I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
23
,
No
.
2
,
A
u
g
u
s
t
20
21
,
p
p
.
7
91
~
8
0
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
23
.i
2
.
pp
7
91
-
8
0
1
791
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Co
mpa
riso
n of le
v
els a
nd f
usio
n ap
pro
a
ches for mul
t
imo
da
l
bio
metrics
S.
Su
j
a
na
1
,
V
.
S
.
K
.
Reddy
2
1
De
p
a
rtme
n
t
of
ECE
,
Ja
wa
h
a
rlal
Ne
h
ru
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsity
,
Hy
d
e
ra
b
a
d
,
I
n
d
ia
1
De
p
a
rtme
n
t
of
ECE
,
Va
rd
h
a
m
a
n
Co
ll
e
g
e
of
E
n
g
i
n
e
e
rin
g
,
Hy
d
e
ra
b
a
d
,
Tela
n
g
a
n
a
,
In
d
ia
2
De
p
a
rtme
n
t
of
ECE
,
M
a
ll
a
Re
d
d
y
Un
i
v
e
rsity
,
Hy
d
e
ra
b
a
d
,
I
n
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
1
8
,
2
0
2
1
R
ev
is
ed
May
26
,
2
0
2
1
Acc
ep
ted
J
u
n
1
,
2
0
2
1
Th
e
b
io
m
e
tri
c
-
b
a
se
d
a
u
t
h
e
n
ti
c
a
ti
o
n
sy
ste
m
o
c
c
u
p
ies
m
a
x
ima
l
sp
a
c
e
in
th
e
field
of
se
c
u
rit
y
a
d
m
in
istrati
o
n
.
Bio
m
e
tri
c
a
p
p
li
c
a
ti
o
n
s
a
r
e
sw
ift
ly
a
c
c
e
ler
a
ti
n
g
in
d
a
y
-
to
-
d
a
y
li
fe
su
c
h
as
c
o
m
p
u
ter
lo
g
i
n
,
sm
a
rt
h
o
m
e
s,
o
n
li
n
e
b
a
n
k
i
n
g
,
h
o
s
p
it
a
ls,
b
o
rd
e
r
a
re
a
s,
in
d
u
str
ies
,
f
o
re
n
sic
s,
e
-
v
o
ti
n
g
a
tt
e
n
d
a
n
c
e
sy
ste
m
a
n
d
i
n
v
e
stig
a
ti
o
n
of
c
rime
.
A
re
li
a
b
le
a
n
d
a
c
c
u
ra
te
re
c
o
g
n
it
io
n
b
o
d
y
can
be
a
c
h
iev
e
d
with
m
u
lt
imo
d
a
l
b
io
m
e
tri
c
m
e
th
o
d
o
l
o
g
ies
.
In
th
is
p
a
p
e
r,
we
d
isc
u
ss
sta
rti
n
g
wit
h
an
in
tr
o
d
u
c
t
io
n
to
b
i
o
m
e
tri
c
sy
ste
m
s
fo
l
lo
we
d
b
y
t
h
e
ir
c
las
sifica
ti
o
n
,
a
n
d
a
d
v
a
n
ta
g
e
s
as
we
ll
as
d
isa
d
v
a
n
tag
e
s.
In
to
d
a
y
’s
wo
rld
,
m
o
st
of
t
h
e
sy
ste
m
s
a
re
u
n
imo
d
a
l
b
io
m
e
tri
c
s
h
a
v
in
g
a
l
o
t
of
li
m
it
a
ti
o
n
s
to
o
v
e
rc
o
m
e
th
o
se
m
u
lt
imo
d
a
l
b
i
o
m
e
tri
c
s
c
o
m
e
s
in
to
p
ictu
re
.
In
t
h
is
p
a
p
e
r
we
h
a
v
e
d
isc
u
ss
e
d
c
o
m
p
re
h
e
n
siv
e
r
e
p
re
se
n
tatio
n
on
t
h
e
sy
ste
m
of
m
u
lt
imo
d
a
l
b
io
m
e
tri
c
,
v
a
rio
u
s
m
o
d
e
s
of
u
n
d
e
rtak
in
g
s,
t
h
e
sig
n
ifi
c
a
n
c
e
of
i
n
fo
rm
a
ti
o
n
fu
sio
n
,
a
d
iffere
n
t
se
c
ti
o
n
is
a
ll
o
t
ted
on
t
h
e
v
a
ri
o
u
s
p
o
ss
ib
le
lev
e
ls
of
fu
sio
n
in
v
o
lv
i
n
g
se
n
s
o
r
-
lev
e
l,
fe
a
tu
re
-
le
v
e
l,
sc
o
re
-
lev
e
l,
a
n
d
d
e
c
isio
n
-
le
v
e
l
as
we
l
l
as
d
iffere
n
t
ru
les
of
f
u
sio
n
.
K
ey
w
o
r
d
s
:
B
io
m
etr
ic
r
ec
o
g
n
itio
n
B
io
m
etr
ic
au
th
en
ticatio
n
Un
im
o
d
al
Fu
s
io
n
lev
els
Mu
ltimo
d
al
b
io
m
etr
ic
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
:
S.
Su
jan
a
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
E
n
g
in
ee
r
i
n
g
R
esear
ch
Sch
o
lar
,
J
awa
h
ar
lal
Neh
r
u
T
ec
h
n
o
lo
g
ical
Un
iv
er
s
ity
,
Hy
d
er
a
b
ad
,
I
n
d
ia
E
m
ail:
s
u
jan
asu
r
in
en
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
B
io
m
etr
ics
is
a
way
to
m
ea
s
u
r
e
a
p
er
s
o
n
’
s
p
h
y
s
ical
ch
ar
ac
te
r
is
tics
to
au
th
en
ticate
th
eir
id
en
tity
.
T
h
e
d
o
m
in
an
t t
h
em
e
o
f
th
e
b
io
m
etr
ic
au
th
en
ticatio
n
s
y
s
tem
is
to
id
en
tify
an
i
n
d
iv
id
u
al
b
ased
o
n
th
eir
u
n
iq
u
e
tr
aits
(
p
h
y
s
ical
o
r
b
eh
av
io
r
al)
[
1
]
.
T
h
e
in
d
iv
id
u
al
b
eh
a
v
i
o
r
al
ch
a
r
a
cter
is
tic
co
n
tain
s
h
o
w
th
e
p
er
s
o
n
u
n
i
q
u
e
q
u
alities
lik
e
allies
an
d
ac
tio
n
,
s
u
c
h
as
th
eir
u
tter
ed
m
an
n
e
r
,
b
o
d
y
p
a
n
to
m
im
e,
s
ig
n
atu
r
e
an
d
v
o
ice.
T
h
e
p
h
y
s
io
lo
g
ical
class
y
ield
s
p
h
y
s
ical
b
ein
g
’
s
attr
ib
u
tes
s
u
ch
as
p
alm
p
r
in
t,
f
ac
e,
ir
is
,
f
in
g
er
p
r
in
ts
,
an
d
m
a
n
y
m
o
r
e
.
T
o
f
i
g
u
r
e
o
u
t
th
ese
attr
ib
u
tes
ass
is
t
s
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
u
s
in
g
th
e
b
io
m
etr
ic
ad
m
in
is
tr
atio
n
[
2
]
.
C
o
n
v
en
tio
n
al
id
en
tific
atio
n
ap
p
r
o
ac
h
es
d
if
f
er
en
tiate
p
eo
p
le
b
ased
o
n
s
u
s
ce
p
tib
le
p
ass
wo
r
d
s
o
r
m
ag
n
et
ic/I
D
ca
r
d
s
.
T
h
ese
k
ey
id
en
tifie
r
s
ar
e
p
r
o
n
e
to
m
is
u
tili
za
tio
n
b
y
u
n
au
th
o
r
ized
p
er
s
o
n
s
o
n
ce
th
ey
h
av
e
th
em
in
h
an
d
[
3
]
.
C
o
m
m
o
n
is
s
u
es
wi
th
th
e
c
o
n
v
en
tio
n
al
ap
p
r
o
ac
h
es
ar
e
s
tealin
g
,
f
o
r
g
ettin
g
,
lo
s
in
g
,
w
h
ich
m
ak
e
it
ca
p
r
icio
u
s
an
d
u
n
s
o
u
n
d
in
th
e
im
m
en
s
ely
ac
c
u
r
ate
s
y
s
tem
lik
e
b
an
k
s
,
f
o
r
e
n
s
i
cs,
an
d
p
o
r
ts
s
y
s
tem
s
[
4
]
.
I
n
th
is
g
en
er
atio
n
,
t
h
er
e
is
a
d
iv
er
s
if
ied
ex
p
er
ie
n
ce
th
at
p
eo
p
le
n
ee
d
to
v
alid
ate
th
em
s
elv
es.
Valid
atio
n
is
a
p
r
o
ce
s
s
to
g
o
v
er
n
th
at
s
o
m
eb
o
d
y
is
ce
r
tain
ly
th
e
p
er
s
o
n
th
at
h
e
p
r
o
cla
im
ed
to
b
e
o
r
n
o
t.
Pre
d
o
m
in
an
tly
,
th
er
e
ar
e
t
h
r
e
e
ty
p
es
o
f
v
alid
atio
n
th
e
y
ar
e
s
o
m
eth
in
g
y
o
u
k
n
o
w
(
p
ass
wo
r
d
)
s
ec
o
n
d
o
n
e
s
o
m
eth
in
g
y
o
u
h
av
e
(
to
k
en
)
,
an
d
th
e
f
in
al
o
n
e
is
s
o
m
eth
in
g
y
o
u
a
r
e
[
5
]
,
[
6
]
.
Peo
p
le
ca
n
v
alid
ate
th
e
m
s
elv
es
with
o
u
t
r
em
e
m
b
er
in
g
th
e
in
tr
i
ca
te
m
ix
o
r
c
ar
r
y
an
y
im
p
lem
en
t.
Peo
p
le
n
ee
d
o
n
ly
th
ei
r
att
r
ib
u
tes
to
v
alid
ate
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
7
91
-
8
0
1
792
th
em
s
elv
es,
f
o
r
ex
am
p
le
,
th
ei
r
f
in
g
e
r
p
r
in
t
,
ey
es,
r
etin
a
a
n
d
h
an
d
[
7
]
.
T
h
is
ty
p
e
o
f
au
th
e
n
ticatio
n
m
eth
o
d
is
ca
lled
b
io
m
etr
ics.
T
h
e
f
o
r
em
o
s
t
ad
v
a
n
tag
e
of
b
i
o
m
etr
ics
wh
en
co
m
p
ar
e
d
to
o
th
er
m
eth
o
d
s
,
it
ca
n
n
o
t
be
v
a
n
is
h
ed
or
s
to
len
.
Du
e
to
th
e
s
k
y
-
s
cr
ap
i
n
g
p
er
f
o
r
m
a
n
ce
of
b
i
o
m
etr
ic
s
,
it
b
ec
am
e
an
ess
en
tial
an
d
p
r
ef
er
r
ed
o
n
e
to
u
n
d
er
s
tan
d
an
d
in
te
r
p
r
et
h
u
m
an
attr
ib
u
tes
f
o
r
s
ec
u
r
ity
.
T
h
is
m
ak
es
s
p
o
o
f
in
g
d
if
f
icu
lt
[
8
]
.
T
h
is
p
ap
er
elab
o
r
ates
on
two
ty
p
es
of
b
i
o
m
etr
ic
s
y
s
tem
s
n
am
ely
m
u
lt
im
o
d
al
an
d
u
n
im
o
d
al,
f
o
c
u
s
t
h
e
is
s
u
es
r
elate
d
to
u
n
im
o
d
al
s
y
s
tem
s
.
Fo
llo
win
g
s
ec
tio
n
s
of
th
is
p
ap
er
:
s
ec
tio
n
2,
d
escr
ib
es
r
ev
iew
cr
iter
i
a;
s
ec
tio
n
3
is
th
e
p
r
o
ce
s
s
in
v
o
l
v
ed
in
a
g
en
e
r
al
b
io
m
etr
ic
s
y
s
tem
.
Sectio
n
4
ta
lk
s
ab
o
u
t
th
e
class
if
icatio
n
of
b
io
m
etr
ic
s
y
s
tem
s
.
Sectio
n
5
d
is
cu
s
s
ed
th
e
lev
el
s
of
f
u
s
io
n
in
m
u
ltimo
d
al
s
y
s
tem
s
,
wh
ile
s
ec
tio
n
6,
h
ig
h
lig
h
ts
th
e
m
eth
o
d
s
of
f
u
s
io
n
in
m
u
ltimo
d
al
b
i
o
m
etr
i
cs,
s
ec
tio
n
7
d
is
cu
s
s
io
n
,
an
d
s
ec
tio
n
9
co
n
clu
d
es
th
is
p
ap
e
r
.
2.
RE
VI
E
W
C
RI
T
E
R
I
A
C
h
en
et
a
l.
[
9
]
s
u
g
g
ested
a
c
o
m
p
r
eh
e
n
s
iv
e
f
ac
e
tem
p
late
p
r
o
tectio
n
s
ch
em
e
to
s
ec
u
r
e
t
h
e
o
r
ig
in
al
f
ac
e
tem
p
late.
T
h
e
f
ac
ial
f
ea
tu
r
e
o
f
ea
ch
is
m
ap
p
ed
to
a
d
if
f
e
r
en
t b
in
ar
y
c
o
d
e
in
th
e
tr
ain
in
g
u
s
in
g
d
ee
p
m
u
lti
-
lab
el
lear
n
in
g
.
I
n
t
h
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
,
C
NN
o
u
tp
u
t
is
d
ec
o
d
ed
with
a
n
L
DPC
d
ec
o
d
er
t
o
s
u
p
p
r
ess
Gau
s
s
ian
n
o
is
e
ca
u
s
ed
b
y
in
t
r
a
-
v
ar
iatio
n
s
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
h
ig
h
e
r
GARs
co
u
ld
b
e
ac
h
iev
ed
b
y
t
h
e
p
r
o
p
o
s
ed
s
ch
em
e.
T
o
e
n
h
an
ce
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
tem
,
it
ca
n
n
o
t
m
ap
th
e
f
ac
i
al
f
ea
tu
r
es
to
h
ig
h
-
d
im
en
s
io
n
al
L
DPC
co
d
es.
Ham
d
an
d
Ah
m
e
d
[
1
0
]
im
p
l
em
en
ted
a
n
ir
is
r
ec
o
g
n
itio
n
s
y
s
tem
b
y
u
s
in
g
two
ap
p
r
o
a
ch
es:
i.e
.
,
p
r
in
cip
al
c
o
m
p
o
n
en
t
a
n
aly
s
is
an
d
Fo
u
r
ier
d
escr
ip
to
r
s
.
I
n
Fo
u
r
ier
d
escr
ip
t
o
r
s
,
ir
is
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
in
t
h
e
f
r
eq
u
e
n
cy
d
o
m
ain
(
FD)
.
Statis
tic
tech
n
iq
u
e
u
s
ed
b
y
th
e
p
r
i
n
cip
al
co
m
p
o
n
en
t
an
al
y
s
is
to
s
elec
t
th
e
im
p
o
r
tan
t
f
ea
tu
r
e
v
al
u
es
f
o
r
r
ed
u
ci
n
g
d
im
en
s
io
n
ality
an
d
f
in
ally
t
h
r
ee
v
ar
io
u
s
d
is
tan
ce
m
ea
s
u
r
em
en
t
m
eth
o
d
s
u
s
ed
f
o
r
co
m
p
ar
is
o
n
.
I
n
m
atch
in
g
r
esu
l
ts
alwa
y
s
Fo
u
r
ier
d
escr
ip
to
r
s
wer
e
ad
v
an
ce
d
with
9
6
%,
9
4
%,
an
d
8
6
%
co
r
r
ec
t
m
atch
in
g
ag
ain
s
t
9
4
%,
9
2
%,
an
d
8
0
%
f
o
r
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
u
s
in
g
Ma
n
h
att
an
,
E
u
clid
ea
n
,
an
d
C
o
s
in
e
clas
s
if
ier
s
,
r
esp
ec
tiv
el
y
.
T
h
ey
co
n
clu
d
ed
th
at
Ma
n
h
attan
ac
h
iev
es
th
e
b
est
r
esu
lts
f
r
o
m
E
u
clid
ea
n
a
n
d
C
o
s
in
e
in
FD a
n
d
PC
A.
Am
m
o
u
r
et
a
l.
[
1
1
]
p
r
o
p
o
s
ed
a
m
u
ltimo
d
al
s
ch
em
e
f
o
r
b
io
m
etr
ic
au
th
e
n
ticatio
n
b
ased
o
n
th
e
i
r
is
an
d
f
ac
e.
T
h
e
y
u
s
ed
f
u
s
io
n
a
t
s
co
r
e
lev
el
with
d
if
f
er
en
t
f
u
s
io
n
r
u
les
n
o
r
m
aliza
tio
n
tec
h
n
iq
u
es.
Face
OR
L
d
atab
ase
an
d
C
ASI
A
-
V3
-
I
n
te
r
v
al
d
ata
b
ase
u
s
ed
to
v
alid
at
e
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
T
h
e
r
esu
lts
s
h
o
wed
th
at
th
eir
p
r
o
p
o
s
ed
o
p
tim
al
s
y
s
tem
h
av
in
g
a
g
o
o
d
r
ec
o
g
n
itio
n
r
at
e
o
f
9
8
%.
Am
m
o
u
r
et
a
l.
[
1
2
]
a
m
u
lti
-
m
o
d
al
f
ac
e
-
i
r
is
f
r
am
ewo
r
k
b
a
s
ed
o
n
tex
tu
r
e
in
f
o
r
m
atio
n
u
s
i
n
g
2
D
L
o
g
Gab
o
r
f
ilter
in
co
m
b
i
n
atio
n
with
s
p
ec
tr
al
r
eg
r
ess
io
n
k
er
n
el
d
is
cr
im
in
an
t
an
aly
s
is
(
SR
KDA)
is
p
r
o
p
o
s
ed
to
ex
tr
ac
t
f
ea
tu
r
es
an
d
m
i
n
im
ize
th
e
d
im
en
s
io
n
ality
o
f
t
h
e
e
x
tr
ac
ted
f
ea
tu
r
es
f
r
o
m
m
o
d
al
ities
.
T
h
ey
s
elec
ted
h
y
b
r
id
-
lev
el
f
u
s
io
n
to
ex
t
r
ac
t
th
e
ad
v
a
n
tag
es
o
f
d
if
f
er
e
n
t
f
u
s
io
n
s
an
d
u
s
in
g
d
atab
ase
C
ASI
A
I
r
is
Dis
tan
ce
ac
h
iev
ed
u
p
to
0
.
2
4
% im
p
r
o
v
e
m
en
t o
f
E
E
R
wh
e
n
co
m
p
ar
ed
to
th
e
u
n
im
o
d
al
Su
jan
a
an
d
R
ed
d
y
[
1
3
]
d
ev
e
lo
p
ed
th
e
o
p
tim
al
m
u
ltim
o
d
a
l
d
ev
ice
f
o
r
ir
is
an
d
f
ac
e
b
y
p
r
o
p
e
r
ly
ch
o
o
s
in
g
f
ea
tu
r
es
an
d
s
co
r
es
t
h
ese
o
p
tim
ized
tr
ait
d
ata
af
f
ec
t
th
e
ef
f
icien
c
y
o
f
th
e
d
ev
ice.
At
d
if
f
er
en
t
f
u
s
io
n
s
tag
es,
th
ey
an
aly
ze
d
s
ev
er
a
l
tech
n
iq
u
es
to
f
in
d
an
e
f
f
e
ctiv
e
tech
n
iq
u
e
f
o
r
m
e
r
g
in
g
f
ac
e
an
d
ir
is
th
en
in
teg
r
atin
g
th
e
ad
v
a
n
tag
es
o
f
m
u
ltip
le
f
u
s
io
n
tech
n
iq
u
es
to
cr
ea
te
a
s
tab
le
co
m
b
in
ed
d
ev
ice.
C
ASI
A
I
r
is
Dis
tan
ce
Data
b
ase
v
er
if
icatio
n
r
esu
lts
with
GAR
=
9
3
.
9
1
p
er
ce
n
t
with
FAR
=
0
.
0
1
p
er
ce
n
t.
Sh
o
win
g
m
ajo
r
ad
v
an
ce
s
o
v
e
r
u
n
im
o
d
al
a
n
d
m
u
ltimo
d
al
f
u
s
io
n
m
eth
o
d
s
in
th
e
s
u
g
g
ested
m
ix
e
d
f
u
s
io
n
s
ch
em
e
Ma
tin
et
a
l.
[
1
4
]
Selecte
d
a
f
u
s
io
n
m
eth
o
d
f
o
r
th
e
weig
h
ted
s
co
r
e
lev
el
in
a
m
u
ltimo
d
al
b
io
m
etr
ic
s
y
s
tem
to
co
m
b
in
e
ir
is
an
d
f
ac
e
s
co
r
es.
T
h
ey
em
p
lo
y
ed
Dau
g
m
an
’
s
tech
n
iq
u
e
f
o
r
I
r
i
s
r
ec
o
g
n
itio
n
a
n
d
th
e
PC
A
tech
n
iq
u
e
f
o
r
f
ac
e
r
ec
o
g
n
itio
n
.
T
h
ey
u
s
ed
th
e
Min
-
m
ax
n
o
r
m
aliza
tio
n
tech
n
iq
u
e
to
b
alan
ce
th
e
f
ac
ial
an
d
ir
is
s
co
r
es.
Fin
ally
,
to
co
m
b
in
e
th
eir
n
o
r
m
alize
d
s
co
r
e
s
weig
h
ted
s
u
m
r
u
le
was
u
s
e
d
.
T
h
is
will
p
r
o
v
id
e
b
etter
r
esu
lts
th
an
a
u
n
im
o
d
al
s
y
s
tem
.
Azo
m
et
a
l.
[
1
5
]
h
av
e
p
r
esen
t
ed
a
h
y
b
r
i
d
f
u
s
io
n
p
r
o
ce
s
s
b
y
co
m
b
in
in
g
th
r
ee
lev
els
o
f
f
u
s
io
n
s
u
ch
as
f
ea
tu
r
e,
s
co
r
e,
a
n
d
d
ec
is
io
n
u
s
in
g
d
ec
is
io
n
r
u
le.
T
o
g
et
th
e
f
u
s
ed
class
if
ier
s
,
th
ey
p
e
r
f
o
r
m
ed
a
f
ea
tu
r
e
-
lev
el
f
u
s
io
n
f
o
r
th
e
f
ac
e
a
n
d
I
r
is
.
T
h
en
th
e
weig
h
te
d
f
u
s
io
n
o
f
th
e
s
co
r
e
lev
el
b
etwe
en
f
ac
e
L
DA
an
d
I
r
is
u
s
in
g
L
B
PH,
b
u
t
in
d
iv
id
u
al
m
o
d
alit
ies
g
en
er
ated
th
e
h
ig
h
est
r
ec
o
g
n
itio
n
r
ate.
T
h
e
y
o
b
tain
e
d
a
9
8
.
7
5
%
r
ec
o
g
n
itio
n
r
ate
wh
en
v
alid
ated
u
s
in
g
th
e
C
ASI
A
ir
is
an
d
OR
L
f
ac
e.
Hu
o
et
a
l.
[
1
6
]
estab
lis
h
ed
a
Mu
lti
-
m
o
d
al
s
y
s
tem
o
f
f
ea
tu
r
e
lev
el
f
ac
e
-
ir
is
.
2
D
Gab
o
r
f
ilter
b
an
k
u
s
ed
to
ex
tr
ac
t
t
h
e
f
ea
tu
r
es
o
f
b
o
th
th
e
m
o
d
alities
,
th
ese
f
ea
t
u
r
es
ar
e
co
n
v
er
ted
u
s
in
g
h
is
to
g
r
am
s
tatis
tics
.
T
h
e
f
u
s
io
n
r
ec
o
g
n
itio
n
d
ep
e
n
d
s
o
n
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
an
d
p
r
in
cip
al
co
m
p
o
n
e
n
ts
an
aly
s
is
.
T
h
eir
r
esu
lts
s
h
o
w
th
at
it e
f
f
ec
tiv
ely
ex
tr
ac
ts
ir
is
an
d
f
ac
e
f
ea
tu
r
es a
s
well
as o
f
f
er
s
h
ig
h
er
ac
cu
r
ac
y
o
f
i
d
en
tif
icatio
n
.
E
s
k
an
d
ar
i
an
d
T
o
y
g
ar
Ö
[
1
7
]
p
r
o
p
o
s
ed
a
f
r
am
ewo
r
k
f
o
r
ir
is
-
f
ac
e
m
o
d
alities
b
ased
o
n
s
co
r
e
an
d
f
ea
tu
r
e
-
lev
el
f
u
s
io
n
.
T
o
g
et
th
e
ir
is
f
ea
tu
r
es
ir
is
1
D
L
o
g
-
Gab
o
r
f
ilter
was
u
s
ed
an
d
a
b
ac
k
tr
ac
k
in
g
s
ea
r
ch
alg
o
r
ith
m
(
B
SA)
is
u
s
ed
to
o
b
tain
th
e
o
p
tim
ized
f
ea
tu
r
es
u
s
ed
in
f
ea
t
u
r
e
lev
el
f
u
s
io
n
an
d
o
p
tim
ize
d
weig
h
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
mp
a
r
is
o
n
o
f le
ve
ls
a
n
d
fu
s
i
o
n
a
p
p
r
o
a
ch
es fo
r
mu
ltimo
d
a
l b
io
metrics
(
S.
S
u
ja
n
a
)
793
ass
ig
n
ed
to
s
co
r
es
in
s
co
r
e
l
ev
el
f
u
s
io
n
to
ac
h
iev
e
an
ef
f
icien
t
au
th
e
n
ticatio
n
s
y
s
tem
at
th
e
f
ea
tu
r
e
a
n
d
m
atch
in
g
s
co
r
e
lev
els.
I
n
c
o
n
tr
ast
with
u
n
im
o
d
al
an
d
o
th
er
m
u
ltimo
d
al
m
eth
o
d
s
,
a
m
ajo
r
in
cr
ea
s
e
in
id
en
tific
atio
n
was
ac
h
iev
ed
.
Kh
iar
i
-
Hili
et
a
l.
[
1
8
]
s
u
g
g
e
s
ted
a
m
u
lti
-
m
o
d
al
s
y
s
tem
u
s
in
g
ir
is
an
d
f
ac
e.
T
h
ey
ex
p
lo
r
ed
tw
o
ap
p
r
o
ac
h
es
f
o
r
co
m
b
in
in
g
th
e
s
co
r
es
at
s
co
r
e
-
lev
el
f
u
s
io
n
.
I
n
itially
,
A
s
in
g
le
jo
in
t
q
u
ality
m
etr
ic
o
f
a
g
aller
y
-
p
r
o
b
e
co
m
p
ar
is
o
n
b
ased
o
n
ir
is
o
cc
lu
s
io
n
.
T
h
en
,
th
ey
p
lace
d
in
th
e
weig
h
te
d
s
u
m
f
u
s
io
n
to
d
y
n
am
ically
co
n
tr
o
l
th
e
weig
h
ts
.
T
h
e
f
u
s
io
n
r
u
le
in
cr
ea
s
es
p
r
o
tectio
n
b
y
r
e
d
u
cin
g
er
r
o
r
r
a
tes
in
u
n
co
n
tr
o
lled
en
v
ir
o
n
m
en
ts
co
m
p
ar
ed
to
s
u
m
an
d
weig
h
ted
s
u
m
laws
b
y
two
s
u
g
g
ested
q
u
ality
m
etr
ic
s
tr
ateg
ies.
T
h
ey
s
u
g
g
ested
a
f
r
am
ewo
r
k
o
n
th
e
MBGC
d
atab
ase
in
th
e
f
u
tu
r
e
with
m
o
r
e
q
u
ality
m
ea
s
u
r
es r
e
lated
to
f
ac
e.
Min
ae
e
et
a
l.
[
1
9
]
d
ev
elo
p
ed
a
f
ac
e
r
ec
o
g
n
itio
n
s
y
s
tem
b
ased
o
n
s
ca
tter
in
g
co
n
v
o
lu
tio
n
al
ar
ch
itectu
r
e,
s
ca
tter
in
g
tr
an
s
f
o
r
m
tech
n
iq
u
e
f
o
r
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
an
d
SVM
f
o
r
class
if
icatio
n
.
Ho
wev
er
,
Scale
-
in
v
ar
ian
t scatter
ed
f
ea
tu
r
es c
an
b
e
u
s
ed
f
o
r
im
p
r
o
v
em
en
t in
ac
cu
r
ac
y
,
wh
ich
th
e
y
d
id
n
’
t u
s
e
h
er
e.
Sh
ar
if
i
an
d
E
s
k
an
d
ar
i
[
2
0
]
h
a
v
e
en
lig
h
ten
ed
u
s
with
th
e
f
ac
ts
o
f
th
r
ee
f
u
s
io
n
s
lev
els
(
f
ea
t
u
r
e,
s
co
r
e
,
an
d
d
ec
is
io
n
)
t
o
ef
f
icien
tly
co
m
b
i
n
e
in
p
u
t
tr
aits
s
u
ch
as
f
ac
e
an
d
ir
is
.
He
h
as
u
s
ed
th
e
lo
g
-
Ga
b
o
r
tr
an
s
f
o
r
m
atio
n
f
o
r
ex
tr
ac
tio
n
o
f
ir
is
an
d
f
ac
e
f
ea
tu
r
es wh
ich
ar
e
co
m
b
in
ed
to
co
n
s
tr
u
ct
a
r
o
b
u
s
t a
n
d
o
p
tim
ized
s
ch
em
e
p
ar
ticu
lar
ly
f
u
s
io
n
at
th
e
d
ec
is
io
n
lev
el
in
th
e
p
r
o
p
o
s
ed
o
n
e.
T
o
im
p
r
o
v
e
r
ec
o
g
n
itio
n
ac
cu
r
ac
y
,
h
e
ap
p
lied
th
e
b
ac
k
tr
ac
k
in
g
Sear
ch
alg
o
r
ith
m
b
y
s
elec
tin
g
th
e
o
p
tim
ized
weig
h
ts
at
th
e
s
co
r
e
lev
el
an
d
r
ed
u
cin
g
f
ea
tu
r
es a
t f
ea
tu
r
e
le
v
el
f
u
s
io
n
.
Ah
m
ad
i
an
d
Gh
o
lam
r
ez
a
[
2
1
]
h
av
e
p
r
o
p
o
s
ed
a
m
eth
o
d
to
in
cr
ea
s
e
th
e
p
er
f
o
r
m
an
ce
b
y
h
u
m
an
r
ec
o
g
n
itio
n
s
y
s
tem
m
u
lti
-
lay
er
p
er
ce
p
t
r
o
n
-
b
ased
an
d
p
a
r
ticle
s
war
m
o
p
tim
izatio
n
,
w
h
o
s
e
co
m
b
in
atio
n
is
co
n
s
id
er
ed
as
a
class
if
ier
wh
er
e
th
e
f
ea
tu
r
es
ar
e
e
x
tr
ac
ted
u
s
in
g
th
e
2
-
D
Gab
o
r
f
ilter
an
d
th
eir
o
b
tain
ed
ac
cu
r
ac
y
was 9
5
.
3
6
wh
ic
h
is
n
o
t v
er
y
h
ig
h
as c
o
m
p
ar
e
d
to
m
an
y
m
o
d
els n
o
wad
ay
s
.
Am
m
o
u
r
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
s
y
s
tem
u
s
in
g
h
y
b
r
i
d
lev
el
f
u
s
io
n
in
wh
ich
is
a
f
ac
e
an
d
ir
i
s
as
in
p
u
t
m
o
d
alities
.
T
h
e
2
D
lo
g
Gab
o
r
f
ilter
is
u
s
ed
f
o
r
th
e
ex
tr
ac
tio
n
o
f
th
e
f
ac
e
an
d
lef
t
an
d
r
i
g
h
t
ir
is
ch
ar
ac
ter
is
tic
s
.
T
h
e
d
atab
ase
o
f
th
e
C
ASI
A
ir
is
d
is
tan
ce
is
u
s
ed
to
test
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
co
n
clu
d
ed
th
at
it a
ch
iev
es a
n
im
p
r
o
v
em
e
n
t u
p
to
0
.
2
4
% to
E
E
R
th
an
th
e
p
r
e
v
io
u
s
.
Du
a
et
a
l.
[
2
3
]
s
u
g
g
ested
a
f
ee
d
-
f
o
r
war
d
ar
c
h
itectu
r
e
an
d
u
s
es
a
k
-
m
ea
n
s
clu
s
ter
in
g
alg
o
r
ith
m
to
d
is
tin
g
u
is
h
ir
is
p
atter
n
s
.
Fo
r
ir
is
an
d
p
u
p
il b
o
u
n
d
ar
y
lo
ca
lizatio
n
,
an
in
teg
r
o
-
d
if
f
er
e
n
t
ial
o
p
er
ato
r
alo
n
g
with
a
cir
cu
lar
Ho
u
g
h
T
r
an
s
f
o
r
m
is
u
s
ed
.
Dau
g
m
a
n
r
u
b
b
e
r
s
h
ee
t
m
o
d
el
f
o
r
I
r
is
n
o
r
m
aliza
tio
n
an
d
th
e
1
D
Gab
o
r
f
ilter
to
ex
tr
ac
tin
g
f
ea
tu
r
e
.
B
u
t
th
e
s
y
s
tem
co
u
ld
n
o
t
p
er
f
o
r
m
well
u
n
d
er
v
ar
io
u
s
en
v
i
r
o
n
m
en
ts
.
T
a
b
le
1
p
r
esen
ts
th
e
liter
atu
r
e
r
elate
d
to
th
e
d
if
f
er
en
t
ex
is
tin
g
tech
n
iq
u
es
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
class
if
icatio
n
,
an
d
f
u
s
io
n
m
eth
o
d
s
at
v
ar
io
u
s
lev
e
ls
o
f
f
u
s
io
n
in
m
u
lti
-
m
o
d
el
b
io
m
etr
ics
.
T
ab
le
1
.
A
g
la
n
ce
of
ex
is
tin
g
t
ec
h
n
iq
u
es
in
m
u
lti
-
m
o
d
el
b
io
m
etr
ics
A
u
t
h
o
r
F
e
a
t
u
r
e
Ex
t
r
a
c
t
i
o
n
Le
v
e
l
of
f
u
si
o
n
F
u
si
o
n
me
t
h
o
d
/
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
(
%)
R
o
h
i
t
A
g
a
r
w
a
l
[
2
4
]
G
r
a
y
-
L
e
v
e
l
Co
-
o
c
c
u
r
r
e
n
c
e
M
a
t
r
i
x
&N
e
i
g
h
b
o
r
h
o
o
d
G
r
a
y
-
o
n
e
D
i
f
f
e
r
e
n
c
e
M
a
t
r
i
x
D
e
c
i
s
i
o
n
l
e
v
e
l
/
D
-
S
t
h
e
o
r
y
S
V
M
9
7
.
8
A
h
me
d
S
h
a
m
i
l
M
u
s
t
a
f
a
[
2
5
]
G
r
a
y
-
L
e
v
e
l
Co
-
O
c
c
u
r
r
e
n
c
e
M
a
t
r
i
x
(
G
LC
M
)
w
i
t
h
K
N
N
.
D
e
c
i
s
i
o
n
f
u
si
o
n
AND
g
a
t
e
95
Le
mm
o
u
c
h
i
M
a
n
s
o
u
r
a
[
2
6
]
.
FFT
(
f
a
c
e
,
i
r
i
s
),
S
V
D
(
f
a
c
e
,
i
r
i
s
)
S
c
o
r
e
l
e
v
e
l
M
i
n
r
u
l
e
w
i
t
h
P
r
c
t
i
l
e
n
o
r
m
a
l
i
z
a
t
i
o
n
/
Eu
c
l
i
d
e
a
n
d
i
s
t
a
n
c
e
9
8
.
3
3
,
9
4
.
1
7
J.
R
a
j
a
[
2
7
]
G
a
b
o
r
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
mat
i
o
n
ESV
M
-
KM
t
e
c
h
n
i
q
u
e
En
se
mb
l
e
d
S
V
M
C
l
a
ss
i
f
i
e
r
9
3
.
1
5
B
a
sm
a
A
mm
o
u
r
[
2
8
]
M
u
l
t
i
-
r
e
s
o
l
u
t
i
o
n
2D
L
o
g
-
G
a
b
o
r
f
i
l
t
e
r
si
n
g
u
l
a
r
sp
e
c
t
r
u
m
a
n
a
l
y
si
s,
N
o
r
m
a
l
i
n
v
e
r
se
G
a
u
ssi
a
n
c
o
m
b
i
n
e
d
w
i
t
h
s
t
a
t
i
s
t
i
c
a
l
f
e
a
t
u
r
e
s
of
w
a
v
e
l
e
t
.
H
y
b
r
i
d
f
u
si
o
n
l
e
v
e
l
(
sc
o
r
e
a
n
d
d
e
c
i
si
o
n
)
M
a
x
r
u
l
e
w
i
t
h
M
i
n
-
M
a
x
n
o
r
m
a
l
i
z
a
t
i
o
n
9
9
.
1
6
9
9
.
3
3
V
e
d
u
r
u
r
u
S
i
r
e
e
sh
[
2
9
]
M
o
d
i
f
i
e
d
L
B
P
F
e
a
t
u
r
e
f
u
si
o
n
S
c
o
r
e
f
u
s
i
o
n
PSO
a
n
d
n
a
i
v
e
b
a
y
e
s
c
l
a
ss
i
f
i
e
r
90
85
S
h
e
e
t
a
l
C
h
a
u
d
h
a
r
y
&Ra
j
e
n
d
e
r
N
a
t
h
[
3
0
]
F
a
c
e
-
Ei
g
e
n
f
a
c
e
a
p
p
r
o
a
c
h
.
F
i
n
g
e
r
p
r
i
n
t
-
m
i
n
u
t
i
a
e
p
o
i
n
t
s
M
a
t
c
h
sc
o
r
e
l
e
v
e
l
f
u
s
i
o
n
M
u
l
t
i
p
l
e
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s
(
S
V
M
s)
9
9
.
0
2
9
9
.
8
S
u
n
e
e
t
N
a
r
u
l
a
G
a
r
g
[
3
1
]
C
o
a
r
se
n
e
ss,
C
o
n
t
r
a
s
t
,
D
i
r
e
c
t
i
o
n
a
l
i
t
y
,
En
t
r
o
p
y
,
H
o
mo
g
e
n
e
i
t
y
a
n
d
En
e
r
g
y
D
e
c
i
s
i
o
n
l
e
v
e
l
f
u
si
o
n
K
N
N
a
n
d
N
e
u
r
a
l
c
l
a
ss
i
f
i
e
r
9
1
.
5
A
r
c
h
a
n
a
P.
P
a
t
i
l
[
3
2
]
M
i
n
u
t
i
a
e
e
x
t
r
a
c
t
o
r
2
D
G
a
b
o
r
f
i
l
t
e
r
h
a
a
r
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
M
a
t
c
h
sc
o
r
e
l
e
v
e
l
f
u
s
i
o
n
w
e
i
g
h
t
e
d
f
u
s
i
o
n
t
e
c
h
n
i
q
u
e
/
K
N
N
9
5
.
2
3
Fro
m
th
e
ab
o
v
e
L
iter
atu
r
e
s
u
r
v
ey
,
we
can
co
n
cl
u
d
e
t
h
at
m
o
s
t
of
th
e
a
u
th
o
r
s
h
av
e
wo
r
k
ed
on
t
h
e
co
n
v
en
tio
n
al
f
ea
tu
r
e
ex
t
r
ac
tio
n
an
d
class
if
icatio
n
tech
n
i
q
u
es
wh
ich
led
th
em
to
a
lo
s
s
of
ac
cu
r
ac
y
.
To
im
p
r
o
v
e
th
e
ac
c
u
r
ac
y
,
th
e
u
s
e
of
ad
v
an
ce
d
m
eth
o
d
o
lo
g
ies
is
r
eq
u
ir
ed
,
f
o
r
ex
am
p
le,
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
,
p
r
e
-
tr
ain
ed
n
etwo
r
k
s
f
o
r
f
ea
tu
r
e
e
x
tr
ac
tio
n
,
an
d
n
e
u
r
al
n
etwo
r
k
f
o
r
class
if
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
7
91
-
8
0
1
794
3.
P
RO
CE
SS
I
NVO
L
VE
D
IN
B
I
O
M
E
T
RIC
SYS
T
E
M
S
Gen
er
ally
,
a
b
io
m
etr
ic
s
y
s
tem
m
ain
ly
co
n
s
is
ts
o
f
two
p
h
ases
n
am
ely
th
e
en
r
o
llm
en
t
s
tag
e
an
d
co
n
f
ir
m
atio
n
s
tag
e.
I
n
th
e
en
r
o
llm
en
t
p
h
ase,
th
e
im
ag
es
a
r
e
co
llected
f
r
o
m
b
i
o
m
etr
ic
attr
ib
u
tes
an
d
it
is
p
r
o
c
ess
ed
to
g
et
a
clea
r
im
ag
e
as
well
as
to
r
ec
tify
d
is
to
r
tio
n
s
an
d
to
g
et
th
e
s
ec
to
r
o
f
i
n
ter
est
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
C
er
tain
f
ea
tu
r
es
alo
n
e
ar
e
ex
t
r
ac
ted
f
r
o
m
th
e
im
ag
e
to
f
o
r
m
th
e
f
ea
t
u
r
e
v
ec
to
r
an
d
ar
e
th
e
n
s
to
r
ed
in
a
d
atab
ase
[
3
3
]
s
h
o
wn
in
Fig
u
r
e
1
t
o
r
ec
o
g
n
ize
p
ar
ticu
lar
in
d
iv
id
u
als.
I
n
th
e
ac
ce
p
ta
n
ce
p
h
ase,
th
e
q
u
er
y
im
ag
e
wh
ich
is
t
o
b
e
test
ed
is
p
r
o
ce
s
s
ed
to
im
p
r
o
v
e
th
e
h
allm
ar
k
o
f
an
im
ag
e.
T
h
e
R
eg
io
n
o
f
I
n
ter
est
is
th
e
p
r
o
ce
d
u
r
e
o
f
e
m
p
h
asis
k
ey
an
d
r
eq
u
ir
e
d
f
ea
tu
r
es
in
a
b
io
m
etr
ic
f
ea
tu
r
e
as
a
n
i
n
ter
esti
n
g
r
e
g
io
n
th
at
will
f
u
r
th
e
r
b
e
u
s
ed
as
m
atch
in
g
p
ar
am
eter
s
an
d
th
en
f
ea
tu
r
e
ex
tr
ac
te
d
.
T
h
u
s
,
f
o
r
m
e
d
f
ea
tu
r
e
v
ec
to
r
s
f
r
o
m
r
etr
iev
e
d
f
ea
tu
r
es
will
b
e
co
m
p
ar
e
d
ag
ain
s
t
th
e
f
ea
t
u
r
e
d
atab
ase
in
th
e
m
atch
in
g
m
o
d
u
le
to
p
r
o
d
u
ce
a
m
atch
s
co
r
e
an
d
f
in
ally
b
y
u
s
in
g
th
e
m
atch
s
co
r
e
d
e
cisi
o
n
m
o
d
u
le
will
id
en
tify
t
h
e
a
u
th
o
r
ize
d
p
er
s
o
n
s
.
T
h
ese
s
eq
u
e
n
ce
s
o
f
s
tep
s
ar
e
s
h
o
wn
in
Fig
u
r
e
1
.
A
b
i
o
m
e
tr
ic
s
y
s
tem
ca
n
b
e
r
ep
r
esen
ted
with
two
im
p
o
r
ta
n
t
f
u
n
cti
o
n
alities
o
n
e
is
v
e
r
if
icatio
n
an
d
th
e
o
th
er
o
n
e
is
i
d
en
tific
atio
n
[
3
4
]
.
Ver
if
icatio
n
in
v
o
lv
es a
o
n
e
-
to
-
o
n
e
m
atch
in
th
e
d
atab
ase.
O
n
th
e
o
th
er
h
an
d
,
id
en
tific
atio
n
is
o
b
tain
ed
wh
en
a
s
y
s
tem
p
er
f
o
r
m
s
o
n
e
to
m
a
n
y
co
m
p
ar
is
o
n
s
.
Fig
u
r
e
1
.
Step
s
ass
o
ciate
d
with
a
b
io
m
etr
ic
s
y
s
tem
d
u
r
in
g
r
e
co
g
n
itio
n
4.
CL
AS
SI
F
I
CAT
I
O
N
OF
B
I
O
M
E
T
RIC
SYS
T
E
M
S
4
.
1
.
Unim
o
da
l
bio
m
et
ric
s
y
s
t
em
s
B
io
m
etr
ic
au
th
en
ticatio
n
o
f
in
d
iv
id
u
als
is
b
y
u
s
in
g
th
eir
b
eh
av
io
r
al
o
r
p
h
y
s
io
lo
g
ical
f
ea
tu
r
es.
T
h
ese
b
io
lo
g
ical
f
ea
tu
r
es
ar
e
o
r
g
an
ized
in
to
u
n
im
o
d
al
an
d
m
u
l
tim
o
d
al
b
i
o
m
etr
ic
s
y
s
tem
s
[
3
5
]
.
Ma
n
y
o
f
th
e
b
io
m
etr
ics
ar
e
u
n
im
o
d
al
s
y
s
tem
s
,
wh
ich
m
ea
n
s
it
em
p
lo
y
s
s
in
g
le
b
io
m
etr
ic
attr
ib
u
tes
to
r
ec
o
g
n
ize
th
e
u
s
er
ar
e
n
o
r
m
ally
co
s
t
-
ef
f
icien
t,
b
u
t
th
e
p
er
f
o
r
m
an
ce
o
f
th
ese
s
y
s
tem
s
m
ay
d
eg
r
ad
e
in
s
o
m
e
p
r
ac
tical
cir
cu
m
s
tan
ce
s
wer
e
th
er
e
ex
is
t
in
g
n
o
is
y
d
ata,
in
tr
a
-
class
v
ar
i
atio
n
s
,
an
d
in
ter
-
class
s
im
ilar
it
ies.
T
h
o
u
g
h
s
o
m
e
u
n
im
o
d
al
s
y
s
te
m
s
h
av
e
m
ad
e
a
s
u
b
s
tan
tial
im
p
r
o
v
e
m
en
t
in
ac
c
u
r
ac
y
a
n
d
r
eliab
ilit
y
,
th
ey
u
s
u
ally
ex
p
er
ien
ce
p
r
o
b
l
em
s
in
th
e
en
r
o
llm
en
t
s
tag
e
d
u
e
to
th
e
n
o
n
-
u
n
iv
er
s
ality
o
f
b
io
m
etr
ic
attr
ib
u
tes.
I
n
B
io
m
etr
ic
s
p
o
o
f
in
g
u
n
au
th
o
r
ized
p
er
s
o
n
ca
n
t
r
y
t
o
im
ita
te
b
eh
av
i
o
r
al
b
i
o
m
etr
ics
lik
e
v
o
ice
an
d
s
ig
n
atu
r
e
f
o
r
a
n
e
n
r
o
lled
u
s
er
.
Ho
wev
er
,
in
ad
eq
u
ate
ac
cu
r
ac
y
ca
u
s
ed
b
y
n
o
is
y
d
ata
th
at
o
cc
u
r
r
ed
wh
ile
ca
p
tu
r
ed
b
io
m
etr
ic
d
ata
u
s
u
ally
co
n
tain
s
in
co
m
p
l
ete
ac
q
u
is
itio
n
co
n
d
itio
n
s
o
r
v
a
r
ian
ts
in
a
c
h
ar
ac
t
er
is
tic
o
f
b
io
m
etr
ic
its
elf
lik
e
u
n
-
wan
ted
s
cr
atch
es
o
n
th
e
b
io
m
etr
ic
im
a
g
e
o
r
d
ir
t
o
n
s
en
s
o
r
[
3
6
]
.
I
n
tr
a
-
class
v
ar
iatio
n
:
T
h
e
b
io
m
etr
ic
d
ata
co
llected
d
u
r
in
g
a
u
th
en
ticatio
n
will
n
o
t
b
e
th
e
s
am
e
as
th
e
one
u
s
ed
f
o
r
g
en
e
r
atin
g
a
tem
p
late
f
o
r
an
in
d
iv
id
u
al
d
u
r
in
g
th
e
en
r
o
llm
en
t
p
r
o
ce
s
s
.
I
n
ter
-
class
s
im
ilar
ities
:
I
t
b
ec
au
s
e
o
f
o
v
er
lap
p
i
n
g
f
ea
tu
r
e
s
p
ac
es
in
th
e
f
ea
tu
r
e
s
ets
o
f
v
ar
i
o
u
s
u
s
er
s
.
T
h
e
u
n
im
o
d
a
l
b
io
m
etr
ic
s
y
s
tem
m
ay
lead
to
b
o
th
f
alse r
ejec
tio
n
r
ate
(
F
R
R
)
an
d
f
alse a
cc
ep
ta
n
ce
r
ate
(
FAR
)
[
1
8
]
.
4
.
2
.
M
ultim
o
da
l
bio
m
et
ric
s
y
s
t
em
s
Un
im
o
d
al
b
io
m
etr
ic
s
y
s
tem
s
co
n
s
tan
tly
f
ail
to
c
o
r
r
ec
tly
au
th
en
ticate
an
in
d
iv
i
d
u
al
with
a
cr
av
in
g
ef
f
ec
t
an
d
ac
cu
r
ac
y
.
Ho
wev
er
,
m
u
ltimo
d
ality
(
m
o
r
e
th
an
o
n
e
tr
ait)
is
ap
p
lied
to
r
eso
lv
e
m
an
y
o
f
th
e
is
s
u
es
r
elate
d
to
u
n
im
o
d
al
s
y
s
tem
s
.
T
h
e
ter
m
'
m
u
ltimo
d
al'
is
u
tili
ze
d
to
d
escr
ib
e
th
e
m
i
x
o
f
at
least
two
d
if
f
er
en
t
b
io
m
etr
ics
o
f
a
p
e
r
s
o
n
(
i.e
.
,
i
r
is
,
f
ac
e,
an
d
f
in
g
er
p
r
in
t)
s
e
n
s
e
d
b
y
u
s
i
n
g
d
i
s
t
i
n
c
t
s
e
n
s
o
r
s
an
d
t
h
u
s
i
m
p
r
o
v
e
t
h
e
r
e
q
u
i
r
e
d
a
c
c
u
r
a
c
y
o
f
a
b
i
o
m
e
t
r
ic
s
y
s
t
e
m
b
y
u
t
i
l
iz
i
n
g
t
h
e
n
e
c
ess
a
r
y
i
n
f
o
r
m
a
t
i
o
n
f
r
o
m
m
u
l
t
i
p
le
i
n
p
u
t
m
o
d
a
l
i
t
i
es
.
I
t
m
ay
b
e
a
f
u
s
io
n
o
f
b
e
h
av
io
r
al
with
p
h
y
s
ical
m
o
d
alities
o
r
d
if
f
er
en
t
p
h
y
s
io
lo
g
ical
tr
aits
to
g
eth
e
r
.
T
h
ese
f
u
s
io
n
m
eth
o
d
o
l
o
g
ies
d
ec
r
ea
s
e
th
e
ef
f
ec
t
o
f
s
p
o
o
f
in
g
attac
k
s
b
y
m
ak
in
g
it
d
if
f
icu
lt
f
o
r
an
u
n
au
t
h
o
r
ize
d
o
n
e
to
f
ak
e
,
co
p
y
o
r
s
teal,
r
aises
th
e
d
eg
r
ee
o
f
f
r
ee
d
o
m
,
d
ec
r
ea
s
es
th
e
f
ailu
r
e
-
to
-
en
r
o
ll
r
ate
,
an
d
h
e
n
ce
m
a
k
es
th
e
b
io
m
etr
ic
s
y
s
tem
m
o
r
e
s
e
cu
r
e.
I
n
cr
ea
s
in
g
th
e
d
is
cr
im
in
ate
in
f
o
r
m
atio
n
lead
s
to
r
ed
u
ce
th
e
er
r
o
r
in
t
h
e
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
[
3
7
]
.
M
u
l
tim
o
d
al
b
io
m
etr
ic’
s
f
u
s
io
n
tec
h
n
iq
u
es
m
e
n
tio
n
h
o
w
th
e
i
n
f
o
r
m
atio
n
is
m
e
r
g
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
mp
a
r
is
o
n
o
f le
ve
ls
a
n
d
fu
s
i
o
n
a
p
p
r
o
a
ch
es fo
r
mu
ltimo
d
a
l b
io
metrics
(
S.
S
u
ja
n
a
)
795
wh
en
it’s
o
b
tain
ed
f
r
o
m
v
ar
io
u
s
b
io
m
etr
ic
tr
aits
.
T
h
is
f
u
s
io
n
ca
n
b
e
d
o
n
e
at
s
in
g
le
as
well
as
m
u
ltip
le
lev
els
in
a
m
u
ltimo
d
al
s
y
s
tem
,
i.e
.
,
f
u
s
io
n
at
th
e
s
en
s
o
r
,
at
f
ea
t
u
r
e
lev
el
an
d
m
atch
in
g
-
s
co
r
e,
o
r
d
ec
is
io
n
lev
el
[
2
1
]
.
Fu
s
io
n
at
th
e
f
ea
tu
r
e
le
v
el,
h
o
wev
er
,
is
m
o
r
e
f
r
u
itf
u
l
b
ec
a
u
s
e
it
co
n
tain
s
m
o
r
e
in
f
o
r
m
at
io
n
ab
o
u
t
th
e
in
p
u
t
tr
ait
th
an
th
e
lev
els o
f
f
u
s
io
n
a
f
ter
m
atch
in
g
[
1
1
]
.
T
o
ac
q
u
ir
e
th
e
tar
g
et
o
f
claim
ed
p
er
f
o
r
m
a
n
ce
im
p
r
o
v
em
en
t,
th
e
f
u
s
io
n
r
u
le
c
h
o
s
en
s
h
o
u
ld
d
ep
en
d
o
n
th
e
ty
p
e
o
f
a
p
p
licatio
n
s
th
at
ar
e
s
elec
ted
,
in
p
u
t
b
io
m
et
r
ic
m
o
d
alities
u
s
ed
f
o
r
f
u
s
io
n
,
a
n
d
th
e
o
p
ted
f
u
s
io
n
lev
el.
Mu
ltimo
d
al
s
y
s
tem
s
ca
n
m
ix
in
f
o
r
m
atio
n
at
v
ar
io
u
s
s
tag
es,
b
u
t
th
e
f
u
s
io
n
at
s
co
r
e
lev
el
b
ec
am
e
th
e
m
o
s
t
f
av
o
r
ed
o
n
e.
Fu
s
io
n
s
also
ad
d
r
ess
th
e
p
r
o
b
lem
o
f
s
p
o
o
f
in
g
an
d
n
o
n
-
u
n
i
v
er
s
ality
.
Sev
er
al
s
tu
d
ies
h
av
e
s
u
g
g
ested
th
at
in
teg
r
atin
g
in
f
o
r
m
atio
n
f
r
o
m
v
ar
io
u
s
b
io
m
etr
ics
an
d
im
p
r
o
v
ed
ac
c
u
r
ac
y
to
s
atis
f
y
th
e
s
p
ec
if
icatio
n
s
o
f
t
h
e
p
h
y
s
ical
wo
r
ld
[
3
8
]
.
Hen
ce
,
t
h
e
m
u
ltimo
d
al
b
i
o
m
e
tr
ic
s
y
s
tem
s
h
o
ws
s
ev
er
al
b
en
ef
its
th
an
a
u
n
im
o
d
al
b
io
m
etr
ic
.
5.
L
E
V
E
L
S
OF
F
USI
O
N
IN
M
UL
T
I
M
O
D
AL
B
I
O
M
E
T
RI
C
SYST
E
M
Mu
ltimo
d
al
f
u
s
io
n
c
a
n
b
e
ac
c
o
m
p
lis
h
ed
in
two
wa
y
s
.
5
.
1
.
F
us
io
n
j
us
t
bef
o
re
ma
t
c
hin
g
It
is
p
o
s
s
ib
le
to
ac
q
u
ir
e
f
u
s
io
n
p
r
ec
ed
e
n
t
to
m
atch
in
g
in
two
d
is
tin
ct
m
an
n
er
s
:
s
en
s
o
r
lev
el
an
d
f
u
s
io
n
lev
el.
5
.
1
.
1
.
Sens
o
r
l
ev
el
f
us
io
n
Sen
s
o
r
-
lev
el
f
u
s
io
n
in
teg
r
ate
s
th
e
d
ata
th
at
is
o
b
tain
e
d
f
r
o
m
m
u
ltip
le
s
en
s
o
r
s
a
n
d
g
iv
es
f
u
s
ed
in
f
o
r
m
atio
n
[
1
0
]
a
n
d
f
r
o
m
th
ese
f
u
s
ed
d
ata
f
ea
tu
r
es c
an
b
e
p
u
lled
s
h
o
wn
in
Fig
u
r
e
2
(
a)
.
D
if
f
er
en
t m
eth
o
d
s
in
th
e
s
en
s
o
r
lev
el
ar
e
s
in
g
le
s
en
s
o
r
m
u
ltip
le
in
s
tan
c
es:
−
Sev
er
al
in
s
tan
ce
s
ac
h
iev
ed
f
r
o
m
a
s
in
g
le
s
en
s
o
r
ar
e
c
o
m
b
in
e
d
h
er
e
to
o
b
tain
t
h
e
co
m
p
lete
d
ata.
−
I
n
tr
ac
lass
m
u
ltip
le
s
en
s
o
r
s
:
Sev
er
al
in
s
tan
ce
s
d
is
co
v
er
e
d
f
r
o
m
d
i
f
f
er
en
t
s
en
s
o
r
s
ar
e
p
u
t
to
g
eth
er
to
id
en
tify
th
e
d
etails
in
th
is
s
itu
atio
n
.
I
n
ter
-
class
m
u
ltip
le
s
en
s
o
r
s
:
T
h
e
d
ata
to
b
e
f
u
s
ed
m
u
s
t
b
e
o
b
liq
u
e
to
b
e
o
f
th
e
s
am
e
k
in
d
,
lik
e
two
im
ag
es
th
at
will
b
e
f
u
s
ed
f
r
o
m
two
s
ep
ar
ate
ca
m
er
as
r
eq
u
ir
ed
f
o
r
th
e
s
am
e
r
eso
lu
tio
n
.
−
Sen
s
o
r
-
lev
el
f
u
s
io
n
ad
d
r
ess
es
th
e
n
o
is
e
in
s
en
s
ed
d
ata
d
u
e
to
n
o
t
p
r
o
p
er
m
ain
ten
a
n
ce
o
f
s
en
s
o
r
s
.
T
h
is
f
u
s
io
n
h
as n
o
t r
ec
eiv
ed
m
u
ch
atten
tio
n
s
in
ce
it h
as m
o
r
e
r
ed
u
n
d
an
t i
n
f
o
r
m
atio
n
[
3
9
]
.
5
.
1
.
2
.
F
ea
t
ure
lev
el
f
us
io
n
T
h
e
f
u
s
io
n
o
f
th
e
f
ea
tu
r
e
lev
el
is
ac
q
u
ir
ed
b
y
jo
in
in
g
v
ar
i
o
u
s
f
ea
tu
r
e
s
ets
o
b
tain
ed
f
r
o
m
m
u
ltip
le
b
io
m
etr
ic
s
o
u
r
ce
s
[
1
2
]
,
[
4
0
]
s
h
o
wn
in
Fig
u
r
e
2
(
b
)
.
Sets
o
f
f
ea
tu
r
es
ca
n
b
e
eith
er
h
o
m
o
g
en
e
o
u
s
o
r
h
eter
o
g
en
e
o
u
s
.
W
h
en
d
is
tin
ct
m
eth
o
d
s
ar
e
u
s
ed
f
o
r
o
n
e
f
e
atu
r
e
ex
tr
ac
tio
n
,
n
o
n
-
u
n
if
o
r
m
f
ea
tu
r
e
v
ec
to
r
s
ar
e
ac
h
iev
ed
,
o
r
f
ea
tu
r
e
v
ec
to
r
s
ar
e
ex
tr
ac
ted
f
r
o
m
v
a
r
io
u
s
m
o
d
alities
.
T
h
e
p
r
o
ce
s
s
o
f
f
u
s
io
n
ca
n
n
o
t
b
e
co
m
p
lete
s
u
cc
ess
f
u
lly
if
th
e
f
ea
tu
r
e
v
ec
to
r
s
u
tili
ze
d
ar
e
n
o
t
co
h
er
e
n
t
with
o
n
e
an
o
th
er
,
lik
e
m
i
x
in
g
o
f
f
in
g
e
r
p
r
in
t
m
in
u
tiae
with
E
ig
en
f
ac
e
co
ef
f
icien
t is n
o
t p
o
s
s
ib
le.
T
h
e
m
ec
h
a
n
is
m
in
v
o
lv
ed
in
f
ea
tu
r
e
lev
el
f
u
s
io
n
ev
o
l
v
es
in
two
s
tep
s
,
i.e
.
,
th
e
n
o
r
m
aliza
tio
n
o
f
an
ex
tr
ac
ted
f
ea
tu
r
e
an
d
th
e
n
th
e
s
elec
tio
n
o
f
a
f
ea
tu
r
e
.
T
h
e
f
ea
t
u
r
e
s
ets ar
e
f
ir
s
t tr
an
s
lated
in
to
a
g
en
er
ic
d
o
m
ain
,
an
d
th
e
r
a
n
g
e
o
f
f
ea
tu
r
e
s
ets ar
e
alter
ed
,
th
is
ca
n
b
e
im
p
lem
e
n
ted
b
y
u
s
in
g
n
o
r
m
aliza
tio
n
te
ch
n
iq
u
es [
4
1
].
L
in
ea
r
d
is
cr
im
in
ate
an
aly
s
is
(
L
DA)
was
ap
p
lied
in
th
e
f
ea
tu
r
e
d
r
awin
g
p
h
ase
to
s
o
lv
e
th
e
is
s
u
e
of
a
lar
g
e
p
r
o
p
o
r
tio
n
of
th
e
c
o
m
b
in
ed
f
ea
t
u
r
es.
T
ec
h
n
iq
u
es
s
u
ch
as
PC
A
or
s
eq
u
en
tial
b
ac
k
war
d
s
elec
tio
n
,
f
o
r
war
d
s
eq
u
e
n
tial
s
elec
tio
n
,
ar
e
u
tili
ze
d
to
m
in
im
ize
th
e
d
im
en
s
io
n
s
of
a
f
ea
tu
r
e
s
et.
T
h
e
am
o
u
n
t
of
in
f
o
r
m
atio
n
at
th
e
f
ea
tu
r
e
lev
e
l
is
s
u
f
f
icien
t
to
au
th
e
n
ticate
an
in
d
iv
id
u
al;
h
o
we
v
er
,
th
e
f
ea
tu
r
e
-
lev
el
f
u
s
io
n
is
h
ar
d
b
ec
a
u
s
e
f
ea
tu
r
e
s
ets
of
v
a
r
io
u
s
s
o
u
r
ce
s
m
ay
eith
e
r
be
i
n
co
m
p
atib
le
or
in
ac
ce
s
s
ib
le
[
4
2
]
.
5
.
2
.
F
us
io
n
j
us
t
a
f
t
er
m
a
t
ching
It
is
a
f
u
s
io
n
af
ter
co
m
p
ar
is
o
n
of
th
e
ex
tr
ac
ted
f
ea
tu
r
es
with
s
to
r
ed
tem
p
late
d
ata
b
a
s
e
can
be
ac
h
iev
ed
in
two
way
s
:
f
u
s
io
n
at
s
co
r
e
lev
el
an
d
d
ec
is
io
n
lev
el.
5
.
2
.
1
.
M
a
t
ch
s
co
re
lev
el
f
us
io
n
T
o
g
e
n
er
ate
m
atc
h
s
co
r
es,
f
ea
tu
r
e
v
ec
to
r
s
ar
e
ex
tr
ac
ted
s
ep
ar
ately
f
o
r
a
n
in
d
iv
id
u
al
b
io
m
etr
ic
tr
ait
an
d
th
ese
f
ea
tu
r
e
v
ec
t
o
r
s
ar
e
co
m
p
ar
e
d
with
tem
p
lates
s
to
r
ed
in
t
h
e
d
atab
ase
d
u
r
in
g
en
r
o
llm
en
t
[
1
2
]
.
T
h
e
s
co
r
e
g
iv
e
n
b
y
th
e
m
atch
er
s
h
as
th
e
r
e
q
u
ir
e
d
in
f
o
r
m
ati
o
n
r
e
g
ar
d
i
n
g
i
n
p
u
t
an
d
also
its
f
ea
tu
r
e
v
ec
to
r
r
ep
r
esen
tatio
n
.
Set
o
f
o
u
t
p
u
ts
f
r
o
m
m
atch
in
g
m
o
d
u
le
i.e
.
,
m
atch
s
co
r
es
ar
e
m
er
g
ed
t
o
c
r
ea
te
a
s
in
g
le
s
ca
lar
s
co
r
e
s
h
o
wn
in
Fig
u
r
e
3
(
a)
.
T
h
e
ac
q
u
ir
ed
s
co
r
es
f
r
o
m
m
at
ch
in
g
m
o
d
u
les
ca
n
n
o
t
b
e
i
n
teg
r
ated
d
ir
ec
tly
s
in
ce
th
e
s
co
r
e
s
o
b
tain
ed
f
r
o
m
d
if
f
e
r
en
t
m
o
d
alities
h
av
e
d
if
f
er
en
t
r
an
g
es.
I
t
i
s
i
m
p
o
r
t
an
t
t
o
c
o
n
v
e
r
t
t
h
es
e
s
c
o
r
es
t
o
a
c
o
m
m
o
n
d
o
m
a
i
n
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
7
91
-
8
0
1
796
s
c
a
l
e
b
y
u
s
i
n
g
Sc
o
r
e
n
o
r
m
a
l
i
za
t
i
o
n
t
o
e
n
s
u
r
e
p
r
o
p
e
r
m
i
x
i
n
g
o
f
s
c
o
r
e
s
f
r
o
m
t
h
e
v
a
r
i
o
u
s
m
o
d
a
l
i
t
i
es
[
1
0
]
,
[
1
3
]
.
Fu
s
io
n
at
th
e
s
co
r
e
lev
el
is
u
s
u
ally
f
av
o
r
ed
b
ec
au
s
e
th
e
s
co
r
es
s
u
p
p
lied
b
y
th
e
in
d
iv
id
u
al
m
atch
in
g
m
o
d
u
les
ar
e
ea
s
ily
ac
ce
s
s
ed
a
n
d
i
n
co
r
p
o
r
ated
.
T
h
e
in
f
o
r
m
atio
n
ac
c
ess
ib
le
at
th
e
s
co
r
e
lev
el
is
a
d
eq
u
ate
t
o
r
e
co
g
n
ize
an
in
d
iv
i
d
u
al
clien
t
s
in
ce
it
h
a
s
n
eith
er
an
ex
ce
s
s
iv
e
am
o
u
n
t
o
f
r
ep
etitiv
e
n
o
r
to
o
litt
le
d
at
a.
I
t
g
iv
es
a
s
tr
o
n
g
s
et
o
f
in
f
o
r
m
atio
n
[
4
3
]
.
I
t
is
s
im
p
le
to
ag
g
r
eg
ate
th
e
s
co
r
es
p
r
o
d
u
ce
d
b
y
s
ev
e
r
al
m
atch
er
s
h
er
e.
T
h
is
m
eth
o
d
o
f
f
u
s
io
n
is
th
e
m
o
s
t c
o
m
m
o
n
l
y
u
s
ed
.
5
.
2
.
2
.
Dec
is
io
n
lev
el
f
us
io
n
In
th
is
f
u
s
io
n
,
th
e
co
m
b
i
n
in
g
of
m
u
ltip
le
s
co
r
e
in
f
o
r
m
at
io
n
is
ca
p
tu
r
ed
f
r
o
m
v
ar
io
u
s
b
io
m
etr
ic
m
o
d
alities
wh
en
th
e
i
n
d
iv
id
u
al
d
ec
is
io
n
m
o
d
u
le
g
i
v
es
its
d
ec
is
io
n
r
eg
ar
d
in
g
th
e
id
en
t
ity
of
a
p
er
s
o
n
of
claim
ed
.
In
th
is
d
ec
is
io
n
f
u
s
io
n
th
e
f
in
al
class
if
icatio
n
r
esu
lt
d
ep
en
d
s
on
th
e
o
u
tp
u
ts
of
th
e
d
ec
is
io
n
m
o
d
u
les
co
r
r
esp
o
n
d
in
g
to
v
ar
io
u
s
m
o
d
alities
s
ee
in
Fig
u
r
e
3
(
b
)
an
d
th
e
f
in
al
s
co
r
e
is
class
if
ied
i
n
to
one
of
th
e
two
(
r
ejec
t
or
ac
ce
p
t)
m
ain
class
es
[
4
4
]
.
T
h
is
Fu
s
io
n
is
to
o
r
ig
id
b
ec
au
s
e
it
h
as
less
in
f
o
r
m
atio
n
to
m
ak
e
a
d
ec
is
io
n
.
C
o
m
m
er
cial
o
f
f
th
e
Sh
elf
t
o
o
ls
g
iv
e
th
e
f
in
al
d
ec
is
io
n
s
by
u
s
in
g
s
o
m
e
of
th
e
tech
n
i
q
u
es
lik
e
m
ajo
r
ity
v
o
tin
g
,
B
ay
esian
d
ec
is
io
n
f
u
s
io
n
,
AND
an
d
OR
.
Gen
er
ally
,
th
e
m
o
s
t
u
s
ed
ap
p
r
o
ac
h
f
o
r
au
th
en
ticatio
n
is
m
ajo
r
ity
v
o
tin
g
f
o
r
d
ec
is
io
n
lev
el
f
u
s
io
n
.
T
h
e
b
en
ef
it
of
th
is
m
et
h
o
d
is
th
at
h
er
e
p
r
io
r
k
n
o
wled
g
e
of
th
e
m
atc
h
er
d
o
e
s
not
r
eq
u
ir
e
as
well
as
an
y
n
e
ed
of
tr
ain
in
g
to
ta
k
e
a
f
in
al
d
ec
is
io
n
.
So
m
etim
es
p
er
f
o
r
m
an
ce
d
eg
r
a
d
atio
n
m
a
y
o
cc
u
r
in
‘
AND’
an
d
‘
OR
’
m
eth
o
d
s
b
ec
au
s
e
of
th
e
m
ix
in
g
of
m
u
ltip
le
m
atch
er
s
.
T
h
e
f
u
s
io
n
at
th
e
d
ec
is
io
n
is
o
n
ly
u
s
ed
wh
er
e
t
h
e
d
ec
is
io
n
s
of
t
h
e
in
d
i
v
id
u
al
u
s
er
s
ar
e
ac
ce
s
s
ib
le
h
en
ce
is
k
n
o
wn
as
an
ab
s
tr
ac
t
lev
el
f
u
s
io
n
[
4
5
]
.
C
o
m
p
ar
ativ
e
an
aly
s
is
of
of
v
ar
io
u
s
lev
e
ls
of
f
u
s
io
n
[
4
6
]
is
s
h
o
wn
in
T
ab
le
2.
(
a)
(
b
)
Fig
u
r
e
2.
Fu
s
io
n
p
r
o
ce
s
s
at
;
(
a
)
s
en
s
o
r
lev
el
of
two
b
io
m
et
r
ic
tr
aits
an
d
(
b
)
f
ea
tu
r
e
le
v
el
of
t
wo
b
io
m
etr
ic
tr
aits
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
mp
a
r
is
o
n
o
f le
ve
ls
a
n
d
fu
s
i
o
n
a
p
p
r
o
a
ch
es fo
r
mu
ltimo
d
a
l b
io
metrics
(
S.
S
u
ja
n
a
)
797
(
a)
(
b
)
Fig
u
r
e
3
.
Fu
s
io
n
of
;
(
a
)
t
wo
b
i
o
m
etr
ic
tr
aits
at
th
e
s
co
r
e
lev
e
l
an
d
(
b
)
b
io
m
etr
ic
tr
aits
at
th
e
d
ec
is
io
n
lev
el
T
ab
le
2
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
of
v
ar
i
o
u
s
lev
els
of
f
u
s
io
n
F
u
si
o
n
l
e
v
e
l
Li
mi
t
a
t
i
o
n
s
F
u
si
o
n
a
t
t
h
e
S
e
n
s
o
r
l
e
v
e
l
Th
e
n
o
i
se
o
f
s
e
n
s
e
d
d
a
t
a
,
l
o
w
se
n
so
r
e
f
f
i
c
i
e
n
c
y
,
a
n
d
a
t
m
o
sp
h
e
r
i
c
i
n
f
l
u
e
n
c
e
s
.
F
u
si
o
n
a
t
fe
a
t
u
r
e
I
n
c
o
mp
a
t
i
b
l
e
f
e
a
t
u
r
e
c
o
l
l
e
c
t
i
o
n
,
t
h
e
u
n
c
e
r
t
a
i
n
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
v
a
r
i
o
u
s
b
i
o
me
t
r
i
c
s
y
st
e
ms'
f
e
a
t
u
r
e
s
p
a
c
e
s
,
w
h
i
c
h
r
e
q
u
i
r
e
c
o
n
si
d
e
r
a
b
l
y
mo
r
e
c
o
m
p
l
e
x
ma
t
c
h
i
n
g
.
F
u
si
o
n
a
t
ma
t
c
h
sco
r
e
Th
e
r
e
a
r
e
n
o
h
o
m
o
g
e
n
o
u
s s
c
o
r
e
s
o
b
t
a
i
n
e
d
f
r
o
m
v
a
r
i
o
u
s m
a
t
c
h
e
r
s.
I
t
i
s
n
o
t
n
e
c
e
ss
a
r
y
t
h
a
t
t
h
e
sc
o
r
e
s
o
b
t
a
i
n
e
d
s
h
o
u
l
d
b
e
w
i
t
h
i
n
t
h
e
s
a
me
sc
o
p
e
.
I
t
i
s i
mp
o
r
t
a
n
t
t
o
a
p
p
l
y
n
o
r
ma
l
i
s
a
t
i
o
n
s
c
h
e
mes
F
u
si
o
n
a
t
sc
o
r
e
l
e
v
e
l
O
n
l
y
a
mi
n
i
ma
l
a
m
o
u
n
t
o
f
k
n
o
w
l
e
d
g
e
a
t
t
h
i
s
st
a
g
e
o
f
f
u
s
i
o
n
i
s
a
v
a
i
l
a
b
l
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
7
91
-
8
0
1
798
6.
M
E
T
H
O
DS
OF
M
U
L
T
I
M
O
DAL
F
US
I
O
N
T
h
er
e
ar
e
th
r
ee
m
ain
ca
teg
o
r
i
es
f
o
r
th
e
class
if
ica
tio
n
of
f
u
s
io
n
m
eth
o
d
s
f
o
r
m
u
ltimo
d
al
b
io
m
etr
ics,
s
u
ch
as
esti
m
atio
n
b
ased
,
class
if
icatio
n
b
ased
an
d
r
u
le
-
b
ase
d
m
eth
o
d
s
[
4
7
]
.
6
.
1
.
Rule
-
ba
s
ed
f
us
io
n t
ec
hn
iqu
es
T
h
e
r
u
le
-
b
ased
tech
n
i
q
u
es
in
m
u
ltimo
d
al
ar
e
in
v
o
l
v
in
g
s
o
m
e
b
asic
r
u
les
f
o
r
f
u
s
in
g
in
f
o
r
m
atio
n
.
I
n
th
is
ca
s
e,
s
o
m
e
s
tatis
t
ical
r
u
les
ar
e
u
s
ed
s
u
ch
as
MI
N,
MA
X,
p
r
o
d
u
ct,
an
d
th
e
s
u
m
-
b
ased
f
u
s
io
n
li
k
e
lin
ea
r
weig
h
ted
,
th
e
m
ajo
r
ity
v
o
tin
g
,
OR
an
d
AND
[
4
8
]
.
T
h
ese
tech
n
iq
u
es a
r
e
d
ep
en
d
in
g
o
n
th
e
s
elec
ted
ap
p
licatio
n
an
d
ar
e
cu
s
to
m
ized
.
Gen
er
all
y
,
th
ese
m
eth
o
d
s
p
er
f
o
r
m
we
ll
if
th
e
tem
p
o
r
al
alig
n
m
en
t
o
f
tr
aits
is
o
f
g
o
o
d
q
u
ality
.
I
n
r
u
le
b
ase
th
er
e
is
n
o
tr
ain
in
g
p
r
o
ce
s
s
ar
e
also
k
n
o
wn
as
u
n
s
u
p
er
v
is
ed
m
eth
o
d
s
,
b
u
t
th
e
lear
n
in
g
o
r
tr
ain
in
g
r
u
les ar
e
m
o
s
tly
ap
p
li
ca
b
le
f
o
r
p
r
e
-
d
ef
in
ed
o
u
tp
u
t
.
6
.
2
.
Cla
s
s
if
ica
t
io
n
ba
s
ed
f
us
io
n
m
et
ho
ds
Fu
s
io
n
b
ased
on
class
if
icatio
n
is
a
s
u
p
er
v
is
ed
ca
teg
o
r
y
as
it
is
b
ased
on
tr
ain
in
g
or
lear
n
in
g
p
r
o
ce
s
s
.
T
h
is
class
if
icatio
n
m
eth
o
d
in
v
o
lv
es
a
s
et
of
tech
n
iq
u
es
to
class
if
y
th
e
o
b
s
er
v
atio
n
s
in
t
o
o
n
e
o
f
th
e
p
r
e
-
d
ec
id
ed
class
es.
T
h
e
m
o
s
t
co
m
m
o
n
ly
u
s
ed
class
if
icatio
n
m
eth
o
d
s
ar
e
n
eu
r
al
n
etwo
r
k
s
,
m
ax
im
u
m
en
tr
o
p
y
m
o
d
els,
Dem
p
s
ter
-
Sh
a
f
er
t
h
eo
r
y
,
d
y
n
am
ic
B
ay
esian
n
et
wo
r
k
,
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
i
n
e,
an
d
B
ay
esian
in
f
er
en
ce
.
Fro
m
a
m
ac
h
i
n
e
le
ar
n
in
g
p
o
in
t
of
v
iew,
it
is
f
u
r
th
er
class
if
ied
in
to
two
way
s
n
am
ely
g
e
n
er
ativ
e
an
d
d
is
cr
im
in
ativ
e
m
et
h
o
d
s
.
B
ay
esian
in
f
er
en
ce
an
d
dy
n
a
m
ic
B
ay
esian
n
etwo
r
k
c
o
m
e
u
n
d
er
g
en
er
ativ
e
,
wh
er
ea
s
n
eu
r
al
n
etwo
r
k
s
a
n
d
s
u
p
p
o
r
tiv
e
v
ec
to
r
m
ac
h
in
es
ar
e
u
n
d
e
r
Dis
cr
im
in
ativ
e
m
o
d
el
s
.
Neu
r
al
n
etwo
r
k
an
d
B
ay
esian
m
eth
o
d
ar
e
ap
p
l
icab
le
to
f
ea
tu
r
e
le
v
el
as
well
as
d
ec
is
io
n
lev
el
f
u
s
io
n
m
et
h
o
d
s
[
4
9
]
.
6
.
3
.
Est
im
a
t
io
n
-
ba
s
ed
f
us
io
n t
ec
hn
iqu
e
s
To
esti
m
ate
th
e
lo
ca
tio
n
of
o
b
jects
m
o
v
in
g
b
ased
on
m
u
ltimo
d
al
d
ata,
esti
m
atio
n
f
u
s
io
n
is
u
s
ed
.
In
a
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
of
a
p
er
s
o
n
,
m
u
ltip
le
in
p
u
t
m
o
d
alities
ar
e
co
m
b
in
ed
to
esti
m
ate
th
e
lo
ca
tio
n
.
T
h
e
p
ar
ticle
f
ilter
an
d
Kalm
an
f
ilter
b
elo
n
g
to
th
ese
f
u
s
io
n
m
eth
o
d
s
.
Kalm
an
f
ilter
allo
ws
lo
w
-
lev
el
d
y
n
am
ic
d
ata
to
be
p
er
f
o
r
m
ed
in
r
ea
l
-
tim
e
an
d
ca
l
cu
lates
th
e
s
tate
of
th
e
s
y
s
tem
f
r
o
m
f
u
s
ed
d
ata
[
5
0
]
.
Par
ticle
-
b
ased
ap
p
r
o
ac
h
or
Seq
u
en
tial
Mo
n
te
C
ar
o
l
me
th
o
d
is
s
im
u
latio
n
-
b
ased
m
eth
o
d
s
in
v
o
lv
es
p
r
ed
ictio
n
a
n
d
u
p
d
ate
s
tep
s
.
B
ased
on
th
e
in
f
o
r
m
atio
n
of
m
u
ltimo
d
al
th
ese
tech
n
iq
u
es
ar
e
u
s
ed
f
o
r
an
esti
m
atio
n
of
th
e
s
tate
of
m
o
v
in
g
.
7.
DIS
CU
SS
I
O
N
S
T
h
e
r
ev
iew
clar
if
ies
th
at
s
ti
ll
th
er
e
is
a
n
ee
d
to
in
v
esti
g
at
e
m
o
r
e
ab
o
u
t
th
e
p
r
o
b
lem
s
ex
is
tin
g
in
v
ar
io
u
s
b
i
o
m
etr
ic
r
ec
o
g
n
itio
n
s
y
s
tem
s
an
d
v
a
r
io
u
s
f
u
s
io
n
m
eth
o
d
s
.
Few
ch
allen
g
es
w
h
ich
ar
e
cu
r
r
e
n
tly
p
r
ev
ailin
g
in
v
a
r
io
u
s
b
io
m
et
r
ics
ca
n
b
e
ex
p
lain
e
d
th
r
o
u
g
h
f
ew
ex
am
p
les.
Firstl
y
,
i
n
f
in
g
er
p
r
i
n
t
-
b
ased
r
ec
o
g
n
itio
n
s
y
s
tem
s
,
th
e
k
e
y
attr
ib
u
tes
ar
e
th
e
f
ea
tu
r
es
t
h
at
ten
d
to
d
eter
io
r
ate
as
o
n
e
b
ec
o
m
es
o
l
d
er
.
Seco
n
d
ly
,
t
h
e
v
o
ice
r
ec
o
g
n
izi
n
g
s
y
s
tem
m
ig
h
t
b
e
p
r
o
b
lem
a
tic
if
th
e
en
r
o
lled
p
er
s
o
n
lo
s
es
th
eir
v
o
ice,
th
e
n
it
m
ay
lead
to
d
if
f
ic
u
lty
in
id
en
tific
atio
n
.
T
h
ir
d
ly
,
if
a
p
e
r
s
o
n
s
u
f
f
e
r
s
f
r
o
m
a
r
th
r
itis
,
th
en
h
e
/s
h
e
m
i
g
h
t
h
av
e
d
if
f
icu
lty
b
ein
g
au
th
o
r
ize
d
o
n
a
h
an
d
g
eo
m
etr
y
b
ase
s
y
s
te
m
.
Mo
r
eo
v
e
r
,
in
a
f
ac
e
r
ec
o
g
n
izin
g
s
y
s
tem
m
ajo
r
p
r
o
b
lem
f
ac
ed
is
d
u
e
to
th
e
d
is
p
ar
it
y
in
f
ea
tu
r
es
ca
u
s
ed
b
y
v
ar
i
o
u
s
f
ac
t
o
r
s
lik
e
f
ac
ial
e
x
p
r
ess
io
n
ch
a
n
g
es,
illu
m
in
atio
n
ch
an
g
es,
an
d
m
aj
o
r
ly
d
u
e
to
o
cc
lu
s
io
n
.
Fin
ally
,
o
n
e
o
f
th
e
m
o
s
t
r
eliab
le
ir
is
r
ec
o
g
n
itio
n
s
y
s
tem
s
also
f
ac
es
r
ec
o
g
n
itio
n
is
s
u
es
d
u
e
t
o
th
e
e
y
elash
es,
len
s
es,
an
d
r
e
f
lectio
n
s
f
r
o
m
o
b
s
tacle
s
.
Fu
r
th
er
m
o
r
e
,
b
ec
au
s
e
o
f
th
e
n
u
m
b
er
o
f
ch
al
len
g
es
an
d
is
s
u
es,
th
e
ac
c
u
r
ac
y
o
f
th
e
s
en
s
in
g
s
y
s
tem
s
is
b
e
co
m
in
g
lo
w
wh
ic
h
s
tim
u
lates
th
e
in
ter
est
to
wo
r
k
in
th
is
ar
ea
.
T
o
o
v
e
r
co
m
e
t
h
e
ab
o
v
e
-
m
e
n
tio
n
ed
p
r
o
b
lem
f
ac
ed
in
u
n
im
o
d
al
b
io
m
etr
ic
s
y
s
t
em
s
we
s
u
g
g
est
u
s
in
g
m
u
ltimo
d
al
b
io
m
e
tr
ics.
T
h
e
k
ey
f
ac
to
r
av
aila
b
le
in
m
u
ltimo
d
al
b
io
m
etr
ics
is
th
e
f
u
s
io
n
tech
n
iq
u
es.
As
p
e
r
o
u
r
r
ev
iew,
we
h
av
e
co
m
e
ac
r
o
s
s
a
wid
e
r
an
g
e
o
f
f
u
s
io
n
tech
n
iq
u
es,
a
p
r
o
p
er
co
m
b
in
a
tio
n
o
f
th
ese
ex
is
tin
g
f
u
s
io
n
tech
n
iq
u
es
lead
s
to
th
e
s
o
lu
tio
n
f
o
r
th
e
a
b
o
v
e
-
m
en
tio
n
ed
p
r
o
b
lem
s
.
T
h
e
n
e
u
r
al
n
etwo
r
k
alo
n
g
with
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
with
p
r
o
p
e
r
p
r
o
ce
s
s
in
g
an
d
f
u
s
io
n
tec
h
n
iq
u
es so
lv
es th
e
is
s
u
es f
ac
ed
b
y
th
e
b
io
m
etr
ic
s
y
s
tem
s
.
8.
CO
NCLU
SI
O
N
A
r
esear
ch
-
b
ased
r
e
v
iew
is
p
er
f
o
r
m
e
d
o
n
a
B
io
m
etr
ic
-
b
ase
d
au
th
en
ticatio
n
s
y
s
tem
.
I
n
th
is
p
ap
er
,
a
d
etailed
s
tu
d
y
o
f
b
io
m
etr
ics
s
t
ar
tin
g
f
r
o
m
tr
ad
itio
n
al
s
ec
u
r
ity
to
t
h
e
r
ec
e
n
t
m
u
ltimo
d
al
b
io
m
etr
ic
s
y
s
tem
s
h
as
b
ee
n
d
o
n
e.
W
e
h
av
e
d
is
cu
s
s
ed
two
m
ain
class
if
icatio
n
s
o
f
b
io
m
etr
ic
s
y
s
tem
s
i.e
.
,
u
n
im
o
d
al,
an
d
m
u
ltimo
d
al
s
y
s
tem
s
.
B
y
th
e
im
p
er
f
ec
tio
n
o
f
u
n
im
o
d
al
an
d
o
t
h
er
p
r
o
b
le
m
s
,
th
e
m
u
ltimo
d
al
r
ec
o
g
n
itio
n
s
y
s
tem
h
as
b
ee
n
in
tr
o
d
u
ce
d
.
T
h
e
v
ar
io
u
s
m
eth
o
d
s
an
d
lev
els
o
f
f
u
s
io
n
a
v
ai
lab
le
in
m
u
ltimo
d
al
s
y
s
tem
s
wer
e
also
co
v
er
ed
.
T
h
is
p
ap
er
g
iv
es
clar
ity
t
h
at
th
er
e'
s
a
h
u
g
e
s
co
p
e
o
f
im
p
r
o
v
em
en
t
to
id
e
n
tify
t
h
e
s
o
lu
tio
n
s
to
th
e
is
s
u
es
o
b
s
er
v
ed
in
t
h
e
v
ar
io
u
s
b
io
m
e
tr
ic
r
ec
o
g
n
itio
n
s
y
s
tem
s
also
i
n
th
e
d
if
f
e
r
en
t
lev
els
o
f
f
u
s
io
n
as
well
as
v
ar
i
o
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
C
o
mp
a
r
is
o
n
o
f le
ve
ls
a
n
d
fu
s
i
o
n
a
p
p
r
o
a
ch
es fo
r
mu
ltimo
d
a
l b
io
metrics
(
S.
S
u
ja
n
a
)
799
m
eth
o
d
s
o
f
f
u
s
io
n
.
Mu
ltimo
d
al
b
io
m
etr
ics
is
an
ex
citin
g
an
d
in
ter
esti
n
g
r
esear
ch
ar
ea
th
a
t
m
ak
es
a
f
u
s
io
n
o
f
s
o
u
r
ce
s
at
v
ar
i
o
u
s
lev
els
f
o
r
b
etter
ac
c
u
r
ac
y
,
s
ec
u
r
ity
,
an
d
r
eliab
ilit
y
.
T
h
e
ap
p
licati
o
n
s
an
d
n
ee
d
f
o
r
Mu
ltimo
d
al
b
io
m
etr
ic
w
o
u
ld
b
e
an
in
teg
r
al
p
ar
t
o
f
th
e
f
u
tu
r
e
g
en
er
atio
n
o
f
a
n
y
tech
n
o
lo
g
y
.
RE
F
E
R
E
NC
E
S
[1
]
Lah
m
id
i
A
.
,
M
in
a
o
u
i
K
.
,
a
n
d
Rz
i
z
a
M
.
,
“
A ro
b
u
st min
u
ti
a
-
b
a
se
d
a
p
p
r
o
a
c
h
fo
r
se
c
u
ri
n
g
fi
n
g
e
r
p
rin
t
t
e
m
p
late
s,”
2
0
1
8
9
th
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
siu
m
o
n
S
ig
n
a
l,
Ima
g
e
,
Vi
d
e
o
a
n
d
Co
mm
u
n
ica
ti
o
n
s
(IS
I
VC)
,
2
0
1
8
,
p
p
.
2
8
6
-
2
9
0
,
d
o
i:
1
0
.
1
1
0
9
/IS
IVC.
2
0
1
8
.
8
7
0
9
1
8
4
.
[2
]
Li
a
k
a
t
Ali
M
.
,
M
o
n
a
c
o
J.
V
.
,
Ta
p
p
e
rt
C.
C
.
,
a
n
d
Qi
u
M
.
,
“
Ke
y
str
o
k
e
b
io
m
e
tri
c
sy
ste
m
s
fo
r
u
se
r
a
u
th
e
n
ti
c
a
ti
o
n
,”
J
o
u
rn
a
l
o
f
S
i
g
n
a
l
Pro
c
e
ss
in
g
S
y
ste
ms
.
,
v
o
l
.
8
5
,
n
o
.
2
-
3
,
p
p
.
1
7
5
-
1
90
,
M
a
r
.
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
2
6
5
-
0
1
6
-
1
1
1
4
-
9
.
[3
]
Ku
m
a
r
T
.
,
B
h
u
sh
a
n
S
.
,
a
n
d
Ja
n
g
ra
S
.
,
“
A
Brief
Re
v
iew
o
f
Im
a
g
e
Qu
a
li
ty
E
n
h
a
n
c
e
m
e
n
t
Tec
h
n
iq
u
e
s
Ba
se
d
M
u
lt
i
-
m
o
d
a
l
Bi
o
m
e
tri
c
F
u
si
o
n
S
y
ste
m
s,”
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
In
f
o
rm
a
ti
c
s
fo
r
C
o
mp
u
ti
n
g
Res
e
a
rc
h
,
2
0
1
8
,
p
p
.
4
0
7
-
4
2
3
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
13
-
3
1
4
0
-
4
_
3
7
.
[4
]
P
a
th
a
k
M
.
a
n
d
S
rin
i
v
a
su
N
.
,
“
P
e
rfo
rm
a
n
c
e
o
f
M
u
lt
im
o
d
a
l
Bi
o
m
e
tri
c
S
y
ste
m
Ba
se
d
o
n
Lev
e
l
a
n
d
M
e
th
o
d
o
f
F
u
sio
n
,
”
Ch
a
k
ra
b
a
rti
A.
,
S
h
a
rm
a
N.,
a
n
d
Ba
las
V.
E.
,
Ad
v
a
n
c
e
s
in
Co
mp
u
ti
n
g
Ap
p
li
c
a
t
io
n
s
,
Ne
w
Yo
rk
,
USA:
S
p
rin
g
e
r
,
2
0
1
6
,
p
p
.
1
3
7
-
1
5
2
,
d
o
i.
o
rg
/
1
0
.
1
0
0
7
/9
7
8
-
9
8
1
-
10
-
2
6
3
0
-
0
_
9
.
[5
]
Bu
c
iu
I.
a
n
d
G
a
c
sa
d
i
A.
,
“
Bi
o
m
e
tri
c
s
sy
ste
m
s
a
n
d
tec
h
n
o
lo
g
ies
:
A
su
rv
e
y
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
s
,
Co
mm
u
n
ica
ti
o
n
s a
n
d
Co
n
tro
l,
v
o
l.
1
1
,
n
o
.
3
,
p
p
.
3
1
5
–
3
3
0
,
2
0
1
6
,
d
o
i:
1
0
.
1
5
8
3
7
/i
jcc
c
.
2
0
1
6
.
3
.
2
5
5
6
.
[6
]
S
a
y
e
e
d
S
,
Na
sir
I,
O
n
g
T
.
S
,
“
An
Eff
icie
n
t
M
u
lt
imo
d
a
l
Bio
m
e
tri
c
Au
th
e
n
t
ica
ti
o
n
I
n
teg
ra
ti
n
g
F
in
g
e
r
p
rin
t
a
n
d
F
a
c
e
F
e
a
tu
re
s,”
Ame
ric
a
n
j
o
u
r
n
a
l
o
f
a
p
p
li
e
d
sc
ien
c
e
s,
sc
ien
c
e
p
u
b
li
c
a
ti
o
n
s
.
,
v
o
l.
1
3
,
n
o
.
1
1
,
p
p
.
1
2
2
1
-
1
2
2
7
,
2
0
1
6
,
d
o
i:
1
0
.
3
8
4
4
/aja
ss
p
.
2
0
1
6
.
1
2
2
1
.
1
2
2
7
.
[7
]
El
h
o
se
n
y
M
.
,
El
k
h
a
teb
A
.
,
S
a
h
l
o
l
A
.
,
a
n
d
Ha
ss
a
n
ien
A
.
E
.
,
“
M
u
lt
imo
d
a
l
b
i
o
m
e
tri
c
p
e
rso
n
a
l
id
e
n
ti
fica
ti
o
n
a
n
d
v
e
rifi
c
a
ti
o
n
,
”
Ha
ss
a
n
ien
A.
E.
a
n
d
Oli
v
a
D.
A.
,
A
d
v
a
n
c
e
s
in
S
o
ft
Co
mp
u
ti
n
g
a
n
d
M
a
c
h
i
n
e
L
e
a
r
n
in
g
in
Ima
g
e
Pro
c
e
ss
in
g
,
Ne
w Yo
r
k
,
USA:
S
p
r
in
g
e
r,
p
p
.
2
4
9
-
2
7
6
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
6
3
7
5
4
-
9
_
1
2
.
[8
]
Ya
n
g
W
.
,
Wan
g
S
.
,
Hu
J
.
,
Z
h
e
n
g
G
.
,
a
n
d
Va
ll
i
C
.
,
“
S
e
c
u
rit
y
a
n
d
a
c
c
u
ra
c
y
o
f
fi
n
g
e
rp
ri
n
t
-
b
a
se
d
b
io
m
e
tri
c
s:
A
re
v
iew
,
”
S
y
mm
e
try
,
v
o
l.
11
,
n
o
.
2
,
2
0
1
9
,
d
o
i:
1
0
.
3
3
9
0
/sy
m
1
1
0
2
0
1
4
1
.
[9
]
Ch
e
n
L
.
,
Z
h
a
o
G
.
,
Zh
o
u
J
.
,
Ho
A
.
T
.
,
a
n
d
C
h
e
n
g
L
.
M
.
,
“
F
a
c
e
tem
p
late
p
ro
tec
ti
o
n
u
sin
g
d
e
e
p
LDP
C
c
o
d
e
s
lea
rn
in
g
,
”
IET
B
io
me
trics
,
v
o
l.
8
,
n
o
.
3
,
p
p
.
1
9
0
-
19
7
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
4
9
/i
e
t
-
b
m
t.
2
0
1
8
.
5
1
5
6
.
[1
0
]
Ha
m
d
M
.
H
a
n
d
Ah
m
e
d
S
.
K,
“
A
Bio
m
e
tri
c
S
y
ste
m
fo
r
Iris
Re
c
o
g
n
it
i
o
n
Ba
se
d
o
n
F
o
u
rier
De
sc
rip
to
rs
a
n
d
P
rin
c
ip
le
Co
m
p
o
n
e
n
t
An
a
ly
sis,
”
Ira
q
i
J
o
u
rn
a
l
fo
r
El
e
c
trica
l
An
d
El
e
c
tro
n
ic
E
n
g
i
n
e
e
rin
g
,
v
o
l.
1
3
,
n
o
.
2
,
p
p
.
1
8
0
-
18
7
,
2
0
1
7
,
d
o
i:
1
0
.
3
3
7
6
2
/
e
e
e
j.
2
0
1
7
.
1
3
5
2
8
2
.
[1
1
]
Am
m
o
u
r
B
.
,
Bo
u
d
e
n
T
.,
a
n
d
A
m
ira
-
Biad
S
.
,
“
M
u
lt
imo
d
a
l
b
io
m
e
tri
c
id
e
n
t
ifi
c
a
ti
o
n
s
y
ste
m
b
a
se
d
o
n
th
e
fa
c
e
a
n
d
iri
s,”
In
2
0
1
7
5
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
En
g
i
n
e
e
rin
g
-
B
o
u
me
rd
e
s
(ICE
E
-
B)
,
2
0
1
7
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/ICE
E
-
B
.
2
0
1
7
.
8
1
9
1
9
8
1
.
[1
2
]
Am
m
o
u
r
B
.
,
B
o
u
d
e
n
T
.
,
a
n
d
Bo
u
b
c
h
ir
L
.
,
”
F
a
c
e
–
iri
s
m
u
lt
i
-
m
o
d
a
l
b
i
o
m
e
tri
c
sy
ste
m
u
sin
g
m
u
lt
i
-
r
e
so
lu
ti
o
n
Lo
g
-
G
a
b
o
r
fil
ter
with
sp
e
c
tral
re
g
re
ss
i
o
n
k
e
rn
e
l
d
isc
rimin
a
n
t
a
n
a
l
y
sis,”
IET
Bi
o
me
trics
,
v
o
l.
7
,
n
o
.
5
,
p
p
.
482
-
48
9
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
4
9
/i
e
t
-
b
m
t.
2
0
1
7
.
0
2
5
1
.
[1
3
]
S
u
jan
a
S
.
a
n
d
Re
d
d
y
V
.
S
.
K
.
,
”
Weig
h
ted
F
u
si
o
n
A
p
p
r
o
a
c
h
fo
r
M
u
lt
i
M
o
d
a
l
Bio
m
e
tri
c
Re
c
o
g
n
it
i
o
n
S
y
ste
m
u
sin
g
De
e
p
Ne
two
rk
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
1
,
n
o
.
12
,
p
p
.
2
2
8
2
-
2
2
9
0
,
2
0
2
0
,
d
o
i:
1
0
.
3
4
2
1
8
/i
jare
t.
1
1
.
1
2
.
2
0
2
0
.
2
1
6
.
[1
4
]
M
a
ti
n
A
.
,
M
a
h
m
u
d
F
.
,
Ah
m
e
d
T
.
,
a
n
d
Ej
a
z
M
.
S
.
,
“
Weig
h
ted
s
c
o
re
lev
e
l
fu
sio
n
o
f
iri
s
a
n
d
fa
c
e
to
id
e
n
ti
f
y
a
n
in
d
i
v
id
u
a
l
,”
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l,
C
o
mp
u
ter
a
n
d
Co
mm
u
n
ica
t
io
n
E
n
g
in
e
e
rin
g
(ECC
E)
,
201
7
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/
ECACE.
2
0
1
7
.
7
9
1
2
8
6
8
.
[1
5
]
Az
o
m
V
.
,
Ad
e
wu
m
i
A
.
,
a
n
d
Tap
a
m
o
J
.
R
.
,
“
F
a
c
e
a
n
d
Iris
b
i
o
m
e
tri
c
s
p
e
rso
n
id
e
n
ti
fica
ti
o
n
u
sin
g
h
y
b
ri
d
f
u
sio
n
a
t
fe
a
tu
re
a
n
d
sc
o
re
-
lev
e
l,
”
2
0
1
5
P
a
tt
e
rn
Rec
o
g
n
it
io
n
Asso
c
ia
ti
o
n
o
f
S
o
u
t
h
Af
ric
a
a
n
d
Ro
b
o
t
ics
a
n
d
M
e
c
h
a
tro
n
ics
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
(PR
AS
A
-
Ro
b
M
e
c
h
)
,
2
0
1
5
,
p
p
.
2
0
7
-
2
1
2
,
d
o
i:
1
0
.
1
1
0
9
/Ro
b
o
M
e
c
h
.
2
0
1
5
.
7
3
5
9
5
2
4
.
[1
6
]
Hu
o
G
.
,
Li
u
Y
.
,
Z
h
u
X
.
,
D
o
n
g
H
.
,
a
n
d
He
F
.
,
“
F
a
c
e
-
iri
s
m
u
lt
i
m
o
d
a
l
b
io
m
e
tri
c
sc
h
e
m
e
b
a
se
d
o
n
fe
a
t
u
re
lev
e
l
fu
sio
n
,
”
J
o
u
r
n
a
l
o
f
El
e
c
tro
n
ic Im
a
g
i
n
g
,
v
o
l.
2
4
,
n
o
.
6
,
2
0
1
5
,
d
o
i:
1
0
.
1
1
1
7
/1
.
JEI.
2
4
.
6
.
0
6
3
0
2
0
.
[1
7
]
Esk
a
n
d
a
ri
M
.
a
n
d
T
o
y
g
a
r
Ö
.
,
“
S
e
lec
ti
o
n
o
f
o
p
ti
m
ize
d
fe
a
tu
re
s
a
n
d
we
ig
h
ts
o
n
fa
c
e
-
iri
s
fu
sio
n
u
sin
g
d
istan
c
e
ima
g
e
s,”
Co
mp
u
ter
Vi
si
o
n
a
n
d
Ima
g
e
U
n
d
e
rs
ta
n
d
i
n
g
,
v
o
l.
1
,
n
o
.
1
3
7
,
p
p
.
63
-
75
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
v
iu
.
2
0
1
5
.
0
2
.
0
1
1
.
[1
8
]
Kh
iari
-
Hili
N
.
,
M
o
n
tag
n
e
C
.
,
Lel
a
n
d
a
is S
.
,
a
n
d
Ha
m
ro
u
n
i
K
.
,
“
Qu
a
li
ty
d
e
p
e
n
d
e
n
t
m
u
lt
im
o
d
a
l
f
u
sio
n
o
f
fa
c
e
a
n
d
iri
s
b
io
m
e
tri
c
s,”
In
2
0
1
6
S
ixt
h
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
T
h
e
o
ry
,
T
o
o
ls
a
n
d
A
p
p
l
i
c
a
ti
o
n
s
(IP
T
A)
,
2
0
1
6
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/I
P
TA.
2
0
1
6
.
7
8
2
0
9
5
4
.
[1
9
]
M
in
a
e
e
S
.
,
Ab
d
o
lras
h
i
d
i
A
.
,
a
n
d
Wan
g
Y
.
,
“
F
a
c
e
re
c
o
g
n
it
i
o
n
u
sin
g
sc
a
tt
e
rin
g
c
o
n
v
o
l
u
ti
o
n
a
l
n
e
tw
o
r
k
,
”
2
0
1
7
IEE
E
sig
n
a
l
p
ro
c
e
ss
in
g
in
me
d
i
c
in
e
a
n
d
b
i
o
lo
g
y
sy
mp
o
si
u
m
(S
P
M
B)
,
2
0
1
7
De
c
2
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/S
P
M
B.
2
0
1
7
.
8
2
5
7
0
2
5
.
[2
0
]
S
h
a
rifi
O
.
a
n
d
Esk
a
n
d
a
ri
M
.
,
“
Op
ti
m
a
l
fa
c
e
-
iri
s
m
u
lt
imo
d
a
l
fu
sio
n
sc
h
e
m
e
,
”
S
y
mm
e
try
,
v
o
l.
8
,
n
o
.
6
,
2
0
1
6
,
d
o
i:
1
0
.
3
3
9
0
/sy
m
8
0
6
0
0
4
8
.
[2
1
]
Ah
m
a
d
i
N
.
,
a
n
d
Ak
b
a
riza
d
e
h
G
.
,
"
Hy
b
ri
d
r
o
b
u
st
iri
s
re
c
o
g
n
it
i
o
n
a
p
p
r
o
a
c
h
u
sin
g
iri
s
ima
g
e
p
re
-
p
ro
c
e
ss
in
g
,
two
-
d
ime
n
sio
n
a
l
g
a
b
o
r
fe
a
tu
re
s
a
n
d
m
u
lt
i
-
lay
e
r
p
e
rc
e
p
tro
n
n
e
u
ra
l
n
e
two
rk
/
P
S
O
,
"
Ie
t
Bi
o
me
trics
,
v
o
l.
7
,
n
o
.
2
,
p
p
.
1
5
3
-
162
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
4
9
/
i
e
t
-
b
m
t.
2
0
1
7
.
0
0
4
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
23
,
No
.
2
,
Au
g
u
s
t
20
21
:
7
91
-
8
0
1
800
[2
2
]
Am
m
o
u
r
B
.
,
Bo
u
d
e
n
T
.
,
a
n
d
Bo
u
b
c
h
ir
L
.
,
“
F
a
c
e
-
iri
s
m
u
lt
imo
d
a
l
b
io
m
e
tri
c
sy
ste
m
b
a
se
d
o
n
h
y
b
ri
d
lev
e
l
fu
si
o
n
,
”
2
0
1
8
4
1
st
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
T
e
lec
o
mm
u
n
ica
ti
o
n
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
(T
S
P)
,
2
0
1
8
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/T
S
P
.
2
0
1
8
.
8
4
4
1
2
7
9
.
[2
3
]
Du
a
M.,
G
u
p
ta
R.
,
Kh
a
ri
M.
,
a
n
d
Cre
sp
o
R
.
G
.
,
“
B
io
m
e
tri
c
iri
s
re
c
o
g
n
it
io
n
u
sin
g
ra
d
ial
b
a
sis
fu
n
c
ti
o
n
n
e
u
ra
l
n
e
two
rk
,
”
S
o
ft
Co
m
p
u
t
in
g
,
v
o
l
.
2
3
,
n
o
.
2
2
,
p
p
.
1
1
8
0
1
-
1
1
8
1
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/s
0
0
5
0
0
-
0
1
8
-
0
3
7
3
1
-
4
.
[
2
4
]
A
g
a
r
w
a
l
R
.
,
S
i
n
g
h
J
a
l
a
l
A
.
,
a
n
d
A
r
y
a
K
.
V
.
,
“
A
m
u
l
t
i
m
o
d
a
l
l
i
v
e
n
e
s
s
d
e
te
c
t
i
o
n
u
s
i
n
g
s
t
a
t
i
s
t
ic
a
l
te
x
tu
r
e
f
e
a
t
u
re
s
a
n
d
s
p
a
t
i
a
l
a
n
a
l
y
s
is
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
7
9
,
n
o
.
1
1
,
p
p
.
1
-
2
5
,
J
a
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
1
9
-
0
8
3
1
3
-
6
.
[2
5
]
M
u
s
t
a
f
a
A
.
S
.
,
A
b
d
u
l
e
l
a
h
A
.
J
.
,
a
n
d
A
h
m
e
d
A
.
K
.
,
”
M
u
l
t
i
m
o
d
a
l
B
i
o
m
e
t
r
i
c
S
y
s
te
m
I
r
is
a
n
d
F
i
n
g
e
r
p
r
i
n
t
R
e
c
o
g
n
i
t
i
o
n
B
a
s
e
d
o
n
F
u
s
i
o
n
T
e
c
h
n
i
q
u
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
7
4
2
3
-
7
4
3
2
,
2
0
2
0
.
[2
6
]
M
a
n
so
u
ra
L
.
,
N
o
u
re
d
d
in
e
A
.
,
As
sa
s
O
.
,
a
n
d
Ya
ss
in
e
A
.
,
“
Bi
o
m
e
tri
c
re
c
o
g
n
it
io
n
b
y
m
u
lt
imo
d
a
l
fa
c
e
a
n
d
iri
s
u
sin
g
F
F
T
a
n
d
S
VD
m
e
th
o
d
s
Wi
t
h
A
d
a
p
ti
v
e
S
c
o
re
No
rm
a
li
z
a
ti
o
n
,
”
2
0
1
9
4
t
h
W
o
rld
Co
n
fer
e
n
c
e
o
n
C
o
mp
lex
S
y
ste
ms
(W
CCS
)
,
2
0
1
9
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
0
9
/ICo
CS
.
2
0
1
9
.
8
9
3
0
7
4
8
.
[2
7
]
Ra
ja
J
.
,
G
u
n
a
se
k
a
ra
n
K
.
,
a
n
d
P
it
c
h
a
i
R
.
,
“
P
ro
g
n
o
stic
e
v
a
lu
a
ti
o
n
o
f
m
u
lt
im
o
d
a
l
b
i
o
m
e
tri
c
traits
re
c
o
g
n
it
io
n
b
a
se
d
h
u
m
a
n
fa
c
e
,
fin
g
e
r
p
ri
n
t
a
n
d
ir
i
s
ima
g
e
s
u
sin
g
e
n
se
m
b
led
S
VM
c
las
sifier,”
Clu
ste
r
Co
mp
u
ti
n
g
,
v
o
l.
2
2
,
n
o
.
1
,
p
p
.
2
1
5
-
2
8
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
0
7
/s1
0
5
8
6
-
0
1
8
-
2
6
4
9
-
2
.
[2
8
]
Am
m
o
u
r
B
.
,
B
o
u
b
c
h
ir
L
.
,
Bo
u
d
e
n
T
.
,
a
n
d
Ra
m
d
a
n
i
M
.
,
“
F
a
c
e
-
Iris
M
u
lt
imo
d
a
l
B
io
m
e
tri
c
Id
e
n
ti
fic
a
ti
o
n
S
y
ste
m
,
”
El
e
c
tro
n
ics
,
v
o
l.
9
,
n
o
.
1
,
p
.
8
5
,
2
0
2
0
Ja
n
,
d
o
i
:
1
0
.
3
3
9
0
/ele
c
tro
n
ics
9
0
1
0
0
8
5
.
[2
9
]
S
iree
sh
a
V
.
a
n
d
Re
d
d
y
S
.
R
.
,
“
Two
Lev
e
ls
F
u
si
o
n
B
a
se
d
M
u
l
ti
m
o
d
a
l
Bi
o
m
e
tri
c
Au
th
e
n
ti
c
a
ti
o
n
Us
in
g
Iris
a
n
d
F
in
g
e
r
p
rin
t
M
o
d
a
li
ti
e
s,”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
In
telli
g
e
n
t
E
n
g
i
n
e
e
rin
g
a
n
d
S
y
ste
ms
,
v
o
l.
9
,
n
o
.
3
,
p
p
.
2
1
-
3
5
,
2
0
1
6
,
d
o
i:
1
0
.
2
2
2
6
6
/IJIES
2
0
1
6
.
0
9
3
0
.
0
3
.
[3
0
]
Ch
a
u
d
h
a
ry
S
.
a
n
d
Na
th
R
.
,
“
A
ro
b
u
st
m
u
lt
imo
d
a
l
b
i
o
m
e
tri
c
sy
ste
m
in
teg
ra
ti
n
g
iri
s,
fa
c
e
a
n
d
fi
n
g
e
rp
ri
n
t
u
sin
g
m
u
lt
ip
le
S
VMs,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
7
,
n
o
.
2
,
2
0
1
6
,
d
o
i:
1
0
.
2
6
4
8
3
/
ij
a
rc
s.v
7
i
2
.
2
6
4
7
.
[3
1
]
Ka
b
ir
W
.
,
Ah
m
a
d
M
.
O
.
,
a
n
d
S
w
a
m
y
M
.
N
.
,
“
A
m
u
lt
i
-
b
io
m
e
tri
c
sy
ste
m
b
a
se
d
o
n
fe
a
tu
re
a
n
d
sc
o
re
lev
e
l
fu
sio
n
s,
”
IEE
E
Acc
e
ss
,
v
o
l
.
7
,
p
p
.
5
9
4
3
7
-
5
9
4
5
0
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/ACCES
S
.
2
0
1
9
.
2
9
1
4
9
9
2
.
[3
2
]
P
a
ti
l
A.
P
.
a
n
d
Bh
a
l
k
e
D.
G
.
,
“
F
u
sio
n
o
f
fi
n
g
e
rp
r
in
t
,
p
a
lmp
rin
t
a
n
d
iri
s
fo
r
p
e
rso
n
id
e
n
t
if
ica
ti
o
n
,
”
2
0
1
6
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
u
to
ma
ti
c
Co
n
tro
l
a
n
d
Dy
n
a
mic
Op
ti
miza
ti
o
n
T
e
c
h
n
iq
u
e
s
(ICACDOT)
,
2
0
1
6
,
p
p
.
9
6
0
-
963
,
d
o
i:
1
0
.
1
1
0
9
/ICAC
DO
T.
2
0
1
6
.
7
8
7
7
7
3
0
.
[3
3
]
To
y
g
a
r
Ö
.
,
Alq
a
ra
ll
e
h
E
.
,
a
n
d
Afa
n
e
h
A
.
,
”
P
e
rso
n
Id
e
n
ti
fica
ti
o
n
Us
in
g
M
u
lt
imo
d
a
l
Bio
m
e
tri
c
s
u
n
d
e
r
Diffe
re
n
t
Ch
a
ll
e
n
g
e
s,”
Hu
m
a
n
-
R
o
b
o
t
I
n
ter
a
c
ti
o
n
-
T
h
e
o
ry
a
n
d
A
p
p
l
ica
ti
o
n
,
p
p
.
8
1
-
9
6
,
2
0
1
8
,
d
o
i:
1
0
.
5
7
7
2
/i
n
tec
h
o
p
e
n
.
7
1
6
6
7
.
[3
4
]
Ali
M
.
M
.
,
M
a
h
a
le
V
.
H
.
,
Ya
n
n
a
wa
r
P
.
,
a
n
d
G
a
ik
wa
d
A.
T
.
,
“
F
in
g
e
rp
rin
t
re
c
o
g
n
i
ti
o
n
f
o
r
p
e
rso
n
id
e
n
ti
fica
ti
o
n
a
n
d
v
e
rifi
c
a
ti
o
n
b
a
se
d
o
n
m
in
u
ti
a
e
m
a
t
c
h
in
g
,
”
2
0
1
6
IEE
E
6
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
d
Co
mp
u
ti
n
g
(IA
CC)
,
2
0
1
6
,
p
p
.
3
3
2
-
3
3
9
,
d
o
i:
1
0
.
1
1
0
9
/IACC.
2
0
1
6
.
6
9
.
[3
5
]
S
a
rh
a
n
S
.
,
Alh
a
ss
a
n
S
.,
a
n
d
E
lmo
u
g
y
S
.
,
“
M
u
lt
imo
d
a
l
b
i
o
m
e
tri
c
sy
ste
m
s:
a
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
”
Ara
b
ia
n
J
o
u
rn
a
l
fo
r S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
4
2
,
n
o
.
2
,
p
p
.
4
4
3
-
4
5
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
7
/s1
3
3
6
9
-
0
1
6
-
2
2
4
1
-
0
.
[3
6
]
G
a
d
R.
,
El
-
F
ish
a
wy
N.
,
El
-
S
a
y
e
d
A.
Y,
a
n
d
Z
o
rk
a
n
y
M
.
,
“
M
u
lt
i
-
b
io
m
e
tri
c
sy
ste
m
s:
a
sta
te
o
f
t
h
e
a
rt
su
rv
e
y
a
n
d
re
se
a
rc
h
d
irec
ti
o
n
s,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Co
m
p
u
t
e
r
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
t
io
n
s
(IJ
ACS
A)
,
v
o
l
.
6
,
n
o
.
6
,
2
0
1
5
,
d
o
i:
1
0
.
1
4
5
6
9
/IJACS
A.2
0
1
5
.
0
6
0
6
1
8
.
[3
7
]
S
a
n
jek
a
r
P
.
S
.
a
n
d
P
a
ti
l
J.
B
.
,
“
An
o
v
e
rv
iew
o
f
m
u
lt
imo
d
a
l
b
io
m
e
t
rics
,
”
S
ig
n
a
l
&
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
5
7
-
6
4
,
2
0
1
3
F
e
b
1
,
d
o
i:
1
0
.
5
1
2
1
/si
p
ij
.
2
0
1
3
.
4
1
0
5
.
[3
8
]
Ja
m
d
a
r
C
.
a
n
d
B
o
k
e
A
.
,
“
M
u
lt
im
o
d
a
l
b
i
o
m
e
tri
c
id
e
n
ti
fica
ti
o
n
s
y
st
e
m
u
sin
g
f
u
sio
n
le
v
e
l
o
f
m
a
tch
i
n
g
sc
o
re
lev
e
l
in
sin
g
le
m
o
d
a
l
t
o
m
u
lt
i
-
m
o
d
a
l
b
io
m
e
tri
c
sy
ste
m
,
”
2
0
1
7
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
En
e
rg
y
,
Co
mm
u
n
ica
ti
o
n
,
Da
t
a
An
a
lytics
a
n
d
S
o
ft
C
o
mp
u
ti
n
g
(IC
ECDS
)
,
2
0
1
7
,
p
p
.
2
2
7
7
-
2
2
8
0
,
d
o
i
:
1
0
.
1
1
0
9
/ICE
CDS.
2
0
1
7
.
8
3
8
9
8
5
8
.
[3
9
]
Olo
y
e
d
e
M
.
O
.
a
n
d
Ha
n
c
k
e
G
.
P
.
,
“
Un
imo
d
a
l
a
n
d
m
u
l
ti
m
o
d
a
l
b
i
o
m
e
tri
c
se
n
sin
g
sy
ste
m
s:
a
re
v
iew
,
”
IEE
E
Acc
e
ss
,
v
o
l.
4
,
p
p
.
7
5
3
2
-
5
5
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
0
9
/ACCE
S
S
.
2
0
1
6
.
2
6
1
4
7
2
0
.
[4
0
]
Ka
u
r
G
,
Bh
u
sh
a
n
S
.,
a
n
d
S
in
g
h
D
.
,
“
F
u
sio
n
in
m
u
lt
imo
d
a
l
b
io
m
e
tri
c
sy
ste
m
:
A
re
v
iew
,
”
In
d
ia
n
J
o
u
rn
a
l
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
0
,
n
o
.
2
8
,
p
p
.
1
-
6
,
2
0
1
7
,
d
o
i:
1
0
.
1
7
4
8
5
/i
jst/
2
0
1
7
/
v
1
0
i1
9
/1
1
4
3
8
2
.
[4
1
]
F
ried
m
a
n
L
.
a
n
d
Ko
m
o
g
o
rtse
v
O.
V
.
,
“
As
se
ss
m
e
n
t
o
f
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
se
v
e
n
b
io
m
e
tri
c
fe
a
tu
r
e
n
o
rm
a
li
z
a
ti
o
n
tec
h
n
iq
u
e
s,”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
Fo
re
n
sic
s
a
n
d
S
e
c
u
rity
,
v
o
l.
1
4
,
n
o
.
1
0
,
p
p
.
2
5
2
8
-
2
5
3
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
1
0
9
/T
IF
S
.
2
0
1
9
.
2
9
0
4
8
4
4
.
[4
2
]
S
u
lt
a
n
a
M
.
,
P
a
u
l
P
.
P
.
,
a
n
d
G
a
v
ril
o
v
a
M
.
L
.
,
“
S
o
c
ial
b
e
h
a
v
io
ra
l
in
fo
rm
a
ti
o
n
fu
sio
n
in
m
u
l
ti
m
o
d
a
l
b
io
m
e
tri
c
s,”
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s:
S
y
ste
ms
,
v
o
l.
4
8
,
n
o
.
1
2
,
p
p
.
2
1
7
6
-
2
1
8
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
1
0
9
/T
S
M
C.
2
0
1
7
.
2
6
9
0
3
2
1
.
[4
3
]
Walia
G
.
S
.
,
S
in
g
h
T
.
,
S
in
g
h
K
.
,
a
n
d
Ve
rm
a
N
.
,
“
Ro
b
u
st
m
u
lt
imo
d
a
l
b
io
m
e
tri
c
sy
ste
m
b
a
se
d
o
n
o
p
ti
m
a
l
sc
o
re
lev
e
l
fu
sio
n
m
o
d
e
l
,
“
Exp
e
rt S
y
ste
ms
wi
th
A
p
p
li
c
a
ti
o
n
s
,
v
o
l
.
1
1
6
,
p
p
.
3
6
4
-
3
7
6
,
2
0
1
9
,
d
o
i:
1
0
.
1
0
1
6
/
j.
e
sw
a
.
2
0
1
8
.
0
8
.
0
3
6
.
[4
4
]
Ku
m
a
r
A
.
a
n
d
S
h
e
k
h
a
r
S
.
,
“
P
e
rso
n
a
l
id
e
n
ti
fica
ti
o
n
u
sin
g
m
u
l
ti
b
i
o
m
e
tri
c
s
ra
n
k
-
lev
e
l
fu
si
o
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s,
Pa
rt
C
(A
p
p
l
ica
ti
o
n
s
a
n
d
Rev
iews
)
,
v
o
l.
4
1
,
n
o
.
5
,
p
p
.
7
4
3
-
7
5
2
,
2
0
1
0
,
d
o
i:
1
0
.
1
1
0
9
/T
S
M
CC.2
0
1
0
.
2
0
8
9
5
1
6
.
[4
5
]
Li
J
.
,
Qi
u
T
.
,
Wen
C
.
,
Xie
K
.
,
a
n
d
Wen
F
.
Q
.
,
“
Ro
b
u
st
fa
c
e
re
c
o
g
n
it
io
n
u
sin
g
th
e
d
e
e
p
C2
D
-
CNN
m
o
d
e
l
b
a
se
d
o
n
d
e
c
isio
n
-
lev
e
l
fu
si
o
n
,
”
S
e
n
so
rs
,
v
o
l.
1
8
,
n
o
.
7
,
p
p
.
2
0
8
0
,
2
0
1
8
,
d
o
i:
1
0
.
3
3
9
0
/s
1
8
0
7
2
0
8
0
.
[4
6
]
M
e
h
d
i
C
h
e
rra
t
E
.
,
Ala
o
u
i
R
.
,
a
n
d
Bo
u
z
a
h
ir
H
.
,
“
Co
n
v
o
l
u
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
s
a
p
p
ro
a
c
h
f
o
r
m
u
lt
im
o
d
a
l
b
io
m
e
tri
c
id
e
n
ti
fica
ti
o
n
sy
ste
m
u
si
n
g
th
e
f
u
sio
n
o
f
f
in
g
e
rp
rin
t,
f
in
g
e
r
-
v
e
in
a
n
d
fa
c
e
ima
g
e
s,”
Pee
rJ
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
6
,
p
.
e
2
4
8
,
2
0
2
0
,
d
o
i:
1
0
.
7
7
1
7
/
p
e
e
rj
-
c
s.2
4
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.