I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
201
6
,
p
p
.
266
5
~
2
6
7
3
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
0
9
0
9
2665
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Sig
na
ture
Ve
rific
a
tion usin
g
Nor
ma
liz
ed
St
a
ti
c F
ea
t
ures a
nd
Neura
l Ne
tw
o
rk
Clas
sifica
tion
M
a
nis
h T
ri
kh
a
,
M
a
na
s
Sin
g
ha
l
,
M
a
it
re
y
ee
Dut
t
a
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
Na
ti
o
n
a
l
In
stit
u
te
o
f
T
e
c
h
n
ica
l
T
e
a
c
h
e
r
T
ra
in
in
g
a
n
d
Re
se
a
rc
h
,
Ch
a
n
d
ig
a
rh
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
9
,
2
0
1
6
R
ev
i
s
ed
A
u
g
31
,
2
0
1
6
A
cc
ep
ted
Sep
1
3
,
2
0
1
6
S
ig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
is
v
e
r
y
w
i
d
e
ly
u
se
d
in
v
e
ri
f
ica
ti
o
n
o
f
th
e
i
d
e
n
ti
ty
o
f
a
n
y
p
e
rso
n
.
No
w
a
d
a
y
s
o
th
e
r
b
io
m
e
tri
c
v
e
ri
f
ica
ti
o
n
s
y
ste
m
h
a
s b
e
e
n
e
v
o
lv
e
d
v
e
r
y
w
id
e
l
y
li
k
e
f
i
g
u
re
p
rin
t,
ir
is
e
tc.,
b
u
t
sig
n
a
tu
re
v
e
rif
ica
ti
o
n
th
ro
u
g
h
c
o
m
p
u
ter
s
y
ste
m
is
stil
l
in
d
e
v
e
lo
p
m
e
n
t
p
h
a
se
.
T
h
e
v
e
ri
f
ica
ti
o
n
s
y
ste
m
is
e
it
h
e
r
th
ro
u
g
h
o
f
f
li
n
e
m
o
d
e
o
r
o
n
li
n
e
m
o
d
e
in
o
n
li
n
e
sy
ste
m
s
th
e
d
y
n
a
m
ic
in
f
o
rm
a
ti
o
n
o
f
a
si
g
n
a
tu
re
c
a
p
tu
re
d
a
t
th
e
ti
m
e
th
e
sig
n
a
tu
re
is
m
a
d
e
w
h
il
e
in
o
f
f
li
n
e
s
y
ste
m
s
b
a
se
d
o
n
th
e
sc
a
n
n
e
d
im
a
g
e
o
f
a
sig
n
a
tu
re
.
In
th
i
s
p
a
p
e
r,
a
m
e
th
o
d
is
p
re
se
n
te
d
f
o
r
Of
f
li
n
e
sig
n
a
tu
re
s
V
e
rif
ica
ti
o
n
,
f
o
r
th
is
v
e
ri
f
ica
ti
o
n
s
y
ste
m
si
g
n
a
tu
re
im
a
g
e
is
f
i
rst
p
re
-
p
r
o
c
e
ss
e
d
a
n
d
c
o
n
v
e
rted
i
n
to
b
i
n
a
ry
im
a
g
e
o
f
sa
m
e
siz
e
w
it
h
2
0
0
x
2
0
0
P
ix
e
ls
a
n
d
th
e
n
d
if
fe
re
n
t
fe
a
tu
re
s
a
re
e
x
trac
ted
f
ro
m
th
e
i
m
a
g
e
li
k
e
Ec
c
e
n
tri
c
it
y
,
Ku
rto
sis,
S
k
e
w
n
e
ss
e
t
c
.
a
n
d
t
h
a
t
f
e
a
tu
re
s
a
re
u
se
d
to
train
th
e
n
e
u
ra
l
n
e
tw
o
rk
u
sin
g
b
a
c
k
-
p
ro
p
a
g
a
ti
o
n
tec
h
n
iq
u
e
.
F
o
r
t
h
is
v
e
rif
ica
ti
o
n
sy
ste
m
6
d
if
f
e
r
e
n
t
u
se
r
sig
n
a
tu
re
s
a
re
tak
e
n
to
m
a
k
e
d
a
tab
a
se
o
f
th
e
f
e
a
tu
re
a
n
d
re
su
lt
s
a
re
a
n
a
l
y
s
e
d
.
T
h
e
re
su
lt
d
e
m
o
n
stra
te
th
e
e
ff
icie
n
c
y
o
f
th
e
p
ro
p
o
se
d
m
e
th
o
d
o
lo
g
y
w
h
e
n
c
o
m
p
a
re
d
w
it
h
o
th
e
r
e
x
isti
n
g
stu
d
ies
.
T
h
e
p
r
o
p
o
se
d
a
l
g
o
rit
h
m
g
i
v
e
s
F
a
lse
A
c
c
e
p
tan
c
e
Ra
te
(F
A
R)
a
s 5
.
0
5
%
a
n
d
F
a
lse
Re
jec
ti
o
n
ra
te
(F
RR)
a
s 4
.
2
5
%
.
K
ey
w
o
r
d
:
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
al
n
et
w
o
r
k
No
r
m
a
lized
s
tatic
f
ea
tu
r
e
s
Of
f
li
n
e
s
i
g
n
a
tu
r
e
v
er
i
f
icat
io
n
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Ma
n
is
h
T
r
ik
h
a,
Dep
ar
t
m
en
t o
f
E
lectr
o
n
ics a
n
d
C
o
m
m
u
n
icat
io
n
E
n
g
i
n
ee
r
in
g
,
Natio
n
al
I
n
s
tit
u
te
o
f
T
ec
h
n
ica
l
T
ea
ch
er
T
r
ain
in
g
an
d
R
esear
c
h
,
C
h
a
n
d
ig
ar
h
,
I
n
d
ia
.
E
m
ail:
m
a
n
is
h
.
tr
ik
h
a
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
U
CT
I
O
N
T
o
d
ay
t
h
er
e
ar
e
v
ar
io
u
s
b
io
m
etr
ic
s
y
s
te
m
s
i
m
p
le
m
en
t
in
g
f
o
r
id
en
ti
f
icatio
n
a
n
d
v
er
i
f
icatio
n
o
f
h
u
m
a
n
b
ein
g
lik
e
f
i
g
u
r
e
p
r
in
t,
ir
is
,
v
o
ca
l
etc.
,
[1
-
2
]
,
b
u
t
h
an
d
w
r
itte
n
s
i
g
n
a
tu
r
es
ar
e
co
n
s
id
er
ed
a
m
o
s
t
i
m
p
o
r
tan
t
b
io
m
etr
ic
f
o
r
id
en
tif
icatio
n
o
f
g
e
n
u
in
e
p
er
s
o
n
,
also
h
an
d
w
r
itte
n
s
i
g
n
atu
r
e
s
u
s
ed
v
er
y
w
id
el
y
i
n
f
i
n
an
cia
l
in
s
tit
u
tio
n
s
li
k
e
b
an
k
in
g
s
y
s
te
m
s
.
B
u
t
th
e
s
e
s
y
s
te
m
ar
e
s
til
l
lag
g
i
n
g
b
eh
i
n
d
as
d
ep
en
d
b
asicall
y
o
n
h
u
m
a
n
v
er
if
icatio
n
i.e
.
,
o
n
l
y
b
y
lo
o
k
i
n
g
at
t
h
e
s
ig
n
at
u
r
e,
t
h
er
e
is
s
til
l
n
o
s
y
s
te
m
a
v
aila
b
le
w
h
ic
h
p
r
o
v
id
e
1
0
0
%
v
er
if
icatio
n
u
s
in
g
d
ig
it
al
co
m
p
u
ter
.
Var
io
u
s
r
e
s
ea
r
ch
ca
r
r
ied
o
u
t
in
th
e
f
ield
o
f
s
ig
n
atu
r
e
o
v
er
th
e
la
s
t
t
w
o
d
ec
ad
es
an
d
a
s
ev
er
al
v
e
r
if
icatio
n
a
n
d
r
ec
o
g
n
itio
n
m
o
d
els
h
a
v
e
ap
p
ea
r
ed
.
T
h
e
m
ai
n
ai
m
o
f
s
ig
n
at
u
r
e
r
ec
o
g
n
itio
n
is
to
d
etec
t
f
o
r
g
er
y
an
d
al
s
o
at
t
h
e
s
a
m
e
ti
m
e
r
e
d
u
ce
r
ej
ec
tio
n
o
f
g
e
n
u
in
e
s
i
g
n
atu
r
e
[
3
]
.
T
h
er
e
ar
e
t
w
o
d
if
f
er
e
n
t c
ateg
o
r
ies i
n
h
an
d
w
r
itte
n
s
i
g
n
a
tu
r
es
v
er
i
f
icatio
n
[
4
-
5]
O
f
f
lin
e
s
ig
na
t
ures v
er
if
ica
t
io
n
a
nd
O
nli
ne
s
ig
na
t
ures v
er
if
ica
t
io
n
I
n
O
f
f
l
in
e
s
i
g
n
a
tu
r
e
v
er
if
icati
o
n
s
y
s
te
m
a
n
i
m
a
g
e
o
f
a
s
i
g
n
atu
r
e
is
ca
p
tu
r
ed
b
y
a
d
i
g
ital
ca
m
er
a
o
r
o
b
tain
ed
b
y
s
ca
n
n
i
n
g
a
s
i
g
n
at
u
r
e,
w
h
ic
h
is
o
n
a
p
ap
er
o
r
a
d
o
cu
m
e
n
t
an
d
t
h
en
d
i
f
f
er
en
t
f
e
atu
r
es
ar
e
ex
tr
ac
ted
lik
e
E
cc
en
tr
ici
t
y
,
K
u
r
to
s
is
S
k
e
w
n
es
s
etc.
,
w
h
ile
in
ca
s
e
o
f
o
n
lin
e
s
i
g
n
atu
r
es
v
er
if
icatio
n
u
s
ed
th
e
d
y
n
a
m
i
c
f
ea
t
u
r
es o
f
t
h
e
i
m
a
g
e
w
h
ic
h
is
tak
en
at
t
h
e
ti
m
e
o
f
s
ig
n
at
u
r
e
i
s
m
ad
e
li
k
e
p
r
ess
u
r
e,
co
o
r
d
in
ates e
tc.
[
6
-
7]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
ig
n
a
tu
r
e
V
erif
ica
tio
n
u
s
in
g
N
o
r
ma
liz
ed
S
ta
tic
F
ea
tu
r
es a
n
d
N
eu
r
a
l Netw
o
r
k
C
la
s
s
ifica
tio
n
(
Ma
n
is
h
Tr
ikh
a
)
2666
1
.
T
y
p
e
o
f
f
o
r
g
er
y
Fo
r
g
er
y
i
s
to
co
p
y
an
y
o
n
e
els
e
s
ig
n
at
u
r
e
f
o
r
a
n
y
f
i
n
a
n
cial
o
r
o
th
er
t
y
p
e
o
f
b
e
n
ef
it.
T
h
e
f
o
r
g
e
r
elate
d
to
s
ig
n
atu
r
e
ca
n
b
e
class
i
f
ie
d
in
to
th
r
ee
ca
teg
o
r
ies
s
u
c
h
as
R
a
n
d
o
m
f
o
r
g
er
y
,
Si
m
p
le
f
o
r
g
er
y
a
n
d
s
k
illed
f
o
r
g
er
y
[
8
]
.
a.
R
an
d
o
m
f
o
r
g
er
y
:
I
t
is
a
n
u
n
s
k
illed
atte
m
p
t
to
co
p
y
s
ig
n
at
u
r
e
f
r
o
m
n
a
m
e
an
d
p
er
s
o
n
d
o
n
‟
t
h
av
e
e
x
ac
t
k
n
o
w
led
g
e
o
f
t
h
e
o
r
ig
in
a
l si
g
n
at
u
r
e.
T
h
is
t
y
p
e
o
f
f
o
r
g
er
y
is
v
er
y
ea
s
y
to
d
etec
t th
r
o
u
g
h
n
a
k
ed
ey
e
s
.
b.
Sk
illed
f
o
r
g
er
y
:
I
t
is
m
o
s
t
d
if
f
icu
lt
to
m
a
k
e
an
d
ev
e
n
d
etec
t.
I
n
th
is
t
y
p
e
a
s
k
illed
p
er
s
o
n
tr
y
to
m
a
k
e
t
h
e
s
a
m
e
s
ig
n
at
u
r
e
as th
e
o
r
i
g
in
a
l o
n
e.
T
h
is
s
ig
n
at
u
r
e
v
er
i
f
icatio
n
ca
n
n
o
t b
e
d
o
n
e
as c
h
ar
ac
ter
r
ec
o
g
n
itio
n
a
s
s
i
g
n
a
tu
r
e
co
llect
as d
ig
ital i
m
a
g
e.
T
h
e
m
ai
n
p
r
o
ce
d
u
r
e
in
v
er
i
f
i
ca
tio
n
o
f
o
f
f
li
n
e
s
i
g
n
at
u
r
e
i
s
f
ir
s
t
p
r
e
-
p
r
o
ce
s
s
i
n
g
th
e
s
i
g
n
at
u
r
e
i
m
ag
e
s
u
c
h
th
at
n
o
is
e
r
e
m
o
v
a
l,
n
o
r
m
aliza
tio
n
o
f
th
e
s
i
g
n
at
u
r
e
im
ag
e
a
n
d
co
n
v
er
ti
n
g
s
ig
n
at
u
r
e
i
m
ag
e
i
n
to
b
in
ar
y
f
o
r
m
a
n
d
t
h
e
n
f
i
n
d
in
g
t
h
e
d
i
f
f
er
en
t
s
tat
ic
f
ea
t
u
r
es
o
f
t
h
e
s
i
g
n
at
u
r
e
i
m
a
g
e
lik
e
m
o
m
e
n
t,
s
k
e
w
n
ess
etc.
,
t
h
en
d
ep
en
d
in
g
u
p
o
n
th
e
t
h
ese
f
ea
t
u
r
es
f
o
r
g
e
s
ig
n
at
u
r
es
ca
n
ea
s
il
y
b
e
r
ec
o
g
n
ized
b
y
u
s
in
g
o
n
e
o
f
th
e
clas
s
i
f
icatio
n
m
et
h
o
d
s
lik
e
Su
p
p
o
r
t
v
e
cto
r
m
ac
h
in
e
(
SV
M)
[
9
]
,
Hid
d
en
Ma
r
k
o
v
Mo
d
el
(
HM
M)
an
d
f
ee
d
-
f
o
r
w
ar
d
b
ac
k
-
p
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
.
[
1
0
]
2
.
L
iter
atu
r
e
S
u
r
v
e
y
T
h
e
p
r
esen
t
r
esear
ch
is
r
elate
d
to
a
n
u
m
b
er
o
f
d
if
f
er
en
t
ar
ea
s
w
it
h
i
n
s
i
g
n
a
tu
r
e
v
er
i
f
icati
o
n
u
n
d
er
o
f
f
li
n
e
ap
p
r
o
ac
h
,
C
e
m
il
O
Z
in
[
1
1
]
,
r
ep
o
r
ted
an
o
f
f
-
li
n
e
s
i
g
n
at
u
r
e
r
ec
o
g
n
it
io
n
an
d
v
er
i
f
i
ca
tio
n
s
y
s
te
m
w
h
ic
h
is
b
ased
o
n
m
o
m
e
n
t
in
v
ar
ia
n
t
m
et
h
o
d
u
s
i
n
g
A
r
ti
f
icial
Ne
u
r
al
Net
w
o
r
k
.
T
w
o
s
ep
ar
ate
n
eu
r
al
n
et
w
o
r
k
s
ar
e
d
esig
n
ed
,
o
n
e
f
o
r
s
ig
n
at
u
r
e
r
ec
o
g
n
itio
n
,
an
d
a
n
o
th
er
f
o
r
v
er
if
icatio
n
(
i.e
.
f
o
r
d
etec
tin
g
f
o
r
g
er
y
)
,
S
n
e
h
il
G
.
j
aiw
a
l
i
n
[
1
2
]
,
th
en
d
i
v
id
e
t
h
e
i
m
a
g
e
i
n
to
n
u
m
b
er
o
f
s
u
b
i
m
ag
e
s
a
n
d
ex
tr
ac
t
th
e
f
ea
t
u
r
e
s
o
f
ea
c
h
s
u
b
i
m
a
g
e
an
d
ca
ll
it
a
s
lo
ca
l
f
ea
t
u
r
es,
t
h
en
NN
is
u
s
ed
as
clas
s
i
f
icati
o
n
is
u
s
ed
,
s
y
s
te
m
p
r
o
d
u
ce
s
F
AR
5
.
8
%
a
n
d
F
R
R
5
.
0
%.
K
.
V
L
a
k
s
h
m
i
i
n
[
8
]
,
s
t
atic
f
ea
t
u
r
es
f
r
o
m
t
h
e
i
m
ag
e
l
ik
e
T
o
k
en
le
n
g
t
h
,
A
v
er
a
g
e
v
a
lu
e
o
f
o
b
s
er
v
atio
n
,
Stan
d
ar
d
d
ev
iatio
n
,
T
r
en
d
co
ef
f
icien
ts
(
s
lo
p
e
o
f
tr
en
d
lin
e
)
ar
e
u
s
ed
as
f
ea
tu
r
es.
Mi
g
u
e
l
A
.
Fer
r
er
in
[
1
4
]
,
u
s
i
n
g
r
o
tatio
n
in
v
ar
ia
n
t
u
n
i
f
o
r
m
lo
ca
l
b
in
ar
y
p
a
tter
n
(
L
B
P
)
an
d
g
r
a
y
le
v
el
co
-
o
cc
u
r
r
en
ce
m
atr
ices
(
G
L
M
C
)
w
it
h
M
C
YT
o
f
f
li
n
e
s
ig
n
at
u
r
e
d
atab
ase.
Sh
as
h
i
k
u
m
ar
D.
R
in
[
1
5
]
,
f
o
r
th
is
a
u
t
h
o
r
co
m
b
in
e
th
e
g
lo
b
al
an
d
g
r
id
f
ea
tu
r
e
s
o
f
th
e
s
i
g
n
atu
r
e
i
m
ag
e
a
f
ter
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
th
e
i
m
a
g
e,
th
e
n
n
e
u
r
al
n
e
t
w
o
r
k
i
s
u
s
ed
as
a
class
i
f
ier
s
y
s
te
m
,
Stép
h
a
n
e
A
r
m
an
d
in
[
1
6
]
,
f
ea
t
u
r
es
lik
e
C
e
n
tr
o
id
,
T
r
i
-
Su
r
f
ac
e,
L
e
n
g
th
,
Si
x
-
f
o
ld
-
Su
r
f
ac
e
a
n
d
B
est
-
f
it
Feat
u
r
e,
I
n
d
r
aj
it
B
h
attac
h
ar
y
aa
i
n
[
1
7
]
,
au
th
o
r
ap
p
ly
p
ix
e
l
m
a
tch
i
n
g
tec
h
n
iq
u
e
(
P
MT
)
f
o
r
class
i
f
icatio
n
o
f
f
o
r
g
e
an
d
g
e
n
u
i
n
e
s
i
g
n
at
u
r
e,
Srik
a
n
ta
P
al
in
[
1
8
]
,
th
e
f
ea
tu
r
es
e
x
tr
ac
te
d
ar
e
g
r
ad
ien
t
an
d
Z
er
n
i
k
e
m
o
m
e
n
t a
n
d
th
e
n
SV
M
u
s
i
n
g
R
B
F k
er
n
el
is
u
s
ed
as
class
i
f
ier
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
g
e
n
er
al,
th
er
e
ar
e
f
i
v
e
m
aj
o
r
s
tag
es i
n
an
y
s
ig
n
at
u
r
e
v
er
i
f
i
ca
tio
n
p
r
o
b
lem
:
a.
T
ak
in
g
s
ig
n
at
u
r
e
i
m
a
g
e
f
r
o
m
d
ig
ital
ca
m
er
a:
T
h
e
s
i
g
n
a
tu
r
e
is
ta
k
en
f
r
o
m
d
i
g
ital
ca
m
er
a
a
n
d
s
e
n
d
to
th
e
co
m
p
u
ter
.
A
s
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Fig
u
r
e
1
.
Sa
m
p
le
Si
g
n
a
tu
r
e
o
f
R
an
d
o
m
U
s
er
b.
P
r
e
-
p
r
o
ce
s
s
in
g
o
f
s
i
g
n
at
u
r
e
im
ag
e
:
Af
ter
i
m
ag
e
i
s
s
ca
n
n
ed
an
d
tr
an
s
f
er
to
co
m
p
u
ter
it
i
s
p
r
e
-
p
r
o
ce
s
s
ed
f
o
r
r
e
m
o
v
al
o
f
n
o
is
e
a
n
d
co
n
v
er
t th
e
i
m
a
g
e
i
n
to
g
r
e
y
s
ca
le
F
ig
u
r
e
2.
Fig
u
r
e
2
.
P
r
e
-
p
r
o
ce
s
s
ed
I
m
ag
e
o
f
R
an
d
o
m
Us
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
: 2
6
6
5
–
2
6
7
3
2667
c.
C
o
v
er
t
to
b
in
ar
y
i
m
ag
e
:
I
m
a
g
e
is
t
h
en
co
n
v
er
ted
i
n
to
b
in
ar
y
i
m
ag
e
a
n
d
also
i
n
v
er
t
th
e
i
m
ag
e
f
o
r
m
o
r
e
en
h
a
n
ce
d
f
ea
t
u
r
e
ex
tr
ac
t
io
n
.
As s
h
o
w
n
i
n
Fi
g
u
r
e
3
Fig
u
r
e
3
.
B
in
ar
y
I
m
a
g
e
o
f
R
a
n
d
o
m
U
s
e
r
d.
Featu
r
e
e
x
tr
ac
tio
n
:
Featu
r
e
s
ex
tr
ac
tio
n
i
s
a
v
er
y
i
m
p
o
r
tan
t
r
o
le
to
p
lay
i
n
s
ig
n
at
u
r
e
r
ec
o
g
n
itio
n
a
n
d
v
er
if
ica
tio
n
s
y
s
te
m
,
f
ea
t
u
r
es
m
u
s
t
p
r
o
v
id
e
s
i
g
n
if
ican
t
d
if
f
e
r
en
ce
to
t
h
e
c
lass
if
ier
b
et
w
ee
n
g
en
u
i
n
e
a
n
d
f
o
r
g
e
s
i
g
n
at
u
r
e
a
n
d
at
t
h
e
s
a
m
e
t
i
m
e
s
h
o
u
ld
b
e
co
n
s
is
te
n
t
b
et
w
ee
n
d
i
f
f
er
e
n
t
s
i
g
n
a
tu
r
es
p
r
o
v
id
ed
b
y
th
e
s
a
m
e
s
ig
n
o
r
.
e.
No
r
m
a
lizatio
n
o
f
f
ea
t
u
r
es:
Af
ter
s
elec
ti
n
g
th
e
ap
p
r
o
p
r
iate
f
ea
tu
r
es
f
r
o
m
t
h
e
s
i
g
n
at
u
r
e,
n
o
r
m
al
izatio
n
i
s
r
eq
u
ir
ed
as
ce
r
tai
n
f
ea
t
u
r
es
m
ag
n
i
tu
d
e
ar
e
v
er
y
h
i
g
h
g
r
ea
ter
th
a
n
1
0
0
b
u
t
at
th
e
s
a
m
e
t
i
m
e
s
o
m
e
f
ea
tu
r
e
s
h
av
e
v
er
y
s
m
al
l
m
ag
n
it
u
d
e
s
o
,
if
t
h
e
c
lass
if
ica
tio
n
p
r
o
ce
s
s
d
o
n
e
w
ith
o
u
t
n
o
r
m
aliza
tio
n
o
f
f
ea
t
u
r
es
t
h
e
n
ce
r
tain
f
ea
t
u
r
es
w
h
o
s
e
m
ag
n
it
u
d
e
is
lar
g
e
ar
e
b
ec
o
m
e
d
o
m
i
n
an
t
.
f.
C
las
s
i
f
icatio
n
:
Af
ter
f
ea
t
u
r
es
ex
tr
ac
tio
n
an
d
n
o
r
m
al
izatio
n
ce
r
tain
t
y
p
e
o
f
clas
s
i
f
icati
o
n
p
r
o
ce
s
s
is
r
eq
u
ir
ed
in
m
a
n
y
r
esear
ch
e
s
d
if
f
er
e
n
t
t
y
p
e
s
o
f
cla
s
s
i
f
icat
i
o
n
s
y
s
te
m
ar
e
d
esig
n
ed
li
k
e
SVM
(
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
e)
,
HM
M
(
Hid
d
en
m
ar
k
o
v
m
o
d
el)
,
VQ
(
Vec
t
o
r
Qu
an
tizatio
n
)
,
B
ac
k
p
r
o
p
ag
atio
n
Neu
r
a
l
Net
w
o
r
k
.
Fig
u
r
e
4
.
Flo
w
Ch
ar
t
f
o
r
th
e
S
y
s
te
m
I
n
th
is
p
ap
er
,
th
e
o
f
f
l
in
e
s
i
g
n
atu
r
e
v
er
i
f
icatio
n
is
p
r
o
p
o
s
ed
,
b
lo
ck
d
iag
r
a
m
o
f
t
h
e
w
h
o
le
s
y
s
te
m
s
h
o
w
n
i
n
Fi
g
u
r
e
4
,
s
y
s
te
m
u
s
e
s
n
eu
r
al
n
et
w
o
r
k
f
o
r
v
er
if
icatio
n
an
d
u
s
i
n
g
g
en
er
a
l
b
ac
k
p
r
o
p
ag
atio
n
o
p
tim
izatio
n
m
et
h
o
d
f
o
r
tr
ain
i
n
g
t
h
e
n
eu
r
al
n
et
w
o
r
k
.
Fo
r
th
e
f
ir
s
t t
h
e
s
i
g
n
atu
r
e
f
r
o
m
6
d
if
f
er
en
t u
s
es a
r
e
tak
e
n
o
n
b
lan
k
p
ap
er
an
d
co
n
v
er
t
t
h
at
s
ig
n
at
u
r
e
to
d
ig
ita
l
i
m
ag
e
o
f
.
j
p
g
f
o
r
m
at
a
n
d
t
h
en
ap
p
l
y
in
g
p
r
e
-
p
r
o
ce
s
s
i
n
g
o
f
t
h
e
i
m
a
g
e
f
o
r
r
e
m
o
v
i
n
g
t
h
e
n
o
is
e
f
r
o
m
th
e
i
m
ag
e
a
n
d
t
h
en
c
o
n
v
er
t
th
i
s
n
o
is
e
f
r
ee
i
m
ag
e
i
n
to
f
i
x
ed
s
ize
b
i
n
ar
y
i
m
a
g
e
o
f
2
0
0
x
2
0
0
p
ix
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
ig
n
a
tu
r
e
V
erif
ica
tio
n
u
s
in
g
N
o
r
ma
liz
ed
S
ta
tic
F
ea
tu
r
es a
n
d
N
eu
r
a
l Netw
o
r
k
C
la
s
s
ifica
tio
n
(
Ma
n
is
h
Tr
ikh
a
)
2668
Af
ter
co
n
v
er
ti
n
g
t
h
e
i
m
a
g
e
i
n
to
b
in
ar
y
i
m
ag
e
a
n
d
t
h
en
i
n
v
er
t
th
e
i
m
ag
e
f
o
r
m
o
r
e
d
etail
r
esu
lt
t
h
e
n
d
if
f
er
e
n
t f
ea
tu
r
es o
f
th
a
t i
m
a
g
e
ar
e
ex
tr
ac
ted
f
r
o
m
th
at
i
m
a
g
e
th
ese
f
ea
tu
r
e
s
ar
e
as f
o
llo
w
s
:
a.
Sk
e
w
n
es
s
: S
k
e
w
n
ess
i
s
a
m
ea
s
u
r
e
o
f
s
y
m
m
etr
y
.
A
d
is
tr
ib
u
ti
o
n
,
o
r
d
ata
s
et,
is
s
y
m
m
etr
ic
i
f
it lo
o
k
s
s
a
m
e
to
th
e
lef
t a
n
d
r
ig
h
t o
f
t
h
e
ce
n
t
r
e
p
o
in
t.
Fo
r
d
ata
Y1
,
Y2
,
.
.
.
,
YN,
th
e
f
o
r
m
u
la
f
o
r
s
k
e
w
n
e
s
s
is
:
∑
̅
⁄
(
1
)
w
h
er
e
̅
th
e
m
ea
n
,
s
is
is
th
e
s
t
an
d
ar
d
d
ev
iatio
n
,
an
d
N
is
th
e
n
u
m
b
er
o
f
d
ata
p
o
in
ts
.
T
h
is
f
o
r
m
u
la
f
o
r
s
k
e
w
n
es
s
is
ca
l
led
Fis
h
er
-
P
e
ar
s
o
n
co
ef
f
icie
n
t
o
f
s
k
e
w
n
es
s
.
T
h
e
s
k
e
w
n
e
s
s
f
o
r
a
n
o
r
m
al
d
is
tr
ib
u
tio
n
i
s
ze
r
o
,
an
d
an
y
s
y
m
m
etr
ic
d
ata
s
h
o
u
ld
h
a
v
e
a
s
k
e
w
n
e
s
s
n
ea
r
ze
r
o
.
Neg
ativ
e
v
alu
e
s
f
o
r
th
e
s
k
e
w
n
es
s
r
ep
r
esen
t
th
at
d
ata
o
n
w
h
ich
t
h
e
s
k
e
w
n
e
s
s
i
s
ca
lcu
la
ted
is
s
k
e
w
ed
lef
t
a
n
d
p
o
s
itiv
e
v
alu
e
s
in
d
icate
t
h
at
d
ata
ar
e
s
k
e
w
ed
r
i
g
h
t
.
b.
Ku
r
to
s
is
:
I
t
is
a
m
ea
s
u
r
e
o
f
t
h
e
"
tailed
n
ess
"
o
f
th
e
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
an
y
r
ea
l
-
v
alu
ed
r
an
d
o
m
v
ar
iab
le.
Ku
r
to
s
i
s
is
a
m
ea
s
u
r
e
o
f
s
h
ap
e
o
f
a
p
r
o
b
ab
ilit
y
d
i
s
tr
ib
u
tio
n
an
d
,
j
u
s
t
l
ik
e
s
k
e
wn
es
s
,
th
er
e
ar
e
d
if
f
er
e
n
t
w
a
y
s
o
f
ca
lc
u
lati
n
g
it
f
o
r
a
th
eo
r
etica
l
d
is
tr
ib
u
ti
o
n
an
d
co
r
r
esp
o
n
d
in
g
w
a
y
s
o
f
esti
m
ati
n
g
it
f
r
o
m
a
s
a
m
p
le
o
f
a
g
i
v
e
n
p
o
p
u
latio
n
.
Fo
r
u
n
iv
ar
iate
d
ata
Y
1
,
Y
2
,
……Y
N
,
t
h
e
f
o
r
m
u
la
f
o
r
k
u
r
to
s
is
i
s
:
∑
(
̅
)
⁄
(
2
)
w
h
er
e
̅
th
e
m
ea
n
,
s
i
s
t
h
e
s
ta
n
d
ar
d
d
ev
iatio
n
,
an
d
N
is
th
e
n
u
m
b
er
o
f
d
ata
p
o
in
t
s
c.
Mo
m
en
t
:
Mo
m
e
n
t
s
ar
e
s
ca
lar
q
u
an
ti
ties
u
s
ed
to
ch
ar
ac
ter
i
ze
a
f
u
n
c
tio
n
a
n
d
to
ca
p
tu
r
e
its
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
es.
Ma
n
y
t
y
p
e
s
o
f
m
o
m
en
ts
ar
e
t
h
er
e
an
d
ar
e
w
id
el
y
u
s
ed
i
n
s
tati
s
tics
f
o
r
d
esc
r
ip
tio
n
o
f
th
e
s
h
ap
e
o
f
a
p
r
o
b
ab
ilit
y
d
e
n
s
it
y
f
u
n
cti
o
n
.
Gen
er
al
m
o
m
e
n
t
C
o
n
s
id
er
a
g
r
e
y
-
s
ca
le
i
m
a
g
e
g
(
x
,
y
)
o
f
w
id
t
h
w
a
n
d
h
eig
h
t
h
an
d
p
ix
el
s
v
a
lu
e
s
in
t
h
e
r
an
g
e
0
-
2
5
5
.
Geo
m
etr
ic
m
o
m
en
ts
o
f
a
p
+q
th
o
r
d
er
o
f
f
ar
e
g
iv
e
n
b
y
:
[
]
∑
∑
(
3
)
d.
C
en
tr
al
Mo
m
e
n
t:
C
e
n
tr
al
m
o
m
en
t
is
a
m
o
m
e
n
t
o
f
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
a
r
an
d
o
m
v
ar
iab
le
ab
o
u
t
th
e
r
an
d
o
m
v
ar
iab
le's
m
ea
n
.
T
h
e
r
th
m
o
m
e
n
t
ab
o
u
t
an
y
p
o
in
t
A
is
ca
lled
a
ce
n
tr
al
m
o
m
en
t;
it
is
t
h
e
ex
p
ec
ted
v
alu
e
o
f
a
s
p
ec
if
ied
i
n
teg
er
p
o
w
er
o
f
th
e
d
ev
iatio
n
o
f
th
e
r
an
d
o
m
v
ar
iab
le
f
r
o
m
t
h
e
m
ea
n
.
e.
E
n
tr
o
p
y
:
E
n
tr
o
p
y
is
a
m
ea
s
u
r
e
o
f
r
an
d
o
m
n
e
s
s
o
f
th
e
p
i
x
els
th
at
ca
n
b
e
u
s
ed
to
ch
ar
ac
ter
ize
th
e
tex
tu
r
e
f
ea
t
u
r
es
o
f
t
h
e
i
n
p
u
t
i
m
a
g
e
i
n
d
ig
ital
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
E
n
t
r
o
p
y
is
d
e
f
i
n
ed
as
s
u
m
(
p
.
*
lo
g
2
(
p
)
)
w
h
er
e
p
co
n
tain
s
th
e
h
is
to
g
r
a
m
co
u
n
ts
.
f.
Me
an
:
I
t
is
u
s
ed
to
ca
lcu
late
t
h
e
m
ea
n
o
f
all
th
e
w
h
ite
p
ix
el
s
in
i
m
a
g
e
an
d
it
ca
n
b
e
u
s
e
f
u
l
as
a
f
ea
tu
r
e
o
f
i
m
a
g
e
b
ec
au
s
e
e
v
er
y
s
ig
n
at
u
r
e
h
av
e
d
i
f
f
er
e
n
t le
n
g
t
h
s
s
o
to
tal
w
h
ite
p
ix
el
s
ar
e
also
d
if
f
er
en
t
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
Fo
r
th
e
s
i
m
u
latio
n
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
s
i
x
p
er
s
o
n
s
s
i
g
n
at
u
r
es a
r
e
u
s
es a
n
d
th
e
n
co
n
v
er
ted
in
to
d
ig
ital
i
m
a
g
e
b
y
u
s
i
n
g
d
ig
i
tal
s
ca
n
n
er
,
g
e
n
u
in
e
s
i
g
n
at
u
r
es
ar
e
u
s
ed
to
tr
ain
th
e
n
e
u
r
al
n
e
t
w
o
r
k
,
t
h
e
n
d
if
f
er
en
t
f
o
r
g
e
s
i
g
n
atu
r
e
s
lik
e
r
an
d
o
m
an
d
s
k
i
lled
ar
e
u
s
ed
to
test
th
e
n
et
w
o
r
k
,
b
ef
o
r
e
tr
ain
i
n
g
t
h
e
n
eu
r
al
n
e
t
w
o
r
k
th
e
f
ea
t
u
r
es
ar
e
f
ir
s
t
n
o
r
m
al
ized
s
o
th
at
o
n
e
f
ea
t
u
r
e
v
al
u
e
ca
n
n
o
t
d
o
m
in
ate
b
y
o
th
er
f
ea
tu
r
e
f
o
r
n
o
r
m
aliza
tio
n
ea
ch
f
ea
t
u
r
e
is
d
iv
id
ed
b
y
it
s
lar
g
es
t
v
alu
e
to
g
et
a
n
o
r
m
a
lized
v
al
u
e
T
ab
le
1
s
h
o
w
t
h
e
d
atab
ase
ex
tr
ac
ted
f
r
o
m
t
h
e
n
o
r
m
a
lized
f
ea
t
u
r
es
o
f
th
e
s
i
g
n
at
u
r
e
i
m
a
g
e.
E
ac
h
f
ea
t
u
r
es
h
a
v
e
d
if
f
er
en
t
v
al
u
es
t
h
at
ar
e
d
ep
e
n
d
u
p
o
n
t
h
e
u
s
er
lik
e
f
o
r
f
ir
s
t
u
s
e
r
v
alu
e
o
f
s
k
e
w
n
es
s
is
in
0
.
8
r
an
g
e
an
d
f
o
r
u
s
er
2
it
is
i
n
0
.
6
r
an
g
e.
T
ab
le
2
an
d
T
ab
le
3
s
h
o
w
th
e
s
i
g
n
at
u
r
e
u
s
ed
as
o
n
e
o
f
th
e
s
k
illed
f
o
r
g
e
s
i
g
n
atu
r
e
a
n
d
s
ig
n
at
u
r
e
u
s
ed
as o
n
e
o
f
t
h
e
r
an
d
o
m
f
o
r
g
e
s
i
g
n
at
u
r
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
: 2
6
6
5
–
2
6
7
3
2669
T
ab
le
1
.
Data
b
ase
o
f
th
e
E
x
tr
a
cted
Fea
tu
r
es
f
r
o
m
Gen
u
i
n
e
Si
g
na
t
u
r
es
F
e
a
t
u
r
e
I
mag
e
S
k
e
w
n
e
ss
K
u
r
t
o
si
s
O
r
d
e
r
M
o
me
n
t
C
e
n
t
r
e
M
o
me
n
t
N
o
r
mal
M
o
me
n
t
En
t
r
o
p
y
M
e
a
n
U
se
r
1
0
.
8
7
6
1
9
4
3
0
.
7
8
1
5
3
4
0
.
5
2
5
9
5
9
8
-
0
.
9
7
9
2
0
9
5
-
2
.
0
3
4
5
1
8
2
0
.
6
6
8
5
6
4
9
0
.
5
5
7
5
1
4
7
U
se
r
1
0
.
8
6
6
7
3
2
5
0
.
7
6
6
0
2
3
8
0
.
5
0
6
2
1
9
2
-
0
.
8
8
9
4
5
2
5
-
1
.
7
8
4
3
0
3
2
0
.
6
7
7
1
0
7
1
0
.
5
6
6
7
5
0
6
U
se
r
1
0
.
8
8
4
8
4
9
2
0
.
7
9
5
8
6
8
8
0
.
4
0
9
4
0
4
-
0
.
6
8
5
6
3
4
-
1
.
4
7
0
7
2
8
4
0
.
6
6
0
9
7
1
9
0
.
5
4
8
2
7
8
8
U
se
r
1
0
.
8
3
5
0
6
2
4
0
.
7
1
5
3
3
4
3
0
.
4
6
8
9
6
4
5
-
0
.
8
1
6
5
5
8
1
-
1
.
4
5
3
9
3
7
0
.
7
0
6
5
3
0
.
6
0
2
0
1
5
1
U
se
r
2
0
.
6
5
8
6
6
0
5
0
.
4
6
7
5
1
4
7
0
.
9
9
2
4
6
3
6
0
.
6
8
8
5
4
7
1
0
.
5
9
8
4
4
4
6
0
.
9
0
6
0
3
6
4
0
.
8
6
1
4
6
1
U
se
r
2
0
.
6
9
9
5
4
5
0.
5
1
9
7
4
0
7
0
.
7
0
7
2
1
5
2
-
0
.
1
0
4
3
5
6
3
-
0
.
1
0
7
9
8
2
0
.
8
5
3
8
3
4
5
0
.
7
8
9
2
5
2
7
U
se
r
2
0
.
6
2
0
5
6
6
0
.
4
2
1
6
8
2
4
0
.
8
1
8
8
5
0
1
-
0
.
1
2
5
7
7
1
3
-
0
.
0
9
2
4
6
8
9
0
.
9
5
7
8
5
8
8
0
.
9
3
7
0
2
7
7
U
se
r
2
0
.
6
1
0
6
3
8
0
.
4
1
0
1
8
6
2
0
.
7
5
4
5
4
4
3
-
0
.
2
8
6
2
6
7
7
-
0
.
2
0
1
3
8
0
5
0
.
9
7
2
0
9
5
7
0
.
9
5
8
0
1
8
5
U
se
r
3
0
.
5
9
8
7
1
5
0
.
3
9
6
6
2
4
9
1
0
.
5
5
2
7
18
0
.
3
6
8
4
9
5
5
0
.
9
8
9
3
6
9
8
0
.
9
8
4
0
4
7
U
se
r
3
0
.
6
9
1
4
2
2
8
0
.
5
0
9
1
1
5
1
0
.
9
4
9
1
8
8
5
1
1
0
.
8
6
3
8
9
5
2
0
.
8
0
3
5
2
6
4
U
se
r
3
0
.
6
1
9
1
5
8
6
0
.
4
2
0
0
4
1
4
0
.
9
0
6
3
7
2
1
0
.
5
8
7
8
2
5
5
0
.
4
2
9
5
2
8
4
0
.
9
5
9
9
4
6
8
0
.
9
3
9
5
4
6
6
U
se
r
3
0
.
7
4
7
7
9
4
8
0
.
5
8
5
4
2
0
.
6
1
3
6
9
1
8
0
.
3
8
4
5
2
0
7
0
.
4
8
5
7
3
8
9
0
.
7
9
7
2
6
6
5
0
.
7
1
4
5
2
5
6
U
se
r
4
0
.
9
0
4
5
0
4
6
0
.
8
2
8
9
4
6
9
0
.
4
1
1
5
3
1
9
-
0
.
0
2
5
9
2
5
2
-
0
.
0
5
9
7
5
7
6
0
.
6
4
4
0
7
7
4
0
.
5
2
8
9
6
7
3
U
se
r
4
0
.
7
3
5
1
4
4
8
0
.
5
6
7
7
7
6
8
0
.
5
8
0
3
0
8
-
0
.
1
5
5
9
7
-
0
.
1
8
7
1
1
6
5
0
.
8
1
1
6
9
3
2
0
.
7
3
2
9
9
7
5
U
se
r
4
0
.
8
5
2
8
6
5
1
0
.
7
4
3
5
9
6
1
0
.
4
1
6
3
2
-
0
.
3
0
8
2
7
2
1
-
0
.
5
8
7
1
4
6
7
0
.
6
8
9
8
2
5
4
0
.
5
8
1
8
6
4
U
se
r
4
0
.
8
3
2
6
8
9
8
0
.
7
1
1
6
1
2
8
0
.
4
6
0
7
5
4
1
-
0
.
3
3
2
3
0
5
1
-
0
.
5
8
6
3
6
2
4
0
.
7
0
8
8
0
7
9
0
.
6
0
4
5
3
4
U
se
r
5
0
.
8
7
5
1
7
6
7
0
.
7
7
9
8
5
7
8
0
.
4
5
7
6
2
2
3
-
1
.
1
9
0
1
5
9
8
-
2
.
4
6
3
5
4
1
2
0
.
6
6
9
5
1
4
0
.
5
5
8
3
5
4
3
U
se
r
5
0
.
8
8
3
6
0
1
0
.
7
9
3
7
9
2
7
0
.
4
8
1
5
7
8
5
-
0
.
9
5
3
1
1
5
7
-
2
.
0
3
5
1
2
8
3
0
.
6
6
2
1
1
0
9
0
.
5
4
9
9
5
8
U
se
r
5
0
.
9
8
3
9
6
0
5
0
.
9
7
0
0
6
9
7
0
.
3
4
5
7
9
2
7
-
1
.
1
9
5
0
3
0
2
-
3
.
6
4
2
6
2
8
1
0
.
5
8
1
6
2
4
9
0
.
4
6
0
1
1
7
5
U
se
r
5
1
.
0
0
0
0
0
0
9
1
0
.
3
5
7
1
8
8
6
-
0
.
9
8
1
2
9
1
1
-
3
.
1
5
8
8
7
3
3
0
.
5
7
0
2
3
5
4
0
.
4
4
7
5
2
3
1
U
se
r
6
0
.
6
0
5
2
9
8
1
0
.
4
0
4
0
7
9
5
0
.
7
1
8
4
4
4
2
-
0
.
1
2
4
1
5
7
4
-
0
.
0
8
5
2
6
4
2
0
.
9
7
9
6
8
8
7
0
.
9
6
9
7
7
3
3
U
se
r
6
0
.
5
9
1
4
2
3
4
0
.
3
8
8
4
6
3
2
0
.
7
4
7
3
4
2
1
-
0
.
0
5
2
9
2
9
5
-
0
.
0
3
4
1
3
4
7
1
1
U
se
r
6
0
.
6
1
8
5
5
7
2
0
.
4
1
9
3
4
1
4
0
.
7
7
0
8
8
0
3
-
0
.
0
3
7
4
5
9
9
-
0
.
0
2
7
3
0
7
8
0
.
9
6
0
7
0
6
2
0
.
9
4
1
2
2
5
9
U
se
r
6
0
.
6
2
8
1
0
2
4
0
.
4
3
0
5
3
3
1
0
.
6
0
4
1
2
5
1
-
0
.
5
5
2
1
0
4
6
-
0
.
4
1
9
7
5
5
7
0
.
9
4
7
4
1
8
4
0
.
9
2
1
0
7
4
7
T
ab
le
2
.
Sig
n
at
u
r
e
u
s
ed
as o
n
e
o
f
th
e
S
k
illed
Fo
r
g
e
Si
g
n
at
u
r
e
F
e
a
t
u
r
e
I
mag
e
S
k
e
w
n
e
ss
K
u
r
t
o
si
s
O
r
d
e
r
M
o
me
n
t
C
e
n
t
r
e
M
o
me
n
t
N
o
r
mal
M
o
me
n
t
En
t
r
o
p
y
M
e
a
n
U
se
r
1
0
.
6
7
7
2
5
8
0
.
4
9
0
8
8
5
0
.
8
2
6
8
0
4
-
0
.
5
9
7
0
9
-
0
.
5
6
2
1
3
0
.
8
8
1
7
3
9
0
.
8
2
7
8
7
6
U
se
r
2
1
.
0
1
0
6
8
1
1
.
0
2
0
1
7
2
0
.
3
6
5
6
0
9
-
0
.
1
3
3
0
8
-
0
.
4
4
4
1
9
0
.
5
6
2
6
4
2
0
.
4
3
9
9
6
6
U
se
r
3
0
.
6
2
1
1
7
2
0
.
4
2
2
3
9
1
0
.
5
4
0
8
5
7
-
0
.
4
7
3
2
1
-
0
.
3
4
8
9
0
.
9
5
7
0
9
9
0
.
9
3
5
3
4
8
U
se
r
4
0
.
8
4
6
7
7
4
0
.
7
3
3
8
6
4
0
.
5
0
8
4
7
2
0
.
0
2
0
2
0
6
0
.
0
3
7
4
7
6
0
.
6
9
5
5
2
0
.
5
8
8
5
8
1
U
se
r
5
0
.
8
6
8
7
3
0
.
7
6
9
2
8
0
.
4
1
5
1
0
6
-
1
.
4
5
1
0
6
-
2
.
9
3
2
6
8
0
.
6
7
5
3
9
9
0
.
5
6
5
0
7
1
U
se
r
6
0
.
5
3
9
2
5
6
0
.
3
3
2
9
8
0
.
8
9
9
8
2
5
-
0
.
1
5
7
6
-
0
.
0
7
9
8
9
1
.
0
8
0
6
7
6
1
.
1
2
8
4
6
3
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
ig
n
a
tu
r
e
V
erif
ica
tio
n
u
s
in
g
N
o
r
ma
liz
ed
S
ta
tic
F
ea
tu
r
es a
n
d
N
eu
r
a
l Netw
o
r
k
C
la
s
s
ifica
tio
n
(
Ma
n
is
h
Tr
ikh
a
)
2670
T
ab
le
3.
Sig
n
at
u
r
e
Use
d
as o
n
e
o
f
th
e
R
a
n
d
o
m
Fo
r
g
e
Sig
n
at
u
r
e
F
e
a
t
u
r
e
I
mag
e
S
k
e
w
n
e
ss
K
u
r
t
o
si
s
O
r
d
e
r
M
o
me
n
t
C
e
n
t
r
e
M
o
me
n
t
N
o
r
mal
M
o
me
n
t
En
t
r
o
p
y
M
e
a
n
U
se
r
1
0
.
5
4
5
6
4
4
0
.
3
3
9
5
0
6
1
.
2
9
6
6
1
3
0
.
7
9
1
3
5
5
0
.
4
1
3
3
9
4
1
.
0
7
0
4
2
5
1
.
1
1
1
6
7
1
U
se
r
2
0
.
6
0
0
0
4
5
0
.
3
9
8
1
1
8
1
.
1
4
8
3
4
5
0
.
4
4
5
5
6
4
0
.
2
9
8
9
3
3
0
.
9
8
7
4
7
2
0
.
9
8
0
6
8
8
U
se
r
3
1
.
1
4
0
0
0
6
1
.
2
8
1
8
0
8
0
.
2
2
0
7
8
8
0
.
1
0
5
0
5
6
0
.
5
3
1
0
5
0
.
4
8
1
9
6
7
0
.
3
5
6
8
4
3
U
se
r
4
1
.
2
8
2
4
3
4
1
.
6
0
6
2
7
4
0
.
3
0
1
6
4
4
0
.
0
8
5
6
0
4
0
.
6
5
7
4
2
1
0
.
4
1
1
1
6
2
0
.
2
8
9
6
7
3
U
se
r
5
1
.
0
5
0
5
9
5
1
.
0
9
7
5
6
5
0
.
3
4
5
9
6
2
0
.
1
8
8
6
0
3
0
.
7
1
8
4
2
8
0
.
5
3
5
6
8
7
0
.
4
1
1
4
1
9
U
se
r
6
0
.
9
1
0
4
5
5
0
.
8
3
9
1
1
8
0
.
7
4
9
0
8
0
.
0
9
5
5
3
0
.
2
2
4
8
5
4
0
.
6
3
9
1
4
2
0
.
5
2
3
9
2
9
Fig
u
r
e
5
.
User
1
Sig
n
at
u
r
e
Fea
tu
r
es C
o
m
p
ar
is
on
Fig
u
r
e
6
.
User
2
Sig
n
at
u
r
e
Fea
tu
r
es C
o
m
p
ar
is
o
n
Fig
u
r
e
7
.
User
3
Sig
n
at
u
r
e
Fea
tu
r
es C
o
m
p
ar
is
o
n
Fig
u
r
e
8
.
User
4
Sig
n
at
u
r
e
Fea
tu
r
es C
o
m
p
ar
is
o
n
Fig
u
r
e
9
.
User
5
Sig
n
at
u
r
e
Fea
tu
r
es C
o
m
p
ar
is
o
n
Fig
u
r
e
10
.
User
6
Sig
n
at
u
r
e
F
ea
tu
r
es C
o
m
p
ar
is
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
: 2
6
6
5
–
2
6
7
3
2671
Fig
u
r
e
5
-
1
0
s
h
o
w
s
th
at
ea
c
h
g
en
u
i
n
e
s
i
g
n
at
u
r
e
h
a
v
e
d
if
f
er
en
t
f
ea
t
u
r
es
v
al
u
e
s
w
h
e
n
co
m
p
ar
ed
w
it
h
d
if
f
er
e
n
t
f
o
r
g
e
s
i
g
n
a
tu
r
e
t
y
p
e
s
i.e
.
,
s
k
illed
a
n
d
r
an
d
o
m
f
o
r
g
e.
So
it
v
er
i
f
ies
th
at
t
h
e
s
e
f
e
atu
r
es
ca
n
v
ar
ies
i
f
th
at
s
ig
n
at
u
r
e
is
tr
y
in
g
to
b
e
f
o
r
g
ed
an
d
ca
n
b
e
ea
s
il
y
id
en
ti
f
ied
w
it
h
g
o
o
d
class
i
f
icat
io
n
s
y
s
te
m
i
n
t
h
is
p
ap
er
n
eu
r
al
n
et
w
o
r
k
i
s
u
s
ed
a
class
i
f
ier
.
T
h
e
n
eu
r
al
n
et
w
o
r
k
is
tr
ain
f
o
r
t
h
e
class
if
icat
io
n
an
d
v
er
i
f
icatio
n
o
f
th
e
s
i
g
n
a
tu
r
e
,
f
o
r
th
is
n
n
s
tar
t
to
o
l
o
f
MA
T
L
A
B
is
u
s
ed
an
d
th
en
p
atter
n
r
ec
o
g
n
itio
n
ap
p
licatio
n
is
u
s
ed
to
r
ec
o
g
n
ize
th
e
s
ig
n
atu
r
e.
T
ab
le
4
s
h
o
w
s
t
h
e
v
a
lu
e
o
f
F
AR
(
Fal
s
e
r
ej
ec
tio
n
R
ate)
an
d
FR
R
(
Fa
ls
e
A
cc
ep
tan
ce
R
ate)
co
m
p
ar
i
s
o
n
o
f
t
h
e
p
r
o
p
o
s
e
d
s
y
s
te
m
w
it
h
th
e
e
x
is
t
in
g
s
y
s
te
m
s
.
T
ab
le
4
.
P
er
f
o
r
m
a
n
ce
A
n
al
y
s
i
s
o
f
P
r
o
p
o
s
ed
Sy
s
te
m
w
it
h
E
x
is
ti
n
g
S
y
s
te
m
S
y
st
e
m
F
A
R
F
R
R
P
r
o
p
o
se
d
S
y
st
e
m
5
.
0
5
%
4
.
2
5
%.
[
8
]
1
2
%
8%
[
1
2
]
5
.
8
%
5
.
0
%
[
2
1
]
1
1
%
2%
4.
CO
NCLU
SI
O
N
Sig
n
at
u
r
e
is
w
id
el
y
u
s
e
d
as
m
ea
n
s
o
f
p
er
s
o
n
al
r
ec
o
g
n
itio
n
an
d
v
er
if
ica
tio
n
p
r
o
ce
s
s
;
an
d
n
eu
r
al
n
et
w
o
r
k
is
t
h
e
v
er
if
icat
io
n
s
y
s
te
m
w
h
ich
i
s
b
ased
o
n
h
u
m
a
n
b
r
ain
ap
p
r
o
ac
h
f
o
r
p
atter
n
r
e
co
g
n
itio
n
,
s
o
w
h
e
n
n
eu
r
al
n
et
w
o
r
k
is
u
s
ed
to
v
er
if
icatio
n
o
f
h
an
d
w
r
it
ten
s
i
g
n
at
u
r
e
th
e
n
t
h
e
e
f
f
icien
c
y
o
f
th
e
v
er
if
ica
tio
n
s
y
s
te
m
in
cr
ea
s
es
b
y
a
g
r
ea
t
a
m
o
u
n
t
.
I
n
th
is
p
ap
er
th
e
O
f
f
li
n
e
s
ig
n
at
u
r
es
Ver
i
f
icatio
n
s
y
s
te
m
is
u
s
ed
f
o
r
th
e
v
er
if
ica
tio
n
o
f
s
ig
n
at
u
r
e
i
m
a
g
e.
I
n
th
is
ap
p
r
o
ac
h
a
s
ig
n
a
tu
r
e
i
m
ag
e
i
s
f
ir
s
t
p
r
e
-
p
r
o
ce
s
s
ed
f
o
r
th
e
r
e
m
o
v
al
o
f
n
o
is
e
a
n
d
co
n
v
er
ted
in
to
b
in
a
r
y
i
m
ag
e
o
f
2
0
0
x
2
0
0
P
ix
els
a
n
d
th
e
n
th
e
f
ea
t
u
r
es,
l
ik
e
E
cc
en
tr
icit
y
,
K
u
r
to
s
is
,
Sk
e
w
n
es
s
etc.
,
ar
e
e
x
tr
ac
ted
f
r
o
m
th
e
i
m
a
g
e
a
n
d
t
h
en
n
o
r
m
aliza
tio
n
o
f
th
e
f
ea
tu
r
es
ar
e
d
o
n
e
an
d
a
f
ter
t
h
at
th
ese
n
o
r
m
alize
d
f
ea
t
u
r
es
ar
e
u
s
ed
to
tr
ain
t
h
e
n
e
u
r
al
n
et
w
o
r
k
u
s
in
g
b
ac
k
-
p
r
o
p
ag
ati
o
n
tech
n
iq
u
e.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
s
s
h
o
w
n
in
T
ab
le
4
p
r
o
v
id
e
m
o
r
e
r
o
b
u
s
t
v
er
i
f
icatio
n
s
y
s
te
m
w
h
en
co
m
p
ar
ed
to
o
th
er
m
et
h
o
d
s
an
d
t
h
i
s
i
m
p
r
o
v
e
m
e
n
t
i
s
m
ai
n
l
y
d
u
e
to
n
o
r
m
a
liza
tio
n
o
f
th
e
f
ea
tu
r
es
b
ef
o
r
e
u
s
ed
in
cla
s
s
i
f
icati
o
n
p
r
o
ce
s
s
w
h
ich
p
r
ev
e
n
t t
h
e
d
o
m
i
n
an
ce
o
f
ce
r
tain
f
ea
tu
r
e
s
o
v
er
o
th
er
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
w
o
u
ld
lik
e
to
th
an
k
Dir
ec
to
r
,
Natio
n
al
I
n
s
tit
u
te
o
f
T
ec
h
n
ical
T
ea
ch
er
T
r
ain
i
n
g
a
n
d
R
esear
ch
,
C
h
a
n
d
ig
ar
h
,
I
n
d
ia
f
o
r
th
eir
co
n
s
tan
t su
p
p
o
r
t a
n
d
i
n
s
p
ir
atio
n
t
h
r
o
u
g
h
o
u
t t
h
is
r
ese
ar
ch
w
o
r
k
.
RE
F
E
R
E
NC
E
S
[1
]
Ja
in
,
A
.
,
Ro
ss
,
A
.
a
n
d
P
ra
b
h
a
k
a
r,
S
.
,
“
A
n
In
tro
d
u
c
t
io
n
to
b
i
o
m
e
tri
c
re
c
o
g
n
it
io
n
”
,
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
Circ
u
it
a
n
d
S
y
ste
ms
fo
r V
id
e
o
T
e
c
h
n
o
l
o
g
y
,
1
4
(1
),
p
p
.
4
-
20
(
2
0
0
4
)
.
[2
]
Ju
n
g
p
il
S
h
in
a
n
d
T
e
tsu
y
a
Tak
a
n
a
sh
i,
“
On
li
n
e
-
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
b
a
se
d
o
n
P
e
n
In
c
li
n
a
ti
o
n
a
n
d
P
re
ss
u
re
In
f
o
rm
a
ti
o
n
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
2
,
N
o
.
4
,
p
p
.
4
4
1
-
4
4
6
,
A
u
g
u
st 2
0
1
2
.
[3
]
A
.
F
a
ll
a
h
,
M
.
Ja
m
a
a
ti
a
n
d
A
.
S
o
l
e
a
m
a
n
i,
"
A
n
e
w
o
n
li
n
e
sig
n
a
tu
re
v
e
rif
i
c
a
ti
o
n
sy
ste
m
b
a
se
d
o
n
c
o
m
b
in
in
g
M
e
ll
in
tran
sf
o
r
m
,
M
F
CC
a
n
d
n
e
u
ra
l
n
e
t
w
o
rk
"
,
S
c
ien
c
e
Dire
c
t
J
o
u
rn
a
l
o
n
Dig
it
a
l
S
ig
n
a
l
Pr
o
c
e
ss
.
,
v
o
l.
2
1
,
n
o
.
2
,
p
p
.
4
0
4
-
4
1
6
,
2
0
1
1
.
[4
]
M
a
d
a
b
u
si,
S
.
,
S
ri
n
iv
a
s,
V
.
,
Bh
a
s
k
a
ra
n
,
S
.
,
Ba
las
u
b
ra
m
a
n
ian
,
M
.
:„
On
-
li
n
e
a
n
d
o
f
f
-
li
n
e
sig
n
a
tu
r
e
v
e
rif
ica
ti
o
n
u
sin
g
re
lativ
e
slo
p
e
a
lg
o
rit
h
m
‟.
In
t.
W
o
rk
sh
o
p
o
n
M
e
a
su
re
me
n
t
S
y
ste
ms
fo
r Ho
me
la
n
d
S
e
c
u
rity
,
2
0
0
5
,
p
p
.
1
1
–
1
5
.
[5
]
G
.
P
irl
o
,
V
.
Cu
c
c
o
v
il
l
o
,
M
.
Dia
z
-
Ca
b
re
ra
,
D.
Im
p
e
d
o
v
o
,
a
n
d
P
.
M
ig
n
o
n
e
,
“
M
u
l
ti
d
o
m
a
in
v
e
rif
i
c
a
t
io
n
o
f
d
y
n
a
m
ic
sig
n
a
tu
re
s
u
sin
g
lo
c
a
l
sta
b
il
it
y
a
n
a
l
y
sis”
,
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
H
u
ma
n
-
M
a
c
h
in
e
S
y
ste
ms
,
v
o
l.
4
5
,
n
o
.
6
,
p
p
.
8
0
5
–
8
1
0
,
De
c
.
2
0
1
5
.
[6
]
G
a
u
ta
m
.
S
.
P
ra
k
a
sh
a
n
d
S
h
a
n
u
S
h
a
rm
a
,
“
Co
m
p
u
ter
v
isio
n
&
f
u
z
z
y
lo
g
ic
b
a
se
d
o
ff
li
n
e
sig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
a
n
d
f
o
rg
e
r
y
d
e
tec
ti
o
n
”
,
IEE
E
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
C
o
mp
u
ti
n
g
Res
e
a
rc
h
(
ICCIC)
,
p
p
.
1
-
6
,
De
c
e
m
b
e
r,
2
0
1
4
.
[7
]
M
.
R
Nilch
iy
a
l,
R.
Bte
Yu
so
f
a
n
d
S
.
E
A
lav
i,
“
S
tatisti
c
a
l
On
li
n
e
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
Us
in
g
Ro
t
a
ti
o
n
-
I
n
v
a
rian
t
D
y
n
a
m
ic De
s
c
rip
to
rs”
,
Asia
n
C
o
n
tro
l
C
o
n
fer
e
n
c
e
(
AS
CC),
Ko
ta
K
in
a
b
a
l
u
,
p
p
.
1
-
6
,
2
0
1
5
.
[8
]
K.V
L
a
k
sh
m
i
a
n
d
S
e
e
m
a
Na
y
a
k
,
“
O
ff
-
li
n
e
sig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s”
,
A
d
v
a
n
c
e
Co
m
p
u
ti
n
g
Co
n
f
e
re
n
c
e
(I
A
CC),
IEE
E
3
rd
In
ter
n
a
ti
o
n
a
l
Ad
v
a
n
c
e
Co
mp
u
t
in
g
Co
n
fer
e
n
c
e
(
IACC),
p
p
.
1
0
6
5
-
1
0
6
9
,
F
e
b
r
u
a
ry
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
S
ig
n
a
tu
r
e
V
erif
ica
tio
n
u
s
in
g
N
o
r
ma
liz
ed
S
ta
tic
F
ea
tu
r
es a
n
d
N
eu
r
a
l Netw
o
r
k
C
la
s
s
ifica
tio
n
(
Ma
n
is
h
Tr
ikh
a
)
2672
[9
]
J.F
.
V
a
rg
a
s,
M
.
A
.
F
e
rre
r,
C.
M
.
T
ra
v
ies
o
a
n
d
J.B
.
A
lo
n
so
,
“
Of
f
-
li
n
e
sig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
b
a
se
d
o
n
g
re
y
lev
e
l
in
f
o
rm
a
ti
o
n
u
sin
g
tex
tu
re
f
e
a
tu
re
s”
,
S
c
ien
c
e
Dire
c
t
J
o
u
rn
a
l
o
n
Pa
tt
e
rn
Rec
o
g
n
i
ti
o
n
,
V
o
l.
4
4
,
Iss
u
e
2
,
p
p
.
3
7
5
–
3
8
5
,
F
e
b
ru
a
ry
2
0
1
1
.
[1
0
]
Zh
a
n
g
Jia
n
-
z
h
o
n
g
,
He
y
o
n
g
-
y
i
a
n
d
L
i
J
u
n
,
“
A
ss
e
m
b
l
y
Qu
a
li
t
y
P
re
d
ictio
n
Ba
se
d
o
n
Ba
c
k
-
p
ro
p
a
g
a
ti
o
n
A
rti
f
ica
l
Ne
u
ra
l
Ne
t
w
o
rk
”
,
T
EL
KOM
NIK
A
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
v
o
l.
1
2
,
n
o
.
1
,
p
p
.
1
7
9
-
1
8
5
,
Ja
n
u
a
ry
2
0
1
4
.
[1
1
]
Ce
m
il
OZ,
F
ik
re
t
Erca
l
a
n
d
Zaf
e
r
De
m
ir,
“
S
ig
n
a
tu
re
Re
c
o
g
n
it
io
n
a
n
d
V
e
rif
ica
ti
o
n
w
it
h
A
NN
”
,
Ch
a
mb
e
r
o
f
El
e
c
trica
l
En
g
in
e
e
rs
(
EM
O
–
El
e
k
trik
M
u
h
e
n
d
isler
i
Od
a
si)
T
h
ird
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
El
e
c
trica
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
p
p
.
1
-
5
,
A
p
ril
,
2
0
0
9
.
[1
2
]
S
n
e
h
il
G
.
jaiw
a
l
a
n
d
A
b
h
a
y
R
K
a
se
t
w
a
r,
“
O
ff
-
li
n
e
sig
n
a
tu
re
v
e
rifi
c
a
ti
o
n
u
si
n
g
g
lo
b
a
l
&
lo
c
a
l
f
e
a
tu
re
s
w
it
h
n
e
u
ra
l
n
e
tw
o
rk
s”
,
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
mm
u
n
ica
ti
o
n
Co
n
tro
l
a
n
d
Co
mp
u
ti
o
n
g
T
e
c
h
n
o
lo
g
ies
(
ICACCCT
)
,
p
p
.
1
5
2
5
-
1
5
3
1
,
2
0
1
4
.
[1
3
]
M
ig
u
e
l
A
.
F
e
rre
r,
J.
F
ra
n
c
is
c
o
Va
rg
a
s,
Ay
th
a
m
i
M
o
ra
les
,
a
n
d
Aa
ró
n
Or
d
ó
ñ
e
z
,
“
Ro
b
u
stn
e
ss
o
f
O
ff
li
n
e
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
Ba
se
d
o
n
G
ra
y
L
e
v
e
l
F
e
a
tu
re
s”
,
IEE
E
T
ra
n
sa
c
ti
o
n
s O
n
In
f
o
rm
a
ti
o
n
Fo
re
n
sic
s A
n
d
S
e
c
u
rity
,
v
o
l.
7
,
n
o
.
3
,
p
p
.
9
6
6
-
9
7
7
,
Ju
n
e
2
0
1
2
.
[1
4
]
D.
R.
S
h
a
sh
ik
u
m
a
r,
K.
B.
R
a
ja,
R.
K.
Ch
h
o
tara
y
,
S
.
P
a
tt
a
n
a
ik
,
“
Bio
m
e
tri
c
se
c
u
rit
y
s
y
ste
m
b
a
se
d
o
n
sig
n
a
tu
re
v
e
ri
f
ica
ti
o
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
r
k
s”
,
IEE
E
Co
n
fer
e
n
c
e
o
n
Co
m
p
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
C
o
mp
u
ti
n
g
Res
e
a
rc
h
(
ICCIC)
,
Ba
n
g
a
lo
re
,
p
p
.
1
-
6
,
2
0
1
0
[1
5
]
S
tép
h
a
n
e
A
rm
a
n
d
,
M
ich
a
e
l
Blu
m
e
n
ste
in
a
n
d
V
a
ll
ip
u
ra
m
M
u
th
u
k
k
u
m
a
ra
sa
m
y
,
“
O
ff
-
li
n
e
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
u
sin
g
th
e
E
n
h
a
n
c
e
d
M
o
d
if
ied
Di
re
c
ti
o
n
F
e
a
tu
re
a
n
d
Ne
u
ra
l
-
b
a
se
d
Clas
sif
ic
a
ti
o
n
”
,
In
ter
n
a
ti
o
n
a
l
J
o
in
t
C
o
n
fer
e
n
c
e
o
n
Ne
u
ra
l
Ne
two
rk
s
S
h
e
ra
to
n
V
a
n
c
o
u
v
e
r
W
a
ll
Ce
n
tre
Ho
tel,
Va
n
c
o
u
v
e
r,
BC,
Ca
n
a
d
a
,
p
p
.
6
8
4
-
6
9
1
,
Ju
ly
1
6
-
2
1
,
2
0
0
6
.
[1
6
]
In
d
ra
ji
t
Bh
a
tt
a
c
h
a
ry
a
a
,
P
ra
b
ir
Gh
o
sh
b
,
S
w
a
ru
p
Bisw
a
sb
,
“
Off
li
n
e
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
Us
in
g
P
ix
e
l
M
a
tch
in
g
T
e
c
h
n
iq
u
e
”
,
El
se
v
ier
(
Pro
c
e
d
ia
T
e
c
h
n
o
l
o
g
y
1
0
)
I
n
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Co
mp
u
t
a
ti
o
n
a
l
In
tell
ig
e
n
c
e
:
M
o
d
e
li
n
g
T
e
c
h
n
iq
u
e
s a
n
d
Ap
p
li
c
a
ti
o
n
s
,
p
p
.
9
7
0
-
9
7
7
,
2
0
1
3
.
[1
7
]
S
ri
k
a
n
ta
P
a
l,
Um
a
p
a
d
a
P
a
l,
M
ic
h
a
e
l
Blu
m
e
n
ste
in
,
“
O
ff
-
li
n
e
v
e
ri
f
ica
ti
o
n
tec
h
n
iq
u
e
f
o
r
Hin
d
i
sig
n
a
tu
re
s”
,
IEE
E
T
ra
n
se
c
ti
o
n
s o
n
IET
Bi
o
me
trics
,
v
o
l.
2,
n
o
.
4
,
p
p
.
1
8
2
-
1
9
0
,
Oc
to
b
e
r
2
0
1
3
.
[1
8
]
M.
-
K.
Hu
,
“
V
isu
a
l
p
a
tt
e
rn
re
c
o
g
n
it
io
n
b
y
m
o
m
e
n
t
in
v
a
rian
ts,
”
I
RE
T
ra
n
s
.
In
fo
r
ma
t
io
n
T
h
e
o
ry
,
v
o
l.
8
,
n
o
.
2
,
p
p
.
179
–
1
8
7
,
1
9
6
2
.
[1
9
]
Oth
m
a
n
o
-
k
h
a
li
f
a
,
M
d
.
Kh
o
rsh
e
d
A
la
m
a
n
d
A
ish
a
Ha
ss
a
n
A
b
d
a
ll
a
“
A
n
Ev
a
lu
a
ti
o
n
o
n
O
ff
li
n
e
S
ig
n
a
tu
re
V
e
rif
ica
ti
o
n
u
si
n
g
A
rti
f
i
c
ial
Ne
u
ra
l
Ne
tw
o
rk
A
p
p
ro
a
c
h
,
”
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ti
n
g
,
El
e
c
trica
l
a
n
d
El
e
c
tro
n
ic E
n
g
i
n
e
e
rin
g
(
ICCEE
E
)
(
2
0
1
3
)
,
p
p
.
3
6
8
-
3
7
1
,
2
0
1
3
.
[2
0
]
A
li
Ka
ro
u
n
i,
Ba
ss
a
m
D
a
y
a
a
n
d
S
a
m
ia
B
a
h
lak
,
“
O
ff
li
n
e
sig
n
a
tu
re
re
c
o
g
n
it
io
n
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s
a
p
p
ro
a
c
h
”
,
EL
S
EV
I
ER
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
3
,
p
p
.
1
5
5
–
1
6
1
,
2
0
1
1
.
[2
1
]
P
a
n
sa
re
,
A
sh
w
in
i
a
n
d
S
h
a
li
n
i
B
h
a
t
ia,
“
Ha
n
d
w
rit
ten
S
ig
n
a
tu
re
Ve
rif
ic
a
ti
o
n
u
sin
g
Ne
u
ra
l
n
e
tw
o
rk
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
li
e
d
In
f
o
rm
a
ti
o
n
S
y
ste
ms
,
1
(2
0
1
2
),
p
p
.
4
4
-
49.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
a
n
ish
Tr
i
k
h
a
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r‟s
d
e
g
re
e
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
i
n
e
e
rin
g
f
ro
m
M
o
ra
d
a
b
a
d
In
sti
tu
te
o
f
T
e
c
h
n
o
lo
g
y
(M
IT
),
M
o
ra
d
a
b
a
d
,
In
d
i
a
in
2
0
0
7
,
a
n
d
He
is
p
u
rs
u
in
g
M
a
ste
rs
o
f
En
g
in
e
e
rin
g
d
e
g
re
e
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
f
ro
m
Na
ti
o
n
a
l
In
stit
u
te
o
f
T
e
c
h
n
ica
l
T
e
a
c
h
e
rs
‟
T
ra
in
in
g
&
Re
se
a
rc
h
(NITT
T
R),
P
a
n
ja
b
Un
iv
e
r
sity
,
a
n
d
Ch
a
n
d
ig
a
rh
,
In
d
ia.
He
is
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
w
it
h
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
M
o
ra
d
a
b
a
d
In
sti
tu
te
o
f
T
e
c
h
n
o
l
o
g
y
,
a
n
d
M
o
ra
d
a
b
a
d
,
In
d
ia.
His
c
u
rre
n
t
re
se
a
rc
h
a
n
d
te
a
c
h
in
g
in
tere
sts
a
re
in
Ne
u
ra
l
Ne
tw
o
rk
,
I
m
a
g
e
P
ro
c
e
ss
in
g
,
Dig
it
a
l
e
lec
tro
n
ics
a
n
d
P
o
w
e
r
El
e
c
tro
n
ics
.
He
h
a
s
a
u
t
h
o
re
d
1
4
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s i
n
c
lu
d
in
g
9
in
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
a
n
d
5
i
n
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
s.
M
a
n
a
s
S
in
g
h
a
l
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r‟s
d
e
g
re
e
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
f
ro
m
G
r
e
a
ter
No
id
a
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
UP
T
U,
G
re
a
ter
No
id
a
,
a
n
d
In
d
ia
in
2
0
0
8
,
a
n
d
He
is
p
u
rsu
i
n
g
M
a
ste
rs
o
f
En
g
in
e
e
rin
g
d
e
g
re
e
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
f
ro
m
Na
ti
o
n
a
l
I
n
stit
u
te
o
f
T
e
c
h
n
ica
l
T
e
a
c
h
e
rs‟
T
ra
in
in
g
&
Re
se
a
r
c
h
(NITT
T
R),
P
a
n
jab
Un
iv
e
rsity
,
Ch
a
n
d
ig
a
rh
,
In
d
ia.
He
is
a
n
A
ss
istan
t
P
r
o
f
e
ss
o
r
w
it
h
th
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
&
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
M
o
ra
d
a
b
a
d
I
n
stit
u
te
o
f
Tec
h
n
o
lo
g
y
(M
I
T
),
M
o
ra
d
a
b
a
d
,
In
d
ia.
His
c
u
rre
n
t
re
se
a
rc
h
a
n
d
tea
c
h
in
g
in
tere
sts
a
re
in
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
Dig
it
a
l
El
e
c
tro
n
ics
a
n
d
Dig
it
a
l
S
ig
n
a
l
P
ro
c
e
ss
in
g
.
He
h
a
s au
th
o
re
d
1
5
re
se
a
rc
h
p
u
b
l
ica
ti
o
n
s i
n
c
lu
d
in
g
1
0
in
J
o
u
r
n
a
ls.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
: 2
6
6
5
–
2
6
7
3
2673
Dr
.
M
a
ity
r
e
e
Du
tta
c
u
rre
n
tl
y
wo
rk
in
g
a
s
a
P
r
o
f
e
ss
o
r
a
n
d
He
a
d
o
f
th
e
De
p
a
rt
m
e
n
t,
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
ri
n
g
,
Na
ti
o
n
a
l
In
st
it
u
te o
f
T
e
c
h
n
ica
l
Tea
c
h
e
r
T
r
a
in
in
g
a
n
d
Re
se
a
rc
h
(NITT
T
R),
Ch
a
n
d
ig
a
rh
,
In
d
ia.
H
e
r
a
re
a
o
f
in
tere
st
in
c
lu
d
e
s
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
,
Ne
u
ra
l
Ne
tw
o
rk
e
t
c
.
S
h
e
h
a
s au
t
h
o
re
d
v
a
rio
u
s
p
a
p
e
rs i
n
Jo
u
r
n
a
ls
a
n
d
Co
n
f
e
re
n
c
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.