T
E
L
KO
M
NIK
A
, V
ol
.
16
,
No.
4,
A
ug
us
t
20
1
8,
p
p.
1
864
~1
869
IS
S
N: 1
69
3
-
6
93
0
,
accr
ed
ited
F
irst
Gr
ad
e b
y K
em
en
r
istekdikti,
Decr
ee
No: 2
1/E/
K
P
T
/20
18
DOI:
10.12928/TE
LK
OM
N
IK
A
.v
1
6
i
4
.
8534
18
64
Rec
ei
v
ed
J
an
u
ary
6
, 2
01
8
;
Rev
i
s
ed
Ma
r
c
h 6
,
20
1
8
;
A
c
c
ep
ted
J
u
l
y
9
,
20
1
8
Fin
g
erprin
t Pat
t
ern
of
Matc
hin
g
Fam
il
y
w
ith
G
L
CM
Feat
ure
Baht
iar
I
mran
*
,
K
ar
ya
G
u
n
aw
an
,
M
u
h
amm
ad Z
o
h
r
i, Lalu Da
r
maw
an Bakti
Col
l
a
g
e
Co
m
p
u
te
r
I
n
f
o
rm
a
ti
o
n
M
a
n
a
g
e
m
e
n
t
(ST
M
IK
M
a
ta
ra
m
),
In
d
o
n
e
s
i
a
*C
o
rre
s
p
o
n
d
i
n
g
a
u
th
o
r,
e
-
m
a
i
l
:
b
a
h
t
i
a
ri
m
ra
n
l
o
m
b
o
k
@
g
m
a
i
l
.
c
o
m
Ab
strac
t
In
th
i
s
re
s
e
a
r
c
h
,
fi
n
g
e
r
p
ri
n
t
p
a
tt
e
rn
m
a
tc
h
i
n
g
i
s
d
o
n
e
to
fi
n
d
o
u
t
whe
th
e
r
th
e
re
i
s
th
e
s
i
m
i
l
a
ri
t
y
b
e
twe
e
n
p
a
re
n
t
a
n
d
c
h
i
l
d
fi
n
g
e
rp
ri
n
t
p
a
t
te
rn
.
A
n
i
m
p
o
rt
a
n
t
s
te
p
i
n
fi
n
g
e
r
p
ri
n
t
m
a
t
c
h
i
n
g
i
s
th
e
f
i
n
g
e
rp
ri
n
t
p
a
tt
e
rn
s
e
a
r
c
h
a
n
d
m
a
tc
h
i
n
g
.
Fi
n
g
e
r
p
ri
n
t
d
a
ta
i
s
u
s
e
d
b
y
1
1
fa
m
i
l
i
e
s
fro
m
v
a
r
i
o
u
s
fa
m
i
l
i
e
s
.
Th
e
m
e
th
o
d
u
s
e
d
i
n
fi
n
g
e
rp
ri
n
t
fe
a
t
u
re
e
x
t
ra
c
ti
o
n
i
s
G
L
CM
.
Th
e
G
L
C
M
a
n
g
l
e
u
s
e
d
i
s
0
o
,
a
n
d
th
e
fe
a
tu
re
s
u
s
e
d
a
r
e
c
o
n
tr
a
s
t,
h
o
m
o
g
e
n
e
i
ty
,
c
o
rre
l
a
ti
o
n
,
a
n
d
e
n
e
rg
y
.
Fo
r
fi
n
g
e
rp
ri
n
t
p
a
tt
e
rn
m
a
tc
h
i
n
g
u
s
e
m
i
n
u
t
i
a
e
s
c
o
r
e
.
Fro
m
th
e
re
s
u
l
t
s
o
b
t
a
i
n
e
d
G
L
CM
h
a
s
b
e
e
n
wid
e
l
y
u
s
e
d
i
n
fi
n
g
e
r
p
ri
n
t
te
x
tu
re
a
n
a
l
y
s
i
s
.
T
h
i
s
s
tu
d
y
p
ro
v
e
s
th
a
t
th
e
p
ro
p
o
s
e
d
m
e
t
h
o
d
f
o
r
m
a
tc
h
i
n
g
fi
n
g
e
rp
ri
n
ts
o
n
p
a
re
n
t
s
a
n
d
c
h
i
l
d
re
n
g
e
t
s
th
e
m
o
s
t
d
o
m
i
n
a
n
t
p
a
tt
e
rn
i
s
th
e
l
o
o
p
p
a
tt
e
rn
.
Key
w
ords
:
F
i
n
g
e
r
p
ri
n
t,
GLCM
,
P
a
tt
e
rn
,
T
e
x
tu
r
e
,
A
n
a
l
y
s
i
s
Copy
righ
t
©
2
0
1
8
Uni
v
e
rsi
t
a
s
Ahm
a
d
D
a
hl
a
n.
All
rig
ht
s
r
e
s
e
rve
d
.
1.
Int
r
o
d
u
ctio
n
F
i
ng
er
prin
t
i
s
c
ate
g
ori
z
ed
a
s
on
e
of
the
b
es
t
i
de
nt
i
f
i
c
ati
on
t
oo
l
s
f
or
i
ts
un
i
q
ue
n
es
s
[1
-
2].
Ma
n
y
r
es
ea
r
c
he
r
s
ab
o
ut
c
o
m
bi
na
t
i
on
d
ev
el
op
m
en
t
[3]
,
f
ea
ture
ex
tr
ac
ti
on
i
s
wel
l
do
n
e
[4].
F
i
ng
er
prin
t
m
atc
hi
ng
i
s
an
es
s
en
ti
a
l
an
d
d
i
f
f
i
c
ul
t
predi
c
am
en
t
i
n
f
i
ng
erpr
i
nt
r
ec
og
n
i
ti
on
.
S
t
i
l
l
,
ev
e
n
i
f
s
o
m
an
y
d
i
f
f
er
en
t
m
eth
od
s
are
th
ere,
i
t
ha
s
be
en
eru
di
t
e
f
r
om
s
tud
i
es
t
ha
t
a
i
m
prov
e
d
f
ea
ture
ex
tr
ac
ti
o
n
tec
hn
i
q
u
e
m
a
y
l
e
ad
s
to
es
p
ec
i
a
l
l
y
go
od
ou
tc
om
e
[5]
.
E
v
en
t
h
ou
gh
s
o
m
an
y
di
f
f
erent
m
eth
od
s
are
th
ere,
i
t
h
as
be
en
l
e
arned
f
r
om
s
tud
i
es
tha
t
a
be
tt
er
f
ea
ture
ex
tr
ac
ti
o
n
tec
hn
i
qu
e
m
a
y
l
ea
ds
to
v
er
y
go
od
r
es
u
l
ts
.
Co
-
oc
c
u
r
r
en
c
e
m
atri
c
es
c
an
be
us
ed
to
ex
tr
ac
t
f
ea
tures
f
r
o
m
th
e f
i
ng
erpr
i
n
t i
m
ag
e b
ec
a
us
e t
h
e
y
are c
om
po
s
ed
o
f
r
eg
ul
ar t
ex
ture
pa
tte
r
ns
[
6].
F
i
ng
er
prin
ts
are
the
m
os
t
wi
de
l
y
us
e
d
pa
r
am
ete
r
f
or
pe
r
s
on
a
l
i
de
nti
f
i
c
a
t
i
on
am
on
gs
t
a
l
l
bi
om
etri
c
s
.
F
i
ng
erpr
i
nt
i
de
nti
f
i
c
ati
on
i
s
c
om
m
on
l
y
em
pl
o
y
e
d
i
n
f
orens
i
c
s
c
i
en
c
e
to
ai
d
c
r
i
m
i
na
l
i
n
v
es
ti
ga
t
i
on
s
etc
.
A
f
i
ng
erpr
i
nt
i
s
a
un
i
q
ue
p
att
ern
o
f
r
i
dg
es
an
d
v
a
l
l
e
y
s
o
n
th
e
s
urf
ac
e
of
a
f
i
ng
er
of
an
i
nd
i
v
i
du
a
l
[7]
.
In
ad
d
i
ti
on
,
th
e
f
i
ng
erpr
i
nt
i
s
us
ed
f
or
ge
ne
ti
c
s
[8]
,
th
e
r
el
at
i
on
s
h
i
p
be
t
w
e
en
th
e
c
hi
l
d's
f
i
ng
er
prin
t
ha
s
a
c
orr
el
at
i
o
n
r
el
ati
o
ns
hi
p
wi
th
th
e
pa
r
e
nt's
f
i
ng
erpr
i
nt
[9]
.
P
aren
ts
wi
th
a
pa
r
t
i
c
ul
ar
f
i
ng
erpr
i
nt
pa
t
tern
ha
v
e
a
r
el
at
i
v
e
hi
gh
te
nd
e
nc
y
to
pr
od
uc
e
c
hi
l
dre
n
wi
th
the
s
am
e p
att
ern [1
0].
S
e
v
era
l
prev
i
o
us
s
tud
i
es
h
av
e
ex
am
i
ne
d
f
i
ng
erpr
i
n
t
m
atc
hi
n
g
us
i
n
g
the
G
LCM
m
eth
o
d.
A
s
f
or
the
c
on
c
e
ntrati
on
c
on
du
c
te
d
i
n
thi
s
s
tud
y
i
s
,
f
i
ng
erpr
i
nt
m
atc
hi
ng
i
s
d
on
e
on
f
am
i
l
y
f
i
ng
erpr
i
n
t
be
t
ween
pa
r
en
t
s
an
d
c
hi
l
dre
n.
T
he
da
ta
u
s
ed
i
n
th
i
s
s
tud
y
wer
e
11
di
f
f
erent
f
a
m
i
l
y
f
i
ng
erpr
i
n
ts
. T
he
G
LCM
m
e
tho
d
i
s
us
e
d t
o e
x
tr
ac
t
pa
r
e
nt
a
nd
c
h
i
l
d f
i
ng
erpr
i
nts
.
M
i
nu
ti
ae
s
c
ore
i
s
do
ne
to
m
atc
h t
he
f
i
n
ge
r
pri
nt
pa
tte
r
n.
2.
Rel
ated
W
o
r
k
F
i
ng
er
prin
t
m
atc
hi
ng
i
s
p
erf
or
m
ed
ba
s
ed
on
f
i
n
di
ng
t
h
e
no
r
m
al
i
z
ed
E
uc
l
i
de
a
n
di
s
tan
c
e
be
t
w
e
en
t
he
i
n
pu
t
an
d
t
he
tem
pl
at
e
f
ea
ture
v
ec
t
ors
.
E
x
pe
r
i
m
en
ta
l
r
es
ul
ts
v
a
l
i
da
te
th
e
ef
f
ec
ti
v
en
es
s
of
the
pro
po
s
ed
m
eth
od
i
n
ex
tr
ac
ti
n
g
f
i
ng
erpr
i
n
t
f
ea
tures
a
nd
a
c
hi
e
v
i
n
g
g
oo
d
pe
r
f
or
m
an
c
e [
6].
T
hi
s
w
ork
us
es
v
ec
tor
whi
c
h
i
s
g
en
erated
f
r
om
Huffm
an
c
od
i
ng
c
om
pres
s
i
on
p
r
oc
es
s
.
T
he
r
ef
ore,
the
m
atc
hi
ng
pr
oc
es
s
i
s
do
ne
be
t
ween
c
o
de
(
v
ec
tor)
an
d
c
od
es
(
v
e
c
tors
)
an
d
the
da
ta
ba
s
e
i
s
s
ha
r
pl
y
de
c
r
ea
s
ed
.
T
he
ob
t
ai
ne
d
r
es
ul
ts
a
r
e
c
on
s
i
d
erabl
y
prom
i
s
i
ng
s
i
nc
e
v
er
y
l
o
w
F
A
R
i
.
e.
0.7
33
%,
F
R
R
i
.e
.
2.6
%
an
d
hi
gh
ac
c
urac
y
i
.e.
ap
prox
i
m
ate
l
y
97
%
[1
1
].
F
i
ng
er
prin
t
r
ec
og
ni
t
i
o
n
an
d
m
atc
hi
ng
al
g
orit
hm
i
s
ex
pl
ai
n
ed
an
d
r
es
ul
ts
gi
v
e
r
em
ar
k
ab
l
e
pe
r
f
or
m
an
c
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
F
i
ng
er
prin
t
P
a
tte
r
n
of
Ma
tc
hi
n
g Fam
i
l
y
W
i
th
G
LC
M Fe
atu
r
e
(
B
ah
t
i
ar I
mran
)
1865
Im
ag
es
are
c
r
op
pe
d
an
d
f
ea
tures
are
ex
tr
ac
te
d,
t
he
n
m
atc
hi
ng
i
s
do
ne
us
i
ng
E
uc
l
i
d
ea
n
di
s
tan
c
e
[5
].
3
.
Re
se
a
r
ch M
eth
o
d
In
thi
s
s
tud
y
,
we
de
t
erm
i
ne
d
the
c
l
as
s
i
f
i
c
at
i
on
of
the
f
i
ng
erpr
i
nts
of
pa
r
en
ts
an
d
c
hi
l
dren
i
n
ac
c
ordanc
e
w
i
th
Re
v
i
e
w
s
t
he
i
r
r
es
pe
c
t
i
v
e
f
am
i
l
i
e
s
.
F
i
ng
erpr
i
n
t
D
ata
tak
en
us
i
ng
a
di
gi
t
al
f
i
ng
erpr
i
n
t
p
ers
on
a
u
are
u
4
50
0
S
D
K
.
T
he
n
t
he
ap
pl
i
c
a
t
i
o
n
us
ed
i
s
C
#
b
as
e
d
a
pp
l
i
c
at
i
on
s
.
B
ef
ore
the
s
tag
e
c
l
as
s
i
f
i
c
ati
on
wi
l
l
be
d
on
e
f
i
r
s
t
pre
-
proc
es
s
i
ng
of
the
f
i
ng
erpr
i
nt
of
da
ta,
the
s
i
z
e
of
the
orig
i
n
al
f
i
ng
erpr
i
n
t
2
54
x
29
2
.A
t
th
e
s
tag
e
of
pre
-
proc
es
s
i
ng
w
i
l
l
be
C
arr
i
ed
ou
tc
r
op
pi
ng
of
the
f
i
n
ge
r
pri
nt
of
d
ata
to
t
h
e
s
i
z
e
of
154x
19
2
.
A
f
ter
th
e
pre
-
proc
es
s
i
ng
s
ta
ge
wi
l
l
be
Car
r
i
e
d
o
ut
l
ate
r
on
f
i
ng
erpr
i
nt
f
ea
ture
ex
tr
ac
ti
on
pa
r
e
nts
a
nd
c
h
i
l
dren
t
o
g
et
i
ts
v
al
ue
,
th
en
i
t
wi
l
l
b
e
do
ne
af
ter
the
pa
tte
r
n
m
atc
hi
ng
.
T
he
m
eth
od
of
f
ea
ture
ex
t
r
ac
ti
on
pro
po
s
ed
i
n
thi
s
r
e
s
ea
r
c
h
i
s
gra
y
l
e
v
el
c
o
-
oc
c
urr
en
c
e
m
atri
x
(
G
LCM)
m
eth
od
.
G
LC
M
f
ea
tures
us
ed
i
n
t
hi
s
r
es
ea
r
c
h
are
c
orr
el
ati
on
, c
o
ntras
t,
ho
m
og
en
e
i
t
y
, a
nd
en
erg
y
.
W
h
ere
:
i=
r
o
w
j=
c
ol
um
ns
p=
g
l
c
m
m
atri
x
Me
as
uri
ng
t
he
s
pa
ti
al
f
r
eq
u
en
c
y
of
th
e
i
m
ag
e
an
d
th
e
di
f
f
erenc
e
G
LCM
m
o
m
en
t.
T
he
di
f
f
erenc
e
i
s
m
ea
nt
a
di
f
f
erenc
e
of
i
ts
hi
g
h
an
d
l
o
w
pi
x
e
l
.
Cont
r
as
t
w
i
l
l
b
e
0
i
f
the
pi
x
el
ne
i
g
h
bo
r
ho
od
s
ha
v
e
the
s
am
e v
al
ue
.
T
he
v
al
u
e
w
as
v
er
y
s
e
ns
i
t
i
v
e
to
th
e
v
al
ue
aro
un
d
th
e
m
ai
n
di
ag
on
al
.
It
wi
l
l
ha
s
a
hi
g
h
v
al
u
e
when
a
l
l
t
he
p
i
x
el
s
ha
v
e
th
e
s
am
e
v
al
ue
.
T
he
op
p
os
i
t
e
of
c
on
tr
as
t
w
i
l
l
h
av
e
a
gr
ea
t
v
al
u
e
i
f
i
t
ha
s
th
e
s
am
e p
i
x
el
v
a
l
ue
at
th
e t
i
m
e o
f
v
al
u
ab
l
e e
ne
r
g
y
.
E
ne
r
g
y
w
i
l
l
ha
v
e
a
h
i
gh
v
a
l
ue
w
he
n
the
p
i
x
el
v
a
l
ue
s
a
r
e
s
i
m
i
l
ar
to
on
e
an
o
the
r
woul
d
oth
erw
i
s
e
be
of
l
i
t
tl
e
v
a
l
u
e
i
n
di
c
a
tes
the
v
al
ue
of
G
LCM
no
r
m
al
i
z
ati
on
i
s
h
ete
r
o
ge
n
eo
us
.
T
he
m
ax
i
m
u
m
v
a
l
ue
of
the
en
er
g
y
was
1,
whi
c
h
m
ea
ns
the
d
i
s
tr
i
b
uti
o
n
of
pi
x
el
s
i
n
a
s
tat
e
of
c
on
s
tan
t
or
i
n
the
f
or
m
(
no
t rando
m
)
.
T
he
m
ai
n s
tep
s
of
prop
os
ed
m
eth
o
d a
r
e
:
1.
Data
c
o
l
l
ec
ti
o
n f
i
ng
erpr
i
nt
2.
Im
ag
e res
a
m
pl
i
ng
to
25
4 x
29
2
nu
m
be
r
of
pi
x
el
s
i
z
e
.
3.
P
r
e
-
proc
es
s
i
ng
th
e
i
n
pu
t
i
m
ag
e (1
54
x
1
92
)
.
4.
Regi
on
-
of
-
i
nte
r
es
t
5.
F
ea
ture
ex
tr
ac
ti
o
n GLC
M
6.
Dete
r
m
i
na
ti
o
n o
f
f
i
ng
erpr
i
nt
pa
tt
ern us
i
ng
m
i
nu
ti
ae
s
c
o
r
e.
4
.
R
es
u
lt
s
a
nd
A
n
al
ys
is
4
.1.
D
ata
Co
ll
ec
t
ion
Fin
g
e
r
p
r
int
Data
w
ere
t
ak
en
f
r
o
m
11
di
f
f
ere
nt
f
a
m
i
l
i
es
i
n
the
L
om
bo
k
r
eg
i
on
.
T
he
f
i
ng
erpr
i
n
t
s
w
ere
tak
en
ou
r
c
hi
l
dren's
f
i
ng
er
p
r
i
nts
an
d
pa
r
e
nta
l
f
i
ng
erpr
i
n
ts
.
T
he
tot
al
f
i
ng
erpr
i
nt
us
e
d
i
n
t
hi
s
s
tud
y
was
33
f
i
n
ge
r
pri
nts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N:
1
69
3
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
16
,
No.
4,
A
ug
us
t
20
1
8:
1
86
4
-
18
6
9
1866
4
.2.
Im
age R
es
a
mp
ling
In
thi
s
s
tud
y
,
us
i
n
g
the
ori
gi
na
l
f
i
ng
e
r
prin
t
i
m
ag
e
w
i
t
h
a
s
i
z
e
of
25
4x
29
2
p
i
x
el
s
as
s
ho
w
n
i
n F
i
gu
r
e
1.
F
i
gu
r
e
1.
F
i
ng
erpr
i
nt
ori
gi
n
al
(
a) f
ath
er (
b) m
oth
er (
c
)
c
hi
l
d
4
.3.
P
r
eproce
ss
ing
In
th
e
pre
proc
es
s
i
ng
s
tag
e
w
i
l
l
be
c
r
op
p
i
ng
on
the
orig
i
na
l
f
i
n
ge
r
pri
nt
i
m
ag
e
i
nt
o
a
15
4x
19
2
pi
x
e
l
s
to
re
du
c
e
the
c
om
pu
ti
ng
proc
es
s
,
1
54
x
19
2
c
r
op
pi
n
g
r
es
ul
ts
c
an
be
s
ee
n
i
n
F
i
gu
r
e
2.
F
i
gu
r
e
2.
Cr
o
pp
i
ng
f
i
n
ge
r
pri
nt
(
a) f
ath
er (
b) m
oth
er (
c
)
c
hi
l
d
4
.4.
R
egio
n
of
Int
er
e
st
A
t th
i
s
s
tag
e
w
e
wi
l
l
l
o
ok
f
o
r
th
e RO
I
of
f
i
ng
erpr
i
nts
f
at
he
r
, m
oth
er and
c
hi
l
dren
to
s
pe
ed
up
th
e p
r
oc
es
s
of
c
l
as
s
i
f
i
c
a
ti
on
, th
e res
ul
ts
of
f
i
ng
erpr
i
nt
RO
I a
s
F
i
gu
r
e
3.
F
i
gu
r
e
3.
R
eg
i
on
of
i
nte
r
es
t
4
.5.
Fe
atu
r
e
E
xtr
ac
t
ion
G
L
CM
F
ea
ture
ex
tr
ac
t
i
on
to
o
bta
i
n
f
i
ng
erpr
i
n
t
f
ea
tures
,
pa
r
e
nt
,
an
d
c
h
i
l
d
.
A
n
gl
es
us
e
d
are
0
o
an
d
f
ea
t
ures
us
ed
are
e
ne
r
g
y
,
c
o
ntras
t,
c
orr
el
at
i
on
,
an
d
ho
m
og
en
e
i
t
y
.
T
he
r
es
ul
ts
of
f
i
ng
erpr
i
nt
f
ea
ture ex
tr
ac
ti
on
f
or pare
n
ts
an
d c
h
i
l
dren s
uc
h
as
i
n
Tabl
e 1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
F
i
ng
er
prin
t
P
a
tte
r
n
of
Ma
tc
hi
n
g Fam
i
l
y
W
i
th
G
LC
M Fe
atu
r
e
(
B
ah
t
i
ar I
mran
)
1867
T
ab
l
e
1.
G
L
CM
No
N
a
m
e
C
o
n
t
r
a
s
t
H
o
m
o
g
e
n
i
t
y
C
o
r
r
e
lat
ion
E
n
e
r
g
y
Fa
m
il
y
1
Fathe
r
M
o
t
h
e
r
C
h
il
d
9
3
4
7
.
3
8
4
0
2
.
3
6
9
0
3
.
3
0
.
3
4
9
7
0
.
4
3
2
1
0
.
5
2
0
2
0
.
5
0
4
9
0
.
5
6
5
4
0
.
5
5
5
8
0
.
0
9
7
8
0
.
1
4
7
0
0
.
2
4
7
8
Fa
m
il
y
2
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
1
6
0
.
2
8
4
0
2
.
3
9
7
2
3
.
9
0
.
4
2
0
9
0
.
4
3
2
1
0
.
4
1
0
1
0
.
5
4
3
8
0
.
5
6
5
4
0
.
4
9
1
8
0
.
1
4
4
7
0
.
1
4
7
0
0
.
1
2
9
0
Fa
m
il
y
3
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
1
6
0
.
2
8
4
0
2
.
3
9
1
8
1
.
6
0
.
4
2
0
9
0
.
4
3
2
1
0
.
4
0
5
7
0
.
5
4
3
8
0
.
5
6
5
4
0
.
4
5
0
7
0
.
1
4
4
7
0
.
1
4
7
0
0
.
1
3
5
3
Fa
m
il
y
4
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
4
9
8
.
5
9
6
1
1
.
9
7
9
5
7
.
9
0
.
4
6
7
0
0
.
4
7
6
8
0
.
5
1
1
2
0
.
5
2
8
9
0
.
4
9
6
7
0
.
4
3
3
4
0
.
1
7
4
8
0
.
1
9
2
1
0
.
2
4
6
6
Fa
m
il
y
5
Fathe
r
M
o
t
h
e
r
C
h
il
d
7
5
2
5
.
4
6
6
5
9
.
4
6
5
3
0
.
0
0
.
4
5
5
3
0
.
3
6
6
9
0
.
5
0
6
0
0
.
5
4
8
7
0
.
5
9
1
9
0
.
4
8
6
8
0
.
1
6
7
8
0
.
1
8
6
4
0
.
2
4
3
7
Fa
m
il
y
6
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
9
7
1
0
.
9
0
.
3
8
4
6
0
.
3
2
2
9
0
.
3
3
5
5
0
.
4
8
4
5
0
.
4
0
8
2
0
.
4
6
1
9
0
.
1
1
8
3
0
.
0
8
4
0
0
.
0
9
2
4
Fa
m
il
y
7
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
9
0
3
4
.
0
0
.
3
8
4
6
0
.
3
2
2
9
0
.
3
6
0
7
0
.
4
8
4
5
0
.
4
0
8
2
0
.
4
3
7
1
0
.
1
1
8
3
0
.
0
8
4
0
0
.
1
0
4
8
Fa
m
il
y
8
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
7
4
9
0
.
3
0
.
3
8
4
6
0
.
3
2
2
9
0
.
4
6
7
2
0
.
4
8
4
5
0
.
4
0
8
2
0
.
5
1
3
4
0
.
1
1
8
3
0
.
0
8
4
0
0
.
1
9
0
5
Fa
m
il
y
9
Fathe
r
M
o
t
h
e
r
C
h
il
d
7
3
1
3
.
2
8
4
7
0
.
9
8
2
5
4
.
4
0
.
3
7
9
9
0
.
4
8
7
5
0
.
4
9
2
1
0
.
6
1
7
0
0
.
4
8
9
8
0
.
5
3
9
7
0
.
1
1
3
7
0
.
2
1
2
8
0
.
2
1
3
2
Fa
m
il
y
1
0
Fathe
r
M
o
t
h
e
r
C
h
il
d
9
8
0
1
.
7
9
0
5
3
.
9
12617
0
.
3
4
5
2
0
.
3
4
1
1
0
.
3
7
6
4
0
.
4
5
6
5
0
.
5
2
8
2
0
.
3
7
9
3
0
.
0
9
6
7
0
.
0
9
0
9
0
.
1
1
4
4
Fa
m
il
y
1
1
Fathe
r
M
o
t
h
e
r
C
h
il
d
10374
7
8
5
2
.
2
5
9
1
8
.
9
0
.
3
2
2
7
0
.
4
3
4
1
0
.
4
6
0
4
0
.
4
1
1
7
0
.
5
7
5
4
0
.
6
8
9
9
0
.
0
8
2
9
0
.
1
5
1
8
0
.
1
6
9
1
4
.6.
F
ing
e
r
p
r
int
P
att
er
n
P
att
ern
m
atc
hi
ng
to
f
ac
i
l
i
ta
te
the
c
l
as
s
i
f
i
c
ati
on
of
ea
c
h
f
i
ng
erpr
i
nt
p
att
ern
af
ter
pa
tte
r
n
r
ec
og
ni
t
i
o
n
i
s
do
n
e
ac
c
ordi
ng
to
ea
c
h
f
am
i
l
y
.
F
i
ng
erpr
i
nt
m
atc
hi
ng
i
s
do
n
e
us
i
ng
m
i
nu
ti
ae
s
c
ore
b
y
c
ou
nti
ng
t
he
m
i
nu
t
i
ae
de
tec
te
d
l
ate
r
i
n
c
om
pa
r
i
s
on
w
i
th
m
i
nu
ti
ae
o
n
ot
he
r
f
i
ng
erpr
i
nts
.
E
x
am
pl
e m
i
nu
ti
ae
de
t
ec
ted
i
n
F
i
gu
r
e
4,
t
o
v
i
e
w th
e res
ul
ts
of
T
ab
l
e 2
.
F
i
g
ure
4
.
M
i
n
uti
ae
de
tec
t
i
o
n
T
hi
s
s
tud
y
us
es
11
f
a
m
i
l
y
f
i
ng
erpr
i
nt
d
ata
c
on
s
i
s
ti
n
g
of
f
ath
er'
s
f
i
ng
erpr
i
nt
,
m
oth
er'
s
f
i
ng
erpr
i
n
t,
an
d
c
hi
l
d's
f
i
ng
erpr
i
nt,
the
t
ota
l
nu
m
be
r
of
f
i
ng
erpr
i
n
ts
us
ed
i
s
3
3
f
i
n
ge
r
prin
ts
.
G
r
a
y
l
e
v
el
c
o
-
oc
c
urr
en
c
e
m
atri
x
(
G
LCM)
m
eth
od
i
s
us
e
d
to
ob
ta
i
n
t
he
ex
tr
ac
ti
o
n
r
es
ul
t
on
f
i
ng
erpr
i
nt
,
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N:
1
69
3
-
6
93
0
T
E
L
KO
M
NIK
A
V
ol
.
16
,
No.
4,
A
ug
us
t
20
1
8:
1
86
4
-
18
6
9
1868
the
an
g
l
e
us
e
d
i
n
th
i
s
r
es
ea
r
c
h
i
s
an
gl
e
0
o
.
Mi
n
uti
ae
s
c
ore
i
s
us
ed
to
c
al
c
ul
ate
the
nu
m
be
r
o
f
de
tec
te
d
m
i
nu
ti
ae
s
o
th
at
i
t
c
an
be
m
atc
he
d
w
i
t
h
ev
er
y
m
i
nu
t
i
a
of
the
f
ath
e
r
's
f
i
ng
erpr
i
n
t,
m
oth
er'
s
f
i
ng
erpr
i
nt,
a
nd
c
h
i
l
d's
f
i
ng
erpr
i
nt.
T
ab
l
e 2
. G
L
CM
and
F
i
n
ge
r
prin
t
pa
tt
ern us
i
ng
m
i
nu
t
i
ae
s
c
ore
No
N
a
m
e
C
o
n
t
r
a
s
t
H
o
m
o
g
e
n
i
t
y
C
o
r
r
e
lat
ion
E
n
e
r
g
y
M
inu
t
iae
P
a
t
t
e
r
n
Fa
m
il
y
1
Fathe
r
M
o
t
h
e
r
C
h
il
d
9
3
4
7
.
3
8
4
0
2
.
3
6
9
0
3
.
3
0
.
3
4
9
7
0
.
4
3
2
1
0
.
5
2
0
2
0
.
5
0
4
9
0
.
5
6
5
4
0
.
5
5
5
8
0
.
0
9
7
8
0
.
1
4
7
0
0
.
2
4
7
8
30
32
30
Loop
Loop
Loop
Fa
m
il
y
2
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
1
6
0
.
2
8
4
0
2
.
3
9
7
2
3
.
9
0
.
4
2
0
9
0
.
4
3
2
1
0
.
4
1
0
1
0
.
5
4
3
8
0
.
5
6
5
4
0
.
4
9
1
8
0
.
1
4
4
7
0
.
1
4
7
0
0
.
1
2
9
0
35
32
36
Loop
Loop
Loop
Fa
m
il
y
3
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
1
6
0
.
2
8
4
0
2
.
3
9
1
8
1
.
6
0
.
4
2
0
9
0
.
4
3
2
1
0
.
4
0
5
7
0
.
5
4
3
8
0
.
5
6
5
4
0
.
4
5
0
7
0
.
1
4
4
7
0
.
1
4
7
0
0
.
1
3
5
3
35
32
39
Loop
Loop
Loop
Fa
m
il
y
4
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
4
9
8
.
5
9
6
1
1
.
9
7
9
5
7
.
9
0
.
4
6
7
0
0
.
4
7
6
8
0
.
5
1
1
2
0
.
5
2
8
9
0
.
4
9
6
7
0
.
4
3
3
4
0
.
1
7
4
8
0
.
1
9
2
1
0
.
2
4
6
6
31
33
17
Loop
Loop
W
h
o
r
l
Fa
m
il
y
5
Fathe
r
M
o
t
h
e
r
C
h
il
d
7
5
2
5
.
4
6
6
5
9
.
4
6
5
3
0
.
0
0
.
4
5
5
3
0
.
3
6
6
9
0
.
5
0
6
0
0
.
5
4
8
7
0
.
5
9
1
9
0
.
4
8
6
8
0
.
1
6
7
8
0
.
1
8
6
4
0
.
2
4
3
7
28
35
20
W
h
o
r
l
Loop
W
h
o
r
l
Fa
m
il
y
6
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
9
7
1
0
.
9
0
.
3
8
4
6
0
.
3
2
2
9
0
.
3
3
5
5
0
.
4
8
4
5
0
.
4
0
8
2
0
.
4
6
1
9
0
.
1
1
8
3
0
.
0
8
4
0
0
.
0
9
2
4
32
39
38
Loop
Loop
Loop
Fa
m
il
y
7
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
9
0
3
4
.
0
0
.
3
8
4
6
0
.
3
2
2
9
0
.
3
6
0
7
0
.
4
8
4
5
0
.
4
0
8
2
0
.
4
3
7
1
0
.
1
1
8
3
0
.
0
8
4
0
0
.
1
0
4
8
32
39
45
Loop
Loop
W
h
o
r
l
Fa
m
il
y
8
Fathe
r
M
o
t
h
e
r
C
h
il
d
8
7
5
1
.
3
10448
7
4
9
0
.
3
0
.
3
8
4
6
0
.
3
2
2
9
0
.
4
6
7
2
0
.
4
8
4
5
0
.
4
0
8
2
0
.
5
1
3
4
0
.
1
1
8
3
0
.
0
8
4
0
0
.
1
9
0
5
32
39
53
Loop
Loop
W
h
o
r
l
Fa
m
il
y
9
Fathe
r
M
o
t
h
e
r
C
h
il
d
7
3
1
3
.
2
8
4
7
0
.
9
8
2
5
4
.
4
0
.
3
7
9
9
0
.
4
8
7
5
0
.
4
9
2
1
0
.
6
1
7
0
0
.
4
8
9
8
0
.
5
3
9
7
0
.
1
1
3
7
0
.
2
1
2
8
0
.
2
1
3
2
31
30
39
Loop
Loop
Loop
Fa
m
il
y
1
0
Fathe
r
M
o
t
h
e
r
C
h
il
d
9
8
0
1
.
7
9
0
5
3
.
9
12617
0
.
3
4
5
2
0
.
3
4
1
1
0
.
3
7
6
4
0
.
4
5
6
5
0
.
5
2
8
2
0
.
3
7
9
3
0
.
0
9
6
7
0
.
0
9
0
9
0
.
1
1
4
4
52
51
52
Loop
Loop
Loop
Fa
m
il
y
1
1
Fathe
r
M
o
t
h
e
r
C
h
il
d
10374
7
8
5
2
.
2
5
9
1
8
.
9
0
.
3
2
2
7
0
.
4
3
4
1
0
.
4
6
0
4
0
.
4
1
1
7
0
.
5
7
5
4
0
.
6
8
9
9
0
.
0
8
2
9
0
.
1
5
1
8
0
.
1
6
9
1
41
41
42
Loop
Loop
Loop
5
. Con
clus
ion
In
th
i
s
s
tud
y
pres
en
ts
t
w
o
m
eth
od
s
of
f
i
ng
erpr
i
nt
c
l
as
s
i
f
i
c
ati
on
of
pa
r
e
nts
an
d
c
h
i
l
dre
n.
T
he
r
e
are
tw
o
m
aj
or
c
on
tr
i
bu
ti
on
s
to
r
es
ea
r
c
h.
T
he
f
i
r
s
t
i
s
f
i
ng
erpr
i
nt
ex
tr
ac
ti
o
n
u
s
i
ng
G
LCM
to
ge
t
th
e
v
a
l
u
e
of
a
f
ea
ture.
T
he
s
ec
on
d
i
s
the
us
e
of
the
m
i
nu
ti
a
e
s
c
ore
m
eth
od
f
or
m
atc
hi
ng
f
i
ng
erpr
i
n
t
p
att
erns
.
G
L
CM
i
s
al
s
o
us
ed
to
pe
r
f
orm
f
i
ng
erpr
i
nt
a
na
l
y
s
i
s
.
T
he
da
t
a
us
ed
are
11
f
a
m
i
l
y
f
i
ng
erpr
i
nts
c
o
ns
i
s
ti
ng
of
c
hi
l
d
f
i
n
ge
r
pri
nt,
f
ath
er'
s
f
i
ng
erpr
i
nt
,
m
oth
er'
s
f
i
ng
erpr
i
nt.
T
he
m
o
s
t
do
m
i
na
nt
pa
tt
ern
i
s
t
he
l
o
op
p
att
er
n.
T
he
s
uc
c
es
s
r
ate
of
the
m
i
nu
ti
ae
ex
tr
ac
ti
on
proc
es
s
de
pe
nd
s
he
av
i
l
y
o
n
the
qu
al
i
t
y
of
the
f
i
n
ge
r
pri
nt
i
m
a
ge
.
Im
ag
e
ob
ta
i
ne
d
w
i
t
h
l
o
w
i
m
ag
e
qu
al
i
t
y
c
an
r
es
ul
t
i
n m
i
nu
t
i
ae
proc
e
s
s
i
s
no
t m
ax
i
m
al
s
o m
i
nu
ti
ae
c
an
no
t
be
f
ou
n
d.
Ref
er
en
ce
s
[1
]
So
m
a
n
MA
,
Av
a
d
h
a
n
i
R,
J
a
c
o
b
M
,
Nal
l
a
th
a
m
b
y
R.
Stu
d
y
o
f
Fi
n
g
e
r
p
ri
n
t
P
a
tt
e
r
n
s
i
n
Rel
a
t
i
o
n
s
h
i
p
w
i
th
Bl
o
o
d
g
ro
u
p
a
n
d
G
e
n
d
e
r
.
Res
e
a
rc
h
J
o
u
rn
a
l
o
f
F
o
re
n
s
i
c
Sc
i
e
n
c
e
s
.
2
0
1
3
;
1
(1
):
1
5
-
1
7
.
[2
]
Che
n
W
,
G
a
o
Y
.
A
M
i
n
u
ti
a
e
-
b
a
s
e
d
Fi
n
g
e
rp
ri
n
t
M
a
tc
h
i
n
g
Al
g
o
ri
th
m
Us
i
n
g
Ph
a
s
e
Corre
l
a
t
i
o
n
.
Dig
i
ta
l
Im
a
g
e
Co
m
p
u
ti
n
g
T
e
c
h
n
i
q
u
e
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
.
2
0
0
7
;
233
-
2
3
8
.
[3
]
M
o
h
a
n
i
a
h
P,
Sa
th
y
a
n
a
ra
y
a
n
a
,
G
u
ru
Ku
m
a
r
L
.
I
m
a
g
e
T
e
x
tu
re
Fe
a
tu
re
Ex
tra
c
ti
o
n
Us
i
n
g
G
L
CM
Ap
p
ro
a
c
h
.
I
n
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
c
i
e
n
ti
f
i
c
a
n
d
R
e
s
e
a
rc
h
P
u
b
l
i
c
a
t
i
o
n
s
.
2
0
1
3
;
3
(5
):
1
-
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KO
M
NIK
A
IS
S
N: 1
69
3
-
6
93
0
F
i
ng
er
prin
t
P
a
tte
r
n
of
Ma
tc
hi
n
g Fam
i
l
y
W
i
th
G
LC
M Fe
atu
r
e
(
B
ah
t
i
ar I
mran
)
1869
[4
]
Pa
th
a
k
B,
Ba
r
o
o
a
h
D.
T
e
x
tu
re
An
a
l
y
s
i
s
B
a
s
e
d
o
n
th
e
G
ra
y
-
L
e
v
e
l
Co
-
o
c
c
u
rre
n
c
e
M
a
tri
x
C
o
n
s
i
d
e
ri
n
g
Po
s
s
i
b
l
e
O
ri
e
n
t
a
t
i
o
n
s
.
In
te
r
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
r
c
h
i
n
El
e
c
tr
i
c
a
l
,
El
e
c
tro
n
i
c
s
a
n
d
In
s
tru
m
e
n
ta
ti
o
n
En
g
i
n
e
e
ri
n
g
.
2
0
1
3
;
2
(
9
):
4
2
0
6
-
4
2
1
2
.
[5
]
M
i
s
h
ra
A,
M
a
h
e
s
h
w
a
ri
P.
An
E
ff
i
c
i
e
n
t
Sy
s
te
m
f
o
r
F
i
n
g
e
rp
ri
n
t
Fi
n
g
e
r
Pri
n
t
M
a
tc
h
i
n
g
a
n
d
C
l
a
s
s
i
f
i
c
a
ti
o
n
.
In
te
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
Com
p
u
te
r
S
c
i
e
n
c
e
a
n
d
So
f
twa
re
En
g
i
n
e
e
r
i
n
g
.
2
0
1
3
;
3
(1
1
):
2
9
5
-
3
0
0
.
[6
]
K
K
B
Vi
j
a
y
a
k
u
m
a
r
.
Fi
n
g
e
rp
ri
n
t
M
a
tc
h
i
n
g
b
y
Ex
t
ra
c
t
i
n
g
G
L
C
M
Fe
a
tu
re
s
.
In
t
e
rn
a
t
i
o
n
a
l
Co
n
fe
re
n
c
e
&
W
o
r
k
s
h
o
p
o
n
Rec
e
n
t
T
re
n
d
s
i
n
T
e
c
h
n
o
l
o
g
y
Pro
c
e
e
d
i
n
g
s
p
u
b
l
i
s
h
e
d
i
n
I
n
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Com
p
u
t
e
r Ap
p
l
i
c
a
ti
o
n
s
®
(
I
J
CA
),
(T
CET
).
2
0
1
2
:
30
-
34
[7
]
Ve
rm
a
P
,
Ba
h
e
n
d
w
a
r
Y
,
Sa
h
u
A,
Du
b
e
y
A.
F
e
a
tu
re
Ex
tra
c
ti
o
n
A
l
g
o
r
i
th
m
o
f
Fi
n
g
e
r
p
ri
n
t
R
e
c
o
g
n
i
ti
o
n
.
In
te
rn
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Re
s
e
a
r
c
h
i
n
Com
p
u
te
r
S
c
i
e
n
c
e
a
n
d
So
f
twa
re
En
g
i
n
e
e
r
i
n
g
.
2
0
1
2
;
2
(1
0
):
2
9
2
-
2
9
7
.
[8
]
Ab
ra
h
a
m
AT
,
M
Y
K.
G
e
n
o
ty
p
i
n
g
-
W
a
v
e
l
e
t
Ap
p
r
o
a
c
h
.
I
n
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Sc
i
e
n
c
e
a
n
d
Res
e
a
r
c
h
(IJ
SR)
.
2
0
1
3
;
4
(2
):
1
0
2
5
-
1
0
2
7
.
[9
]
Su
h
a
rj
i
to
,
I
m
ra
n
B,
G
i
rs
a
n
g
A
S.
Fa
m
i
l
y
Rel
a
t
i
o
n
s
h
i
p
Id
e
n
ti
f
i
c
a
ti
o
n
b
y
Us
i
n
g
Ex
tra
c
t
Fe
a
tu
re
o
f
G
ra
y
L
e
v
e
l
Co
-
o
c
c
u
rre
n
c
e
M
a
tri
x
(G
L
CM
) Ba
s
e
d
o
n
Pa
r
e
n
t
s
a
n
d
C
h
i
l
d
r
e
n
F
i
n
g
e
r
p
ri
n
t
.
In
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
te
r E
n
g
i
n
e
e
r
i
n
g
(I
J
ECE).
2
0
1
7
;
7
(5
)
:
2
7
3
8
-
2
7
4
5
.
[1
0
]
M
a
ts
u
y
a
m
a
N,
It
o
Y
.
T
h
e
Fre
q
u
e
n
c
y
o
f
Fi
n
g
e
rp
r
i
n
t
T
y
p
e
i
n
Pa
re
n
t
s
o
f
Chi
l
d
re
n
w
i
th
T
ri
s
o
m
y
2
1
i
n
J
a
p
a
n
.
J
o
u
rn
a
l
o
f
Ph
y
s
i
o
l
o
g
i
c
a
l
An
th
r
o
p
o
l
o
g
y
.
2
0
0
6
:
1
5
-
2
1
.
[1
1
]
Ab
u
ra
s
AA,
R
a
h
i
e
l
S
A.
F
i
n
g
e
r
p
ri
n
t
Pa
tt
e
rn
s
Rec
o
g
n
i
ti
o
n
Sy
s
te
m
Us
i
n
g
Hu
ff
m
a
n
Cod
i
n
g
.
Pr
o
c
e
e
d
i
n
g
s
o
f
th
e
W
o
rl
d
Co
n
g
re
s
s
o
n
En
g
i
n
e
e
ri
n
g
.
L
o
n
d
o
n
,
U.K.
2
0
0
8
;
II
I
.
Evaluation Warning : The document was created with Spire.PDF for Python.