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.
7
,
No
.
5
,
Octo
b
e
r
2
0
1
7
,
p
p
.
2
5
4
7
~2
554
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
5
.
pp
2
5
4
7
-
2554
2547
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
A Nov
el 2D
Featu
re Ex
traction M
e
t
ho
d f
o
r F
i
ng
erpri
nts Using
M
inutiae Poin
ts a
nd Their
Interse
c
tions
Nibra
s
Ar
Ra
k
ib
, S
M
Z
a
m
s
hed F
a
rha
n
,
M
d
M
a
s
hrur
B
a
ri
So
bh
a
n,
J
ia
Uddi
n,
Ara
f
a
t
H
a
bib
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
BRA
C
Un
iv
e
rsity
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
5
,
2
0
1
7
R
ev
i
s
ed
J
u
n
1
7
,
2
0
1
7
A
cc
ep
ted
A
ug
11
,
2
0
1
7
T
h
e
f
ield
o
f
b
io
m
e
tri
c
s
h
a
s
e
v
o
lv
e
d
trem
e
n
d
o
u
sly
f
o
r
o
v
e
r
th
e
la
st
c
e
n
tu
ry
.
Ye
t
sc
ien
ti
sts
a
re
stil
l
c
o
n
ti
n
u
i
n
g
to
c
o
m
e
u
p
w
it
h
p
re
c
ise
a
n
d
e
f
f
ici
e
n
t
a
lg
o
rit
h
m
s
to
fa
c
il
it
a
te
a
u
to
m
a
ti
c
f
in
g
e
rp
rin
t
re
c
o
g
n
it
io
n
sy
st
e
m
s.
L
ik
e
o
th
e
r
a
p
p
li
c
a
ti
o
n
s,
a
n
e
f
f
i
c
ien
t
f
e
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
p
lay
s
a
n
i
m
p
o
rtan
t
ro
le
i
n
f
in
g
e
rp
ri
n
t
b
a
se
d
re
c
o
g
n
it
i
o
n
sy
s
tem
s.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
o
v
e
l
f
e
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
u
sin
g
m
in
u
ti
a
e
p
o
in
ts
o
f
a
f
in
g
e
rp
rin
t
im
a
g
e
a
n
d
th
e
ir
in
ters
e
c
ti
o
n
s.
I
n
t
h
is
m
e
th
o
d
,
i
n
it
ially
,
it
c
a
lcu
late
s
th
e
rid
g
e
e
n
d
s
a
n
d
ri
d
g
e
b
if
u
rc
a
ti
o
n
s
o
f
e
a
c
h
f
in
g
e
rp
rin
t
i
m
a
g
e
.
A
n
d
th
e
n
,
it
e
stim
a
tes
th
e
m
in
u
ti
a
e
p
o
i
n
ts
f
o
r
th
e
i
n
ters
e
c
ti
o
n
o
f
e
a
c
h
rid
g
e
e
n
d
a
n
d
rid
g
e
b
if
u
rc
a
ti
o
n
.
In
t
h
e
e
x
p
e
ri
m
e
n
tal
e
v
a
lu
a
ti
o
n
,
w
e
tes
ted
th
e
e
x
trac
ted
f
e
a
tu
re
s
o
f
o
u
r
p
ro
p
o
se
d
m
o
d
e
l
u
sin
g
a
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(S
VM)
c
las
sif
ier
a
n
d
e
x
p
e
rim
e
n
tal
re
su
lt
s
sh
o
w
th
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
c
a
n
a
c
c
u
ra
tely
c
las
si
fy
d
iffere
n
t
f
in
g
e
rp
rin
t
im
a
g
e
s.
K
ey
w
o
r
d
s
:
Featu
r
e
ex
tr
ac
tio
n
Fin
g
er
p
r
in
t i
m
ag
e
s
Min
u
tiae
P
o
in
ts
Su
p
p
o
r
t V
ec
to
r
Ma
ch
in
e
Co
p
y
rig
h
t
©
2
0
1
7
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
:
J
ia
Ud
d
in
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
i
n
ee
r
in
g
,
B
R
AC
U
n
iv
er
s
it
y
,
6
6
Mo
h
ak
h
ali,
D
h
ak
a
-
1
2
1
2
,
B
an
g
lad
e
s
h
E
m
ail:
j
ia.
u
d
d
in
@
b
r
ac
u
.
ac
.
b
d
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
p
o
ten
tial
o
f
t
h
e
u
s
e
o
f
f
i
n
g
er
p
r
in
t
s
h
as
lo
n
g
b
ee
n
r
ec
o
g
n
ized
as
a
f
u
n
d
a
m
e
n
tal
o
n
e.
On
e
o
f
t
h
e
ea
r
lies
t
in
s
tan
ce
s
o
f
th
is
ca
n
b
e
f
o
u
n
d
in
th
e
co
n
tr
ib
u
tio
n
s
o
f
J
o
h
n
E
d
g
ar
Ho
o
v
er
,
th
e
f
ir
s
t
Dir
ec
to
r
o
f
th
e
Fed
er
al
B
u
r
ea
u
o
f
I
n
v
e
s
ti
g
ati
o
n
,
w
h
e
n
h
e
cr
ea
ted
o
n
e
o
f
l
ar
g
est
d
atab
ases
o
f
f
i
n
g
er
p
r
in
ts
to
d
ate.
A
s
s
u
c
h
,
f
i
n
g
er
p
r
in
t
h
as
b
ec
o
m
e
a
co
m
m
o
n
r
ef
er
e
n
ce
p
o
in
t
f
o
r
id
en
ti
f
y
in
g
a
h
u
m
a
n
b
ein
g
,
s
i
n
ce
it
h
ap
p
en
s
to
b
e
u
n
iq
u
e
f
o
r
a
p
er
s
o
n
.
Fin
g
er
p
r
in
ts
,
w
h
e
n
a
n
al
y
ze
d
,
r
ev
ea
l
u
n
e
v
en
f
lo
w
o
f
th
e
ir
u
n
iq
u
e
p
atter
n
s
ca
lled
r
id
g
e
s
.
A
r
id
g
e
is
d
efin
ed
as
a
s
i
n
g
le
cu
r
v
ed
s
e
g
m
en
t,
an
d
a
v
alle
y
i
s
t
h
e
r
e
g
io
n
b
et
w
ee
n
t
w
o
ad
j
ac
en
t
r
id
g
es
[
1
]
.
T
h
e
p
atter
n
o
f
r
id
g
es
al
s
o
co
n
s
is
t
s
o
f
u
n
e
v
e
n
d
is
co
n
ti
n
u
i
ties
a
t
s
e
v
er
al
p
o
in
ts
,
k
n
o
w
n
a
s
m
i
n
u
tiae
p
o
i
n
ts
.
T
h
e
p
o
ten
tial
o
f
th
is
p
h
e
n
o
m
en
o
n
w
a
s
r
ea
lized
w
h
en
C
h
i
-
J
i
m
[
2
]
s
h
o
w
ed
a
s
m
o
o
t
h
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
,
a
th
o
r
o
u
g
h
an
al
y
s
i
s
o
f
f
i
n
g
er
p
r
in
ts
,
its
i
n
d
ex
in
g
p
r
o
ce
d
u
r
es a
n
d
h
o
w
th
e
s
e
ca
n
b
e
u
s
ed
later
to
id
en
ti
f
y
a
h
u
m
a
n
b
ein
g
[
3
-
5
]
.
T
h
e
m
i
n
u
tiae
f
ea
tu
r
es
ar
e
co
n
s
id
er
ed
to
b
e
a
m
aj
o
r
f
ea
tu
r
e
o
f
b
io
m
e
tr
ics
an
d
i
n
clu
d
e
s
e
v
er
al
p
ar
ts
–
r
id
g
e
en
d
i
n
g
s
,
r
id
g
e
b
if
u
r
ca
ti
o
n
s
,
i
s
lan
d
,
co
r
e,
d
elta,
b
r
id
g
e
o
r
cr
o
s
s
o
v
er
,
r
id
g
e
e
n
clo
s
u
r
e,
s
h
o
r
t
r
id
g
e,
s
p
u
r
,
etc.
B
u
t,
f
o
r
t
h
e
p
u
r
p
o
s
e
o
f
id
en
ti
f
icatio
n
u
s
i
n
g
f
i
n
g
er
p
r
in
t
s
m
o
s
tl
y
o
n
l
y
t
w
o
o
f
th
e
s
e
f
ea
t
u
r
es
ar
e
s
i
g
n
if
ican
t
:
r
id
g
e
en
d
in
g
s
a
n
d
r
id
g
e
b
if
u
r
ca
tio
n
s
,
as
s
h
o
w
n
in
F
ig
u
r
e
1
.
R
id
g
e
b
if
u
r
ca
tio
n
s
ar
e
th
e
p
o
in
ts
w
h
er
e
a
r
id
g
e
g
ets
d
i
v
id
ed
in
to
t
w
o
a
n
d
r
id
g
e
en
d
in
g
s
ar
e
th
o
s
e
p
o
in
t
s
w
h
er
e
th
e
r
id
g
es
g
et
ter
m
i
n
ated
.
T
h
ese
f
ea
tu
r
e
s
ar
e
u
n
iq
u
e
f
o
r
a
h
u
m
an
b
ei
n
g
a
n
d
th
u
s
h
e
lp
in
t
h
e
id
en
ti
f
icatio
n
an
d
v
er
if
icatio
n
p
r
o
ce
s
s
es.
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.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
4
7
–
2
5
5
4
2548
Fig
u
r
e
1
.
Fin
g
er
p
r
in
t i
m
ag
e
s
h
o
w
i
n
g
r
id
g
e
s
,
r
id
g
e
en
d
i
n
g
s
a
n
d
r
id
g
e
b
if
u
r
ca
t
io
n
s
.
T
h
er
e
a
r
e
tw
o
s
tep
s
in
v
o
lv
e
d
w
ith
m
atch
in
g
:
r
eg
is
t
r
ati
o
n
an
d
v
e
r
if
ic
ati
o
n
.
I
n
th
e
r
eg
is
tr
ati
o
n
s
te
p
,
al
l
f
in
g
er
p
r
in
ts
o
f
a
s
e
t
o
f
p
e
r
s
o
n
ar
e
c
ap
tu
r
ed
,
p
r
o
ce
s
s
ed
an
d
s
t
o
r
e
d
as
a
tem
p
lat
e
w
h
ich
is
m
u
ch
s
m
aller
th
an
th
e
o
r
ig
in
al
im
ag
e,
in
a
d
ata
b
as
e
f
o
r
l
ate
r
u
s
e
[
6
-
7
]
.
I
n
th
e
v
e
r
if
i
ca
ti
o
n
s
te
p
,
a
p
er
s
o
n
g
iv
es
h
is
f
in
g
er
p
r
in
t
t
o
v
er
if
y
th
e
i
d
en
t
ity
-
th
e
f
in
g
e
r
p
r
in
t
is
co
m
p
a
r
e
d
w
ith
th
e
o
n
es
s
t
o
r
e
d
in
th
e
d
a
ta
b
as
e
[
3
]
.
I
n
th
is
p
a
p
e
r
,
a
s
et
o
f
f
in
g
er
p
r
in
ts
o
f
d
if
f
er
en
t
p
e
r
s
o
n
n
el
is
ch
o
s
en
at
r
an
d
o
m
an
d
th
e
r
i
d
g
e
en
d
in
g
p
o
in
ts
al
o
n
g
w
ith
th
e
b
if
u
r
ca
ti
o
n
p
o
in
ts
ar
e
f
o
u
n
d
o
u
t
f
r
o
m
th
e
f
in
g
er
p
r
in
ts
.
T
h
es
e
a
r
e
th
e
n
p
r
o
c
ess
e
d
f
u
r
th
e
r
u
s
in
g
f
ilter
in
g
te
ch
n
iq
u
e,
n
am
ely
s
in
g
le
-
lev
el
2
-
D
D
is
c
r
et
e
W
av
e
let
T
r
an
s
f
o
r
m
(
DW
T
)
,
t
o
f
in
d
an
in
cr
ea
s
ed
n
u
m
b
er
o
f
p
o
in
ts
an
d
th
u
s
o
p
ti
m
izin
g
th
e
w
h
o
le
p
r
o
c
e
d
u
r
e
.
T
h
ey
ar
e
th
en
p
l
o
tt
e
d
an
d
jo
in
ed
t
o
m
ak
e
s
ep
a
r
at
e
b
est
f
it
cu
r
v
es
.
T
h
e
p
o
in
ts
w
h
er
e
th
e
cu
r
v
es
in
t
e
r
s
ec
t
ar
e
f
o
u
n
d
.
T
h
is
p
a
p
e
r
p
r
o
p
o
s
es
th
at
th
ese
in
te
r
s
e
cti
o
n
p
o
in
ts
ar
e
u
n
iq
u
e
f
o
r
d
if
f
e
r
e
n
t
h
u
m
an
b
ein
g
s
an
d
th
e
as
s
u
m
p
tio
n
is
p
r
o
v
en
f
u
r
th
er
t
h
r
o
u
g
h
th
e
u
s
e
o
f
clu
s
te
r
in
g
.
F
in
ally
,
th
e
m
ac
h
in
e
le
ar
n
in
g
t
ec
h
n
i
q
u
e,
Su
p
p
o
r
t
Ve
ct
o
r
Ma
ch
in
e
(
SV
M)
is
u
s
ed
t
o
cl
ass
if
y
th
e
f
in
g
er
p
r
in
ts
ef
f
icien
t
ly
.
Ho
w
ev
er
,
th
e
r
ec
en
t
p
e
r
f
o
r
m
an
ce
c
o
m
p
ar
is
o
n
in
th
e
a
r
ea
o
f
f
in
g
er
p
r
in
t
d
e
p
en
d
s
o
n
h
o
w
f
ar
th
e
a
cc
y
r
ac
y
,
ef
f
icac
y
an
d
s
ca
la
b
il
ity
p
e
r
f
o
r
m
an
ce
ca
n
b
e
in
cr
ea
s
e
d
[
8
-
1
3
]
.
Fin
g
er
p
r
in
t
i
m
a
g
e
s
e
g
m
en
ta
t
io
n
is
a
n
i
m
p
o
r
tan
t
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
tep
i
n
au
to
m
atic
f
in
g
er
p
r
in
t
r
ec
o
g
n
itio
n
s
y
s
te
m
a
n
d
a
w
e
ll
-
d
esi
g
n
ed
f
i
n
g
er
p
r
in
t
s
e
g
m
e
n
tatio
n
tech
n
iq
u
e
ca
n
i
m
p
r
o
v
e
th
e
ac
c
u
r
ac
y
i
n
co
llectin
g
clea
r
f
i
n
g
er
p
r
in
t
a
r
ea
an
d
m
ar
k
n
o
is
e
ar
ea
s
[
1
4
]
.
T
o
o
v
er
co
m
e
th
e
li
m
it
atio
n
o
f
th
e
w
o
r
k
s
m
en
tio
n
ed
ab
o
v
e,
A
No
v
el
2
D
Feat
u
r
e
E
x
tr
ac
t
io
n
Me
t
h
o
d
f
o
r
Fi
n
g
er
p
r
in
t
s
U
s
i
n
g
Mi
n
u
t
i
ae
P
o
in
ts
a
n
d
T
h
eir
I
n
ter
s
ec
tio
n
s
h
a
s
b
ee
n
p
r
p
o
s
ed
in
th
i
s
ar
ticle.
T
h
e
r
est
o
f
th
e
p
ap
er
is
o
r
g
a
n
ized
as
f
o
llo
w
s
-
Sectio
n
I
I
p
r
o
v
id
es
a
d
etailed
o
v
er
v
ie
w
o
f
th
e
s
tep
s
o
f
th
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
,
Sec
tio
n
I
I
I
in
cl
u
d
es
t
h
e
r
esu
lt
s
o
f
t
h
e
ex
p
er
i
m
e
n
t
s
ca
r
r
ied
o
u
t a
n
d
th
eir
an
a
l
y
s
is
a
n
d
Sectio
n
I
V
co
n
cl
u
d
es th
e
p
ap
e
r
.
2.
P
R
OP
OS
E
D
F
E
A
T
UR
E
E
X
T
RAC
T
I
O
N
M
E
T
H
O
D
T
o
ca
r
r
y
o
u
t
th
e
e
x
tr
ac
tio
n
o
f
f
ea
t
u
r
es
an
d
th
e
cla
s
s
i
f
ica
tio
n
s
a
s
et
o
f
s
tep
s
h
as
b
ee
n
ca
r
ef
u
ll
y
d
esig
n
ed
.
A
b
lo
ck
d
iag
r
a
m
o
f
p
r
o
p
o
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
is
p
r
esen
ted
in
Fig
u
r
e
2
.
T
o
v
alid
ate
th
e
p
r
o
p
o
s
ed
m
o
d
el,
a
s
et
o
f
f
in
g
er
p
r
in
t
i
m
a
g
es
is
tak
e
n
f
r
o
m
th
e
in
ter
n
et
an
d
t
h
e
n
co
n
v
er
ted
in
to
g
r
a
y
le
v
el
i
m
a
g
es
w
it
h
a
s
ize
3
0
0
×3
0
0
.
T
h
e
i
m
ag
e
i
s
th
e
n
p
r
o
ce
s
s
ed
u
s
in
g
an
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e,
w
h
ic
h
i
s
clea
r
l
y
d
escr
ib
e
in
th
e
f
o
llo
w
i
n
g
s
u
b
-
s
ec
tio
n
A
.
T
h
is
i
s
d
o
n
e
to
m
ak
e
s
u
r
e
t
h
at
t
h
e
m
i
n
u
t
iae
f
ea
tu
r
es
o
f
t
h
e
f
i
n
g
er
p
r
in
t
ar
e
v
er
y
m
u
ch
v
i
s
ib
le
,
as
it
ca
n
th
e
n
b
e
f
ed
to
o
th
er
p
r
o
ce
s
s
es
as
p
er
r
eq
u
ir
e
m
en
ts
.
I
n
t
h
is
p
ap
er
,
s
ev
en
f
i
n
g
er
p
r
in
t i
m
a
g
es
w
er
e
u
s
ed
to
test
o
u
r
p
r
o
p
o
s
ed
m
o
d
el
.
2
.
1
.
I
m
a
g
e
P
ro
ce
s
s
ing
Fo
r
a
f
in
g
er
p
r
in
t
i
m
ag
e,
a
p
o
r
tio
n
o
f
th
e
f
i
n
g
er
p
r
in
t
is
f
ir
s
t
s
elec
ted
an
d
cr
o
p
p
ed
,
as
d
o
in
g
o
th
er
w
is
e
w
o
u
ld
p
r
o
d
u
ce
to
o
m
u
c
h
in
f
o
r
m
at
io
n
.
On
t
h
at
p
ar
ticu
lar
s
elec
tio
n
,
i
m
ag
e
p
r
o
ce
s
s
i
n
g
t
ec
h
n
iq
u
e
is
ap
p
lied
,
w
h
ic
h
w
o
u
ld
u
l
ti
m
atel
y
co
n
v
er
t
th
e
i
m
a
g
e
i
n
to
it
s
b
i
n
ar
y
f
o
r
m
at,
w
h
er
e
ea
c
h
p
i
x
el
i
s
r
e
p
r
esen
ted
b
y
1
-
b
it.
T
h
e
b
in
ar
y
i
m
ag
e
o
f
t
h
e
f
i
n
g
e
r
p
r
in
t
is
t
h
en
f
u
r
t
h
er
th
i
n
n
ed
t
o
r
ev
ea
l
th
e
m
i
n
u
tiae
p
o
in
t
s
.
T
h
e
r
id
g
e
en
d
s
a
n
d
th
e
r
id
g
e
b
i
f
u
r
ca
tio
n
s
ar
e
p
o
in
ted
o
u
t,
as
d
ep
icted
in
Fi
g
u
r
e
3
,
an
d
in
t
h
e
n
e
x
t
s
ec
tio
n
t
h
ese
ar
e
f
ilter
ed
to
o
p
tim
ize
r
esu
l
ts
.
2
.
2
.
Appl
y
ing
2
-
D
Wa
v
elet
T
ra
ns
f
o
r
m
As
m
en
tio
n
ed
ea
r
lier
,
to
o
p
ti
m
ize
t
h
e
p
r
o
ce
s
s
o
f
f
i
n
d
in
g
o
u
t
t
h
e
m
i
n
u
tiae
f
ea
t
u
r
es
o
f
t
h
e
f
i
n
g
er
p
r
in
t
i
m
a
g
es
t
h
e
y
ar
e
f
ilter
ed
u
s
i
n
g
s
o
m
e
f
il
ter
in
g
tec
h
n
iq
u
e
s
.
A
t
f
ir
s
t
t
h
e
s
i
n
g
le
-
lev
e
l
2
-
D
D
W
T
w
as
ap
p
lied
o
n
th
e
i
m
a
g
e.
T
h
e
2
-
D
w
a
v
elets
ar
e
u
s
ed
in
a
n
u
m
b
er
o
f
ar
ea
s
,
m
o
s
t
n
o
tab
l
y
in
i
m
a
g
e
m
a
n
i
p
u
latio
n
an
d
h
elp
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
N
o
ve
l 2
D
F
ea
tu
r
e
E
xtra
ctio
n
Meth
o
d
fo
r
F
in
g
erp
r
in
ts
Usi
n
g
Min
u
tia
e
P
o
in
ts
a
n
d
Th
eir
I
n
ters
ec
tio
n
s
(
N
ib
r
a
s
A
r
R
a
kib
)
2549
w
it
h
d
e
-
n
o
i
s
in
g
[
1
0
]
.
2
-
D
w
a
v
elet
w
o
r
k
s
w
it
h
ap
p
r
o
x
i
m
ati
o
n
co
ef
f
icie
n
ts
m
atr
i
x
-
cA
a
n
d
d
etails
co
ef
f
icie
n
ts
m
atr
ices
-
cH,
cV
,
a
n
d
cD
(
h
o
r
izo
n
tal,
v
er
tical,
a
n
d
d
iag
o
n
al
)
,
b
u
t
w
e
h
a
v
e
o
n
l
y
u
s
ed
th
e
v
er
tical
o
n
e,
cV
[
6
]
.
T
h
is
is
b
ec
au
s
e,
w
h
ile
h
ig
h
-
f
r
eq
u
en
c
y
co
m
p
o
n
en
ts
ca
n
ca
p
t
u
r
e
d
is
co
n
ti
n
u
i
ties
,
r
u
p
tu
r
e
s
an
d
s
in
g
u
lar
ities
i
n
th
e
o
r
ig
i
n
al
d
ata,
lo
w
-
f
r
eq
u
e
n
c
y
co
m
p
o
n
en
t
s
ch
ar
ac
ter
ize
th
e
co
ar
s
e
s
tr
u
ct
u
r
e
o
f
th
e
d
ata,
to
id
en
tify
t
h
e
lo
n
g
-
ter
m
tr
en
d
s
i
n
th
e
o
r
i
g
in
a
l d
ata
[
9
]
.
Fig
u
r
e
2
.
B
lo
ck
d
iag
r
a
m
co
n
s
i
s
tin
g
o
f
t
h
e
s
tep
s
f
o
llo
w
ed
f
o
r
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
v
er
i
f
icatio
n
.
2
.
3
.
P
lo
t
s
a
nd
I
nte
rsect
ing
P
o
ints
I
n
t
h
e
n
ex
t
s
tep
t
h
e
p
r
o
d
u
ce
d
r
id
g
e
e
n
d
s
a
n
d
th
e
b
if
u
r
ca
tio
n
s
ar
e
p
lo
tted
s
ep
ar
atel
y
.
T
h
e
p
o
in
ts
o
n
ea
ch
o
f
t
h
e
b
if
u
r
ca
tio
n
a
n
d
r
id
g
e
en
d
p
lo
ts
ar
e
t
h
en
j
o
in
ed
to
g
eth
er
to
p
r
o
d
u
ce
a
b
est
f
it
li
n
e
f
o
r
ea
ch
o
f
t
h
e
m
.
W
h
ile
w
e
ar
e
f
i
n
d
in
g
b
i
f
u
r
ca
tio
n
p
o
in
t
f
r
o
m
i
m
a
g
e,
w
e
r
e
p
r
esen
t
t
h
e
m
as
r
o
w
a
n
d
co
lu
m
n
.
Fro
m
i
m
a
g
e,
b
if
u
r
ca
tio
n
p
o
in
ts
r
et
u
r
n
ed
as
th
e
r
o
w
a
n
d
co
lu
m
n
s
u
b
s
cr
ip
t
o
f
n
o
n
ze
r
o
ele
m
e
n
t.
Sa
m
e
p
r
o
ce
d
u
r
e
f
o
llo
w
s
to
p
lo
t
r
id
g
e.
T
h
ese
t
w
o
p
lo
ts
ar
e
th
en
m
ap
p
ed
o
n
to
ea
ch
o
th
e
r
,
as
s
h
o
w
n
b
elo
w
,
Fi
g
u
r
e
5
,
an
d
m
er
g
ed
to
f
in
d
o
u
t th
e
i
n
ter
s
ec
ti
n
g
p
o
in
ts
b
et
w
ee
n
th
e
m
.
Fig
u
r
e
3
.
Fin
g
er
p
r
in
t
w
it
h
r
id
g
e
en
d
s
(
r
ed
)
,
an
d
r
id
g
e
b
if
u
r
ca
tio
n
s
(
b
lu
e)
.
T
h
e
r
o
w
a
n
d
co
lu
m
n
n
u
m
b
er
i
s
r
ep
r
esen
t
f
o
r
ea
c
h
b
i
f
u
r
ca
tio
n
a
n
d
r
id
g
e
a
n
d
it
is
r
ep
r
ese
n
te
d
in
X
a
n
d
Y
ax
i
s
r
e
s
p
ec
tiv
el
y
.
D
u
r
in
g
th
e
f
i
n
d
i
n
g
o
f
in
ter
s
ec
tio
n
p
o
in
t
b
et
w
ee
n
b
i
f
u
r
ca
tio
n
a
n
d
r
id
g
e,
B
if
u
r
ca
tio
n
-
X
a
n
d
R
id
g
e
-
X
r
ep
r
esen
t
X
ax
i
s
an
d
B
if
u
r
ca
tio
n
-
Y
an
d
R
id
g
e
-
Y
r
ep
r
esen
t
Y
ax
is
.
T
h
e
p
u
r
p
o
s
e
o
f
it
to
f
in
d
o
u
t
th
e
in
ter
s
ec
ti
n
g
p
o
in
t
s
b
et
w
ee
n
t
h
e
lin
e
s
p
r
o
d
u
ce
d
f
r
o
m
t
h
e
r
id
g
e
en
d
s
a
n
d
r
id
g
e
b
if
u
r
ca
tio
n
s
.
I
t
is
n
o
ticea
b
le
t
h
a
t
th
e
in
ter
s
ec
ti
n
g
p
o
in
ts
o
f
d
i
f
f
er
en
t f
in
g
er
p
r
in
ts
ar
e
u
n
iq
u
e.
2
.
4
.
Clus
t
er
ing
a
nd
Ver
if
ica
t
io
n
Usi
n
g
th
e
p
o
in
ts
o
f
i
n
ter
s
ec
tio
n
s
f
o
u
n
d
i
n
t
h
e
ea
r
lier
s
ec
tio
n
,
a
p
lo
t is
m
ad
e
w
h
er
e
b
o
th
s
et
s
o
f
p
o
i
n
t
s
r
esid
e.
Fig
u
r
e
6
illu
s
tr
ates
an
o
v
er
v
ie
w
to
ex
a
m
in
e
w
h
et
h
er
th
e
p
o
in
ts
r
esid
e
w
ith
in
d
is
ti
n
ct
clu
s
ter
s
,
co
n
tai
n
s
G
r
a
y
L
e
v
e
l
I
mag
e
s o
f
F
i
n
g
e
r
p
r
i
n
t
s
Ex
e
c
u
t
i
o
n
o
f
S
i
n
g
l
e
-
L
e
v
e
l
D
i
scre
t
e
2
D
W
a
v
e
l
e
t
T
r
a
n
sf
o
r
mat
i
o
n
Ex
t
r
a
c
t
c
o
-
o
r
d
i
n
a
t
e
s o
f
M
i
n
u
t
i
a
e
P
o
i
n
t
s
(
B
i
f
u
r
c
a
t
i
o
n
s
a
n
d
R
i
d
g
e
s)
a
s
f
e
a
t
u
r
e
s
F
i
n
d
c
o
-
o
r
d
i
n
a
t
e
s o
f
i
n
t
e
r
se
c
t
i
o
n
p
o
i
n
t
s
b
e
t
w
e
e
n
B
i
f
u
r
c
a
t
i
o
n
s
a
n
d
R
i
d
g
e
s
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
t
h
e
i
n
t
e
r
se
c
t
i
o
n
p
o
i
n
t
s
u
s
i
n
g
S
u
p
p
o
r
t
V
e
c
t
o
r
M
a
c
h
i
n
e
s (S
V
M
)
O
u
t
p
u
t
I
mag
e
C
o
n
t
a
i
n
i
n
g
t
h
e
i
n
t
e
r
se
c
t
i
o
n
p
o
i
n
t
s
a
s
samp
l
e
s a
n
d
t
h
e
S
V
M
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.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
4
7
–
2
5
5
4
2550
d
ata
-
p
o
in
ts
f
r
o
m
s
ep
ar
ate
f
i
n
g
er
p
r
in
ts
ac
c
u
m
u
lated
to
g
et
h
er
.
A
s
d
ep
icted
in
Fig
u
r
e
6
,
th
e
p
lo
t
d
o
es
n
o
t
p
r
o
d
u
ce
a
clea
r
clu
s
ter
i
n
g
i
m
a
g
e.
So
,
t
h
e
s
a
m
e
cl
u
s
ter
is
r
ep
r
o
d
u
ce
d
f
o
r
a
p
ar
ticu
lar
r
an
g
e,
8
0
-
1
5
0
(
h
o
r
izo
n
tal)
an
d
7
0
-
1
5
0
(
v
er
tical)
,
w
h
ich
g
iv
e
s
a
clea
r
er
clu
s
ter
i
n
g
i
m
a
g
e,
as
s
h
o
w
n
in
Fi
g
u
r
e
7
.
Fro
m
t
h
e
p
lo
t,
it
is
v
er
y
m
u
c
h
ev
id
e
n
t
t
h
at,
th
e
in
ter
s
ec
tin
g
p
o
in
t
s
f
r
o
m
d
if
f
er
en
t
f
in
g
er
p
r
in
ts
m
a
k
e
s
ep
ar
ate
cl
u
s
ter
s
d
is
tin
c
tiv
e
l
y
,
m
ea
n
in
g
t
h
at
t
h
e
i
n
ter
s
ec
t
in
g
p
o
in
ts
f
r
o
m
t
h
e
r
id
g
e
e
n
d
s
a
n
d
r
id
g
e
b
if
u
r
ca
tio
n
s
ar
e
u
n
iq
u
e
an
d
th
er
e
f
o
r
e
it
is
ex
p
e
cted
th
at
it
ca
n
u
s
ed
as
a
g
o
o
d
f
ea
tu
r
e
o
f
a
f
i
n
g
er
p
r
in
t
i
m
a
g
e.
I
t
is
i
m
p
o
r
ta
n
t
t
o
class
if
y
d
if
f
er
en
t
p
er
s
o
n
n
el
u
s
i
n
g
th
e
s
e
p
ar
ticu
l
ar
f
ea
tu
r
es
t
h
r
o
u
g
h
th
e
u
s
e
o
f
s
o
m
e
m
eth
o
d
,
a
m
ac
h
i
n
e
lea
r
n
in
g
tec
h
n
iq
u
e
i
n
o
u
r
ca
s
e,
w
h
ic
h
th
e
f
o
llo
w
i
n
g
s
ec
tio
n
w
il
l d
escr
ib
e
th
o
r
o
u
g
h
l
y
.
Fig
u
r
e
4
.
Af
ter
Si
n
g
le
-
le
v
el
d
i
s
cr
ete
2
-
D
W
av
elet
tr
a
n
s
f
o
r
m
,
f
in
g
er
p
r
in
t
w
i
th
r
id
g
e
e
n
d
s
(
r
ed
)
,
an
d
r
id
g
e
b
if
u
r
ca
tio
n
s
(
b
lu
e)
Fig
u
r
e
5
.
L
in
e
s
j
o
in
in
g
t
h
e
b
if
u
r
ca
tio
n
s
a
n
d
th
e
r
id
g
e
e
n
d
in
g
s
ar
e
d
r
aw
n
o
n
to
t
h
e
s
a
m
e
p
lo
t to
f
in
d
o
u
t
t
h
e
in
ter
s
ec
ti
n
g
p
o
in
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
N
o
ve
l 2
D
F
ea
tu
r
e
E
xtra
ctio
n
Meth
o
d
fo
r
F
in
g
erp
r
in
ts
Usi
n
g
Min
u
tia
e
P
o
in
ts
a
n
d
Th
eir
I
n
ters
ec
tio
n
s
(
N
ib
r
a
s
A
r
R
a
kib
)
2551
Fig
u
r
e
6
.
Dif
f
er
en
t c
o
lo
u
r
ed
p
o
in
ts
r
ep
r
esen
t d
ata
-
p
o
in
ts
f
r
o
m
d
if
f
er
en
t f
i
n
g
er
p
r
in
t i
m
ag
e
s
.
Fig
u
r
e
7
.
P
r
ev
io
u
s
clu
s
ter
in
g
p
ictu
r
e
f
o
r
a
p
ar
ticu
lar
r
an
g
e,
8
0
-
1
5
0
(
h
o
r
izo
n
tal)
an
d
7
0
-
1
5
0
(
v
er
tical)
,
to
g
et
a
clea
r
er
clu
s
ter
in
g
i
m
a
g
e.
2
.
4
.
Cla
s
s
if
ica
t
io
n o
f
B
io
m
et
rics
T
o
class
if
y
d
i
f
f
er
e
n
t
s
et
s
o
f
f
i
n
g
er
p
r
in
t
f
ea
t
u
r
es
it
is
i
m
p
o
r
tan
t
to
u
s
e
a
m
ac
h
i
n
e
lear
n
in
g
tech
n
iq
u
e.
I
n
t
h
is
p
ap
er
,
t
h
e
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
(
SVM)
w
a
s
u
til
ized
[
1
1
,
1
2
]
.
T
h
e
SVM
i
s
a
le
ar
n
in
g
m
ac
h
i
n
e
f
o
r
t
w
o
-
g
r
o
u
p
class
i
f
icatio
n
p
r
o
b
l
e
m
s
[
4
]
.
Gen
er
all
y
,
a
n
SVM
c
r
ea
tes
a
h
y
p
er
p
lan
e
o
r
a
s
et
o
f
h
y
p
er
p
lan
es
th
a
t
ca
n
b
e
u
s
ed
f
o
r
clas
s
if
icatio
n
an
d
r
eg
r
ess
io
n
.
T
h
e
h
y
p
er
p
lan
e
tak
e
s
a
f
o
r
m
o
f
th
e
eq
u
a
tio
n
:
f
(
x
)
=
w
.
x
+b
(
1
)
w
h
er
e,
w
is
t
h
e
w
ei
g
h
t v
ec
to
r
,
x
is
th
e
d
ata
an
d
b
is
ca
lled
th
e
b
ias [
8
]
.
T
o
class
if
y
a
s
et
o
f
p
o
in
ts
,
t
h
e
y
ar
e
p
u
t a
s
x
in
to
a
d
ec
is
io
n
f
u
n
ct
io
n
:
D(
x
)
=si
g
n
(
w
.
x
+b
)
(
2
)
3.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S AN
D
A
NALY
SI
S
I
t
is
i
m
p
o
r
ta
n
t
to
n
o
te
t
h
at,
t
h
e
s
ig
n
i
f
ica
n
t
r
es
u
lt
s
f
o
r
t
h
is
wh
o
le
ex
p
er
i
m
en
t
is
p
r
o
v
id
ed
b
y
t
h
e
SVM
class
i
f
icatio
n
.
Fo
r
s
tar
ter
,
th
e
SVM
w
as
tr
ain
ed
u
s
i
n
g
t
w
o
g
r
o
u
p
s
,
ea
ch
co
n
tain
in
g
th
e
f
ea
tu
r
es
o
b
tain
ed
f
r
o
m
a
p
er
s
o
n
’
s
f
i
n
g
er
p
r
in
t.
T
h
e
p
r
o
d
u
ce
d
r
esu
lts
f
o
r
th
e
clas
s
i
f
i
ca
tio
n
th
r
o
u
g
h
SVM
ar
e
p
r
es
en
ted
in
F
ig
u
r
e
8
.
T
h
e
s
a
m
e
m
et
h
o
d
w
a
s
th
e
n
u
s
ed
to
let
th
e
SVM
clas
s
if
y
t
wo
d
if
f
er
en
t
f
in
g
er
p
r
in
t
f
ea
t
u
r
es
b
y
its
el
f
,
a
n
d
f
r
o
m
th
e
r
esu
lts
p
r
o
d
u
ce
d
.
I
n
Fig
u
r
e
9
,
it c
an
b
e
s
ee
n
th
at,
t
h
ese
t
wo
p
r
o
d
u
ce
d
p
lo
ts
d
o
n
o
t d
if
f
er
m
u
c
h
.
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.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
4
7
–
2
5
5
4
2552
T
h
ese
p
r
ev
io
u
s
s
tep
s
ar
e
t
h
e
n
r
ep
ea
ted
u
s
i
n
g
o
n
e
f
i
n
g
er
p
r
in
t
f
ea
tu
r
e
s
o
n
o
n
e
g
r
o
u
p
a
n
d
s
ev
e
n
f
i
n
g
er
p
r
in
t
f
ea
t
u
r
es
to
g
et
h
er
o
n
th
e
o
th
er
to
tr
ain
th
e
SVM,
as
s
h
o
w
n
i
n
Fig
u
r
e
1
0
.
T
h
e
s
a
m
e
m
et
h
o
d
is
ap
p
lied
to
let
th
e
SVM
clas
s
i
f
y
a
d
i
f
f
er
e
n
t,
b
u
t
s
a
m
e
n
u
m
b
er
o
n
ea
c
h
g
r
o
u
p
,
s
et
o
f
f
in
g
er
p
r
in
t
f
ea
t
u
r
es,
an
d
ag
ain
t
h
e
r
es
u
lt
s
p
r
o
d
u
ce
d
as
g
i
v
en
i
n
Fi
g
u
r
e
1
1
d
o
n
o
t
d
if
f
er
m
u
c
h
.
T
h
e
p
r
o
d
u
ce
d
r
esu
lts
s
h
o
w
p
r
o
m
i
s
i
n
g
clas
s
i
f
icatio
n
s
o
f
s
ep
ar
ate
f
in
g
er
p
r
in
t
s
u
s
in
g
t
h
e
in
ter
s
ec
tio
n
o
f
t
h
e
b
if
u
r
ca
tio
n
an
d
r
id
g
e
en
d
f
ea
t
u
r
es o
f
t
h
o
s
e
f
in
g
er
p
r
in
t
s
.
Fig
u
r
e
8
.
SVM
tr
ain
i
n
g
u
s
in
g
t
w
o
f
in
g
er
p
r
in
t
f
ea
t
u
r
es.
Fig
u
r
e
9
.
SVM
class
i
f
icat
io
n
P
lo
t u
s
in
g
t
w
o
s
ep
ar
ate
f
i
n
g
er
p
r
in
t f
ea
t
u
r
es.
Fig
u
r
e
1
0
.
SVM
tr
ain
in
g
P
lo
t u
s
i
n
g
o
n
e
f
in
g
er
p
r
in
t
f
ea
tu
r
e
s
o
n
o
n
e
g
r
o
u
p
an
d
s
e
v
e
n
f
i
n
g
er
p
r
in
t f
ea
t
u
r
es o
n
th
e
o
th
er
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
N
o
ve
l 2
D
F
ea
tu
r
e
E
xtra
ctio
n
Meth
o
d
fo
r
F
in
g
erp
r
in
ts
Usi
n
g
Min
u
tia
e
P
o
in
ts
a
n
d
Th
eir
I
n
ters
ec
tio
n
s
(
N
ib
r
a
s
A
r
R
a
kib
)
2553
Fig
u
r
e
1
1
.
SVM
tr
ain
in
g
P
lo
t u
s
i
n
g
o
n
e
f
in
g
er
p
r
in
t
f
ea
tu
r
e
s
o
n
o
n
e
g
r
o
u
p
an
d
s
e
v
e
n
f
i
n
g
er
p
r
in
t f
ea
t
u
r
es
o
n
th
e
o
th
er
.
4.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
o
p
o
s
ed
a
n
e
w
2
D
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
eth
o
d
f
o
r
f
i
n
g
er
p
r
in
t
i
m
a
g
e
s
.
I
n
t
h
is
m
et
h
o
d
,
th
e
y
ex
tr
ac
ted
u
n
iq
u
e
f
ea
t
u
r
e
o
f
ea
ch
f
i
n
g
er
p
r
in
t
i
m
a
g
e
u
s
i
n
g
t
h
e
i
n
ter
s
ec
tio
n
o
f
its
r
id
g
e
e
n
d
s
a
n
d
r
id
g
e
b
if
u
r
ca
tio
n
s
.
Fi
n
all
y
,
t
h
e
cla
s
s
if
icatio
n
ac
c
u
r
ac
y
o
f
p
r
o
p
o
s
ed
m
et
h
o
d
w
as
tes
ted
f
o
r
a
d
ata
s
et
u
s
i
n
g
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
clas
s
if
ier
.
A
cc
o
r
d
in
g
to
SVM
r
esu
lts
,
th
e
ca
p
ab
ilit
y
o
f
th
e
m
i
n
u
tiae
ex
tr
ac
tin
g
an
d
m
atc
h
in
g
h
as
b
ee
n
p
r
o
v
ed
in
e
x
p
er
i
m
e
n
tal
r
esu
l
ts
.
I
n
s
p
ite
o
f
a
g
r
ea
te
r
co
n
ce
p
tu
al
co
m
p
le
x
it
y
,
it
h
a
s
b
ee
n
s
h
o
w
n
t
h
at
th
is
tec
h
n
iq
u
e
h
a
s
less
co
m
p
u
tatio
n
a
l
co
m
p
lex
it
y
at
th
e
c
lass
i
f
icatio
n
p
ar
t
as
f
e
w
er
p
o
in
ts
ar
e
n
ee
d
ed
to
class
i
f
y
w
it
h
in
t
h
e
SV
M.
RE
F
E
R
E
NC
E
S
[
1
]
R.
T
h
a
i,
“
F
in
g
e
rp
rin
t
Im
a
g
e
En
h
a
n
c
e
m
e
n
t
a
n
d
M
i
n
u
t
iae
Ex
trac
ti
o
n
,
”
Re
p
o
rt
o
f
Ho
n
o
u
rs
P
ro
g
ra
m
m
e
o
f
th
e
S
c
h
o
o
l
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
S
o
f
tw
a
r
e
En
g
in
e
e
rin
g
,
T
h
e
Un
iv
e
rsity
o
f
W
e
ste
rn
A
u
stra
li
a
,
2
0
0
3
.
[
2
]
C.
Ch
i
-
Jim
,
P
.
T
u
n
-
W
e
n
,
a
n
d
C
.
M
o
x
,
“
A
S
u
p
p
o
r
t
V
e
c
to
r
M
a
c
h
in
e
A
p
p
ro
a
c
h
f
o
r
T
ru
n
c
a
ted
F
i
n
g
e
rp
rin
t
Im
a
g
e
De
tec
ti
o
n
f
ro
m
S
w
e
e
p
in
g
F
in
g
e
rp
rin
t
S
e
n
so
rs,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
e
n
so
rs
,
2
0
1
5
,
v
o
l.
1
5
,
p
p
.
7
8
0
7
-
7
8
2
2
.
[
3
]
S
.
M
.
M
o
h
se
n
,
S
.
M
.
Z.
F
a
rh
a
n
,
a
n
d
M
.
M
.
A
.
Ha
sh
e
m
,
“
A
u
to
m
a
ted
F
in
g
e
rp
rin
t
Re
c
o
g
n
it
io
n
:
Us
in
g
M
in
u
ti
a
e
M
a
tch
in
g
T
e
c
h
n
iq
u
e
f
o
r
T
h
e
L
a
r
g
e
F
in
g
e
rp
rin
t
Da
tab
a
se
,
”
i
n
P
r
o
c
.
o
f
3
r
d
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
tri
c
a
l
&
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
ICEC
E
2
0
0
4
,
2
8
-
3
0
De
c
e
m
b
e
r
2
0
0
4
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
[
4
]
C.
Co
rtes
,
a
n
d
V
.
V
a
p
n
ik
,
“
S
u
p
p
o
rt
-
v
e
c
to
r
n
e
tw
o
rk
s,” M
a
c
h
in
e
L
e
a
rn
in
g
,
1
9
9
5
,
v
o
l.
2
0
,
n
o
.
3
,
p
p
.
2
7
3
.
[
5
]
A
.
J
a
in
,
A
.
Ro
ss
,
a
n
d
S
.
P
ra
b
h
a
k
a
r,
“
F
in
g
e
rp
rin
t
M
a
tch
in
g
Us
in
g
M
in
u
ti
a
e
A
n
d
Tex
tu
re
F
e
a
tu
r
e
s,”
in
P
ro
c
.
o
f
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Im
a
g
e
P
r
o
c
e
ss
in
g
,
ICI
P
2
0
0
1
,
p
p
.
2
8
2
-
2
8
5
,
Oc
t
7
-
1
0
,
2
0
0
1
,
T
h
e
ss
a
lo
n
i
k
i,
G
re
e
c
e
.
[
6
]
S
in
g
le
-
lev
e
l
d
isc
re
te
2
-
D
wa
v
e
let
tran
s
f
o
r
m
s.
[
On
li
n
e
]
.
[
A
c
c
e
ss
e
d
3
1
No
v
e
m
b
e
r
2
0
1
5
]
.
O
n
li
n
e
.
h
tt
p
:
//
ww
w
.
m
a
th
w
o
rk
s.co
m
/h
e
lp
/
w
a
v
e
let/re
f
/d
w
t2
.
h
tm
l
[
7
]
P
.
D.
S
iri
v
e
ll
a
,
a
n
d
D.R
V
a
m
si,
“
F
in
g
e
rp
rin
t
V
a
li
d
a
ti
o
n
a
n
d
O
u
tl
ie
r
De
tec
ti
o
n
Us
in
g
M
in
u
ti
a
e
A
p
p
ro
a
c
h
in
Ne
tw
o
rk
S
e
c
u
rit
y
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
a
n
d
Or
g
a
n
iza
ti
o
n
T
r
e
n
d
s
,
2
0
1
2
,
v
o
l.
2
,
n
o
.
5
,
p
p
.
1
2
3
-
1
2
7
.
[
8
]
A
Yu
n
iarti
,
"
Clas
si
f
ica
ti
o
n
a
n
d
n
u
m
b
e
rin
g
o
f
d
e
n
tal
ra
d
io
g
ra
p
h
s
f
o
r
a
n
a
u
to
m
a
ted
h
u
m
a
n
id
e
n
ti
f
ica
ti
o
n
sy
ste
m
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
,
C
o
mp
u
ti
n
g
,
El
e
c
tr
o
n
ics
a
n
d
Co
n
tro
l.
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
1
3
7
-
1
4
6
,
2
0
1
2
.
[
9
]
S
.
L
a
h
m
iri
,
“
W
a
v
e
let
l
ow
-
a
n
d
h
ig
h
-
f
re
q
u
e
n
c
y
c
o
m
p
o
n
e
n
ts
a
s
f
e
a
tu
re
s
f
o
r
p
re
d
ictin
g
sto
c
k
p
rice
s
w
it
h
b
a
c
k
p
ro
p
a
g
a
ti
o
n
n
e
u
ra
l
n
e
tw
o
rk
s
,
”
J
o
u
rn
a
l
o
f
Kin
g
S
a
u
d
Un
ive
rs
it
y
-
Co
mp
u
ter
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s
a
rc
h
ive
,
Ju
ly
2
0
1
4
,
v
o
l.
2
6
,
n
o
.
2
,
p
p
.
2
1
8
-
2
2
7
.
[
1
0
]
F
.
X
iao
,
a
n
d
Y.
Z
h
a
n
g
,
“
A
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
n
th
re
sh
o
l
d
in
g
m
e
th
o
d
s
i
n
w
a
v
e
let
-
b
a
se
d
i
m
a
g
e
d
e
n
o
i
sin
g
,
”
P
ro
c
e
d
ia
En
g
in
e
e
rin
g
,
2
0
1
1
,
v
o
l.
1
5
,
n
o
.
0
,
p
p
.
3
9
9
8
-
4
0
0
3
.
[
1
1
]
J.
Ud
d
in
,
D.
Ng
u
y
e
n
a
n
d
J.
Kim
,
“
A
Re
li
a
b
le
F
a
u
lt
De
tec
ti
o
n
a
n
d
Clas
si
f
ica
ti
o
n
M
o
d
e
l
o
f
In
d
u
c
ti
o
n
M
o
t
o
rs
u
sin
g
T
e
x
tu
re
F
e
a
tu
re
s
a
n
d
M
u
lt
i
-
c
las
s
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s,”
J
o
u
rn
a
l
o
f
M
a
t
h
e
ma
ti
c
a
l
Pr
o
b
lem
s
in
En
g
in
e
e
rin
g
,
Hin
d
a
w
i,
Un
it
e
d
S
tate
s,
v
o
l.
2
0
1
4
(2
0
1
4
)
,
a
rti
c
le ID
8
1
4
5
9
3
,
p
p
.
1
-
9.
[
1
2
]
J.
Ud
d
in
,
R.
Isla
m
a
n
d
J.
Ki
m
,
“
T
e
x
tu
re
F
e
a
tu
re
Ex
tra
c
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
F
a
u
lt
Dia
g
n
o
s
is
o
f
In
d
u
c
ti
o
n
M
o
to
rs,”
J
o
u
rn
a
l
o
f
Co
n
v
e
rg
e
n
c
e
,
F
T
RA
,
S
o
u
t
h
K
o
re
a
,
v
o
l.
5
,
n
o
.
2
,
Ju
n
e
2
0
1
4
,
p
p
.
1
5
-
2
0
.
[
1
3
]
G
.
In
d
ra
w
a
n
,
S
.
A
k
b
a
r
a
n
d
B.
S
it
o
h
a
n
g
,
“
F
i
n
g
e
rp
rin
t
Dire
c
t
-
A
c
c
e
ss
S
trate
g
y
Us
in
g
L
o
c
a
l
-
S
tar
-
S
tru
c
tu
re
b
a
se
d
Disc
ri
m
in
a
to
r
F
e
a
tu
re
s:
A
Co
m
p
a
riso
n
S
tu
d
y
,
”
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
v
o
l.
4
,
n
o
.
5
,
Oc
to
b
e
r
2
0
1
4
,
p
p
.
8
1
7
-
8
3
0
.
[
1
4
]
S
.
S
a
p
a
ru
d
in
,
S
.
A
k
b
a
r
a
n
d
G
.
S
u
lo
n
g
,
“
S
e
g
m
e
n
tatio
n
o
f
F
in
g
e
rp
rin
t
Im
a
g
e
B
a
se
d
o
n
G
ra
d
ien
t
M
a
g
n
it
u
d
e
a
n
d
Co
h
e
re
n
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
v
o
l
.
5
,
n
o
.
5
,
Oc
to
b
e
r
2
0
1
,
p
p
.
8
3
4
-
8
4
9
.
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.
7
,
No
.
5
,
Octo
b
er
2
0
1
7
:
2
5
4
7
–
2
5
5
4
2554
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Nib
ra
s
A
r
Ra
k
ib
,
is
a
G
ra
d
u
a
te
S
tu
d
e
n
t
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
in
BRA
C
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
d
id
h
is
B.
S
c
.
d
e
g
re
e
(Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
)
f
ro
m
A
h
sa
n
u
ll
a
h
Un
iv
e
rsit
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sg
h
.
M
r.
Nib
ra
s
is
w
o
rk
in
g
a
s
a
Re
se
a
rc
h
Off
i
c
e
r
a
t
icd
d
r,
b
.
His
r
e
se
a
rc
h
a
re
a
in
c
lu
d
e
s
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
M
a
c
h
in
e
lea
rn
in
g
.
S
M
Zam
sh
e
d
F
a
rh
a
n
,
is
a
G
ra
d
u
a
te S
tu
d
e
n
t
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
in
BRA
C
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
re
c
e
iv
e
d
B.
S
c
.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
f
ro
m
Kh
u
ln
a
Un
iv
e
rsity
o
f
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
(KU
E
T
)
Ba
n
g
lad
e
sh
in
2
0
0
3
a
n
d
M
a
ste
rs
in
Bu
si
n
e
ss
A
d
m
in
istratio
n
in
M
a
n
a
g
e
m
e
n
t
f
ro
m
Un
iv
e
rsit
y
o
f
Dh
a
k
a
,
Ba
n
g
lad
e
sh
in
2
0
0
9
.
He
sta
rte
d
h
is
IT
c
a
re
e
r
o
n
2
0
0
4
a
s
a
S
o
f
twa
r
e
En
g
in
e
e
r
o
n
th
e
p
latf
o
rm
o
f
G
N
U
C
a
t
BDCO
M
On
li
n
e
L
im
it
e
d
.
T
h
e
n
m
o
v
e
d
to
w
e
b
tec
h
n
o
l
o
g
y
a
t
BR
A
C
BDMail
Ne
t
w
o
rk
Li
m
it
e
d
(Cu
rre
n
tl
y
it
is
BR
A
C
Ne
t)
o
n
2
0
0
6
.
On
2
0
1
0
,
h
e
jo
i
n
e
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
In
tern
a
ti
o
n
a
l
Ce
n
tre
f
o
r
Dia
rrh
o
e
a
l
Dise
a
s
e
Re
se
a
rc
h
,
Ba
n
g
lad
e
sh
(ICDD
R,
B).
His
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s
in
c
lu
d
e
s
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
M
a
c
h
i
n
e
lea
rn
in
g
.
M
d
.
M
a
sh
r
u
r
Ba
r
i
S
o
b
h
a
n
,
is
a
G
r
a
d
u
a
te
S
tu
d
e
n
t
a
t
De
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
in
BRA
C
Un
iv
e
rsit
y
,
Dh
a
k
a
,
Ba
n
g
lad
e
sh
.
He
re
c
e
iv
e
d
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
(BEn
g
),
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
,
Qu
e
e
n
M
a
r
y
,
U.
o
f
L
o
n
d
o
n
,
UK.
M
r.
M
a
sh
r
u
r
w
o
rk
e
d
o
n
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
we
b
a
p
p
li
c
a
ti
o
n
f
o
r
t
h
e
L
o
c
a
l
G
o
v
e
rn
m
e
n
t
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t
(LG
ED
)
o
f
Ba
n
g
lad
e
sh
to
re
c
o
rd
s
u
rv
e
y
a
n
d
ro
a
d
s’
i
n
f
o
rm
a
ti
o
n
f
o
r
f
u
rth
e
r
a
n
a
ly
si
s.
Re
sp
o
n
sib
il
it
ies
i
n
c
lu
d
e
d
d
e
sig
n
i
n
g
th
e
d
a
tab
a
se
sy
ste
m
s alo
n
g
w
it
h
d
e
c
id
in
g
o
n
th
e
in
d
e
p
e
n
d
e
n
t
f
u
n
c
ti
o
n
a
li
ti
e
s
o
f
th
e
we
b
a
p
p
li
c
a
ti
o
n
,
im
p
lem
e
n
tatio
n
o
f
A
S
P
.
NET
M
V
C
f
ra
m
e
w
o
rk
w
it
h
th
e
su
p
p
o
rt
o
f
S
QL
S
e
r
v
e
r
M
a
n
a
g
e
m
e
n
t
S
tu
d
io
f
o
r
th
e
p
u
r
p
o
se
o
f
w
e
b
d
e
v
e
lo
p
m
e
n
ts
a
n
d
m
a
in
tain
in
g
a
li
a
iso
n
w
it
h
f
o
re
ig
n
c
o
n
su
lt
a
n
ts
a
n
d
L
G
ED
to
f
a
c
il
it
a
te
th
e
d
e
v
e
lo
p
m
e
n
ts
a
t
e
v
e
r
y
ste
p
.
His
re
se
a
r
c
h
a
re
a
s
a
r
e
d
a
tab
a
se
,
i
m
a
g
e
p
ro
c
e
ss
in
g
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
Dr.
Jia
Ud
d
in
,
is
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
De
p
a
rtm
e
n
t
o
f
BRA
C
Un
iv
e
rsit
y
.
He
wa
s
a
n
A
s
sista
n
t
P
ro
f
e
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
a
n
d
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
D
e
p
a
rtme
n
t
in
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsit
y
Ch
it
tag
o
n
g
,
Ba
n
g
lad
e
sh
.
He
re
c
e
iv
e
d
P
h
.
D.
d
e
g
re
e
(Co
m
p
u
ter
En
g
in
e
e
rin
g
)
f
r
o
m
Un
iv
e
rsit
y
o
f
Ulsa
n
,
S
o
u
t
h
Ko
re
a
in
Ja
n
u
a
ry
2
0
1
5
.
Du
ri
n
g
h
i
s
P
h
.
D.
d
u
ra
ti
o
n
(2
0
1
1
-
2
0
1
4
)
,
h
e
w
a
s
in
v
o
lv
e
d
w
it
h
a
re
se
a
rc
h
lab
o
ra
to
ry
“
E
m
b
e
d
d
e
d
Ub
iq
u
it
o
u
s
Co
m
p
u
ti
n
g
S
y
ste
m
Lab
”
a
n
d
h
a
s
a
n
u
m
b
e
r
o
f
p
e
e
r
re
v
ie
w
e
d
jo
u
r
n
a
ls.
He
a
tt
e
n
d
e
d
se
v
e
r
a
l
in
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
s
a
n
d
s
y
m
p
o
siu
m
s
a
t
h
o
m
e
a
n
d
a
b
ro
a
d
.
P
ri
o
r
to
h
is
P
h
.
D.,
h
e
o
b
tain
e
d
M
.
S
c
.
En
g
g
.
(T
e
l
e
c
o
m
m
u
n
ica
ti
o
n
s)
d
e
g
re
e
f
ro
m
Blek
in
g
e
In
stit
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
S
w
e
d
e
n
a
t
2
0
1
0
.
He
re
c
e
i
v
e
d
B.
S
c
.
En
g
g
.
in
Co
m
p
u
ter
a
nd
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
ri
n
g
f
ro
m
In
tern
a
ti
o
n
a
l
Isla
m
ic
Un
iv
e
rsi
ty
Ch
it
tag
o
n
g
,
Ba
n
g
lad
e
sh
a
t
2
0
0
5
.
His
re
se
a
rc
h
in
tere
sts in
c
lu
d
e
P
a
ra
ll
e
l
Co
m
p
u
ti
n
g
,
F
a
u
lt
Dia
g
n
o
sis a
n
d
A
d
-
Ho
c
Ne
tw
o
rk
s.
A
ra
fa
t
Ha
b
ib
h
a
s
c
o
m
p
lete
d
B.
S
c
in
Co
m
p
u
ter
S
c
ien
c
e
f
ro
m
BR
A
C
Un
iv
e
rsit
y
v
e
r
y
re
c
e
n
tl
y
.
His
re
se
a
r
c
h
in
tere
st
li
e
s
in
Clo
u
d
Co
m
p
u
ti
n
g
,
Re
in
f
o
rc
e
m
e
n
t
Lea
rn
in
g
,
Ro
b
o
ti
c
s
a
n
d
S
u
p
p
ly
Ch
a
in
M
a
n
a
g
e
m
e
n
t.
P
re
v
io
u
sly
,
h
e
w
o
rk
e
d
a
s
a
Da
tab
a
se
A
d
m
in
istrato
r
a
n
d
Ja
v
a
d
e
v
e
lo
p
e
r
in
h
is
stu
d
e
n
t
l
if
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.