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.
24
,
No
.
2
,
N
o
v
em
b
e
r
2
0
2
1
,
p
p
.
1
2
1
2
~
1
2
1
9
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
24
.i
2
.
pp
1
2
1
2
-
1
2
1
9
1212
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
An
ea
r r
ecog
nition sy
stem ba
sed o
n loca
l wav
elet
su
bba
nd
energy
distribu
tio
n
Rua
a
I
s
a
m
F
a
dh
il
1
,
L
o
a
y
E
.
G
eo
rg
e
2
1
M
in
istr
y
o
f
e
d
u
c
a
ti
o
n
,
Ba
g
h
d
a
d
,
Ira
q
2
Un
iv
e
rsity
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
a
n
d
C
o
m
m
u
n
ica
ti
o
n
,
As
sista
n
t
P
re
sid
e
n
t
fo
r
S
c
ien
ti
fic Affa
ir
s
,
Ba
g
h
d
a
d
,
Ira
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
15
,
2
0
2
1
R
ev
is
ed
Sep
2
,
2
0
2
1
Acc
ep
ted
Sep
13
,
2
0
2
1
Th
e
o
u
ter
e
a
r
fe
a
tu
re
s
h
a
v
e
b
e
e
n
u
se
d
fo
r
m
a
n
y
y
e
a
rs
in
fo
re
n
sic
sc
ien
c
e
o
f
re
c
o
g
n
it
i
o
n
.
Hu
m
a
n
e
a
r
is
a
v
a
l
u
a
b
le
i
n
fo
rm
a
ti
o
n
p
ro
v
e
n
a
n
c
e
o
f
d
a
ta
fo
r
in
d
i
v
id
u
a
l
id
e
n
t
ifi
c
a
ti
o
n
/au
t
h
e
n
ti
c
a
ti
o
n
.
Ear
m
e
e
ts
b
i
o
m
e
tri
c
c
h
a
ra
c
teristic
(u
n
i
v
e
rsa
li
ty
,
d
isti
n
c
ti
v
e
n
e
ss
,
p
e
rm
a
n
e
n
c
e
a
n
d
c
o
ll
e
c
tab
il
it
y
)
.
Bio
m
e
tri
c
sy
ste
m
d
e
p
e
n
d
i
n
g
o
n
e
a
r
ima
g
e
f
a
c
in
g
two
m
a
jo
r
c
h
a
ll
e
n
g
e
s;
th
e
first
o
n
e
is
th
e
lo
c
a
li
z
a
ti
o
n
o
f
h
u
m
a
n
e
a
r
a
re
a
in
g
i
v
e
n
p
r
o
fil
e
fa
c
e
ima
g
e
,
a
n
d
t
h
e
se
c
o
n
d
o
n
e
is
t
h
e
se
lec
ti
o
n
o
f
p
ro
p
e
r
fe
a
tu
re
s
t
o
d
isti
n
g
u
ish
b
e
t
we
e
n
in
d
i
v
id
u
a
ls.
I
n
th
is
wo
r
k
,
we
p
r
o
p
o
se
a
n
a
lo
g
o
r
it
h
m
fo
r
e
a
r
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
th
e
l
o
c
a
l
sp
a
ti
a
l
e
n
e
rg
y
d
istri
b
u
t
io
n
o
f
wa
v
e
let
su
b
-
b
a
n
d
s
,
b
e
c
a
u
se
o
f
wa
v
e
let
tran
sfo
rm
h
a
s
t
h
e
a
b
i
li
ty
t
o
a
n
a
ly
z
e
th
e
l
o
c
a
l
fe
a
tu
re
o
f
2
-
D
ima
g
e
b
y
d
e
term
in
in
g
w
h
e
re
th
e
lo
w
fre
q
u
e
n
c
y
a
n
d
h
ig
h
fre
q
u
e
n
c
y
a
re
a
s
a
re
a
n
d
it
p
ro
v
id
e
s
fu
l
l
d
e
sc
rip
ti
o
n
o
f
t
h
e
sp
a
ti
a
l
d
istri
b
u
t
io
n
o
f
t
h
e
e
a
r
ima
g
e
.
Ne
a
re
st
c
las
sifier
a
re
u
se
d
to
m
a
k
e
a
re
c
o
g
n
i
ti
o
n
d
e
c
isio
n
in
m
a
tch
in
g
sta
g
e
.
Th
e
sy
ste
m
wa
s
tes
ted
o
v
e
r
a
p
u
b
li
c
d
a
tab
a
se
c
o
n
sist
o
f
4
9
3
i
m
a
g
e
s.
Th
e
a
tt
a
in
e
d
re
c
o
g
n
it
i
o
n
ra
te
wa
s
(9
5
.
2
8
%
)
a
n
d
th
e
a
c
h
iev
e
d
m
in
i
m
u
m
e
q
u
a
l
e
rro
r
ra
te
(
EER
)
is
0
.
0
2
%
.
K
ey
w
o
r
d
s
:
C
en
tr
al
m
o
m
en
t c
o
ef
f
icien
ts
n
ea
r
est cla
s
s
if
ier
E
ar
r
ec
o
g
n
itio
n
Haa
r
wav
elet
tr
an
s
f
o
r
m
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
:
R
u
aa
I
s
am
Fad
h
i
l
Min
is
tr
y
o
f
ed
u
c
atio
n
B
ag
h
d
ad
,
I
r
aq
E
m
ail:
R
o
aa
ess
8
7
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
As
th
er
e
is
an
in
cr
ea
s
in
g
n
ee
d
to
au
t
o
m
atica
lly
r
ec
o
g
n
ize
in
d
iv
id
u
als,
m
a
n
y
m
et
h
o
d
s
ar
e
u
s
ed
f
o
r
p
er
s
o
n
al
id
e
n
tific
atio
n
,
a
n
d
it
h
as
b
ee
n
a
n
ef
f
icien
t
f
ield
o
f
r
esear
ch
o
v
e
r
th
e
last
d
ec
ad
e
[1
]
,
[
2
]
.
P
ass
wo
r
d
s
,
an
d
I
D
ca
r
d
s
r
ep
r
esen
ted
tr
a
d
itio
n
al
m
eth
o
d
s
f
o
r
p
e
r
s
o
n
al
id
en
tific
atio
n
,
b
u
t
th
ey
ca
n
b
e
p
u
r
lo
in
,
f
o
r
g
e
,
o
r
f
o
r
g
o
tt
en
,
wh
ile
b
io
m
etr
ic
m
e
th
o
d
h
as
m
an
y
ch
a
r
ac
ter
is
tics
,
s
u
ch
as:
u
n
iv
er
s
al,
u
n
iq
u
e
,
p
er
p
etu
al,
a
n
d
c
o
u
ld
b
e
m
ea
s
u
r
ed
[
3
]
-
[
5]
.
T
h
e
s
h
ap
e
o
f
th
e
o
u
ter
ea
r
k
n
o
wn
f
o
r
m
an
y
y
ea
r
s
as
a
v
alu
ab
le
r
eso
u
r
ce
f
o
r
p
er
s
o
n
al
id
en
tific
atio
n
b
y
c
r
im
in
al
in
v
esti
g
ato
r
s
,
Alp
h
o
n
s
e
B
er
till
o
n
t
h
e
Fre
n
ch
cr
im
in
o
lo
g
is
t
was
th
e
ea
r
lies
t
to
r
ec
o
g
n
ize
th
e
p
o
ten
tial
d
e
p
lo
y
m
en
t
o
f
ea
r
s
h
ap
e
as
d
is
tin
ctiv
e
ch
ar
ac
ter
is
tic
f
o
r
id
en
tif
y
in
g
h
u
m
a
n
s
,
m
o
r
e
th
an
a
ce
n
t
u
r
y
a
g
o
[
6
]
.
T
h
e
ea
r
ca
n
b
e
ca
p
tu
r
e
d
ea
s
ily
f
r
o
m
a
d
is
tan
ce
,
an
d
d
o
n
'
t
r
eq
u
i
r
e
a
p
er
s
o
n
to
en
tire
ly
b
e
co
o
p
er
atin
g
[
7
]
.
T
h
is
p
r
o
d
u
ce
s
ea
r
r
ec
o
g
n
itio
n
as
an
in
t
er
esti
n
g
tech
n
i
q
u
e
f
o
r
s
m
ar
t
m
o
n
ito
r
in
g
f
u
n
ctio
n
s
an
d
f
o
r
f
o
r
e
n
s
ic
im
ag
e
an
aly
s
is
.
I
t
is
wo
r
th
tak
in
g
in
to
c
o
n
s
id
er
atio
n
th
at
ea
r
im
ag
es
is
a
m
o
r
e
r
eliab
le
u
n
i
-
m
o
d
al
b
i
o
m
etr
ic
r
ec
o
g
n
itio
n
tech
n
iq
u
e
th
an
f
ac
e
b
io
m
etr
ic
r
ec
o
g
n
itio
n
tech
n
iq
u
es
,
b
asically
s
in
ce
th
e
ass
o
ciatio
n
o
f
ea
r
im
ag
e
with
a
g
iv
en
in
d
iv
id
u
al
is
v
er
y
d
if
f
icu
lt
in
f
ac
t,
m
o
s
t
o
f
in
d
iv
i
d
u
als
ar
e
n
o
t
c
a
pa
b
le
of
r
ec
o
g
n
iz
in
g
th
eir
o
wn
im
a
g
e
,
s
u
b
s
eq
u
e
n
tly
,
th
e
ea
r
d
at
ab
ases
d
o
not
r
eq
u
ir
e
b
ein
g
s
ec
u
r
ed
as
th
e
f
ac
e
d
atab
ases
,
s
in
ce
th
e
p
o
s
s
ib
ilit
y
o
f
attac
k
s
is
m
u
ch
lo
wer
i
n
g
[
8
]
,
an
d
it
is
r
eq
u
ir
e
less
co
m
p
u
tatio
n
tim
e
t
h
an
o
th
er
b
io
m
etr
ic
tech
n
iq
u
es,
s
in
ce
th
e
s
ize
o
f
ea
r
im
ag
es
ar
e
r
elativ
ely
s
m
all
[
9
]
.
Fu
r
th
er
m
o
r
e,
ea
r
s
h
ap
e
d
id
n
'
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
A
n
ea
r
r
ec
o
g
n
itio
n
s
ystem
b
a
s
ed
o
n
l
o
ca
l wa
ve
let
s
u
b
b
a
n
d
e
n
erg
y
d
is
tr
ib
u
tio
n
(
R
u
a
a
I
s
a
m
F
a
d
h
il
)
1213
af
f
ec
ted
b
y
ex
p
r
ess
io
n
,
m
o
d
e,
o
r
h
ea
lth
.
B
u
t,
r
ec
o
g
n
itio
n
s
y
s
tem
s
b
ased
o
n
ea
r
im
a
g
es
,
s
till
s
u
f
f
er
f
r
o
m
m
an
y
is
s
u
es
s
u
ch
as
illu
m
in
atio
n
,
p
o
s
e
,
an
d
o
b
s
tr
u
ctio
n
[
10
]
-
[
15
]
.
All
th
ese
ch
allen
g
es
s
h
o
u
ld
b
e
tak
en
in
co
n
s
id
er
atio
n
wh
e
n
d
e
s
ig
n
ea
r
r
ec
o
g
n
itio
n
s
y
s
tem
.
B
io
m
etr
ic
s
y
s
tem
s
b
ased
o
n
ea
r
im
ag
es
f
ac
i
n
g
m
an
y
ch
all
en
g
es
ca
n
b
e
g
r
o
u
p
ed
m
ain
ly
in
to
two
m
ain
p
ar
ts
,
f
ir
s
t
is
allo
ca
tin
g
ea
r
r
eg
io
n
an
d
elim
in
atin
g
u
n
wan
ted
s
k
in
a
n
d
h
air
ar
ea
.
Fu
r
th
er
m
o
r
e,
th
e
im
ag
es
ar
e
ca
p
tu
r
ed
in
d
if
f
er
e
n
t
illu
m
in
an
ce
cir
cu
m
s
tan
ce
s
wh
ich
p
r
o
d
u
ce
im
ag
es
with
m
an
y
p
r
o
b
lem
s
s
u
ch
as:
n
o
is
e,
b
lu
e
r
,
a
n
d
lo
w
illu
m
in
an
ce
,
w
h
ich
m
ak
es
allo
ca
t
in
g
ea
r
ar
ea
v
er
y
c
o
m
p
licated
.
T
h
e
s
ec
o
n
d
o
n
e
is
f
in
d
in
g
p
r
o
p
e
r
f
ea
tu
r
es
to
r
ep
r
esen
t
ea
r
im
ag
e
f
o
r
d
is
tin
g
u
i
s
h
in
g
in
d
iv
id
u
a
ls
.
I
n
th
is
p
ap
er
we
h
an
d
le
th
ese
ch
allen
g
es
b
y
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
ea
r
im
ag
es
to
im
p
r
o
v
e
t
h
e
ea
r
im
ag
e
d
ata
(
f
ea
tu
r
es)
th
r
o
w
s
u
p
p
r
ess
in
g
u
n
wan
ted
d
ata
(
s
u
r
r
o
u
n
d
in
g
s
k
in
an
d
h
air
r
eg
io
n
)
a
n
d
e
n
h
a
n
ce
m
en
t
o
f
s
o
m
e
im
p
o
r
tan
t
ea
r
im
ag
e
f
ea
tu
r
es
s
o
th
at
ea
r
r
ec
o
g
n
itio
n
s
y
s
tem
c
an
b
en
e
f
it
f
r
o
m
th
is
im
p
r
o
v
e
d
d
ata
in
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
d
ec
is
io
n
m
ak
in
g
s
tag
es.
r
ep
r
esen
tin
g
in
:
im
ag
e
en
h
an
cin
g
,
af
ter
th
at
im
ag
e
s
ize
n
o
r
m
aliza
tio
n
r
eq
u
ir
e
d
to
u
n
if
ied
f
ea
t
u
r
es
in
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tep
.
I
n
f
ea
t
u
r
e
ex
tr
ac
tio
n
th
e
lo
ca
l
s
p
atial
en
er
g
y
d
is
tr
ib
u
tio
n
o
f
wav
ele
t
s
u
b
-
b
an
d
s
o
f
ea
r
im
ag
e
is
ap
p
lied
,
to
d
ec
o
m
p
o
s
e
ea
r
im
ag
e
in
to
d
if
f
e
r
en
t
r
eso
lu
tio
n
s
.
Fo
r
r
ed
u
ci
n
g
th
e
n
u
m
b
er
o
f
wav
elet
co
ef
f
icien
ts
,
an
d
p
r
eser
v
ein
g
im
ag
e
in
f
o
r
m
atio
n
th
e
p
r
o
d
u
ce
d
im
ag
e
is
d
iv
id
e
d
in
t
o
b
lo
ck
es
with
o
v
e
r
lap
,
ce
n
tr
al
m
o
m
en
t
a
r
e
ca
lcu
lated
f
o
r
ea
ch
b
lo
ck
t
o
r
ep
r
esen
t
th
e
ea
r
im
ag
e
f
ea
tu
r
es.
T
h
e
s
u
g
g
ested
s
y
s
tem
co
u
ld
u
s
ed
as
a
to
o
l
f
o
r
e
x
tr
ac
tin
g
ea
r
r
eg
io
n
an
d
f
ea
tu
r
es
o
f
d
if
f
er
en
t
ea
r
im
ag
es
in
co
lo
r
s
,
s
h
ap
es,
an
d
s
ize.
T
h
e
p
ap
er
r
est
o
f
p
a
p
er
is
o
r
g
an
ized
as
f
o
llo
ws,
Sectio
n
2
d
is
cu
s
s
es
th
e
r
esear
ch
m
eth
o
d
o
lo
g
y
,
Sectio
n
3
d
escr
ib
es th
e
ex
p
er
im
e
n
tal
r
esu
lts
an
d
d
escu
s
s
io
n
,
an
d
f
in
ally
co
n
clu
s
io
n
a
r
e
p
r
o
v
id
ed
in
Se
ctio
n
4.
2.
RE
S
E
ARCH
M
E
T
HOD
Du
r
in
g
th
e
last
f
ew
y
ea
r
s
,
r
es
ea
r
ch
es
p
aid
a
lo
t
o
f
atten
tio
n
to
th
e
ea
r
b
io
m
etr
ic
s
y
s
tem
d
u
e
to
its
ch
ar
ac
ter
is
tics
.
R
ec
en
t
s
tu
d
ie
s
h
av
e
in
tr
o
d
u
ce
d
d
if
f
er
en
t
m
eth
o
d
s
f
o
r
b
io
m
etr
ic
r
ec
o
g
n
itio
n
.
Geo
m
etr
ical
m
ea
s
u
r
es
b
ased
o
n
ea
r
ed
g
e
i
m
ag
es
ar
e
u
s
ed
,
b
e
ca
u
s
e
o
f
its
in
v
ar
ian
t
to
p
ar
allel
m
o
v
e,
s
c
ale
an
d
r
o
tatio
n
,
th
e
f
ea
tu
r
e
v
ec
to
r
co
m
p
o
s
ed
o
f
m
u
ltip
le
g
eo
m
etr
ical
f
ea
tu
r
e,
s
u
ch
as
(
s
h
ap
e,
E
u
clid
ea
n
d
is
tan
ce
s
o
f
s
id
e
o
f
a
tr
ian
g
le,
an
d
a
n
g
les
o
f
a
tr
ian
g
le)
,
b
u
t
th
e
im
a
g
es
m
ay
s
u
f
f
er
f
r
o
m
a
p
r
o
b
le
m
with
th
e
o
u
ter
s
h
ap
e
o
f
th
e
ea
r
,
wh
ich
m
ay
ca
u
s
e
th
e
f
ailu
r
e
o
f
th
e
wh
o
le
s
y
s
tem
[
1
2
]
,
[
1
3
]
.
Oth
er
s
tu
d
ies
co
m
b
in
e
m
u
ltib
le
tech
n
iq
u
e
t
o
im
p
r
o
v
e
r
ec
o
g
n
itio
n
r
esu
lts
s
u
ch
as,
a
p
p
lin
g
o
f
a
b
ac
k
p
r
o
p
ag
atio
n
(
BP
)
ar
tific
ial
n
e
u
tr
al
n
etwo
r
k
with
g
eo
m
etr
ical
f
ea
tu
r
es
[
1
4
]
.
T
h
en
r
esear
ch
s
atten
d
ed
to
u
s
e
m
eth
o
d
s
f
o
r
ch
an
g
e
th
e
s
p
ac
e
an
d
d
ata
r
ep
r
esen
tatio
n
,
t
o
d
ec
r
ea
s
e
th
e
d
im
en
s
io
n
alities
,
o
r
to
c
h
o
o
s
e
o
n
ly
th
e
v
alu
ab
le
in
f
o
r
m
atio
n
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
.
A
co
m
b
in
atio
n
o
f
ellip
tical
lo
ca
l
b
in
ar
y
p
atter
n
o
p
er
ato
r
an
d
h
aa
r
wav
elets
tr
a
n
s
f
o
r
m
as
a
m
eth
o
d
f
o
r
ch
ar
ac
ter
izin
g
th
e
s
p
ec
if
ic
d
etails
o
f
th
e
two
d
im
en
s
io
n
al
ea
r
im
ag
es
in
[
1
5
]
wer
e
p
r
o
p
o
s
ed
,
th
is
ap
p
r
o
ac
h
is
b
ased
o
n
p
ix
el
in
f
o
r
m
atio
n
,
th
e
p
ix
els
o
f
th
e
ea
r
im
ag
e
ar
e
ar
r
an
g
ed
,
a
n
d
p
r
o
ce
s
s
ed
in
o
n
e
v
ec
to
r
,
wh
ile
th
e
s
ize
o
f
th
e
v
ec
to
r
r
ep
r
esen
te
d
b
y
th
e
to
tal
n
u
m
b
er
o
f
th
e
p
ix
els,
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
aly
s
is
(
PC
A
)
[
1
6
]
,
co
lo
r
s
p
ac
es f
u
s
io
n
[
1
7
]
,
2
D
G
ab
o
r
f
ilter
[
1
8
]
ar
e
s
im
ilar
co
m
m
o
n
tech
n
iq
u
es.
T
h
is
p
ap
er
p
r
o
d
u
ce
s
an
au
to
m
ated
ea
r
r
ec
o
g
n
itio
n
s
y
s
tem
o
f
b
o
t
h
s
p
atial
a
n
d
g
eo
m
etr
ical
f
ea
tu
r
es
.
T
h
er
e
ar
e
th
r
ee
s
tag
es
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
First,
p
r
ep
r
o
ce
s
s
in
g
is
ap
p
lied
to
allo
ca
te
e
ar
r
eg
io
n
an
d
u
n
if
y
ea
r
im
ag
e
s
ize
in
o
r
d
er
to
im
p
r
o
v
e
th
e
f
ea
tu
r
e
v
ec
to
r
.
Nex
t,
ex
tr
ac
tin
g
th
e
f
ea
tu
r
es b
y
a
p
p
l
y
2
-
D
Haa
r
wav
elet
tr
an
s
f
o
r
m
,
th
e
n
,
im
ag
e
p
o
r
tio
n
in
g
in
to
b
lo
c
k
es
with
o
v
er
la
p
f
o
r
lo
ca
l
f
ea
tu
r
e
e
x
tr
ac
tio
n
in
o
r
d
er
to
g
en
er
ate
s
tatis
t
ical
n
o
r
m
to
b
u
ild
th
e
f
ea
tu
r
e
v
ec
to
r
.
Fin
ally
,
c
o
m
p
ar
es
th
e
ex
tr
ac
ted
f
ea
t
u
r
e
s
et
(
v
ec
to
r
)
with
th
e
f
ea
tu
r
e
s
ets
th
at
ar
e
alr
ea
d
y
ex
tr
ac
ted
f
r
o
m
tr
ain
in
g
s
am
p
le
s
an
d
s
av
ed
as
tem
p
late
v
ec
to
r
s
in
a
d
atab
ase
to
d
ef
in
e
th
e
id
e
n
tity
o
r
au
th
en
tic
ity
o
f
a
p
e
r
s
o
n
wh
o
s
e
ea
r
is
b
e
in
g
test
ed
as sh
o
wn
in
F
ig
u
r
e
1
.
2
.
1
.
P
re
pro
ce
s
s
ing
Pr
ep
r
o
ce
s
s
in
g
is
an
im
p
o
r
tan
t
s
tag
e
th
at
af
ac
t
th
e
o
u
tco
m
in
g
d
ata,
an
d
it
is
co
n
s
id
er
to
b
e
a
ch
allen
g
in
g
o
n
e,
s
o
it
r
eq
u
ir
es
m
an
y
s
tep
s
to
o
v
er
co
m
e
th
e
a
r
tifa
ct
in
th
e
ac
q
u
ir
ed
im
ag
e.
T
h
e
in
v
o
lv
e
d
s
tep
s
o
f
th
is
s
tag
e
ar
e
th
e
f
o
llo
win
g
s
.
2
.
1
.
1
.
Allo
ca
t
io
n
o
f
ea
r
re
g
io
n
T
h
is
is
an
im
p
o
r
tan
t
s
tep
a
n
d
th
e
m
o
s
t
ch
allen
g
in
g
s
tep
;
it
aim
s
to
d
ef
in
e
th
e
ea
r
ar
ea
f
r
o
m
all
s
u
r
r
o
u
n
d
in
g
r
eg
i
o
n
s
.
T
h
e
ac
c
u
r
ac
y
o
f
th
e
ea
r
r
eg
io
n
allo
ca
tio
n
p
r
o
ce
s
s
g
r
ea
tly
af
f
ec
ts
th
e
wh
o
le
p
r
o
ce
s
s
o
f
id
en
tific
atio
n
o
r
v
er
if
icatio
n
t
ask
.
T
h
e
allo
ca
tio
n
p
r
o
ce
s
s
im
p
lies
th
e
f
o
llo
win
g
im
ag
e
p
r
o
ce
s
s
in
g
s
tep
s
;
it
i
s
co
n
s
is
t o
f
th
e
s
tep
s
g
iv
en
.
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
2
1
2
-
1
2
1
9
1214
Fig
u
r
e
1
.
T
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
lay
o
u
t
a)
Cubi
c
s
pli
ne
T
h
e
o
r
ig
in
al
ea
r
im
ag
e
is
ca
p
t
u
r
ed
as
p
ar
t
o
f
th
e
s
id
e
p
ar
t
o
f
th
e
f
ac
e;
it
h
o
ld
s
u
n
wan
ted
a
r
ea
wh
ich
in
cr
ea
s
es
th
e
r
eq
u
ir
ed
co
m
p
u
t
atio
n
co
m
p
lex
ity
an
d
s
ca
le
d
o
wn
th
e
ac
cu
r
ac
y
o
f
m
atc
h
in
g
.
I
n
o
r
d
e
r
to
en
h
a
n
ce
th
e
ea
r
r
eg
io
n
allo
ca
tio
n
tas
k
a
cu
b
ic
s
p
lin
e
i
n
ter
p
o
latio
n
was
ap
p
lied
.
C
u
b
ic
s
p
lin
e
in
ter
p
o
latio
n
is
a
p
iece
wis
e
co
n
tin
u
o
u
s
cu
r
v
e,
w
ith
co
n
tin
u
o
u
s
d
er
iv
ativ
es o
f
f
i
r
s
t a
n
d
s
ec
o
n
d
o
r
d
er
[
1
9
]
.
C
u
b
ic
s
p
lin
e
p
r
o
d
u
ce
s
a
s
m
o
o
th
ea
r
im
a
g
e
in
s
u
ch
a
way
th
at
we
ca
n
co
r
r
ec
tly
d
e
f
in
e
s
k
in
r
eg
i
o
n
f
r
o
m
u
n
wan
t
ed
r
eg
io
n
(
e.
g
.
h
air
r
eg
io
n
)
.
Fig
u
r
e
s
2
(
a
)
an
d
(
b
)
s
h
o
ws th
e
s
m
o
o
th
n
ess
o
f
th
e
o
u
tp
u
t im
ag
e
a
f
ter
ap
p
ly
in
g
t
h
e
cu
b
ic
s
p
lin
e.
(
a)
(
b
)
Fig
u
r
e
2
.
I
m
ag
e
s
m
o
o
th
in
g
;
(
a
)
o
r
ig
in
al
im
a
g
e,
(
b
)
cu
b
ic
s
p
lin
e
im
ag
e
b)
E
a
r
im
a
g
e
enha
ncem
ent
us
ing
his
t
o
g
ra
m
equa
liza
t
io
n
T
h
e
o
r
ig
in
al
ea
r
im
ag
e
is
en
h
an
ce
d
u
s
in
g
h
is
to
g
r
a
m
eq
u
a
lizatio
n
m
eth
o
d
.
T
h
is
m
eth
o
d
lead
s
to
r
ed
is
tr
ib
u
te
th
e
o
r
ig
in
al
im
ag
e
h
is
to
g
r
am
in
o
r
d
e
r
to
o
b
tain
m
o
r
e
co
n
tr
asted
im
ag
e
wh
o
s
e
h
is
to
g
r
am
is
wid
er
[
2
0
]
,
[
2
1
]
.
T
h
e
ex
p
an
s
io
n
o
f
lu
m
in
o
s
ity
d
is
tr
ib
u
tio
n
is
p
r
o
cu
r
ed
b
y
g
ath
e
r
in
g
th
e
a
d
ja
ce
n
t
g
r
ey
v
al
u
es
to
s
p
ec
if
ic
v
alu
e.
So
,
th
e
g
r
ey
l
ev
els
n
u
m
b
er
o
f
th
e
e
n
h
an
ce
d
im
ag
e
is
less
th
an
th
e
g
r
ey
lev
els
n
u
m
b
er
th
at
b
elo
n
g
s
to
th
e
o
r
ig
in
al
im
a
g
e.
T
h
is
s
tep
h
as
ef
f
icien
t
ef
f
ec
t
to
d
is
cr
im
in
ate
th
e
ea
r
r
eg
io
n
s
f
r
o
m
th
e
s
u
r
r
o
u
n
d
in
g
s
k
in
ar
ea
as sh
o
w
n
in
th
e
F
ig
u
r
e
3
(
a
)
.
c)
B
ina
riza
t
io
n
B
i
n
a
r
i
za
t
i
o
n
is
a
p
r
o
c
es
s
o
f
t
r
a
n
s
f
o
r
m
i
n
g
a
g
r
a
y
i
m
a
g
e
t
o
a
b
i
n
a
r
y
i
m
a
g
e
w
h
i
c
h
c
o
n
t
ai
n
s
o
n
l
y
t
w
o
c
l
a
s
s
es
,
b
l
a
c
k
(
p
i
x
e
l
v
a
l
u
e
=
0
)
,
a
n
d
w
h
i
t
e
(
p
i
x
e
l
v
a
l
u
e
=
1
)
.
S
i
n
c
e
t
h
e
i
m
a
g
e
b
r
i
g
h
t
n
es
s
w
a
s
e
n
h
a
n
c
e
d
,
t
h
e
b
i
n
a
r
i
z
a
t
i
o
n
p
r
o
c
e
s
s
b
e
c
o
m
e
s
i
m
p
l
e
;
w
h
e
r
e
as
t
h
e
e
n
h
a
n
c
e
d
i
m
a
g
e
c
o
n
s
is
ts
o
f
s
e
p
a
r
a
t
e
d
in
t
e
n
s
i
t
y
le
v
e
l
s
t
h
a
t
f
a
c
i
l
it
a
t
e
d
t
h
e
b
i
n
a
r
iz
a
t
i
o
n
p
r
o
c
e
s
s
.
I
n
t
h
e
p
r
o
p
o
s
e
d
s
y
s
t
e
m
t
h
e
b
i
n
a
r
i
z
at
i
o
n
p
r
o
c
es
s
d
e
p
e
n
d
s
o
n
t
h
e
v
al
u
e
o
f
g
l
o
b
a
l
t
h
r
e
s
h
o
l
d
;
it
w
as
s
e
le
c
te
d
d
e
p
e
n
d
i
n
g
o
n
t
h
e
h
i
g
h
es
t
in
t
e
n
s
i
t
y
f
o
u
n
d
i
n
t
h
e
cl
o
s
es
t
r
e
g
i
o
n
t
o
t
h
e
c
a
p
t
u
r
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
A
n
ea
r
r
ec
o
g
n
itio
n
s
ystem
b
a
s
ed
o
n
l
o
ca
l wa
ve
let
s
u
b
b
a
n
d
e
n
erg
y
d
is
tr
ib
u
tio
n
(
R
u
a
a
I
s
a
m
F
a
d
h
il
)
1215
d
e
v
i
c
e
a
s
s
h
o
w
n
i
n
F
i
g
u
r
e
3
(
a
)
.
W
h
e
r
e
m
a
x
r
e
p
r
e
s
e
n
t
s
t
h
e
m
a
x
i
m
u
m
i
n
t
e
n
s
i
t
y
v
a
l
u
e
a
n
d
t
h
r
i
s
t
h
e
t
h
r
e
s
h
o
l
d
v
a
l
u
e
.
′
(
,
)
=
{
1
(
,
)
≥
−
ℎ
0
ℎ
(
1
)
d)
E
a
r
re
g
io
n lo
ca
liza
t
io
n
T
h
e
p
u
r
p
o
s
e
o
f
th
is
s
tep
is
to
ex
tr
ac
t
ea
r
r
e
g
io
n
,
with
o
u
t
u
n
n
ec
ess
ar
y
p
ar
ts
lik
e
s
k
in
,
a
n
d
h
air
p
ar
ts
.
Firstl
y
,
m
ak
e
a
s
ca
n
n
in
g
f
o
r
t
h
e
co
o
r
d
i
n
ates
o
f
a
s
k
in
a
r
ea
in
o
r
d
er
t
o
f
in
d
th
e
m
in
im
u
m
an
d
m
ax
im
u
m
p
o
i
n
ts
in
x
an
d
y
-
co
o
r
d
in
ates
(
f
ir
s
t
an
d
last
h
it
to
wh
ite
p
ix
el)
,
as
s
h
o
wn
in
Fig
u
r
e
3
(
b
)
.
Seco
n
d
clip
p
in
g
ea
r
r
eg
io
n
ac
co
r
d
in
g
to
th
e
r
ec
tan
g
le
r
e
p
r
esen
ted
b
y
th
e
allo
ca
te
d
p
o
in
ts
as sh
o
wn
in
Fig
u
r
e
3
(
c)
.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
E
a
r
r
eg
i
o
n
s
eg
m
en
ta
tio
n
;
(
a)
h
is
to
g
r
am
eq
u
aliza
tio
n
im
ag
e,
(
b
)
b
in
ar
ized
im
a
g
e,
(
c)
cr
o
p
p
ed
ea
r
r
eg
i
o
n
2
.
1
.
2
.
I
m
a
g
e
s
ize
no
rm
a
liza
t
i
o
n
E
ar
im
ag
e
s
ize,
an
d
s
h
a
p
e
s
u
f
f
er
f
r
o
m
m
an
y
ch
an
g
es
d
u
r
in
g
im
ag
e
ca
p
tu
r
in
g
,
w
h
ich
ca
u
s
e
s
er
io
u
s
p
r
o
b
lem
s
in
d
esig
n
in
g
ea
r
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
.
I
n
th
e
i
m
ag
e
d
atab
ase
w
h
en
we
o
b
s
e
r
v
in
g
t
h
e
ea
r
im
ag
e
s
am
p
les
we
ca
n
n
o
tice
m
an
y
s
ize
v
ar
iatio
n
s
in
th
e
c
o
llect
ed
ea
r
im
a
g
e
p
atter
n
s
.
Fu
r
th
er
m
o
r
e,
ea
r
im
a
g
e
cr
o
p
p
in
g
ca
u
s
es
m
o
r
e
v
ar
iati
o
n
in
ea
r
im
ag
es.
So
s
ize
n
o
r
m
aliza
tio
n
is
a
n
ec
ess
ar
y
s
tep
f
o
r
ex
cl
u
d
in
g
s
ize
in
v
ar
ian
ce
o
n
ea
r
im
ag
es
b
e
f
o
r
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
I
t
is
m
ap
p
ed
in
to
a
s
tan
d
ar
d
win
d
o
w
s
ize
as
s
h
o
wn
i
n
F
ig
u
r
e
4
(
a)
.
T
o
a
p
p
ly
th
is
m
a
p
p
in
g
th
e
af
f
in
e
t
r
an
s
f
o
r
m
ati
o
n
tech
n
i
q
u
e
is
u
s
ed
o
n
th
e
e
ar
im
ag
es
with
th
e
B
ilin
ea
r
I
n
ter
p
o
latio
n
al
g
o
r
ith
m
u
s
in
g
f
o
u
r
n
ea
r
est n
eig
h
b
o
r
s
f
o
r
in
ter
p
o
latio
n
[
2
1
]
.
2
.
2
.
F
ea
t
ure
ex
t
ra
ct
io
n
T
h
e
m
ajo
r
ch
allen
g
e
f
o
r
b
io
m
etr
ic
s
y
s
tem
s
th
at
estab
lis
h
ed
o
n
co
m
p
u
ter
v
is
io
n
is
t
o
ex
tr
ac
t
s
u
ch
f
ea
tu
r
es
th
at
will
c
h
ar
ac
ter
ize
in
d
iv
id
u
al
ea
r
s
in
a
d
is
tin
ctiv
e
tech
n
iq
u
e.
Dis
cr
ete
wa
v
elet
tr
an
s
f
o
r
m
(
DW
T
)
is
co
n
s
id
er
ed
to
b
e
o
n
e
o
f
th
e
co
m
m
o
n
u
s
ed
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
i
n
c
o
m
p
u
te
r
v
i
s
io
n
f
o
r
o
b
ject
d
etec
tio
n
,
an
aly
s
is
an
d
class
if
icatio
n
[
2
2
]
.
T
h
e
I
m
p
lem
e
n
tatio
n
o
f
DW
T
as
an
im
ag
e
p
r
o
ce
s
s
in
g
m
eth
o
d
u
s
e
d
f
o
r
p
r
o
d
u
ci
n
g
th
e
tr
an
s
f
o
r
m
a
tio
n
v
alu
es
(
wav
elet
co
ef
f
ici
en
t)
.
I
n
th
is
s
tag
e
th
e
cr
itical
p
o
in
t
is
h
o
w
to
in
ter
p
r
et
th
e
wav
elet
co
ef
f
i
cie
n
t
to
s
y
m
b
o
lize
in
d
iv
id
u
al
f
o
r
class
if
icatio
n
o
r
d
etec
tio
n
.
I
n
th
is
s
tu
d
y
,
wav
elet
co
ef
f
icien
ts
will
b
e
u
s
ed
in
th
e
p
r
o
ce
s
s
in
g
an
d
a
n
aly
s
es
o
f
ea
r
im
ag
es
s
in
ce
DW
T
d
ec
o
m
p
o
s
e
ea
r
im
ag
e
in
t
o
v
ar
ian
t
s
tag
es
o
f
r
eso
lu
tio
n
.
B
y
ap
p
lin
g
DW
T
,
we
ca
n
p
r
o
d
u
ce
a
n
ew
f
ea
tu
r
e
s
et
d
ep
en
d
in
g
o
n
wav
elet
co
ef
f
icien
t
an
aly
s
es
o
f
.
T
h
e
tech
n
iq
u
e
h
elp
s
in
r
ed
u
cin
g
th
e
r
eq
u
ir
ed
co
e
f
f
icien
ts
f
o
r
f
ea
tu
r
e
v
ec
to
r
s
.
T
h
e
in
v
o
lv
ed
s
tep
s
f
o
r
d
eter
m
in
in
g
t
h
e
s
p
atial
d
is
tr
ib
u
tio
n
o
f
s
u
b
-
b
an
d
wav
elet
en
er
g
y
a
r
e
th
e
f
o
llo
win
g
s
as
s
h
o
wn
in
Fig
u
r
e
4
:
−
Step
1
:
ap
p
ly
2
-
D
Haa
r
wav
e
let
tr
an
s
f
o
r
m
in
o
r
d
er
d
ec
o
m
p
o
s
e
ea
r
s
ig
n
al
in
to
f
o
u
r
s
u
b
-
im
ag
es,
wh
er
e
L
L
r
ep
r
esen
ts
th
e
lo
w
f
r
eq
u
en
cy
(
ap
p
r
o
x
im
atio
n
)
s
u
b
-
b
a
n
d
,
HL
r
ef
er
s
to
h
ig
h
f
r
eq
u
e
n
cy
co
m
p
o
n
en
t
alo
n
g
th
e
h
o
r
izo
n
tal
d
ir
ec
tio
n
,
L
H
r
ef
e
r
s
to
h
i
g
h
f
r
eq
u
en
cy
co
m
p
o
n
e
n
t
alo
n
g
t
h
e
v
e
r
tical
d
ir
ec
tio
n
a
n
d
HH
r
ep
r
esen
ts
th
e
d
iag
o
n
al
h
i
g
h
f
r
eq
u
e
n
cy
co
m
p
o
n
e
n
t.
T
h
e
b
an
d
L
H,
HL
a
n
d
HH
ar
e
ca
lled
d
etail
(
o
r
wav
elet)
s
u
b
-
b
a
n
d
s
.
A
f
ter
f
i
r
s
t
wav
elet
d
ec
o
m
p
o
s
itio
n
,
th
e
ap
p
r
o
x
im
atio
n
(
L
L
)
s
u
b
-
b
an
d
is
f
ed
f
o
r
n
ex
t
wav
elet
d
ec
o
m
p
o
s
itio
n
.
T
h
en
,
th
e
s
ec
o
n
d
L
L
s
u
b
-
b
an
d
is
s
u
b
m
itted
ag
ain
f
o
r
n
ex
t
d
ec
o
m
p
o
s
itio
n
is
s
h
o
wn
in
F
ig
u
r
e
4
(
b
)
.
−
Step
2
: th
e
wav
elet
im
ag
e
is
d
i
v
id
ed
in
to
b
lo
ck
s
with
o
v
er
lap
as d
escr
ib
ed
in
F
ig
u
r
e
4
(
c
)
.
−
Step
3
:
Gen
er
ate
s
tatis
tical
n
o
r
m
to
b
u
ild
t
h
e
f
ea
tu
r
e
v
ec
to
r
o
f
th
e
im
ag
e.
I
m
ag
e
m
o
m
en
ts
ar
e
u
tili
tar
ian
f
o
r
d
escr
ib
in
g
o
b
jects
af
ter
s
e
g
m
en
tatio
n
[
2
3
]
.
T
h
e
ad
o
p
ted
m
o
m
en
ts
ar
e
th
e
ce
n
t
r
al
m
o
m
en
ts
in
s
tead
o
f
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
2
1
2
-
1
2
1
9
1216
th
e
o
r
d
i
n
ar
y
m
o
m
e
n
ts
.
T
h
ey
a
r
e
co
m
p
u
ted
i
n
ter
m
s
o
f
d
e
v
ia
tio
n
s
f
r
o
m
th
e
m
ea
n
in
s
tead
f
r
o
m
th
e
o
r
ig
in
.
T
h
e
f
u
n
ctio
n
o
f
s
u
ch
m
o
m
en
ts
is
,
m
o
s
tly
,
s
elec
ted
to
h
av
e
s
o
m
e
attr
ac
tiv
e
p
r
o
p
er
ty
o
r
f
ea
t
u
r
e.
‖
‖
=
1
×
∑
∑
(
(
,
)
−
)
(
(
,
)
−
)
−
1
=
0
−
1
=
0
(
2
)
wh
er
e
,
0
<
p
<
1
.
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
Featu
r
e
ex
tr
ac
tio
n
;
(
a)
s
ize
n
o
r
m
alize
d
im
a
g
e,
(
b
)
3
-
Pas
s
es D
W
T
,
(
c)
p
ar
titi
o
n
in
g
s
u
b
-
b
a
n
d
to
o
v
er
lap
p
i
n
g
b
l
o
ck
s
2
.
3
.
M
a
t
ching
a
nd
decisi
o
n m
a
k
ing
I
n
th
is
s
tag
e,
an
in
p
u
t
ea
r
i
m
ag
e
is
f
ee
d
ed
to
th
e
s
y
s
tem
to
ca
lcu
late
th
e
d
eg
r
ee
o
f
m
atch
in
g
.
T
h
e
in
p
u
t
ea
r
im
ag
e
is
p
r
o
ce
s
s
ed
to
o
b
tain
ed
f
ea
tu
r
es
lis
t
th
at
will
b
e
s
tr
aig
h
tly
m
atch
ed
with
th
e
p
r
ev
io
u
s
ly
s
av
ed
tem
p
lates
u
s
in
g
KNN
c
lass
if
ier
(
k
-
n
ea
r
est
n
eig
h
b
o
r
)
,
it
is
co
n
s
id
er
ed
as
wid
ely
k
n
o
wn
alg
o
r
ith
m
s
f
o
r
s
u
p
er
v
is
ed
lear
n
in
g
in
p
atter
n
r
ec
o
g
n
itio
n
an
d
,
class
if
icatio
n
.
KNN
class
if
ier
h
as
m
an
y
f
ea
t
u
r
es:
ef
f
icien
cy
,
s
im
p
licity
,
i
n
t
u
itiv
en
ess
an
d
c
o
m
p
etitiv
e
class
if
icatio
n
f
u
n
ctio
n
ality
in
m
an
y
a
r
ea
[
2
4
]
.
T
h
e
KNN
class
if
ier
is
u
s
es
b
asically
th
e
eu
clid
ea
n
d
is
tan
ce
f
o
r
c
o
m
p
ar
i
n
g
s
am
p
les,
a
test
s
am
p
le
(
in
p
u
t
o
n
e)
a
n
d
th
e
s
et
o
f
t
r
ain
in
g
s
am
p
les
(
s
to
r
ed
tem
p
lates)
wit
h
K
v
alu
e
e
q
u
al
t
o
o
n
e.
I
n
1
-
n
ea
r
est
n
eig
h
b
o
r
alg
o
r
ith
m
,
th
e
p
o
r
ten
d
class
o
f
te
s
t
s
am
p
le
x
is
ad
ju
s
t
eq
u
al
to
th
e
ac
tu
al
class
ω
o
f
i
ts
n
ea
r
est n
eig
h
b
o
r
,
wh
er
e
mi
is
a
clo
s
est n
eig
h
b
o
r
to
x
if
th
e
d
is
tan
ce
:
(
,
)
=
{
(
,
)
}
(
3
)
3.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
T
h
e
d
ataset
u
s
ed
f
o
r
test
in
g
i
n
th
is
r
esear
ch
is
tak
en
f
r
o
m
Delh
i
ea
r
im
ag
e
d
atab
ase
th
at
is
p
u
b
licly
av
ailab
le.
T
h
e
ea
r
im
a
g
es
ar
e
o
b
tain
ed
f
r
o
m
a
d
is
tan
ce
(
to
u
ch
less
)
.
T
h
e
d
atab
ase
is
o
b
tain
ed
f
r
o
m
1
2
5
in
d
iv
id
u
als,
an
d
ea
ch
o
n
e
h
as
at
least
th
r
ee
ea
r
im
a
g
es.
T
h
e
r
eso
lu
tio
n
o
f
th
e
o
b
tain
ed
i
m
ag
es
is
2
7
2
×
2
0
4
p
ix
els,
an
d
ar
e
a
v
ailab
le
in
b
m
p
f
o
r
m
at.
I
n
t
h
e
f
o
llo
win
g
e
x
p
er
im
en
ts
,
th
e
d
ata
s
et
h
ad
b
ee
n
d
iv
id
e
d
in
t
o
two
s
ets,
o
n
e
f
o
r
tr
ain
i
n
g
,
an
d
th
e
o
th
er
f
o
r
test
in
g
.
A
f
ir
s
t
s
et
co
n
s
is
t
o
f
2
8
0
s
am
p
les
h
ad
b
ee
n
u
s
ed
f
o
r
tr
ain
in
g
to
b
u
ild
th
e
n
ea
r
est
n
eig
h
b
o
r
(
NN
)
class
if
ier
,
an
d
th
e
s
ec
o
n
d
s
et
co
n
s
is
t
o
f
2
1
3
s
am
p
les
h
ad
b
e
en
u
s
ed
f
o
r
test
in
g
th
e
p
r
o
p
o
s
ed
s
y
s
tem
.
All
th
e
im
ag
es
ar
e
p
r
ep
r
o
ce
s
s
ed
an
d
th
e
ea
r
r
eg
io
n
ar
e
allo
ca
ted
f
r
o
m
th
e
ac
q
u
ir
ed
im
ag
e
as
s
h
o
wn
in
F
ig
u
r
e
5
,
wh
er
e
F
ig
u
r
e
5
(
a)
r
ep
r
esen
t
th
e
a
q
u
ir
e
d
im
ag
e
,
F
ig
u
r
e
5
(
b
)
r
ep
r
esen
t
th
e
im
ag
e
af
ter
ap
p
l
y
in
g
cu
b
i
c
s
p
lin
e
f
o
r
im
ag
e
s
m
o
o
t
h
,
F
ig
u
r
e
5
(
c
)
h
is
to
g
r
am
e
q
u
aliza
tio
n
im
ag
e
to
ad
j
u
s
t
th
e
b
r
ig
h
t
n
ess
,
F
ig
u
r
e
5
(
d
)
co
n
v
er
tin
g
t
o
b
in
r
y
im
ag
e
to
allo
ca
te
th
e
ea
r
r
eg
i
o
n
,
F
ig
u
r
e
5
(
e
)
cr
o
p
p
ed
im
a
g
e.
3
.
1
.
I
dentif
ica
t
io
n (
re
c
o
g
nitio
n)
re
s
ults
T
h
e
p
er
f
o
r
m
an
ce
o
f
id
e
n
tific
atio
n
s
y
s
tem
is
ev
alu
ated
b
y
ap
p
ly
in
g
th
e
co
r
r
ec
t
r
ec
o
g
n
itio
n
r
ate
(
C
R
R
)
;
wh
ich
r
ep
r
esen
ted
th
e
r
atio
b
etwe
en
th
e
n
u
m
b
er
o
f
co
r
r
ec
ts
r
ec
o
g
n
itio
n
d
ec
is
io
n
s
(
n
c
)
an
d
th
e
to
tals
n
u
m
b
er
o
f
tr
ie
d
test
s
(
n
T
):
=
(
4
)
T
ab
le
s
1
,
2
an
d
3
illu
s
tr
ates
th
e
attain
ed
r
ec
o
g
n
itio
n
r
esu
lts
wh
en
ap
p
ly
in
g
s
tatis
tical
n
o
r
m
3
/4
o
n
th
e
ea
r
im
ag
e
.
T
h
e
atten
d
e
d
r
esu
lts
s
h
o
ws
th
at
th
e
r
ec
o
g
n
itio
n
r
ate
is
in
c
r
ea
s
ed
with
r
esp
ec
t
to
in
c
r
ea
s
in
g
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
A
n
ea
r
r
ec
o
g
n
itio
n
s
ystem
b
a
s
ed
o
n
l
o
ca
l wa
ve
let
s
u
b
b
a
n
d
e
n
erg
y
d
is
tr
ib
u
tio
n
(
R
u
a
a
I
s
a
m
F
a
d
h
il
)
1217
wav
elet
p
ass
es,
in
cr
ea
s
in
g
b
lo
ck
n
u
m
b
e
r
ca
u
s
es
d
elay
in
th
e
s
y
s
tem
an
d
d
is
p
er
s
io
n
in
th
e
b
lo
ck
in
f
o
r
m
atio
n
,
wh
ile
in
cr
ea
s
in
g
o
v
e
r
lap
r
atio
lead
to
in
cr
ea
s
in
g
b
lo
ck
s
ize.
(
a)
(
b
)
(
c)
(
d
)
(
e)
Fig
u
r
e
5
.
T
h
e
r
esu
lts
o
f
ea
r
r
e
g
io
n
allo
ca
tio
n
;
(
a)
o
r
ig
in
al
im
ag
e,
(
b
)
cu
b
ic
s
p
lin
e
im
a
g
e,
(
c
)
h
is
to
g
r
am
eq
u
aliza
tio
n
im
ag
e,
(
d
)
co
n
v
er
tin
g
to
b
in
r
y
im
ag
e
,
(
e)
c
r
o
p
p
e
d
im
ag
e
T
ab
le
1
.
T
h
e
r
ec
o
g
n
itio
n
r
ate
f
o
r
d
if
f
e
r
en
t w
av
elet
p
ass
es with
b
lo
ck
s
ize
(
9
×9
)
a
n
d
o
v
er
lap
r
atio
(
0
.
2
)
W
a
v
e
l
e
t
P
a
sses
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
1
-
p
a
ss
8
6
.
3
2
2
-
p
a
ss
8
7
.
2
6
3
-
p
a
ss
9
5
.
2
8
T
ab
le
2
.
T
h
e
r
ec
o
g
n
itio
n
r
ate
f
o
r
d
if
f
e
r
en
t b
l
o
ck
s
ize
B
l
o
c
k
S
i
z
e
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
(
%)
5
×
5
8
2
.
0
7
7
×
7
8
4
.
9
9
×
9
9
5
.
2
8
1
1
×
1
1
9
0
.
5
6
1
3
×1
3
9
2
.
4
5
T
ab
le
3
.
T
h
e
r
ec
o
g
n
itio
n
r
ate
f
o
r
d
if
f
e
r
en
t o
v
er
lap
r
atio
O
v
e
r
l
a
p
R
a
t
i
o
R
e
c
o
g
n
i
t
i
o
n
R
a
t
e
0
.
0
8
5
.
3
7
0
.
1
9
1
.
0
3
0
.
2
0
.
3
9
5
.
2
8
9
2
.
0
4
0
.
5
9
0
.
0
9
3
.
2
.
Ver
if
ica
t
io
n (
a
uthent
ica
t
io
n)
re
s
ults
T
h
e
r
ec
eiv
er
o
p
e
r
atin
g
ch
ar
ac
ter
is
tic
(
R
O
C
)
cu
r
v
e
is
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
v
er
if
icatio
n
s
y
s
tem
,
it
p
er
f
o
r
m
s
th
e
f
alse
r
ejec
tio
n
r
ate
(
FR
R
)
ag
ain
s
t
th
e
f
alse
ac
ce
p
tan
ce
r
ate
(
FAR
)
at
v
ar
io
u
s
th
r
esh
o
l
d
s
o
n
th
e
m
atch
in
g
s
co
r
e.
T
h
e
s
y
s
tem
th
r
esh
o
ld
v
alu
e
is
o
b
tain
e
d
ac
co
r
d
in
g
to
th
e
eq
u
a
l
er
r
o
r
r
ate
(
EER
)
cr
iter
ia,
wh
er
e
FAR
=
FR
R
.
=
,
=
(
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.
24
,
No
.
2
,
No
v
em
b
er
2
0
2
1
:
1
2
1
2
-
1
2
1
9
1218
w
h
er
e,
A
is
th
e
n
u
m
b
er
o
f
s
u
cc
ess
f
u
l
au
th
en
ticatio
n
s
b
y
im
p
o
s
to
r
s
,
B
is
th
e
n
u
m
b
er
o
f
attem
p
ts
at
au
th
en
ticatio
n
b
y
u
n
a
u
th
o
r
ize
d
u
s
er
s
,
C
is
th
e
n
u
m
b
er
o
f
f
ailed
attem
p
ts
at
au
t
h
en
ticatio
n
b
y
a
u
th
o
r
ize
d
u
s
er
s
,
an
d
D
is
th
e
n
u
m
b
er
o
f
attem
p
ts
at
au
th
en
ticatio
n
b
y
g
en
u
in
e
u
s
er
s
.
Fu
r
th
er
m
o
r
e
a
cc
u
r
ac
y
p
ar
am
eter
can
b
e
u
s
ed
to
ev
alu
ate
th
e
p
e
r
f
o
r
m
a
n
ce
o
f
b
io
m
etr
ic
s
y
s
tem
s
(
i.e
.
,
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
t
p
r
ed
ictio
n
s
)
an
d
it d
o
es n
o
t
n
ee
d
to
tak
e
i
n
to
co
n
s
id
er
atio
n
wh
at
is
p
o
s
itiv
e
(
P
)
an
d
wh
at
is
n
e
g
ativ
e
(
N
)
[
2
5
]
,
[
2
6
].
=
+
+
(
6
)
w
h
er
e
tr
u
e
p
o
s
itiv
e
(
TP
)
is
th
e
n
u
m
b
er
o
f
g
e
n
u
in
e
u
s
er
s
th
at
id
en
tifie
d
co
r
r
ec
tly
,
tr
u
e
n
e
g
ativ
e
(
TN
)
is
th
e
n
u
m
b
er
o
f
im
p
o
s
to
r
u
s
er
s
attem
p
ts
th
at
r
ejec
ted
b
y
th
e
s
y
s
tem
.
T
ab
le
4
s
h
o
ws
F
AR
,
FR
R
an
d
ac
cu
r
ac
y
v
alu
es
f
o
r
d
if
f
e
r
en
t
th
r
esh
o
ld
v
alu
es,
th
e
v
er
if
icatio
n
r
esu
lts
is
p
er
f
o
r
m
ed
u
s
in
g
th
e
b
est
p
ar
am
eter
s
s
etu
p
th
at
lead
to
b
est
r
ec
o
g
n
itio
n
r
ate.
T
h
e
R
OC
cu
r
v
e
b
etwe
en
th
e
FAR
an
d
FR
R
with
v
ar
io
u
s
th
r
esh
o
ld
s
is
p
lo
tted
in
Fig
u
r
e
6
.
T
h
e
eq
u
al
er
r
o
r
r
ate
is
0
.
0
2
% f
o
r
t
h
e
th
r
esh
o
l
d
v
al
u
e
is
eq
u
al
to
0
.
0
1
5
.
Fig
u
r
e
6
.
T
h
e
R
OC
cu
r
v
e
T
ab
le
4
.
FAR
,
FR
R
an
d
ac
cu
r
ac
y
v
er
s
u
s
th
r
esh
o
l
d
v
alu
es
Th
r
e
s
h
o
l
d
F
R
R
(
%)
F
A
R
(
%)
A
c
c
u
r
a
c
y
(
%)
0
.
0
1
4
0
.
0
2
0
.
0
3
6
0
.
9
7
2
0
.
0
1
4
5
0
.
0
2
4
0
.
0
2
4
0
.
9
7
6
0
.
0
1
5
0
.
0
3
6
0
.
0
0
8
0
.
9
7
8
0
.
0
1
5
5
0
.
0
6
0
.
0
0
4
0
.
9
6
8
0
.
0
1
6
0
.
0
9
2
0
.
0
0
1
0
.
9
5
4
4.
CO
NCLU
SI
O
N
I
n
th
is
p
a
p
er
,
a
p
e
r
s
o
n
al
v
e
r
if
i
ca
tio
n
an
d
id
en
tific
atio
n
s
y
s
tem
b
ased
o
n
t
h
e
ea
r
im
ag
e
is
in
tr
o
d
u
ce
d
.
Allo
ca
tin
g
ea
r
r
eg
io
n
is
ac
h
al
len
g
in
g
s
tep
,
b
ec
a
u
s
e
o
f
all
f
o
llo
win
g
s
tep
s
ar
e
d
ep
en
d
in
g
o
n
it.
So
it
r
eq
u
ir
e
d
m
an
y
task
s
to
d
o
it
s
tar
tin
g
with
im
ag
e
p
r
ep
r
o
ce
s
s
in
g
with
cu
b
ic
s
p
lin
e
an
d
h
is
to
g
r
am
eq
u
aliza
tio
n
,
th
e
n
im
ag
e
b
in
ar
az
atio
n
is
ap
p
lied
,
af
ter
th
at
s
k
in
r
e
g
io
n
allo
ca
tio
n
is
p
er
f
o
r
m
ed
.
T
h
is
s
tep
m
a
y
ap
p
lied
f
o
r
s
u
ch
s
y
s
tem
s
th
at
r
eq
u
ir
e
s
k
in
r
eg
io
n
lo
ca
lizatio
n
.
A
n
ew
f
ea
tu
r
e
s
et
i
s
p
r
o
p
o
s
ed
in
th
i
s
wo
r
k
;
it
d
ep
en
d
s
o
n
th
e
"
lo
ca
l
s
p
atial
en
er
g
y
d
is
tr
ib
u
t
io
n
o
f
wav
elet
s
u
b
-
b
an
d
s
".
T
h
e
co
n
d
u
cted
r
esu
lts
in
d
icate
d
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
ed
h
ig
h
r
ec
o
g
n
itio
n
r
ate
C
C
R
9
5
.
2
8
%,
an
d
E
E
R
eq
u
al
to
0
.
0
2
%,
wh
ich
in
d
icate
s
h
ig
h
p
er
f
o
r
m
an
ce
in
v
er
if
icatio
n
.
RE
F
E
R
E
NC
E
S
[1
]
G
.
M
.
S
h
i
v
a
k
u
m
a
r
a
n
d
C.
M
.
P
a
ti
l,
"
A
n
I
n
v
e
stig
a
ti
o
n
to
wa
rd
s
Ef
fe
c
ti
v
e
n
e
ss
o
f
P
re
se
n
t
S
tate
o
f
B
io
m
e
tri
c
-
Ba
se
d
Au
th
e
n
t
ica
ti
o
n
S
y
ste
m
"
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Res
e
a
rc
h
a
n
d
S
c
ien
ti
fi
c
I
n
n
o
v
a
ti
o
n
(IJ
RS
I)
,
v
o
l.
4
,
n
o
.
7
,
p
p
.
4
4
-
5
5
,
Ju
l
y
2
0
1
7
.
[2
]
Z.
Wan
g
,
J.
Ya
n
g
,
a
n
d
Y.
Z
h
u
,
“
Re
v
iew
o
f
Ear
Bio
m
e
tri
c
s
,
”
Arc
h
Co
mp
u
t
a
t
M
e
th
o
d
s
En
g
.
,
v
o
l
.
2
8
,
p
p
.
1
4
9
-
1
8
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/s
1
1
8
3
1
-
0
1
9
-
0
9
3
7
6
-
2.
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
A
n
ea
r
r
ec
o
g
n
itio
n
s
ystem
b
a
s
ed
o
n
l
o
ca
l wa
ve
let
s
u
b
b
a
n
d
e
n
erg
y
d
is
tr
ib
u
tio
n
(
R
u
a
a
I
s
a
m
F
a
d
h
il
)
1219
[3
]
S
.
B.
Ku
tem
a
te
a
n
d
R.
U.
S
h
e
k
o
k
a
r
,
"
S
e
c
u
re
a
n
d
Re
li
a
b
le
Hu
m
a
n
Id
e
n
ti
fica
ti
o
n
Ba
se
d
o
n
F
i
n
g
e
r
-
Ve
in
P
a
tt
e
rn
s
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
Res
e
a
r
c
h
&
T
e
c
h
n
o
lo
g
y
(IJ
ER
T
)
,
v
o
l
.
4
,
n
o
.
3
,
p
p
.
9
7
8
-
9
8
0
,
2
0
1
5
,
doi
:
1
0
.
1
7
5
7
7
/IJERT
V
4
IS
0
3
0
9
3
8
.
[4
]
T.
F
.
Kie
l
y
,
“
Fo
re
n
sic
Evi
d
e
n
c
e
:
S
c
ien
c
e
a
n
d
t
h
e
Crimi
n
a
l
L
a
w
,
”
S
e
c
o
n
d
E
d
it
i
o
n
,
c
h
a
p
ter
E
a
r
Im
p
re
ss
io
n
s,
pp.
3
6
8
-
3
7
0
,
CRC P
re
ss
,
2
0
0
5
.
[5
]
S
.
Nik
o
se
a
n
d
H.
K.
M
e
e
n
a
,
“
Ear
-
b
io
m
e
tri
c
s
fo
r
h
u
m
a
n
id
e
n
ti
fica
ti
o
n
,
”
IEE
E
,
0
6
Oc
to
b
e
r
2
0
2
0
,
doi
:
1
0
.
1
1
0
9
/ACCTHP
A4
9
2
7
1
.
2
0
2
0
.
9
2
1
3
1
9
0
.
[6
]
A.
Be
rti
ll
o
n
,
“
L
a
P
h
o
t
o
g
r
a
p
h
i
e
J
u
d
ici
a
ire
:
Ave
c
Un
Ap
p
e
n
d
ice
S
u
r
L
a
Cl
a
ss
if
ica
ti
o
n
Et
L
’Id
e
n
ti
fi
c
a
ti
o
n
An
th
r
o
p
o
me
triq
u
e
s
,
”
G
a
u
th
ier
-
Vi
ll
a
rs,
P
a
ris;
1
8
9
0
.
[7
]
L.
Yu
a
n
a
n
d
Z
.
M
u
,
"
Ear
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
G
a
b
o
r
F
e
a
tu
re
s
a
n
d
KFDA
,
"
T
h
e
S
c
ien
ti
fi
c
W
o
rld
J
o
u
rn
a
l
,
v
o
l.
2
0
1
4
,
Article
ID
7
0
2
0
7
6
,
p
.
1
2
,
2
0
1
4
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
1
4
/7
0
2
0
7
6
.
[8
]
M
.
Kh
o
sr
o
w
-
P
o
u
r
,
“
En
c
y
c
lo
p
e
d
i
a
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
”
Th
ir
d
a
d
d
it
io
n
,
IG
I
G
lo
b
a
l,
2
0
1
4
,
doi
:
1
0
.
4
0
1
8
/9
7
8
-
1
-
5
2
2
5
-
2
2
5
5
-
3
.
[9
]
B.
S
.
El
-
De
so
u
k
y
,
M
.
El
-
Ka
d
y
,
M
.
Z.
Ra
sh
a
d
,
a
n
d
M
.
M
.
Ei
d
,
“
Ear
Re
c
o
g
n
it
io
n
An
d
Oc
c
lu
sio
n
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
&
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(
IJ
CS
IT
)
,
v
o
l.
4
,
n
o
.
6
,
p
p
.
9
7
-
1
0
4
,
2
0
1
2
,
doi
:
1
0
.
5
1
2
1
/i
jcs
it
.
2
0
1
2
.
4
6
0
8
.
[1
0
]
C.
S
fo
rz
a
,
G
.
G
ra
n
d
i,
M
.
Bin
e
ll
i
,
D
.
G
.
To
m
m
a
si,
R.
Ro
sa
ti
,
a
n
d
V.
F
.
F
e
rra
rio
,
“
Ag
e
-
An
d
S
e
x
-
Re
la
ted
Ch
a
n
g
e
s In
Th
e
No
rm
a
l
Hu
m
a
n
Ear
,
”
F
o
re
n
sic
S
c
ien
c
e
In
ter
n
a
ti
o
n
a
l
,
v
o
l.
1
8
7
,
n
o
.
1
-
3
,
p
p
.
1
1
0
.
e
1
-
1
1
0
.
e
7
,
2
0
0
9
,
doi
:
1
0
.
1
0
1
6
/j
.
f
o
rsc
ii
n
t
.
2
0
0
9
.
0
2
.
0
1
9
.
[1
1
]
L.
M
e
ij
e
rm
a
n
,
C.
V
.
D
.
Lu
g
t
a
n
d
G
.
J
.
R.
M
a
a
t,
“
Cr
o
ss
-
S
e
c
ti
o
n
a
l
An
th
r
o
p
o
m
e
tri
c
S
t
u
d
y
o
f
t
h
e
Ex
tern
a
l
Ear
,
”
J
o
u
rn
a
l
o
f
F
o
re
n
sic
S
c
ien
c
e
s
,
v
o
l
.
52
,
n
o
.
2
,
p
p
.
2
8
6
-
2
9
3
,
2
0
0
7
,
d
o
i
:
1
0
.
1
1
1
1
/j
.
1
5
5
6
-
4
0
2
9
.
2
0
0
6
.
0
0
3
7
6
.
x
.
[1
2
]
Z.
M
u
,
L.
Y
u
a
n
,
Z
.
Xu
,
D
.
Xi
,
a
n
d
S
.
Qi
,
“
S
h
a
p
e
a
n
d
S
tr
u
c
tu
ra
l
F
e
a
tu
re
Ba
se
d
Ear
Re
c
o
g
n
it
i
o
n
,
”
L
e
c
tu
re
No
tes
in
Co
mp
u
ter
S
c
ien
c
e
(L
NCS
)
,
v
o
l.
3
3
3
8
,
p
p
.
6
6
3
-
6
7
0
,
2
0
0
4
,
d
o
i
:
1
0
.
1
0
0
7
/9
7
8
-
3
-
5
4
0
-
3
0
5
4
8
-
4
_
7
6
.
[1
3
]
B.
Ja
wa
le
a
n
d
S
.
Bh
a
lch
a
n
d
ra
,
“
Th
e
Hu
m
a
n
Id
e
n
ti
fica
ti
o
n
S
y
ste
m
Us
in
g
M
u
lt
ip
le
G
e
o
m
e
tri
c
a
l
F
e
a
tu
re
Ex
trac
ti
o
n
o
f
Ear
-
A
n
I
n
n
o
v
a
ti
v
e
Ap
p
ro
a
c
h
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Em
e
rg
in
g
T
e
c
h
n
o
l
o
g
y
a
n
d
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
6
6
2
-
6
6
6
,
2
0
1
2
.
[1
4
]
X.
Q.
Wan
g
,
H.
Y.
Xia
,
a
n
d
Z.
I.
Wan
g
,
“
T
h
e
Re
se
a
rc
h
o
f
Ear
Id
e
n
ti
fica
ti
o
n
Ba
se
d
o
n
Im
p
ro
v
e
d
Alg
o
r
it
h
m
o
f
M
o
m
e
n
t
I
n
v
a
rian
ts
,
”
In
Pro
c
e
e
d
i
n
g
s
o
f
T
h
ird
In
t
.
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
a
n
d
Co
m
p
u
ti
n
g
(ICI
C)
,
Wu
x
i
Jia
n
g
S
u
,
p
p
.
5
8
-
6
0
,
2
0
1
0
,
d
o
i
:
1
0
.
1
1
0
9
/ICIC.
2
0
1
0
.
2
1
.
[1
5
]
Be
n
z
a
o
u
i,
A.
Kh
e
id
e
r
,
a
n
d
A.
Bo
u
k
r
o
u
c
h
e
,
"
Ear
d
e
sc
rip
ti
o
n
a
n
d
re
c
o
g
n
it
i
o
n
u
sin
g
EL
BP
a
n
d
wa
v
e
lets
,
"
in
:
Pro
c
e
e
d
in
g
s
o
f
th
e
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
A
p
p
li
e
d
Res
e
a
rc
h
in
Co
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
p
p
.
1
-
6
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
0
9
/ARC
S
E.
2
0
1
5
.
7
3
3
8
1
4
6
.
[1
6
]
K.
Ch
a
n
g
,
K.
W
.
Bo
wy
e
r,
S
.
S
a
rk
a
r
,
a
n
d
B.
Vic
to
r
,
“
Co
m
p
a
riso
n
a
n
d
Co
m
b
in
a
ti
o
n
o
f
Ear
a
n
d
F
a
c
e
Im
a
g
e
s
in
Ap
p
e
a
ra
n
c
e
-
Ba
se
d
Bio
m
e
tri
c
s
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
P
a
tt
e
rn
An
a
lys
is
a
n
d
M
a
c
h
i
n
e
In
tell
ig
e
n
c
e
,
v
o
l.
2
5
,
n
o
.
9
,
p
p
.
1
1
6
0
-
1
1
6
5
,
2
0
0
3
,
d
o
i
:
1
0
.
1
1
0
9
/T
P
AMI
.
2
0
0
3
.
1
2
2
7
9
9
0
.
[1
7
]
L.
Na
n
n
i
a
n
d
A.
L
u
m
in
i,
“
F
u
sio
n
o
f
c
o
l
o
r
sp
a
c
e
s
fo
r
e
a
r
a
u
th
e
n
ti
c
a
ti
o
n
”
,
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
(E
lse
v
ier
)
,
v
o
l.
4
2
,
pp.
1
9
0
6
-
1
9
1
3
,
2
0
0
9
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
p
a
tco
g
.
2
0
0
8
.
1
0
.
0
1
6
.
[1
8
]
C.
Wu
Ku
m
a
r,
“
Au
to
m
a
ted
h
u
m
a
n
id
e
n
t
ifi
c
a
ti
o
n
u
sin
g
e
a
r
im
a
g
in
g
,
”
P
a
tt
e
rn
Rec
o
g
n
it
io
n
(El
se
v
ier
)
,
v
o
l.
4
5
,
pp.
9
5
6
-
9
6
8
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
tco
g
.
2
0
1
1
.
0
6
.
0
0
5
.
[1
9
]
J.
S
.
Jim
m
y
Li
a
n
d
S
.
Ra
n
d
h
a
wa
,
“
c
o
lo
u
r
f
il
ter
a
rra
y
d
e
m
o
sa
ick
in
g
u
sin
g
c
u
b
ic
sp
li
n
e
in
terp
o
lati
o
n
,
”
Co
n
fer
e
n
c
e
Pa
p
e
r
in
Aco
u
st
ics
,
S
p
e
e
c
h
,
a
n
d
S
ig
n
a
l
Pr
o
c
e
ss
in
g
,
1
9
8
8
.
ICA
S
S
P
-
8
8
,
1
9
8
8
I
n
tern
a
ti
o
n
a
l
Co
n
fe
re
n
c
e
,
n
o
.
1
,
p
p
.
I
-
8
6
5
-
I
-
8
6
8
,
2
0
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/ICAS
S
P
.
2
0
0
7
.
3
6
6
0
4
5
.
[2
0
]
S
.
S
.
Ba
g
a
d
e
a
n
d
V.
K.
S
h
a
n
d
il
y
a
,
“
Us
e
o
f
Histo
g
ra
m
Eq
u
a
li
z
a
ti
o
n
in
Im
a
g
e
P
r
o
c
e
ss
in
g
fo
r
Im
a
g
e
En
h
a
n
c
e
m
e
n
t
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
S
o
f
twa
re
En
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
Pra
c
t
ice
s
,
v
o
l.
1
,
n
o
.
2
,
p
p
.
6
-
1
0
,
2
0
1
1
.
[2
1
]
C.
L.
He
,
P
.
Zh
a
n
g
,
J.
D
o
n
g
,
C.
Y.
S
u
e
n
,
a
n
d
T.
D.
Bu
i
,
“
Th
e
Ro
l
e
o
f
S
ize
No
rm
a
li
z
a
ti
o
n
o
n
t
h
e
R
e
c
o
g
n
it
i
o
n
Ra
te
o
f
Ha
n
d
wri
tt
e
n
Nu
m
e
ra
ls
,
”
Ce
n
tre
fo
r
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
a
n
d
M
a
c
h
in
e
I
n
telli
g
e
n
c
e
,
Co
n
c
o
rd
ia
Un
iv
e
rsit
y
M
o
n
trea
l,
Qu
e
b
e
c
,
Ca
n
a
d
a
H
3
G
1
M
8
.
[2
2
]
Y.
Ern
e
st,
C.
M
.
Lam
Yu
a
n
,
a
n
d
Y.
Tan
g
,
“
F
e
a
tu
re
Ex
trac
ti
o
n
U
sin
g
Wav
e
let
A
n
d
F
ra
c
tal
”
,
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
L
e
tt
e
rs
,
v
ol
.
2
2
,
n
o
.
3
-
4
,
p
p
.
2
7
1
-
2
8
7
,
2
0
0
1
,
d
o
i
:
1
0
.
1
0
1
6
/
S
0
1
6
7
-
8
6
5
5
(0
1
)0
0
0
0
3
-
4.
[2
3
]
M
.
Nix
o
n
a
n
d
A.
A
g
u
a
d
o
,
"
F
e
a
tu
re
Extra
c
ti
o
n
&
Ima
g
e
Pro
c
e
ss
in
g
fo
r
Co
m
p
u
ter
Vi
si
o
n
,
"
Th
ird
E
d
it
i
o
n
,
Ac
a
d
e
m
ic P
re
ss
,
2
0
1
2
.
[2
4
]
J.
G
o
u
a
,
L.
Du
,
Y.
Zh
a
n
g
,
a
n
d
T.
Xio
n
g
,
“
A
Ne
w
Dista
n
c
e
-
we
ig
h
ted
k
-
n
e
a
re
st
Ne
ig
h
b
o
r
Clas
si
e
r
,
”
J
o
u
rn
a
l
o
f
In
fo
rm
a
t
io
n
&
Co
m
p
u
t
a
ti
o
n
a
l
S
c
i
e
n
c
e
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
1
4
2
9
-
1
4
3
6
,
2
0
1
2
.
[2
5
]
R.
M
.
P
o
ll
i,
A.
V.
M
a
ra
n
,
A
.
T.
Z.
Jo
u
g
las
,
E.
S
il
v
a
,
P
.
S
.
Bra
n
d
i
,
a
n
d
D.
I
.
Ha
ss
,
"
A
P
ro
p
o
sa
l
f
o
r
th
e
Ha
n
d
P
a
lm
Id
e
n
ti
fica
ti
o
n
,
Us
in
g
L
o
c
a
l
Bi
n
a
ry
P
a
tt
e
rn
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
En
g
i
n
e
e
rin
g
S
c
ien
c
e
s
a
n
d
T
e
c
h
n
o
l
o
g
y
(IJ
AE
S
T
)
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
3
0
2
-
3
0
9
,
2
0
1
1
.
[2
6
]
R.
E.
F
a
d
h
il
a
n
d
L.
E.
G
e
o
rg
e
,
“
T
h
e
Us
e
o
f
S
p
a
ti
a
l
Distri
b
u
t
io
n
o
f
th
e
Lo
c
a
l
Histo
g
ra
m
Ba
se
d
F
e
a
tu
re
s
fo
r
F
in
g
e
r'
s
Ve
in
s
Bio
m
e
tri
c
s
,
”
Brit
ish
J
o
u
rn
a
l
o
f
M
a
th
e
ma
ti
c
s
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
15
,
n
o
.
4
,
n
o
.
BJMCS
.
2
4
7
2
9
,
p
p
.
1
-
1
1
,
2
0
1
6
,
d
o
i
:
1
0
.
9
7
3
4
/BJM
CS
/2
0
1
6
/2
4
7
2
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.