I
n
d
on
e
s
i
a
n
Jo
u
r
n
al
of
E
l
e
c
t
r
i
c
al
E
n
g
i
n
e
e
r
i
n
g a
n
d
C
om
p
u
t
e
r
S
c
i
e
n
c
e
V
ol
.
4
3
, N
o.
2
,
A
u
g
us
t
202
6
, pp.
595
~
60
6
I
S
S
N
:
2502
-
4752, D
O
I
:
10.11591/
i
j
e
e
c
s
.
v
4
3
.i
2
.
pp
595
-
606
595
Jou
r
n
al
h
om
e
page
:
ht
t
p:
/
/
i
j
e
e
c
s
.i
ae
s
c
or
e
.c
om
A
f
f
i
n
e
-
i
n
var
i
a
n
t
f
e
at
u
r
e
l
e
ar
n
i
n
g
f
or
ac
c
u
r
at
e
u
l
c
e
r
d
e
t
e
c
t
i
on
i
n
w
i
r
e
l
e
s
s c
ap
s
u
l
e
e
n
d
osc
o
p
y i
m
age
s
S
.
B
h
u
va
n
e
s
w
ar
i
1
,
M
. S
u
l
t
h
an
I
b
r
ah
i
m
2
1
D
e
pa
r
t
m
e
n
t
of
C
o
m
put
e
r
S
c
i
e
n
c
e
,
M
a
dur
a
i
K
a
m
a
r
a
j
U
n
i
ve
r
s
i
t
y,
M
a
dur
a
i
,
I
n
di
a
2
D
e
pa
r
t
m
e
n
t
of
C
o
m
put
e
r
S
c
i
e
n
c
e
,
G
ove
r
nm
e
n
t
A
r
t
s
a
nd
S
c
i
e
n
c
e
C
ol
l
e
g
e
,
M
a
dur
a
i
,
I
n
di
a
A
r
t
i
c
l
e
I
n
f
o
A
B
S
T
R
A
C
T
A
r
t
i
c
l
e
h
i
s
t
o
r
y
:
R
e
c
e
i
v
e
d
S
e
p 27, 2024
R
e
v
i
s
e
d
M
a
y
28, 2026
A
c
c
e
pt
e
d
J
ul
23, 2026
Ul
c
e
r
s
a
r
e
l
e
s
i
o
n
s
th
a
t
d
e
v
e
l
o
p
i
n
th
e
l
i
n
i
n
g
o
f
th
e
g
a
s
tr
o
i
n
tes
ti
n
a
l
(
GI
)
tr
a
c
t,
p
a
r
ti
c
u
l
a
r
l
y
i
n
th
e
s
to
m
a
c
h
a
n
d
s
m
a
l
l
i
n
tes
ti
n
e
,
a
n
d
m
a
y
l
e
a
d
to
s
e
v
e
r
e
c
o
m
p
l
i
c
a
t
i
o
n
s
s
u
c
h
a
s
C
r
o
h
n
’
s
d
i
s
e
a
s
e
a
n
d
u
l
c
e
r
a
ti
v
e
c
o
li
t
i
s
if
n
o
t
d
e
tec
ted
a
t
a
n
e
a
r
l
y
s
tag
e
.
C
o
n
v
e
n
ti
o
n
a
l
e
n
d
o
s
c
o
p
i
c
p
r
o
c
e
d
u
r
e
s
a
r
e
o
f
ten
u
n
c
o
m
f
o
r
tab
l
e
f
o
r
p
a
t
i
e
n
ts
a
n
d
m
a
y
p
r
o
v
i
d
e
li
m
i
ted
v
i
s
u
a
li
z
a
t
i
o
n
o
f
th
e
e
n
ti
r
e
s
m
a
ll
i
n
tes
ti
n
e
.
W
ir
e
l
e
s
s
c
a
p
s
u
l
e
e
n
d
o
s
c
o
p
y
(
W
C
E
)
h
a
s
e
m
e
r
g
e
d
a
s
a
n
o
n
-
i
n
v
a
s
i
v
e
a
l
ter
n
a
t
i
v
e
f
o
r
c
o
m
p
r
e
h
e
n
s
i
v
e
GI
tr
a
c
t
e
x
a
m
i
n
a
ti
o
n
;
h
o
we
v
e
r
,
a
u
to
m
a
ted
u
l
c
e
r
d
e
te
c
ti
o
n
f
r
o
m
W
C
E
i
m
a
g
e
s
r
e
m
a
i
n
s
c
h
a
ll
e
n
g
i
n
g
d
u
e
to
i
m
a
g
e
n
o
i
s
e
,
c
o
m
p
l
e
x
ti
s
s
u
e
s
tr
u
c
tu
r
e
s
,
a
n
d
c
o
m
p
u
tati
o
n
a
l
r
e
q
u
i
r
e
m
e
n
ts
.
T
o
a
d
d
r
e
s
s
th
e
s
e
i
s
s
u
e
s
,
th
i
s
p
a
p
e
r
p
r
o
p
o
s
e
s
a
C
a
m
a
r
g
o
’
s
I
n
d
e
x
i
v
e
Ku
wa
h
a
r
a
f
il
te
r
i
n
g
-
b
a
s
e
d
a
f
f
i
n
e
-
i
n
v
a
r
i
a
n
t
s
li
c
e
d
r
e
g
r
e
s
s
i
o
n
(
C
I
KF
-
AI
S
R
)
f
r
a
m
e
wo
r
k
f
o
r
a
c
c
u
r
a
te
a
n
d
e
f
f
i
c
i
e
n
t
u
l
c
e
r
d
e
tec
t
i
o
n
.
T
h
e
p
r
o
p
o
s
e
d
f
r
a
m
e
wo
r
k
c
o
n
s
i
s
ts
o
f
i
m
a
g
e
a
c
q
u
i
s
i
t
i
o
n
,
p
r
e
p
r
o
c
e
s
s
i
n
g
,
s
e
g
m
e
n
tati
o
n
,
a
n
d
f
e
a
tu
r
e
e
x
tr
a
c
t
i
o
n
s
tag
e
s
.
Ad
a
p
ti
v
e
C
I
KF
i
s
e
m
p
l
o
y
e
d
to
s
u
p
p
r
e
s
s
n
o
i
s
e
wh
i
le
p
r
e
s
e
r
v
i
n
g
e
d
g
e
i
n
f
o
r
m
a
ti
o
n
.
S
u
b
s
e
q
u
e
n
tl
y
,
Vo
n
Ne
u
m
a
n
n
l
o
c
a
li
ty
s
e
g
m
e
n
tati
o
n
c
o
m
b
i
n
e
d
wi
th
th
e
C
a
n
b
e
r
r
a
d
i
s
tan
c
e
m
e
a
s
u
r
e
i
s
u
t
i
li
z
e
d
to
i
d
e
n
ti
f
y
r
e
g
i
o
n
s
o
f
i
n
ter
e
s
t
(
R
OI
s
)
.
F
i
n
a
ll
y
,
a
f
f
i
n
e
-
i
n
v
a
r
i
a
n
t
s
a
li
e
n
c
y
s
li
c
e
d
r
e
g
r
e
s
s
i
o
n
e
x
tr
a
c
ts
d
i
s
c
r
i
m
i
n
a
t
i
v
e
s
h
a
p
e
,
c
o
l
o
r
,
a
n
d
tex
tu
r
e
f
e
a
tu
r
e
s
f
o
r
u
l
c
e
r
d
e
tec
ti
o
n
.
E
x
p
e
r
i
m
e
n
tal
e
v
a
l
u
a
ti
o
n
o
n
th
e
Hy
p
e
r
-
Kv
a
s
i
r
d
a
tas
e
t
d
e
m
o
n
s
tr
a
tes
t
h
a
t
th
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
a
c
h
i
e
v
e
s
h
i
g
h
e
r
u
l
c
e
r
d
e
tec
ti
o
n
a
c
c
u
r
a
c
y
,
i
m
p
r
o
v
e
d
p
r
e
c
i
s
i
o
n
,
e
n
h
a
n
c
e
d
p
e
a
k
s
i
g
n
a
l
-
to
-
n
o
i
s
e
r
a
t
i
o
(
P
S
NR
)
,
a
n
d
l
o
we
r
d
e
tec
ti
o
n
ti
m
e
c
o
m
p
a
r
e
d
wi
th
e
x
i
s
ti
n
g
d
e
e
p
C
NN
a
n
d
VA
E
-
GAN
a
p
p
r
o
a
c
h
e
s
.
T
h
e
s
e
r
e
s
u
l
ts
c
o
n
f
i
r
m
th
e
e
f
f
e
c
ti
v
e
n
e
s
s
o
f
th
e
p
r
o
p
o
s
e
d
f
r
a
m
e
wo
r
k
f
o
r
c
o
m
p
u
ter
-
a
i
d
e
d
GI
d
iag
n
o
s
i
s
.
K
e
y
w
or
d
s
:
A
da
pt
i
v
e
c
a
m
a
r
a
g
o
’
s
i
nde
xi
v
e
A
f
f
i
ne
i
n
v
a
r
i
a
nt
F
i
l
t
e
r
i
ng
t
e
c
hni
que
R
e
g
r
e
s
s
i
on
U
l
c
e
r
de
t
e
c
t
i
on
V
onne
u
m
a
nn
l
oc
a
l
i
t
y
W
i
r
e
l
e
s
s
c
a
ps
ul
e
e
ndos
pc
opy
T
h
i
s
i
s
a
n
o
p
e
n
a
c
c
e
s
s
a
r
ti
c
l
e
u
n
d
e
r
th
e
C
C
B
Y
-
SA
l
i
c
e
n
s
e
.
C
or
r
e
s
pon
di
n
g A
u
t
h
or
:
S.
B
huv
a
ne
s
w
a
r
i
D
e
pa
r
t
m
e
nt
of
C
o
m
put
e
r
S
c
i
e
nc
e
,
M
a
dur
a
i
K
a
m
a
r
a
j
U
ni
v
e
r
s
i
t
y
M
a
dur
a
i
, I
ndi
a
E
m
a
i
l
:
bhu
v
a
e
s
w
a
r
i
.s
@
c
pa
c
ol
l
e
g
e
.or
g
1.
I
N
T
R
O
D
U
C
T
I
O
N
G
a
s
t
r
oi
nt
e
s
t
i
na
l
(
G
I
)
di
s
e
a
s
e
s
a
r
e
a
m
on
g
t
he
m
os
t
pr
e
v
a
l
e
nt
he
a
l
t
h
di
s
or
de
r
s
w
or
l
d
w
i
de
a
n
d
c
ont
i
nue
t
o
po
s
e
s
i
g
ni
f
i
c
a
nt
c
ha
l
l
e
ng
e
s
t
o
he
a
l
t
hc
a
r
e
s
y
s
t
e
m
s
.
A
m
on
g
t
he
s
e
di
s
or
de
r
s
,
ul
c
e
r
s
a
r
e
c
o
m
m
on
l
e
s
i
ons
t
ha
t
de
v
e
l
op
i
n
t
he
l
i
ni
ng
of
t
he
s
t
o
m
a
c
h,
s
m
a
l
l
i
nt
e
s
t
i
ne
,
or
ot
he
r
r
e
g
i
ons
of
t
h
e
GI
t
r
a
c
t
.
I
f
l
e
f
t
unt
r
e
a
t
e
d,
ul
c
e
r
s
m
a
y
pr
o
g
r
e
s
s
t
o
s
e
v
e
r
e
c
o
m
pl
i
c
a
t
i
ons
,
i
nc
l
udi
ng
GI
bl
e
e
di
ng
,
C
r
o
hn
’
s
di
s
e
a
s
e
,
a
nd
ul
c
e
r
a
t
i
v
e
c
ol
i
t
i
s
.
C
on
s
e
que
nt
l
y
,
e
a
r
l
y
a
nd
a
c
c
ur
a
t
e
ul
c
e
r
de
t
e
c
t
i
on
i
s
e
s
s
e
nt
i
a
l
f
or
t
i
m
e
l
y
c
l
i
ni
c
a
l
i
nt
e
r
v
e
nt
i
on
a
nd e
f
f
e
c
t
i
v
e
di
s
e
a
s
e
m
a
na
ge
m
e
nt
.
R
e
c
e
nt
a
d
v
a
nc
e
s
i
n
m
e
di
c
a
l
i
m
a
g
i
n
g
t
e
c
hnol
og
i
e
s
ha
v
e
s
ubs
t
a
nt
i
a
l
l
y
i
m
pr
o
v
e
d
t
he
di
a
g
no
s
i
s
of
GI
di
s
or
de
r
s
.
A
m
on
g
t
he
a
v
a
i
l
a
bl
e
di
a
g
nos
t
i
c
m
oda
l
i
t
i
e
s
,
w
i
r
e
l
e
s
s
c
a
ps
ul
e
e
ndos
c
opy
(
W
C
E
)
ha
s
e
m
e
r
ge
d
a
s
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
,
V
ol
.
4
3
, N
o.
2
,
A
ug
us
t
20
2
6
:
595
-
606
596
v
a
l
ua
bl
e
a
nd
m
i
ni
m
a
l
l
y
i
n
v
a
s
i
v
e
t
e
c
hni
que
f
or
v
i
s
ua
l
i
z
i
ng
t
he
e
nt
i
r
e
GI
t
r
a
c
t
,
pa
r
t
i
c
ul
a
r
l
y
r
e
g
i
ons
t
ha
t
a
r
e
di
f
f
i
c
ul
t
t
o
a
c
c
e
s
s
us
i
ng
c
on
v
e
nt
i
ona
l
e
ndos
c
opy
.
W
C
E
s
y
s
t
e
m
s
c
a
pt
ur
e
t
hous
a
nds
of
hi
g
h
-
r
e
s
ol
ut
i
on
i
m
a
g
e
s
dur
i
ng
a
s
i
ng
l
e
e
xa
m
i
na
t
i
on,
pr
o
v
i
di
ng
c
o
m
pr
e
he
ns
i
v
e
i
n
f
or
m
a
t
i
on
f
or
de
t
e
c
t
i
ng
ul
c
e
r
s
a
nd
ot
he
r
GI
a
bnor
m
a
l
i
t
i
e
s
.
H
o
w
e
v
e
r
,
t
he
l
a
r
ge
v
ol
u
m
e
of
ge
ne
r
a
t
e
d
i
m
a
g
e
s
m
a
k
e
s
m
a
nua
l
e
xa
m
i
na
t
i
on
l
a
bor
-
i
nt
e
ns
i
v
e
,
t
i
m
e
-
c
ons
u
m
i
n
g
, a
nd s
us
c
e
pt
i
bl
e
t
o obs
e
r
v
e
r
v
a
r
i
a
bi
l
i
t
y
.
A
s
a
r
e
s
ul
t
, a
ut
om
a
t
e
d ul
c
e
r
de
t
e
c
t
i
on s
y
s
t
e
m
s
ba
s
e
d
on m
a
c
hi
ne
l
e
a
r
ni
n
g
(
M
L
)
a
nd de
e
p l
e
a
r
ni
ng
(
D
L
)
ha
v
e
r
e
c
e
i
v
e
d c
ons
i
de
r
a
bl
e
a
t
t
e
nt
i
on f
r
om
r
e
s
e
a
r
c
he
r
s
.
S
e
v
e
r
a
l
s
t
udi
e
s
ha
v
e
e
xpl
or
e
d
M
L
-
a
nd
D
L
-
ba
s
e
d
a
ppr
oa
c
he
s
f
or
ul
c
e
r
de
t
e
c
t
i
on
a
nd
GI
di
s
e
a
s
e
di
a
g
nos
i
s
. D
e
e
p
c
onv
ol
ut
i
o
na
l
ne
ur
a
l
ne
t
w
or
k
s
(
C
N
N
s
)
w
e
r
e
e
m
pl
oy
e
d i
n [
1]
t
o e
nha
nc
e
t
he
v
i
s
i
bi
l
i
t
y
of
W
C
E
i
m
a
g
e
s
a
nd
i
m
pr
o
v
e
ul
c
e
r
de
t
e
c
t
i
o
n
pe
r
f
or
m
a
nc
e
.
A
l
t
houg
h
i
m
pr
o
v
e
d
c
ont
r
a
s
t
a
nd
e
dg
e
r
e
pr
e
s
e
nt
a
t
i
on
w
e
r
e
a
c
hi
e
v
e
d,
i
m
a
ge
noi
s
e
a
m
pl
i
f
i
c
a
t
i
on
r
e
m
a
i
ne
d
a
c
ha
l
l
e
ng
e
.
A
n
i
nt
e
g
r
a
t
e
d
v
a
r
i
a
t
i
ona
l
a
u
t
oe
nc
ode
r
-
g
e
ne
r
a
t
i
v
e
a
d
v
e
r
s
a
r
i
a
l
ne
t
w
o
r
k
(
V
A
E
-
G
A
N
)
f
r
a
m
e
w
or
k
w
a
s
pr
opo
s
e
d
i
n
[
2]
f
or
ul
c
e
r
de
t
e
c
t
i
on;
how
e
v
e
r
,
a
c
c
ur
a
t
e
s
e
gm
e
nt
a
t
i
on
of
r
e
g
i
ons
of
i
nt
e
r
e
s
t
(
R
O
I
s
)
r
e
m
a
i
ne
d
di
f
f
i
c
ul
t
.
C
N
N
-
ba
s
e
d
m
ode
l
s
w
e
r
e
a
l
s
o
i
n
t
r
oduc
e
d
f
or
ul
c
e
r
a
nd
e
r
os
i
o
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
n
c
a
p
s
u
l
e
e
ndos
c
opy
i
m
a
ge
s
[
3]
,
w
hi
l
e
DL
a
ppr
oa
c
he
s
f
or
e
ndos
c
op
i
c
i
m
a
ge
c
a
t
e
g
or
i
z
a
t
i
on
w
e
r
e
i
n
v
e
s
t
i
g
a
t
e
d
i
n
[
4]
.
H
y
br
i
d
a
r
c
hi
t
e
c
t
ur
e
s
s
uc
h
a
s
C
N
N
-
F
F
N
N
a
nd
C
N
N
–
X
G
B
oos
t
w
e
r
e
de
v
e
l
ope
d
i
n
[
5]
f
or
GI
di
s
e
a
s
e
di
a
g
nos
i
s
,
b
ut
t
he
y
e
xhi
bi
t
e
d
l
i
m
i
t
a
t
i
on
s
i
n
a
c
hi
e
v
i
ng
hi
g
h
a
c
c
ur
a
c
y
w
i
t
h
l
ow
c
om
put
a
t
i
ona
l
c
o
s
t
.
S
i
m
i
l
a
r
l
y
,
t
hr
e
e
-
di
m
e
ns
i
ona
l
C
N
N
s
[
6]
,
ML
a
l
g
or
i
t
hm
s
f
or
c
a
ps
ul
e
e
ndos
c
opy
i
m
a
ge
c
a
t
e
g
or
i
z
a
t
i
on
[
7]
,
a
nd
f
ul
l
y
a
ut
om
a
t
e
d
DL
f
r
a
m
e
w
or
ks
[
8]
de
m
ons
t
r
a
t
e
d
pr
om
i
s
i
ng
pe
r
f
or
m
a
nc
e
but
s
uf
f
e
r
e
d
f
r
om
i
s
s
ue
s
r
e
l
a
t
e
d t
o c
om
put
a
t
i
o
na
l
c
om
pl
e
xi
t
y
, s
e
g
m
e
nt
a
t
i
on a
c
c
ur
a
c
y
, or
f
e
a
t
ur
e
ut
i
l
i
z
a
t
i
o
n.
A
ddi
t
i
ona
l
s
t
udi
e
s
ha
v
e
i
n
v
e
s
t
i
g
a
t
e
d
a
ut
om
a
t
e
d
G
I
di
s
e
a
s
e
de
t
e
c
t
i
on us
i
ng
m
ul
t
i
-
m
e
t
hod
s
y
s
t
e
m
s
[
9]
,
m
ul
t
i
-
br
a
nc
h C
N
N
a
r
c
hi
t
e
c
t
ur
e
s
[
10]
, a
n
d C
N
N
-
ba
s
e
d di
s
e
a
s
e
c
l
a
s
s
i
f
i
c
a
t
i
on m
ode
l
s
[
11]
. D
L
f
r
a
m
e
w
or
ks
s
uc
h
a
s
R
e
s
N
e
t
50
[
12]
,
a
r
t
i
f
i
c
i
a
l
i
nt
e
l
l
i
g
e
nc
e
-
ba
s
e
d
pr
e
di
c
t
i
o
n
s
y
s
t
e
m
s
[
13]
,
a
n
d
c
l
a
s
s
-
ba
l
a
nc
e
d
hi
g
h
-
r
e
s
ol
u
t
i
on
ne
t
w
or
ks
[
14]
ha
v
e
a
l
s
o
be
e
n
e
xpl
or
e
d
f
or
ul
c
e
r
a
t
i
v
e
c
ol
i
t
i
s
a
s
s
e
s
s
m
e
nt
a
nd
r
e
l
a
t
e
d
G
I
di
s
or
de
r
s
. F
ur
t
he
r
m
or
e
,
m
ul
t
i
c
e
nt
e
r
de
e
p
l
e
a
r
ni
ng
m
ode
l
s
f
or
e
ndos
c
op
i
c
s
e
v
e
r
i
t
y
g
r
a
di
ng
[
15]
,
a
ut
om
a
t
e
d
di
s
e
a
s
e
a
c
t
i
v
i
t
y
a
s
s
e
s
s
m
e
nt
[
16]
,
hy
br
i
d
f
e
a
t
ur
e
f
us
i
on
f
r
a
m
e
w
or
ks
[
17]
,
M
a
y
o
e
nd
os
c
op
i
c
s
c
or
e
pr
e
di
c
t
i
on
m
ode
l
s
[
18]
,
[
19]
,
de
e
p
ne
ur
a
l
ne
t
w
or
k
-
ba
s
e
d
e
ndo
s
c
opi
c
e
v
a
l
ua
t
i
on
[
20]
,
i
n
t
e
r
pr
e
t
a
bl
e
de
e
p
l
e
a
r
n
i
ng
a
ppr
oa
c
he
s
f
or
i
nf
l
a
m
m
a
t
or
y
bow
e
l
di
s
e
a
s
e
c
l
a
s
s
i
f
i
c
a
t
i
on
[
21]
,
c
om
put
e
r
v
i
s
i
on
s
y
s
t
e
m
s
f
or
e
ndos
c
opi
c
di
s
e
a
s
e
qua
nt
i
f
i
c
a
t
i
on
[
22]
,
ne
ur
a
l
ne
t
w
or
k
-
ba
s
e
d
c
e
nt
r
a
l
r
e
a
di
ng
s
y
s
t
e
m
s
[
23]
,
a
nd
s
e
v
e
r
a
l
de
e
p
C
N
N
a
nd
pa
t
h
ol
og
y
-
s
e
ns
i
t
i
v
e
a
r
c
hi
t
e
c
t
ur
e
s
f
or
g
a
s
t
r
oi
nt
e
s
t
i
na
l
a
bn
or
m
a
l
i
t
y
de
t
e
c
t
i
on
[
24]
–
[
3
0]
ha
v
e
be
e
n
pr
opos
e
d
.
D
e
s
pi
t
e
t
he
i
r
e
nc
our
a
g
i
ng
r
e
s
ul
t
s
,
m
a
n
y
of
t
he
s
e
a
p
pr
oa
c
he
s
r
e
qu
i
r
e
e
xt
e
ns
i
v
e
c
o
m
put
a
t
i
ona
l
r
e
s
our
c
e
s
,
r
e
l
y
he
a
v
i
l
y
on
l
a
r
g
e
a
nnot
a
t
e
d
da
t
a
s
e
t
s
,
or
e
xhi
bi
t
l
i
m
i
t
a
t
i
on
s
i
n i
m
a
g
e
e
nha
nc
e
m
e
nt
, R
O
I
e
xt
r
a
c
t
i
on
, a
nd e
f
f
i
c
i
e
nt
f
e
a
t
ur
e
r
e
pr
e
s
e
n
t
a
t
i
o
n.
A
c
a
r
e
f
ul
a
n
a
l
y
s
i
s
of
t
he
e
xi
s
t
i
ng
l
i
t
e
r
a
t
ur
e
r
e
v
e
a
l
s
s
e
v
e
r
a
l
i
m
por
t
a
nt
r
e
s
e
a
r
c
h
c
ha
l
l
e
ng
e
s
.
F
i
r
s
t
,
W
C
E
i
m
a
g
e
s
a
r
e
of
t
e
n
a
f
f
e
c
t
e
d
b
y
noi
s
e
a
nd
i
l
l
u
m
i
na
t
i
on
v
a
r
i
a
t
i
ons
t
ha
t
de
gr
a
de
i
m
a
g
e
qu
a
l
i
t
y
a
n
d
r
e
duc
e
di
a
g
nos
t
i
c
r
e
l
i
a
bi
l
i
t
y
.
S
e
c
ond,
m
a
n
y
e
xi
s
t
i
ng
a
ppr
oa
c
he
s
f
oc
us
pr
i
m
a
r
i
l
y
on
c
l
a
s
s
i
f
i
c
a
t
i
on
pe
r
f
or
m
a
nc
e
w
hi
l
e
o
v
e
r
l
ooki
ng
r
obus
t
pr
e
pr
oc
e
s
s
i
ng
m
e
c
ha
ni
s
m
s
t
ha
t
pr
e
s
e
r
v
e
di
a
g
nos
t
i
c
a
l
l
y
s
i
g
ni
f
i
c
a
nt
i
m
a
g
e
s
t
r
uc
t
ur
e
s
.
T
hi
r
d,
i
na
c
c
ur
a
t
e
s
e
gm
e
nt
a
t
i
on
of
ul
c
e
r
-
r
e
l
a
t
e
d
r
e
g
i
ons
m
a
y
i
nt
r
oduc
e
i
r
r
e
l
e
v
a
n
t
i
nf
or
m
a
t
i
on
i
nt
o
t
he
a
na
l
y
s
i
s
pr
oc
e
s
s
,
t
he
r
e
b
y
i
nc
r
e
a
s
i
n
g
c
o
m
put
a
t
i
ona
l
c
o
m
pl
e
xi
t
y
a
nd
r
e
duc
i
ng
de
t
e
c
t
i
on
pe
r
f
or
m
a
nc
e
.
F
i
na
l
l
y
,
DL
-
b
a
s
e
d
m
e
t
hods
of
t
e
n
r
e
qui
r
e
s
ubs
t
a
nt
i
a
l
c
om
put
a
t
i
ona
l
r
e
s
our
c
e
s
a
nd
l
a
r
g
e
t
r
a
i
ni
n
g
da
t
a
s
e
t
s
, l
i
m
i
t
i
ng
t
he
i
r
a
ppl
i
c
a
bi
l
i
t
y
i
n pr
a
c
t
i
c
a
l
c
l
i
ni
c
a
l
e
n
v
i
r
on
m
e
nt
s
.
M
ot
i
v
a
t
e
d
b
y
t
he
s
e
l
i
m
i
t
a
t
i
ons
,
t
hi
s
pa
pe
r
pr
opos
e
s
a
C
a
m
a
r
g
o
’
s
I
nde
xi
v
e
K
u
w
a
ha
r
a
f
i
l
t
e
r
i
ng
-
ba
s
e
d
a
f
f
i
ne
-
i
n
v
a
r
i
a
nt
s
l
i
c
e
d
r
e
g
r
e
s
s
i
on
(
C
I
K
F
-
A
I
S
R
)
f
r
a
m
e
w
or
k
f
or
ul
c
e
r
de
t
e
c
t
i
on
us
i
ng
W
C
E
i
m
a
g
e
s
.
T
h
e
pr
opos
e
d
f
r
a
m
e
w
o
r
k
i
nt
e
g
r
a
t
e
s
a
d
a
pt
i
v
e
i
m
a
g
e
pr
e
pr
o
c
e
s
s
i
ng
,
e
f
f
i
c
i
e
nt
R
O
I
e
xt
r
a
c
t
i
on,
a
nd
di
s
c
r
i
m
i
na
t
i
v
e
f
e
a
t
ur
e
a
na
l
y
s
i
s
w
i
t
hi
n
a
uni
f
i
e
d
de
t
e
c
t
i
on
pi
pe
l
i
ne
.
I
ni
t
i
a
l
l
y
,
a
da
pt
i
v
e
C
I
K
F
i
s
e
m
pl
o
y
e
d
t
o
s
uppr
e
s
s
n
oi
s
e
w
hi
l
e
pr
e
s
e
r
v
i
n
g
e
d
g
e
i
nf
or
m
a
t
i
on
a
nd
i
m
pr
o
v
i
ng
i
m
a
g
e
qu
a
l
i
t
y
.
S
ubs
e
que
nt
l
y
,
V
on
N
e
u
m
a
nn
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on
c
o
m
bi
ne
d
w
i
t
h
t
he
C
a
nbe
r
r
a
di
s
t
a
nc
e
m
e
a
s
ur
e
i
s
ut
i
l
i
z
e
d
t
o
a
c
c
ur
a
t
e
l
y
i
de
nt
i
f
y
a
nd
e
xt
r
a
c
t
ul
c
e
r
-
r
e
l
a
t
e
d
R
O
I
s
.
F
i
n
a
l
l
y
,
a
f
f
i
ne
-
i
nv
a
r
i
a
nt
s
a
l
i
e
nc
y
s
l
i
c
e
d
r
e
g
r
e
s
s
i
on
i
s
a
ppl
i
e
d
t
o
e
x
t
r
a
c
t
s
i
g
ni
f
i
c
a
nt
s
ha
pe
,
c
ol
or
,
a
nd
t
e
xt
ur
e
f
e
a
t
ur
e
s
t
ha
t
f
a
c
i
l
i
t
a
t
e
a
c
c
ur
a
t
e
ul
c
e
r
de
t
e
c
t
i
on.
T
hr
ou
g
h
t
he
i
nt
e
g
r
a
t
i
on
of
t
he
s
e
c
o
m
pone
nt
s
,
t
he
pr
opos
e
d
C
I
K
F
-
A
I
S
R
f
r
a
m
e
w
or
k
a
i
m
s
t
o
i
m
pr
o
v
e
p
e
a
k
s
i
g
na
l
-
to
-
noi
s
e
r
a
t
i
o
(
P
S
N
R
)
,
e
nha
nc
e
ul
c
e
r
d
e
t
e
c
t
i
on
a
c
c
ur
a
c
y
a
nd
pr
e
c
i
s
i
on,
a
nd
r
e
duc
e
c
o
m
put
a
t
i
ona
l
t
i
m
e
c
o
m
p
a
r
e
d
w
i
t
h
e
xi
s
t
i
ng
a
ppr
oa
c
he
s
.
E
xpe
r
i
m
e
nt
a
l
e
v
a
l
ua
t
i
ons
c
onduc
t
e
d
on
t
he
H
y
pe
r
-
K
v
a
s
i
r
da
t
a
s
e
t
d
e
m
ons
t
r
a
t
e
t
he
e
f
f
e
c
t
i
v
e
n
e
s
s
of
t
he
pr
opos
e
d
m
e
t
hod f
or
c
o
m
put
e
r
-
a
i
de
d
GI
di
s
e
a
s
e
di
a
g
nos
i
s
.
2.
P
R
O
P
O
S
E
D
M
E
T
H
O
D
U
l
c
e
r
di
s
e
a
s
e
s
a
r
e
a
m
a
j
or
he
a
l
t
h
c
onc
e
r
n,
a
f
f
e
c
t
i
n
g
m
a
n
y
pe
opl
e
’
s
w
or
l
d
w
i
de
.
T
he
s
e
a
r
e
c
ha
r
a
c
t
e
r
i
z
e
d
b
y
l
e
s
i
ons
t
ha
t
de
v
e
l
op
on
t
he
i
ns
i
de
l
a
y
e
r
o
f
s
t
o
m
a
c
h,
s
m
a
l
l
i
nt
e
s
t
i
ne
,
or
ot
he
r
a
r
e
a
s
of
t
he
GI
a
r
e
a
.
A
c
o
m
m
on
s
ym
pt
o
m
of
ul
c
e
r
di
s
e
a
s
e
s
i
nc
l
ude
s
a
n
a
bdo
m
i
na
l
pa
i
n,
i
ndi
g
e
s
t
i
on,
na
us
e
a
,
a
nd
v
o
m
i
t
i
ng.
D
e
t
e
c
t
i
ng
ul
c
e
r
di
s
e
a
s
e
s
a
t
a
n
e
a
r
l
y
s
t
a
ge
i
s
c
r
uc
i
a
l
f
or
e
f
f
e
c
t
i
v
e
m
a
n
a
ge
m
e
nt
a
nd
t
r
e
a
t
m
e
nt
.
U
l
c
e
r
de
t
e
c
t
i
on
i
m
pr
o
v
e
d
us
i
ng
W
C
E
i
m
a
g
e
s
of
G
I
t
r
a
c
t
.
C
I
K
F
-
A
I
S
R
de
v
e
l
ope
d.
I
t
c
a
pt
ur
e
s
G
I
t
r
a
c
t
i
m
a
g
e
s
t
o
v
i
s
ua
l
i
z
e
a
n
a
ppa
r
e
nt
v
i
e
w
o
f
i
t
s
i
nt
e
r
na
l
pa
r
t
s
of
t
he
hu
m
a
n body t
ha
n
t
he
c
on
v
e
nt
i
ona
l
e
ndos
c
opy
t
e
c
h
ni
que
s
. W
C
E
a
l
s
o
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p S
c
i
I
S
S
N
:
2502
-
4752
A
f
f
i
ne
-
i
nv
ar
i
an
t
f
e
at
ur
e
l
e
ar
n
i
ng f
o
r
ac
c
ur
at
e
ul
c
e
r
d
e
t
e
c
t
i
on i
n w
i
r
e
l
e
s
s
c
aps
u
l
e
…
(
S. B
hu
v
ane
s
w
ar
i
)
597
of
f
e
r
s
a
l
e
s
s
pe
r
s
i
s
t
e
nt
a
nd
m
or
e
c
o
m
f
or
t
a
bl
e
a
l
t
e
r
na
t
i
v
e
f
or
pa
t
i
e
nt
s
t
ha
n
t
he
t
r
a
di
t
i
ona
l
e
ndos
c
opy
.
T
he
s
m
a
l
l
c
a
ps
ul
e
,
w
hi
c
h
c
ont
a
i
ns
m
i
ni
a
t
ur
e
c
a
m
e
r
a
,
ha
s
i
ng
e
s
t
e
d
v
i
a
pa
t
i
e
nt
a
s
w
e
l
l
a
s
t
r
a
ns
m
i
t
s
i
m
a
g
e
s
be
c
a
us
e
i
t
pa
s
s
e
s
dur
i
ng
di
g
e
s
t
i
v
e
s
y
s
t
e
m
.
C
on
v
e
nt
i
ona
l
l
y
,
ul
c
e
r
de
t
e
c
t
i
on
us
i
ng
m
a
c
hi
ne
a
s
w
e
l
l
a
s
D
L
a
l
g
or
i
t
h
m
s
ha
s
be
e
n
de
v
e
l
ope
d
i
n
e
a
r
l
y
de
t
e
c
t
i
on
a
nd
t
r
e
a
t
m
e
nt
.
H
o
w
e
v
e
r
,
a
c
hi
e
v
i
ng
a
c
c
ur
a
t
e
ul
c
e
r
de
t
e
c
t
i
on
w
i
t
h
l
e
s
s
e
r
t
i
m
e
c
o
m
pl
e
xi
t
y
f
a
c
e
s
m
a
j
or
c
ha
l
l
e
nge
s
.
C
I
K
F
-
A
I
S
R
m
e
t
hod
f
or
i
m
pr
o
v
i
ng
t
he
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
w
i
t
h
m
i
ni
m
a
l
t
i
m
e
a
nd hi
g
he
r
pe
a
k t
o s
i
g
na
l
t
o noi
s
e
r
a
t
i
o
.
A
r
c
hi
t
e
c
t
ur
e
di
a
g
r
a
m
of
pr
opos
e
d
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
f
or
a
c
c
ur
a
t
e
de
t
e
c
t
i
on
of
u
l
c
e
r
de
t
e
c
t
i
on
w
i
t
h W
C
E
i
m
a
g
e
s
d
e
m
ons
t
r
a
t
e
d i
n F
i
g
ur
e
1.
T
he
pr
opos
e
d ul
c
e
r
de
t
e
c
t
i
on
m
e
t
hod i
n
v
ol
v
e
s
f
our
f
unda
m
e
nt
a
l
s
t
e
ps
na
m
e
l
y
i
m
a
ge
a
c
qui
s
i
t
i
on,
pr
e
pr
oc
e
s
s
i
ng
,
s
e
gm
e
nt
a
t
i
on
a
nd
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on.
T
he
s
e
f
unda
m
e
nt
a
l
pr
oc
e
s
s
e
s
of
t
he
pr
opos
e
d C
I
K
F
-
A
I
S
R
t
e
c
hni
que
a
r
e
e
xpl
a
i
ne
d br
i
e
f
l
y
i
n t
he
f
ol
l
ow
i
n
g
s
ubs
e
c
t
i
ons
.
F
i
g
ur
e
1
.
B
l
oc
k di
a
g
r
a
m
o
f
pr
opos
e
d C
I
K
F
-
A
I
S
R
2.1.
i
m
age
ac
q
u
i
s
i
t
i
o
n
I
t
ha
s
pr
oc
e
dur
e
of
c
ol
l
e
c
t
i
n
g
t
he
W
C
E
i
m
a
g
e
a
s
of
H
y
pe
r
-
K
v
a
s
i
r
da
t
a
s
e
t
.
I
t
ha
s
w
i
de
l
y
unc
onf
i
ne
d
G
I
t
r
a
c
t
i
m
a
g
e
da
t
a
s
e
t
f
or
ul
c
e
r
de
t
e
c
t
i
on.
I
t
ha
s
s
e
pa
r
a
t
e
dt
o
f
our
s
e
pa
r
a
t
e
e
l
e
m
e
nt
s
s
uc
h
a
s
L
a
b
e
l
e
d
i
m
a
g
e
d
a
t
a
,
unl
a
be
l
e
d
i
m
a
g
e
d
a
t
a
,
s
e
gm
e
nt
e
d
i
m
a
g
e
da
t
a
,
a
s
w
e
l
l
a
s
a
nnot
a
t
e
d
v
i
de
o
da
t
a
.
A
m
ong
s
t
t
he
s
e
pa
r
t
s
,
l
a
be
l
e
d
i
m
a
g
e
s
e
m
pl
o
y
e
d
t
o
e
s
t
i
m
a
t
e
e
xp
e
r
i
m
e
nt
a
l
.
F
r
o
m
t
he
l
a
be
l
e
d
i
m
a
g
e
s
,
ul
c
e
r
W
C
E
i
m
a
ge
s
g
a
t
he
r
e
d t
o f
i
nd di
s
e
a
s
e
.
2
.2
.
p
r
e
p
r
oc
e
s
s
i
n
g
P
r
e
pr
oc
e
s
s
i
ng
i
s
a
f
unda
m
e
nt
a
l
s
t
e
p
t
o
a
c
hi
e
v
e
hi
g
he
r
W
C
E
i
m
a
g
e
qua
l
i
t
y
f
o
r
f
ur
t
he
r
a
na
l
y
s
i
s
.
P
r
opos
e
d
t
e
c
hni
que
ut
i
l
i
z
e
s
a
da
pt
i
v
e
C
I
K
F
f
or
i
m
a
g
e
de
noi
s
i
ng
t
o
i
m
pr
o
v
e
i
m
a
g
e
q
ua
l
i
t
y
.
C
I
K
F
i
s
a
non
-
l
i
ne
a
r
s
m
oot
hi
ng
f
i
l
t
e
r
us
e
d
f
or
a
da
pt
i
v
e
noi
s
e
r
e
duc
t
i
on
i
n
W
C
E
i
m
a
g
e
s
.
P
r
opos
e
d
f
i
l
t
e
r
i
s
a
bl
e
t
o
a
ppl
y
s
m
oot
hi
ng
on W
C
E
i
m
a
g
e
s
w
hi
l
e
pr
e
s
e
r
v
i
n
g
t
he
e
d
g
e
s
a
l
s
o.
F
i
g
ur
e
2 i
l
l
us
t
r
a
t
e
s
bl
oc
k di
a
g
r
a
m
of
a
da
pt
i
v
e
C
I
K
F
f
or
i
m
a
g
e
noi
s
e
a
r
t
i
f
a
c
t
s
r
e
m
o
v
a
l
i
n
g
i
v
e
n
W
C
E
i
m
a
g
e
.
L
e
t
us
c
ons
i
de
r
num
be
r
of
i
nput
s
W
C
E
i
m
a
g
e
de
not
e
d
a
s
1
,
2
,
3
,
…
,
t
a
ke
n
f
r
om
da
t
a
s
e
t
.
F
or
e
a
c
h
i
nput
i
m
a
g
e
s
,
pi
xe
l
s
a
r
e
e
xt
r
a
c
t
e
d
a
nd
i
t
r
e
pr
e
s
e
nt
e
d
by
1
,
2
,
3
,
…
,
.
P
i
xe
l
s
a
r
e
or
g
a
ni
z
e
d
b
y
f
i
l
t
e
r
i
ng
w
i
ndow
s
i
z
e
.
I
t
m
e
a
s
ur
e
d a
s
,
=
2
∗
+
1
(
1)
w
he
r
e
,
f
i
l
t
e
r
i
n
g
w
i
ndow
s
i
z
e
d
e
not
e
d
a
s
,
de
not
e
s
a
r
a
di
us
of
f
i
l
t
e
r
.
T
he
f
our
s
qua
r
e
qu
a
dr
a
nt
s
w
i
t
h
s
i
z
e
(
+
1
)
∗
(
+
1
)
i
s
u
s
e
d
t
o
a
r
r
a
ng
e
t
he
pi
xe
l
s
i
n
t
he
f
or
m
of
r
o
w
‘
’
a
nd
c
ol
um
n
‘
’
w
he
r
e
,
(
1
≤
≤
ℎ
)
a
nd,
(
1
≤
≤
)
.
F
i
r
s
t
, num
be
r
s
of
pi
xe
l
s
a
r
e
di
v
i
de
d i
nt
o f
our
s
qua
r
e
qua
dr
a
nt
s
a
s
g
i
v
e
n be
l
ow
,
=
[
(
−
,
+
)
∗
(
−
,
+
)
]
(
2)
w
he
r
e
,
de
not
e
s
a
s
qua
r
e
qua
dr
a
nt
,
i
nput
pi
xe
l
s
of
i
m
a
g
e
s
‘
’
pa
r
t
i
t
i
one
d
f
our
s
q
ua
r
e
qua
dr
a
nt
s
s
uc
h
a
s
−
,
+
,
−
,
a
nd
+
r
e
s
pe
c
t
i
v
e
l
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
,
V
ol
.
4
3
, N
o.
2
,
A
ug
us
t
20
2
6
:
595
-
606
598
T
he
s
e
f
our
-
s
qua
r
e
qua
dr
a
nt
s
a
r
e
e
xpr
e
s
s
e
d a
s
f
ol
l
ow
s
,
1
=
(
−
,
)
∗
(
−
,
)
(
3)
2
=
(
−
,
)
∗
(
,
+
)
(
4)
3
=
(
,
+
)
∗
(
−
,
)
(
5)
4
=
(
,
+
)
∗
(
,
+
)
(
6)
F
i
g
ur
e
2
.
F
l
ow
pr
oc
e
s
s
of
a
da
pt
i
v
e
C
a
m
a
r
g
o
’
s
i
nde
xi
v
e
K
u
w
a
h
a
r
a
f
i
l
t
e
r
i
n
g
t
e
c
hni
que
T
he
l
a
y
out
of
a
5
∗
5
K
u
w
a
ha
r
a
ke
r
n
e
l
w
i
t
h f
our
s
qua
r
e
qua
dr
a
nt
s
i
s
s
how
n be
l
ow
.
F
i
g
ur
e
3
i
l
l
us
t
r
a
t
e
s
t
he
pi
xe
l
a
r
r
a
n
g
e
m
e
nt
or
l
a
y
out
of
i
n
5
∗
5
K
u
w
a
ha
r
a
ke
r
ne
l
w
i
n
dow
.
A
t
a
s
c
e
ndi
ng
o
r
de
r
,
pi
xe
l
s
pos
i
t
i
one
d.
F
i
l
t
e
r
i
ng
w
i
ndow
i
s
pa
r
t
i
t
i
one
d
i
nt
o
f
our
qua
dr
a
nt
s
1
,
2
,
3
,
a
nd
4
.
A
s
s
how
n i
n
F
i
g
ur
e
3,
i
ndi
c
a
t
e
s
c
e
nt
e
r
pi
xe
l
s
of
ke
r
ne
l
w
i
ndo
w
F
i
g
ur
e
3
.
L
a
y
out
of
a
5
∗
5
K
u
w
a
h
a
r
a
f
i
l
t
e
r
ke
r
ne
l
F
or
e
a
c
h qua
dr
a
nt
, t
he
m
e
a
n (
)
a
nd de
v
i
a
t
i
on (
)
i
s
c
a
l
c
ul
a
t
e
d.
T
he
n
c
o
m
put
e
t
he
m
e
a
n
f
or
e
a
c
h
qua
dr
a
nt
i
s
c
om
put
e
d a
s
f
ol
l
o
w
s
,
(
)
=
1
(
)
∑
∑
=
1
ℎ
=
1
(
7)
w
he
r
e
,
(
)
de
not
e
s
a
m
e
a
n
of
pi
xe
l
s
,
∑
∑
=
1
ℎ
=
1
de
not
e
s
a
s
um
of
a
l
l
t
he
pi
xe
l
v
a
l
ue
i
n
t
he
pa
r
t
i
c
ul
a
r
qua
dr
a
nt
, nu
m
be
r
of
pi
xe
l
s
de
not
e
d
a
s
(
)
a
t
pa
r
t
i
c
ul
a
r
qua
dr
a
nt
.
C
e
nt
e
r
pi
xe
l
s
‘
’
i
s
c
o
m
put
e
d
de
pe
nde
d
on m
e
a
n
v
a
l
ue
f
ol
l
ow
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p S
c
i
I
S
S
N
:
2502
-
4752
A
f
f
i
ne
-
i
nv
ar
i
an
t
f
e
at
ur
e
l
e
ar
n
i
ng f
o
r
ac
c
ur
at
e
ul
c
e
r
d
e
t
e
c
t
i
on i
n w
i
r
e
l
e
s
s
c
aps
u
l
e
…
(
S. B
hu
v
ane
s
w
ar
i
)
599
=
1
4
∑
(
)
4
=
1
(
8)
w
he
r
e
,
(
)
de
not
e
s
a
m
e
a
n
of
a
l
l
f
our
qua
dr
a
nt
s
.
A
f
t
e
r
t
ha
t
,
t
he
de
v
i
a
t
i
on
i
s
c
om
put
e
d
f
or
e
a
c
h
qua
dr
a
nt
ba
s
e
d
on
t
he
a
bov
e
e
s
t
i
m
a
t
e
d
m
e
a
n
v
a
l
ue
b
y
a
ppl
y
i
ng
a
C
a
m
a
r
g
o
’
s
i
nde
x.
T
he
C
a
m
a
r
g
o
’
s
i
nde
x
i
s
a
qua
l
i
t
a
t
i
v
e
m
e
t
hod
t
o
m
e
a
s
ur
e
t
he
de
pe
nd
e
nc
y
be
t
w
e
e
n
pi
xe
l
v
a
l
ue
s
a
nd
t
he
m
e
a
n
of
p
a
r
t
i
c
ul
a
r
qua
dr
a
nt
.
T
he
C
a
m
a
r
g
o
’
s
i
nde
x
f
unc
t
i
on i
s
f
or
m
ul
a
t
e
d a
s
f
ol
l
ow
s
,
(
)
=
1
−
∑
∑
|
−
(
)
|
(
)
=
1
ℎ
=
1
(
9)
w
he
r
e
,
(
)
i
n
di
c
a
t
e
s
a
n
o
ut
p
ut
C
a
m
a
r
g
o
’
s
i
n
de
x
f
u
nc
t
i
on
f
or
pa
r
t
i
c
u
l
a
r
qua
dr
a
nt
,
de
no
t
e
s
a
pi
x
e
l
v
a
l
ue
i
n t
he
pa
r
t
i
c
ul
a
r
q
ua
dr
a
n
t
,
(
)
i
n
di
c
a
t
e
s
m
e
a
n of
pi
xe
l
s
i
n
t
he
pa
r
t
i
c
ul
a
r
qua
dr
a
nt
,
(
)
i
ndi
c
a
t
e
s
a
n
u
m
be
r
o
f
pi
xe
l
s
.
F
r
om
t
he
a
na
l
y
s
i
s
,
t
he
i
nde
x
f
unc
t
i
on
pr
ov
i
de
s
t
he
o
ut
p
ut
r
a
ng
e
s
f
r
om
t
he
0
t
o
1.
A
f
t
e
r
t
ha
t
,
m
i
n
i
m
u
m
de
v
i
a
t
i
on a
m
ong
t
he
f
o
ur
q
ua
dr
a
nt
s
i
s
i
de
nt
i
f
i
e
dt
hr
oug
h
hi
g
he
r
ou
t
p
ut
r
a
ng
e
s
o
f
C
a
m
a
r
g
o
’
s
i
n
de
x f
u
nc
t
i
o
n.
=
{
,
(
)
>
,
(
)
<
(
10)
W
he
r
e
,
de
not
e
s
a
f
i
l
t
e
r
e
d
out
put
,
m
i
n
de
not
e
s
a
m
i
ni
m
u
m
d
e
v
i
a
t
i
on,
m
a
x
de
not
e
s
a
m
a
xi
m
u
m
de
v
i
a
t
i
on
de
not
e
s
a
t
hr
e
s
hol
d,
(
)
i
ndi
c
a
t
e
s
a
out
put
C
a
m
a
r
g
o
’
s
i
nde
x
f
unc
t
i
on.
F
r
o
m
t
h
e
a
na
l
y
s
i
s
,
t
he
pi
xe
l
s
w
i
t
h
m
i
ni
m
u
m
de
v
i
a
t
i
on
f
r
o
m
t
he
m
e
a
n
pi
xe
l
s
a
r
e
c
a
l
l
e
d
nor
m
a
l
pi
xe
l
s
.
O
t
he
r
w
i
s
e
,
t
he
pi
xe
l
s
w
i
t
h
m
a
xi
m
u
m
d
e
v
i
a
t
i
on
f
r
o
m
t
he
m
e
a
n
a
r
e
c
a
l
l
e
d
noi
s
e
pi
xe
l
s
.
T
he
noi
s
e
pi
xe
l
s
a
r
e
t
he
n
r
e
m
o
v
e
d
f
r
o
m
t
he
f
i
l
t
e
r
i
ng
w
i
ndo
w
t
hr
oug
h
r
e
pl
a
c
i
n
g
a
v
e
r
a
ge
of
no
r
m
a
l
pi
xe
l
s
w
i
t
hi
n
r
e
s
pe
c
t
i
v
e
qua
dr
a
n
t
.
T
hi
s
de
noi
s
i
ng
pr
oc
e
s
s
e
f
f
e
c
t
i
v
e
l
y
r
e
du
c
e
s
M
S
E
a
s
w
e
l
l
a
s
e
nha
nc
e
s
P
S
N
R
r
e
s
ul
t
i
ng
i
n e
nha
nc
e
d i
m
a
g
e
qu
a
l
i
t
y
.
A
l
g
or
i
t
h
m
1
de
s
c
r
i
be
s
t
he
v
a
r
i
ous
s
t
e
ps
i
nv
ol
v
e
d
i
n
e
nha
nc
i
n
g
i
m
a
ge
qua
l
i
t
y
b
y
f
i
l
t
e
r
i
ng
out
noi
s
e
pi
xe
l
s
. F
i
na
l
l
y
, t
he
qua
l
i
t
y
-
e
nha
nc
e
d i
m
a
ge
i
s
obt
a
i
ne
d w
i
t
h l
e
s
s
e
r
M
S
E
a
s
w
e
l
l
a
s
hi
g
he
r
P
S
N
R
.
A
l
g
or
i
t
h
m
1
.
A
d
a
pt
i
v
e
C
a
m
a
r
g
o
’
s
i
nde
xi
v
e
K
u
w
a
ha
r
a
f
i
l
t
e
r
i
ng
t
e
c
hni
que
I
n
p
u
t
:
i
m
a
g
e
d
a
t
a
b
a
s
e
,
N
u
m
b
e
r
o
f
i
n
p
u
t
W
C
E
i
m
a
g
e
1
,
2
,
3
,
…
.
O
u
t
p
u
t
:
P
r
e
p
r
o
c
e
s
s
e
d
i
m
a
g
e
s
B
e
g
i
n
S
t
e
p
1
:
C
o
l
l
e
c
t
n
u
m
b
e
r
o
f
i
n
p
u
t
W
C
E
i
m
a
g
e
1
,
2
,
3
,
…
.
f
r
o
m
d
a
t
a
s
t
S
t
e
p
2
:
F
o
r
e
a
c
h
i
n
p
u
t
i
m
a
g
e
S
t
e
p
3
:
E
x
t
r
a
c
t
t
h
e
n
u
m
b
e
r
o
f
p
i
x
e
l
s
1
,
2
,
3
,
…
.
S
t
e
p
4
:
O
r
g
a
n
i
z
e
t
h
e
p
i
x
e
l
s
i
n
f
i
l
t
e
r
i
n
g
w
i
n
d
o
w
i
n
a
s
c
e
n
d
i
n
g
o
r
d
e
r
S
t
e
p
5
:
D
i
v
i
d
e
t
h
e
i
m
a
g
e
p
i
x
e
l
s
i
n
t
o
f
o
u
r
q
u
a
d
r
a
n
t
s
u
s
i
n
g
(
3
)
(
4
)
(
5
)
(
6
)
S
t
e
p
6
:
F
o
r
e
a
c
h
q
u
a
d
r
a
n
t
S
t
e
p
7
:
C
o
m
p
u
t
e
m
e
a
n
u
s
i
n
g
(
7
)
S
t
e
p
8
:
D
e
f
i
n
e
c
e
n
t
e
r
p
i
x
e
l
v
a
l
u
e
‘
’
u
s
i
n
g
(
8
)
S
t
e
p
9
:
C
o
m
p
u
t
e
t
h
e
d
e
v
i
a
t
i
o
n
u
s
i
n
g
C
a
m
a
r
g
o
’
s
i
n
d
e
x
(
9
)
S
t
e
p
1
0
:
i
f
(
(
)
>
)
t
h
e
n
S
t
e
p
1
1
:
R
e
t
u
r
n
s
m
i
n
i
m
u
m
d
e
v
i
a
t
i
o
n
b
e
t
w
e
e
n
t
h
e
p
i
x
e
l
s
a
n
d
m
e
a
n
S
t
e
p
1
2
:
e
l
s
e
S
t
e
p
1
3
:
R
e
t
u
r
n
s
m
a
x
i
m
u
m
d
e
v
i
a
t
i
o
n
b
e
t
w
e
e
n
t
h
e
p
i
x
e
l
s
a
n
d
m
e
a
n
S
t
e
p
1
4
:
e
n
d
i
f
S
t
e
p
1
5
:
S
e
l
e
c
t
m
i
n
i
m
u
m
d
e
v
i
a
t
i
o
n
p
i
x
e
l
s
a
n
d
r
e
m
o
v
e
m
a
x
i
m
u
m
d
e
v
i
a
t
i
o
n
p
i
x
e
l
s
S
t
e
p
1
6
:
R
e
p
l
a
c
e
n
o
i
s
y
p
i
x
e
l
s
w
i
t
h
m
e
a
n
v
a
l
u
e
o
f
n
o
r
m
a
l
p
i
x
e
l
S
t
e
p
1
7
:
E
n
d
f
o
r
S
t
e
p
1
8
:
E
n
d
f
o
r
S
t
e
p
1
9
:
R
e
t
u
r
n
(
q
u
a
l
i
t
y
e
n
h
a
n
c
e
d
i
m
a
g
e
)
End
2
.3
.
V
on
N
e
u
m
an
n
l
oc
al
i
t
y I
m
age
s
e
g
m
e
n
t
at
i
on
A
f
t
e
r
t
he
i
m
a
ge
pr
e
p
r
oc
e
s
s
i
ng
,
t
he
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
pe
r
f
or
m
s
t
he
s
e
gm
e
nt
a
t
i
on
t
o
pa
r
t
i
t
i
on
i
m
a
g
e
t
o
s
e
v
e
r
a
l
s
e
gm
e
nt
s
de
pe
nde
d
on
c
e
r
t
a
i
n
pi
xe
l
i
nt
e
ns
i
t
y
c
ha
r
a
c
t
e
r
i
s
t
i
c
s
.
T
he
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
ut
i
l
i
z
e
s
t
he
V
on
N
e
um
a
nn
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on
m
e
t
hod
i
s
e
m
pl
o
y
e
d
t
o
s
e
gm
e
nt
t
he
i
m
a
ge
i
nt
o
di
f
f
e
r
e
nt
r
e
g
i
ons
a
nd
e
xt
r
a
c
t
t
he
R
O
I
w
i
t
h
C
a
nbe
r
r
a
di
s
t
a
nc
e
m
e
a
s
ur
e
be
t
w
e
e
n
t
he
i
m
a
ge
pi
xe
l
s
.
T
he
V
on
N
e
u
m
a
nn
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on
i
s
a
c
onc
e
pt
us
e
d
i
n
i
m
a
ge
pr
oc
e
s
s
i
ng
t
o
de
f
i
ne
s
e
t
of
s
pa
t
i
a
l
r
e
l
a
t
i
on
s
hi
p
be
t
w
e
e
n
a
s
e
t
of
ne
i
g
hbor
i
n
g
pi
xe
l
s
.
I
t
de
f
i
ne
s
t
he
c
onne
c
t
i
v
i
t
y
of
pi
xe
l
s
i
n
i
m
a
g
e
p
r
oc
e
s
s
i
ng
t
a
s
ks
.
T
hi
s
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on i
s
us
e
d t
o de
f
i
ne
t
he
not
i
on of
4
-
c
onne
c
t
e
d pi
xe
l
s
s
ur
r
oundi
ng
a
c
e
nt
r
a
l
pi
xe
l
.
F
i
g
ur
e
4
de
pi
c
t
s
a
4
-
c
onne
c
t
e
d
ne
i
g
hbor
hood
pi
xe
l
s
m
e
t
hod
or
V
on
N
e
um
a
nn
pi
xe
l
s
c
on
ne
c
t
i
v
i
t
y.
F
i
r
s
t
,
t
he
s
t
a
r
t
i
ng
poi
n
t
i
s
m
a
r
ke
d
w
i
t
h
a
c
e
nt
r
a
l
pi
xe
l
l
oc
a
t
e
d
i
n
t
w
o
-
di
m
e
ns
i
ona
l
s
pa
c
e
(
,
)
.
T
he
ne
i
g
hbor
hood c
onne
c
t
i
v
i
t
y
i
s
m
e
a
s
ur
e
d us
i
ng
C
a
nbe
r
r
a
di
s
t
a
nc
e
m
e
a
s
ur
e
be
t
w
e
e
n t
he
p
i
xe
l
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
,
V
ol
.
4
3
, N
o.
2
,
A
ug
us
t
20
2
6
:
595
-
606
600
F
i
g
ur
e
4. V
on N
e
u
m
a
nn pi
xe
l
s
c
onne
c
t
i
v
i
t
y
=
{
(
,
,
)
}
(
11)
=
{
−
1
,
+
1
,
,
−
1
,
+
1
}
(
12)
(
,
,
)
=
(
,
−
)
|
,
|
+
|
|
(
13)
W
he
r
e
,
‘
’
de
not
e
s
a
c
onne
c
t
i
v
i
t
y
be
t
w
e
e
n
t
he
pi
xe
l
i
nt
e
ns
i
t
y
,
a
r
g
de
not
e
s
a
a
r
g
u
m
e
nt
o
f
m
i
ni
m
u
m
f
un
c
t
i
on,
de
not
e
s
a
C
a
nbe
r
r
a
di
s
t
a
nc
e
be
t
w
e
e
n
t
he
t
w
o
pi
xe
l
s
,
a
nd
,
,
de
not
e
s
a
c
e
nt
e
r
pi
xe
l
s
i
nt
e
ns
i
t
y
,
de
not
e
s
f
our
a
not
he
r
pi
xe
l
’
s
i
nt
e
ns
i
t
y
,
|
,
|
de
not
e
s
a
bs
ol
ut
e
v
a
l
ue
of
c
e
nt
e
r
pi
xe
l
s
i
nt
e
ns
i
t
y
,
|
,
|
de
not
e
s
a
bs
ol
ut
e
v
a
l
ue
of
a
not
he
r
pi
xe
l
’
s
i
nt
e
ns
i
t
y
.
T
he
r
e
f
or
e
,
t
he
m
i
ni
m
u
m
di
s
t
a
nc
e
be
t
w
e
e
n
pi
xe
l
i
nt
e
ns
i
t
i
e
s
i
s
c
ons
i
de
r
e
d
a
dj
a
c
e
nc
y
or
ne
i
g
hbor
hood,
f
a
c
i
l
i
t
a
t
i
ng
t
he
c
onne
c
t
i
on
of
s
i
m
i
l
a
r
r
e
g
i
ons
.
T
hi
s
a
ppr
oa
c
h
i
s
ut
i
l
i
z
e
d
i
n
i
m
a
g
e
s
e
gm
e
nt
a
t
i
on,
w
h
e
r
e
r
e
g
i
ons
w
i
t
h
s
i
m
i
l
a
r
pi
xe
l
i
nt
e
ns
i
t
i
e
s
a
r
e
g
r
oupe
d t
o
g
e
t
he
r
. S
ubs
e
que
nt
l
y
,
R
O
I
s
, s
uc
h a
s
i
nf
e
c
t
e
d r
e
g
i
ons
a
r
e
e
xt
r
a
c
t
e
d f
or
ul
c
e
r
de
t
e
c
t
i
on. T
hi
s
pr
oc
e
s
s
he
l
ps
m
i
ni
m
i
z
e
t
i
m
e
c
o
m
pl
e
xi
t
y
of
ul
c
e
r
de
t
e
c
t
i
on f
or
c
ons
i
de
r
i
ng
R
O
I
s
i
n i
m
a
ge
.
A
l
g
or
i
t
h
m
2
out
l
i
ne
s
t
he
s
t
e
ps
i
nv
ol
v
e
d
i
n
i
m
a
g
e
s
e
gm
e
nt
a
t
i
on
t
o
m
i
ni
m
i
z
e
t
he
t
i
m
e
c
o
m
pl
e
xi
t
y
of
ul
c
e
r
de
t
e
c
t
i
on
.
F
i
na
l
l
y
,
t
he
s
e
gm
e
nt
e
d
i
m
a
g
e
s
a
r
e
obt
a
i
ne
d
t
o
i
m
pr
o
v
e
t
he
pr
oc
e
s
s
of
ul
c
e
r
de
t
e
c
t
i
on
w
i
t
h
m
i
ni
m
a
l
t
i
m
e
.
A
l
g
or
i
t
h
m
2
.
V
on N
e
u
m
a
nn l
oc
a
l
i
t
y
i
m
a
g
e
s
e
gm
e
nt
a
t
i
on
I
n
p
u
t
:
N
u
m
b
e
r
o
f
p
r
e
p
r
o
c
e
s
s
e
d
i
m
a
g
e
s
1
,
2
,
3
,
…
.
,
O
u
t
p
u
t
:
S
e
g
m
e
n
t
e
d
i
m
a
g
e
B
e
g
i
n
S
t
e
p
1
:
C
o
l
l
e
c
t
t
h
e
p
r
e
p
r
o
c
e
s
s
e
d
i
m
a
g
e
s
1
,
2
,
3
,
…
.
,
,
S
t
e
p
2
:
f
o
r
e
v
e
r
y
i
n
p
u
t
i
m
a
g
e
S
t
e
p
3
:
M
e
a
s
u
r
e
t
h
e
d
e
g
r
e
e
o
f
c
o
n
n
e
c
t
i
v
i
t
y
b
e
t
w
e
e
n
t
h
e
p
i
x
e
l
s
u
s
i
n
g
(
1
1
)
S
t
e
p
4
:
i
f
{
(
,
,
)
}
t
h
e
n
S
t
e
p
5
:
F
i
n
d
A
d
j
a
c
e
n
t
p
i
x
e
l
s
S
t
e
p
6
:
e
n
d
i
f
S
t
e
p
7
:
e
n
d
f
o
r
S
t
e
p
8
:
S
e
g
m
e
n
t
t
h
e
R
O
I
f
r
o
m
i
m
a
g
e
End
2.3.1.
A
f
f
i
n
e
i
n
var
i
an
t
s
a
l
i
e
n
c
y
S
l
i
c
e
d
r
e
gr
e
s
s
i
on
m
e
t
h
od
-
b
as
e
d
f
e
at
u
r
e
e
xt
r
ac
t
i
on
I
n
or
de
r
t
o
i
m
pr
o
v
e
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
,
a
f
f
i
ne
i
n
v
a
r
i
a
nt
s
a
l
i
e
nc
y
s
l
i
c
e
d
r
e
gr
e
s
s
i
onpe
r
f
or
m
s
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on.
S
l
i
c
e
d
i
nv
e
r
s
e
r
e
g
r
e
s
s
i
on
i
s
a
ML
t
e
c
hni
que
f
or
di
m
e
ns
i
ona
l
i
t
y
r
e
duc
t
i
on
i
n
m
ul
t
i
v
a
r
i
a
t
e
s
t
a
t
i
s
t
i
c
s
.
T
he
di
m
e
ns
i
ona
l
i
t
y
r
e
duc
t
i
on
i
s
t
he
pr
oc
e
s
s
us
e
d
t
o
r
e
duc
e
t
he
r
e
pr
e
s
e
nt
a
t
i
on
of
a
n
i
m
a
g
e
b
y
e
xt
r
a
c
t
i
ng
t
he
s
i
g
ni
f
i
c
a
nt
f
e
a
t
ur
e
s
l
i
ke
, s
ha
pe
, c
ol
or
,
a
nd t
e
xt
ur
e
s
.
=
(
1
1
,
2
2
,
3
3
,
)
(
14)
w
he
r
e
,
de
not
e
s
a
r
e
g
r
e
s
s
i
on
out
c
om
e
,
1
,
2
,
3
a
r
e
pr
oj
e
c
t
i
on
v
e
c
t
or
s
t
o
e
xt
r
a
c
t
t
he
t
hr
e
e
f
e
a
t
ur
e
s
na
m
e
l
y
s
ha
pe
,
T
de
not
e
s
a
t
r
a
ns
pos
e
,
‘
1
’
i
ndi
c
a
t
e
s
a
s
ha
pe
f
e
a
t
ur
e
,
‘
2
’
i
ndi
c
a
e
s
a
c
ol
or
f
e
a
t
ur
e
,
a
nd
t
e
x
t
ur
e
f
e
a
t
ur
e
‘
3
’
,
t
he
s
ym
bol
r
e
pr
e
s
e
nt
s
t
he
e
r
r
or
t
e
r
m
.
I
t
r
e
pr
e
s
e
nt
s
t
he
di
f
f
e
r
e
nc
e
be
t
w
e
e
n
t
he
obs
e
r
v
e
d
v
a
l
ue
a
nd
t
he
v
a
l
ue
obt
a
i
ne
d by
t
he
r
e
g
r
e
s
s
i
on
m
ode
l
.
T
he
A
f
f
i
ne
i
n
v
a
r
i
a
nt
s
a
l
i
e
nc
y
r
e
f
e
r
s
t
o
a
m
e
a
s
ur
e
of
t
he
i
m
por
t
a
nc
e
of
i
m
a
g
e
r
e
g
i
ons
t
ha
t
r
e
m
a
i
ns
c
ons
i
s
t
e
nt
unde
r
a
f
f
i
ne
t
r
a
ns
f
or
m
a
t
i
ons
.
T
o
de
t
e
c
t
a
f
f
i
ne
-
i
n
v
a
r
i
a
nt
r
e
g
i
ons
,
a
n
e
l
l
i
ps
e
de
t
e
c
t
i
on
a
ppr
oa
c
h
i
s
e
m
pl
oye
d
f
or
s
ha
pe
de
t
e
c
t
i
on.
T
hi
s
a
ppr
oa
c
h
pa
r
a
m
e
t
e
r
i
z
e
s
r
e
g
i
ons
us
i
ng
t
hr
e
e
pa
r
a
m
e
t
e
r
s
na
m
e
l
y
s
c
a
l
e
(
)
,
a
xi
s
r
a
t
i
o (
)
, a
nd or
i
e
nt
a
t
i
on (
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p S
c
i
I
S
S
N
:
2502
-
4752
A
f
f
i
ne
-
i
nv
ar
i
an
t
f
e
at
ur
e
l
e
ar
n
i
ng f
o
r
ac
c
ur
at
e
ul
c
e
r
d
e
t
e
c
t
i
on i
n w
i
r
e
l
e
s
s
c
aps
u
l
e
…
(
S. B
hu
v
ane
s
w
ar
i
)
601
T
he
s
c
a
l
e
pa
r
a
m
e
t
e
r
r
e
pr
e
s
e
nt
s
t
he
s
i
z
e
of
t
he
e
l
l
i
ps
e
or
i
m
a
g
e
r
e
g
i
ons
.
I
t
i
s
de
f
i
ne
d
a
s
t
he
a
v
e
r
a
ge
di
s
t
a
nc
e
be
t
w
e
e
n
t
he
c
e
nt
e
r
a
nd
i
t
s
bou
nda
r
y
.
L
e
t
us
c
ons
i
de
r
t
he
c
e
nt
e
r
c
o
-
or
di
na
t
e
s
of
obj
e
c
t
p
oi
nt
s
(
1
,
1
)
,
a
nd
t
he
bounda
r
y
c
o
-
or
di
na
t
e
s
of
obj
e
c
t
s
(
2
,
2
)
.
T
h
e
di
s
t
a
nc
e
i
s
c
om
put
e
d
f
r
o
m
t
he
c
e
nt
e
r
a
nd
t
he
bounda
r
y
a
s
g
i
v
e
n be
l
ow
,
=
√
(
2
−
1
)
2
+
(
2
−
1
)
2
(
15)
b
a
s
e
d
on
t
he
di
s
t
a
nc
e
m
e
a
s
ur
e
‘
’
,
t
he
c
l
os
e
d
c
ont
our
i
s
de
t
e
r
m
i
ne
d,
w
hi
c
h
he
l
ps
i
n
i
de
nt
i
f
y
i
ng
t
he
s
ha
p
e
w
i
t
hi
n t
he
i
m
a
ge
.
T
he
a
xi
s
r
a
t
i
o
pa
r
a
m
e
t
e
r
r
e
p
r
e
s
e
nt
s
t
he
r
a
t
i
o
of
t
he
l
e
ng
t
hs
of
t
he
m
a
j
or
a
nd
m
i
nor
a
xe
s
.
I
t
i
s
e
xpr
e
s
s
e
d a
s
f
ol
l
ow
s
,
=
(
16)
w
he
r
e
,
de
not
e
s
a
m
a
j
or
a
xi
s
,
i
ndi
c
a
t
e
s
a
m
i
nor
a
xi
s
.
O
r
i
e
nt
a
t
i
on (
)
pa
r
a
m
e
t
e
r
r
e
p
r
e
s
e
nt
s
t
he
r
ot
a
t
i
on a
ng
l
e
of
t
he
e
l
l
i
ps
e
r
e
l
a
t
i
v
e
t
o
t
he
x
-
a
xi
s
.
=
−
1
(
(
2
−
1
)
(
2
−
1
)
)
(
17)
W
he
r
e
,
(
1
,
1
)
de
not
e
s
a
c
e
nt
e
r
c
o
-
or
di
na
t
e
of
poi
nt
s
, a
nd
(
2
,
2
)
de
not
e
s
a
bounda
r
y
c
o
-
or
di
na
t
e
poi
nt
.
Q
ua
nt
i
z
e
d
c
ol
or
hi
s
t
og
r
a
m
s
i
s
e
m
pl
oye
d
f
or
di
s
t
r
i
but
i
on
of
pi
xe
l
i
nt
e
ns
i
t
i
e
s
.
I
n
t
he
f
i
r
s
t
s
t
e
p
i
s
t
o
c
on
v
e
r
t
t
he
i
m
a
ge
f
r
o
m
i
t
s
or
i
g
i
na
l
c
ol
or
s
pa
c
e
R
G
B
(
r
e
d,
G
r
e
e
n,
bl
ue
)
t
o
a
s
ui
t
a
bl
e
c
ol
or
s
pa
c
e
H
S
V
(
H
u
e
(
)
, S
a
t
ur
a
t
i
on
(
)
,
a
nd
V
a
l
ue
(
)
)
. T
he
c
ol
or
c
on
v
e
r
s
i
on pr
oc
e
s
s
i
s
g
i
v
e
n
be
l
ow
,
=
−
1
[
1
2
∗
[
(
−
)
+
(
−
)
]
√
(
−
)
2
+
(
−
)
(
−
)
]
(
18)
=
1
−
3
∗
1
(
+
+
)
[
(
,
,
)
]
(
19)
=
1
3
∗
[
(
+
+
)
]
(
20)
O
nc
e
t
he
i
m
a
ge
i
s
i
n
t
he
de
s
i
r
e
d
c
ol
or
s
pa
c
e
,
a
hi
s
t
og
r
a
m
i
s
c
o
m
put
e
d
f
o
r
e
a
c
h
c
ol
or
c
ha
nne
l
.
A
hi
s
t
og
r
a
m
i
s
a
r
e
pr
e
s
e
nt
a
t
i
on
of
t
he
f
r
e
que
nc
y
of
oc
c
ur
r
e
nc
e
of
di
f
f
e
r
e
nt
c
ol
or
v
a
l
ue
s
w
i
t
hi
n
a
s
pe
c
i
f
i
e
d
r
a
nge
.
I
f
t
he
c
ol
or
s
pa
c
e
i
s
l
a
r
ge
,
t
he
n
i
t
f
i
r
s
t
di
v
i
de
s
i
nt
o
c
e
r
t
a
i
n
nu
m
be
r
s
of
s
m
a
l
l
e
r
i
nt
e
r
v
a
l
s
.
E
a
c
h
of
t
he
i
nt
e
r
v
a
l
s
i
s
c
a
l
l
e
d
a
bi
n.
T
hi
s
pr
oc
e
s
s
i
s
c
a
l
l
e
d
c
o
l
or
qua
nt
i
z
a
t
i
on.
A
f
t
e
r
t
he
qu
a
nt
i
z
a
t
i
on,
t
he
hi
s
t
og
r
a
m
i
s
c
o
m
put
e
d a
s
f
ol
l
ow
s
,
=
1
∪
2
∪
3
…
.
.
∪
(
21)
W
he
r
e
,
s
i
z
e
of
i
nput
c
ol
or
s
pa
c
e
,
1
,
2
…
de
not
e
s
a
bi
ns
,
∪
de
not
e
s
a
uni
on s
ym
bol
.
A
f
t
e
r
t
ha
t
,
t
he
hi
s
t
og
r
a
m
i
s
c
o
m
put
e
d f
or
e
a
c
h bi
n i
s
g
i
v
e
n be
l
ow
,
(
)
=
(
(
)
)
(
22)
w
he
r
e
,
(
)
r
e
pr
e
s
e
nt
s
t
he
hi
s
t
og
r
a
m
i
.e
.
,
f
r
e
que
nc
y
of
oc
c
u
r
r
e
nc
e
of
pi
xe
l
s
i
n
ℎ
bi
n,
(
(
)
)
de
not
e
s
c
ount
s
t
he
num
be
r
of
pi
xe
l
s
i
n
t
he
i
m
a
g
e
t
ha
t
ha
v
e
a
n
i
nt
e
ns
i
t
y
v
a
l
ue
f
a
l
l
i
ng
w
i
t
hi
n
t
he
bi
n
of
t
he
hi
s
t
og
r
a
m
.
I
n t
hi
s
w
a
y
, t
he
c
ol
or
hi
s
t
og
r
a
m
of
t
he
i
m
a
g
e
i
s
obt
a
i
ne
d.
T
e
xt
ur
e
f
e
a
t
ur
e
i
s
us
e
d
t
o
pr
o
v
i
de
t
he
s
pa
t
i
a
l
c
or
r
e
l
a
t
i
on
be
t
w
e
e
n
t
he
pi
xe
l
s
’
i
nt
e
ns
i
t
i
e
s
w
i
t
hi
n
t
he
R
O
I
i
m
a
ge
.
=
1
∗
∑
∑
(
−
)
(
−
)
(
23)
w
he
r
e
‘
’
i
ndi
c
a
t
e
s
t
he
t
e
xt
ur
e
f
e
a
t
ur
e
,
de
not
e
s
a
p
i
xe
l
,
de
not
e
s
a
ne
i
g
hbor
i
ng
pi
xe
l
,
a
nd
i
ndi
c
a
t
e
s
a
m
e
a
n
of
t
he
pi
xe
l
s
a
nd
ne
i
g
hbor
i
ng
pi
xe
l
s
,
a
nd
i
ndi
c
a
t
e
s
a
de
v
i
a
t
i
on
of
t
he
pi
xe
l
s
a
nd
ne
i
g
hbor
i
ng
pi
xe
l
s
.
A
l
g
or
i
t
h
m
3,
out
l
i
ne
s
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
pr
oc
e
s
s
f
or
e
nha
nc
i
n
g
t
he
a
c
c
ur
a
c
y
of
ul
c
e
r
de
t
e
c
t
i
on.
R
e
s
ul
t
i
ng
f
e
a
t
ur
e
s
s
ubs
e
que
nt
l
y
ut
i
l
i
z
e
d t
o e
nha
nc
e
t
he
a
c
c
ur
a
c
y
o
f
ul
c
e
r
de
t
e
c
t
i
on.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
,
V
ol
.
4
3
, N
o.
2
,
A
ug
us
t
20
2
6
:
595
-
606
602
A
l
g
or
i
t
h
m
3.
F
e
a
t
ur
e
e
xt
r
a
c
t
i
on
I
n
p
u
t
:
s
e
g
m
e
n
t
e
d
i
m
a
g
e
s
R
O
I
O
u
t
p
u
t
:
e
x
t
r
a
c
t
t
h
e
f
e
a
t
u
r
e
s
B
e
g
i
n
S
t
e
p
1
:
f
o
r
e
a
c
h
s
e
g
m
e
n
t
e
d
i
m
a
g
e
S
t
e
p
2
:
A
p
p
l
y
r
e
g
r
e
s
s
i
o
n
t
o
p
r
o
j
e
c
t
t
h
e
f
e
a
t
u
r
e
v
e
c
t
o
r
u
s
i
n
g
(
1
4
)
S
t
e
p
3
:
E
x
t
r
a
c
t
t
h
e
s
h
a
p
e
f
e
a
t
u
r
e
s
u
s
i
n
g
(
1
5
)
(
1
6
)
(
1
7
)
S
t
e
p
4
:
C
o
n
v
e
r
t
R
G
B
i
n
t
o
H
S
V
u
s
i
n
g
(
1
8
)
(
1
9
)
(
2
0
)
S
t
e
p
5
:
D
i
v
i
d
e
c
o
l
o
r
s
p
a
c
e
i
n
t
o
b
i
n
u
s
i
n
g
=
1
∪
2
∪
3
…
.
.
∪
S
t
e
p
6
:
M
e
a
s
u
r
e
c
o
l
o
r
h
i
s
t
o
g
r
a
m
(
2
2
)
S
t
e
p
7
:
E
x
t
r
a
c
t
t
e
x
t
u
r
e
f
e
a
t
u
r
e
u
s
i
n
g
c
o
r
r
e
l
a
t
i
o
n
u
s
i
n
g
(
2
3
)
S
t
e
p
8
:
e
n
d
f
o
r
S
t
e
p
9
:
E
x
t
r
a
c
t
s
i
g
n
i
f
i
c
a
n
t
f
e
a
t
u
r
e
s
End
3.
E
X
P
E
R
I
M
E
N
T
A
L
S
E
T
U
P
T
he
pr
opos
e
d
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
i
s
i
m
pl
e
m
e
nt
e
d
us
i
ng
M
A
T
L
A
B
a
nd
e
v
a
l
ua
t
e
d
a
ga
i
ns
t
t
w
o
e
xi
s
t
i
ng
ul
c
e
r
de
t
e
c
t
i
on
m
e
t
hods
,
na
m
e
l
y
d
e
e
p
C
N
N
[
1]
a
nd
V
A
E
-
G
A
N
[
2]
.
A
l
l
e
xpe
r
i
m
e
nt
s
a
r
e
c
onduc
t
e
d
unde
r
t
he
s
a
m
e
i
m
pl
e
m
e
nt
a
t
i
on
e
n
v
i
r
on
m
e
nt
t
o
e
ns
ur
e
a
f
a
i
r
c
o
m
p
a
r
i
s
o
n
a
m
on
g
t
he
c
o
m
pe
t
i
ng
a
ppr
oa
c
h
e
s
.
T
o
e
v
a
l
ua
t
e
t
he
pe
r
f
or
m
a
nc
e
of
t
he
pr
opos
e
d
f
r
a
m
e
w
or
k,
t
he
H
y
p
e
r
-
K
v
a
s
i
r
da
t
a
s
e
t
i
s
e
m
pl
oy
e
d
.
H
y
pe
r
-
K
v
a
s
i
r
i
s
one
o
f
t
he
l
a
r
g
e
s
t
publ
i
c
l
y
a
v
a
i
l
a
bl
e
GI
i
m
a
g
e
da
t
a
s
e
t
s
a
nd
c
ont
a
i
ns
110,079 i
m
a
g
e
s
a
nd 373
v
i
de
os
r
e
pr
e
s
e
nt
i
n
g
a
na
t
o
m
i
c
a
l
l
a
nd
m
a
r
ks
,
pa
t
hol
og
i
c
a
l
f
i
ndi
ng
s
,
t
he
r
a
pe
ut
i
c
i
nt
e
r
v
e
nt
i
ons
,
a
nd
nor
m
a
l
GI
c
ondi
t
i
ons
.
T
he
da
t
a
s
e
t
i
s
di
v
i
de
d
i
nt
o
s
e
v
e
r
a
l
c
a
t
e
g
or
i
e
s
,
i
nc
l
udi
ng
l
a
be
l
e
d
i
m
a
ge
s
,
unl
a
be
l
e
d
i
m
a
g
e
s
,
s
e
gm
e
nt
e
d
i
m
a
ge
s
,
a
nd
a
nnot
a
t
e
d
v
i
de
os
.
I
n
t
hi
s
s
t
udy
,
onl
y
t
he
l
a
be
l
e
d
W
C
E
i
m
a
g
e
s
c
or
r
e
s
pondi
ng
t
o
ul
c
e
r
c
a
s
e
s
a
r
e
ut
i
l
i
z
e
d f
or
e
xpe
r
i
m
e
nt
a
l
e
v
a
l
ua
t
i
on.
A
m
ong
t
he
a
v
a
i
l
a
bl
e
l
a
be
l
e
d s
a
m
pl
e
s
, a
t
ot
a
l
of
851 ul
c
e
r
i
m
a
ge
s
a
r
e
c
ol
l
e
c
t
e
d a
nd us
e
d f
or
a
na
l
y
s
i
s
.
T
o
i
n
v
e
s
t
i
g
a
t
e
t
he
s
c
a
l
a
bi
l
i
t
y
a
nd
r
obus
t
ne
s
s
of
t
he
pr
opos
e
d
m
e
t
h
od,
di
f
f
e
r
e
nt
s
ubs
e
t
s
r
a
ng
i
n
g
f
r
o
m
50
t
o
500
i
m
a
g
e
s
a
r
e
s
e
l
e
c
t
e
d
f
r
o
m
t
he
da
t
a
s
e
t
.
P
r
i
or
t
o
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
a
nd
ul
c
e
r
de
t
e
c
t
i
on,
a
l
l
i
npu
t
i
m
a
g
e
s
unde
r
g
o
pr
e
pr
o
c
e
s
s
i
ng
us
i
ng
t
he
pr
opos
e
d
a
da
pt
i
v
e
C
I
K
F
t
e
c
hni
que
t
o
r
e
duc
e
noi
s
e
a
nd
pr
e
s
e
r
v
e
di
a
g
nos
t
i
c
a
l
l
y
r
e
l
e
v
a
nt
e
d
g
e
i
nf
or
m
a
t
i
on.
S
ubs
e
que
nt
l
y
,
V
on
N
e
um
a
nn
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on
i
s
a
ppl
i
e
d
t
o
i
de
nt
i
f
y
a
nd e
xt
r
a
c
t
ul
c
e
r
-
r
e
l
a
t
e
d
R
O
I
s
f
r
o
m
t
he
pr
e
pr
oc
e
s
s
e
d i
m
a
g
e
s
.
T
he
e
xt
r
a
c
t
e
d
R
O
I
s
a
r
e
t
he
n pr
o
c
e
s
s
e
d us
i
n
g t
he
pr
opos
e
d a
f
f
i
ne
-
i
n
v
a
r
i
a
nt
s
a
l
i
e
nc
y s
l
i
c
e
d r
e
g
r
e
s
s
i
on
f
r
a
m
e
w
or
k
t
o
obt
a
i
n
di
s
c
r
i
m
i
na
t
i
v
e
s
ha
pe
,
c
ol
or
,
a
nd
t
e
xt
ur
e
f
e
a
t
ur
e
s
.
T
he
s
e
f
e
a
t
ur
e
s
a
r
e
s
ubs
e
que
nt
l
y
e
m
pl
oye
d
f
or
ul
c
e
r
de
t
e
c
t
i
on
a
nd
pe
r
f
o
r
m
a
n
c
e
e
v
a
l
ua
t
i
on.
T
he
e
f
f
e
c
t
i
v
e
ne
s
s
of
t
he
p
r
opos
e
d
C
I
K
F
-
A
I
S
R
f
r
a
m
e
w
or
k
i
s
a
s
s
e
s
s
e
d
us
i
ng
s
e
v
e
r
a
l
qua
nt
i
t
a
t
i
v
e
m
e
t
r
i
c
s
,
i
nc
l
udi
ng
P
S
N
R
,
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
,
pr
e
c
i
s
i
on,
a
nd
ul
c
e
r
de
t
e
c
t
i
on
t
i
m
e
.
P
S
N
R
i
s
u
s
e
d
t
o
e
v
a
l
ua
t
e
t
he
qua
l
i
t
y
of
t
he
pr
e
p
r
oc
e
s
s
e
d
i
m
a
g
e
s
,
w
hi
l
e
a
c
c
ur
a
c
y
a
nd pr
e
c
i
s
i
on
m
e
a
s
ur
e
t
he
e
f
f
e
c
t
i
v
e
ne
s
s
of
ul
c
e
r
i
de
nt
i
f
i
c
a
t
i
on. D
e
t
e
c
t
i
on t
i
m
e
i
s
e
m
pl
o
y
e
d t
o a
s
s
e
s
s
t
he
c
o
m
put
a
t
i
ona
l
e
f
f
i
c
i
e
nc
y
of
t
he
pr
opos
e
d
m
e
t
hod.
F
or
c
o
m
pa
r
a
t
i
v
e
a
na
l
y
s
i
s
,
t
he
s
a
m
e
da
t
a
s
e
t
pa
r
t
i
t
i
ons
a
nd
e
v
a
l
ua
t
i
on
c
ondi
t
i
ons
a
r
e
a
ppl
i
e
d
t
o
t
he
d
e
e
p
C
N
N
[
1]
a
nd
V
A
E
-
G
A
N
[
2]
a
ppr
o
a
c
he
s
.
T
he
e
xpe
r
i
m
e
nt
a
l
r
e
s
ul
t
s
obt
a
i
ne
d
f
r
om
t
he
s
e
m
e
t
hods
a
r
e
c
o
m
pa
r
e
d
w
i
t
h
t
hos
e
of
t
he
pr
opos
e
d
C
I
K
F
-
A
I
S
R
f
r
a
m
e
w
or
k
t
o
de
m
ons
t
r
a
t
e
i
t
s
e
f
f
e
c
t
i
v
e
ne
s
s
i
n
i
m
pr
o
v
i
n
g
i
m
a
g
e
qua
l
i
t
y
,
e
nha
nc
i
ng
ul
c
e
r
d
e
t
e
c
t
i
on
pe
r
f
or
m
a
nc
e
,
a
nd
r
e
duc
i
ng
c
o
m
put
a
t
i
ona
l
c
o
m
pl
e
xi
t
y
i
n
W
C
E
i
m
a
g
e
a
na
l
y
s
i
s
.
4.
C
O
M
P
A
R
A
T
I
V
E
P
E
R
F
O
R
M
A
N
C
E
A
N
A
L
Y
S
I
S
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
,
a
l
ong
w
i
t
h
t
w
o
e
xi
s
t
i
ng
m
e
t
hods
,
de
e
p
C
N
N
[
1]
V
A
E
-
G
A
N
[
2]
c
om
p
a
r
e
d
.
T
he
p
e
r
f
or
m
a
nc
e
a
na
l
y
s
i
s
e
m
pl
o
y
s
di
f
f
e
r
e
nt
m
e
t
r
i
c
s
. P
e
r
f
o
r
m
a
nc
e
of
e
a
c
h t
e
c
hni
que
i
n t
e
r
m
s
of
t
he
s
e
m
e
t
r
i
c
s
i
s
i
l
l
u
s
t
r
a
t
e
d t
hr
oug
h t
a
bl
e
s
a
nd g
r
a
phi
c
a
l
r
e
p
r
e
s
e
nt
a
t
i
ons
.
4
.1
.
p
e
r
f
or
m
an
c
e
an
al
ys
i
s
of
P
e
ak
s
i
gn
a
l
t
o n
o
i
s
e
r
at
i
o
Q
ua
l
i
t
y
of
pr
e
pr
oc
e
s
s
e
d
W
C
E
i
m
a
g
e
m
e
a
s
ur
e
d
a
s
P
S
N
R
,
by
c
o
m
pa
r
i
n
g
i
t
t
o
t
he
or
i
g
i
na
l
i
m
a
g
e
.
S
N
R
de
t
e
r
m
i
ne
d t
o c
o
m
put
e
M
S
E
a
m
on
g
or
i
g
i
na
l
a
s
w
e
l
l
a
s
pr
e
pr
o
c
e
s
s
e
d W
C
E
i
m
a
g
e
.
=
10
∗
10
[
2
]
(
24)
=
[
−
]
2
(
25)
w
he
r
e
pe
a
k
s
i
g
na
l
t
o
noi
s
e
r
a
t
i
o
i
s
‘
’
,
‘
’
r
e
pr
e
s
e
nt
s
m
a
xi
m
u
m
pos
s
i
bl
e
pi
xe
l
v
a
l
ue
(
255)
,
i
ndi
c
a
t
e
s
a
m
e
a
n
s
qua
r
e
e
r
r
or
,
i
nd
i
c
a
t
e
s
pr
e
pr
oc
e
s
s
e
d
i
m
a
ge
s
i
z
e
,
de
not
e
s
or
i
g
i
na
l
i
m
a
g
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p S
c
i
I
S
S
N
:
2502
-
4752
A
f
f
i
ne
-
i
nv
ar
i
an
t
f
e
at
ur
e
l
e
ar
n
i
ng f
o
r
ac
c
ur
at
e
ul
c
e
r
d
e
t
e
c
t
i
on i
n w
i
r
e
l
e
s
s
c
aps
u
l
e
…
(
S. B
hu
v
ane
s
w
ar
i
)
603
s
i
z
e
.
I
t
i
s
e
xpr
e
s
s
e
d
i
n
de
c
i
be
l
s
(
dB
)
.
T
hr
e
e
m
e
t
hods
na
m
e
l
y
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
,
de
e
p
C
N
N
[
1]
V
A
E
-
G
A
N
[
2]
a
r
e
e
m
pl
o
y
e
d
i
n
T
a
bl
e
1.
T
he
a
v
e
r
a
g
e
of
t
e
n
c
o
m
p
a
r
i
s
ons
r
e
s
ul
t
s
s
h
ow
s
t
ha
t
P
S
N
R
w
a
s
e
nha
nc
e
d us
i
ng
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
by
17%
a
nd 8%
w
he
n
c
o
m
pa
r
e
d t
o [
1]
[
2]
.
T
a
bl
e
1
.
P
S
N
R
W
C
E
i
m
a
g
e
s
i
z
e
(
K
B
)
P
S
N
R
(
dB
)
C
I
K
F
-
A
I
S
R
de
e
p
C
N
N
V
A
E
-
GAN
228
54.
15
46.
54
50.
06
214.
7
62.
11
51.
22
56.
08
171.
3
58.
58
49.
04
54.
15
270.
4
62.
11
56.
08
58.
58
233
60.
17
52.
86
57.
50
235.
3
63.
27
55.
87
59.
18
244.
7
57.
50
51.
22
54.
15
191.
8
64.
60
50.
06
55.
26
266.
8
60.
89
53.
16
57.
24
267.
4
63.
52
55.
06
58.
58
4
.2
.
P
e
r
f
or
m
an
c
e
an
al
ys
i
s
of
u
l
c
e
r
d
e
t
e
c
t
i
on
ac
c
u
r
ac
y
I
t
m
e
a
s
ur
e
d
a
s
nu
m
be
r
of
W
C
E
i
m
a
ge
s
a
c
c
ur
a
t
e
l
y
de
t
e
c
t
e
d.
A
c
c
ur
a
c
y
m
a
t
he
m
a
t
i
c
a
l
l
y
f
or
m
ul
a
t
e
d
a
s
g
i
v
e
n be
l
o
w
,
=
(
+
+
+
+
)
∗
1
0
0
(
26)
w
he
r
e
,
i
ndi
c
a
t
e
s
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
,
de
not
e
s
t
he
t
r
ue
pos
i
t
i
v
e
s
,
t
r
ue
ne
g
a
t
i
v
e
i
s
,
f
a
l
s
e
pos
i
t
i
v
e
i
s
, f
a
l
s
e
ne
g
a
t
i
v
e
i
ndi
c
a
t
e
s
f
a
l
s
e
ne
g
a
t
i
v
e
.
T
he
a
c
c
ur
a
c
y
i
s
m
e
a
s
ur
e
d i
n pe
r
c
e
nt
a
g
e
(
%
)
.
F
i
g
ur
e
5
de
m
ons
t
r
a
t
e
s
a
pe
r
f
or
m
a
nc
e
a
n
a
l
y
s
i
s
of
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
v
e
r
s
us
t
he
num
b
e
r
o
f
W
C
E
i
m
a
ge
s
.
T
he
o
v
e
r
a
l
l
c
o
m
pa
r
i
s
on r
e
s
ul
t
s
pr
o
v
e
t
ha
t
t
he
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
i
nc
r
e
a
s
e
d a
c
c
ur
a
c
y
b
y
9%
a
nd 5%
t
ha
n t
he
[
1]
,
[
2]
.
F
i
g
ur
e
5
.
pe
r
f
or
m
a
nc
e
r
e
s
ul
t
s
of
ul
c
e
r
de
t
e
c
t
i
on a
c
c
ur
a
c
y
4
.3
.
P
e
r
f
or
m
an
c
e
an
al
ys
i
s
of
p
r
e
c
i
s
i
on
I
t
i
s
t
he
m
e
a
s
ur
e
s
of
r
a
t
i
o
of
t
r
ue
pos
i
t
i
v
e
d
e
t
e
c
t
i
on
of
ul
c
e
r
di
s
e
a
s
e
m
a
d
e
b
y
t
h
e
m
ode
l
.
P
r
e
c
i
s
i
on c
om
put
e
d b
y
,
=
+
(
27)
w
he
r
e
,
de
not
e
s
a
pr
e
c
i
s
i
on,
de
not
e
s
a
t
r
ue
pos
i
t
i
v
e
t
ha
t
t
he
i
m
a
g
e
s
a
r
e
c
o
r
r
e
c
t
l
y
de
t
e
c
t
e
d
a
s
ul
c
e
r
,
i
ndi
c
a
t
e
s
a
f
a
l
s
e
pos
i
t
i
v
e
r
e
f
e
r
t
o
i
m
a
g
e
s
i
nc
o
r
r
e
c
t
l
y
de
t
e
c
t
e
d
a
s
ul
c
e
r
.
T
a
bl
e
2
i
l
l
us
t
r
a
t
e
s
a
pe
r
f
o
r
m
a
nc
e
a
na
l
y
s
i
s
of
pr
e
c
i
s
i
on
i
n
ul
c
e
r
de
t
e
c
t
i
on.
O
n
a
v
e
r
a
g
e
,
t
he
c
o
m
pa
r
i
s
on
of
t
e
n
r
e
s
ul
t
s
r
e
v
e
a
l
s
t
ha
t
t
he
pr
e
c
i
s
i
on
pe
r
f
or
m
a
nc
e
dur
i
ng
ul
c
e
r
de
t
e
c
t
i
on
w
a
s
i
nc
r
e
a
s
e
d
by
9%
c
om
p
a
r
e
d
t
o
de
e
p
C
N
N
[
1]
a
nd
b
y
5%
c
o
m
pa
r
e
d
t
o
V
A
E
-
G
A
N
[
2]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2502
-
4752
I
ndone
s
i
a
n J
E
l
e
c
E
n
g
&
C
om
p
S
c
i
,
V
ol
.
4
3
, N
o.
2
,
A
ug
us
t
20
2
6
:
595
-
606
604
T
a
bl
e
2
.
P
r
e
c
i
s
i
on
v
e
r
s
us
nu
m
be
r
of
W
C
E
i
m
a
ge
s
N
um
be
r
of
W
C
E
i
m
a
g
e
s
P
r
e
c
i
s
i
o
n
(
%
)
C
I
K
F
-
A
I
S
R
D
e
e
p
C
N
N
V
A
E
-
GAN
50
0.
902
0.
837
0.
871
100
0.
912
0.
845
0.
875
150
0.
915
0.
832
0.
856
200
0.
908
0.
855
0.
866
250
0.
911
0.
826
0.
857
300
0.
895
0.
835
0.
858
350
0.
918
0.
847
0.
869
400
0.
907
0.
833
0.
875
450
0.
905
0.
826
0.
855
500
0.
903
0.
818
0.
852
4
.4.
P
e
r
f
or
m
an
c
e
an
al
ys
i
s
of
u
l
c
e
r
d
e
t
e
c
t
i
on
t
i
m
e
T
he
o
v
e
r
a
l
l
t
i
m
e
f
or
ul
c
e
r
de
t
e
c
t
i
on
f
r
om
t
he
g
i
v
e
n
i
nput
W
C
E
i
m
a
ge
s
i
s
m
e
a
s
ur
e
d
a
s
t
he
a
m
ount
o
f
t
i
m
e
t
he
a
l
g
or
i
t
h
m
’
s
t
a
ke
n t
o de
t
e
c
t
t
he
ul
c
e
r
s
.
I
t
i
s
m
a
t
he
m
a
t
i
c
a
l
l
y
c
a
l
c
ul
a
t
e
d a
s
f
ol
l
o
w
s
,
=
∑
=
1
∗
[
]
(
28)
w
he
r
e
,
i
ndi
c
a
t
e
s
t
he
ul
c
e
r
de
t
e
c
t
i
on t
i
m
e
,
[
]
i
ndi
c
a
t
e
s
a
t
i
m
e
f
or
de
t
e
c
t
i
on of
s
i
ng
l
e
i
m
a
g
e
‘
’
.
T
he
o
v
e
r
a
l
l
t
i
m
e
e
s
t
i
m
a
t
e
d i
n
m
i
l
l
i
s
e
c
onds
(
m
s
)
.
F
i
g
ur
e
6
i
l
l
us
t
r
a
t
e
s
pe
r
f
or
m
a
n
c
e
a
n
a
l
y
s
i
s
of
ul
c
e
r
de
t
e
c
t
i
on
t
i
m
e
us
i
n
g
C
I
K
F
-
A
I
S
R
a
nd
d
e
e
p
C
N
N
[
1]
,
V
A
E
-
G
A
N
[
2]
.
F
r
o
m
t
hi
s
a
na
l
y
s
i
s
,
t
he
ul
c
e
r
de
t
e
c
t
i
on
t
i
m
e
us
i
ng
C
I
K
F
-
A
I
S
R
t
e
c
hni
que
w
a
s
m
i
ni
m
i
z
e
d
by
15%
a
nd 8%
t
ha
n t
he
[
1]
a
nd [
2]
.
F
i
g
ur
e
6
.
P
e
r
f
or
m
a
nc
e
r
e
s
ul
t
s
of
ul
c
e
r
de
t
e
c
t
i
on t
i
m
e
5.
C
O
N
C
L
U
S
I
O
N
T
hi
s
pa
pe
r
pr
e
s
e
nt
e
d
a
C
I
K
F
-
A
I
S
R
f
r
a
m
e
w
or
k
f
or
a
ut
o
m
a
t
e
d
ul
c
e
r
de
t
e
c
t
i
on
us
i
ng
W
C
E
i
m
a
g
e
s
.
T
h
e
pr
opos
e
d
f
r
a
m
e
w
or
k
i
nt
e
g
r
a
t
e
s
a
d
a
pt
i
v
e
i
m
a
ge
pr
e
pr
oc
e
s
s
i
ng
,
r
e
g
i
on
-
of
-
i
nt
e
r
e
s
t
s
e
gm
e
nt
a
t
i
on,
a
nd
a
f
f
i
ne
-
i
n
v
a
r
i
a
nt
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
t
o
i
m
pr
o
v
e
ul
c
e
r
de
t
e
c
t
i
on
pe
r
f
or
m
a
nc
e
w
hi
l
e
r
e
duc
i
n
g
c
o
m
put
a
t
i
ona
l
c
o
m
pl
e
xi
t
y
.
A
d
a
pt
i
v
e
C
I
K
F
w
a
s
e
m
pl
o
y
e
d
t
o
s
uppr
e
s
s
noi
s
e
a
nd
pr
e
s
e
r
v
e
e
dg
e
i
nf
or
m
a
t
i
on,
t
he
r
e
by
e
nha
nc
i
n
g
i
m
a
ge
qua
l
i
t
y
.
S
ubs
e
que
nt
l
y
,
V
on
N
e
u
m
a
nn
l
oc
a
l
i
t
y
s
e
gm
e
nt
a
t
i
on
c
om
bi
ne
d
w
i
t
h
t
h
e
C
a
nbe
r
r
a
di
s
t
a
nc
e
m
e
a
s
ur
e
w
a
s
ut
i
l
i
z
e
d
t
o
a
c
c
ur
a
t
e
l
y
e
xt
r
a
c
t
ul
c
e
r
-
r
e
l
a
t
e
d
R
O
I
s
.
F
i
na
l
l
y
,
a
f
f
i
ne
-
i
n
v
a
r
i
a
nt
s
a
l
i
e
nc
y
s
l
i
c
e
d
r
e
g
r
e
s
s
i
on
w
a
s
a
ppl
i
e
d
t
o
de
r
i
v
e
di
s
c
r
i
m
i
na
t
i
v
e
s
ha
pe
,
c
ol
or
,
a
nd
t
e
xt
ur
e
f
e
a
t
ur
e
s
f
or
ul
c
e
r
i
de
nt
i
f
i
c
a
t
i
on.
E
xpe
r
i
m
e
nt
a
l
e
v
a
l
ua
t
i
ons
c
onduc
t
e
d
on
t
he
H
y
pe
r
-
K
v
a
s
i
r
da
t
a
s
e
t
de
m
ons
t
r
a
t
e
d
t
he
e
f
f
e
c
t
i
v
e
ne
s
s
of
t
he
pr
opos
e
d
f
r
a
m
e
w
or
k.
C
o
m
pa
r
a
t
i
v
e
r
e
s
ul
t
s
s
how
e
d
t
ha
t
C
I
K
F
-
A
I
S
R
a
c
hi
e
v
e
d
s
upe
r
i
or
ul
c
e
r
de
t
e
c
t
i
on
a
c
c
ur
a
c
y
,
hi
g
h
e
r
pr
e
c
i
s
i
on,
i
m
pr
o
v
e
d
P
S
N
R
,
a
nd
r
e
duc
e
d
de
t
e
c
t
i
on
t
i
m
e
c
o
m
p
a
r
e
d
w
i
t
h
d
e
e
p
C
N
N
a
nd
V
A
E
-
G
A
N
a
ppr
oa
c
he
s
.
T
he
s
e
i
m
pr
o
v
e
m
e
nt
s
i
ndi
c
a
t
e
t
ha
t
t
he
pr
opos
e
d
f
r
a
m
e
w
or
k
c
a
n
e
f
f
e
c
t
i
v
e
l
y
e
nha
nc
e
di
a
g
nos
t
i
c
r
e
l
i
a
bi
l
i
t
y
w
hi
l
e
m
a
i
nt
a
i
ni
ng
c
o
m
put
a
t
i
ona
l
e
f
f
i
c
i
e
nc
y
f
or
l
a
r
g
e
-
s
c
a
l
e
W
C
E
i
m
a
ge
a
na
l
y
s
i
s
.
T
he
obt
a
i
ne
d
r
e
s
ul
t
s
de
m
ons
t
r
a
t
e
t
he
pot
e
nt
i
a
l
of
C
I
K
F
-
A
I
S
R
a
s
a
c
o
m
put
e
r
-
a
i
de
d
di
a
g
nos
t
i
c
t
ool
f
or
GI
ul
c
e
r
de
t
e
c
t
i
on.
F
ut
ur
e
w
or
k
m
a
y
f
oc
us
on
i
nt
e
g
r
a
t
i
n
g
a
d
v
a
n
c
e
d
DL
a
r
c
hi
t
e
c
t
ur
e
s
a
nd
v
a
l
i
da
t
i
ng
t
he
f
r
a
m
e
w
or
k on l
a
r
g
e
r
m
ul
t
i
c
e
nt
e
r
da
t
a
s
e
t
s
t
o f
ur
t
he
r
i
m
pr
o
v
e
i
t
s
r
obus
t
ne
s
s
a
nd c
l
i
ni
c
a
l
a
ppl
i
c
a
bi
l
i
t
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.