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.
8
,
No
.
5
,
Octo
b
e
r
2
0
1
8
,
p
p
.
3
6
2
0
~
3
6
2
6
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
5
.
p
p
.
3
6
2
0
-
3626
3620
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
En
la
rg
e Medica
l
I
m
a
g
e Using
Lin
e
-
c
o
lu
m
n Int
erpo
l
a
tion
(LCI) Me
thod
J
ufr
ia
dif
Na
`
a
m
,
J
uli
us
Sa
nt
o
ny
,
Yuha
nd
ri,
Su
m
ij
a
n,
G
u
na
di Widi
N
urca
hy
o
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra I
n
d
o
n
e
sia
Y
P
T
K
P
a
d
a
n
g
,
2
5
2
2
1
,
I
n
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
1
1
,
2
0
1
8
R
ev
i
s
ed
J
u
n
2
8
,
2
0
1
8
A
cc
ep
ted
J
ul
5
,
2
0
1
8
Qu
a
li
ty
o
f
m
e
d
ica
l
i
m
a
g
e
h
a
s
a
n
im
p
o
rtan
t
ro
le
in
c
o
n
stru
c
ti
n
g
rig
h
t
m
e
d
ica
l
d
iag
n
o
sis.
T
h
is
p
a
p
e
r
re
c
o
m
m
e
n
d
s
a
m
e
th
o
d
t
o
im
p
ro
v
e
th
e
q
u
a
li
ty
o
f
m
e
d
ica
l
i
m
a
g
e
s
b
y
in
c
re
a
sin
g
th
e
siz
e
o
f
th
e
i
m
a
g
e
p
ix
e
ls.
B
y
in
c
re
a
sin
g
th
e
siz
e
o
f
p
ix
e
ls,
th
e
siz
e
o
f
th
e
o
b
je
c
ts
c
o
n
tain
e
d
th
e
re
in
is
a
lso
g
re
a
ter,
m
a
k
in
g
it
e
a
sie
r
to
o
b
se
rv
e
.
In
th
is
stu
d
y
m
e
d
ica
l
ima
g
e
s
o
f
Bra
in
CT
-
S
c
a
n
,
Ch
e
st X
-
Ra
y
a
n
d
P
a
n
o
ra
m
ic
X
-
Ra
y
we
re
p
ro
c
e
ss
e
d
u
sin
g
L
in
e
-
Co
lu
m
n
In
terp
o
latio
n
(L
CI)
M
e
th
o
d
.
T
h
e
re
su
lt
s
o
f
th
e
trea
t
m
e
n
t
a
r
e
th
e
n
c
o
m
p
a
re
d
to
Ne
a
re
st
Ne
ig
h
b
o
r
In
terp
o
latio
n
(NN
I),
Bil
in
e
a
r
In
terp
o
latio
n
(BL
I)
a
n
d
Bicu
b
ic
In
terp
o
latio
n
(BCI)
p
ro
c
e
ss
in
g
re
su
lt
s.
T
h
e
e
x
p
e
rime
n
t
sh
o
w
s
th
a
t
L
in
e
-
Co
lu
m
n
In
terp
o
lati
o
n
M
e
t
h
o
d
p
r
o
d
u
c
e
s
a
larg
e
r
i
m
a
g
e
w
it
h
d
e
ta
il
s
o
f
th
e
o
b
jec
ts
in
it
a
re
n
o
t
b
lu
rre
d
a
n
d
h
a
s
e
q
u
a
l
v
isu
a
l
e
ffe
c
ts.
T
h
u
s,
th
is
m
e
th
o
d
is
e
x
p
e
c
ted
to
b
e
a
re
f
e
re
n
c
e
m
a
teri
a
l
in
e
n
larg
in
g
th
e
siz
e
o
f
th
e
m
e
d
ica
l
im
a
g
e
f
o
r
e
a
se
in
c
li
n
ica
l
a
n
a
ly
sis.
K
ey
w
o
r
d
:
B
icu
b
ic
in
ter
p
o
latio
n
B
ilin
ea
r
in
ter
p
o
latio
n
E
n
lar
g
e
L
i
n
e
-
c
o
l
u
m
n
i
n
ter
p
o
latio
n
Me
d
ical
i
m
a
g
e
Nea
r
est
n
ei
g
h
b
o
r
in
ter
p
o
latio
n
Co
p
y
rig
h
t
©
2
0
1
8
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
u
f
r
iad
if
Na
`
a
m
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
,
Un
i
v
er
s
ita
s
P
u
tr
a
I
n
d
o
n
esia Y
PT
K
P
a
d
an
g
,
J
l.
R
a
y
a
L
u
b
u
k
B
eg
al
u
n
g
P
ad
an
g
,
2
5
2
2
1
,
I
n
d
o
n
esia.
E
m
ail:
j
u
f
r
iad
if
n
aa
m
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
Me
d
ical
i
m
ag
e
s
ar
e
a
clin
ic
al
n
ee
d
to
u
n
d
er
s
tan
d
d
is
ea
s
es
in
ca
r
e
an
d
tr
ea
t
m
en
t
[
1
]
[
2
]
.
Go
o
d
i
m
a
g
in
g
ea
s
e
m
ed
ical
p
er
s
o
n
n
el
to
p
r
o
d
u
ce
m
o
r
e
p
r
ec
is
e
cli
n
ical
tr
ial
s
.
Ho
w
e
v
er
,
to
o
b
tain
a
g
o
o
d
i
m
a
g
e,
a
s
o
p
h
is
ticated
tec
h
n
o
lo
g
y
w
h
ic
h
is
u
s
u
all
y
ex
p
e
n
s
i
v
e
is
to
b
e
r
eq
u
ir
ed
.
T
h
e
p
r
o
cu
r
em
e
n
ts
o
f
s
u
c
h
eq
u
ip
m
e
n
t i
s
ch
ar
g
ed
to
t
h
e
p
atien
t
[
3
]
.
T
h
er
ef
o
r
e,
a
b
etter
in
f
o
r
m
ati
o
n
tech
n
o
lo
g
y
ap
p
r
o
ac
h
is
n
ee
d
ed
to
d
iag
n
o
s
e
d
is
ea
s
es
[
4
]
.
On
e
s
u
ch
in
f
o
r
m
atio
n
tec
h
n
o
lo
g
y
ap
p
r
o
ac
h
i
s
th
e
m
ed
ical
i
m
a
g
e.
Me
d
ical
i
m
ag
e
s
ca
n
b
e
u
s
ed
f
o
r
ea
r
l
y
d
iag
n
o
s
is
i
n
ac
cu
r
ate
l
y
id
en
ti
f
y
i
n
g
d
y
s
f
u
n
ctio
n
al
o
b
j
ec
ts
in
th
e
h
u
m
an
b
o
d
y
[
5
]
.
So
m
e
s
tep
s
ar
e
r
eq
u
ir
ed
in
th
e
p
r
o
ce
s
s
i
n
g
o
f
m
ed
ical
i
m
ag
e
s
f
o
r
b
etter
i
n
f
l
u
en
ce
o
f
cli
n
ical
o
u
tco
m
es.
T
h
e
n
ec
es
s
ar
y
s
tep
is
to
i
m
p
r
o
v
e
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
i
m
ag
e
f
ir
s
t.
T
h
is
i
m
p
r
o
v
e
m
e
n
t
m
a
k
es
th
e
d
iag
n
o
s
i
s
ac
c
u
r
ate.
T
h
e
tas
k
o
f
r
ef
i
n
i
n
g
t
h
e
m
ed
ical
i
m
ag
e
ca
n
b
e
s
u
p
p
o
r
ted
b
y
in
cr
ea
s
in
g
t
h
e
s
ize
o
f
t
h
e
i
m
a
g
e,
b
u
t
s
t
ill
p
a
y
i
n
g
atten
ti
o
n
to
th
e
p
r
eser
v
atio
n
o
f
t
h
e
d
etails
o
f
t
h
e
p
ar
ticu
lar
i
m
ag
e
[
6
]
.
T
h
e
en
lar
g
ed
i
m
a
g
e
co
n
tai
n
s
p
r
o
b
le
m
s
s
u
c
h
as lo
s
s
o
f
co
n
tr
a
s
t a
n
d
t
h
e
d
etail
b
ec
o
m
e
s
b
lu
r
r
ed
.
B
esid
es,
en
lar
g
in
g
t
h
e
i
m
a
g
e
s
ize
is
al
s
o
a
f
u
n
d
a
m
e
n
tal
p
r
o
ce
s
s
.
L
ar
g
er
s
izes
s
h
o
u
ld
b
e
ab
l
e
to
r
etain
i
m
p
o
r
tan
t
co
n
ten
t
i
n
i
m
a
g
er
y
as
w
ell
as
v
i
s
u
al
e
f
f
ec
ts
in
g
e
n
er
al.
T
h
e
m
ai
n
d
is
ad
v
a
n
ta
g
es
t
h
at
o
f
te
n
o
cc
u
r
ar
e
lo
ca
l
s
tr
u
ctu
r
al
d
a
m
a
g
e
o
r
v
is
u
al
ef
f
ec
t
s
[
7
]
.
I
n
cr
ea
s
in
g
th
e
i
m
a
g
e
s
iz
e
is
r
eq
u
ir
ed
to
in
cr
ea
s
e
th
e
s
ize
o
f
t
h
e
in
itial
i
m
a
g
e
p
ix
e
ls
.
T
h
e
i
m
a
g
e
en
lar
g
e
m
e
n
t
ad
d
s
n
e
w
p
i
x
el
s
an
d
n
ar
r
o
w
s
t
h
e
s
a
m
p
li
n
g
i
n
ter
v
al
o
f
t
h
e
i
m
ag
e
to
th
e
p
ix
e
l
v
a
lu
e
in
ter
p
o
lati
o
n
.
T
h
e
v
al
u
e
o
f
t
h
i
s
ad
d
itio
n
al
p
ix
e
l
is
d
eter
m
i
n
ed
b
y
t
h
e
in
ter
p
o
latio
n
(
t
h
e
v
alu
e
o
f
its
n
ei
g
h
b
o
r
in
g
p
i
x
el
s
)
.
E
x
is
ti
n
g
in
ter
p
o
latio
n
m
et
h
o
d
s
ar
e
Nea
r
est
Neig
h
b
o
r
I
n
ter
p
o
latio
n
(
NNI
)
,
B
ilin
ea
r
I
n
ter
p
o
latio
n
(
B
L
I
)
an
d
B
icu
b
ic
I
n
ter
p
o
latio
n
(
B
C
I
)
[
8
]
.
I
n
th
is
r
esear
c
h
,
w
e
p
r
o
p
o
s
e
a
L
in
e
-
c
o
lu
m
n
I
n
ter
p
o
latio
n
Me
t
h
o
d
(
L
C
I
)
as
a
n
e
w
m
e
t
h
o
d
.
T
h
is
m
eth
o
d
i
s
test
ed
to
e
n
lar
g
e
th
e
s
ize
o
f
t
h
e
m
ed
ical
i
m
ag
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
E
n
la
r
g
e
Med
ica
l I
ma
g
e
Usi
n
g
Lin
e
-
C
o
lu
mn
I
n
terp
o
la
tio
n
(
LC
I
)
Meth
o
d
(
Ju
fr
ia
d
if
N
a
`
a
m
)
3621
L
ar
g
er
i
m
a
g
e
s
izes
p
r
o
d
u
ce
l
ar
g
er
o
b
j
ec
ts
b
y
r
etai
n
i
n
g
t
h
e
v
alu
e
o
f
th
eir
lo
ca
l
s
tr
u
ct
u
r
e.
T
h
u
s
,
th
e
r
es
u
lt
o
f
th
is
m
a
g
n
if
ica
tio
n
m
ak
e
s
b
ette
r
o
b
s
er
v
atio
n
to
th
e
o
b
j
ec
ts
in
th
e
i
m
ag
e.
Th
e
L
C
I
m
et
h
o
d
is
test
ed
u
s
i
n
g
m
ed
ical
i
m
ag
e
o
f
B
r
ain
C
T
-
Scan
,
C
h
est
X
-
R
a
y
a
n
d
P
a
n
o
r
a
m
ic
X
-
R
a
y
in
Ma
tlab
s
o
f
t
w
ar
e.
T
h
e
s
a
m
e
d
ata
ar
e
al
s
o
tes
ted
in
th
e
s
a
m
e
w
a
y
b
y
i
m
p
le
m
e
n
ti
n
g
NNI
,
B
L
I
,
an
d
B
C
I
m
et
h
o
d
s
[
9
]
.
Fu
n
d
a
m
e
n
tal
p
r
in
cip
les
th
at
n
ee
d
to
b
e
f
u
l
f
ill
ed
b
y
i
m
ag
e
en
lar
g
e
m
en
t
is
t
h
at
t
h
e
co
m
p
o
s
itio
n
r
atio
,
n
a
m
el
y
t
h
e
v
alu
e
a
n
d
p
o
s
itio
n
o
f
p
i
x
el
m
u
s
t
b
e
t
h
e
s
a
m
e
as
th
e
o
r
i
g
in
a
l
i
m
ag
e
ca
n
b
e
test
ed
u
s
i
n
g
a
h
is
to
g
r
a
m
.
Sev
er
al
s
tu
d
ie
s
o
n
i
m
ag
e
s
ize
en
lar
g
e
m
e
n
t
w
er
e
S
u
etak
e
et
al
[
10
]
co
n
d
u
cted
a
s
tu
d
y
to
ac
ce
ler
ate
i
m
a
g
e
e
n
lar
g
e
m
e
n
t
u
s
i
n
g
B
C
I
m
et
h
o
d
ag
ai
n
s
t
e
m
p
t
y
p
ix
el
s
u
s
i
n
g
b
ac
k
p
r
o
j
ec
tio
n
tec
h
n
iq
u
e.
B
esid
es
t
h
at
,
Z
h
an
g
et
al
[
1
1
]
p
er
f
o
r
m
ed
i
m
ag
e
e
x
p
an
s
io
n
u
s
in
g
t
h
e
n
ea
r
e
s
t
q
u
ad
r
atic
p
o
l
y
n
o
m
ial
p
r
ec
is
io
n
(
NNI
)
m
et
h
o
d
.
I
m
ag
e
e
n
lar
g
e
m
e
n
t
r
esu
l
ts
w
e
r
e
also
test
ed
f
o
r
ed
g
e
d
etec
ti
o
n
;
s
u
c
h
as
s
t
u
d
y
b
y
Z
h
o
n
g
et
al
[
1
2
]
co
n
d
u
cted
a
s
tu
d
y
o
f
r
etain
in
g
t
h
e
b
o
r
d
er
o
f
an
o
b
j
ec
t a
g
ain
s
t a
n
e
n
lar
g
ed
i
m
ag
e
u
s
in
g
t
h
e
B
C
I
m
et
h
o
d
.
T
h
er
e
w
ill
b
e
ad
d
itio
n
al
p
i
x
el
s
in
i
m
a
g
e
e
n
lar
g
e
m
e
n
t.
T
h
e
v
alu
e
o
f
t
h
ese
ad
d
itio
n
a
l
p
ix
e
ls
m
a
y
b
e
e
m
p
t
y
,
m
is
s
i
n
g
o
r
n
o
t
s
y
n
ch
r
o
n
ized
(
ex
ac
t)
.
Oliv
ier
et
al.
[
1
3
]
c
o
n
d
u
cted
a
s
tu
d
y
in
t
h
e
d
eter
m
i
n
atio
n
o
f
m
is
s
i
n
g
p
ix
el
v
alu
e
s
i
n
e
n
lar
g
in
g
h
i
g
h
-
r
eso
lu
t
io
n
i
m
a
g
es
u
s
i
n
g
t
h
e
n
ea
r
est
n
e
ig
h
b
o
r
m
eth
o
d
.
B
ash
ar
et
al.
[1
4
]
co
n
d
u
cted
a
s
tu
d
y
u
s
i
n
g
th
e
b
ili
n
ea
r
i
n
ter
p
o
latio
n
m
eth
o
d
to
esti
m
ate
in
co
r
r
ec
t
p
ix
el
v
al
u
es
i
n
f
ac
e
i
m
a
g
e
r
ec
o
g
n
itio
n
.
Kai
-
y
u
et
al
[
1
5
]
d
esig
n
ed
a
m
et
h
o
d
to
en
lar
g
e
h
ig
h
-
q
u
alit
y
an
d
f
a
s
t
i
m
ag
e
d
is
p
la
y
b
ased
o
n
FP
G
A
(
F
ield
P
r
o
g
r
a
m
m
ab
le
Gate
A
r
r
a
y
)
u
s
i
n
g
t
h
e
B
ic
u
b
ic
m
et
h
o
d
.
Go
p
in
ath
a
n
e
t
a
l
[
1
6
]
co
n
d
u
cted
a
s
tu
d
y
to
r
e
m
o
v
e
n
o
i
s
e
(
d
en
o
i
s
e)
b
y
ap
p
l
y
in
g
th
e
B
L
I
m
et
h
o
d
to
t
h
e
i
m
a
g
e
p
o
r
tio
n
h
av
in
g
lo
w
f
r
eq
u
e
n
c
y
.
T
h
e
lim
ited
n
u
m
b
er
an
d
d
if
f
e
r
en
t
e
m
p
h
asizes
o
f
th
o
s
e
p
r
ev
io
u
s
s
t
u
d
ies,
w
e
co
n
d
u
c
ted
a
s
tu
d
y
to
e
n
lar
g
e
t
h
e
i
m
a
g
e
b
y
u
s
i
n
g
L
i
n
e
-
c
o
lu
m
n
I
n
ter
p
o
latio
n
Me
th
o
d
o
n
g
r
a
y
s
ca
le
m
ed
ical
i
m
ag
e
s
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
o
b
j
ec
ts
co
n
tai
n
ed
i
n
t
h
e
m
ed
ical
i
m
a
g
e
m
u
s
t
b
e
o
b
s
er
v
ab
le.
E
r
r
o
r
s
in
th
e
o
b
s
er
v
ati
o
n
o
f
th
e
s
e
o
b
j
ec
ts
ca
n
lead
to
m
i
s
d
iag
n
o
s
is
.
T
h
is
er
r
o
r
co
m
p
licate
s
th
e
p
atien
t's
ca
r
e
an
d
tr
ea
tm
e
n
t
p
r
o
ce
s
s
.
T
o
f
ac
ilit
ate
th
is
o
b
s
er
v
a
tio
n
,
it
is
n
ec
es
s
ar
y
to
en
lar
g
e
t
h
e
s
ize
o
f
t
h
e
o
b
j
ec
t.
I
n
th
is
s
t
u
d
y
,
a
m
et
h
o
d
o
f
en
lar
g
i
n
g
o
b
j
ec
ts
in
m
ed
ical
i
m
a
g
es i
s
p
r
o
p
o
s
ed
w
h
er
e
th
e
s
eq
u
en
ce
o
f
th
e
p
r
o
ce
s
s
ca
n
b
e
s
ee
n
in
Fig
u
r
e
1
.
T
h
e
p
r
o
ce
s
s
s
tag
e
s
o
f
t
h
is
s
t
u
d
y
co
n
s
i
s
t
o
f
4
(
f
o
u
r
p
r
o
ce
s
s
es
to
p
r
o
d
u
ce
a
n
e
n
lar
g
ed
i
m
ag
e
f
ile)
.
E
v
er
y
s
tep
o
f
en
lar
g
e
m
en
t
p
r
o
ce
s
s
p
r
o
d
u
ce
s
i
m
a
g
e
s
ize
2
ti
m
es
t
h
e
s
ize
o
f
t
h
e
i
n
p
u
t
i
m
a
g
e
p
ix
el.
T
h
e
ac
tiv
atio
n
p
r
o
ce
s
s
ca
n
r
ep
ea
tead
ly
b
e
d
o
n
e
u
n
til
th
e
m
ax
i
m
u
m
s
ize
o
f
m
e
m
o
r
y
t
y
p
e
d
ata
u
s
ed
is
n
o
lo
n
g
er
s
u
f
f
icie
n
t (
o
u
t o
f
m
e
m
o
r
y
)
.
I
ll
u
s
tr
atio
n
o
f
L
C
I
m
eth
o
d
ca
n
b
e
s
ee
n
i
n
Fi
g
u
r
e
2
.
Fig
u
r
e
1
.
Stag
e
o
f
p
r
o
ce
s
s
o
n
C
L
I
m
et
h
o
d
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
I
llu
s
tr
atio
n
o
f
L
C
I
,
(
a)
A
d
d
an
d
in
p
u
t t
h
e
p
ix
e
l
m
a
p
p
in
g
,
(
b
)
L
in
e
I
n
ter
p
o
latio
n
,
(
c)
C
o
lu
m
n
I
n
ter
p
o
latio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
6
2
0
-
3626
3622
2
.
1
.
I
np
ut
I
m
a
g
e
T
h
e
in
p
u
t
i
m
a
g
e
s
p
r
o
ce
s
s
ed
in
th
is
r
esear
ch
ar
e
o
b
tain
ed
f
r
o
m
r
ad
io
lo
g
y
d
ep
ar
t
m
e
n
t
o
f
C
en
tr
al
Gen
er
al
Ho
s
p
ital
(
R
SUP
)
Dr
.
M.
Dj
am
il
P
ad
an
g
.
A
ll
o
f
t
h
e
i
m
ag
e
s
ar
e
in
th
e
f
o
r
m
o
f
t
h
e
g
r
a
y
s
ca
le
i
m
ag
e
w
h
er
e
d
etails
ab
o
u
t
th
e
d
ata
ca
n
b
e
s
ee
n
in
T
ab
le
1
.
T
h
is
in
p
u
t
i
m
a
g
e
w
a
s
u
s
ed
in
p
r
ev
io
u
s
s
tu
d
ie
s
w
it
h
a
s
p
ec
if
ic
p
u
r
p
o
s
e
[
1
7
-
1
8
]
.
T
ab
le
1
.
I
n
p
u
t I
m
a
g
e
Sp
ec
i
f
ic
atio
n
C
a
t
e
g
o
r
y
F
o
r
mat
Q
u
a
n
t
i
t
y
C
o
mp
u
t
e
d
T
o
mo
g
r
a
p
h
y
S
c
a
n
(
C
T
S
c
a
n
)
W
i
n
d
o
w
s b
i
t
ma
p
(
b
mp
)
5
C
h
e
st
X
-
Ray
Jo
i
n
t
P
h
o
t
o
g
r
a
p
h
i
c
Ex
p
e
r
t
s G
r
o
u
p
(
j
p
g
)
42
P
a
n
o
r
a
mi
c
X
-
R
a
y
P
o
r
t
a
b
l
e
N
e
t
w
o
r
k
G
r
a
p
h
i
c
s (p
n
g
)
27
2
.
2
.
P
ix
el
Addi
t
io
n
I
m
ag
e
e
n
lar
g
e
m
e
n
t
i
s
d
o
n
e
b
y
ad
d
in
g
n
e
w
p
ix
el
s
.
So
t
h
e
i
m
a
g
e
s
ize
is
e
n
lar
g
ed
to
n
t
i
m
es,
th
e
eq
u
atio
n
is
:
c
n
z
f
.
)
(
(
1
)
w
h
er
e:
f
(
z)
: i
m
ag
e
e
n
lar
g
e
m
e
n
t
n
: i
m
ag
e
s
ize
p
r
o
lif
er
atio
n
c:
in
p
u
t i
m
a
g
e
Fo
r
ea
ch
e
n
lar
g
e
m
e
n
t
p
r
o
ce
s
s
in
th
e
tes
tin
g
p
h
ase,
ad
d
itio
n
o
f
as
m
a
n
y
p
i
x
els
as
th
e
p
r
ev
i
o
u
s
i
m
a
g
e
is
ap
p
lied
.
So
t
h
e
i
m
a
g
e
s
ize
b
ec
o
m
e
s
2
-
f
o
ld
f
r
o
m
t
h
e
p
r
e
v
io
u
s
s
ize.
An
e
x
a
m
p
le
ill
u
s
tr
atio
n
o
f
t
h
e
ad
d
itio
n
o
f
p
ix
els
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
2
(
a)
.
I
f
k
c
in
itialize
s
th
e
n
u
m
b
er
o
f
i
n
itial
i
m
a
g
e
co
lu
m
n
s
an
d
,
b
c
in
itializes
th
e
n
u
m
b
er
o
f
r
o
w
s
t
h
en
th
e
n
u
m
b
er
o
f
i
m
ag
e
en
lar
g
e
m
en
t
co
lu
m
n
s
b
ec
o
m
es
k
x
a
n
d
th
e
r
ea
r
in
g
r
o
w
b
ec
o
m
e
s
b
x
.
T
h
en
th
e
eq
u
a
tio
n
s
o
f
m
a
n
y
r
o
w
s
a
n
d
co
lu
m
n
s
o
f
m
a
g
n
if
ica
tio
n
i
m
a
g
e
ar
e
as f
o
llo
w
s
:
1
kc
kc
kx
(
2
)
1
bc
bc
bx
(
3
)
2
.
3
.
I
np
ut
P
ix
el
M
a
pp
ing
T
o
m
ap
an
in
itial
p
i
x
el
i
m
a
g
e
v
al
u
e
w
i
th
a
m
ag
n
i
f
ied
i
m
a
g
e
b
ased
o
n
p
ix
e
l
p
o
s
itio
n
,
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
p
ix
el
i
n
p
u
t is
u
s
ed
:
)
1
,
1
(
)
,
(
b
b
k
k
b
k
c
z
(
4
)
2
.
4
.
L
ine In
t
er
po
la
t
io
n
L
i
n
e
I
n
ter
p
o
latio
n
is
th
e
p
r
o
ce
s
s
o
f
ch
ar
g
in
g
ag
ai
n
s
t
e
m
p
t
y
p
ix
els
u
s
i
n
g
th
e
clo
s
es
t
v
al
u
e
in
a
r
o
w
.
T
h
e
p
o
s
i
tio
n
o
f
t
h
e
p
r
o
ce
s
s
e
d
r
o
w
is
in
ter
r
u
p
ted
b
y
a
n
e
x
is
t
in
g
p
i
x
el
v
alu
e.
T
h
e
i
llu
s
tr
atio
n
o
f
th
e
lin
e
in
ter
p
o
latio
n
ca
n
b
e
s
ee
n
i
n
F
ig
u
r
e
2
(
b
)
.
T
h
e
v
alu
e
o
f
t
h
e
e
m
p
t
y
p
i
x
el
s
b
et
w
ee
n
th
e
li
n
es
is
s
p
ec
i
f
ied
u
s
i
n
g
th
e
f
o
llo
w
i
n
g
f
o
r
m
u
la
:
2
)
,
1
(
)
,
1
(
)
,
(
b
k
b
k
b
k
z
z
z
(
5
)
2
.
5
.
Co
lu
m
n I
nte
rpo
la
t
io
n
On
ce
th
e
b
la
n
k
p
i
x
el
v
a
lu
e
i
n
a
r
o
w
f
illed
,
co
lu
m
n
s
ar
e
in
ter
p
o
lated
.
I
n
ter
p
o
latio
n
o
f
co
lu
m
n
s
is
t
h
e
p
r
o
ce
s
s
o
f
ch
ar
g
i
n
g
ag
a
in
s
t
e
m
p
t
y
p
i
x
els
u
s
in
g
t
h
e
clo
s
est
v
alu
e
i
n
a
s
in
g
le
co
lu
m
n
.
T
h
e
p
o
s
itio
n
o
f
th
e
p
r
o
ce
s
s
ed
co
lu
m
n
i
s
in
ter
r
u
p
t
ed
b
y
an
ex
is
ti
n
g
p
ix
el
v
al
u
e.
I
llu
s
tr
atio
n
o
f
lin
e
i
n
ter
p
o
latio
n
ca
n
b
e
s
ee
n
i
n
Fig
u
r
e
2
(
c)
.
T
h
e
v
alu
e
o
f
e
m
p
t
y
p
ix
el
s
b
et
w
ee
n
co
lu
m
n
s
ar
e
ca
lcu
lated
u
s
i
n
g
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
la:
2
)
1
,
(
)
1
,
(
)
,
(
b
k
b
k
b
k
z
z
z
(
6
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
E
n
la
r
g
e
Med
ica
l I
ma
g
e
Usi
n
g
Lin
e
-
C
o
lu
mn
I
n
terp
o
la
tio
n
(
LC
I
)
Meth
o
d
(
Ju
fr
ia
d
if
N
a
`
a
m
)
3623
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
T
ests
co
n
d
u
cted
o
n
t
h
is
m
et
h
o
d
is
t
h
e
cr
o
p
p
ed
m
ed
ical
i
m
a
g
e
d
ata
w
it
h
m
an
u
al
[
1
7
]
.
T
h
is
is
ess
e
n
tial
to
eli
m
in
ate
u
n
n
ee
d
e
d
ar
ea
s
in
th
e
an
al
y
s
is
.
O
n
e
i
m
ag
e
o
f
ea
ch
d
ata
f
o
r
m
at
p
r
esen
ted
i
n
th
i
s
p
ap
er
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
P
r
io
r
to
th
e
p
r
o
ce
s
s
o
f
i
m
ag
e
e
n
l
ar
g
e
m
e
n
t,
a
n
i
m
ag
e
ar
ea
t
h
at
w
o
u
ld
b
ec
o
m
e
th
e
o
b
j
ec
t
o
f
o
b
s
er
v
atio
n
w
as
ta
k
en
.
T
h
e
p
r
o
ce
s
s
o
f
ta
k
in
g
t
h
is
ar
ea
w
as
d
o
n
e
b
y
c
u
tt
in
g
(
cr
o
p
)
.
I
m
ag
e
o
f
p
r
o
ce
s
s
in
g
r
es
u
lt c
a
n
b
e
s
ee
n
i
n
T
ab
le
2
.
B
ased
o
n
th
e
test
r
esu
lts
i
n
T
a
b
le
2
,
it
ca
n
b
e
o
b
s
er
v
ed
th
at
th
e
i
m
a
g
e
r
esu
lt
h
as
r
elati
v
el
y
th
e
s
a
m
e
s
ize.
T
h
e
d
if
f
er
e
n
ce
is
,
t
h
e
i
m
ag
e
r
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
o
n
l
y
a
1
-
p
ix
el
co
l
u
m
n
a
n
d
1
-
p
i
x
el
r
o
w
less
t
h
a
n
t
h
o
s
e
o
f
t
h
e
NNI
,
B
L
I
a
n
d
B
C
I
m
e
th
o
d
s
.
T
h
is
d
ef
icien
c
y
is
ca
u
s
ed
b
y
t
h
e
ad
d
iti
o
n
o
f
p
i
x
els
o
n
l
y
o
n
th
e
s
id
elin
e
s
o
f
t
h
e
o
r
ig
i
n
al
p
i
x
els.
Ho
w
e
v
er
,
t
h
is
1
-
p
i
x
el
d
i
f
f
er
en
ce
ca
n
s
till
b
e
i
g
n
o
r
ed
b
ec
au
s
e
i
t
i
s
o
n
l
y
a
d
ef
icien
c
y
in
t
h
e
f
i
n
al
r
o
w
o
r
co
lu
m
n
p
o
s
itio
n
an
d
n
o
t
th
e
p
o
s
itio
n
o
f
th
e
o
b
j
ec
t
to
b
e
o
b
s
er
v
ed
in
th
e
m
ed
ical
i
m
a
g
e.
T
ab
le
2
.
T
w
o
T
im
e
s
E
n
lar
g
e
m
en
t Re
s
u
l
t (
T
h
e
Size
is
2
5
% o
f
th
e
Or
ig
i
n
al
S
ize
)
M
e
d
i
c
a
l
I
mag
e
C
r
o
p
p
e
d
I
mag
e
En
l
a
r
g
e
I
mag
e
/
H
i
st
o
g
r
a
m
L
C
I
M
e
t
h
o
d
(
P
r
o
p
o
se
d
)
N
N
I
M
e
t
h
o
d
B
L
I
M
e
t
h
o
d
B
C
I
M
e
t
h
o
d
B
r
a
i
n
CT
-
S
c
a
n
(
7
8
x
1
1
2
p
i
x
e
l
)
(
1
5
5
x
2
2
3
p
i
x
e
l
)
(
1
5
6
x
2
2
4
p
i
x
e
l
)
(
1
5
6
x
2
2
4
p
i
x
e
l
)
(
1
5
6
x
2
2
4
p
i
x
e
l
)
C
h
e
st
X
-
Ray
(
2
0
9
x
2
5
1
p
i
x
e
l
)
(
4
1
7
x
5
0
1
p
i
x
e
l
)
(
4
1
8
x
5
0
2
p
i
x
e
l
)
(
4
1
8
x
5
0
2
p
i
x
e
l
)
(
4
1
8
x
5
0
2
p
i
x
e
l
)
P
a
n
o
r
a
m
i
c
X
-
Ray
(
1
4
8
x
2
3
3
p
i
x
e
l
)
(
2
9
5
x
4
6
5
p
i
x
e
l
)
(
2
9
6
x
4
6
6
p
i
x
e
l
)
(
2
9
6
x
4
6
6
p
i
x
e
l
)
(
2
9
6
x
4
6
6
p
i
x
e
l
)
0
10
20
30
40
50
60
70
80
90
100
0
50
100
150
200
250
0
50
100
150
200
250
300
350
400
0
50
100
150
200
250
0
50
100
150
200
250
300
350
400
0
50
100
150
200
250
0
50
100
150
200
250
300
350
400
0
50
100
150
200
250
0
50
100
150
200
250
300
350
400
0
50
100
150
200
250
0
100
200
300
400
500
600
700
800
0
50
100
150
200
250
0
500
1000
1500
2000
2500
0
50
100
150
200
250
0
500
1000
1500
2000
2500
3000
3500
0
50
100
150
200
250
0
500
1000
1500
2000
2500
3000
3500
0
50
100
150
200
250
0
500
1000
1500
2000
2500
3000
3500
0
50
100
150
200
250
0
50
100
150
200
250
300
350
400
450
500
0
1
2
3
4
5
6
x
1
0
4
0
200
400
600
800
1000
1200
1400
0
50
100
150
200
250
0
200
400
600
800
1000
1200
1400
1600
1800
2000
0
50
100
150
200
250
0
200
400
600
800
1000
1200
1400
1600
1800
2000
0
50
100
150
200
250
0
200
400
600
800
1000
1200
1400
1600
1800
2000
0
50
100
150
200
250
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
6
2
0
-
3626
3624
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
I
m
a
g
e
tes
t (
a)
B
r
ain
C
T
-
Scan
,
(
b
)
C
h
e
s
t X
-
R
a
y
,
(
c)
P
an
o
r
am
ic
X
-
R
a
y
T
h
e
f
o
r
m
o
f
o
b
j
ec
ts
co
n
tain
e
d
in
th
e
i
m
a
g
e
o
f
th
e
r
esu
l
ts
ca
n
b
e
w
ell
o
b
s
er
v
ed
.
T
h
is
c
an
b
e
s
ee
n
f
r
o
m
t
h
e
f
l
u
ctu
a
tio
n
o
f
t
h
e
h
is
to
g
r
a
m
g
r
ap
h
,
p
ar
ticu
lar
l
y
t
h
r
o
u
g
h
t
h
e
r
elati
v
el
y
s
i
m
ilar
s
p
r
ea
d
o
f
g
r
e
y
v
al
u
es.
P
r
in
cip
all
y
,
th
e
d
if
f
er
e
n
ce
b
et
w
ee
n
o
b
j
ec
ts
o
n
th
e
i
m
a
g
e
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
ap
p
ea
r
s
m
o
r
e
s
h
ar
p
l
y
.
T
h
e
s
p
r
ea
d
o
f
m
o
r
e
g
r
a
y
v
al
u
es
ca
u
s
es
t
h
e
s
h
ar
p
n
e
s
s
o
f
t
h
i
s
o
b
j
ec
t.
Her
e
is
th
e
r
esu
lt
o
f
th
e
en
lar
g
e
m
e
n
t
p
r
o
ce
s
s
to
4
ti
m
e
s
f
r
o
m
th
e
in
itial
i
m
a
g
e
to
B
r
ain
C
T
-
Sca
n
i
m
ag
e.
T
h
e
r
esu
l
ts
o
f
t
h
e
co
m
p
ar
is
o
n
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
4
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
4
.
4
tim
e
s
B
r
ain
C
T
-
Sc
an
I
m
a
g
e
en
lar
g
e
m
en
t (
i
n
o
r
ig
in
al
s
ize)
,
(
a)
P
r
o
p
o
s
ed
m
et
h
o
d
,
(
b
)
NNI
m
et
h
o
d
,
(
c)
B
L
I
m
et
h
o
d
,
(
d
)
B
C
I
m
eth
o
d
T
h
e
p
ix
el
s
ize
at
4
ti
m
es
m
ag
n
i
f
icatio
n
r
es
u
lt
s
f
o
r
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
3
0
9
x
4
4
5
p
ix
els,
w
h
ile
t
h
e
o
th
er
m
eth
o
d
h
as
t
h
e
s
a
m
e
s
i
ze
,
w
h
ic
h
is
3
1
2
x
4
4
8
p
ix
els.
T
h
is
4
x
3
p
i
x
el
d
i
f
f
er
en
ce
is
n
o
t
v
er
y
i
n
f
lu
e
n
tial
,
w
h
er
e:
000086
.
0
139776
12
448
312
4
3
x
x
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
E
n
la
r
g
e
Med
ica
l I
ma
g
e
Usi
n
g
Lin
e
-
C
o
lu
mn
I
n
terp
o
la
tio
n
(
LC
I
)
Meth
o
d
(
Ju
fr
ia
d
if
N
a
`
a
m
)
3625
0
.
0
0
0
0
8
6
is
th
e
r
elativ
el
y
s
m
a
ll
d
if
f
er
e
n
ce
b
et
w
ee
n
i
m
a
g
e
s
i
ze
in
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
co
m
p
ar
ed
to
th
e
i
m
a
g
e
s
ize
o
f
ex
i
s
ti
n
g
m
e
th
o
d
s
.
I
n
Fig
u
r
e
4
ca
n
also
b
e
o
b
s
er
v
ed
th
at
th
e
d
if
f
er
en
c
e
b
et
w
ee
n
t
h
e
n
e
w
p
ix
el
v
al
u
es
o
n
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
th
e
u
n
d
er
l
y
in
g
p
i
x
els
o
f
t
h
e
in
i
tial
i
m
ag
e
is
n
o
t
s
o
co
n
s
p
icu
o
u
s
.
T
h
er
ef
o
r
e,
th
e
d
etails
o
f
t
h
e
o
b
j
ec
ts
in
th
e
i
m
a
g
e
ar
e
s
till
th
e
s
a
m
e.
T
h
e
d
if
f
er
en
ce
s
o
f
t
h
i
s
p
r
o
p
o
s
ed
m
et
h
o
d
to
ex
is
ti
n
g
m
et
h
o
d
s
(
NNI
,
B
L
I
an
d
B
C
I
)
a
r
e
a
d
d
itio
n
al
p
ix
el
v
alu
e
s
clo
s
er
to
th
e
v
alu
e
o
f
n
eig
h
b
o
r
in
g
p
ix
els
s
o
th
e
d
etail
v
ie
w
is
n
o
t b
l
u
r
r
ed
.
4.
CO
NCLU
SI
O
N
Fro
m
th
e
te
s
t
r
es
u
lt
s
o
f
t
h
e
m
ed
ical
i
m
ag
e
ca
n
b
e
s
ee
n
th
at
th
e
i
m
a
g
e
en
lar
g
e
m
en
t
u
s
i
n
g
L
C
I
ca
n
in
cr
ea
s
e
t
h
e
s
ize
o
f
t
h
e
o
r
ig
in
al
i
m
a
g
e.
E
ac
h
s
ta
g
e
in
t
h
e
p
r
o
ce
s
s
p
r
o
d
u
ce
s
an
i
m
a
g
e
s
iz
e
t
w
o
ti
m
es
lar
g
e
r
th
an
t
h
e
o
r
ig
in
al
i
m
ag
e.
T
h
u
s
,
th
e
o
b
j
ec
ts
co
n
ta
in
ed
i
n
th
e
i
m
a
g
e
r
e
s
u
l
t
ar
e
lar
g
er
a
n
d
s
h
ar
p
er
.
T
h
is
s
t
u
d
y
in
d
icate
s
t
h
at
t
h
e
L
C
I
m
et
h
o
d
ca
n
f
ac
i
litate
t
h
e
o
b
s
er
v
atio
n
o
f
o
b
j
ec
ts
in
th
e
m
ed
ical
i
m
ag
e
in
t
h
e
p
r
o
ce
s
s
o
f
m
ed
ical
an
al
y
s
is
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
w
o
u
ld
li
k
e
to
t
h
an
k
f
o
r
Di
r
ec
to
r
an
d
all
s
ta
f
f
o
f
Dep
ar
t
m
en
t
o
f
R
ad
io
lo
g
y
,
Dr
.
M.
Dj
am
il
C
e
n
ter
Gen
er
al
Ho
s
p
ital,
P
ad
an
g
,
w
h
i
ch
h
a
s
allo
w
ed
th
e
u
s
e
o
f
t
h
e
d
ata
in
th
i
s
s
t
u
d
y
.
RE
F
E
R
E
NC
E
S
[1
]
B.
I.
Re
in
e
r
,
e
t
a
l
,
“
T
h
e
Cli
n
ica
l
Im
p
e
ra
ti
v
e
o
f
M
e
d
ica
l
I
m
a
g
in
g
In
f
o
rm
a
ti
c
s,”
Jo
u
rn
a
l
o
f
Dig
it
a
l
Im
a
g
in
g
,
v
o
l.
2
2
,
n
o
.
4
,
p
p
.
3
4
5
-
3
4
7
,
2
0
0
9
.
[2
]
S
.
Bh
a
rg
a
v
a
a
n
d
A
.
S
o
m
k
u
w
a
r,
“
Ev
a
lu
a
ti
o
n
o
f
No
ise
Ex
c
lu
sio
n
o
f
M
e
d
i
c
a
l
Im
a
g
e
s
u
sin
g
H
y
b
rid
iza
ti
o
n
o
f
P
a
rti
c
a
l
S
w
a
r
m
Op
ti
m
iz
a
ti
o
n
a
n
d
Biv
a
riate
S
h
rin
k
a
g
e
M
e
th
o
d
s,”
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(IJECE),
v
o
l.
5
,
n
o
.
3
,
p
p
.
4
2
1
-
4
2
8
,
2
0
1
5
.
[3
]
A
.
T
.
B.
A
le
x
a
n
d
K.
T
.
Rick
y
,
M
e
d
ica
l
Im
a
g
in
g
In
f
o
r
m
a
ti
c
s,
S
p
rin
g
e
r
Ne
w
Yo
rk
Do
rd
re
c
h
t
He
id
e
lb
e
rg
,
L
o
n
d
o
n
,
p
p
.
3
,
2
0
1
0
.
[4
]
S
.
P
o
h
o
a
ta
a
n
d
A
.
G
ra
u
r,
"
HD
T
V
S
y
ste
m
f
o
r
P
a
rk
in
s
o
n
'
s
Dise
a
se
Dia
g
n
o
sis,"
A
d
v
a
n
c
e
s
in
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
1
3
,
n
o
.
2
,
p
p
.
9
1
-
9
6
,
2
0
1
3
.
[5
]
F
.
M
a
li
k
,
e
t
a
l
,
"
A
n
En
se
m
b
le
o
f
Clas
si
f
ie
rs
b
a
se
d
A
p
p
ro
a
c
h
f
o
r
P
re
d
icti
o
n
o
f
A
lzh
e
i
m
e
r'
s
Dis
e
a
se
u
sin
g
f
M
R
I
Im
a
g
e
s b
a
se
d
o
n
F
u
sio
n
o
f
V
o
lu
m
e
tri
c
,
T
e
x
tu
ra
l
a
n
d
He
m
o
d
y
n
a
m
ic F
e
a
tu
re
s,"
A
d
v
a
n
c
e
s in
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
1
8
,
n
o
.
1
,
p
p
.
6
1
-
7
0
,
2
0
1
8
.
[6
]
R.
M
.
Ko
k
a
te
a
n
d
V.
K.
S
h
a
n
d
il
y
a
,
“
E
n
h
a
n
c
e
m
e
n
t
T
e
c
h
n
iq
u
e
s
o
f
M
e
d
ica
l
Im
a
g
e
s
-
A
R
e
v
ie
w
,
”
In
te
rn
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Re
se
a
rc
h
in
Co
m
p
u
t
e
r
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
5
3
3
-
5
3
5
,
2
0
1
6
.
[7
]
W
.
Do
n
g
,
e
t
a
l
,
“
Op
t
im
ize
d
I
m
a
g
e
Re
siz
in
g
Us
in
g
S
e
a
m
Ca
rv
in
g
a
n
d
S
c
a
li
n
g
,
”
A
CM
T
ra
n
sa
c
t
io
n
s
o
n
G
ra
p
h
ics
,
A
s
so
c
iatio
n
f
o
r
Co
m
p
u
ti
n
g
M
a
c
h
in
e
ry
,
v
o
l.
2
9
,
n
o
.
5
,
p
p
.
1
-
1
0
,
2
0
0
9
.
[8
]
L
.
S
e
o
n
g
su
a
n
d
J.
G
wa
n
g
g
il
,
“
L
a
g
ra
n
g
e
M
e
th
o
d
f
o
r
Up
sa
m
p
li
n
g
,
”
A
d
v
a
n
c
e
d
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
L
e
tt
e
r
s,
v
o
l.
8
0
,
p
p
.
9
-
1
3
,
2
0
1
5
.
[9
]
M
a
th
W
o
rk
s:
I
m
a
g
e
P
r
o
c
e
ss
in
g
we
b
site,
2
0
1
8
.
A
v
a
il
a
b
le:
h
tt
p
s:/
/www
.
m
a
th
w
o
rk
s.co
m
/
m
a
t
lab
c
e
n
tral/an
sw
e
rs/1
4
1
0
3
-
im
a
g
e
-
p
ro
c
e
ss
in
g
[1
0
]
N.
S
u
e
tak
e
,
e
t
a
l
,
“
F
a
st i
m
a
g
e
e
n
larg
e
m
e
n
t
u
sin
g
p
re
d
e
f
in
e
d
c
o
d
e
b
o
o
k
a
n
d
e
ig
e
n
sp
a
c
e
b
a
c
k
p
ro
jec
ti
o
n
f
o
r
lo
st p
ix
e
l,
”
Op
ti
c
a
l
Re
v
ie
w
,
v
o
l.
1
8
,
n
o
.
6
,
p
p
.
4
2
3
–
4
2
9
,
2
0
1
1
.
[1
1
]
F
.
Z
h
a
n
g
,
e
t
a
l
,
“
En
larg
in
g
im
a
g
e
b
y
c
o
n
stra
in
e
d
lea
st
sq
u
a
re
a
p
p
r
o
a
c
h
w
it
h
sh
a
p
e
p
re
se
rv
in
g
,
“
Jo
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
3
0
,
n
o
3
,
p
p
.
4
8
9
–
4
9
8
,
2
0
1
5
.
[1
2
]
X
.
Z
h
o
n
g
,
e
t
a
l
,
“
A
n
o
v
e
l
a
d
a
p
t
iv
e
i
m
a
g
e
z
o
o
m
in
g
sc
h
e
m
e
v
ia
w
e
i
g
h
ted
lea
st
-
sq
u
a
re
s
e
stim
a
ti
o
n
,
”
F
ro
n
ti
e
rs
o
f
Co
m
p
u
ter S
c
ien
c
e
,
v
o
l.
9
,
n
o
.
5
,
p
p
.
7
0
3
-
7
1
2
,
2
0
1
5
.
[1
3
]
R.
Oliv
ier
a
n
d
C.
Ha
n
q
ian
g
,
“
Ne
a
re
st
Ne
i
g
h
b
o
r
V
a
lu
e
In
ter
p
o
lati
o
n
,
”
(IJA
CS
A
)
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
Co
m
p
u
ter S
c
ien
c
e
a
n
d
A
p
p
li
c
a
ti
o
n
s,
v
o
l.
3
,
n
o
.
4
,
p
p
.
1
-
6
,
2
0
1
2
.
[1
4
]
F
.
Ba
sh
a
r
,
e
t
a
l
,
"
F
a
c
e
Re
c
o
g
n
it
io
n
u
sin
g
S
im
il
a
rit
y
P
a
tt
e
rn
o
f
I
m
a
g
e
Dir
e
c
ti
o
n
a
l
Ed
g
e
Re
sp
o
n
se
,
"
A
d
v
a
n
c
e
s
in
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
v
o
l.
1
4
,
n
o
.
1
,
p
p
.
6
9
-
7
6
,
2
0
1
4
.
[1
5
]
L
.
Ka
i
-
yu
,
e
t
a
l
,
“
T
h
e
a
p
p
li
c
a
ti
o
n
o
f
B
-
sp
li
n
e
b
a
se
d
i
n
terp
o
lati
o
n
i
n
re
a
l
-
ti
m
e
i
m
a
g
e
e
n
larg
in
g
p
ro
c
e
ss
in
g
,
”
T
h
e
2
0
1
4
2
n
d
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
y
st
e
m
s an
d
In
f
o
rm
a
ti
c
s (ICS
A
I
2
0
1
4
),
S
h
a
n
g
h
a
i
,
p
p
.
8
2
3
-
8
2
7
,
2
0
1
4
.
[1
6
]
S
.
G
o
p
in
a
t
h
a
n
,
e
t
a
l
,
“
W
a
v
e
let
a
n
d
F
F
T
Ba
se
d
Im
a
g
e
De
n
o
isin
g
Us
in
g
No
n
-
L
in
e
a
r
F
il
ters
,
”
In
tern
a
t
io
n
a
l
Jo
u
r
n
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
(IJECE),
v
o
l
.
5
,
n
o
.
5
,
p
p
.
1
0
1
8
-
1
0
2
6
,
2
0
1
5
.
[1
7
]
J.
Na
`a
m
,
e
t
a
l
,
“
De
tec
ti
o
n
o
f
p
ro
x
im
a
l
c
a
ries
a
t
th
e
m
o
lar
tee
th
u
sin
g
e
d
g
e
e
n
h
a
n
c
e
m
e
n
t
a
lg
o
rit
h
m
,
”
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
El
e
c
tri
c
a
l
a
n
d
C
o
m
p
u
ter E
n
g
in
e
e
rin
g
(IJECE),
v
o
l.
8
,
n
o
.
5
,
p
p
.
3
2
5
9
-
3
2
6
6
,
2
0
1
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
5
,
Octo
b
er
2
0
1
8
:
3
6
2
0
-
3626
3626
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
J
u
fr
ia
d
if
Na
`
a
m
wa
s
b
o
rn
in
P
a
d
a
n
g
,
W
e
st
S
u
m
a
tra
-
in
1
9
6
7
.
H
e
is
a
n
A
ss
o
c
iate
P
ro
f
e
ss
o
r
in
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K.
He
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r
De
g
re
e
in
In
f
o
rm
a
ti
c
s
M
a
n
a
g
e
m
e
n
t
a
n
d
M
a
ste
r
De
g
re
e
in
In
f
o
rm
a
ti
o
n
T
e
c
n
o
lo
g
y
in
1
9
9
4
a
n
d
2
0
0
6
f
ro
m
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
YP
T
K.
M
o
re
o
v
e
r,
h
e
c
o
m
p
lete
d
h
is
Do
c
to
ra
te
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
s
In
f
o
rm
a
ti
c
s
M
e
d
ica
l
I
m
a
g
e
e
x
p
e
rti
se
fro
m
G
u
n
a
d
a
r
m
a
Un
iv
e
r
sit
y
in
Ja
n
u
a
ry
2
0
1
7
.
He
h
a
s
m
e
m
b
e
r
o
f
IEE
E
(9
4
3
1
3
3
3
3
).
S
c
o
p
u
s
I
d
is
5
7
1
8
9
3
7
1
4
9
9
.
C
u
rre
n
tl
y
,
h
e
h
a
s
b
e
e
n
re
se
a
r
c
h
in
g
o
n
A
lg
o
rit
h
m
s
a
n
d
In
f
o
r
m
a
ti
c
s
M
e
d
ica
l
I
m
a
g
e
.
E
-
m
a
il
:
ju
f
riad
if
n
a
a
m
@g
m
a
il
.
c
o
m
J
u
li
u
s
S
a
n
t
o
n
y
wa
s
b
o
rn
in
P
a
d
a
n
g
P
a
n
jan
g
,
W
e
st
S
u
m
a
tera
,
In
d
o
n
e
sia
,
o
n
Ju
ly
2
9
th
1
9
7
3
.
His
De
p
a
rtme
n
t
is
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
YP
T
K
P
a
d
a
n
g
,
W
e
s
S
u
m
a
ter
a
In
d
o
n
e
sia
a
n
d
He
is
a
n
A
ss
o
c
ia
te
P
r
o
f
e
ss
o
r.
He
g
r
a
d
u
a
ted
th
e
Ba
c
h
e
lo
r
De
g
re
e
in
1
9
9
6
i
n
In
f
o
rm
a
ti
c
s M
a
n
a
g
e
m
e
n
t
f
o
r
m
Gu
n
a
d
a
rm
a
Un
iv
e
r
sit
y
a
n
d
M
a
ste
r
De
g
re
e
in
2
0
0
6
i
n
In
f
o
rm
a
ti
o
n
T
e
c
n
o
lo
g
y
f
ro
m
Un
iv
e
rsita
s
P
u
tr
a
In
d
o
n
e
sia
Y
P
T
K.
T
h
e
n
,
h
e
g
ra
d
u
a
ted
th
e
Do
c
to
ra
te
De
g
re
e
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
s
M
e
d
ica
l
I
m
a
g
e
e
x
p
e
rti
se
f
ro
m
G
u
n
a
d
a
r
m
a
Un
iv
e
rsit
y
in
De
c
e
m
b
e
r
2
0
1
5
.
S
c
o
p
u
s
Id
is
5
7
1
8
9
3
6
2
0
2
1
.
S
u
sta
in
a
b
ly
,
h
e
h
a
s
b
e
e
n
re
se
a
rc
h
in
g
o
n
Im
a
g
e
P
ro
c
e
ss
in
g
A
l
g
o
rit
h
m
f
o
r
M
e
d
ica
l
Im
a
g
e
s.
E
-
m
a
il
:
ju
li
u
ss
a
n
to
n
y
@
y
a
h
o
o
.
c
o
.
id
Yuh
a
n
d
r
i
w
a
s
b
o
rn
in
T
a
n
ju
n
g
A
la
m
o
n
M
a
y
1
5
.
He
is
a
n
A
ss
istan
t
P
ro
f
e
ss
o
r
in
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
s
ia
YP
T
K.
He
re
c
e
iv
e
d
th
e
Ba
c
h
e
lo
r
De
g
re
e
in
In
f
o
rm
a
ti
c
s
M
a
n
a
g
e
m
e
n
t
a
n
d
M
a
ste
r
De
g
r
e
e
in
In
f
o
r
m
a
ti
o
n
T
e
c
n
o
lo
g
y
in
1
9
9
2
a
n
d
2
0
0
6
f
ro
m
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
Y
P
T
K.
M
o
re
o
v
e
r,
h
e
c
o
m
p
lete
d
h
is
Do
c
to
ra
te
o
f
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
a
s
In
f
o
r
m
a
ti
c
s
M
e
d
i
c
a
l
I
m
a
g
e
e
x
p
e
rti
se
f
ro
m
G
u
n
a
d
a
rm
a
Un
iv
e
rsit
y
in
A
p
ril
2
0
1
7
.
He
is
a
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
P
u
tra
I
n
d
o
n
e
sia
Y
P
T
K.
S
c
o
p
u
s
Id
is
5
7
1
9
3
4
3
0
9
2
0
.
E
-
m
a
i
l:
y
u
y
u
@u
p
iy
p
tk
.
a
c
.
id
S
u
m
ija
n
wa
s
b
o
rn
in
Ng
a
n
ju
k
o
n
M
a
y
7
1
9
6
6
.
He
re
c
e
iv
e
d
th
e
B
a
c
h
e
lo
r
De
g
re
e
in
In
f
o
r
m
a
ti
c
s
M
a
n
a
g
e
m
e
n
t
in
1
9
9
1
f
ro
m
U
n
iv
e
rsitas
P
u
tra
I
n
d
o
n
e
sia
Y
P
T
K,
M
a
ste
r
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
lo
g
y
in
1
9
9
8
f
ro
m
Un
iv
e
r
sity
T
e
c
h
n
o
lo
g
y
M
a
la
y
sia
(U
T
M
).
He
c
o
m
p
lete
d
h
a
s
Do
c
to
ra
te
o
f
In
f
o
r
m
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
s
M
e
d
ica
l
I
m
a
g
e
Ex
p
e
rti
se
f
ro
m
G
u
n
a
d
a
rm
a
Un
iv
e
rsit
y
in
De
c
e
m
b
e
r
2
0
1
5
.
He
is
m
e
m
b
e
r
o
f
A
CM
(2
3
1
4
5
7
5
1
)
.
S
c
o
p
u
s
Id
is
5
7
1
9
4
7
8
7
0
7
6
.
E
-
m
a
il
:
so
e
@u
p
iy
p
tk
.
o
rg
G
u
n
a
d
i
W
i
d
i
Nu
r
c
a
h
y
o
w
a
s
b
o
rn
i
n
T
e
m
a
n
g
g
u
n
g
,
1
4
M
a
rc
h
1
9
6
9
.
He
w
a
s
g
ra
d
u
a
ted
Ba
c
h
e
lo
r
d
e
g
re
e
in
In
f
o
rm
a
ti
c
s
M
a
n
a
g
e
m
e
n
t
a
t
Un
iv
e
rsitas
P
u
tra
In
d
o
n
e
sia
YP
T
K
P
a
d
a
n
g
i
n
1
9
9
2
.
He
c
o
m
p
lete
d
h
is
M
a
ste
r
a
n
d
P
h
D
in
Co
m
p
u
ter
S
c
ien
c
e
a
t
Un
iv
e
rs
it
i
T
e
k
n
o
lo
g
i
M
a
lay
sia
in
2
0
0
3
.
S
c
o
p
u
s I
d
is
5
7
2
0
0
5
6
3
3
5
6
.
E
-
m
a
il
:
g
u
n
a
d
iw
id
i@
y
a
h
o
o
.
c
o
.
i
d
Evaluation Warning : The document was created with Spire.PDF for Python.