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.
38
,
No
.
3
,
J
u
n
e
2
0
2
5
,
p
p
.
202
0
~
203
0
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
38
.i
3
.
pp
202
0
-
2
0
3
0
2020
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Desig
n of
face
rec
o
g
nition ba
sed ef
f
ective auto
ma
ted
sm
a
rt
a
tt
enda
nce
sy
ste
m
J
y
o
t
i L.
B
a
ng
a
re
1
,
Dipte
e
Ch
ik
m
urg
e
2
,
K
a
rt
hik
e
y
a
n K
a
li
y
a
perum
a
l
3
,
M
ee
na
k
s
hi
4
,
Su
nil
L
.
B
a
ng
a
re
5
,
K
is
ho
ri
K
a
s
a
t
6
,
K
a
ntila
l P
i
t
a
m
ba
r
Ra
ne
7
,
Ra
v
i K
is
ho
re
Veluri
8
,
B
a
t
y
rk
ha
n O
m
a
ro
v
9
,
M
a
lik
J
a
wa
rneh
10
,
Abhi
s
hek
Ra
g
hu
v
a
ns
hi
11
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
M
K
S
S
S
’
s,
C
u
mm
i
n
s
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
f
o
r
W
o
me
n
,
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
si
t
y
,
P
u
n
e
,
I
n
d
i
a
2
S
c
h
o
o
l
o
f
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
r
i
n
g
,
M
I
T
A
c
a
d
e
m
y
o
f
En
g
i
n
e
e
r
i
n
g
,
A
l
a
n
d
i
,
I
n
d
i
a
3
D
e
p
a
r
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
Te
c
h
n
o
l
o
g
y
,
A
mb
o
U
n
i
v
e
r
s
i
t
y
,
A
mb
o
,
Et
h
i
o
p
i
a
4
S
c
h
o
o
l
o
f
J
o
u
r
n
a
l
i
sm
a
n
d
M
a
ss
C
o
m
mu
n
i
c
a
t
i
o
n
,
A
p
e
e
j
a
y
S
t
y
a
U
n
i
v
e
r
si
t
y
S
o
h
n
a
H
a
r
y
a
n
a
,
G
u
r
g
a
o
n
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
S
a
v
i
t
r
i
b
a
i
P
h
u
l
e
P
u
n
e
U
n
i
v
e
r
s
i
t
y
,
S
i
n
h
g
a
d
A
c
a
d
e
my
o
f
En
g
i
n
e
e
r
i
n
g
,
P
u
n
e
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
t
u
d
i
e
s,
S
y
mb
i
o
si
s Sc
h
o
o
l
f
o
r
Li
b
e
r
a
l
A
r
t
s,
S
y
m
b
i
o
si
s
I
n
t
e
r
n
a
t
i
o
n
a
l
(
D
e
e
me
d
U
n
i
v
e
r
si
t
y
)
,
P
u
n
e
,
I
n
d
i
a
7
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
T
e
l
e
c
o
mm
u
n
i
c
a
t
i
o
n
s
En
g
i
n
e
e
r
i
n
g
,
B
h
a
r
a
t
i
V
i
d
y
a
p
e
e
t
h
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
N
a
v
i
M
u
m
b
a
i
,
I
n
d
i
a
8
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
A
d
i
t
y
a
U
n
i
v
e
r
si
t
y
,
A
n
d
h
r
a
P
r
a
d
e
s
h
,
I
n
d
i
a
9
Al
-
F
a
r
a
b
i
K
a
z
a
k
h
N
a
t
i
o
n
a
l
U
n
i
v
e
r
si
t
y
,
I
n
t
e
r
n
a
t
i
o
n
a
l
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
U
n
i
v
e
r
si
t
y
,
A
l
m
a
t
y
,
K
a
z
a
k
h
st
a
n
10
C
o
l
l
e
g
e
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
mat
i
c
s
,
A
mm
a
n
A
r
a
b
U
n
i
v
e
r
si
t
y
,
A
mm
a
n
,
J
o
r
d
a
n
11
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
M
a
h
a
k
a
l
I
n
st
i
t
u
t
e
o
f
T
e
c
h
n
o
l
o
g
y
,
U
j
j
a
i
n
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
11
,
2
0
2
4
R
ev
is
ed
J
an
10
,
2
0
2
5
Acc
ep
ted
Feb
27
,
2
0
2
5
Th
e
issu
e
o
f
a
u
t
o
m
a
ti
c
a
tt
e
n
d
a
n
c
e
m
a
rk
in
g
h
a
s
b
e
e
n
su
c
c
e
ss
fu
ll
y
r
e
so
lv
e
d
in
re
c
e
n
t
y
e
a
rs
t
h
ro
u
g
h
th
e
u
ti
l
iza
ti
o
n
o
f
sta
n
d
a
rd
b
i
o
m
e
tri
c
a
p
p
ro
a
c
h
e
s.
Alth
o
u
g
h
th
is
stra
teg
y
is
a
u
t
o
m
a
ted
a
n
d
fo
rwa
rd
-
t
h
in
k
i
n
g
,
it
s
u
se
i
s
h
in
d
e
re
d
b
y
ti
m
e
c
o
n
stra
i
n
ts.
Ac
q
u
ir
in
g
a
th
u
m
b
imp
re
ss
io
n
re
q
u
ires
th
e
in
d
iv
id
u
a
l
to
fo
rm
a
li
n
e
,
wh
ich
m
ig
h
t
lea
d
to
in
c
o
n
v
e
n
ien
c
e
.
Th
e
i
n
n
o
v
a
t
iv
e
v
isu
a
l
sy
ste
m
u
ti
li
z
e
s
a
c
o
m
p
u
ter
a
n
d
c
a
m
e
ra
to
d
e
tec
t
a
n
d
re
c
o
rd
stu
d
e
n
ts
’
a
tt
e
n
d
a
n
c
e
b
a
se
d
o
n
t
h
e
ir
fa
c
ial
fe
a
tu
re
s.
Th
is
a
rti
c
le
p
re
se
n
ts
a
fa
c
e
re
c
o
g
n
it
i
o
n
b
a
se
d
a
u
to
m
a
ti
c
a
tt
e
n
d
a
n
c
e
sy
ste
m
.
Th
is
sy
ste
m
in
c
lu
d
e
s
-
ima
g
e
a
c
q
u
isit
io
n
,
ima
g
e
e
n
h
a
n
c
e
m
e
n
t
u
si
n
g
h
ist
o
g
ra
m
e
q
u
a
li
z
a
ti
o
n
,
ima
g
e
se
g
m
e
n
tatio
n
b
y
f
u
z
z
y
C
m
e
a
n
s
c
lu
ste
rin
g
tec
h
n
i
q
u
e
,
b
u
il
d
i
n
g
c
las
sifica
ti
o
n
m
o
d
e
l
u
si
n
g
K
-
n
e
a
re
st
n
e
ig
h
b
o
u
r
(KN
N)
,
su
p
p
o
r
t
v
e
c
t
o
r
m
a
c
h
in
e
(S
VM)
a
n
d
A
d
a
Bo
o
st
tec
h
n
iq
u
e
.
F
o
r
e
x
p
e
rime
n
tal
wo
r
k
,
5
0
0
ima
g
e
s
o
f
stu
d
e
n
ts
o
f
a
c
las
s
a
re
se
lec
ted
a
t
r
a
n
d
o
m
.
Ac
c
u
ra
c
y
o
f
KN
N
a
lg
o
rit
h
m
in
p
ro
p
o
se
d
fra
m
e
wo
rk
is
9
8
.
7
5
%
.
It
is
h
i
g
h
e
r
th
a
n
t
h
e
a
c
c
u
ra
c
y
o
f
S
VM
(
9
6
.
2
5
%
)
a
n
d
Ad
a
Bo
o
st
(8
6
.
5
0
%
).
KN
N
is
a
lso
p
e
rfo
rm
in
g
b
e
tt
e
r
o
n
p
a
ra
m
e
ters
li
k
e
-
se
n
siti
v
it
y
,
sp
e
c
ifi
c
it
y
,
p
re
c
isio
n
a
n
d
F
_
m
e
a
su
re
.
K
ey
w
o
r
d
s
:
Acc
u
r
ac
y
Face
r
ec
o
g
n
itio
n
Fu
zz
y
C
m
ea
n
s
His
to
g
r
am
eq
u
aliza
tio
n
K
-
n
ea
r
est
n
eig
h
b
o
r
Sm
ar
t a
tten
d
an
ce
s
y
s
tem
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
:
Ab
h
is
h
ek
R
ag
h
u
v
a
n
s
h
i
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Ma
h
ak
al
I
n
s
titu
te
o
f
T
ec
h
n
o
lo
g
y
Ujjain
,
I
n
d
ia
E
m
ail:
ab
h
is
h
ek
1
4
4
8
2
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
ex
am
in
atio
n
o
f
b
io
lo
g
ical
d
ata,
o
f
ten
k
n
o
wn
as
b
io
m
etr
i
cs,
is
g
ain
in
g
s
ig
n
if
ican
ce
in
t
h
e
cu
r
r
en
t
tech
n
o
lo
g
y
lan
d
s
ca
p
e.
I
n
co
n
tem
p
o
r
ar
y
tim
es,
wh
en
in
d
iv
id
u
als
wan
t
to
au
th
en
ticate
s
o
m
eo
n
e
’
s
id
en
tific
atio
n
b
y
th
e
ex
a
m
in
atio
n
o
f
th
eir
f
i
n
g
er
p
r
in
ts
,
f
ac
ial
f
ea
tu
r
es,
b
e
h
av
io
u
r
al
ch
ar
ac
ter
is
tics
,
o
r
s
ig
n
atu
r
e,
th
ey
c
o
m
m
o
n
ly
r
e
f
er
to
th
e
f
ield
o
f
b
io
m
etr
ic
s
.
B
io
m
etr
ics
p
r
o
v
id
es
a
v
er
y
r
eliab
le
f
o
r
m
o
f
au
th
en
ticatio
n
c
o
m
p
ar
e
d
to
I
D
ca
r
d
s
,
k
e
y
s
,
PIN
s
,
p
ass
wo
r
d
s
,
o
r
o
th
er
o
u
t
d
ated
te
ch
n
iq
u
es
d
u
e
to
th
e
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
Desig
n
o
f fa
ce
r
ec
o
g
n
itio
n
b
a
s
ed
effec
tive
a
u
to
ma
ted
s
ma
r
t a
tten
d
a
n
ce
s
ystem
(
Jy
o
ti L.
B
a
n
g
a
r
e
)
2021
in
d
iv
id
u
ality
o
f
a
p
er
s
o
n
’
s
p
h
y
s
ical
an
d
b
eh
av
i
o
u
r
al
c
h
ar
ac
ter
is
tics
.
B
io
m
etr
ics
s
er
v
es
as
a
k
in
d
o
f
id
en
tific
atio
n
an
d
ac
ce
s
s
co
n
tr
o
l,
p
r
o
v
id
in
g
r
ea
lis
tic
v
er
if
icatio
n
.
Mo
r
eo
v
e
r
,
it
ca
n
b
e
em
p
lo
y
ed
to
ascer
tain
th
e
id
en
tity
o
f
a
s
p
ec
if
ic
p
er
s
o
n
.
B
io
m
etr
ic
id
e
n
tifie
r
s
ar
e
d
is
tin
ct,
q
u
an
tifia
b
le,
an
d
d
u
r
ab
le
tr
aits
th
at
ar
e
u
s
ed
to
d
ef
i
n
e
an
d
d
escr
ib
e
an
in
d
iv
id
u
al
[
1
]
.
B
io
m
etr
ic
tech
n
o
lo
g
ies,
in
clu
d
in
g
f
in
g
er
p
r
in
t,
s
m
ar
t
ca
r
d
,
d
ig
ital
s
ig
n
atu
r
e,
an
d
we
b
-
b
ase
d
s
y
s
tem
s
,
ar
e
ex
ten
s
iv
ely
u
tili
ze
d
in
v
ar
i
o
u
s
co
m
p
an
ies
th
r
o
u
g
h
o
u
t
all
d
ev
elo
p
e
d
co
u
n
t
r
ies.
T
h
is
o
b
v
iates
th
e
n
ec
ess
i
ty
f
o
r
an
y
s
u
p
p
lem
en
tar
y
d
ev
ic
es
to
d
is
ce
r
n
th
e
lear
n
er
s
.
Fro
m
an
ad
m
in
is
tr
ativ
e
s
tan
d
p
o
in
t,
atten
d
an
ce
is
ess
en
tial a
n
d
ad
v
an
tag
eo
u
s
wh
en
ass
ess
in
g
an
o
r
g
an
izatio
n
.
R
ec
o
r
d
in
g
atten
d
a
n
ce
v
ia
tr
a
d
itio
n
al
m
eth
o
d
s
is
a
lab
o
r
io
u
s
an
d
tim
e
-
co
n
s
u
m
i
n
g
p
r
o
ce
s
s
.
T
h
e
p
r
im
a
r
y
im
p
etu
s
f
o
r
d
ev
elo
p
in
g
th
is
tech
n
o
lo
g
y
is
to
p
r
o
v
id
e
an
ef
f
icien
t
au
to
m
ated
s
y
s
tem
f
o
r
m
o
n
ito
r
in
g
atten
d
an
ce
u
s
in
g
f
ac
ial
d
etec
tio
n
an
d
id
en
tific
atio
n
.
I
n
co
n
t
r
ast
to
th
e
tr
ad
itio
n
al
ap
p
r
o
ac
h
o
f
r
e
co
r
d
in
g
atte
n
d
an
ce
,
t
h
is
m
o
d
er
n
m
eth
o
d
is
m
o
r
e
ac
cu
r
ate
an
d
d
em
a
n
d
s
less
ex
er
tio
n
[
2
]
.
Mo
r
eo
v
e
r
,
th
is
s
y
s
tem
is
ad
v
an
tag
eo
u
s
f
o
r
t
h
e
p
u
r
p
o
s
es
o
f
au
th
en
ticatio
n
,
s
u
r
v
eillan
ce
,
an
d
r
ec
o
r
d
k
ee
p
in
g
in
th
e
m
a
n
ag
em
en
t
o
f
ed
u
ca
tio
n
al
in
s
titu
tio
n
s
s
u
ch
as
s
ch
o
o
ls
,
co
lleg
es,
an
d
u
n
iv
e
r
s
ities
.
C
o
n
s
is
ten
tly
atten
d
in
g
class
es
is
cr
u
cial
f
o
r
a
s
tu
d
en
t
’
s
ac
ad
e
m
ic
ac
h
iev
em
en
t.
An
au
t
o
m
at
ed
v
is
u
al
s
y
s
tem
i
s
m
o
r
e
ess
en
tial
as
th
e
n
u
m
b
er
o
f
s
tu
d
en
ts
in
ed
u
ca
tio
n
al
in
s
titu
tio
n
s
co
n
tin
u
es
to
r
is
e,
lead
in
g
t
o
a
co
m
m
en
s
u
r
ate
in
c
r
ea
s
e
in
d
e
m
an
d
[
3
]
.
A
f
ac
e
id
en
tific
atio
n
s
y
s
tem
r
ef
er
s
to
o
n
e
o
r
m
o
r
e
co
m
p
u
te
r
p
r
o
g
r
am
s
th
at
ass
is
t
in
th
e
v
er
if
icatio
n
o
r
id
en
tific
atio
n
o
f
an
in
d
iv
id
u
al
b
ased
o
n
a
d
ig
ital
p
ictu
r
e
o
r
v
id
eo
o
u
tlin
e
o
b
tain
ed
f
r
o
m
a
v
id
eo
s
o
u
r
ce
.
An
ap
p
r
o
ac
h
to
ac
co
m
p
lis
h
t
h
is
is
b
y
co
n
d
u
ctin
g
a
co
m
p
a
r
is
o
n
b
etwe
en
a
f
ac
e
d
atab
ase
an
d
s
p
ec
if
ic
f
ac
ial
ch
ar
ac
ter
is
tics
ex
tr
ac
ted
f
r
o
m
th
e
im
ag
e.
T
h
e
f
ac
e
-
b
ased
id
e
n
tific
atio
n
s
y
s
tem
m
ay
ac
cu
r
a
tely
r
ec
o
g
n
ize
an
d
au
th
en
ticate
an
in
d
iv
id
u
al
b
y
u
s
in
g
a
d
ig
ital
ca
m
er
a
o
r
v
id
e
o
ca
m
er
a
[
4
]
.
T
h
e
tech
n
o
lo
g
y
g
ath
er
s
im
ag
es
o
f
in
d
iv
id
u
als
in
a
c
o
m
m
u
n
ity
ar
ea
,
co
n
n
ec
ts
with
t
h
e
s
u
r
v
eillan
ce
s
y
s
tem
,
an
d
in
co
r
p
o
r
ates
a
p
r
e
-
ex
is
tin
g
d
atab
ase.
Facial
r
ec
o
g
n
itio
n
s
y
s
tem
s
h
av
e
a
b
r
o
ad
r
an
g
e
o
f
ap
p
licatio
n
s
,
in
clu
d
in
g
v
er
if
y
in
g
s
tatic
“
m
u
g
-
s
h
o
t
”
im
ag
es
an
d
id
en
tif
y
in
g
f
ac
es
in
u
n
co
n
tr
o
lled
co
n
tex
ts
s
u
ch
as
air
p
o
r
ts
.
On
e
estab
lis
h
ed
m
eth
o
d
f
o
r
th
is
tech
n
iq
u
e
is
to
s
h
ap
e
th
e
f
ac
ia
l
f
ea
tu
r
es,
in
clu
d
in
g
th
e
ea
r
s
,
ey
eb
r
o
ws,
ey
es,
lip
s
,
n
o
s
e,
an
d
ch
in
,
an
d
co
n
s
id
er
th
eir
th
r
ee
-
d
im
e
n
s
io
n
al
r
elatio
n
s
h
ip
[
5
]
.
Face
r
ec
o
g
n
itio
n
is
a
p
o
p
u
lar
an
d
r
ea
d
ily
ap
p
a
r
en
t
u
s
e
o
f
d
i
g
ital
im
ag
e
p
r
o
ce
s
s
in
g
.
On
e
a
p
p
licatio
n
o
f
f
ac
ial
r
ec
o
g
n
itio
n
is
th
e
id
e
n
tific
atio
n
o
f
in
d
iv
i
d
u
als
in
s
id
e
an
o
r
g
an
izatio
n
to
p
r
o
m
o
te
th
eir
in
v
o
l
v
em
en
t.
T
o
ass
ess
th
e
f
u
n
ctio
n
in
g
o
f
a
n
o
r
g
an
izatio
n
,
it
is
cr
u
cial
to
m
ain
tain
a
d
atab
ase
o
f
p
ar
ticip
atio
n
r
ec
o
r
d
s
.
T
h
e
d
ec
is
io
n
to
in
co
r
p
o
r
ate
p
ar
tic
ip
atio
n
in
to
th
e
b
o
a
r
d
ar
ch
ite
ctu
r
e
was
m
o
tiv
ated
b
y
th
e
d
esire
to
m
ec
h
an
ize
th
e
co
n
v
en
tio
n
al
m
eth
o
d
o
f
ass
ess
in
g
in
v
o
lv
em
e
n
t.
T
h
e
au
to
m
ate
d
atten
d
an
ce
i
d
e
n
tific
atio
n
s
y
s
tem
au
to
n
o
m
o
u
s
ly
v
e
r
if
ies an
d
ex
a
m
in
es p
ar
ticip
atio
n
o
n
a
d
aily
b
asis
,
with
m
in
im
al
h
u
m
an
i
n
v
o
lv
em
en
t
[
6
]
.
Fig
u
r
e
1
s
h
o
ws
p
r
o
p
o
s
ed
ar
ch
itectu
r
e
o
f
a
u
to
m
atic
f
ac
e
id
en
tific
atio
n
s
y
s
tem
,
it
a
u
to
m
atica
lly
d
etec
ts
(
r
ec
o
g
n
ize)
a
n
d
id
en
ti
f
ies
m
u
ltip
le
f
ac
es
f
r
o
m
g
r
o
u
p
p
h
o
to
g
r
ap
h
.
I
n
th
is
au
to
m
a
ted
m
eth
o
d
,
in
p
u
t
p
ictu
r
e
is
u
n
k
n
o
wn
f
ac
es
an
d
s
y
s
tem
g
iv
es
b
ac
k
o
u
t
p
u
t
to
t
h
e
id
en
tity
f
r
o
m
d
ataset
o
f
m
u
lt
ip
le
p
er
s
o
n
s
.
T
h
u
s
,
th
e
test
f
ac
es
s
h
o
u
ld
b
e
co
m
p
ar
ed
to
all
tr
ain
ed
p
ictu
r
es
p
r
esen
t
in
th
e
d
ataset
f
o
r
g
et
tin
g
th
e
id
en
tifie
d
p
ictu
r
e.
Ma
tch
f
ac
e
will
m
ar
k
au
to
m
atica
lly
f
o
r
atten
d
an
c
e
an
d
is
s
av
ed
in
s
ep
ar
ate
d
atab
ase
f
ile.
I
m
ag
e
ac
q
u
is
itio
n
en
tails
ca
p
tu
r
in
g
a
p
h
o
to
g
r
ap
h
u
s
in
g
a
s
u
itab
le
ca
m
er
a.
B
ef
o
r
e
co
m
m
e
n
cin
g
an
y
v
id
eo
o
r
im
ag
e
p
r
o
ce
s
s
in
g
,
it
is
n
ec
ess
ar
y
to
ca
p
tu
r
e
a
p
h
o
t
o
g
r
a
p
h
u
s
in
g
th
e
ca
m
er
a
a
n
d
c
o
n
v
er
t
it
in
to
a
m
ea
s
u
r
ab
le
e
n
tity
.
T
h
e
p
r
o
ce
d
u
r
e
r
ef
er
r
ed
to
as
i
m
ag
e
ac
q
u
is
itio
n
aim
s
to
c
o
n
v
er
t
an
o
p
tical
im
ag
e
in
to
a
s
et
o
f
m
ath
em
atica
l
d
ata
th
at
m
ay
b
e
f
u
r
th
e
r
p
r
o
ce
s
s
ed
o
n
a
co
m
p
u
ter
[
7
]
.
Face
d
etec
tio
n
in
v
o
lv
es
d
eter
m
i
n
in
g
th
e
p
r
esen
ce
o
f
a
f
ac
e
in
a
p
h
o
to
g
r
ap
h
an
d
,
if
p
r
esen
t,
p
r
o
v
id
in
g
in
f
o
r
m
atio
n
o
n
th
e
l
o
ca
tio
n
an
d
ap
p
ea
r
an
c
e
o
f
th
e
f
ac
e
in
t
h
e
im
ag
e.
Au
to
m
atic
f
ac
e
d
etec
t
io
n
is
a
co
m
p
u
ter
-
b
ased
tech
n
iq
u
e
u
s
ed
to
ass
ess
th
e
s
ize
an
d
p
o
s
itio
n
o
f
a
p
er
s
o
n
’
s
f
ac
e
in
a
d
ig
ital
im
ag
e.
Face
d
etec
tio
n
is
th
e
in
itial
s
tep
in
an
y
f
ac
e
p
r
ep
ar
atio
n
f
r
am
ewo
r
k
.
I
t
s
er
v
es
v
ar
io
u
s
p
u
r
p
o
s
es,
in
clu
d
in
g
f
ac
e
id
en
tific
atio
n
,
en
h
an
ci
n
g
b
ea
u
ty
ca
r
e
p
r
o
d
u
cts,
ca
teg
o
r
izin
g
b
y
s
ex
,
g
r
o
u
p
in
g
,
a
n
d
e
x
tr
ac
tin
g
f
ac
ial
co
m
p
o
n
en
ts
[
8
]
.
Fig
u
r
e
1.
Step
s
in
v
o
lv
ed
in
au
t
o
m
atic
f
ac
e
id
en
tific
atio
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
2
0
2
0
-
203
0
2022
Facial
f
ea
tu
r
e
ex
tr
ac
tio
n
is
th
e
id
en
tific
atio
n
o
f
d
is
tin
ct
r
eg
io
n
s
o
f
th
e
f
ac
e,
in
clu
d
in
g
th
e
ey
es,
f
o
r
eh
ea
d
,
lip
s
,
n
o
s
e,
jawlin
e,
an
d
o
th
er
lo
ca
tio
n
s
.
Ov
er
th
e
co
u
r
s
e
o
f
th
eir
life
s
p
an
,
in
d
i
v
id
u
als
p
o
s
s
ess
th
e
ab
ilit
y
to
d
if
f
er
e
n
tiate
b
etwe
en
n
u
m
e
r
o
u
s
d
is
tin
ct
v
is
u
al
ch
ar
ac
ter
is
tics
an
d
ef
f
o
r
tles
s
ly
r
ec
o
g
n
ize
f
ac
es.
Pre
cisi
o
n
in
id
en
tify
in
g
f
ac
es a
n
d
o
th
er
f
ac
ial
f
ea
tu
r
es
is
cr
u
cial
in
s
ev
er
al
d
o
m
ain
s
,
s
u
ch
as
h
u
m
an
-
co
m
p
u
ter
in
ter
ac
tio
n
,
f
ac
e
ac
tiv
ity
a
n
d
d
is
p
lay
,
f
ac
e
r
ec
o
g
n
itio
n
,
an
d
f
ac
e
p
h
o
t
o
d
atab
ase
ad
m
in
is
tr
atio
n
.
An
im
p
o
r
tan
t
en
h
an
ce
m
e
n
t
in
th
ese
a
p
p
licat
io
n
s
is
th
e
ca
p
ab
ilit
y
t
o
d
if
f
er
en
tiate
b
etwe
en
v
ar
i
o
u
s
f
ac
ial
h
ig
h
lig
h
ts
.
Facial
elem
en
t
ex
tr
ac
tio
n
is
a
s
ig
n
if
i
ca
n
t
ad
v
a
n
ce
m
en
t
in
h
u
m
a
n
f
ac
e
r
ec
o
g
n
itio
n
.
Facial
r
ec
o
g
n
itio
n
p
lay
s
a
cr
u
cial
r
o
le
in
s
ev
e
r
al
ap
p
licatio
n
s
with
in
th
e
d
o
m
ain
s
o
f
h
u
m
an
-
c
o
m
p
u
ter
in
ter
ac
tio
n
an
d
f
ac
ia
l
r
ec
o
g
n
itio
n
its
elf
[
9
]
.
Face
id
en
tific
atio
n
aim
s
to
au
t
h
en
ticate
o
r
d
is
tin
g
u
is
h
an
in
d
iv
id
u
al
’
s
id
en
tity
b
a
s
ed
o
n
t
h
eir
f
ac
ial
f
ea
tu
r
es.
B
y
em
p
lo
y
i
n
g
a
f
ac
e
r
ec
o
g
n
itio
n
f
r
am
ewo
r
k
,
in
d
iv
i
d
u
als m
ay
b
e
ac
c
u
r
ately
id
e
n
tifie
d
in
b
o
t
h
p
h
o
to
s
an
d
v
id
eo
s
.
T
h
e
f
ac
ial
r
ec
o
g
n
i
tio
n
s
y
s
tem
em
p
lo
y
s
a
co
m
p
u
ter
alg
o
r
ith
m
to
ch
o
o
s
e
s
p
ec
if
ic
an
d
u
n
eq
u
iv
o
ca
l
d
etails
r
eg
ar
d
in
g
an
in
d
iv
id
u
al
’
s
f
ac
e.
T
o
f
ac
ilit
ate
co
m
p
ar
is
o
n
with
d
ata
f
r
o
m
o
th
e
r
in
s
tan
ce
s
in
a
f
ac
e
r
ec
o
g
n
itio
n
d
ataset,
in
tr
icate
f
ac
ial
ch
ar
ac
ter
is
tics
lik
e
th
e
d
i
s
tan
ce
b
etwe
en
th
e
ey
es o
r
th
e
lo
ca
tio
n
o
f
th
e
jaw
ar
e
co
n
v
e
r
ted
in
to
a
n
u
m
er
ical
f
o
r
m
at.
Face
f
o
r
m
ats
s
av
e
s
p
ec
if
ic
d
ata
ab
o
u
t
ea
ch
i
n
d
iv
id
u
al
f
ac
e
an
d
m
a
y
b
e
ea
s
ily
d
if
f
er
en
tiated
f
r
o
m
p
h
o
to
g
r
ap
h
s
d
u
e
to
th
eir
p
u
r
p
o
s
e
o
f
in
clu
d
in
g
o
n
ly
th
e
n
ec
ess
ar
y
in
f
o
r
m
atio
n
f
o
r
d
is
tin
g
u
is
h
in
g
o
n
e
f
ac
e
f
r
o
m
a
n
o
th
er
[
1
0
]
.
T
h
is
ar
ticle
in
tr
o
d
u
ce
s
a
f
ac
ial
r
ec
o
g
n
itio
n
s
y
s
tem
th
at
au
to
m
atica
lly
r
ec
o
r
d
s
atten
d
an
ce
.
T
h
is
s
y
s
tem
co
m
p
r
is
es
o
f
m
an
y
c
o
m
p
o
n
en
ts
:
p
ictu
r
e
ca
p
tu
r
e
,
i
m
ag
e
au
g
m
en
tatio
n
b
y
h
is
to
g
r
am
e
q
u
aliza
tio
n
,
im
ag
e
s
eg
m
en
tatio
n
u
s
in
g
t
h
e
f
u
zz
y
C
m
ea
n
s
clu
s
ter
in
g
a
p
p
r
o
ac
h
,
an
d
th
e
co
n
s
tr
u
ctio
n
o
f
a
class
if
icatio
n
m
o
d
el
u
s
in
g
th
e
K
-
n
ea
r
est
n
eig
h
b
o
u
r
(
KNN)
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
es
(
SVM
)
,
an
d
Ad
aBo
o
s
t
tech
n
iq
u
es.
T
h
e
ac
cu
r
ac
y
o
f
th
e
g
iv
en
m
eth
o
d
s
u
r
p
ass
es
th
at
o
f
SVM
(
9
6
.
2
5
%)
an
d
Ad
aBo
o
s
t
(
8
6
.
5
0
%).
KNN
d
em
o
n
s
tr
ates su
p
er
io
r
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
ac
cu
r
ac
y
,
an
d
F_
m
ea
s
u
r
e
.
2.
RE
L
AT
E
D
WO
RK
2
.
1
.
F
a
ce
re
co
g
nitio
n
Au
th
o
r
s
d
ev
el
o
p
ed
an
in
n
o
v
at
iv
e
f
ac
ial
r
ec
o
g
n
itio
n
tec
h
n
iq
u
e
to
d
eter
m
i
n
e
a
p
e
r
s
o
n
’
s
in
ter
ests
u
s
in
g
o
n
ly
a
p
o
r
tio
n
o
f
th
eir
f
ac
e.
Fu
r
th
er
m
o
r
e,
th
ey
h
a
v
e
p
r
o
v
id
ed
two
f
ac
ial
p
h
o
to
g
r
a
p
h
s
in
o
r
d
er
to
ex
tr
ac
t
th
e
ess
en
tial
ch
ar
ac
ter
is
tics
.
Fu
r
th
er
m
o
r
e
,
th
ey
h
av
e
d
e
v
elo
p
ed
a
p
o
in
t
s
et
m
atch
in
g
m
eth
o
d
th
at
u
tili
s
es
d
is
cr
im
in
ativ
e
m
atch
in
g
o
n
tex
tu
al
f
ea
tu
r
es
to
p
er
f
o
r
m
th
e
m
atch
in
g
f
u
n
ctio
n
.
I
n
a
d
d
itio
n
,
t
h
ey
h
av
e
d
is
co
v
er
ed
a
p
o
i
n
t
s
et
m
atch
in
g
tech
n
iq
u
e
t
h
at
is
ca
p
ab
le
o
f
s
im
u
ltan
eo
u
s
ly
m
atch
in
g
b
o
th
th
e
ex
tr
ac
ted
ch
ar
ac
ter
is
tics
an
d
th
e
f
ac
e
p
h
o
to
g
r
a
p
h
s
.
Af
ter
c
o
n
s
id
er
in
g
all
f
ac
to
r
s
,
th
e
p
r
o
x
im
it
y
o
f
th
e
ac
k
n
o
wled
g
ed
s
ig
n
if
ican
t
ch
ar
ac
ter
is
tics
is
d
eter
m
in
ed
b
y
e
x
am
in
in
g
th
e
s
im
ilar
ity
o
f
th
e
two
alter
ed
f
ac
ial
im
ag
es.
T
h
e
f
in
d
i
n
g
s
in
d
icate
th
at
th
e
in
v
esti
g
atio
n
s
,
wh
ich
u
tili
s
ed
a
f
ac
ial
d
ataset,
wer
e
ef
f
icac
io
u
s
[
1
1
]
.
I
n
o
r
d
er
to
g
ain
a
d
ee
p
er
co
m
p
r
eh
en
s
io
n
o
f
th
e
n
u
m
er
o
u
s
r
ec
u
r
r
in
g
elem
en
ts
in
f
ac
ial
im
ag
es,
R
esear
ch
er
s
d
ev
elo
p
ed
a
n
o
v
e
l
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
C
NN)
k
n
o
wn
as
th
e
wass
er
s
tein
co
n
v
o
l
u
tio
n
al
n
eu
r
al
n
etwo
r
k
(
W
C
NN)
.
T
h
e
p
r
o
ce
s
s
o
f
u
n
d
er
s
tan
d
in
g
th
e
m
o
d
alities
an
d
in
v
ar
ia
n
ts
o
f
f
ea
tu
r
es
is
d
is
tr
ib
u
ted
ac
r
o
s
s
th
r
ee
le
v
els
in
th
e
W
C
NN.
I
n
ad
d
itio
n
,
a
W
C
N
N
lay
er
is
u
tili
s
ed
to
ca
l
cu
late
th
e
d
is
tan
ce
,
wh
ich
r
ep
r
esen
ts
th
e
d
is
s
im
il
ar
ity
o
f
th
e
f
ea
tu
r
e
d
is
tr
ib
u
ti
o
n
s
.
I
n
a
d
d
itio
n
,
a
co
r
r
elatio
n
is
in
co
r
p
o
r
ated
to
r
ed
u
ce
t
h
e
m
ag
n
itu
d
e
o
f
th
e
p
ar
am
eter
a
n
d
m
itig
ate
th
e
r
is
k
o
f
o
v
er
f
itti
n
g
.
Fin
ally
,
th
e
y
h
av
e
p
r
o
v
en
th
at
th
eir
W
C
NN
s
u
r
p
ass
es
o
th
er
l
ea
r
n
in
g
alg
o
r
ith
m
s
in
ter
m
s
o
f
p
r
e
d
ictio
n
ac
c
u
r
ac
y
[
1
2
]
.
I
n
t
h
is
m
eth
o
d
,
a
u
th
o
r
s
h
av
e
cr
ea
ted
a
n
ew
m
eth
o
d
f
o
r
g
en
e
r
atin
g
r
ea
lis
tic
f
ac
es
with
h
ig
h
r
eso
lu
tio
n
.
T
h
is
m
et
h
o
d
co
m
b
in
es
tex
tu
r
e
in
p
ain
tin
g
an
d
p
o
s
itio
n
co
r
r
e
ctio
n
,
wh
ich
ar
e
two
s
ep
ar
ate
co
m
p
o
n
en
ts
.
T
h
ey
u
s
ed
an
i
n
n
o
v
ativ
e
war
p
in
g
ap
p
r
o
ac
h
to
m
er
g
e
th
e
two
p
a
r
ts
in
to
a
p
r
o
f
o
u
n
d
n
etwo
r
k
.
I
n
ad
d
itio
n
,
t
h
ey
h
av
e
d
em
o
n
s
tr
ated
th
e
in
clu
s
io
n
o
f
th
e
co
r
r
ec
tiv
e
co
m
p
o
n
e
n
t,
th
e
s
im
p
lific
atio
n
o
f
h
ete
r
o
g
en
eo
u
s
f
ac
e
s
y
n
th
esis
f
r
o
m
u
n
p
air
e
d
to
p
air
e
d
im
ag
es
d
u
r
in
g
tr
an
s
latio
n
,
a
n
d
th
e
m
itig
atio
n
o
f
p
o
s
tu
r
e
a
n
d
s
p
ec
tr
al
in
co
n
s
is
ten
cies
in
h
eter
o
g
e
n
eo
u
s
f
ac
e
im
ag
e
id
en
tific
atio
n
.
Fin
ally
,
t
h
ey
h
a
v
e
s
im
p
lifie
d
th
e
p
r
o
ce
s
s
o
f
ac
h
iev
in
g
p
r
ec
is
e
f
ac
ial
r
e
co
g
n
itio
n
[
1
3
]
.
I
n
o
r
d
er
to
r
ed
u
ce
th
e
o
cc
u
r
r
e
n
ce
o
f
d
is
p
ar
ities
in
f
ac
ial
c
h
ar
ac
ter
is
tics
,
au
th
o
r
s
h
a
v
e
d
e
v
elo
p
ed
an
in
n
o
v
ativ
e
f
ac
ial
au
g
m
en
tatio
n
n
etwo
r
k
.
A
u
n
iq
u
e
h
ier
a
r
c
h
ical
d
is
en
tan
g
lem
en
t
m
o
d
u
l
e
was
d
ev
elo
p
ed
to
s
ep
ar
ate
f
ea
tu
r
es
f
r
o
m
id
en
ti
ty
r
ep
r
esen
tatio
n
.
Fu
r
t
h
er
m
o
r
e,
g
r
a
p
h
c
o
n
v
o
lu
tio
n
al
n
etwo
r
k
s
ar
e
u
tili
s
ed
to
ex
tr
ac
t
g
e
o
m
etr
ic
i
n
f
o
r
m
atio
n
b
y
u
n
co
v
e
r
in
g
th
e
r
elatio
n
s
h
ip
s
b
etwe
en
g
eo
g
r
ap
h
ically
d
is
tin
ct
r
eg
io
n
s
th
at
ar
e
co
n
s
er
v
ed
.
T
h
e
ex
p
er
im
e
n
tal
r
esu
lts
s
u
b
s
tan
tiated
th
e
s
u
p
er
io
r
ity
o
f
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
o
v
e
r
th
e
alter
n
ativ
e
ap
p
r
o
ac
h
es
[
1
4
]
.
W
o
r
k
in
[
1
5
]
p
r
esen
ted
a
n
ew
m
eth
o
d
f
o
r
J
o
in
t
Gr
o
u
p
Sp
ar
s
e
Prin
cip
le
C
o
m
p
o
n
en
t
An
aly
s
is
.
T
h
is
s
tr
ateg
y
en
f
o
r
ce
d
a
s
et
o
f
c
o
n
d
it
io
n
s
o
n
th
e
b
asic
co
e
f
f
icien
ts
to
en
s
u
r
e
th
at
th
ey
wer
e
r
eg
ar
d
e
d
s
im
u
ltan
eo
u
s
ly
s
p
ar
s
e.
T
h
eir
m
eth
o
d
o
l
o
g
y
e
n
s
u
r
ed
th
e
p
r
eser
v
atio
n
o
f
t
h
e
tr
aits
.
Fin
ally
,
th
ey
h
av
e
v
alid
ated
th
eir
m
eth
o
d
o
l
o
g
y
b
y
co
n
s
id
er
in
g
b
o
th
th
e
co
m
p
r
ess
ed
im
ag
e
a
n
d
f
ac
ial
r
ec
o
g
n
itio
n
.
T
h
eir
m
eth
o
d
o
l
o
g
y
s
u
r
p
ass
es
th
e
m
o
s
t
ad
v
an
ce
d
tech
n
iq
u
es
in
ter
m
s
o
f
s
elec
tin
g
r
elev
an
t
f
ea
tu
r
es
an
d
ac
h
iev
in
g
h
ig
h
ac
cu
r
ac
y
in
f
ac
ial
r
ec
o
g
n
itio
n
[
1
5
]
.
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
Desig
n
o
f fa
ce
r
ec
o
g
n
itio
n
b
a
s
ed
effec
tive
a
u
to
ma
ted
s
ma
r
t a
tten
d
a
n
ce
s
ystem
(
Jy
o
ti L.
B
a
n
g
a
r
e
)
2023
A
n
o
v
el
class
if
icatio
n
ap
p
r
o
ac
h
co
n
s
is
tin
g
o
f
f
o
u
r
s
tep
s
h
as
b
ee
n
p
r
o
p
o
s
ed
:
f
ea
tu
r
e
s
elec
tio
n
,
d
etec
tio
n
,
iter
atio
n
,
an
d
co
n
v
er
s
io
n
.
I
n
itially
,
a
n
o
n
-
lin
ea
r
f
u
n
ctio
n
is
em
p
lo
y
ed
to
s
elec
t
th
e
ap
p
r
o
p
r
iate
f
ea
tu
r
e
d
u
r
in
g
th
e
f
ea
tu
r
e
s
ele
ctio
n
p
h
ase.
Fu
r
th
e
r
m
o
r
e,
s
p
atial
p
ar
am
eter
s
ar
e
em
p
lo
y
ed
t
o
d
etec
t
d
is
tin
ctiv
e
ch
ar
ac
ter
is
tics
in
th
e
h
y
p
er
s
p
ec
tr
al
im
ag
e
(
HI
S)
d
ata,
wh
ic
h
ar
e
s
u
b
s
eq
u
en
tly
ta
k
en
in
t
o
ac
co
u
n
t
d
u
r
i
n
g
th
e
ev
alu
atio
n
o
f
p
o
ten
tial
HSI
f
ac
e
ca
n
d
id
ates.
Nex
t,
in
th
e
iter
ativ
e
ap
p
r
o
ac
h
,
th
e
Gau
s
s
ian
f
ilter
is
u
s
ed
as
th
e
th
ir
d
s
tep
.
Fin
ally
,
t
o
ac
h
iev
e
ef
f
ec
tiv
e
ca
teg
o
r
izatio
n
,
th
e
r
e
al
-
tim
e
m
ap
s
ar
e
tr
a
n
s
f
o
r
m
e
d
in
to
d
is
tin
ct
v
alu
es
u
s
in
g
Ots
u
’
s
m
eth
o
d
.
T
h
eir
a
p
p
r
o
ac
h
s
u
r
p
ass
es
th
e
o
th
er
s
in
ter
m
s
o
f
ac
cu
r
ac
y
a
n
d
th
e
f
r
eq
u
en
c
y
o
f
wr
o
n
g
ca
teg
o
r
izatio
n
wh
en
c
o
m
p
ar
e
d
to
c
o
m
p
etin
g
ap
p
r
o
ac
h
es
[
1
6
]
.
W
o
r
k
in
[
1
7
]
d
e
v
elo
p
e
d
a
s
p
ec
tr
u
m
b
an
d
s
elec
tio
n
m
eth
o
d
th
at
co
m
b
in
es
th
e
clu
s
ter
in
g
m
eth
o
d
o
lo
g
y
,
Gab
o
r
f
ilter
,
an
d
g
r
ad
ien
t
m
eth
o
d
.
T
h
is
m
eth
o
d
ef
f
ec
tiv
ely
ex
tr
a
cts
in
f
o
r
m
atio
n
wh
ile
r
ed
u
cin
g
th
e
im
p
ac
t
o
f
n
o
is
e.
Fu
r
t
h
er
m
o
r
e,
f
o
r
th
e
p
u
r
p
o
s
e
o
f
d
o
in
g
a
co
m
p
ar
is
o
n
an
aly
s
is
,
th
e
n
ea
r
est
n
eig
h
b
o
u
r
awa
r
e
class
if
ier
in
teg
r
ates
th
e
Ho
g
a
n
d
Ga
b
o
r
f
ea
tu
r
es.
Fin
ally
,
th
e
ex
p
er
im
e
n
tal
f
in
d
in
g
s
illu
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
t
h
eir
s
tr
ateg
y
in
ter
m
s
o
f
tim
e
c
o
m
p
lex
ity
[
1
7
]
.
T
o
tack
le
th
e
is
s
u
e
o
f
tin
y
s
ec
tio
n
s
et
p
r
o
b
lem
,
r
esear
ch
e
r
s
p
r
o
p
o
s
ed
a
u
n
iq
u
e
C
NN
ar
ch
i
tectu
r
e
th
at
em
p
lo
y
s
lig
h
tweig
h
t
co
m
p
o
n
en
ts
to
ac
h
iev
e
ef
f
icien
t
class
if
icatio
n
.
T
h
eir
r
esear
ch
f
o
c
u
s
es
o
n
r
ed
u
cin
g
t
h
e
d
im
en
s
io
n
ality
o
f
im
ag
es
an
d
u
s
in
g
s
p
atio
-
s
p
ec
tr
al
Sch
r
o
d
in
g
er
E
ig
en
m
a
p
s
to
f
in
d
im
p
o
r
tan
t
f
ea
tu
r
es
in
o
r
d
er
to
o
b
tain
in
te
g
r
ated
s
p
at
ial
-
s
p
ec
tr
al
im
ag
e
d
ata.
I
n
ad
d
itio
n
,
th
ey
h
av
e
cr
ea
ted
a
co
n
v
o
lu
tio
n
m
o
d
el
th
at
ca
n
h
an
d
le
f
ea
tu
r
es
o
b
tain
e
d
f
r
o
m
d
ata
p
o
in
ts
in
a
o
n
e
-
d
im
en
s
io
n
al
v
ec
to
r
v
iewp
o
in
t,
u
s
in
g
a
d
u
al
-
s
ca
le
ap
p
r
o
ac
h
.
Su
b
s
eq
u
e
n
tly
,
th
e
r
esear
ch
er
s
em
p
lo
y
e
d
th
e
in
n
o
v
ativ
e
B
i
-
ch
an
n
el
f
u
s
io
n
m
e
th
o
d
to
s
elec
tiv
ely
r
ef
in
e
th
e
f
ea
tu
r
es
ac
q
u
ir
e
d
u
s
in
g
d
u
al
s
ca
le
co
n
v
o
lu
tio
n
[
1
8
]
.
Ultim
ately
,
a
g
lo
b
al
av
er
a
g
e
p
o
o
lin
g
class
if
ier
is
em
p
lo
y
ed
to
e
n
h
an
ce
th
e
a
cc
u
r
ac
y
o
f
class
if
y
in
g
h
y
p
er
s
p
ec
tr
al
im
ag
es
with
a
lim
ited
n
u
m
b
er
o
f
la
b
elled
s
am
p
les b
y
m
er
g
in
g
an
d
in
clu
d
in
g
th
e
f
ilter
ed
ch
ar
ac
ter
is
tics
.
2
.
2
.
F
e
a
t
ure
s
elec
t
io
n t
ec
hn
iqu
es
R
esear
ch
wo
r
k
[
1
9
]
in
t
r
o
d
u
ce
d
a
n
o
v
el
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
u
s
in
g
a
wr
a
p
p
er
-
b
ased
ap
p
r
o
ac
h
.
W
h
en
co
n
s
tr
u
ctin
g
th
e
r
a
n
d
o
m
f
o
r
est
f
o
r
ca
teg
o
r
izatio
n
,
t
h
e
cr
ea
to
r
s
o
f
th
is
m
o
d
el
co
n
s
id
er
ed
two
ess
en
tial
f
ac
to
r
s
:
co
o
p
er
ativ
e
n
ess
an
d
co
-
ev
alu
atio
n
.
I
n
ad
d
itio
n
,
th
e
s
cien
tis
t
s
em
p
lo
y
ed
two
d
is
tin
ct
s
ets
o
f
d
ata
-
a
b
en
ch
m
ar
k
d
ataset
an
d
a
co
llectio
n
o
f
d
atasets
o
b
tain
ed
f
r
o
m
clin
ics
-
to
ev
alu
ate
an
d
co
n
tr
ast
th
eir
f
ea
tu
r
e
s
elec
tio
n
tech
n
iq
u
e
with
a
cla
s
s
if
icatio
n
alg
o
r
ith
m
b
ased
o
n
r
an
d
o
m
f
o
r
ests
.
T
h
eir
m
eth
o
d
o
lo
g
y
was
s
h
o
w
n
to
en
h
a
n
ce
t
h
e
d
ec
is
io
n
-
m
ak
i
n
g
ab
ilit
ies
o
f
h
ea
lth
ca
r
e
wo
r
k
e
r
s
b
y
r
ed
u
cin
g
th
e
tim
e
u
s
ed
f
o
r
ca
teg
o
r
is
in
g
an
d
im
p
r
o
v
in
g
th
e
ac
c
u
r
ac
y
o
f
cla
s
s
if
icatio
n
[
1
9
]
.
W
o
r
k
d
o
n
e
i
n
[
2
0
]
d
e
v
elo
p
ed
a
n
ew
m
eth
o
d
f
o
r
f
a
ce
r
ec
o
g
n
itio
n
ca
lled
s
p
ec
tr
u
m
b
ased
d
is
cr
im
in
ativ
e
d
ee
p
lear
n
in
g
(
DL
)
.
T
h
is
m
eth
o
d
in
v
o
l
v
es
tr
ain
in
g
th
e
s
am
p
les
in
a
s
u
b
s
p
ac
e.
T
h
eir
r
esear
ch
r
ev
ea
led
th
e
ab
ilit
y
to
d
is
tin
g
u
is
h
b
etwe
en
d
if
f
er
e
n
t
ty
p
es
o
f
f
ac
e
s
am
p
les
with
in
th
e
s
am
e
s
p
ec
tr
u
m
,
as
well
as
b
etwe
en
d
if
f
er
e
n
t
s
p
ec
tr
a.
Fin
ally
,
th
ey
h
a
v
e
en
h
an
ce
d
th
e
ac
cu
r
ac
y
o
f
th
eir
p
r
ed
ic
tio
n
ap
p
r
o
ac
h
a
n
d
ass
es
s
ed
it
b
y
co
n
d
u
ctin
g
m
an
y
test
s
u
s
in
g
th
r
ee
s
ep
ar
ate
d
atasets
:
HK
Po
ly
U,
C
MU
,
an
d
UW
A
[
2
0
]
.
Sach
in
&
B
ir
m
o
h
an
d
ev
el
o
p
ed
a
n
o
v
e
l
m
o
d
el
f
o
r
d
etec
tin
g
p
h
is
h
in
g
u
tili
s
in
g
K
NN
an
d
B
in
ar
y
M
o
d
if
ied
E
q
u
ilib
r
iu
m
Op
tim
is
atio
n
,
alo
n
g
with
a
n
e
wly
d
ev
elo
p
ed
AV
-
s
h
a
p
e
tr
a
n
s
f
er
tech
n
iq
u
e.
T
h
eir
m
o
d
el
h
as
th
e
ca
p
ab
ilit
y
to
d
o
class
if
icatio
n
an
d
o
p
tim
is
atio
n
task
s
,
as
well
a
s
f
ea
tu
r
e
s
elec
tio
n
,
d
u
e
to
its
r
o
b
u
s
t
le
v
els
o
f
ex
p
lo
r
atio
n
an
d
ex
p
lo
itatio
n
.
A
s
tatis
tica
l
v
alid
atio
n
was
u
n
d
e
r
tak
en
b
y
co
m
p
ar
in
g
1
7
s
tr
ateg
ies
i
n
o
r
d
er
t
o
ass
ess
class
if
icatio
n
ac
cu
r
ac
y
an
d
t
h
e
s
elec
tio
n
o
f
f
ea
tu
r
es f
r
o
m
1
8
d
if
f
er
en
t
d
atasets
[
2
1
]
.
Kh
ar
e
et
a
l.
[
2
2
]
p
r
o
p
o
s
ed
a
n
ew
m
o
d
el
f
o
r
f
ea
tu
r
e
s
elec
tio
n
th
at
co
m
b
in
es
two
c
u
r
r
e
n
t
o
p
tim
is
atio
n
alg
o
r
ith
m
s
,
n
am
el
y
th
e
Sp
id
e
r
Mo
n
k
ey
Op
tim
is
atio
n
alg
o
r
it
h
m
an
d
th
e
Pad
d
y
Field
Alg
o
r
ith
m
,
u
s
in
g
a
b
io
-
in
s
p
ir
ed
ap
p
r
o
ac
h
.
T
h
ey
em
p
lo
y
ed
a
wr
a
p
p
er
s
tr
ateg
y
f
o
r
f
ea
tu
r
e
s
elec
tio
n
.
T
h
e
task
o
f
class
if
icatio
n
was
p
er
f
o
r
m
ed
u
s
in
g
SVMs
.
Valid
atio
n
was
co
n
d
u
cte
d
u
s
in
g
t
en
-
f
o
ld
cr
o
s
s
v
alid
atio
n
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
was
ev
alu
ated
u
s
in
g
a
r
ea
l
-
tim
e
b
en
ch
m
ar
k
d
ataset.
T
h
ey
s
h
o
wed
th
at
em
p
lo
y
in
g
T
PM
(
tr
u
e
p
o
s
itiv
e,
f
alse
n
eg
ativ
e,
tr
u
e
p
o
s
itiv
e,
an
d
f
alse
n
eg
ativ
e)
a
n
aly
s
is
f
o
r
ass
es
s
in
g
ac
cu
r
ac
y
u
s
in
g
p
r
ec
is
io
n
an
d
r
ec
all
en
h
an
ce
s
class
if
icatio
n
ac
cu
r
ac
y
.
B
y
em
p
lo
y
in
g
s
war
m
in
tellig
en
ce
-
b
ased
o
p
tim
is
atio
n
,
th
eir
s
tu
d
ies
h
ig
h
lig
h
ted
th
e
ef
f
icac
y
o
f
th
eir
p
r
o
p
o
s
ed
f
ea
tu
r
e
s
elec
tio
n
m
eth
o
d
in
ef
f
ec
tiv
el
y
r
e
d
u
ci
n
g
th
e
n
u
m
b
er
o
f
f
ea
tu
r
es
to
an
id
ea
l
lev
el.
H
o
wev
er
,
v
ia
t
h
e
p
r
o
ce
s
s
o
f
ex
p
er
i
m
en
tin
g
with
alter
n
ativ
e
class
if
icatio
n
s
tr
ateg
ies,
th
eir
m
o
d
el
h
as th
e
p
o
te
n
tial to
b
ec
o
m
e
ev
en
m
o
r
e
p
r
ec
is
e
[
2
2
]
.
2
.
3
.
Cla
s
s
if
ica
t
io
n
J
ain
et
a
l.
[
2
3
]
d
ev
el
o
p
ed
an
ad
v
an
ce
d
class
if
icatio
n
m
o
d
el
th
at
u
tili
ze
s
SVM
an
d
s
elf
o
r
g
an
is
in
g
m
ap
s
(
SOM)
to
ca
teg
o
r
is
e
p
ix
els
as
eith
er
in
s
id
e
o
r
e
x
ter
io
r
b
ased
o
n
th
e
c
o
m
p
a
r
i
s
o
n
o
f
p
o
s
t
e
r
i
o
r
p
r
o
b
a
b
i
l
i
t
y
p
i
x
e
l
i
n
t
e
n
s
i
t
i
es
.
T
h
e
y
h
a
v
e
s
h
o
w
n
t
h
a
t
t
h
e
i
r
m
o
d
e
l
s
u
r
p
a
s
s
e
s
t
h
e
e
x
i
s
t
i
n
g
m
e
t
h
o
d
s
i
n
t
e
r
m
s
o
f
c
l
a
s
s
i
f
i
c
at
i
o
n
a
c
c
u
r
a
c
y
,
a
s
e
v
al
u
a
t
e
d
b
y
K
ap
p
a
s
t
a
ti
s
t
i
cs
v
a
l
u
es
[
2
3
]
.
W
o
r
k
i
n
[
2
4
]
u
t
i
l
i
s
e
d
r
a
n
d
o
m
f
o
r
e
s
t
a
n
d
p
r
i
n
c
i
p
al
c
o
m
p
o
n
e
n
t
a
n
a
l
y
s
is
t
o
d
e
v
e
l
o
p
a
n
o
v
e
l
c
l
a
s
s
i
f
ie
r
t
h
a
t
i
n
c
o
r
p
o
r
a
t
e
s
a
ll
t
h
r
e
e
s
e
ts
o
f
a
t
t
r
i
b
u
te
s
.
S
u
b
s
e
q
u
e
n
t
l
y
,
t
o
d
e
t
e
r
m
i
n
e
t
h
e
o
p
t
i
m
a
l
c
h
a
r
a
ct
e
r
i
s
t
i
cs
f
o
r
c
o
n
s
t
r
u
c
t
i
n
g
t
h
e
i
r
n
o
v
e
l
c
l
a
s
s
i
f
i
e
r
,
t
h
e
y
h
a
v
e
n
a
r
r
o
w
e
d
d
o
w
n
t
h
e
f
e
a
t
u
r
e
s
d
e
p
e
n
d
i
n
g
o
n
t
h
e
a
c
c
u
r
a
c
y
a
t
t
a
i
n
e
d
b
y
t
h
e
i
r
n
e
w
c
l
a
s
s
i
f
i
e
r
.
A
d
d
i
ti
o
n
a
l
r
e
s
e
a
r
ch
i
s
c
a
r
r
i
e
d
o
u
t
t
o
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
2
0
2
0
-
203
0
2024
d
e
t
e
r
m
i
n
e
t
h
e
o
p
t
i
m
al
h
y
p
e
r
p
ar
a
m
e
t
e
r
s
f
o
r
t
h
e
r
a
n
d
o
m
f
o
r
e
s
t
c
l
as
s
i
f
i
e
r
.
T
h
e
o
p
t
i
m
al
r
a
n
d
o
m
f
o
r
e
s
t
a
n
d
KN
N
m
o
d
e
l
s
h
a
v
e
b
o
t
h
d
e
t
e
r
m
i
n
e
d
a
s
i
g
n
i
f
i
c
a
n
ce
t
h
r
e
s
h
o
l
d
o
f
0
.
0
5
[
2
4
]
.
R
esear
ch
wo
r
k
in
[
2
5
]
c
o
n
d
u
c
ted
v
ar
io
u
s
e
x
p
er
im
en
ts
o
n
th
e
m
o
d
if
ied
n
atio
n
al
in
s
titu
te
o
f
s
tan
d
ar
d
s
an
d
tech
n
o
lo
g
y
(
MN
I
ST)
d
at
aset
to
ass
es
s
an
d
ex
am
in
e
th
e
p
er
f
o
r
m
an
ce
o
f
co
n
v
en
tio
n
a
l
m
ac
h
in
e
lear
n
in
g
(
ML
)
an
d
d
ee
p
lear
n
in
g
(
DL
)
m
o
d
els
f
o
r
im
ag
e
ca
teg
o
r
izatio
n
.
B
y
u
tili
s
in
g
a
v
ast
an
d
co
m
m
o
n
ly
u
s
ed
im
ag
e
d
ataset
as
th
e
in
p
u
t,
th
ey
h
av
e
ac
h
iev
ed
a
C
NN
ac
cu
r
ac
y
o
f
9
8
%
an
d
a
SVM
ac
cu
r
ac
y
o
f
8
8
%.
T
h
e
y
h
av
e
ac
h
iev
ed
a
n
ac
c
u
r
ac
y
o
f
8
3
%
f
o
r
C
NN
an
d
8
6
%
f
o
r
SVM,
wh
ile
u
s
in
g
lim
ited
im
ag
e
d
atasets
[
2
5
]
.
T
h
e
s
p
ec
tr
al
d
im
e
n
s
io
n
,
i
n
itially
in
tr
o
d
u
ce
d
b
y
[
2
6
]
en
h
a
n
ce
s
o
b
ject
d
etec
tio
n
in
r
elat
io
n
to
i
m
ag
es
an
d
en
ab
les
th
e
a
d
v
an
ce
m
en
t
o
f
a
r
o
b
u
s
t
f
ac
ial
r
e
co
g
n
itio
n
s
y
s
tem
.
T
h
e
s
p
ec
tr
al
d
im
e
n
s
io
n
o
f
a
HSI
en
h
an
ce
s
th
e
p
r
ec
is
io
n
o
f
f
ac
e
id
en
tifi
ca
tio
n
b
y
en
h
a
n
cin
g
t
h
e
lev
el
o
f
d
etail
in
th
e
im
a
g
e.
B
y
em
p
lo
y
in
g
b
an
d
f
u
s
io
n
an
d
b
a
n
d
s
elec
tio
n
tec
h
n
iq
u
es,
a
r
em
ar
k
ab
le
ac
c
u
r
a
cy
o
f
9
7
.
3
%
was
ac
h
iev
ed
in
th
e
f
ield
o
f
f
ac
ial
r
ec
o
g
n
itio
n
[
2
6
]
.
T
ah
er
k
h
a
n
i
et
a
l.
[
2
7
]
d
ev
elo
p
ed
a
n
o
v
el
f
r
am
ewo
r
k
th
at
i
n
teg
r
ates
th
e
C
NN
an
d
s
p
ar
s
i
ty
lear
n
in
g
ap
p
r
o
ac
h
to
d
eter
m
in
e
t
h
e
m
o
s
t
ef
f
ec
tiv
e
s
p
ec
tr
al
b
an
d
s
f
o
r
o
p
tim
al
p
er
f
o
r
m
a
n
ce
in
f
ac
e
r
ec
o
g
n
itio
n
.
Sp
ec
if
ically
,
o
n
ce
all
th
e
b
a
n
d
s
h
av
e
b
ee
n
p
r
o
ce
s
s
ed
b
y
a
C
NN
,
th
e
f
ilter
s
in
th
e
in
itial
lay
er
o
f
th
e
C
NN
ar
e
r
eg
u
lar
is
ed
u
s
in
g
a
g
r
o
u
p
L
as
s
o
tech
n
iq
u
e
to
r
em
o
v
e
r
ed
u
n
d
an
t
b
a
n
d
s
d
u
r
in
g
th
e
tr
ain
in
g
p
r
o
ce
s
s
.
I
n
o
r
d
e
r
to
g
et
th
e
b
est
p
o
s
s
ib
le
p
er
f
o
r
m
an
ce
in
th
e
f
ac
e
r
ec
o
g
n
itio
n
tech
n
iq
u
e,
t
h
ey
h
a
v
e
s
elec
ted
th
e
m
o
s
t
s
u
itab
le
s
p
ec
tr
al
b
an
d
s
.
E
x
p
er
im
e
n
ts
u
s
in
g
HSI
d
atasets
ac
h
iev
ed
h
ig
h
er
class
if
icatio
n
ac
cu
r
ac
y
th
an
th
e
m
o
s
t
ad
v
an
ce
d
alg
o
r
ith
m
s
c
u
r
r
en
tly
av
ailab
le
[
2
7
]
.
R
esear
ch
wo
r
k
[
2
8
]
em
p
l
o
y
e
d
a
DL
m
eth
o
d
o
lo
g
y
to
d
ev
e
lo
p
a
n
o
v
el
n
etwo
r
k
th
at
ad
d
r
ess
es
th
e
is
s
u
es
an
d
en
h
an
ce
s
th
e
ac
cu
r
ac
y
o
f
HSI
ca
teg
o
r
izatio
n
.
T
h
eir
3
D
C
NN
is
a
s
o
p
h
is
ticat
ed
DL
ar
ch
itectu
r
e
th
at
en
h
an
ce
s
class
if
icatio
n
ac
cu
r
ac
y
.
I
n
o
r
d
e
r
to
en
s
u
r
e
t
h
e
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
o
f
th
e
d
ata,
th
e
DL
ar
ch
itectu
r
e
u
tili
s
es
s
p
ec
tr
al
a
n
d
s
p
atial
d
en
s
e
co
n
n
ec
tiv
ity
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
e
ac
q
u
ir
i
n
g
an
d
u
tili
s
in
g
th
e
p
er
tin
en
t
ch
a
r
ac
ter
is
tics
v
ia
a
s
p
ec
tr
al
an
d
s
p
atial
d
iv
is
i
o
n
.
Fu
r
th
e
r
m
o
r
e
,
th
ey
h
av
e
em
p
lo
y
e
d
s
ev
er
al
o
p
tim
is
atio
n
m
eth
o
d
s
s
u
ch
as
r
eg
u
lar
is
atio
n
,
n
o
r
m
alis
atio
n
,
d
r
o
p
o
u
t,
d
ata
au
g
m
en
tatio
n
,
an
d
lear
n
in
g
r
ate
ad
ju
s
tm
en
ts
to
ad
d
r
ess
th
e
is
s
u
es
an
d
e
n
h
an
ce
th
e
ac
c
u
r
ac
y
o
f
class
if
icatio
n
.
Ultim
ately
,
th
ey
co
n
d
u
cted
a
co
m
p
r
eh
e
n
s
iv
e
s
er
ies
o
f
test
s
to
d
em
o
n
s
tr
ate
th
at
th
eir
DL
f
r
am
ewo
r
k
s
u
r
p
ass
ed
th
e
c
o
m
p
etitio
n
,
with
a
r
em
ar
k
ab
le
ac
c
u
r
ac
y
r
ate
o
f
9
9
% [
2
8
]
.
3.
P
RO
P
O
SE
D
M
E
T
H
O
DO
L
O
G
Y
T
h
is
s
ec
tio
n
in
tr
o
d
u
ce
s
a
f
ac
i
al
r
ec
o
g
n
itio
n
s
y
s
tem
th
at
au
t
o
m
atica
lly
r
ec
o
r
d
s
atten
d
an
ce
s
y
s
tem
as
s
h
o
wn
in
Fig
u
r
e
2
.
T
h
is
s
y
s
te
m
co
m
p
r
is
es
o
f
m
an
y
c
o
m
p
o
n
en
ts
:
im
ag
e
ac
q
u
is
itio
n
.
Acq
u
i
r
ed
im
ag
es
co
n
tain
n
o
is
es.
His
to
g
r
am
eq
u
aliza
tio
n
is
u
s
ed
to
r
em
o
v
e
n
o
is
es
f
r
o
m
im
ag
es
an
d
also
to
en
h
a
n
ce
im
ag
e
q
u
ality
.
I
m
ag
e
s
eg
m
en
tatio
n
is
co
n
d
u
cted
u
s
in
g
th
e
f
u
zz
y
C
m
ea
n
s
clu
s
ter
in
g
ap
p
r
o
ac
h
,
an
d
t
h
e
co
n
s
tr
u
ctio
n
o
f
a
class
if
icatio
n
m
o
d
el
u
s
in
g
th
e
KNN
,
SVM
,
an
d
Ad
aBo
o
s
t
t
ec
h
n
iq
u
es.
A
r
an
d
o
m
s
elec
tio
n
o
f
5
0
0
p
h
o
to
s
o
f
p
u
p
ils
f
r
o
m
a
class
is
m
ad
e
f
o
r
ex
p
er
im
en
tal
p
u
r
p
o
s
es.
T
h
e
s
u
g
g
ested
f
r
am
ewo
r
k
a
ch
iev
es
a
9
8
.
7
5
%
ac
cu
r
ac
y
f
o
r
th
e
KNN
alg
o
r
ith
m
.
KNN
d
em
o
n
s
tr
ates su
p
er
io
r
p
er
f
o
r
m
an
ce
in
ter
m
s
o
f
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
ac
cu
r
ac
y
,
a
n
d
F_
m
ea
s
u
r
e
.
Fig
u
r
e
2
.
Ma
ch
i
n
e
lear
n
in
g
b
a
s
ed
au
to
m
ated
s
m
ar
t a
tten
d
an
ce
s
y
s
tem
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
Desig
n
o
f fa
ce
r
ec
o
g
n
itio
n
b
a
s
ed
effec
tive
a
u
to
ma
ted
s
ma
r
t a
tten
d
a
n
ce
s
ystem
(
Jy
o
ti L.
B
a
n
g
a
r
e
)
2025
Utilizin
g
h
is
to
g
r
am
eq
u
aliza
tio
n
,
a
b
asic
m
eth
o
d
in
im
ag
e
p
r
o
ce
s
s
in
g
m
ay
p
r
o
v
id
e
p
i
ctu
r
es
o
f
en
h
an
ce
d
clar
ity
an
d
d
etail.
Hig
h
-
d
ef
in
itio
n
p
h
o
to
s
ar
e
ess
en
tial
f
o
r
ac
cu
r
ately
id
en
tify
in
g
im
ag
es.
B
y
ap
p
ly
in
g
h
is
to
g
r
am
eq
u
aliza
ti
o
n
to
t
h
e
f
in
al
p
ictu
r
e,
an
y
p
r
ev
io
u
s
ly
s
u
p
p
r
ess
ed
s
o
u
n
d
s
w
ill
b
e
r
esto
r
ed
w
h
en
all
th
e
p
r
o
ce
s
s
in
g
is
f
in
is
h
ed
.
T
h
is
ap
p
r
o
ac
h
is
o
f
ten
u
s
ed
in
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
.
T
h
is
ap
p
r
o
ac
h
g
en
er
ates
a
h
is
to
g
r
am
o
f
g
r
ey
lev
els
th
at
ar
e
co
n
s
is
ten
tly
s
m
o
o
th
an
d
p
er
f
ec
t
b
y
d
eter
m
in
in
g
th
e
g
r
ey
m
ap
p
in
g
o
f
th
e
p
ictu
r
e
u
s
in
g
g
r
ey
o
p
er
atio
n
s
[
2
9
]
.
T
h
e
clu
s
ter
in
g
tech
n
iq
u
e
s
ee
k
s
to
id
en
tify
th
e
u
n
d
er
ly
in
g
r
elatio
n
s
h
ip
s
b
etwe
en
p
ix
els in
a
p
ictu
r
e
b
y
o
r
g
an
izin
g
s
im
ilar
p
atter
n
s
in
to
g
r
o
u
p
s
.
C
lu
s
ter
in
g
is
th
e
p
r
o
ce
s
s
o
f
class
if
y
in
g
item
s
in
to
g
r
o
u
p
s
b
ased
o
n
co
m
m
o
n
ch
a
r
ac
ter
is
tics
.
W
h
e
n
th
e
FC
M
ap
p
r
o
ac
h
is
u
s
ed
,
d
ata
o
b
jects
ar
e
o
r
g
an
ized
in
t
o
s
ets
ac
co
r
d
in
g
to
th
eir
m
em
b
er
s
h
ip
v
alu
es.
W
h
en
m
ax
im
izin
g
th
e
o
b
jectiv
e
f
u
n
ctio
n
,
t
h
e
m
eth
o
d
o
f
least
s
q
u
ar
es
is
u
s
ed
,
an
d
u
p
o
n
c
alcu
latio
n
,
th
e
f
in
al
d
at
a
is
d
iv
id
ed
[
3
0
]
.
Fo
r
class
if
icatio
n
p
u
r
p
o
s
es,
th
e
KNN
m
eth
o
d
,
wh
ich
is
a
k
in
d
o
f
s
u
p
e
r
v
is
ed
alg
o
r
ith
m
,
is
th
e
m
o
s
t
r
eliab
le
ch
o
ice.
I
t
is
im
p
o
r
tan
t
to
n
o
te
th
at
th
is
tech
n
iq
u
e
c
o
n
s
tan
tly
p
r
o
d
u
ce
s
id
e
n
tical
o
u
tco
m
es,
r
eg
ar
d
less
o
f
th
e
tr
ain
in
g
d
ata
u
s
ed
.
E
ac
h
s
am
p
le
m
ay
b
e
class
if
ied
b
ased
o
n
its
s
im
i
lar
ity
to
th
e
p
o
p
u
latio
n
v
alu
e,
with
o
n
ly
a
f
ew
s
am
p
les
b
ein
g
allo
ca
ted
a
class
.
T
h
e
eq
u
atio
n
p
r
o
v
id
e
d
p
r
o
v
id
es
th
e
E
u
clid
ea
n
d
is
tan
ce
as
a
m
ea
n
s
to
q
u
an
tif
y
th
e
s
im
ilar
ity
b
etwe
en
two
-
p
ix
el
p
o
s
itio
n
s
.
C
o
n
s
id
er
in
g
t
h
ese
f
ac
to
r
s
,
it
wo
u
ld
h
av
e
b
ee
n
p
r
ef
er
ab
le
f
o
r
th
e
p
ix
els
to
b
e
in
itially
g
r
o
u
p
ed
to
g
eth
er
,
an
d
th
at
is
p
r
ec
is
ely
wh
at
o
cc
u
r
s
.
T
h
e
KNN
alg
o
r
ith
m
id
e
n
tifie
s
th
e
n
eig
h
b
o
u
r
h
o
o
d
with
th
e
m
in
im
u
m
d
is
tan
ce
b
etwe
en
an
y
two
n
ei
g
h
b
o
u
r
s
,
wh
ich
is
d
en
o
ted
b
y
th
e
letter
K.
Prim
a
r
ily
,
co
n
s
id
er
th
e
q
u
an
tity
o
f
r
esid
en
ce
s
in
th
e
v
icin
ity
.
W
h
en
th
er
e
ar
e
ju
s
t
two
co
u
r
s
es,
it
is
q
u
ite
lik
el
y
th
a
t
th
er
e
will
b
e
an
o
d
d
n
u
m
b
er
o
f
th
e
m
.
T
h
e
n
u
m
b
er
K
=
1
is
u
s
ed
f
o
r
th
e
ca
lcu
latio
n
o
f
th
e
n
ea
r
est n
eig
h
b
o
u
r
at
th
at
p
ar
ticu
lar
s
tep
in
th
e
alg
o
r
ith
m
.
I
f
th
is
wer
e
to
h
ap
p
en
,
it wo
u
ld
b
e
th
e
m
o
s
t stra
ig
h
tf
o
r
war
d
an
d
u
n
co
m
p
licated
r
esu
lt [
3
1
]
.
SVMs
ar
e
a
k
in
d
o
f
d
is
cr
im
in
ativ
e
class
if
ier
th
at
m
ath
em
atica
lly
r
ep
r
esen
ts
a
d
ec
is
io
n
b
o
u
n
d
ar
y
in
a
s
in
g
le
h
y
p
er
p
lan
e.
Nev
e
r
th
el
ess
,
wh
en
n
ew
m
o
d
els
ar
e
b
u
ilt
u
tili
zin
g
s
tam
p
ed
p
r
e
p
ar
atio
n
d
ata
,
th
e
co
m
p
u
tatio
n
y
ield
s
an
o
p
tim
a
l
h
y
p
er
p
lan
e.
Fin
d
a
lin
ea
r
b
o
u
n
d
a
r
y
th
at
ca
n
ef
f
ec
tiv
el
y
d
is
tin
g
u
is
h
b
etwe
en
two
s
ets
o
f
2
D
ce
n
tr
es
b
y
f
o
ll
o
win
g
a
d
is
tin
ct
tr
ajec
to
r
y
.
D
ata
m
ay
b
e
p
a
r
titi
o
n
ed
a
n
d
a
m
eth
o
d
o
l
o
g
y
ca
n
b
e
s
h
o
wn
u
s
in
g
SVM
.
T
h
ese
in
cl
u
d
e
s
ev
er
al
co
m
p
u
tatio
n
al
alg
o
r
ith
m
s
an
d
s
u
p
e
r
v
is
ed
lear
n
i
n
g
m
o
d
els.
Usu
ally
,
SVM
is
u
s
ed
f
o
r
r
e
p
r
esen
tatio
n
an
d
r
eg
r
ess
io
n
a
n
aly
s
is
.
SVM
ar
e
u
s
ed
t
o
tack
le
th
e
is
s
u
e
o
f
class
if
y
in
g
m
a
n
y
class
es.
T
h
e
o
b
jectiv
e
o
f
th
e
f
ig
u
r
e
is
to
d
eter
m
in
e
th
e
p
o
s
itio
n
o
f
th
e
class
h
y
p
er
p
lan
e.
Fu
r
th
er
m
o
r
e
,
alo
n
g
s
id
e
th
e
h
y
p
er
p
lan
es th
at
s
ca
tter
th
e
d
ata,
two
s
y
m
m
etr
i
ca
l h
y
p
er
p
lan
es a
r
e
also
ex
p
an
d
in
g
[
3
2
]
.
Ad
a
B
o
o
s
t
is
a
m
eth
o
d
th
at
m
ay
b
e
u
s
ed
to
tr
ain
class
if
ier
s
th
at
ar
e
n
o
t
v
er
y
ef
f
ec
tiv
e
in
ac
cu
r
ately
ca
teg
o
r
izin
g
d
ata,
with
th
e
ai
m
o
f
im
p
r
o
v
in
g
th
eir
ac
cu
r
ac
y
.
T
h
e
Ad
a
B
o
o
s
t
m
eth
o
d
will
b
e
u
s
ed
to
allo
ca
te
in
itial
weig
h
ts
to
ea
ch
o
b
s
er
v
atio
n
.
Ob
s
er
v
atio
n
s
th
at
wer
e
in
co
r
r
ec
tly
ca
teg
o
r
ized
will
b
e
ass
ig
n
ed
m
o
r
e
im
p
o
r
tan
ce
af
ter
a
f
ew
cy
c
les,
wh
ils
t
th
o
s
e
th
at
wer
e
co
r
r
ec
tly
class
if
ied
wo
u
ld
b
e
ass
ig
n
ed
less
er
im
p
o
r
tan
ce
.
B
y
ap
p
ly
in
g
wei
g
h
ts
to
o
b
s
er
v
atio
n
s
ac
co
r
d
in
g
to
th
eir
r
esp
ec
tiv
e
class
es,
we
m
ay
s
ig
n
if
ican
tly
im
p
r
o
v
e
th
e
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
class
if
ier
.
As
a
r
esu
lt,
th
e
r
e
ar
e
f
ewe
r
i
n
s
tan
ce
s
o
f
in
co
r
r
ec
t
ca
teg
o
r
izatio
n
.
T
h
e
tech
n
iq
u
e
o
f
“
b
o
o
s
tin
g
”
in
v
o
lv
es
im
p
le
m
en
tin
g
a
s
eq
u
en
ce
o
f
tailo
r
ed
a
d
ju
s
tm
en
ts
to
p
u
p
ils
wh
o
ar
e
ex
p
er
ien
cin
g
ac
ad
em
ic
ch
allen
g
es.
As
th
e
s
er
ie
s
ad
v
an
ce
s
,
ea
ch
s
u
b
s
eq
u
en
t
m
o
d
el
ass
ig
n
s
m
o
r
e
im
p
o
r
tan
c
e
to
d
ata
th
at
wer
e
p
r
ev
io
u
s
ly
g
i
v
en
less
em
p
h
asis
[
3
3
]
.
4.
E
XP
E
R
I
M
E
N
T
A
L
SE
T
T
I
N
G
AND
RE
SU
L
T
ANA
L
YSI
S
T
o
ca
r
r
y
o
u
t
th
e
ex
p
er
im
e
n
t,
a
s
elec
tio
n
o
f
5
0
0
p
h
o
to
g
r
ap
h
s
o
f
s
tu
d
en
ts
f
r
o
m
a
ce
r
tain
clas
s
is
m
ad
e
u
s
in
g
a
r
an
d
o
m
s
am
p
lin
g
m
eth
o
d
.
T
h
e
tr
ain
in
g
s
et
co
m
p
r
is
es
4
0
0
p
h
o
to
g
r
a
p
h
s
,
wh
ils
t
th
e
test
in
g
s
et
co
n
s
is
ts
o
f
1
0
0
p
ictu
r
es.
T
h
e
i
n
p
u
t
im
ag
e
co
n
tain
s
m
an
y
au
d
ito
r
y
s
tim
u
li.
His
to
g
r
am
e
q
u
aliza
tio
n
f
ilter
s
ar
e
u
s
ed
to
r
em
o
v
e
o
r
s
ig
n
if
ican
tly
m
in
i
m
ize
u
n
wan
ted
d
is
tu
r
b
a
n
ce
s
.
Af
ter
r
em
o
v
in
g
n
o
is
e,
h
is
to
g
r
am
eq
u
aliza
tio
n
is
a
p
r
o
m
is
in
g
o
p
tio
n
f
o
r
im
p
r
o
v
i
n
g
th
e
q
u
ality
o
f
a
n
im
ag
e.
C
lass
if
icatio
n
m
o
d
el
is
b
u
ilt
u
s
in
g
KNN,
SVM
,
an
d
Ad
aBo
o
s
t
tech
n
iq
u
es.
Me
tr
ics
s
u
ch
as
ac
cu
r
ac
y
,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
p
r
ec
is
io
n
an
d
F_
m
ea
s
u
r
e
ar
e
u
s
ed
in
th
e
ev
alu
atio
n
p
r
o
ce
s
s
to
ev
al
u
ate
p
er
f
o
r
m
an
ce
.
KNN
is
p
er
f
o
r
m
in
g
m
u
c
h
b
etter
t
h
an
th
e
o
th
er
m
eth
o
d
s
u
s
ed
in
th
e
f
r
am
ewo
r
k
.
R
esu
lts
ar
e
p
r
esen
ted
in
T
ab
le
1
an
d
Fig
u
r
e
3.
Acc
u
r
ac
y
o
f
KNN
alg
o
r
ith
m
in
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
is
9
8
.
7
5
%
.
I
t
is
h
i
g
h
er
t
h
an
t
h
e
ac
cu
r
ac
y
o
f
SVM
(
9
6
.
2
5
%)
a
n
d
Ad
aBo
o
s
t
(
8
6
.
5
0
%).
KNN
is
also
p
er
f
o
r
m
in
g
b
etter
o
n
p
ar
am
ete
r
s
lik
e
-
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
p
r
ec
is
io
n
an
d
F_
m
ea
s
u
r
e
.
T
ab
le
1
.
R
esu
lts
o
f
KNN,
SVM
an
d
Ad
aBo
o
s
t a
lg
o
r
ith
m
f
o
r
f
ac
e
r
ec
o
g
n
itio
n
b
ased
s
m
ar
t
atten
d
an
ce
s
y
s
tem
A
c
c
u
r
a
c
y
S
e
n
s
i
t
i
v
i
t
y
S
p
e
c
i
f
i
c
i
t
y
P
r
e
c
i
s
i
o
n
F
_
M
e
a
s
u
r
e
A
d
a
B
o
o
st
8
6
.
5
0
9
4
.
2
5
9
3
.
5
0
9
3
.
2
5
8
8
.
7
5
S
V
M
9
6
.
2
5
9
6
.
5
0
9
5
.
7
5
9
4
.
5
0
9
5
.
2
5
K
N
N
9
8
.
7
5
9
8
.
2
5
9
8
.
2
5
9
8
.
5
0
9
8
.
7
5
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
2
0
2
0
-
203
0
2026
Fig
u
r
e
3
.
Per
f
o
r
m
an
c
e
o
f
KN
N,
SVM
an
d
Ad
aBo
o
s
t a
lg
o
r
it
h
m
f
o
r
f
ac
e
r
ec
o
g
n
itio
n
b
ased
s
m
ar
t a
tten
d
an
ce
s
y
s
te
m
5.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
An
au
to
m
ated
atten
d
a
n
ce
s
y
s
tem
b
ased
o
n
f
ac
ial
r
ec
o
g
n
itio
n
is
p
r
esen
ted
in
th
is
ar
ticle.
T
h
is
s
y
s
te
m
co
n
s
is
ts
o
f
ac
q
u
is
itio
n
o
f
im
a
g
es,
im
ag
e
s
eg
m
en
tatio
n
u
s
in
g
f
u
zz
y
C
m
ea
n
s
clu
s
ter
in
g
,
im
ag
e
au
g
m
en
tatio
n
u
s
in
g
h
is
to
g
r
am
e
q
u
aliza
tio
n
,
an
d
th
e
co
n
s
tr
u
ctio
n
o
f
a
class
if
icatio
n
m
o
d
el
u
tili
zin
g
KNN
,
SVM
,
an
d
Ad
aBo
o
s
t
tech
n
iq
u
es.
T
h
e
f
ac
ial
r
ec
o
g
n
itio
n
s
y
s
tem
ca
n
ef
f
ec
tiv
ely
id
en
tify
an
d
v
e
r
if
y
an
in
d
iv
i
d
u
al
’
s
id
en
tity
b
y
u
tili
zin
g
a
d
ig
ital
ca
m
er
a
o
r
v
id
eo
ca
m
er
a.
T
h
e
d
ev
ice
ca
p
tu
r
es
p
h
o
t
o
g
r
ap
h
s
o
f
in
d
iv
i
d
u
als
in
a
co
m
m
u
n
ity
ar
ea
,
lin
k
s
with
th
e
s
u
r
v
eillan
ce
s
y
s
tem
,
an
d
in
t
eg
r
ates
with
an
ex
is
tin
g
d
atab
ase.
5
0
0
p
h
o
to
s
o
f
a
class
’
s
s
tu
d
en
ts
ar
e
ch
o
s
en
at
r
an
d
o
m
f
o
r
th
e
e
x
p
er
im
e
n
t.
I
n
th
e
s
u
g
g
ested
f
r
am
ewo
r
k
,
th
e
KNN
alg
o
r
ith
m
’
s
ac
cu
r
ac
y
is
9
8
.
7
5
%
.
I
t su
r
p
ass
es th
e
ac
cu
r
ac
y
o
f
Ad
aBo
o
s
t (
8
6
.
5
0
%)
an
d
SVM
(
9
6
.
2
5
%).
Ad
d
itio
n
ally
,
KNN
is
o
u
tp
er
f
o
r
m
in
g
o
t
h
er
m
o
d
el
s
in
ter
m
s
o
f
F_
m
ea
s
u
r
e,
s
en
s
itiv
ity
,
s
p
ec
if
icity
,
an
d
ac
cu
r
ac
y
.
I
n
n
ea
r
f
u
tu
r
e,
atten
d
an
ce
s
y
s
tem
p
r
o
p
o
s
ed
i
n
th
is
p
ap
er
ca
n
b
e
u
p
g
r
a
d
ed
to
wo
r
k
in
r
ea
l
tim
e
en
v
ir
o
n
m
en
t
b
y
u
s
in
g
I
o
T
b
ased
ca
m
er
as a
n
d
d
ev
ices.
ACK
NO
WL
E
DG
E
M
E
NT
S
W
e
ar
e
d
ee
p
ly
th
an
k
f
u
l
to
o
u
r
in
s
titu
tio
n
s
f
o
r
p
r
o
v
id
i
n
g
th
e
n
ec
ess
ar
y
r
eso
u
r
ce
s
an
d
f
ac
ilit
ies
th
at
en
ab
led
th
e
s
u
cc
ess
f
u
l c
o
m
p
le
tio
n
o
f
th
is
r
esear
ch
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
No
f
u
n
d
in
g
r
ec
ei
v
ed
f
o
r
th
is
r
ea
s
ea
r
ch
wo
r
k
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
J
y
o
ti L
.
B
an
g
ar
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Dip
tee
C
h
ik
m
u
r
g
e
✓
✓
✓
✓
✓
✓
✓
Kar
th
ik
ey
an
Kaliy
ap
er
u
m
al
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Me
en
ak
s
h
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Su
n
il L
.
B
an
g
ar
e
✓
✓
✓
✓
✓
✓
✓
Kis
h
o
r
i K
asat
✓
✓
✓
✓
✓
✓
✓
Kan
tilal Pitam
b
ar
R
an
e
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
R
av
i K
is
h
o
r
e
Velu
r
i
✓
✓
✓
✓
B
aty
r
k
h
an
Om
ar
o
v
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ma
lik
J
awa
r
n
eh
✓
✓
✓
✓
Ab
h
is
h
ek
R
ag
h
u
v
a
n
s
h
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
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
Desig
n
o
f fa
ce
r
ec
o
g
n
itio
n
b
a
s
ed
effec
tive
a
u
to
ma
ted
s
ma
r
t a
tten
d
a
n
ce
s
ystem
(
Jy
o
ti L.
B
a
n
g
a
r
e
)
2027
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
E
th
ical
ap
p
r
o
v
al
was n
o
t r
e
q
u
i
r
ed
f
o
r
th
is
s
tu
d
y
,
as it d
id
n
o
t
in
v
o
lv
e
h
u
m
an
o
r
a
n
im
al
s
u
b
j
ec
ts
.
DATA AV
AI
L
AB
I
L
I
T
Y
Data
av
ailab
ilit
y
is
n
o
t
ap
p
li
ca
b
le
to
th
is
p
ap
er
as
n
o
n
e
w
d
ata
wer
e
cr
ea
ted
o
r
an
aly
ze
d
in
th
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[
1
]
V
.
R
o
h
i
n
i
,
M
.
S
o
b
h
a
n
a
,
a
n
d
C
.
S
.
C
h
o
w
d
a
r
y
,
“
A
t
t
e
n
d
a
n
c
e
m
o
n
i
t
o
r
i
n
g
s
y
s
t
e
m
d
e
s
i
g
n
b
a
s
e
d
o
n
f
a
c
e
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n,
”
Re
c
e
n
t
Pa
t
e
n
t
s
o
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
6
,
A
p
r
.
2
0
2
2
,
d
o
i
:
1
0
.
2
1
7
4
/
1
8
7
2
2
1
2
1
1
6
6
6
6
2
2
0
4
0
1
1
5
4
6
3
9
.
[
2
]
M
.
Z.
K
h
a
n
,
S
.
H
a
r
o
u
s
,
S
.
U
.
H
a
ss
a
n
,
M
.
U
.
G
.
K
h
a
n
,
R
.
I
q
b
a
l
,
a
n
d
S
.
M
u
m
t
a
z
,
“
D
e
e
p
u
n
i
f
i
e
d
m
o
d
e
l
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
e
d
g
e
c
o
m
p
u
t
i
n
g
,
”
i
n
I
E
EE
Ac
c
e
ss,
v
o
l
.
7
,
p
p
.
7
2
6
2
2
-
7
2
6
3
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
1
8
2
7
5
.
[
3
]
K
.
A
l
h
a
n
a
e
e
,
M
.
A
l
h
a
mm
a
d
i
,
N
.
A
l
men
h
a
l
i
,
a
n
d
M
.
S
h
a
t
n
a
w
i
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
smar
t
a
t
t
e
n
d
a
n
c
e
s
y
s
t
e
m
u
si
n
g
d
e
e
p
t
r
a
n
sf
e
r
l
e
a
r
n
i
n
g
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
9
2
,
p
p
.
4
0
9
3
–
4
1
0
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
1
.
0
9
.
1
8
4
.
[
4
]
S
.
B
h
a
t
t
a
c
h
a
r
y
a
,
G
.
S
.
N
a
i
n
a
l
a
,
P
.
D
a
s,
a
n
d
A
.
R
o
u
t
r
a
y
,
“
S
mar
t
a
t
t
e
n
d
a
n
c
e
mo
n
i
t
o
r
i
n
g
s
y
s
t
e
m
(
S
A
M
S
)
:
a
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
-
b
a
s
e
d
a
t
t
e
n
d
a
n
c
e
s
y
st
e
m
f
o
r
c
l
a
ssr
o
o
m
e
n
v
i
r
o
n
me
n
t
,
”
I
EEE
X
p
l
o
re
,
J
u
l
.
0
1
,
2
0
1
8
,
h
t
t
p
s
:
/
/
i
e
e
e
x
p
l
o
r
e
.
i
e
e
e
.
o
r
g
/
a
b
s
t
r
a
c
t
/
d
o
c
u
m
e
n
t
/
8
4
3
3
5
3
7
[
5
]
S
.
S
a
w
h
n
e
y
,
K
.
K
a
c
k
e
r
,
S
.
Ja
i
n
,
S
.
N
.
S
i
n
g
h
,
a
n
d
R
.
G
a
r
g
,
“
R
e
a
l
-
t
i
m
e
sm
a
r
t
a
t
t
e
n
d
a
n
c
e
s
y
st
e
m
u
si
n
g
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
t
e
c
h
n
i
q
u
e
s
,
”
2
0
1
9
9
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
D
a
t
a
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
(
C
o
n
f
l
u
e
n
c
e
)
,
N
o
i
d
a
,
I
n
d
i
a
,
2
0
1
9
,
p
p
.
5
2
2
-
5
2
5
,
d
o
i
:
1
0
.
1
1
0
9
/
C
O
N
F
LU
E
N
C
E.
2
0
1
9
.
8
7
7
6
9
3
4
.
[
6
]
M
.
S
.
S
.
S
a
r
n
i
n
,
M
.
A
.
I
d
r
i
s,
N
.
F
.
N
a
i
m,
a
n
d
A
.
K
a
d
i
r
,
“
S
mar
t
a
t
t
e
n
d
a
n
c
e
sy
s
t
e
m
u
si
n
g
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
S
p
r
i
n
g
e
r
Pro
c
e
e
d
i
n
g
s
i
n
Ph
y
si
c
s
,
p
p
.
6
9
5
–
7
0
8
,
Ja
n
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
19
-
9
2
6
7
-
4
_
6
8
.
[
7
]
L
.
N
.
T
h
a
l
l
u
r
i
e
t
a
l
.
,
“
A
u
t
o
m
a
t
e
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
m
f
o
r
smar
t
a
t
t
e
n
d
a
n
c
e
a
p
p
l
i
c
a
t
i
o
n
u
s
i
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
R
o
b
o
t
i
c
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
Ja
n
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s4
1
3
1
5
-
0
2
3
-
0
0
3
1
0
-
1.
[
8
]
N
u
r
k
h
a
m
i
d
,
P
.
S
e
t
i
a
l
a
n
a
,
H
.
Ja
t
i
,
R
.
W
a
r
d
a
n
i
,
Y
.
I
n
d
r
i
h
a
p
s
a
r
i
,
a
n
d
N
.
M
.
N
o
r
w
a
w
i
,
“
I
n
t
e
l
l
i
g
e
n
t
a
t
t
e
n
d
a
n
c
e
sy
st
e
m
w
i
t
h
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
t
h
e
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
me
t
h
o
d
,
”
J
o
u
r
n
a
l
o
f
P
h
y
s
i
c
s:
C
o
n
f
e
re
n
c
e
S
e
r
i
e
s
,
v
o
l
.
1
7
3
7
,
n
o
.
1
,
p
.
0
1
2
0
3
1
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
7
3
7
/
1
/
0
1
2
0
3
1
.
[
9
]
A
.
S
.
N
a
d
h
a
n
e
t
a
l
.
,
“
S
mart
a
t
t
e
n
d
a
n
c
e
m
o
n
i
t
o
r
i
n
g
t
e
c
h
n
o
l
o
g
y
f
o
r
i
n
d
u
s
t
r
y
4
.
0
,
”
J
o
u
r
n
a
l
o
f
N
a
n
o
m
a
t
e
ri
a
l
s
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
9
,
Ju
n
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
4
8
9
9
7
6
8
.
[
1
0
]
R
.
U
l
l
a
h
e
t
a
l
.
,
“
A
r
e
a
l
-
t
i
me
f
r
a
mew
o
r
k
f
o
r
h
u
ma
n
f
a
c
e
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
i
n
C
C
TV
i
ma
g
e
s
,
”
Ma
t
h
e
m
a
t
i
c
a
l
Pro
b
l
e
m
s
i
n
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
1
2
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
3
2
7
6
7
0
4
.
[
1
1
]
R
.
W
e
n
g
,
J.
L
u
,
Y
.
-
P
.
T
a
n
,
a
n
d
J
.
Zh
o
u
,
“
L
e
a
r
n
i
n
g
c
a
s
c
a
d
e
d
d
e
e
p
a
u
t
o
-
e
n
c
o
d
e
r
n
e
t
w
o
r
k
s
f
o
r
f
a
c
e
a
l
i
g
n
men
t
,
”
i
n
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
M
u
l
t
i
m
e
d
i
a
,
v
o
l
.
1
8
,
n
o
.
1
0
,
p
p
.
2
0
6
6
-
2
0
7
8
,
O
c
t
.
2
0
1
6
,
d
o
i
:
1
0
.
1
1
0
9
/
T
M
M
.
2
0
1
6
.
2
5
9
1
5
0
8
.
[
1
2
]
R
.
H
e
,
J
.
C
a
o
,
L.
S
o
n
g
,
Z.
S
u
n
a
n
d
T
.
T
a
n
,
“
A
d
v
e
r
sar
i
a
l
c
r
o
ss
-
sp
e
c
t
r
a
l
f
a
c
e
c
o
m
p
l
e
t
i
o
n
f
o
r
N
I
R
-
V
I
S
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
P
a
t
t
e
r
n
A
n
a
l
y
si
s
a
n
d
M
a
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
2
,
n
o
.
5
,
p
p
.
1
0
2
5
-
1
0
3
7
,
1
M
a
y
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
1
9
.
2
9
6
1
9
0
0
.
[
1
3
]
R
.
H
e
,
X
.
W
u
,
Z.
S
u
n
,
a
n
d
T.
T
a
n
,
“
W
a
ssers
t
e
i
n
C
N
N
:
l
e
a
r
n
i
n
g
i
n
v
a
r
i
a
n
t
f
e
a
t
u
r
e
s
f
o
r
N
I
R
-
V
I
S
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
Pa
t
t
e
rn
A
n
a
l
y
s
i
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
1
,
n
o
.
7
,
p
p
.
1
7
6
1
–
1
7
7
3
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
t
p
a
m
i
.
2
0
1
8
.
2
8
4
2
7
7
0
.
[
1
4
]
M
.
L
u
o
,
J
.
C
a
o
,
X
.
M
a
,
X
.
Z
h
a
n
g
,
a
n
d
R
.
H
e
,
“
FA
-
G
A
N
:
f
a
c
e
a
u
g
me
n
t
a
t
i
o
n
G
A
N
f
o
r
d
e
f
o
r
m
a
t
i
o
n
-
i
n
v
a
r
i
a
n
t
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
I
EEE
T
r
a
n
sa
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
Fo
re
n
s
i
c
s
a
n
d
S
e
c
u
ri
t
y
,
v
o
l
.
1
6
,
p
p
.
2
3
4
1
-
2
3
5
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
F
S
.
2
0
2
1
.
3
0
5
3
4
6
0
.
[
1
5
]
Z.
K
h
a
n
,
F
.
S
h
a
f
a
i
t
a
n
d
A
.
M
i
a
n
,
“
J
o
i
n
t
g
r
o
u
p
s
p
a
r
se
P
C
A
f
o
r
c
o
m
p
r
e
ss
e
d
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
i
n
g
,
”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
v
o
l
.
2
4
,
n
o
.
1
2
,
p
p
.
4
9
3
4
-
4
9
4
2
,
D
e
c
.
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
P
.
2
0
1
5
.
2
4
7
2
2
8
0
.
[
1
6
]
B
.
X
u
e
e
t
a
l
.
,
“
A
s
u
b
p
i
x
e
l
t
a
r
g
e
t
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
t
o
h
y
p
e
r
s
p
e
c
t
r
a
l
i
ma
g
e
c
l
a
s
si
f
i
c
a
t
i
o
n
,
”
i
n
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
G
e
o
s
c
i
e
n
c
e
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
5
5
,
n
o
.
9
,
p
p
.
5
0
9
3
-
5
1
1
4
,
S
e
p
t
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
TG
R
S
.
2
0
1
7
.
2
7
0
2
1
9
7
.
[
1
7
]
Q
.
C
h
e
n
,
J
.
S
u
n
,
V
.
P
a
l
a
d
e
,
X
.
S
h
i
,
a
n
d
L.
L
i
u
,
“
H
i
e
r
a
r
c
h
i
c
a
l
c
l
u
st
e
r
i
n
g
-
b
a
s
e
d
b
a
n
d
se
l
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
h
y
p
e
r
sp
e
c
t
r
a
l
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
I
EE
E
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
2
4
3
3
3
-
2
4
3
4
2
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
8
9
7
2
1
3
.
[
1
8
]
S
.
Ji
a
e
t
a
l
.
,
“
A
l
i
g
h
t
w
e
i
g
h
t
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
i
n
I
EEE
T
ra
n
s
a
c
t
i
o
n
s
o
n
G
e
o
sc
i
e
n
c
e
a
n
d
Re
m
o
t
e
S
e
n
si
n
g
,
v
o
l
.
5
9
,
n
o
.
5
,
p
p
.
4
1
5
0
-
4
1
6
3
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
TG
R
S
.
2
0
2
0
.
3
0
1
4
3
1
3
.
[
1
9
]
V
.
R
.
E
.
C
h
r
i
st
o
,
H
.
K
.
N
e
h
e
mi
a
h
,
J
.
B
r
i
g
h
t
y
,
a
n
d
A
.
K
a
n
n
a
n
,
“
F
e
a
t
u
r
e
sel
e
c
t
i
o
n
a
n
d
i
n
s
t
a
n
c
e
se
l
e
c
t
i
o
n
f
r
o
m
c
l
i
n
i
c
a
l
d
a
t
a
se
t
s
u
si
n
g
c
o
-
o
p
e
r
a
t
i
v
e
c
o
-
e
v
o
l
u
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
u
s
i
n
g
r
a
n
d
o
m
f
o
r
e
st
,
”
I
ETE
J
o
u
r
n
a
l
o
f
R
e
se
a
rc
h
,
p
p
.
1
–
1
4
,
Ja
n
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
8
0
/
0
3
7
7
2
0
6
3
.
2
0
2
0
.
1
7
1
3
9
1
7
.
[
2
0
]
F
.
W
u
,
X
.
-
Y
.
J
i
n
g
,
Y
.
F
e
n
g
,
Y
.
Ji
,
a
n
d
R
.
W
a
n
g
,
“
S
p
e
c
t
r
u
m
-
a
w
a
r
e
d
i
scr
i
mi
n
a
t
i
v
e
d
e
e
p
f
e
a
t
u
r
e
l
e
a
r
n
i
n
g
f
o
r
m
u
l
t
i
-
s
p
e
c
t
r
a
l
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
Pa
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
1
1
,
p
.
1
0
7
6
3
2
,
M
a
r
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
0
.
1
0
7
6
3
2
.
[
2
1
]
S
.
M
i
n
o
c
h
a
a
n
d
B
.
S
i
n
g
h
,
“
A
n
o
v
e
l
p
h
i
s
h
i
n
g
d
e
t
e
c
t
i
o
n
sy
st
e
m
u
si
n
g
b
i
n
a
r
y
m
o
d
i
f
i
e
d
e
q
u
i
l
i
b
r
i
u
m
o
p
t
i
mi
z
e
r
f
o
r
f
e
a
t
u
r
e
se
l
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
8
,
p
.
1
0
7
6
8
9
,
M
a
r
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
e
l
e
c
e
n
g
.
2
0
2
2
.
1
0
7
6
8
9
.
[
2
2
]
N
.
K
h
a
r
e
e
t
a
l
.
,
“
S
M
O
-
D
N
N
:
S
p
i
d
e
r
m
o
n
k
e
y
o
p
t
i
mi
z
a
t
i
o
n
a
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
h
y
b
r
i
d
c
l
a
ssi
f
i
e
r
mo
d
e
l
f
o
r
i
n
t
r
u
s
i
o
n
d
e
t
e
c
t
i
o
n
,
”
El
e
c
t
ro
n
i
c
s,
v
o
l
.
9
,
n
o
.
4
,
p
.
6
9
2
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
e
l
e
c
t
r
o
n
i
c
s
9
0
4
0
6
9
2
.
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.
38
,
No
.
3
,
J
u
n
e
20
25
:
2
0
2
0
-
203
0
2028
[
2
3
]
D
.
K
.
J
a
i
n
e
t
a
l
.
,
“
A
n
a
p
p
r
o
a
c
h
f
o
r
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
b
y
o
p
t
i
m
i
z
i
n
g
S
V
M
u
si
n
g
se
l
f
o
r
g
a
n
i
z
i
n
g
map
,
”
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
2
5
,
p
p
.
2
5
2
–
2
5
9
,
M
a
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
o
c
s.2
0
1
7
.
0
7
.
0
1
6
.
[
2
4
]
J.
G
a
o
,
D
.
N
u
y
t
t
e
n
s,
P
.
L
o
o
t
e
n
s,
Y
.
H
e
,
a
n
d
J.
G
.
P
i
e
t
e
r
s
,
“
R
e
c
o
g
n
i
s
i
n
g
w
e
e
d
s
i
n
a
ma
i
z
e
c
r
o
p
u
s
i
n
g
a
r
a
n
d
o
m
f
o
r
e
s
t
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
a
n
d
n
e
a
r
-
i
n
f
r
a
r
e
d
sn
a
p
s
h
o
t
mo
sai
c
h
y
p
e
r
s
p
e
c
t
r
a
l
i
m
a
g
e
r
y
,
”
Bi
o
sys
t
e
m
s
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
7
0
,
p
p
.
3
9
–
5
0
,
J
u
n
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
s
t
e
ms
e
n
g
.
2
0
1
8
.
0
3
.
0
0
6
.
[
2
5
]
P
.
W
a
n
g
,
E.
F
a
n
,
a
n
d
P
.
W
a
n
g
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
i
ma
g
e
c
l
a
ssi
f
i
c
a
t
i
o
n
a
l
g
o
r
i
t
h
m
s
b
a
se
d
o
n
t
r
a
d
i
t
i
o
n
a
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
P
a
t
t
e
rn
Re
c
o
g
n
i
t
i
o
n
L
e
t
t
e
rs
,
v
o
l
.
1
4
1
,
A
u
g
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
r
e
c
.
2
0
2
0
.
0
7
.
0
4
2
.
[
2
6
]
R
.
S
e
n
t
h
i
l
k
u
mar,
V
.
S
r
i
n
i
d
h
i
,
S
.
N
e
e
l
a
v
a
t
h
i
a
n
d
S
.
R
.
D
e
v
i
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
h
y
p
e
r
sp
e
c
t
r
a
l
i
m
a
g
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
,
”
2
0
1
8
T
e
n
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
(
I
C
o
AC
)
,
C
h
e
n
n
a
i
,
I
n
d
i
a
,
2
0
1
8
,
p
p
.
3
7
7
-
3
8
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
o
A
C
4
4
9
0
3
.
2
0
1
8
.
8
9
3
9
1
0
8
.
[
2
7
]
F
.
Ta
h
e
r
k
h
a
n
i
,
J.
D
a
w
s
o
n
,
a
n
d
N
.
M
.
N
a
sr
a
b
a
d
i
,
“
H
y
p
e
r
sp
e
c
t
r
a
l
b
a
n
d
sel
e
c
t
i
o
n
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
b
a
s
e
d
o
n
a
st
r
u
c
t
u
r
a
l
l
y
sp
a
r
si
f
i
e
d
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
2
0
1
9
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
B
i
o
m
e
t
r
i
c
s (I
C
B)
,
C
r
e
t
e
,
G
r
e
e
c
e
,
2
0
1
9
,
p
p
.
1
-
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
B
4
5
2
7
3
.
2
0
1
9
.
8
9
8
7
3
6
0
.
[
2
8
]
X
.
Zh
a
n
g
e
t
a
l
.
,
“
S
S
D
A
N
e
t
:
s
p
e
c
t
r
a
l
-
sp
a
t
i
a
l
t
h
r
e
e
-
d
i
me
n
s
i
o
n
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
f
o
r
h
y
p
e
r
sp
e
c
t
r
a
l
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
I
EEE
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
2
7
1
6
7
-
1
2
7
1
8
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
8
0
2
9
.
[
2
9
]
J.
K
o
l
l
i
,
S
.
C
h
a
l
u
v
a
d
i
,
V
.
M
.
M
a
n
i
k
a
n
d
a
n
a
n
d
Y
.
-
C
.
H
u
,
“
A
n
e
f
f
i
c
i
e
n
t
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
m
f
o
r
p
e
r
s
o
n
a
u
t
h
e
n
t
i
c
a
t
i
o
n
w
i
t
h
b
l
u
r
d
e
t
e
c
t
i
o
n
a
n
d
i
m
a
g
e
e
n
h
a
n
c
e
me
n
t
,
”
2
0
2
2
1
st
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
u
s
t
a
i
n
a
b
l
e
T
e
c
h
n
o
l
o
g
y
f
o
r P
o
w
e
r a
n
d
E
n
e
r
g
y
S
y
s
t
e
m
s
(
S
T
PE
S
)
,
S
R
I
N
A
G
A
R
,
I
n
d
i
a
,
2
0
2
2
,
p
p
.
1
-
6
,
d
o
i
:
1
0
.
1
1
0
9
/
S
TPES
5
4
8
4
5
.
2
0
2
2
.
1
0
0
0
6
6
3
3
.
[
3
0
]
M
.
K
.
G
i
b
r
a
n
,
E.
B
.
N
a
b
a
b
a
n
a
n
d
P
.
S
i
h
o
m
b
i
n
g
,
“
A
n
a
l
y
s
i
s
o
f
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
f
u
z
z
y
c
-
me
a
n
s
c
l
u
s
t
e
r
i
n
g
i
m
a
g
e
se
g
me
n
t
a
t
i
o
n
a
n
d
l
e
a
r
n
i
n
g
v
e
c
t
o
r
q
u
a
n
t
i
z
a
t
i
o
n
,
”
2
0
2
0
3
r
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Me
c
h
a
n
i
c
a
l
,
El
e
c
t
ro
n
i
c
s,
C
o
m
p
u
t
e
r,
a
n
d
I
n
d
u
st
r
i
a
l
T
e
c
h
n
o
l
o
g
y
(
ME
C
n
I
T
)
,
M
e
d
a
n
,
I
n
d
o
n
e
si
a
,
2
0
2
0
,
p
p
.
1
8
8
-
1
9
3
,
d
o
i
:
1
0
.
1
1
0
9
/
M
E
C
n
I
T4
8
2
9
0
.
2
0
2
0
.
9
1
6
6
6
4
9
.
[
3
1
]
K
.
S
a
s
i
r
e
k
h
a
a
n
d
K
.
T
h
a
n
g
a
v
e
l
,
“
O
p
t
i
mi
z
a
t
i
o
n
o
f
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
u
s
i
n
g
p
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
f
o
r
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
1
,
n
o
.
1
1
,
p
p
.
7
9
3
5
–
7
9
4
4
,
J
u
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
1
8
-
3
6
2
4
-
9.
[
3
2
]
S
.
B
.
C
h
a
a
b
a
n
e
,
M
.
H
i
j
j
i
,
R
.
H
a
r
r
a
b
i
,
a
n
d
H
.
S
e
d
d
i
k
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
b
a
se
d
o
n
s
t
a
t
i
s
t
i
c
a
l
f
e
a
t
u
r
e
s
a
n
d
S
V
M
c
l
a
ssi
f
i
e
r
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
1
,
n
o
.
6
,
p
p
.
8
7
6
7
–
8
7
8
4
,
F
e
b
.
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
0
4
2
-
0
2
1
-
1
1
8
1
6
-
w.
[
3
3
]
B
.
T
h
i
l
a
g
a
v
a
t
h
i
,
K
.
S
u
t
h
e
n
d
r
a
n
,
a
n
d
K
.
S
r
u
j
a
n
r
a
j
u
,
“
Ev
a
l
u
a
t
i
n
g
t
h
e
A
d
a
B
o
o
s
t
a
l
g
o
r
i
t
h
m
f
o
r
b
i
o
me
t
r
i
c
-
b
a
se
d
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
,
”
L
e
c
t
u
re
N
o
t
e
s
on
D
a
t
a
En
g
i
n
e
e
ri
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
T
e
c
h
n
o
l
o
g
i
e
s
(
O
n
l
i
n
e
)
,
p
p
.
6
6
9
–
6
7
8
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
16
-
0
0
8
1
-
4
_
6
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
J
y
o
ti
L.
Ba
n
g
a
r
e
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
,
M
K
S
S
S
’
s,
Cu
m
m
i
n
s
Co
l
leg
e
o
f
E
n
g
i
n
e
e
rin
g
f
o
r
Wo
m
e
n
,
S
a
v
i
tri
b
a
i
P
h
u
le
P
u
n
e
U
n
iv
e
rsit
y
,
P
u
n
e
,
I
n
d
ia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
e
d
u
c
a
ti
o
n
a
l
d
a
ta
m
in
i
n
g
,
h
e
a
lt
h
c
a
re
a
n
a
ly
ti
c
s,
ML
,
a
n
d
ima
g
e
p
ro
c
e
ss
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
jy
o
ti
.
b
a
n
g
a
re
@c
u
m
m
in
sc
o
ll
e
g
e
.
i
n
.
Dip
te
e
Chi
k
m
u
r
g
e
M
IT
Ac
a
d
e
m
y
o
f
En
g
i
n
e
e
rin
g
,
Ala
n
d
i,
P
u
n
e
,
In
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
ip
tee
.
c
h
ik
m
u
rg
e
@m
it
a
o
e
.
a
c
.
in
.
Dr
.
K
a
r
th
ik
e
y
a
n
K
a
li
y
a
p
e
r
u
m
a
l
is
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
IT@Io
T
-
HH
Ca
m
p
u
s
in
Am
b
o
U
n
iv
e
rsit
y
a
t
A
m
b
o
,
Et
h
io
p
ia.
He
is h
a
v
i
n
g
2
0
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rie
n
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
rt
h
ik
e
y
a
n
@a
m
b
o
u
.
e
d
u
.
e
t.
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
Desig
n
o
f fa
ce
r
ec
o
g
n
itio
n
b
a
s
ed
effec
tive
a
u
to
ma
ted
s
ma
r
t a
tten
d
a
n
ce
s
ystem
(
Jy
o
ti L.
B
a
n
g
a
r
e
)
2029
Dr
.
Mee
n
a
k
shi
is
a
n
e
x
p
e
rt
in
M
e
d
ia
a
n
d
I
n
tern
a
ti
o
n
a
l
Re
lati
o
n
s,
In
terc
u
lt
u
ra
l
Co
m
m
u
n
ica
ti
o
n
,
Ev
e
n
t
M
a
n
a
g
e
m
e
n
t,
Ra
d
i
o
a
n
d
TV
J
o
u
r
n
a
li
s
m
a
n
d
h
a
s
a
b
a
c
k
g
ro
u
n
d
i
n
Co
n
ti
n
e
n
tal
P
h
il
o
so
p
h
y
.
S
h
e
h
a
s
tau
g
h
t
th
e
se
su
b
jec
ts
fo
r
n
e
a
rly
1
1
y
e
a
rs
a
t
u
n
i
v
e
rsiti
e
s
su
c
h
a
s
th
e
Ku
ru
k
sh
e
tra
Un
iv
e
rsity
(
Ha
ry
a
n
a
,
In
d
ia),
LL
DIMS
,
G
G
S
IP
Un
iv
e
rsit
y
(De
lh
i,
I
n
d
ia),
Lo
v
e
l
y
P
ro
fe
ss
io
n
a
l
Un
iv
e
rsit
y
(P
u
n
ja
b
,
In
d
ia),
G
D
G
o
e
n
k
a
Un
iv
e
rsity
(In
d
ia)
a
n
d
a
t
Ap
e
e
jay
Un
iv
e
rsity
,
In
d
ia.
S
h
e
c
a
n
b
e
c
o
n
t
a
c
ted
a
t
e
m
a
il
:
m
t6
4
5
8
@g
m
a
il
.
c
o
m
.
Dr
.
S
u
n
il
L.
Ba
n
g
a
r
e
wo
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
t
h
e
De
p
a
rtme
n
t
o
f
In
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
t
S
in
h
g
a
d
Ac
a
d
e
m
y
o
f
En
g
i
n
e
e
rin
g
,
P
u
n
e
,
In
d
ia.
He
g
ra
d
u
a
ted
in
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
in
El
e
c
tro
n
ics
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
a
t
Am
ra
v
a
ti
Un
iv
e
rsity
(S
G
BAU
),
Am
ra
v
a
ti
,
M
a
h
a
ra
sh
t
ra
,
In
d
ia.
He
se
c
u
re
d
M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
in
In
f
o
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
Bh
a
ra
ti
Vid
y
a
p
e
e
th
De
e
m
e
d
Un
iv
e
rsity
,
P
u
n
e
,
I
n
d
ia.
He
c
o
m
p
lete
d
P
h
.
D.
in
th
e
fiel
d
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
a
t
Ko
n
e
ru
Lak
s
h
m
a
iah
Ed
u
c
a
ti
o
n
F
o
u
n
d
a
ti
o
n
(K.
L.
U
n
iv
e
rsit
y
),
Va
d
d
e
sw
a
ra
m
,
In
d
ia.
He
c
o
m
p
lete
d
h
is
P
G
D
C
-
DA
C.
He
is
a
F
e
ll
o
w
(F
IE
)
-
Th
e
I
n
stit
u
ti
o
n
o
f
En
g
i
n
e
e
rs
(In
d
ia).
He
is
i
n
tea
c
h
i
n
g
p
ro
fe
ss
io
n
f
o
r
m
o
re
t
h
a
n
1
6
y
e
a
rs
a
n
d
h
a
v
e
1
.
6
y
e
a
rs
o
f
in
d
u
strial
e
x
p
e
rien
c
e
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
su
n
il
.
b
a
n
g
a
re
@g
m
a
il
.
c
o
m
.
Dr
.
K
ish
o
r
i
K
a
sa
t
is
wo
r
k
in
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
Co
m
p
u
ter
S
t
u
d
ie
s
De
p
a
rtme
n
t,
S
y
m
b
io
sis
S
c
h
o
o
l
fo
r
Li
b
e
ra
l
Artsin
S
y
m
b
i
o
si
s
In
tern
a
ti
o
n
a
l
(De
e
m
e
d
Un
iv
e
rsity
,
P
u
n
e
,
I
n
d
ia.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
ish
o
ri.
k
a
sa
t@ss
la.ed
u
.
in
.
Dr
.
K
a
n
til
a
l
Pi
t
a
m
b
a
r
R
a
n
e
re
c
e
iv
e
d
B
.
E
.
d
e
g
re
e
i
n
E
lec
tro
n
ics
a
n
d
Tele
c
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
fro
m
No
rth
M
a
h
a
ra
sh
tra
Un
iv
e
rs
it
y
,
Ja
lg
a
o
n
i
n
1
9
9
6
.
M
.
E
.
De
g
re
e
in
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
fro
m
S
h
i
v
a
ji
U
n
iv
e
rsit
y
,
K
o
lh
a
p
u
r
in
2
0
0
5
.
P
h
.
D
.
d
e
g
re
e
i
n
El
e
c
tro
n
ics
E
n
g
i
n
e
e
rin
g
fr
o
m
No
rth
M
a
h
a
ra
sh
tra
Un
i
v
e
rsity
,
Ja
lg
a
o
n
in
2
0
1
3
.
He
is
c
u
rre
n
tl
y
wo
rk
i
n
g
a
s
P
ro
fe
ss
o
r
a
t
Bh
a
ra
ti
Vid
y
a
p
e
e
th
Co
l
leg
e
o
f
En
g
in
e
e
rin
g
Na
v
i
M
u
m
b
a
i,
In
d
ia.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
i
m
a
g
e
p
ro
c
e
ss
in
g
,
I
o
T,
AI
,
a
n
d
ML
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
n
ti
p
ra
n
e
@re
d
iffma
il
.
c
o
m
.
Ra
v
i
K
ish
o
r
e
Ve
lu
r
i
is
wo
rk
i
n
g
a
s
a
ss
o
c
iate
p
ro
fe
ss
o
r
in
CS
E,
Ad
it
y
a
Un
iv
e
rsity
,
S
u
ra
m
p
a
lem
An
d
h
ra
P
ra
d
e
sh
,
I
n
d
ia.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
v
ik
ish
o
re
v
1
9
8
5
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.