v
id
e
[
2
]
. R
ec
en
t d
ev
elo
p
m
en
ts
i
n
t
h
e
f
ield
o
f
f
ac
ial
b
io
m
etr
ic
h
av
e
led
to
a
r
en
e
w
ed
in
ter
e
s
t
i
n
li
v
e
n
es
s
d
etec
tio
n
as
a
s
o
l
u
tio
n
f
o
r
s
p
o
o
f
i
n
g
a
ttack
p
r
o
b
lem
s
.
T
h
e
p
u
r
p
o
s
e
o
f
th
is
p
ap
er
is
to
r
ev
ie
w
r
ec
en
t
r
esear
c
h
ef
f
o
r
ts
m
ap
p
in
g
th
e
m
in
to
a
co
h
esiv
e
tax
o
n
o
m
y
b
a
s
ed
o
n
liv
en
e
s
s
in
d
icato
r
s
an
d
a
f
u
r
t
h
er
clas
s
if
icatio
n
i
s
p
r
o
v
id
ed
o
n
f
ac
e
an
ti
-
s
p
o
o
f
i
n
g
tech
n
iq
u
es.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
A
b
lo
ck
d
iag
r
a
m
o
f
f
ac
e
liv
e
n
ess
d
etec
tio
n
s
y
s
te
m
ar
c
h
itect
u
r
e
is
s
h
o
w
n
i
n
F
i
g
u
r
e
1
,
it
is
n
ec
es
s
ar
y
to
clar
if
y
t
h
e
ex
ac
t
p
r
o
ce
s
s
o
f
u
s
i
n
g
l
iv
e
n
es
s
d
etec
tio
n
s
y
s
t
e
m
w
h
ich
i
n
v
o
lv
e
s
a
u
s
er
to
p
r
esen
t
a
b
io
m
etr
i
c
s
a
m
p
le
to
th
e
s
en
s
o
r
,
w
h
ic
h
is
a
ca
m
er
a
in
o
u
r
ca
s
e.
T
h
e
f
ac
e
i
m
ag
e
i
s
t
h
en
p
r
ep
r
o
ce
s
s
ed
ap
p
r
o
p
r
iate
f
o
r
m
(
e.
g
.
th
r
o
u
g
h
n
o
is
e
r
e
m
o
v
al,
b
lu
r
an
d
f
o
cu
s
co
r
r
ec
tio
n
s
tech
n
iq
u
e
s
)
s
o
th
at
t
h
e
i
m
a
g
e
is
r
ea
d
y
to
th
e
n
e
x
t
s
tep
o
f
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
T
h
e
o
u
t
p
u
t
b
io
m
etr
ic
te
m
p
la
te
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
is
a
d
is
tin
g
u
i
s
h
ab
le
s
a
m
p
le
w
it
h
d
is
ti
n
ct
f
ea
t
u
r
es
th
at
allo
w
s
cla
s
s
i
f
ier
to
d
ec
id
e
w
h
et
h
e
r
p
r
esen
ted
s
a
m
p
le
i
s
r
ea
l
o
r
s
p
o
o
f
ed
b
y
th
e
aid
o
f
p
r
e
-
tr
ain
ed
d
ata.
Gen
u
i
n
e
s
a
m
p
les
w
i
ll
b
e
p
r
o
ce
s
s
ed
f
o
r
id
en
ti
f
icatio
n
,
w
h
i
le
s
p
o
o
f
e
d
s
a
m
p
les
w
ill
b
e
au
to
m
at
icall
y
d
is
ca
r
d
ed
f
o
r
au
th
e
n
tica
tio
n
,
a
n
d
in
o
r
d
er
to
m
ea
s
u
r
e
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
liv
e
n
es
s
d
etec
tio
n
s
y
s
te
m
,
th
e
f
o
llo
w
i
n
g
m
ea
s
u
r
e
m
e
n
ts
a
r
e
d
ef
in
ed
[
3
]
:
-
Fals
e
R
ej
ec
t Ratio
(
F
R
R
)
: it
i
s
th
e
r
ate
w
h
er
e
a
liv
e
s
a
m
p
le
i
s
id
en
ti
f
ied
as a
s
p
o
o
f
attac
k
.
-
Fals
e
A
cc
ep
ta
n
ce
R
atio
(
F
AR
)
:
it
i
s
t
h
e
r
ate
o
f
s
y
s
te
m
w
h
er
e
a
f
ak
e
s
a
m
p
le
i
s
a
u
th
en
ticated
as
li
v
e
(
g
en
u
i
n
e)
s
a
m
p
le.
-
Failu
r
e
to
A
cq
u
ir
e
(
F
A
)
: it
i
s
t
h
e
r
ate
o
f
th
e
s
y
s
te
m
w
h
e
n
it
f
ails
to
p
er
f
o
r
m
s
a
m
p
les co
llect
io
n
.
-
Me
an
T
r
an
s
ac
tio
n
T
i
m
e
(
MT
T
)
: it
is
th
e
av
er
ag
e
o
f
s
y
s
te
m
‟
s
r
eq
u
ir
ed
ti
m
e
f
o
r
m
ak
i
n
g
a
d
ec
is
io
n
.
-
R
ec
eiv
er
Op
er
atin
g
C
h
ar
ac
te
r
is
tic
(
R
OC
)
:
p
lo
ts
t
h
at
ar
e
u
s
ed
to
s
elec
t
t
h
e
o
p
er
atin
g
t
h
r
es
h
o
ld
o
f
th
e
s
y
s
te
m
w
it
h
p
r
io
r
k
n
o
w
led
g
e
o
f
t
h
e
FR
R
an
d
F
AR
p
r
o
b
ab
ilit
y
.
Fig
u
r
e
1
.
B
lo
ck
d
iag
r
a
m
o
f
f
a
ce
liv
en
e
s
s
d
etec
tio
n
s
y
s
te
m
Ac
q
u
isi
tion
De
vice
(Sensor)
P
r
e
-
p
r
o
c
e
ssi
n
g
F
e
a
ture
E
xt
r
ac
t
ion
Classi
f
icat
ion
De
c
isi
on
(Live/F
ak
e
)
T
ra
ini
ng
Da
t
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
t o
n
f
a
ce
liven
ess
d
etec
tio
n
:
a
s
ystema
tic
liter
a
tu
r
e
r
ev
iew
(
E
n
a
s
A
.
R
a
h
ee
m
)
5167
An
o
th
er
i
m
p
o
r
ta
n
t
asp
ec
t
o
f
v
italit
y
d
etec
tio
n
th
at
d
eser
v
es
to
b
e
h
ig
h
li
g
h
ted
is
t
h
e
p
u
b
licl
y
av
ailab
le
d
atab
ases
t
h
at
co
n
s
is
t
o
f
i
m
ag
e
s
o
f
v
ar
io
u
s
te
x
tu
r
e
s
w
h
ich
h
a
v
e
b
ee
n
u
til
ized
ex
ten
s
i
v
el
y
in
v
alid
ati
n
g
l
iv
e
n
es
s
d
etec
tio
n
ag
ain
s
t
s
p
o
o
f
i
n
g
attac
k
s
s
u
c
h
as
h
i
g
h
-
q
u
alit
y
i
m
ag
e
s
attac
k
s
to
v
id
eo
-
r
ep
la
y
s
.
T
h
e
av
ailab
le
d
atab
ases
an
d
th
e
liter
atu
r
e
th
at
u
t
ilized
th
ese
d
atab
ases
is
d
escr
ib
ed
in
T
ab
l
e
1
.
A
lth
o
u
g
h
th
es
e
d
atab
ases
p
r
o
v
id
ed
a
v
er
y
u
s
ef
u
l
to
o
l
f
o
r
r
esear
ch
er
s
,
th
e
lack
o
f
p
u
b
licl
y
a
v
ailab
le
d
atasets
o
f
d
i
f
f
er
en
t
n
atu
r
e
s
u
c
h
as
e
y
e
b
lin
k
i
n
g
v
i
d
eo
s
o
r
m
o
u
th
a
n
d
h
ea
d
m
o
v
e
m
en
t,
th
is
li
m
ita
tio
n
m
ak
e
s
it
h
ar
d
to
b
en
ch
m
ar
k
w
it
h
s
u
c
h
an
t
i
-
s
p
o
o
f
in
g
m
eth
o
d
s
.
T
ab
le
1
.
P
u
b
licl
y
av
ailab
le
d
at
ab
ases
No
D
a
t
a
b
a
se
D
e
t
e
c
t
i
o
n
M
e
t
h
o
d
R
e
f
e
r
e
n
c
e
T
e
x
t
u
r
e
L
i
f
e
si
g
n
i
n
d
i
c
a
t
o
r
3
D
P
r
o
p
e
r
t
i
e
s
1
R
e
p
l
a
y
A
t
t
a
c
k
√
[4
,
5]
2
NUAA
√
[6
-
8]
3
C
A
S
I
A
√
[9
,
1
0
]
4
Y
A
L
E
√
[
6
]
5
X
M
2
V
T
S
√
√
[
1
1
,
12]
6
F
S
A
√
[
1
3
]
7
O
T
C
B
V
S
√
[
1
4
]
8
UC
BN
√
√
[
1
5
]
9
3
D
M
A
D
√
[
1
6
,
17]
10
SC
√
√
[
1
8
]
11
Z
JU
√
√
[
1
9
,
20]
12
A
V
O
Z
ES
√
√
[
1
5
]
13
D
a
F
EX
√
[
2
1
]
14
V
i
d
TI
M
I
T
√
[
1
5
]
3.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
s
ig
n
i
f
ica
n
t
k
e
y
w
o
r
d
i
n
th
e
s
ea
r
ch
d
o
m
ai
n
o
f
t
h
is
p
ap
er
is
“Fac
e”
,
t
h
u
s
p
r
ec
l
u
d
es
a
n
y
n
o
n
-
f
ac
e
liv
e
n
ess
d
etec
tio
n
li
k
e
f
i
n
g
er
p
r
in
t,
p
al
m
p
r
in
t,
ir
is
,
etc.
W
e
also
li
m
i
ted
th
e
s
ea
r
ch
t
h
e
s
ea
r
ch
s
co
p
e
to
E
n
g
li
s
h
liter
atu
r
e
o
n
l
y
.
3
.
1
.
Study
s
elec
t
io
n pro
ce
du
re
Fo
u
r
d
atab
ases
w
er
e
s
elec
ted
to
p
er
f
o
r
m
th
e
s
ea
r
c
h
o
f
r
eq
u
ir
ed
ar
ticles:
th
e
I
E
E
E
Xp
lo
r
e
tech
n
ic
a
l
liter
atu
r
e
lib
r
ar
y
i
n
e
n
g
i
n
ee
r
i
n
g
a
n
d
tec
h
n
o
lo
g
y
;
th
e
(
W
o
S)
w
eb
o
f
s
cie
n
ce
s
er
v
ice;
t
h
e
Scie
n
ce
Dir
ec
t
d
atab
ase
an
d
Sco
p
u
s
d
atab
ase.
T
o
c
o
v
er
all
r
elate
d
liter
atu
r
e
an
d
o
f
f
er
a
w
id
er
v
ie
w
o
f
r
esear
ch
er
‟
s
ef
f
o
r
ts
r
eg
ar
d
in
g
th
i
s
ar
ea
.
St
u
d
y
s
el
ec
tio
n
p
r
o
ce
d
u
r
e
in
cl
u
d
ed
s
ea
r
ch
in
g
t
h
e
s
o
u
r
ce
s
o
f
t
h
e
liter
atu
r
e,
f
o
llo
w
ed
b
y
2
s
tep
s
o
f
s
cr
ee
n
i
n
g
an
d
f
ilte
r
in
g
r
es
u
lted
ar
ticles,
i
n
t
h
e
f
ir
s
t
s
tep
d
u
p
licated
an
d
ir
r
ele
v
an
t
ar
tic
les
w
er
e
ex
clu
d
ed
b
y
ti
tle
an
d
ab
s
tr
ac
t
s
ca
n
n
i
n
g
.
W
h
ile
a
f
u
ll
-
te
x
t
r
e
ad
in
g
r
es
u
lted
i
n
f
ilter
in
g
t
h
e
s
ca
n
n
ed
ar
ticles
as
a
s
ec
o
n
d
s
tep
.
B
o
th
s
tep
s
w
er
e
ap
p
lied
b
ased
o
n
ch
o
s
en
eli
g
i
b
ilit
y
cr
iter
ia
w
h
ich
i
s
f
o
llo
w
e
d
b
y
t
h
e
au
t
h
o
r
s
.
3
.
2
.
Sea
rc
h
T
h
e
s
ea
r
ch
w
a
s
d
o
n
e
i
n
t
h
e
a
f
o
r
e
m
en
tio
n
ed
d
atab
ases
,
u
s
i
n
g
a
ca
r
ef
u
ll
y
s
elec
ted
k
e
y
w
o
r
d
in
cl
u
d
in
g
“f
ac
e
r
ec
o
g
n
itio
n
”
w
it
h
t
h
e
“A
N
D”
o
p
er
ato
r
an
d
“
li
v
e
n
es
s
d
etec
tio
n
”
w
it
h
d
i
f
f
er
e
n
t
s
y
n
o
n
y
m
s
a
s
s
h
o
w
n
i
n
th
e
q
u
er
y
tex
t
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
2
.
W
e
f
u
r
t
h
er
ap
p
lied
r
ef
i
n
e
m
e
n
t
s
in
ea
c
h
s
ea
r
c
h
en
g
i
n
e
to
eli
m
in
ate
a
n
y
t
y
p
e
r
ath
er
th
a
n
j
o
u
r
n
al
a
n
d
co
n
f
er
en
ce
ar
ticle
s
to
en
s
u
r
e
in
cl
u
d
in
g
ap
p
r
o
p
r
iate
s
cien
tif
ic
w
o
r
k
s
r
elate
d
to
o
u
r
s
u
r
v
e
y
.
Fig
u
r
e
2
.
Sear
ch
q
u
er
y
3
.
3
.
I
nclu
s
io
n c
rit
er
io
n
An
elig
ib
le
cr
iter
io
n
w
a
s
s
p
ec
if
ied
in
P
R
I
SM
A
Flo
w
Dia
g
r
a
m
a
s
s
h
o
w
n
i
n
F
ig
u
r
e
3
to
d
ec
id
e
w
h
ic
h
ar
ticle
to
b
e
in
clu
d
ed
an
d
th
u
s
,
m
ap
p
i
n
g
t
h
e
d
o
m
ai
n
o
f
r
esear
ch
[
2
2
]
.
T
h
is
w
as
d
o
n
e
af
ter
r
e
m
o
v
al
o
f
du
p
licates
an
d
ir
r
elev
a
n
t
ar
ti
cles
in
t
h
e
ea
r
lier
s
tep
s
s
cr
ee
n
in
g
a
n
d
f
ilter
i
n
g
.
E
lig
ib
ilit
y
o
f
th
e
ar
ticle
w
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
6
5
-
5
1
7
5
5168
d
ec
id
ed
b
y
s
p
ec
i
f
ic
a
s
p
ec
ts
s
u
ch
as E
n
g
lis
h
ar
ticle
s
o
n
l
y
w
er
e
co
n
s
id
er
ed
an
d
tar
g
e
ted
to
p
ic
w
a
s
co
n
ce
r
n
ed
i
n
f
ac
e
r
ec
o
g
n
i
tio
n
r
at
h
er
th
a
n
an
y
o
th
er
b
io
m
etr
ic
f
ield
s
u
c
h
as
ir
is
,
f
i
n
g
er
p
r
in
t o
r
p
al
m
p
r
in
t
etc.
Fig
u
r
e
3
.
P
R
I
SMA
f
lo
w
d
iag
r
a
m
4.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
4
.
1
.
Sea
rc
h
re
s
ults
T
h
e
in
itial
s
ea
r
ch
r
es
u
lt
s
w
er
e
(
1
2
0
)
a
r
ticles:
(
3
)
f
r
o
m
Scie
n
c
eDir
ec
t,
(
3
4
)
r
esu
lts
o
f
I
E
E
E
Xp
lo
r
e,
4
2
f
r
o
m
Sco
p
u
s
a
n
d
4
1
ar
ticles
ar
e
f
r
o
m
W
o
S,
in
c
lu
d
i
n
g
t
h
e
p
er
io
d
2
0
1
2
to
2
0
1
7
.
T
h
er
e
w
er
e
3
9
ar
ticles
d
u
p
licates
a
m
o
n
g
t
h
e
f
o
u
r
d
atab
ases
.
T
itles
an
d
ab
s
t
r
ac
ts
s
ca
n
n
i
n
g
w
a
s
ap
p
lied
,
1
0
w
e
r
e
ex
clu
d
ed
w
h
ic
h
r
esu
lt
s
in
7
1
p
ap
er
s
.
Nex
t,
a
f
u
ll
tex
t
r
ea
d
in
g
is
p
er
f
o
r
m
ed
th
at
in
cl
u
d
ed
(
6
5
)
ar
ticles
as
a
f
in
al
s
et.
T
h
ese
p
ap
er
s
w
er
e
ca
r
ef
u
l
l
y
r
ea
d
to
s
p
ec
if
y
t
h
e
R
esear
ch
ar
ea
t
h
e
y
b
elo
n
g
to
in
t
h
i
s
to
p
ic.
(
4
)
Of
t
h
e
m
w
er
e
r
ev
ie
w
ar
ticles
t
h
at
r
e
f
er
r
ed
to
ex
i
s
ti
n
g
m
et
h
o
d
s
o
r
p
r
o
v
id
ed
a
g
en
er
a
l
o
v
er
v
ie
w
ab
o
u
t
t
h
e
estab
li
s
h
ed
tech
n
iq
u
es.
T
h
e
o
th
er
b
r
an
ch
o
f
t
h
i
s
la
y
er
o
f
class
i
f
icatio
n
w
a
s
ap
p
lied
b
as
ed
o
n
li
v
en
e
s
s
in
d
icato
r
s
ex
i
s
t
r
esu
l
tin
g
in
6
1
ar
ticles.
L
i
v
en
ess
i
n
d
icato
r
s
la
y
er
w
a
s
f
u
r
th
er
d
i
v
id
ed
in
to
s
u
b
ca
teg
o
r
ies b
ased
o
n
tech
n
iq
u
e
s
u
s
ed
in
ea
ch
i
n
d
icato
r
.
a.
R
ev
ie
w
a
n
d
s
u
r
v
e
y
ar
ticles
:
T
h
e
liter
at
u
r
e
o
n
f
ac
e
li
v
en
e
s
s
d
etec
tio
n
r
ev
ea
led
4
r
ev
ie
w
a
r
ticles
in
ea
r
lie
r
s
p
ec
if
ied
p
er
io
d
o
f
last
f
i
v
e
y
ea
r
s
.
T
h
ese
r
e
v
ie
w
s
m
ai
n
l
y
in
v
es
tig
a
ted
liter
atu
r
e
in
ter
m
s
o
f
s
tate
-
of
-
ar
t
tech
n
iq
u
es
i
n
li
v
e
n
ess
d
etec
tio
n
.
Olg
a
e
t
a
l.
(
2
0
1
2
)
p
r
esen
ted
an
o
v
er
v
ie
w
o
n
2
D
f
ac
e
li
v
e
n
es
s
d
etec
tio
n
th
a
t
ca
teg
o
r
ized
t
h
e
liter
atu
r
e
b
ased
o
n
liv
e
s
i
g
n
clu
es
w
it
h
a
d
etailed
d
is
c
u
s
s
i
o
n
o
n
d
i
f
f
er
e
n
t
s
p
o
o
f
in
g
attac
k
s
t
h
at
h
i
g
h
l
ig
h
ted
th
eir
r
elatio
n
to
t
h
e
d
ev
elo
p
ed
s
o
lu
tio
n
s
.
I
n
h
er
w
o
r
k
Ol
g
a
et
a
l
.
(
2
0
1
2
)
also
s
h
ed
s
o
m
e
l
ig
h
t
o
n
p
u
b
licl
y
a
v
ailab
le
d
atase
ts
an
d
m
ad
e
a
clea
r
p
at
h
f
o
r
s
tu
d
y
f
u
t
u
r
e
d
ir
ec
tio
n
s
[
2
3
]
.
Si
m
ilar
l
y
,
Saj
id
a
et
a
l
.
(
2
0
1
5
)
class
if
ied
h
e
r
r
ev
ie
w
o
n
f
ac
e
a
n
ti
-
s
p
o
o
f
i
n
g
m
eth
o
d
s
i
n
to
in
tr
u
s
i
v
e
a
n
d
n
o
n
-
in
tr
u
s
i
v
e
ap
p
r
o
ac
h
es
an
d
p
r
o
v
id
ed
a
cr
itic
al
r
ev
ie
w
o
n
l
iter
atu
r
e
f
o
r
t
h
e
ar
ch
itect
u
r
e
o
f
liv
e
n
ess
d
etec
tio
n
s
y
s
te
m
an
d
its
i
m
p
le
m
e
n
tatio
n
s
[
2
]
.
T
h
e
s
tu
d
y
b
y
Galb
all
y
et
a
l.
(
2
0
1
5
)
o
f
f
er
s
p
r
o
b
ab
l
y
th
e
m
o
s
t
co
m
p
r
eh
e
n
s
i
v
e
a
n
al
y
s
i
s
o
f
liter
at
u
r
e
o
f
f
a
ce
an
ti
-
s
p
o
o
f
i
n
g
d
u
r
i
n
g
th
e
p
ast
d
ec
ad
e.
A
C
h
r
o
n
o
lo
g
ical
ev
o
l
u
tio
n
o
f
b
io
m
etr
ic
an
ti
-
s
p
o
o
f
i
n
g
w
a
s
r
ep
r
esen
ted
an
d
th
eo
r
ies,
m
et
h
o
d
o
lo
g
ies,
d
atab
ase
ev
alu
atio
n
an
d
s
tate
-
of
-
ar
t
tech
n
iq
u
es
w
er
e
co
v
er
e
d
f
o
r
th
e
p
er
io
d
(
1
9
0
3
-
2
0
1
4
)
[
2
4
]
.
On
e
y
ea
r
later
B
an
g
g
a
a
n
d
Si
n
g
h
i
n
tr
o
d
u
ce
d
a
r
ev
ie
w
o
n
s
p
o
o
f
i
n
g
d
etec
tio
n
i
n
f
ac
e
r
ec
o
g
n
it
io
n
co
n
s
id
er
in
g
f
ac
ia
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
t o
n
f
a
ce
liven
ess
d
etec
tio
n
:
a
s
ystema
tic
liter
a
tu
r
e
r
ev
iew
(
E
n
a
s
A
.
R
a
h
ee
m
)
5169
m
o
tio
n
d
ed
u
ct
io
n
a
n
d
f
ac
ia
l
tex
t
u
r
e
an
a
l
y
s
is
i
n
t
h
eir
class
i
f
icatio
n
o
f
tec
h
n
iq
u
e
s
[
2
5
]
.
Sp
o
o
f
in
g
m
ec
h
a
n
i
s
m
s
f
o
r
f
ac
ial
b
io
m
e
tr
ics
w
er
e
d
is
c
u
s
s
ed
an
d
a
lg
o
r
it
h
m
s
a
n
d
f
ea
tu
r
e
s
f
o
r
v
ar
io
u
s
s
p
o
o
f
in
g
attac
k
s
w
er
e
also
b
r
o
ad
ly
r
e
v
ie
w
ed
.
F
ig
u
r
e
4
s
h
o
w
s
a
tax
o
n
o
m
y
o
f
r
esear
ch
liter
at
u
r
e
o
n
f
ac
e
li
v
e
n
ess
d
etec
tio
n
.
Fig
u
r
e
4
.
A
ta
x
o
n
o
m
y
o
f
r
esea
r
ch
liter
atu
r
e
o
n
f
ac
e
li
v
en
e
s
s
d
etec
tio
n
b.
Face
liv
e
n
es
s
in
d
icato
r
s
:
T
h
e
ex
is
ti
n
g
liter
atu
r
e
o
n
li
v
e
n
e
s
s
d
etec
tio
n
f
o
c
u
s
e
s
p
ar
ticu
la
r
l
y
o
n
liv
e
n
es
s
in
d
icato
r
s
as
a
clu
e
th
at
h
elp
s
to
f
in
d
th
e
ap
p
r
o
p
r
iate
s
o
lu
tio
n
f
o
r
d
if
f
er
e
n
t
s
p
o
o
f
in
g
p
r
o
b
le
m
s
.
B
ased
o
n
th
e
li
v
en
e
s
s
i
n
d
icato
r
u
s
ed
,
ap
p
r
o
ac
h
es o
f
d
etec
tio
n
ar
e
s
ep
ar
ated
in
to
f
iv
e
ca
te
g
o
r
ies as
f
o
llo
w
s
:
4
.
1
.
1
.
T
ex
t
ure
a
na
ly
s
is
B
ased
o
n
th
e
ass
u
m
p
tio
n
t
h
at
f
ak
e
f
ac
e
p
r
o
d
u
ce
s
a
d
if
f
er
en
t
tex
t
u
r
e
p
atter
n
th
at
d
o
es
n
o
t
ex
is
t
i
n
r
ea
l
f
ac
e,
tex
t
u
r
e
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
t
h
e
f
ac
e
i
m
a
g
e
o
r
s
eq
u
en
ce
o
f
i
m
a
g
es
to
p
r
o
v
id
e
d
etec
tab
le
in
f
o
r
m
atio
n
th
a
t
h
e
lp
to
d
is
ti
n
g
u
i
s
h
r
ea
l
f
r
o
m
f
a
k
e
id
e
n
titi
es.
I
n
t
h
is
r
e
v
ie
w
,
te
x
t
u
r
e
-
b
a
s
ed
ap
p
r
o
ac
h
es
ar
e
g
en
er
all
y
d
i
v
id
ed
in
to
t
h
r
ee
g
r
o
u
p
s
b
ased
o
n
d
etec
tio
n
te
ch
n
iq
u
e
u
s
ed
:
i
m
a
g
e
q
u
al
it
y
ass
es
s
m
en
t
(
I
QA
)
,
d
y
n
a
m
ic,
a
n
d
s
tat
ic.
I
m
a
g
e
q
u
alit
y
a
s
s
es
s
m
e
n
t
t
h
eo
r
y
i
n
li
v
en
e
s
s
d
etec
t
io
n
i
m
p
lie
s
t
h
at
th
er
e
i
s
a
q
u
alit
y
d
if
f
er
e
n
ce
b
et
w
ee
n
f
ak
e
a
n
d
r
ea
l
i
m
a
g
es
t
h
at
ca
n
b
e
d
etec
te
d
u
s
in
g
i
m
a
g
e
q
u
alit
y
m
ea
s
u
r
es
w
h
ic
h
allo
w
s
to
b
u
ild
a
p
r
o
tectio
n
m
et
h
o
d
ag
a
in
s
t
s
p
o
o
f
in
g
attac
k
s
.
R
esear
c
h
er
s
e
x
p
lo
ited
th
is
a
s
s
u
m
p
t
io
n
to
d
ev
elo
p
v
ar
io
u
s
I
QA
tec
h
n
iq
u
e
s
in
[5
,
26
-
33
]
.
An
e
v
alu
a
tio
n
o
f
s
e
v
er
al
I
Q
A
tech
n
iq
u
es
w
as
d
o
n
e
i
n
[
3
4
]
.
Sev
er
al
s
t
u
d
ies
h
av
e
test
ed
th
e
ef
f
icac
y
o
f
d
y
n
a
m
ic
tex
tu
r
e
an
al
y
s
i
s
in
li
v
en
e
s
s
d
etec
tio
n
i
n
[
3
5
-
43]
.
Static
te
x
t
u
r
e
a
n
al
y
s
is
o
n
t
h
e
o
th
er
h
a
n
d
h
a
v
e
b
ee
n
e
x
p
lo
r
ed
th
r
o
u
g
h
lar
g
e
n
u
m
b
er
o
f
p
u
b
lis
h
ed
s
t
u
d
ies
in
o
u
r
r
esear
c
h
p
er
io
d
in
[4
,
4
4
-
58]
.
4
.
1
.
2
.
M
o
t
io
n
a
na
ly
s
is
T
h
r
ee
ty
p
es
o
f
tech
n
iq
u
e
s
w
er
e
s
u
r
v
e
y
ed
w
it
h
i
n
m
o
tio
n
an
al
y
s
i
s
w
h
ich
a
s
s
u
m
es
t
h
at
a
p
lan
ar
o
b
j
ec
t
m
o
v
e
s
i
n
a
d
if
f
er
e
n
t
w
a
y
o
t
h
er
th
a
n
a
r
ea
l
f
ac
e.
T
h
e
m
et
h
o
d
en
co
m
p
a
s
s
e
s
t
h
e
ca
lc
u
lat
io
n
o
f
i
n
f
o
r
m
atio
n
r
eg
ar
d
in
g
th
e
m
o
v
in
g
p
o
in
ts
o
f
an
i
m
a
g
e
i
n
t
h
e
s
ce
n
e.
T
h
ese
t
y
p
es
ar
e
:
Fo
cu
s
d
is
ta
n
ce
b
ased
[
5
9
,
1
6
]
,
Op
tical
f
lo
w
b
ased
[
6
0
-
63]
an
d
Scen
ic
clu
e
s
b
ased
m
o
tio
n
a
n
al
y
s
i
s
[
6
4
-
67]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
6
5
-
5
1
7
5
5170
4
.
1
.
3
.
L
if
e
s
ig
n ind
ica
t
o
rs
T
h
e
m
o
v
e
m
en
t
o
f
a
ce
r
tai
n
p
ar
t
in
t
h
e
f
ac
e
s
u
c
h
a
s
a
lip
m
o
v
e
m
en
t
o
r
e
y
e
b
li
n
k
in
g
ca
n
b
e
an
in
d
icato
r
o
f
li
v
e
n
es
s
,
e
y
e
s
tate
an
d
m
o
u
th
s
tate
ar
e
t
w
o
m
ai
n
s
i
g
n
s
to
b
e
tak
e
n
in
to
co
n
s
id
er
atio
n
i
n
li
f
e
s
ig
n
d
etec
tio
n
al
g
o
r
it
h
m
s
w
h
i
ch
w
er
e
estab
li
s
h
ed
i
n
[
6
8
-
72]
r
esp
ec
tiv
el
y
.
A
u
til
izatio
n
o
f
b
o
th
i
n
d
icato
r
s
to
b
u
ild
a
r
o
b
u
s
t liv
e
n
es
s
d
etec
ti
o
n
s
y
s
te
m
w
as a
l
s
o
p
r
o
p
o
s
ed
b
y
A
.
Sin
g
h
et
a
l
.
(
2
0
1
4
)
in
[
7
3
]
.
4
.
1
.
4
.
3
D
pro
pert
ies
Fe
w
s
t
u
d
ies
f
o
c
u
s
ed
o
n
t
h
is
t
y
p
e
o
f
m
e
th
o
d
w
h
er
e
d
etec
t
io
n
tech
n
iq
u
e
s
ar
e
p
r
o
p
o
s
ed
to
an
al
y
z
e
th
e
3
D
f
ac
ial
s
tr
u
ct
u
r
e
to
d
is
ti
n
g
u
i
s
h
r
ea
l
f
r
o
m
f
a
k
e
s
a
m
p
les
in
liv
e
n
e
s
s
d
etec
tio
n
s
y
s
te
m
[
7
4
-
77]
.
4
.
1
.
5
.
O
t
her
liv
eness
ind
ica
t
o
rs
T
h
e
liter
atu
r
e
o
n
l
iv
e
n
es
s
d
et
ec
tio
n
h
a
s
h
i
g
h
l
ig
h
ted
s
e
v
er
al
o
th
er
s
t
u
d
ies
w
i
th
a
co
m
b
i
n
a
tio
n
r
ath
er
th
an
o
n
e
liv
e
n
e
s
s
i
n
d
icato
r
.
T
h
ese
s
tu
d
ies
w
er
e
i
n
cl
u
d
ed
in
o
u
r
s
ea
r
ch
p
er
io
d
ar
e
[
7
8
-
83]
.
4
.
2
.
Da
t
a
a
na
l
y
s
is
T
h
e
in
itial
o
b
j
ec
tiv
e
o
f
t
h
e
p
ap
er
is
to
u
p
d
ate
th
e
s
tate
-
of
-
ar
t
o
f
l
iv
e
n
es
s
d
etec
tio
n
tec
h
n
iq
u
es.
T
h
e
p
u
r
p
o
s
e
is
to
h
ig
h
li
g
h
t
r
ec
en
t
tr
en
d
s
o
n
t
h
i
s
to
p
ic
r
esear
ch
.
T
h
e
d
if
f
er
en
ce
o
f
t
h
is
r
ev
ie
w
f
r
o
m
m
a
n
y
p
r
ev
io
u
s
w
o
r
k
s
is
t
h
at
it
f
o
c
u
s
es
o
n
th
e
liter
atu
r
e
o
f
tech
n
iq
u
es
r
ath
er
th
a
n
tech
n
iq
u
es
th
e
m
s
el
v
es.
Mo
r
eo
v
er
it
p
r
o
p
o
s
es
a
tax
o
n
o
m
y
o
f
th
e
r
elate
d
liter
atu
r
e.
Ma
p
p
in
g
th
e
liter
atu
r
e
in
to
a
tax
o
n
o
m
y
i
n
a
r
esear
ch
ar
ea
ca
n
p
r
o
v
id
e
s
ev
er
al
b
e
n
e
f
its
.
On
e
o
f
w
h
ic
h
is
th
at
it
o
r
g
an
i
ze
s
t
h
e
m
as
s
o
f
p
u
b
lica
tio
n
s
i
n
t
h
e
liter
atu
r
e.
Fo
r
in
s
tan
ce
,
a
n
e
w
r
esear
ch
e
r
in
t
h
e
f
ield
o
f
f
ac
ial
b
io
m
etr
ic
d
etec
tio
n
m
a
y
b
e
o
v
er
w
h
el
m
ed
w
it
h
t
h
e
h
u
g
e
n
u
m
b
er
o
f
p
ap
er
s
in
th
is
p
ar
ti
cu
lar
f
ield
w
it
h
o
u
t
a
n
y
s
o
r
t
o
f
s
tr
u
ct
u
r
e
a
n
d
m
a
y
f
ai
l
to
h
a
v
e
clea
r
id
ea
ab
o
u
t
th
e
ex
i
s
te
n
t
ac
ti
v
ities
o
f
th
e
ar
ea
.
T
ax
o
n
o
m
izi
n
g
th
e
liter
at
u
r
e
ca
n
h
elp
s
o
r
tin
g
o
u
t
t
h
e
d
if
f
er
en
t
ac
tiv
i
ties
i
n
to
m
ea
n
in
g
f
u
l
la
y
o
u
t.
Fu
r
t
h
er
m
o
r
e,
a
tax
o
n
o
m
y
m
ap
p
in
g
t
h
e
w
o
r
k
o
n
l
iv
e
n
es
s
d
etec
tio
n
i
n
t
o
ce
r
tain
ca
te
g
o
r
ies
ca
n
h
e
lp
to
u
n
d
er
lin
e
t
h
e
w
ea
k
n
e
s
s
e
s
an
d
s
tr
en
g
t
h
s
i
n
a
r
es
ea
r
ch
co
v
er
ag
e.
T
h
is
i
s
d
o
n
e
b
y
in
d
icati
n
g
s
e
v
er
al
p
ath
s
t
h
at
t
h
e
r
esear
c
h
er
m
a
y
g
o
th
r
o
u
g
h
to
f
in
d
t
h
e
g
ap
s
in
a
b
r
an
c
h
o
f
t
h
e
s
u
b
j
ec
t.
A
d
ata
an
al
y
s
is
o
f
th
e
l
iter
atu
r
e
is
p
r
o
b
ab
ly
in
ter
esti
n
g
to
p
r
o
v
id
e
r
esear
c
h
er
s
w
it
h
p
r
o
p
o
r
tio
n
s
o
f
t
h
e
p
u
b
li
ca
tio
n
s
in
d
if
f
er
e
n
t
asp
ec
ts
.
Fi
g
u
r
e
5
p
r
esen
ts
t
h
e
r
esu
lt
s
b
y
n
u
m
b
er
o
f
ar
ticle
s
i
n
ea
ch
o
f
t
h
e
e
x
p
lo
r
ed
d
atab
as
es
b
ef
o
r
e
an
d
a
f
ter
ap
p
ly
i
n
g
o
u
r
eli
g
ib
ili
t
y
cr
iter
i
a.
T
h
e
f
in
al
r
es
u
lts
w
er
e
m
o
s
t
l
y
f
o
u
n
d
in
W
OS
w
h
ile
Sco
p
u
s
a
n
d
I
E
E
E
Xp
lo
r
e
m
a
y
b
e
eq
u
i
v
ale
n
t
to
its
r
esu
l
ts
,
an
d
s
cie
n
ce
d
ir
ec
t
s
h
o
w
s
t
h
e
lea
s
t
p
r
o
p
o
r
tio
n
r
eg
ar
d
in
g
o
u
r
to
p
ic.
T
h
is
m
a
y
b
e
b
en
ef
icial
to
t
h
o
s
e
w
h
o
d
o
n
‟
t
h
a
v
e
ac
ce
s
s
to
all
d
atab
ase
s
o
u
r
ce
th
e
y
ca
n
u
s
e
o
th
er
e
n
g
in
e
s
to
g
et
a
clo
s
e
en
o
u
g
h
s
ea
r
ch
r
es
u
lts
.
An
o
th
er
an
a
l
y
s
is
o
f
d
ata
w
as
d
o
n
e
o
n
th
e
n
u
m
b
er
o
f
ar
ticle
s
in
v
ar
io
u
s
ca
teg
o
r
ies
b
y
t
h
ei
r
y
ea
r
o
f
p
u
b
licatio
n
d
u
r
i
n
g
th
e
p
er
io
d
(
2
0
1
2
-
2
0
1
7
)
is
s
h
o
w
n
i
n
F
i
g
u
r
e
6
.
I
t
r
ev
ea
ls
th
at
t
h
er
e
is
a
n
o
ticea
b
le
in
cr
e
m
e
n
t
in
n
u
m
b
er
o
f
p
u
b
li
s
h
ed
w
o
r
k
s
b
et
w
ee
n
2
0
1
2
an
d
2
0
1
6
in
t
h
is
ar
ea
.
An
d
h
i
s
m
o
s
t
s
i
g
n
if
ic
an
t
cla
s
s
o
f
i
n
ter
es
t
is
th
e
te
x
t
u
r
e
an
al
y
s
i
s
an
d
t
h
e
least a
r
e
s
h
o
w
n
to
b
e
th
e
r
ev
ie
w
p
ap
er
s
an
d
3
D
p
r
o
p
er
ties
.
Fig
u
r
e5
.
Nu
m
b
er
o
f
i
n
cl
u
d
ed
ar
ticles b
y
m
a
in
d
atab
ase
s
o
u
r
ce
Fig
u
r
e
6
.
Nu
m
b
er
o
f
i
n
cl
u
d
ed
ar
ticles in
v
ar
io
u
s
ca
teg
o
r
ies b
y
p
u
b
licatio
n
y
ea
r
I
t
is
clea
r
l
y
s
h
o
w
n
t
h
at
te
x
t
u
r
e
an
al
y
s
i
s
tech
n
iq
u
es
o
cc
u
p
y
m
o
s
t
o
f
t
h
e
p
u
b
licatio
n
ar
ea
.
St
atic,
I
QA
,
an
d
d
y
n
a
m
ic
tech
n
iq
u
e
s
r
esp
ec
tiv
el
y
s
h
o
w
s
t
h
e
h
i
g
h
e
s
t
s
c
o
r
es
a
m
o
n
g
o
th
er
tec
h
n
iq
u
es.
An
e
v
alu
a
tio
n
o
f
s
y
s
te
m
s
p
er
f
o
r
m
a
n
ce
f
o
r
liv
en
es
s
d
etec
tio
n
ap
p
r
o
ac
h
es
th
at
p
r
esen
ted
p
r
o
m
is
i
n
g
ac
cu
r
ac
ies
is
b
r
ief
l
y
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
t o
n
f
a
ce
liven
ess
d
etec
tio
n
:
a
s
ystema
tic
liter
a
tu
r
e
r
ev
iew
(
E
n
a
s
A
.
R
a
h
ee
m
)
5171
d
escr
ib
ed
in
T
ab
le
2
in
ter
m
s
o
f
ac
cu
r
ac
y
,
h
al
f
to
tal
er
r
o
r
r
ate
(
HT
E
R
)
,
ar
ea
u
n
d
er
R
OC
c
u
r
v
e
(
A
U
C
)
,
eq
u
a
l
er
r
o
r
r
ate
(
E
E
R
)
,
an
d
tim
e
w
h
er
e
ca
lcu
lated
.
T
ab
le
2
.
E
v
alu
atio
n
o
f
p
er
f
o
r
m
an
ce
C
a
t
e
g
o
r
y
R
e
f
e
r
e
n
c
e
A
c
c
u
r
a
c
y
H
T
ER
EER
A
U
C
T
i
me
T
e
x
t
u
r
e
A
n
a
l
y
si
s
[
3
2
]
-
0
.
0
5
.
8
3
-
-
[
2
6
]
-
4
.
7
8
6
.
2
3
-
-
[
5
]
-
1
5
.
2
-
-
[
2
7
]
-
1
5
.
2
,
3
2
.
4
-
-
-
[
3
0
]
-
0
.
5
-
-
0
.
5
7
3
se
c
[
2
9
]
-
1
.
6
5
-
-
-
[
3
6
]
0
.
8
4
,
0
.
8
1
,
0
.
8
3
-
[
3
7
]
-
1
5
.
1
6
,
8
.
5
1
,
7
.
6
0
1
7
,
1
6
,
10
-
-
[
3
8
]
-
3
.
7
5
,
1
.
3
8
,
1
.
0
3
0
.
2
,
1
,
8
-
-
[
3
9
]
8
0
.
9
5
%
,
9
0
.
4
8
-
-
-
-
[
4
3
]
0
.
9
7
2
0
-
-
-
-
[
4
5
]
-
0,
0
.
2
9
6
.
7
,
2
.
9
-
-
[
4
]
-
1
5
.
1
6
,
1
7
.
1
7
,
3
4
.
0
1
-
-
-
[
4
6
]
-
1
0
%
-
-
-
[
4
7
]
9
3
.
0
6
,
9
3
.
1
3
,
9
3
.
1
6
6
.
9
4
,
6
.
8
7
,
6
.
8
4
-
-
-
[
4
8
]
-
-
1
3
.
3
,
1
2
.
9
,
8
.
5
8
,
5
.
8
2
-
-
[
5
3
]
-
2
.
7
,
4
.
6
,
9
.
5
-
-
-
[
5
7
]
-
1
6
.
2
1
,
1
2
.
3
0
3
4
,
1
5
.
4
5
-
-
-
M
o
t
i
o
n
A
n
a
l
y
si
s
[
5
9
]
9
7
.
5
%
-
-
-
[
1
6
]
-
-
9
.
5
7
,
3
.
4
7
,
0
.
0
0
-
-
[
6
0
]
-
2
2
.
8
1
,
1
3
.
3
3
-
-
-
[
6
1
]
-
4
.
3
8
,
1
.
2
5
-
-
-
[
6
3
]
-
-
9
.
6
,
1
2
.
5
-
-
[
6
2
]
-
1
.
5
2
-
-
-
[
6
4
]
-
-
6
.
8
-
-
[
6
5
]
1
0
0
%
-
-
-
-
[
6
6
]
8
5
%,
9
4
.
5
%,
9
2
.
9
%
-
-
-
-
[
6
7
]
-
5
.
1
%
-
-
-
L
i
f
e
S
i
g
n
I
n
d
i
c
a
t
o
r
s
[
6
8
]
8
9
.
7
%,
9
8
%,
9
4
.
8
%
-
-
-
-
[
6
9
]
9
9
.
4
%,
9
6
.
7
7
%
-
-
-
-
[
7
1
]
9
9
%
-
-
-
-
[
8
4
]
9
0
.
5
%,
8
4
.
4
%
-
-
-
-
3
D
P
r
o
p
e
r
t
i
e
s
[
7
5
]
-
-
1
0
%
-
-
[
7
6
]
1
0
0
%
-
-
-
-
O
t
h
e
r
L
i
v
e
n
e
ss
I
n
d
i
c
a
t
o
r
s
[
63
]
-
2
.
7
5
3
.
3
,
0
.
0
-
-
[
7
9
]
-
1
2
.
5
,
1
3
.
7
2
-
-
3
4
m
se
c
[
8
0
]
-
5
0
,
3
4
.
3
8
-
-
-
5.
CO
NCLU
SI
O
N
I
n
th
i
s
i
n
v
e
s
ti
g
atio
n
,
t
h
e
ai
m
w
a
s
to
h
a
v
e
an
i
n
s
ig
h
t
o
f
f
ac
e
liv
e
n
ess
d
etec
t
io
n
t
h
r
o
u
g
h
u
p
d
atin
g
a
n
d
tax
o
n
o
m
izi
n
g
t
h
e
liter
at
u
r
e.
An
o
th
er
i
m
p
o
r
ta
n
t
t
h
in
g
i
s
th
at
th
e
n
e
w
r
e
s
ea
r
ch
er
s
i
n
t
h
is
f
ie
ld
ca
n
h
a
v
e
a
clea
r
id
ea
ab
o
u
t
w
h
a
t
f
ac
e
li
v
en
e
s
s
d
etec
tio
n
is
an
d
w
h
at
ar
e
th
e
o
p
p
o
r
tu
n
itie
s
to
d
ev
elo
p
n
e
w
m
et
h
o
d
s
,
ad
o
p
t
n
e
w
tech
n
o
lo
g
ies
an
d
g
o
t
h
r
o
u
g
h
s
p
ec
if
ic
d
ir
ec
tio
n
a
n
d
e
x
p
lo
r
e
its
r
esear
c
h
g
ap
s
w
i
th
o
u
t
th
e
n
ee
d
to
w
a
s
te
th
e
ti
m
e
o
n
i
n
v
e
s
ti
g
ati
n
g
ir
r
elev
an
t
w
o
r
k
s
.
W
e
h
a
v
e
f
o
u
n
d
t
h
at
g
en
er
all
y
t
h
e
l
iv
e
n
es
s
i
n
d
i
ca
to
r
s
ar
e
th
e
m
o
s
t
s
u
itab
le
to
o
l
o
f
th
eo
r
y
to
cla
s
s
if
y
th
e
liter
at
u
r
e
s
ea
r
c
h
r
es
u
lts
.
Mo
r
eo
v
er
,
a
w
id
el
y
en
o
u
g
h
r
ea
d
in
g
to
h
a
v
e
k
n
o
w
led
g
e
ab
o
u
t
th
e
to
p
ic
w
o
u
ld
b
e
ea
s
ier
to
g
ain
f
r
o
m
r
ev
ie
w
p
ap
er
s
r
ath
er
th
an
f
r
o
m
b
o
o
k
s
s
p
ec
iall
y
i
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
6
5
-
5
1
7
5
5172
ter
m
s
o
f
id
en
tify
i
n
g
all
th
e
r
elate
d
s
y
n
o
n
y
m
s
o
f
th
e
s
ea
r
c
h
q
u
er
y
k
e
y
w
o
r
d
s
to
b
e
ab
le
t
o
co
v
er
m
o
s
tl
y
all
th
e
r
elate
d
w
o
r
k
.
T
h
e
o
u
tco
m
e
o
f
r
esear
ch
e
f
f
o
r
t
o
n
li
v
e
n
es
s
d
etec
tio
n
ap
p
ea
r
s
to
h
av
e
a
s
ig
n
if
ican
t
p
r
o
g
r
es
s
,
Ho
w
e
v
er
,
it
r
e
m
ai
n
s
a
ch
all
en
g
e
f
o
r
th
e
f
ac
ial
r
ec
o
g
n
it
i
o
n
s
y
s
te
m
s
.
T
h
er
ef
o
r
e,
w
e
r
ec
o
m
m
e
n
d
f
u
t
u
r
e
r
esear
ch
er
s
to
f
o
cu
s
o
n
d
ir
ec
t
io
n
s
t
h
at
h
a
v
e
n
o
t
b
ee
n
es
tab
lis
h
ed
b
e
f
o
r
e
an
d
tr
y
to
b
r
id
g
e
th
e
g
ap
i
n
th
o
s
e
p
ath
s
.
I
n
g
e
n
er
al,
it
s
ee
m
s
t
h
at
a
g
r
ee
n
ar
ea
o
f
t
h
e
r
esear
ch
is
th
e
o
n
e
w
i
th
f
e
w
p
u
b
licatio
n
s
an
d
ca
n
b
e
a
g
o
o
d
g
r
o
u
n
d
f
o
r
i
m
p
la
n
ti
n
g
t
h
e
n
e
w
id
ea
s
,
tec
h
n
o
lo
g
ies
a
n
d
m
e
t
h
o
d
s
th
o
s
e
w
o
u
ld
r
es
u
lt
in
s
i
g
n
i
f
ican
t
s
o
lu
tio
n
s
to
th
e
p
r
o
b
lem
s
o
f
t
h
e
b
io
m
etr
ic
s
y
s
te
m
.
A
co
m
b
in
at
io
n
o
f
m
o
r
e
th
an
o
n
e
liv
e
n
es
s
i
n
d
icato
r
in
o
n
e
s
y
s
te
m
,
a
u
s
e
o
f
test
d
ata
w
ith
d
i
f
f
er
en
t
s
p
o
o
f
in
g
s
ce
n
ar
io
s
,
w
o
u
ld
af
f
e
ct
th
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
o
f
d
etec
tio
n
s
y
s
te
m
.
Fin
all
y
,
t
h
e
a
i
m
is
n
o
t
to
g
et
a
s
y
s
te
m
1
0
0
%
s
ec
u
r
ed
,
b
u
t
to
s
i
m
p
l
y
m
a
k
e
t
h
e
s
y
s
te
m
m
o
r
e
s
ec
u
r
e,
r
o
b
u
s
t
a
n
d
as a
cc
u
r
ate
as p
o
s
s
ib
le.
RE
F
E
R
E
NC
E
S
[1
]
M
.
S
.
Nix
o
n
,
Ha
n
d
b
o
o
k
o
f
B
io
me
tric A
n
ti
-
S
p
o
o
fi
n
g
,
V
e
rlag
L
o
n
d
o
n
:
S
p
rin
g
e
r,
2
0
1
4
.
[2
]
S
.
P
a
rv
e
e
n
,
S
.
M
u
m
taz
a
h
,
S
.
A
h
m
a
d
,
M
.
Ha
n
a
f
i,
W
.
A
z
izu
n
,
a
n
d
W
.
A
d
n
a
n
,
“
F
a
c
e
a
n
ti
-
sp
o
o
f
in
g
m
e
th
o
d
s,”
Cu
rr
.
S
c
i.
,
v
o
l
.
1
0
8
,
n
o
.
8
,
2
0
1
5
.
[3
]
A
.
A
d
ler
a
n
d
S
.
S
c
h
u
c
k
e
rs,
S
e
c
u
rity
a
n
d
L
ive
n
e
ss
,
Ov
e
rv
iew
,
in
E
n
c
y
c
lo
p
e
d
i
a
o
f
Bi
o
me
trics
,
S
.
Z
.
L
i
a
n
d
A
.
J
a
i
n
,
Ed
s.
B
o
sto
n
,
M
A:
S
p
ri
n
g
e
r US
,
2
0
0
9
,
p
p
.
1
1
4
6
–
1
1
5
2
.
[4
]
I.
Ch
i
n
g
o
v
sk
a
,
A
.
A
n
jo
s,
a
n
d
E
.
M
a
rc
e
l,
“
On
th
e
e
f
f
e
c
ti
v
e
n
e
ss
o
f
lo
c
a
l
b
in
a
ry
p
a
tt
e
rn
s
in
f
a
c
e
a
n
ti
-
sp
o
o
f
in
g
,
”
In
t.
C
o
n
f
.
Bi
o
me
trics
S
p
e
c
.
I
n
ter
e
s.
Gr
.
,
2
0
12
,
p
p
.
1
–
7.
[5
]
T
.
De
F
re
it
a
s
P
e
re
ira,
A
.
A
n
jo
s,
J.
M
.
De
M
a
rti
n
o
,
a
n
d
S
.
M
a
rc
e
l
,
“
L
BP
-
T
OP
b
a
se
d
c
o
u
n
term
e
a
su
re
a
g
a
in
st
f
a
c
e
sp
o
o
f
in
g
a
tt
a
c
k
s,”
L
e
c
t.
No
tes
Co
mp
u
t.
S
c
i.
(
in
c
lu
d
i
n
g
S
u
b
se
r.
L
e
c
t
.
No
tes
Arti
f.
I
n
tell.
L
e
c
t.
N
o
tes
B
io
in
f
o
rm
a
ti
c
s)
,
v
o
l.
7
7
2
8
L
NCS,
n
o
.
P
A
RT
1
,
p
p
.
1
2
1
–
1
3
2
,
2
0
1
3
.
[6
]
J.
Ga
lb
a
ll
y
,
S
.
M
a
rc
e
l,
a
n
d
J.
F
ierre
z
,
“
I
m
a
g
e
q
u
a
li
t
y
a
s
se
ss
m
e
n
t
fo
r
f
a
k
e
b
io
m
e
tri
c
d
e
tec
ti
o
n
:
A
p
p
li
c
a
ti
o
n
to
Iris
,
f
in
g
e
rp
rin
t,
a
n
d
f
a
c
e
re
c
o
g
n
it
io
n
,
”
IEE
E
T
r
a
n
s.
Im
a
g
e
Pr
o
c
e
ss
.
,
v
o
l
.
2
3
,
n
o
.
2
,
p
p
.
7
1
0
–
7
2
4
,
2
0
1
4
.
[7
]
B.
P
e
ix
o
t
o
,
C.
M
ich
e
las
si,
a
n
d
A
.
Ro
c
h
a
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
u
n
d
e
r
b
a
d
il
lu
m
in
a
ti
o
n
c
o
n
d
it
i
o
n
s,”
Pro
c
.
-
In
t.
Co
n
f.
Ima
g
e
Pro
c
e
ss
.
ICIP
,
p
p
.
3
5
5
7
–
3
5
6
0
,
2
0
1
1
.
[8
]
W
.
R.
S
c
h
w
a
rtz,
a
t
a
l.
,
“
F
a
c
e
S
p
o
o
f
in
g
De
tec
ti
o
n
th
r
o
u
g
h
P
a
rti
a
l
L
e
a
st S
q
u
a
re
s,”
In
t.
J
t.
Co
n
f.
Bi
o
m
e
trics
,
2
0
1
1
.
[9
]
J.
M
tt
,
A
.
Ha
d
id
,
a
n
d
M
.
P
ieti
k
in
e
n
,
“
F
a
c
e
sp
o
o
f
in
g
d
e
tec
ti
o
n
f
ro
m
sin
g
le
i
m
a
g
e
s
u
sin
g
tex
tu
re
a
n
d
lo
c
a
l
sh
a
p
e
a
n
a
ly
sis,”
IET
Bi
o
me
trics
,
v
o
l.
1
,
n
o
.
1
,
p
.
3
,
2
0
1
2
.
[1
0
]
N.
Ko
se
a
n
d
J.
L
.
Du
g
e
la
y
,
“
Clas
sif
ica
ti
o
n
o
f
c
a
p
tu
re
d
a
n
d
re
c
a
p
t
u
re
d
im
a
g
e
s
to
d
e
tec
t
p
h
o
to
g
ra
p
h
s
p
o
o
f
in
g
,
”
2
0
1
2
In
t.
C
o
n
f
.
In
f
o
rm
a
ti
c
s,
El
e
c
tro
n
.
Vi
sio
n
,
ICIEV
2
0
1
2
,
p
p
.
1
0
2
7
–
1
0
3
2
,
2
0
1
2
.
[1
1
]
J.
G
a
lb
a
ll
y
a
n
d
S
.
M
a
rc
e
l,
“
F
a
c
e
a
n
ti
-
sp
o
o
f
in
g
b
a
se
d
o
n
g
e
n
e
ra
l
i
m
a
g
e
q
u
a
li
ty
a
s
se
ss
m
e
n
t,
”
Pr
o
c
.
-
In
t.
Co
n
f
.
Pa
tt
e
rn
Rec
o
g
n
it
.
,
p
p
.
1
1
7
3
–
1
1
7
8
,
2
0
1
4
.
[1
2
]
Z.
Zh
iw
e
i
e
t
a
l.
,
“
A
f
a
c
e
a
n
ti
sp
o
o
f
in
g
d
a
tab
a
se
w
it
h
d
iv
e
rse
a
tt
a
c
k
s,”
in
P
r
o
c
.
In
t.
C
o
n
f
.
o
n
Bi
o
m
e
tri
c
s
(ICB),
p
p
.
2
6
–
31
,
2
0
1
2
.
[1
3
]
K.
Ko
ll
re
id
e
r,
H.
F
r
o
n
th
a
ler,
M
.
I.
F
a
ra
j,
a
n
d
J.
Big
u
n
,
“
Re
a
l
-
T
i
m
e
F
a
c
e
De
tec
ti
o
n
a
n
d
M
o
ti
o
n
A
n
a
l
y
si
s
W
it
h
A
p
p
li
c
a
ti
o
n
i
n
„
L
iv
e
n
e
ss
‟
A
ss
e
s
s
m
e
n
t,
”
An
a
lys
is
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
5
4
8
–
5
5
8
,
2
0
0
7
.
[1
4
]
K.
Ko
ll
re
id
e
r,
H.
F
ro
n
th
a
ler,
a
n
d
J.
Big
u
n
,
“
No
n
-
in
tr
u
siv
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
b
y
f
a
c
e
i
m
a
g
e
s,”
Ima
g
e
Vi
s.
Co
mp
u
t.
,
v
o
l.
2
7
,
n
o
.
3
,
p
p
.
2
3
3
–
2
4
4
,
2
0
0
9
.
[1
5
]
M
.
H.
S
u
n
,
L
.
,
Hu
a
n
g
,
W
.
B.
a
n
d
W
u
,
“
T
IR/V
IS
c
o
rre
latio
n
f
o
r
li
v
e
n
e
ss
d
e
tec
ti
o
n
in
f
a
c
e
re
c
o
g
n
it
io
n
.
,
”
in
Co
m
p
u
ter
A
n
a
lys
is
o
f
Ima
g
e
s a
n
d
P
a
tt
e
rn
,
S
p
rin
g
e
r
,
p
p
.
1
1
4
–
1
2
1
,
2
0
1
1
.
[1
6
]
G
.
Ch
e
tt
y
a
n
d
M
.
W
a
g
n
e
r,
“
Co
R
u
Re
m
e
F
ro
n
Us
e
ra
I
Ch
len
g
,
”
Bi
o
me
trics
,
2
0
0
6
.
[1
7
]
S
.
Kim
,
S
.
Yu
,
K.
Ki
m
,
Y
.
B
a
n
,
a
n
d
S
.
L
e
e
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
te
c
ti
o
n
u
si
n
g
v
a
riab
le
f
o
c
u
sin
g
,
”
in
Pro
c
e
e
d
in
g
s
-
2
0
1
3
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
,
ICB
2
0
1
3
,
2
0
1
3
.
[1
8
]
N.
Erd
o
g
m
u
s
a
n
d
S
.
M
a
rc
e
l,
“
S
p
o
o
f
in
g
i
n
2
D
f
a
c
e
re
c
o
g
n
it
io
n
w
it
h
3
D
m
a
sk
s
a
n
d
a
n
t
i
-
sp
o
o
f
in
g
w
it
h
Kin
e
c
t,
”
IE
EE
6
t
h
I
n
t.
C
o
n
f.
Bi
o
me
trics
T
h
e
o
ry
,
Ap
p
l.
S
y
st.
BT
A
S
2
0
1
3
,
2
0
1
3
.
[1
9
]
W
.
Ba
o
,
H.
L
i,
N.
L
i,
W
.
Jia
n
g
,
a
n
d
a
O.
F
.
F
ield
,
“
A
L
i
v
e
n
e
ss
De
tec
ti
o
n
M
e
th
o
d
f
o
r
F
a
c
e
R
e
c
o
g
n
it
io
n
Ba
se
d
o
n
Op
ti
c
a
l
F
lo
w
F
ield
,
”
Co
mp
u
ter
(
L
o
n
g
.
Bea
c
h
.
C
a
li
f)
.
,
p
p
.
0
–
3
,
2
0
0
9
.
[2
0
]
S
.
M
.
Ha
tt
u
re
,
“
P
re
v
e
n
ti
o
n
o
f
S
p
o
o
f
A
tt
a
c
k
in
Bio
m
e
tri
c
S
y
ste
m
Us
in
g
L
iv
e
n
e
s
s
De
tec
ti
o
n
,
”
In
t.
J
.
L
a
tes
t
T
re
n
d
s
En
g
.
T
e
c
h
n
o
l.
,
n
o
.
S
p
e
c
ial
Iss
u
e
-
I
DEA
S
-
2
0
1
3
,
p
p
.
4
2
–
4
9
,
2
0
1
3
.
[2
1
]
A
.
Lag
o
rio
,
M
.
T
istare
ll
i,
M
.
Ca
d
o
n
i,
C
.
F
o
o
k
e
s,
a
n
d
S
.
S
r
id
h
a
ra
n
,
“
L
iv
e
n
e
ss
d
e
tec
ti
o
n
b
a
se
d
o
n
3
D
f
a
c
e
sh
a
p
e
a
n
a
ly
sis,”
2
0
1
3
In
t
.
W
o
rk
.
Bi
o
me
t
ric
s F
o
re
n
sic
s
,
p
p
.
1
–
4
,
2
0
1
3
.
[2
2
]
G
.
P
a
n
e
t
a
l.
,
“
E
y
e
b
li
n
k
-
b
a
se
d
An
ti
-
S
p
o
o
n
g
in
F
a
c
e
Re
c
o
g
n
it
io
n
f
ro
m
a
G
e
n
e
ric
W
e
b
c
a
m
e
ra
,
”
1
1
th
IEE
E
ICCV
,
Rio
Ja
n
e
iro
,
Bra
z
il
,
Oc
t.
,
v
o
l.
1
4
,
p
p
.
2
0
,
2
0
0
7
.
[2
3
]
G
.
P
a
n
,
L
.
S
u
n
,
Z.
W
u
,
a
n
d
Y.
Wan
g
,
“
M
o
n
o
c
u
lar ca
m
e
ra
-
b
a
se
d
f
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
b
y
c
o
m
b
in
in
g
e
y
e
b
li
n
k
a
n
d
sc
e
n
e
c
o
n
tex
t,
”
T
e
lec
o
mm
u
n
.
S
y
st
.
,
v
o
l.
4
7
,
n
o
.
3
–
4
,
p
p
.
2
1
5
–
2
2
5
,
2
0
1
1
.
[2
4
]
K.
Ko
ll
re
id
e
r,
H.
F
ro
n
t
h
a
ler,
a
n
d
J.
Big
u
n
,
“
V
e
rify
in
g
li
v
e
n
e
ss
b
y
m
u
lt
ip
l
e
e
x
p
e
rts
in
f
a
c
e
b
io
m
e
tri
c
s,”
2
0
0
8
IEE
E
Co
mp
u
t
.
S
o
c
.
C
o
n
f
.
Co
m
p
u
t.
Vi
s.
Pa
tt
e
rn
Rec
o
g
n
it
.
W
o
rk
.
CV
PR
W
o
rk
.
,
2
0
0
8
.
[2
5
]
C.
Ka
n
t,
“
F
a
k
e
F
a
c
e
Re
c
o
g
n
it
io
n
u
sin
g
F
u
sio
n
o
f
T
h
e
r
m
a
l
I
m
a
g
in
g
a
n
d
S
k
in
El
a
sticit
y
,
”
Ijcs
c
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
6
5
–
7
2
,
2
0
1
3
.
[2
6
]
G
.
Ch
e
tt
y
,
“
Ro
b
u
st
a
u
d
i
o
v
isu
a
l
b
io
m
e
tri
c
p
e
rso
n
a
u
th
e
n
ti
c
a
ti
o
n
w
it
h
li
v
e
n
e
ss
v
e
ri
f
ica
ti
o
n
,
”
In
tel
M
u
lt
ime
d
.
An
a
l.
S
e
c
u
r.
Ap
p
l.
S
CI
2
8
2
,
S
p
ri
n
g
e
r
,
p
p
.
5
9
–
78
,
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
I
n
s
ig
h
t o
n
f
a
ce
liven
ess
d
etec
tio
n
:
a
s
ystema
tic
liter
a
tu
r
e
r
ev
iew
(
E
n
a
s
A
.
R
a
h
ee
m
)
5173
[2
7
]
A
.
L
ib
e
ra
ti
e
t
a
l.
,
“
T
h
e
P
RIS
M
A
S
tate
m
e
n
t
f
o
r
Re
p
o
rti
n
g
S
y
ste
m
a
ti
c
Re
v
ie
w
s
a
n
d
M
e
ta
-
A
n
a
l
y
s
e
s
o
f
S
tu
d
ies
T
h
a
t
Ev
a
lu
a
te He
a
lt
h
Ca
re
In
terv
e
n
ti
o
n
s: E
x
p
lan
a
ti
o
n
a
n
d
El
a
b
o
ra
ti
o
n
,
”
PL
OS
M
e
d
.
,
v
o
l.
6
,
n
o
.
7
,
p
p
.
1
–
2
8
,
2
0
0
9
.
[2
8
]
O.
Ka
h
m
a
n
d
N.
Da
m
e
r,
“
2
D
fa
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
:
A
n
o
v
e
rv
i
e
w
,
”
BIOS
IG
-
Pro
c
e
e
d
in
g
s
IE
EE
In
t.
C
o
n
f
.
th
e
.
Bi
o
me
trics
S
p
e
c
.
I
n
ter
e
s.
Gr
.
(
BIOS
IG)
, 2
0
1
2
,
p
p
.
1
7
1
–
1
8
2
.
[2
9
]
J.
G
a
lb
a
ll
y
,
S
.
M
a
rc
e
l,
a
n
d
J.
F
ierre
z
,
“
Bio
m
e
tri
c
A
n
ti
sp
o
o
f
in
g
M
e
th
o
d
s:
A
S
u
rv
e
y
in
F
a
c
e
Re
c
o
g
n
it
io
n
,”
IEE
E
J
o
u
rn
a
ls
&
a
mp
;
M
a
g
a
zi
n
e
,
v
o
l.
2
,
2
0
1
5
.
[3
0
]
M
.
Ba
g
g
a
a
n
d
B.
S
in
g
h
,
“
S
p
o
o
f
in
g
De
tec
ti
o
n
In
F
a
c
e
Re
c
o
g
n
it
io
n
:
A
Re
v
ie
w
,
”
in
2
0
1
6
3
rd
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ti
n
g
fo
r
S
u
s
ta
in
a
b
le Gl
o
b
a
l
De
v
e
lo
p
me
n
t
(
INDIACo
m)
,
2
0
1
6
,
p
p
.
2
0
3
7
–
2
0
4
2
.
[3
1
]
S
.
L
.
F
e
rn
a
n
d
e
s
a
n
d
G
.
J.
Ba
la,
“
De
v
e
lo
p
in
g
a
No
v
e
l
Tec
h
n
iq
u
e
f
o
r
F
a
c
e
L
iv
e
n
e
ss
De
te
c
ti
o
n
,
”
Ph
y
s.
Pro
c
e
d
ia
,
v
o
l.
7
8
,
n
o
.
De
c
e
m
b
e
r
2
0
1
5
,
p
p
.
2
4
1
–
2
4
7
,
2
0
1
6
.
[3
2
]
J.
G
a
lb
a
ll
y
a
n
d
S
.
M
a
rc
e
l,
“
F
a
c
e
a
n
ti
-
sp
o
o
f
in
g
b
a
se
d
o
n
g
e
n
e
ra
l
ima
g
e
q
u
a
li
ty
a
ss
e
ss
m
e
n
t,
”
in
Pro
c
e
e
d
in
g
s
-
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
P
a
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
1
4
,
p
p
.
1
1
7
3
–
1
1
7
8
.
[3
3
]
A
.
Bh
a
s
k
a
r
a
n
d
R.
P
.
A
n
e
e
sh
,
“
A
d
v
a
n
c
e
d
a
lg
o
rit
h
m
f
o
r
g
e
n
d
e
r
p
re
d
ictio
n
w
it
h
im
a
g
e
q
u
a
li
ty
a
ss
e
ss
m
e
n
t,
”
2
0
1
5
I
n
t.
C
o
n
f.
A
d
v
.
Co
m
p
u
t
.
Co
mm
u
n
.
I
n
fo
rm
a
ti
c
s,
ICACCI
2
0
1
5
,
p
p
.
1
8
4
8
–
1
8
5
5
,
2
0
1
5
.
[3
4
]
P
.
P
ra
v
a
ll
ik
a
,
“
S
V
M
Clas
sif
ica
ti
o
n
F
o
r
F
a
k
e
Bio
m
e
tri
c
D
e
tec
ti
o
n
Us
in
g
Im
a
g
e
Qu
a
li
ty
As
se
s
s
m
e
n
t
:
A
p
p
li
c
a
ti
o
n
t
o
iri
s,
f
a
c
e
a
n
d
p
a
lm
p
rin
t,
”
in
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
v
e
n
ti
v
e
Co
mp
u
ta
ti
o
n
T
e
c
h
n
o
l
o
g
ies
(ICICT
)
,
2
0
1
6
.
[3
5
]
A
.
A
.
S
.
A
.
Dh
o
le,
P
a
ti
l,
“
S
y
ste
m
f
o
r
M
u
lt
i
-
b
i
o
m
e
tri
c
De
t
e
c
ti
o
n
,
”
2
0
1
6
In
t
.
Co
n
f.
In
v
e
n
.
Co
mp
u
t.
T
e
c
h
n
o
l
.
,
v
o
l.
3
,
n
o
.
2
,
2
0
1
6
.
[3
6
]
L
.
F
e
n
g
,
L
.
-
M
.
P
o
,
Y.
L
i,
a
n
d
F
.
Yu
a
n
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
u
sin
g
sh
e
a
rlet
-
b
a
se
d
f
e
a
tu
re
d
e
sc
rip
to
rs,
”
J
.
El
e
c
tro
n
.
Im
a
g
i
n
g
,
v
o
l.
2
5
,
n
o
.
4
,
p
p
.
0
4
3
0
1
4
,
2
0
1
6
.
[3
7
]
L
.
F
e
n
g
e
t
a
l.
,
“
In
teg
ra
ti
o
n
o
f
ima
g
e
q
u
a
li
ty
a
n
d
m
o
ti
o
n
c
u
e
s
f
o
r
f
a
c
e
a
n
ti
-
sp
o
o
f
in
g
:
A
n
e
u
ra
l
n
e
two
rk
a
p
p
ro
a
c
h
,
”
J
.
Vi
s.
Co
mm
u
n
.
Ima
g
e
Re
p
re
se
n
t.
,
v
o
l.
3
8
,
2
0
1
6
.
[3
8
]
E.
A
.
Ra
h
e
e
m
a
n
d
S
.
M
.
S
.
A
h
m
a
d
,
“
S
tatisti
c
a
l
a
n
a
l
y
sis
o
f
i
m
a
g
e
q
u
a
li
ty
m
e
a
su
re
s
f
o
r
fa
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
,
”
in
L
e
c
tu
re
N
o
tes
in
El
e
c
trica
l
E
n
g
in
e
e
rin
g
,
2
0
1
9
,
v
o
l.
5
4
7
,
p
p
.
5
4
3
–
5
4
9
.
[3
9
]
I.
Ch
i
n
g
o
v
sk
a
e
t
a
l.
,
“
T
h
e
2
n
d
c
o
m
p
e
ti
ti
o
n
o
n
c
o
u
n
ter
m
e
a
su
re
s
to
2
D
f
a
c
e
sp
o
o
f
in
g
a
tt
a
c
k
s,”
Pr
o
c
.
-
2
0
1
3
In
t
.
Co
n
f.
Bi
o
me
trics
,
ICB
,
2
0
1
3
,
p
p
.
1
–
6.
[4
0
]
V
.
Ra
v
ib
a
b
u
,
“
A
V
a
r
y
A
p
p
ro
a
c
h
to
F
a
c
e
Re
c
o
g
n
it
io
n
V
e
rit
a
b
le
M
e
c
h
a
n
ism
s
f
o
r
A
n
d
ro
id
M
o
b
i
le
a
g
a
in
st
S
p
o
o
f
in
g
,
”
in
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
t
a
ti
o
n
a
l
In
t
e
ll
ig
e
n
c
e
a
n
d
C
o
mp
u
ti
n
g
Res
e
a
rc
h
,
2
0
1
4
.
[4
1
]
P
.
J.
A
ra
th
y
a
n
d
V
.
V
.
Na
ir,
“
A
n
a
l
y
sis
o
f
S
p
o
o
f
in
g
De
tec
ti
o
n
u
si
n
g
V
id
e
o
S
u
b
se
c
ti
o
n
P
r
o
c
e
ss
in
g
,
”
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
f
o
rm
a
ti
c
s
a
n
d
A
n
a
lytics
-
ICI
A
-
16
,
2
0
1
6
,
p
p
.
1
–
6.
[4
2
]
L
.
F
e
n
g
,
L
.
-
M
.
P
o
,
Y.
L
i,
a
n
d
F
.
Yu
a
n
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
u
sin
g
sh
e
a
rlet
-
b
a
se
d
f
e
a
tu
re
d
e
sc
rip
to
rs,
”
J
.
El
e
c
tro
n
.
I
m
a
g
i
n
g
,
v
o
l.
2
5
,
n
o
.
4
,
p
p
.
0
4
3
0
1
4
,
2
0
1
6
.
[4
3
]
S
.
R.
A
ra
sh
lo
o
,
J.
Kitt
ler,
a
n
d
W
.
Ch
ristm
a
s,
“
F
a
c
e
S
p
o
o
f
in
g
De
tec
ti
o
n
Ba
se
d
o
n
M
u
lt
i
p
le
De
sc
rip
to
r
F
u
sio
n
Us
in
g
M
u
lt
isc
a
le
Dy
n
a
m
ic
Bin
a
rize
d
S
tatisti
c
a
l
Im
a
g
e
F
e
a
tu
re
s,”
IEE
E
T
ra
n
s.
In
f
.
F
o
re
n
sic
s
S
e
c
u
r.
,
v
o
l.
1
0
,
n
o
.
1
1
,
p
p
.
2
3
9
6
–
2
4
0
7
,
2
0
1
5
.
[4
4
]
J.
P
e
n
g
a
n
d
P
.
P
.
K.
Ch
a
n
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
te
c
ti
o
n
f
o
r
c
o
m
b
a
ti
n
g
th
e
sp
o
o
f
in
g
a
tt
a
c
k
in
fa
c
e
re
c
o
g
n
it
io
n
,
”
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
W
a
v
e
let
An
a
lys
is
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
,
2
0
1
4
,
v
o
l.
2
0
1
4
-
Ja
n
.
,
p
p
.
1
7
6
–
1
8
1
.
[4
5
]
R.
R.
R.
K.
M
.
S
.
B.
C,
“
F
a
c
e
P
r
e
se
n
tatio
n
A
tt
a
c
k
De
tec
ti
o
n
A
c
ro
ss
S
p
e
c
tru
m
u
sin
g
T
i
m
e
-
F
re
q
u
e
n
c
y
De
s
c
rip
to
rs
o
f
M
a
x
i
m
a
l
Re
sp
o
n
se
in
L
a
p
lac
ian
S
c
a
le
-
S
p
a
c
e
,
”
in
2
0
1
6
S
ixt
h
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Im
a
g
e
Pro
c
e
ss
in
g
T
h
e
o
ry
,
T
o
o
ls
a
n
d
A
p
p
li
c
a
ti
o
n
s (
IPT
A)
,
2
0
1
6
,
p
p
.
0
–
5.
[4
6
]
K.
G
.
D.
E.
S
.
A
,
“
S
h
o
rt
term
re
-
id
e
n
ti
f
ica
ti
o
n
o
f
A
u
to
m
a
ti
c
Teller
M
a
c
h
in
e
(A
T
M
)
u
se
rs
v
ia
f
a
c
e
a
n
d
b
o
d
y
a
p
p
e
a
ra
n
c
e
f
e
a
tu
re
s,” in
2
0
1
6
4
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
a
n
d
F
o
re
n
sic
s (
IW
BF
)
,
2
0
1
6
,
p
p
.
1
–
6.
[4
7
]
F
.
G
.
B.
D.
N.
Q.
-
T
.
P
.
D.
-
T
.
D
.
-
N.
G
iu
li
a
Bo
a
to
a
n
d
De
p
a
rtm
e
n
t,
“
F
a
c
e
sp
o
o
f
in
g
d
e
tec
ti
o
n
u
si
n
g
L
DP
-
T
OP
,
”
in
2
0
1
6
IE
EE
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Ima
g
e
Pro
c
e
ss
in
g
(
ICIP)
,
2
0
1
6
.
[4
8
]
F
.
Y.
Yu
m
in
g
L
i,
L
a
i
-
M
a
n
P
o
,
X
u
y
u
a
n
Xu
,
L
it
o
n
g
F
e
n
g
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
u
si
n
g
sh
e
a
rlet
b
a
se
d
f
e
a
tu
re
d
e
sc
rip
to
rs,”
ICAS
S
P
,
p
p
.
8
7
4
–
8
7
7
,
2
0
1
6
.
[4
9
]
R.
Ra
g
h
a
v
e
n
d
ra
,
K.
B.
Ra
ja,
a
n
d
C.
B
u
sc
h
,
“
De
tec
ti
n
g
m
o
rp
h
e
d
f
a
c
e
i
m
a
g
e
s,”
in
2
0
1
6
I
EE
E
8
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
T
h
e
o
ry
,
Ap
p
li
c
a
t
io
n
s a
n
d
S
y
ste
ms
,
BT
AS
2
0
1
6
,
2
0
1
6
.
[5
0
]
A
.
Ag
a
r
wa
l,
R
.
S
in
g
h
,
a
n
d
M
.
V
a
tsa
,
“
F
a
c
e
a
n
ti
-
sp
o
o
f
in
g
u
sin
g
Ha
ra
li
c
k
f
e
a
tu
re
s,”
in
2
0
1
6
IEE
E
8
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
T
h
e
o
ry
,
Ap
p
li
c
a
t
io
n
s a
n
d
S
y
ste
ms
,
BT
AS
2
0
1
6
,
2
0
1
6
.
[5
1
]
A
.
A
lo
taib
i
a
n
d
A
.
M
a
h
m
o
o
d
,
“
En
h
a
n
c
i
n
g
c
o
m
p
u
ter
v
isio
n
to
d
e
tec
t
f
a
c
e
sp
o
o
f
in
g
a
tt
a
c
k
u
ti
li
z
in
g
a
sin
g
le
f
ra
m
e
f
ro
m
a
re
p
la
y
v
id
e
o
a
tt
a
c
k
u
sin
g
d
e
e
p
lea
rn
in
g
,
”
i
n
Pr
o
c
e
e
d
in
g
s
-
2
0
1
6
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Op
to
e
lec
tro
n
ics
a
n
d
Ima
g
e
Pro
c
e
ss
in
g
,
ICOIP
2
0
1
6
,
2
0
1
6
,
p
p
.
1
–
5.
[5
2
]
H.
K.
Ba
sh
ier,
L
.
S
.
Ho
e
,
P
.
Y.
Ha
n
,
L
.
Y.
P
i
n
g
,
a
n
d
C.
M
.
L
i
,
“
F
a
c
e
S
p
o
o
f
in
g
De
tec
ti
o
n
Us
in
g
L
o
c
a
l
G
ra
p
h
S
tru
c
tu
re
,
”
I
n
t.
C
o
n
f.
C
o
mp
u
t.
Co
mm
u
n
.
I
n
f.
T
e
c
h
n
o
l.
,
p
p
.
1
4
–
1
7
,
2
0
1
4
.
[5
3
]
D.
W
e
n
,
H.
Ha
n
,
a
n
d
A
.
K.
Ja
in
,
“
F
a
c
e
sp
o
o
f
d
e
tec
ti
o
n
w
it
h
im
a
g
e
d
isto
r
ti
o
n
a
n
a
ly
sis,”
IEE
E
T
ra
n
s.
In
f.
Fo
re
n
sic
s
S
e
c
u
r.
,
v
o
l.
1
0
,
n
o
.
4
,
p
p
.
7
4
6
–
7
6
1
,
2
0
1
5
.
[5
4
]
J.
Ya
n
g
,
Z.
L
e
i,
D.
Yi,
a
n
d
S
.
Z.
L
i,
“
P
e
rso
n
-
S
p
e
c
if
ic
F
a
c
e
An
ti
sp
o
o
f
in
g
W
it
h
S
u
b
jec
t
D
o
m
a
i
n
A
d
a
p
tatio
n
,
”
IEE
E
T
ra
n
s.
I
n
f.
Fo
re
n
sic
s S
e
c
u
r.
,
v
o
l.
1
0
,
n
o
.
4
,
p
p
.
7
9
7
–
8
0
9
,
2
0
1
5
.
[5
5
]
D.
C.
G
a
rc
ia
a
n
d
Rica
rd
o
L
.
d
e
Qu
e
iro
z
,
“
F
a
c
e
-
S
p
o
o
f
in
g
2
D
-
De
te
c
ti
o
n
Ba
se
d
o
n
M
o
iré
-
P
a
tt
e
rn
A
n
a
l
y
sis,”
IEE
E
T
ra
n
s.
I
n
f.
Fo
re
n
sic
s S
e
c
u
r.
,
v
o
l.
1
0
,
n
o
.
4
,
p
p
.
7
7
8
–
7
8
6
,
2
0
1
5
.
[5
6
]
M
.
W
a
ris,
H.
Zh
a
n
g
,
I.
A
h
m
a
d
,
S
.
Kira
n
y
a
z
,
a
n
d
M
.
G
a
b
b
o
u
j,
“
E
USIP
CO
2
0
1
3
1
5
6
9
7
4
4
1
8
7
A
n
a
ly
sis
O
f
T
e
x
tu
ra
l
F
e
a
tu
re
s F
o
r
F
a
c
e
Bio
m
e
tri
c
A
n
ti
-
S
p
o
o
f
in
g
,
”
EUS
IPCO
,
p
p
.
1
–
5
,
2
0
1
3
.
[5
7
]
Z.
Ak
h
tar,
C.
M
ich
e
lo
n
,
a
n
d
G
.
L.
F
o
re
sti,
“
L
iv
e
n
e
ss
d
e
tec
ti
o
n
f
o
r
b
io
m
e
tri
c
a
u
th
e
n
ti
c
a
ti
o
n
i
n
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
s,
”
in
Pro
c
e
e
d
i
n
g
s
-
In
ter
n
a
ti
o
n
a
l
Ca
rn
a
h
a
n
Co
n
fer
e
n
c
e
o
n
S
e
c
u
rity T
e
c
h
n
o
l
o
g
y
,
2
0
1
4
,
v
o
l.
2
0
1
4
-
Oc
t
.
,
n
o
.
Oc
t
o
b
e
r.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
1
6
5
-
5
1
7
5
5174
[5
8
]
Z.
Bo
u
lk
e
n
a
f
e
t,
J.
Ko
m
u
lain
e
n
,
a
n
d
A
.
H
a
d
id
,
“
F
a
c
e
S
p
o
o
f
in
g
De
te
c
ti
o
n
Us
in
g
Co
lo
u
r
T
e
x
tu
re
A
n
a
l
y
sis,”
IEE
E
T
ra
n
s.
I
n
f.
Fo
re
n
sic
s S
e
c
u
r
.
,
v
o
l.
1
1
,
n
o
.
8
,
p
p
.
1
8
1
8
–
1
8
3
0
,
2
0
1
6
.
[5
9
]
Y.
Bin
n
y
Re
e
b
a
a
n
d
R.
S
h
a
n
m
u
g
a
lak
sh
m
i,
“
S
p
o
o
f
in
g
f
a
c
e
re
c
o
g
n
it
io
n
,
”
in
ICACC
S
2
0
1
5
-
Pro
c
e
e
d
in
g
s
o
f
th
e
2
n
d
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
mp
u
ti
n
g
a
n
d
Co
mm
u
n
ic
a
ti
o
n
S
y
ste
ms
,
2
0
1
5
,
p
p
.
3
–
7.
[6
0
]
K.
P
a
tel,
H.
Ha
n
,
a
n
d
A
.
K.
Ja
in
,
“
S
e
c
u
re
F
a
c
e
Un
lo
c
k
:
S
p
o
o
f
De
tec
ti
o
n
o
n
S
m
a
rtp
h
o
n
e
s,”
IEE
E
T
ra
n
s.
I
n
f
.
Fo
re
n
sic
s S
e
c
u
r.
,
v
o
l.
1
1
,
n
o
.
1
0
,
p
p
.
2
2
6
8
–
2
2
8
3
,
2
0
1
6
.
[6
1
]
D.
Da
s
a
n
d
S
.
Ch
a
k
ra
b
o
rty
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
ti
o
n
b
a
se
d
o
n
f
re
q
u
e
n
c
y
a
n
d
m
icro
-
tex
tu
re
a
n
a
l
y
sis,”
in
2
0
1
4
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
s in
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
Res
e
a
rc
h
,
ICAE
T
R
2
0
1
4
,
2
0
1
4
,
p
p
.
3
–
6.
[6
2
]
S
.
P
a
rv
e
e
n
,
S
.
M
.
S
.
A
h
m
e
d
,
N.
H.
A
b
b
a
s,
N.
Na
e
e
m
,
a
n
d
M
.
Ha
n
a
f
i,
“
T
e
x
tu
re
a
n
a
l
y
sis
u
sin
g
lo
c
a
l
tern
a
ry
p
a
tt
e
rn
f
o
r
f
a
c
e
a
n
ti
-
sp
o
o
f
in
g
,
”
S
c
i.
I
n
t
,
v
o
l.
2
8
,
n
o
.
2
,
p
p
.
9
6
5
–
9
7
1
,
2
0
1
6
.
[6
3
]
M
.
Ja
f
a
ri
Ba
ra
n
i,
K.
F
a
e
z
,
a
n
d
F
.
Ja
li
li
,
“
Im
p
le
m
e
n
tatio
n
o
f
G
a
b
o
r
F
il
ters
C
o
m
b
in
e
d
w
it
h
Bi
n
a
ry
F
e
a
tu
re
s
f
o
r
G
e
n
d
e
r
Re
c
o
g
n
it
io
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
1
0
8
–
1
1
5
,
2
0
1
4
.
[6
4
]
L
.
Ya
n
g
,
“
F
a
c
e
li
v
e
n
e
ss
d
e
tec
t
io
n
b
y
f
o
c
u
sin
g
o
n
f
ro
n
tal
f
a
c
e
s
a
n
d
ima
g
e
b
a
c
k
g
ro
u
n
d
s
,
”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
a
v
e
let
An
a
lys
is
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
1
4
,
v
o
l.
2
0
1
4
-
Ja
n
,
p
p
.
9
3
–
9
7
.
[6
5
]
W
.
Yin
,
Y.
M
in
g
,
a
n
d
L
.
T
ian
,
“
A
fa
c
e
a
n
ti
-
sp
o
o
f
in
g
m
e
th
o
d
b
a
se
d
o
n
o
p
t
ica
l
f
lo
w
f
ield
,
”
in
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
Pro
c
e
ss
in
g
Pro
c
e
e
d
in
g
s,
ICS
P
,
2
0
1
7
,
p
p
.
1
3
3
3
–
1
3
3
7
.
[6
6
]
S
.
Bh
a
ra
d
w
a
j,
T
.
I.
Dh
a
m
e
c
h
a
,
M
.
V
a
tsa
,
a
n
d
R.
S
in
g
h
,
“
Co
m
p
u
tatio
n
a
ll
y
e
ff
icie
n
t
fa
c
e
sp
o
o
f
in
g
d
e
tec
ti
o
n
w
it
h
m
o
ti
o
n
m
a
g
n
if
ica
ti
o
n
,
”
in
IEE
E
Co
mp
u
ter
S
o
c
iety
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ter
Vi
si
o
n
a
n
d
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
W
o
rk
sh
o
p
s
,
2
0
1
3
,
p
p
.
1
0
5
–
1
1
0
.
[6
7
]
A
.
A
n
jo
s,
M
.
M
.
C
h
a
k
k
a
,
a
n
d
S
.
M
a
rc
e
l,
“
M
o
ti
o
n
-
b
a
se
d
c
o
u
n
ter
-
m
e
a
su
re
s
to
p
h
o
to
a
tt
a
c
k
s
in
f
a
c
e
re
c
o
g
n
it
io
n
,
”
n
o
.
N
o
v
e
m
b
e
r
2
0
1
2
,
p
p
.
1
4
7
–
1
5
8
,
2
0
1
4
.
[6
8
]
Y.
L
i,
Y.
L
i,
Q.
Y
a
n
,
H.
Ko
n
g
,
a
n
d
R.
H.
De
n
g
,
“
S
e
e
in
g
Yo
u
r
F
a
c
e
Is
No
t
En
o
u
g
h
:
A
n
In
e
rti
a
l
S
e
n
so
r
-
Ba
se
d
L
iv
e
n
e
s
s
De
tec
ti
o
n
f
o
r
F
a
c
e
A
u
t
h
e
n
ti
c
a
ti
o
n
,
”
in
CC
S
1
5
:
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
2
n
d
ACM
S
IGS
AC
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
a
n
d
Co
mm
u
n
ica
ti
o
n
s S
e
c
u
rity
,
2
0
1
5
,
p
p
.
1
5
5
8
–
1
5
6
9
.
[6
9
]
J.
Ko
m
u
lain
e
n
,
A
.
Ha
d
id
,
a
n
d
M
.
P
ietik
a
in
e
n
,
“
Co
n
tex
t
b
a
se
d
f
a
c
e
a
n
ti
-
sp
o
o
f
in
g
,
”
in
IEE
E
6
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
:
T
h
e
o
r
y
,
Ap
p
li
c
a
ti
o
n
s
a
n
d
S
y
ste
ms
,
BT
A
S
2
0
1
3
,
2
0
1
3
.
[7
0
]
I.
P
a
p
e
r
a
n
d
S
.
Z.
L
i,
“
F
a
c
e
L
iv
e
n
e
ss
De
te
c
ti
o
n
b
y
Ex
p
lo
rin
g
M
u
lt
ip
le
S
c
e
n
ic
Clu
e
s,”
In
t.
Co
n
f
.
Co
n
tro
l
Au
t
o
m.
Ro
b
o
t.
Vi
s
.
,
v
o
l
.
2
0
1
2
,
n
o
.
De
c
e
m
b
e
r,
p
p
.
1
8
8
–
1
9
3
,
2
0
1
2
.
[7
1
]
M
.
G
a
v
ril
e
s
c
u
,
“
S
tu
d
y
o
n
u
si
n
g
i
n
d
iv
id
u
a
l
d
if
fe
re
n
c
e
s
in
f
a
c
ial
e
x
p
re
ss
io
n
s
f
o
r
a
f
a
c
e
re
c
o
g
n
it
io
n
s
y
ste
m
i
m
m
u
n
e
to
sp
o
o
f
in
g
a
tt
a
c
k
s,”
IET
Bi
o
me
tr
ics
,
v
o
l.
5
,
n
o
.
3
,
p
p
.
2
3
6
–
2
4
2
,
2
0
1
6
.
[7
2
]
J.
Ko
m
u
lain
e
n
,
A
.
Ha
d
id
,
M
.
P
iet
ik
a
in
e
n
,
A
.
A
n
jo
s,
a
n
d
S
.
M
a
rc
e
l,
“
Co
m
p
le
m
e
n
tar
y
c
o
u
n
term
e
a
su
r
e
s
f
o
r
d
e
tec
ti
n
g
sc
e
n
ic f
a
c
e
sp
o
o
f
in
g
a
tt
a
c
k
s,” in
Pro
c
e
e
d
in
g
s
-
2
0
1
3
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Bi
o
me
trics
,
ICB
2
0
1
3
,
2
0
1
3
.
[7
3
]
M
.
Kill
i
o
ǧ
lu
,
M
.
T
a
şk
iran
,
a
n
d
N.
Ka
h
ra
m
a
n
,
“
A
n
ti
-
sp
o
o
f
in
g
in
f
a
c
e
re
c
o
g
n
it
io
n
w
it
h
li
v
e
n
e
ss
d
e
tec
ti
o
n
u
sin
g
p
u
p
i
l
trac
k
in
g
,
”
in
S
AM
I
2
0
1
7
-
IEE
E
1
5
t
h
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
Ap
p
li
e
d
M
a
c
h
in
e
I
n
telli
g
e
n
c
e
a
n
d
In
f
o
rm
a
ti
c
s,
Pro
c
e
e
d
in
g
s
,
2
0
1
7
,
p
p
.
8
7
–
92.
[7
4
]
A.
M
a
u
r
y
a
a
n
d
S
.
T
a
ra
r,
“
S
p
o
o
f
e
d
V
i
d
e
o
De
tec
ti
o
n
Us
in
g
Histo
g
r
a
m
o
f
Orie
n
ted
G
ra
d
ien
ts,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
T
h
ird
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
Co
m
p
u
ter
Vi
si
o
n
a
n
d
t
h
e
In
ter
n
e
t
-
Vi
sio
n
Ne
t’1
6
,
2
0
1
6
,
p
p
.
1
–
7.
[7
5
]
A
.
A
li
,
F
.
De
ra
v
i,
a
n
d
S
.
Ho
q
u
e
,
“
L
iv
e
n
e
ss
d
e
tec
ti
o
n
u
sin
g
g
a
z
e
c
o
ll
in
e
a
rit
y
,
”
in
Pro
c
e
e
d
in
g
s
-
3
r
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Eme
rg
in
g
S
e
c
u
rity T
e
c
h
n
o
lo
g
ies
,
ES
T
2
0
1
2
,
2
0
1
2
,
p
p
.
6
2
–
6
5
.
[7
6
]
A
.
A
li
,
F
.
De
ra
v
i,
a
n
d
S
.
Ho
q
u
e
,
“
Dire
c
ti
o
n
a
l
se
n
siti
v
it
y
o
f
g
a
z
e
-
c
o
ll
in
e
a
rit
y
fe
a
tu
re
s
in
li
v
e
n
e
ss
d
e
tec
ti
o
n
,
”
in
Pro
c
e
e
d
i
n
g
s
-
2
0
1
3
4
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Eme
rg
in
g
S
e
c
u
rity T
e
c
h
n
o
lo
g
ies
,
E
S
T
2
0
1
3
,
2
0
1
3
,
p
p
.
8
–
1
1
.
[7
7
]
A
.
A
sa
d
u
z
z
a
m
a
n
,
A
.
M
u
m
m
id
i,
M
.
F
.
M
rid
h
a
,
a
n
d
F
.
N.
S
ib
a
i
,
“
Im
p
ro
v
in
g
f
a
c
ial
re
c
o
g
n
it
io
n
a
c
c
u
ra
c
y
b
y
a
p
p
l
y
in
g
li
v
e
n
e
ss
m
o
n
it
o
rin
g
tec
h
n
iq
u
e
,
”
in
Pro
c
e
e
d
in
g
s
o
f
2
0
1
5
3
r
d
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
s
in
El
e
c
trica
l
En
g
i
n
e
e
rin
g
,
ICAE
E
2
0
1
5
,
2
0
1
6
,
p
p
.
1
3
3
–
1
3
6
.
[7
8
]
J.
Ca
o
,
H.
L
i,
Z.
S
u
n
,
a
n
d
R.
He
,
“
A
c
c
u
ra
te
m
o
u
th
sta
te
e
stim
a
ti
o
n
v
ia
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
tw
o
rk
s,”
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
D
ig
it
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
,
DS
P
,
2
0
1
7
,
p
p
.
1
3
4
–
1
3
8
.
[7
9
]
Z.
L
u
,
X
.
W
u
,
a
n
d
R
.
He
,
“
P
e
rs
o
n
i
d
e
n
ti
f
ica
ti
o
n
f
ro
m
li
p
tex
tu
re
a
n
a
ly
sis,”
in
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Dig
it
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
,
DS
P
,
2
0
1
7
,
p
p
.
4
7
2
–
4
7
6
.
[8
0
]
A
.
K.
S
in
g
h
,
P
.
J
o
sh
i,
a
n
d
G
.
C.
Na
n
d
i,
“
F
a
c
e
re
c
o
g
n
it
io
n
w
it
h
li
v
e
n
e
ss
d
e
tec
ti
o
n
u
si
n
g
e
y
e
a
n
d
m
o
u
th
m
o
v
e
m
e
n
t,
”
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
Pro
p
a
g
a
ti
o
n
a
n
d
Co
mp
u
ter
T
e
c
h
n
o
l
o
g
y
(
ICS
PCT
)
,
2
0
1
4
,
p
p
.
5
9
2
–
5
9
7
.
[8
1
]
M
.
De
M
a
rsic
o
,
C.
Ga
ld
i,
M
.
Na
p
p
i,
a
n
d
D.
Ricc
io
,
“
F
IRM
E:
F
a
c
e
a
n
d
iri
s
re
c
o
g
n
it
io
n
f
o
r
m
o
b
il
e
e
n
g
a
g
e
m
e
n
t,
”
Ima
g
e
Vi
s.
C
o
mp
u
t
.
,
v
o
l.
3
2
,
n
o
.
1
2
,
p
p
.
1
1
6
1
–
1
1
7
2
,
2
0
1
4
.
[8
2
]
A
.
Lag
o
rio
,
M
.
T
istare
ll
i,
M
.
Ca
d
o
n
i,
C
.
F
o
o
k
e
s,
a
n
d
S
.
S
r
id
h
a
ra
n
,
“
L
iv
e
n
e
ss
d
e
tec
ti
o
n
b
a
se
d
o
n
3
D
f
a
c
e
sh
a
p
e
a
n
a
ly
sis,”
in
2
0
1
3
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
Bi
o
me
trics
a
n
d
Fo
r
e
n
sic
s (
IW
BF
)
,
2
0
1
3
,
p
p
.
1
–
4.
[8
3
]
T
.
W
a
n
g
,
J.
Ya
n
g
,
Z.
L
e
i,
S
.
L
iao
,
a
n
d
S
.
Z.
L
i,
“
F
a
c
e
li
v
e
n
e
ss
d
e
te
c
ti
o
n
u
sin
g
3
D
stru
c
t
u
re
re
c
o
v
e
re
d
f
ro
m
a
sin
g
le
c
a
m
e
ra
,
”
in
Pro
c
e
e
d
in
g
s
-
2
0
1
3
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Bi
o
m
e
trics
,
ICB
2
0
1
3
,
2
0
1
3
.
[8
4
]
X.
-
J.
C
h
a
i,
“
P
o
se
a
n
d
Ill
u
m
in
a
ti
o
n
I
n
v
a
rian
t
F
a
c
e
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
3
D
F
a
c
e
Re
c
o
n
stru
c
ti
o
n
,
”
J
.
S
o
ft
w
.,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
5
2
5
,
2
0
0
6
.
[8
5
]
T
.
Ed
m
u
n
d
s
a
n
d
A
.
Ca
p
li
e
r,
“
F
a
k
e
f
a
c
e
d
e
tec
ti
o
n
b
a
se
d
o
n
ra
d
io
m
e
tri
c
d
isto
rti
o
n
s,”
in
2
0
1
6
6
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ima
g
e
Pro
c
e
ss
in
g
T
h
e
o
ry
,
T
o
o
l
s
a
n
d
A
p
p
li
c
a
ti
o
n
s,
I
PT
A
2
0
1
6
,
2
0
1
7
.
[8
6
]
W
.
Ki
m
,
S
.
S
u
h
,
a
n
d
J.
Ha
n
,
“
F
a
c
e
L
iv
e
n
e
ss
De
tec
ti
o
n
F
ro
m
a
S
in
g
le
Im
a
g
e
v
ia
Di
ff
u
sio
n
S
p
e
e
d
M
o
d
e
l,
”
IEE
E
T
ra
n
s.
Im
a
g
e
Pr
o
c
e
ss
.
,
v
o
l.
2
4
,
n
o
.
8
,
p
p
.
2
4
5
6
–
2
4
6
5
,
2
0
1
5
.
[8
7
]
A
.
P
in
to
,
S
.
M
e
m
b
e
r,
H.
P
e
d
rin
i,
a
n
d
S
.
M
e
m
b
e
r,
“
F
a
c
e
S
p
o
o
f
in
g
De
tec
ti
o
n
T
h
ro
u
g
h
V
is
u
a
l
Co
d
e
b
o
o
k
s o
f
S
p
e
c
tral
T
e
m
p
o
ra
l
Cu
b
e
s,” v
o
l.
X
,
n
o
.
De
c
e
m
b
e
r
,
p
p
.
1
–
1
5
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.