I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
14
,
No
.
4
,
A
u
g
u
s
t
2
0
2
5
,
p
p
.
2
7
6
5
~
2
7
7
5
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
14
.i
4
.
p
p
2
7
6
5
-
2
7
7
5
2765
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
O
ptimi
zed pap
-
s
mea
r ima
g
e enha
ncement
:
hy
brid
Perona
-
M
a
lik dif
fusio
n f
il
ter
-
CLA
H
E
using
spi
der
mo
nkey
o
ptimiza
tion
Ach
K
ho
za
im
i
1,
2
,
I
s
na
ni Da
rt
i
1
,
Wury
a
ns
a
ri
M
uh
a
ri
ni K
us
um
a
wina
hy
u
1
,
Sy
a
if
ul An
a
m
1
1
D
e
p
a
r
t
me
n
t
o
f
M
a
t
h
e
m
a
t
i
c
s
,
F
a
c
u
l
t
y
o
f
M
a
t
h
e
mat
i
c
s
a
n
d
N
a
t
u
r
a
l
S
c
i
e
n
c
e
s,
B
r
a
w
i
j
a
y
a
U
n
i
v
e
r
si
t
y
,
M
a
l
a
n
g
,
I
n
d
o
n
e
si
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
Tr
u
n
o
j
o
y
o
U
n
i
v
e
r
si
t
y
o
f
M
a
d
u
r
a
,
B
a
n
g
k
a
l
a
n
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
8
,
2
0
2
5
R
ev
is
ed
J
u
n
16
,
2
0
2
5
Acc
ep
ted
J
u
l
10
,
2
0
2
5
P
a
p
-
sm
e
a
r
ima
g
e
q
u
a
li
t
y
is
c
ru
c
i
a
l
fo
r
c
e
rv
ica
l
c
a
n
c
e
r
d
e
tec
ti
o
n
.
Th
is
st
u
d
y
in
tro
d
u
c
e
s
a
n
o
p
ti
m
ize
d
h
y
b
r
id
a
p
p
ro
a
c
h
th
a
t
c
o
m
b
in
e
s
t
h
e
P
e
ro
n
a
-
M
a
li
k
d
iffu
si
o
n
(P
M
D)
f
il
ter
wit
h
c
o
n
tr
a
st
-
li
m
it
e
d
a
d
a
p
ti
v
e
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
(CLAHE)
to
e
n
h
a
n
c
e
p
a
p
-
sm
e
a
r
ima
g
e
q
u
a
li
ty
.
T
h
e
P
M
D
fil
ter
re
d
u
c
e
s
th
e
ima
g
e
n
o
ise
,
wh
e
re
a
s
CLAHE
imp
ro
v
e
s
t
h
e
ima
g
e
c
o
n
tras
t.
T
h
e
h
y
b
ri
d
m
e
th
o
d
wa
s
o
p
ti
m
ize
d
u
sin
g
s
p
id
e
r
m
o
n
k
e
y
o
p
ti
m
iza
ti
o
n
(S
M
O
P
M
D
-
CLAHE).
Bli
n
d
/refe
re
n
c
e
-
les
s
ima
g
e
sp
a
ti
a
l
q
u
a
li
ty
e
v
a
lu
a
t
o
r
(
BRIS
QU
E
)
a
n
d
c
o
n
tras
t
e
n
h
a
n
c
e
m
e
n
t
-
b
a
se
d
i
m
a
g
e
q
u
a
li
ty
(
CE
IQ
)
a
re
th
e
n
e
w
o
b
jec
ti
v
e
fu
n
c
ti
o
n
s
fo
r
th
e
P
M
D
fil
ter
a
n
d
CLAHE
o
p
ti
m
iza
ti
o
n
,
re
sp
e
c
ti
v
e
ly
.
T
h
e
sim
u
latio
n
s
we
re
c
o
n
d
u
c
ted
u
s
in
g
th
e
S
IP
a
KMeD
d
a
tas
e
t.
T
h
e
re
su
lt
s
in
d
ica
te
th
a
t
S
M
O
o
u
t
p
e
rfo
rm
s
sta
te
-
of
-
th
e
-
a
rt
m
e
th
o
d
s
in
o
p
ti
m
izin
g
t
h
e
P
M
D
fil
ter
a
n
d
C
LAHE.
T
h
e
p
r
o
p
o
se
d
m
e
th
o
d
a
c
h
iev
e
d
a
n
a
v
e
ra
g
e
e
ffe
c
ti
v
e
m
e
a
su
re
o
f
e
n
h
a
n
c
e
m
e
n
t
(EM
E)
o
f
5
.
4
5
,
r
o
o
t
m
e
a
n
sq
u
a
re
(RM
S
)
c
o
n
tras
t
o
f
6
0
.
4
5
,
M
ich
e
lso
n
’s
c
o
n
tras
t
(M
C)
o
f
0
.
9
9
5
,
a
n
d
e
n
tr
o
p
y
o
f
6
.
8
0
.
Th
is
a
p
p
ro
a
c
h
o
ffe
rs
a
n
e
w
p
e
rsp
e
c
ti
v
e
fo
r
imp
r
o
v
i
n
g
p
a
p
-
sm
e
a
r
ima
g
e
q
u
a
li
t
y
.
K
ey
w
o
r
d
s
:
B
R
I
SQ
UE
C
o
n
tr
ast en
h
an
ce
m
en
t
-
b
ased
im
ag
e
q
u
ality
C
L
AHE
Pap
-
s
m
ea
r
Per
o
n
a
-
Ma
lik
d
if
f
u
s
io
n
f
ilter
S
p
id
er
m
o
n
k
ey
o
p
tim
izatio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
s
n
an
i D
ar
ti
Dep
ar
tm
en
t o
f
Ma
th
em
atics,
Facu
lty
o
f
Ma
th
e
m
atics a
n
d
Na
tu
r
al
Scien
ce
s
,
B
r
awijay
a
Un
iv
er
s
ity
Vete
r
an
Stre
et
No
.
1
2
-
1
6
,
Ma
lan
g
6
5
1
4
5
,
I
n
d
o
n
esia
E
m
ail:
is
n
an
id
ar
ti@
u
b
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
C
a
n
c
e
r
co
n
t
in
u
e
s
t
o
b
e
a
g
l
o
b
a
l
h
e
a
l
t
h
c
o
n
c
e
r
n
,
w
i
th
c
er
v
i
c
a
l
c
a
n
c
e
r
p
o
s
in
g
a
s
i
g
n
if
i
ca
n
t
h
e
a
l
t
h
r
i
s
k
,
e
s
p
e
c
i
a
l
ly
i
n
d
ev
e
l
o
p
i
n
g
co
u
n
t
r
i
e
s
[
1
]
.
I
n
2
0
2
0
,
I
n
d
o
n
e
s
i
a
r
ep
o
r
t
e
d
3
6
,
6
3
3
ca
s
e
s
o
f
c
er
v
i
ca
l
c
an
c
er
,
t
r
a
i
l
i
n
g
o
n
l
y
b
r
e
a
s
t
c
an
c
er
[
2
]
.
T
h
e
G
lo
b
a
l
C
a
n
c
er
O
b
s
er
v
a
t
o
r
y
p
r
e
d
ic
t
e
d
5
7
0
,
0
0
0
n
e
w
c
a
s
e
s
a
n
d
3
1
1
,
0
0
0
d
e
a
t
h
s
g
lo
b
al
l
y
i
n
2
0
1
8
[
3
]
.
A
p
p
r
o
x
i
m
a
t
e
l
y
9
0
%
o
f
ce
r
v
i
c
a
l
c
a
n
c
e
r
-
r
e
l
a
te
d
d
ea
t
h
s
o
c
c
u
r
in
d
e
v
e
l
o
p
i
n
g
c
o
u
n
t
r
i
e
s
[
4
]
.
E
f
f
o
r
t
s
t
o
r
e
d
u
ce
c
e
r
v
ic
a
l
c
an
c
e
r
m
o
r
t
a
l
i
t
y
in
c
l
u
d
e
in
co
r
p
o
r
a
t
i
n
g
i
n
f
o
r
m
a
t
io
n
t
e
ch
n
o
l
o
g
y
a
n
d
a
r
t
i
f
i
c
i
a
l
in
t
e
l
l
i
g
e
n
c
e
in
t
o
s
cr
e
e
n
in
g
p
r
o
c
e
d
u
r
e
s
[
5
]
.
N
o
i
s
e
r
e
d
u
c
t
i
o
n
a
n
d
c
o
n
t
r
a
s
t
en
h
a
n
c
e
m
e
n
t
en
h
an
c
e
m
e
d
i
c
a
l
i
m
a
g
e
q
u
a
l
i
ty
c
la
s
s
i
f
i
c
a
t
i
o
n
[
6
]
.
T
h
e
P
e
r
o
n
a
-
M
a
l
ik
d
i
f
f
u
s
i
o
n
(
P
M
D
)
f
i
l
t
er
m
i
n
im
i
z
e
s
i
m
a
g
e
n
o
i
s
e
a
n
d
e
n
h
a
n
ce
s
i
m
ag
e
s
m
o
o
t
h
n
e
s
s
w
h
i
l
e
r
e
t
ai
n
in
g
k
e
y
d
e
t
a
i
ls
a
n
d
ed
g
e
s
[
7
]
.
P
M
D
u
s
e
s
a
m
o
d
if
i
e
d
G
a
u
s
s
i
a
n
f
u
n
c
t
i
o
n
to
w
e
ig
h
e
a
ch
p
i
x
e
l
v
a
l
u
e,
w
i
th
h
i
g
h
e
r
v
a
lu
e
s
a
t
th
e
ce
n
t
er
an
d
l
o
w
er
v
a
lu
e
s
a
t
t
h
e
p
er
i
p
h
e
r
y
[
8
]
.
S
t
u
d
i
e
s
h
a
v
e
s
h
o
w
n
t
h
a
t
PM
D
f
i
l
t
er
s
e
x
tr
a
c
t
a
n
d
id
e
n
ti
f
y
m
a
l
i
g
n
an
t
tu
m
o
r
s
i
n
m
ed
i
c
a
l
im
a
g
e
s
[
9]
.
I
n
a
d
d
i
t
io
n
,
t
h
e
P
M
D
f
i
l
t
e
r
h
a
s
im
p
r
o
v
ed
th
e
d
e
ep
l
e
ar
n
in
g
p
er
f
o
r
m
an
c
e
in
ce
r
v
i
c
a
l
ca
n
ce
r
c
l
a
s
s
i
f
i
c
a
t
i
o
n
[
1
0
]
.
H
o
w
e
v
er
,
t
h
e
P
M
D
f
i
l
t
e
r
p
e
r
f
o
r
m
an
c
e
r
e
l
i
e
s
o
n
t
h
e
f
i
n
e
-
t
u
n
i
n
g
o
f
i
t
s
p
a
r
am
e
t
e
r
s
.
T
s
i
o
t
s
i
o
s
a
n
d
P
e
tr
o
u
[
1
1
]
c
h
o
s
e
th
e
P
M
D
f
i
l
t
er
p
a
r
am
et
e
r
i
t
er
a
t
i
v
e
ly
.
T
h
e
o
t
h
er
r
e
s
ea
r
c
h
u
s
e
s
p
a
r
t
i
c
le
s
w
a
r
m
o
p
t
im
i
z
a
t
i
o
n
(
P
S
O
)
t
o
s
e
l
e
c
t
P
M
D
p
ar
a
m
e
t
e
r
s
an
d
im
p
r
o
v
e
t
h
e
P
M
D
f
i
l
te
r
p
e
r
f
o
r
m
a
n
c
e
[
1
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t
20
25
:
2
7
6
5
-
2
7
7
5
2766
C
o
n
t
r
a
s
t
-
l
im
i
t
e
d
ad
a
p
t
iv
e
h
is
t
o
g
r
am
e
q
u
a
l
i
z
a
t
io
n
(
C
L
AH
E
)
i
s
a
v
ar
i
a
n
t
o
f
a
d
a
p
t
iv
e
h
i
s
to
g
r
a
m
e
q
u
a
l
iz
a
t
i
o
n
(
A
H
E
)
t
h
a
t
l
i
m
i
ts
c
o
n
tr
a
s
t
en
h
a
n
c
em
e
n
t
[
1
3
]
.
C
L
A
H
E
e
f
f
e
c
t
i
v
e
l
y
i
m
p
r
o
v
e
s
p
ap
-
s
m
ea
r
im
a
g
e
s
a
n
d
en
h
a
n
c
e
s
V
G
G1
6
,
I
n
c
e
p
t
i
o
n
V
3
,
an
d
E
f
f
i
c
ie
n
t
N
e
t
p
e
r
f
o
r
m
a
n
c
e
i
n
ce
r
v
i
c
a
l
c
an
c
er
c
l
a
s
s
i
f
i
c
a
t
i
o
n
[
1
4
]
.
C
L
A
H
E
h
a
s
d
e
m
o
n
s
t
r
a
te
d
ef
f
e
c
t
iv
e
n
e
s
s
i
n
en
h
an
c
in
g
im
a
g
e
q
u
a
l
i
ty
an
d
i
m
p
r
o
v
i
n
g
th
e
p
e
r
f
o
r
m
a
n
c
e
o
f
v
a
r
io
u
s
m
a
c
h
in
e
l
e
a
r
n
i
n
g
a
lg
o
r
i
t
h
m
s
i
n
c
er
v
i
c
a
l
c
an
c
e
r
c
la
s
s
i
f
i
c
a
t
i
o
n
t
a
s
k
s
,
i
n
c
lu
d
in
g
k
-
n
e
a
r
e
s
t
n
e
ig
h
b
o
r
s
(
K
N
N
)
an
d
a
r
t
if
i
c
i
a
l
n
eu
r
a
l
n
e
t
w
o
r
k
s
(
A
N
N
)
.
Ad
d
i
t
io
n
a
l
ly
,
C
L
A
H
E
h
a
s
en
h
an
c
ed
th
e
d
e
t
e
c
t
i
o
n
a
c
cu
r
a
c
y
o
f
t
h
e
y
o
u
o
n
ly
l
o
o
k
o
n
c
e
(
Y
O
L
O
)
a
lg
o
r
i
t
h
m
in
n
ig
h
t
-
t
i
m
e
r
o
a
d
m
a
r
k
i
n
g
r
e
co
g
n
i
t
io
n
,
im
p
r
o
v
e
d
th
e
p
e
r
f
o
r
m
a
n
c
e
o
f
c
o
n
v
o
l
u
t
io
n
a
l
n
eu
r
a
l
n
e
t
wo
r
k
s
(
C
N
N
s
)
i
n
lu
n
g
ca
n
c
er
s
eg
m
en
t
a
t
io
n
f
r
o
m
c
o
m
p
u
te
d
t
o
m
o
g
r
ap
h
y
(
CT
)
s
c
an
i
m
ag
es
,
an
d
co
n
t
r
ib
u
te
d
t
o
w
a
te
r
i
m
a
g
e
c
l
a
s
s
i
f
i
c
a
t
io
n
t
a
s
k
s
[
1
5
]
–
[
1
9
]
.
H
o
w
ev
e
r
,
th
e
e
f
f
e
c
t
iv
en
e
s
s
o
f
C
L
A
H
E
d
ep
e
n
d
s
o
n
i
t
s
p
a
r
am
e
t
e
r
s
,
i
.
e
.
,
cl
i
p
l
i
m
i
t
an
d
t
i
l
e
s
i
z
e
.
Qa
s
s
i
m
e
t
a
l
.
[
1
6
]
s
e
t
u
p
a
c
l
i
p
li
m
i
t
o
f
0
.
0
1
an
d
a
t
i
l
e
s
iz
e
o
f
8
×
8
t
o
g
e
t
t
h
e
b
e
s
t
C
L
AH
E
p
e
r
f
o
r
m
a
n
c
e
,
en
h
an
c
i
n
g
d
e
n
t
a
l
d
i
g
i
t
a
l
X
-
r
ay
i
m
a
g
e
s
.
S
e
v
e
r
a
l
s
t
u
d
ie
s
h
a
v
e
a
p
p
l
i
ed
d
i
f
f
e
r
en
t
h
eu
r
i
s
t
i
c
o
p
t
i
m
i
z
a
t
io
n
a
lg
o
r
i
t
h
m
s
t
o
i
m
p
r
o
v
e
C
L
A
H
E
p
e
r
f
o
r
m
a
n
c
e
.
P
S
O
w
a
s
u
s
e
d
t
o
o
p
t
i
m
i
z
e
C
L
A
H
E
p
e
r
f
o
r
m
a
n
c
e
w
i
th
m
u
lt
i
-
o
b
je
c
t
i
v
e
f
u
n
ct
i
o
n
s
,
i
.
e
.
,
e
n
t
r
o
p
y
a
n
d
s
t
r
u
c
t
u
r
e
s
i
m
i
l
ar
i
t
y
in
d
e
x
m
e
a
s
u
r
e
(
S
S
I
M
)
.
T
h
i
s
ap
p
r
o
ac
h
m
ax
i
m
i
z
ed
i
m
ag
e
co
n
tr
a
s
t
w
h
i
l
e
m
in
i
m
i
z
in
g
d
i
s
t
o
r
t
io
n
in
X
-
r
a
y
m
e
d
ic
a
l
i
m
a
g
e
s
[
1
7
]
.
F
a
w
z
i
e
t
a
l
.
[
1
8
]
ap
p
l
i
ed
t
h
e
w
h
a
l
e
o
p
t
im
i
z
a
t
i
o
n
a
l
g
o
r
i
th
m
(
W
O
A
)
t
o
o
p
t
i
m
iz
e
C
L
A
HE
p
e
r
f
o
r
m
an
c
e
w
i
th
D
a
t
a
S
ig
n
a
l
a
s
th
e
o
b
j
e
c
t
iv
e
f
u
n
c
t
io
n
.
T
h
e
Da
t
a
S
i
g
n
a
l
r
e
s
u
l
t
s
f
r
o
m
m
u
l
t
ip
l
y
in
g
t
h
e
e
n
tr
o
p
y
b
y
t
h
e
p
e
a
k
s
i
g
n
a
l
-
to
-
n
o
i
s
e
r
a
t
io
(
P
S
N
R
)
.
I
t
ef
f
e
c
t
i
v
e
ly
e
n
h
a
n
ce
s
i
m
a
g
e
co
n
tr
a
s
t
a
c
r
o
s
s
d
a
t
a
s
et
s
l
i
k
e
f
a
c
e
s
-
1
9
9
9
,
B
r
a
T
S
,
an
d
P
a
s
a
d
e
n
a
-
h
o
u
s
e
s
2
0
0
0
[
1
8
]
.
T
h
e
r
e
s
e
a
r
ch
i
n
[
1
9
]
em
p
lo
y
ed
th
e
cu
ck
o
o
s
e
a
r
c
h
a
l
g
o
r
i
th
m
(
C
S
A
)
w
i
th
en
t
r
o
p
y
a
n
d
f
a
s
t
n
o
i
s
e
v
a
r
i
a
n
ce
e
s
t
i
m
a
t
io
n
(
F
N
V
E
)
a
s
o
b
je
c
t
i
v
e
f
u
n
c
t
io
n
s
.
T
h
i
s
s
t
u
d
y
s
h
o
w
ed
s
u
p
e
r
io
r
p
e
r
f
o
r
m
an
c
e
in
C
L
A
H
E
o
p
t
i
m
i
z
a
t
io
n
o
n
t
h
e
c
o
n
tr
a
s
t
e
n
h
an
c
e
m
en
t
ev
a
l
u
a
t
i
o
n
2
0
1
6
(
C
E
E
D
2
0
1
6
)
d
at
a
s
e
t
c
o
m
p
a
r
e
d
to
t
h
e
b
a
t
f
i
r
e
f
ly
an
d
f
l
o
w
er
p
o
l
l
in
a
t
i
o
n
a
lg
o
r
i
t
h
m
s
(
F
P
A)
[
1
9
]
.
I
n
2
0
2
2
,
F
P
A
o
p
t
i
m
i
ze
d
C
L
A
H
E
w
i
t
h
e
n
tr
o
p
y
an
d
F
N
V
E
a
s
o
b
j
e
c
t
iv
e
f
u
n
c
t
i
o
n
s
.
T
h
i
s
s
t
u
d
y
a
ch
i
ev
ed
n
o
t
a
b
le
n
o
i
s
e
r
ed
u
c
t
i
o
n
an
d
c
o
n
t
r
a
s
t
e
n
h
a
n
ce
m
en
t
o
n
th
e
P
a
s
a
d
e
n
a
-
h
o
u
s
e
s
2
0
0
0
an
d
d
i
ab
e
t
i
c
r
e
t
in
o
p
a
t
h
y
d
e
t
e
c
t
io
n
(
DI
A
R
E
T
D
B
0
)
d
a
ta
s
e
t
s
[
2
0
]
.
S
u
r
y
a
an
d
Mu
t
h
u
k
u
m
ar
a
v
e
l
[
2
1
]
u
s
e
d
ad
a
p
t
iv
e
s
a
i
l
f
i
s
h
o
p
ti
m
i
z
a
t
i
o
n
(
A
S
F
O
)
t
o
en
h
an
c
e
C
L
A
H
E
p
e
r
f
o
r
m
a
n
c
e
.
T
h
i
s
s
t
u
d
y
f
o
c
u
s
e
s
o
n
m
a
x
im
i
z
in
g
c
o
n
t
r
a
s
t
a
n
d
en
t
r
o
p
y
w
i
th
s
u
c
c
es
s
f
u
l
en
h
an
c
e
m
e
n
t
o
u
t
co
m
e
s
o
n
m
a
m
m
o
g
r
a
m
im
a
g
e
s
f
r
o
m
t
h
e
m
a
m
m
o
g
r
ap
h
i
c
im
a
g
e
an
a
ly
s
i
s
s
o
c
i
e
ty
(
MI
AS
)
d
a
t
ab
a
s
e
[
2
1
]
.
C
a
t
s
w
a
r
m
o
p
t
im
i
z
a
t
i
o
n
(
C
S
O
)
i
s
a
l
s
o
u
s
ed
to
en
h
an
c
e
C
L
A
H
E
p
e
r
f
o
r
m
a
n
ce
w
i
th
en
tr
o
p
y
an
d
F
N
V
E
a
s
o
b
j
e
c
t
iv
e
f
u
n
c
t
i
o
n
s
.
T
h
i
s
a
p
p
r
o
a
c
h
o
u
tp
e
r
f
o
r
m
ed
t
r
ad
i
t
i
o
n
a
l
m
e
th
o
d
s
l
i
k
e
h
u
e,
s
a
t
u
r
at
i
o
n
,
a
n
d
l
i
g
h
t
n
e
s
s
(
H
S
L
)
,
E
u
r
o
p
e
a
n
c
o
m
m
i
s
s
i
o
n
(
EC
)
,
h
i
s
t
o
g
r
a
m
e
q
u
a
l
i
z
a
t
io
n
(
HE
)
,
an
d
C
L
A
H
E
-
C
S
A
o
n
th
e
C
E
E
D2
0
1
6
d
a
t
a
s
e
t
[
2
2
]
.
I
n
2
0
2
4
,
H
ad
d
a
d
i
e
t
a
l
.
[
2
3
]
i
n
tr
o
d
u
c
e
d
th
e
p
el
i
c
a
n
o
p
t
i
m
i
z
a
t
io
n
a
lg
o
r
i
t
h
m
(
P
O
A
)
to
o
p
t
i
m
i
z
e
C
L
A
H
E
p
e
r
f
o
r
m
an
c
e
w
i
t
h
s
e
v
e
r
a
l
m
e
t
r
ic
s
,
i
n
c
lu
d
in
g
P
SN
R
,
m
e
a
n
s
q
u
ar
e
d
er
r
o
r
(
MS
E
)
,
en
t
r
o
p
y
,
an
d
S
S
I
M
a
s
o
b
j
e
c
t
iv
e
f
u
n
c
t
io
n
s
.
T
h
i
s
s
t
u
d
y
u
s
e
s
a
p
r
iv
a
te
d
a
ta
s
e
t
an
d
o
u
t
p
er
f
o
r
m
s
th
e
ex
i
s
t
i
n
g
i
m
a
g
e
e
n
h
an
c
em
e
n
t
t
e
c
h
n
i
q
u
e
s
[
2
3
]
.
I
n
t
h
i
s
s
t
u
d
y
,
w
e
a
i
m
e
d
t
o
en
h
a
n
ce
ce
r
v
i
c
a
l
i
m
ag
e
q
u
a
l
i
t
y
u
s
i
n
g
a
h
y
b
r
i
d
P
M
D
f
i
l
t
er
-
C
L
A
H
E
.
T
h
e
P
M
D
f
i
l
t
e
r
i
s
u
s
e
d
f
o
r
n
o
i
s
e
r
e
d
u
c
t
io
n
,
a
n
d
C
L
A
H
E
i
s
u
s
ed
f
o
r
c
o
n
t
r
a
s
t
en
h
an
c
em
e
n
t.
T
h
e
s
p
id
e
r
m
o
n
k
ey
o
p
t
i
m
iz
a
t
i
o
n
(
S
M
O
)
a
lg
o
r
i
th
m
o
p
t
i
m
i
z
ed
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
(
h
y
b
r
id
P
M
D
f
i
l
te
r
-
C
L
A
H
E
)
.
S
M
O
p
e
r
f
o
r
m
s
b
e
s
t
in
o
p
t
im
i
z
i
n
g
U
C
A
V
p
a
t
h
-
p
l
an
n
in
g
p
r
o
b
l
em
s
c
o
m
p
a
r
e
d
to
o
t
h
er
m
e
t
a
h
e
u
r
i
s
t
i
c
a
lg
o
r
i
t
h
m
s
[
2
4
]
.
A
n
e
w
o
b
j
e
c
t
iv
e
f
u
n
c
t
i
o
n
w
a
s
in
t
r
o
d
u
c
e
d
i
n
t
h
i
s
s
tu
d
y
.
T
h
e
b
l
in
d
/
r
e
f
er
e
n
c
e
-
l
e
s
s
im
a
g
e
s
p
a
t
i
a
l
q
u
a
l
i
t
y
e
v
a
l
u
a
t
o
r
(
B
R
I
S
Q
U
E
)
i
s
a
n
e
w
o
b
j
ec
t
i
v
e
f
u
n
c
t
i
o
n
f
o
r
P
M
D
f
i
l
t
er
o
p
t
im
i
z
a
t
i
o
n
.
B
R
I
S
Q
U
E
i
s
h
i
g
h
ly
c
o
m
p
e
t
i
t
i
v
e
w
i
t
h
t
h
i
s
n
o
-
r
ef
e
r
e
n
ce
i
m
ag
e
q
u
a
l
i
t
y
a
s
s
e
s
s
m
e
n
t
(
N
R
-
I
Q
A)
ap
p
r
o
a
ch
.
I
t
i
s
a
l
s
o
s
t
a
t
i
s
t
i
c
a
l
ly
b
e
t
t
e
r
th
a
n
t
h
e
p
o
p
u
la
r
f
u
l
l
-
r
e
f
e
r
en
c
e
i
m
ag
e
q
u
a
l
i
ty
a
s
s
e
s
s
m
e
n
t
(
F
R
-
I
Q
A)
,
s
u
c
h
a
s
P
SN
R
a
n
d
S
S
I
M
[
2
5
]
.
C
o
n
t
r
a
s
t
en
h
an
c
em
e
n
t
-
b
a
s
ed
i
m
a
g
e
q
u
a
l
i
t
y
(
C
E
I
Q
)
i
s
a
n
ew
o
b
j
ec
t
i
v
e
f
u
n
c
t
io
n
f
o
r
C
L
A
H
E
o
p
t
im
i
z
a
t
io
n
.
T
h
e
C
E
I
Q
i
s
c
o
m
p
u
t
e
d
u
s
in
g
th
e
h
i
s
t
o
g
r
a
m
’
s
ch
a
r
a
c
t
e
r
i
s
t
i
c
s
o
f
en
t
r
o
p
y
,
c
r
o
s
s
-
e
n
t
r
o
p
y
,
a
n
d
S
S
I
M
[
2
6
]
.
C
E
I
Q
i
d
en
t
i
f
i
e
s
th
a
t
th
e
im
p
r
o
v
ed
i
m
a
g
e
e
x
h
i
b
i
t
s
co
n
tr
a
s
t
d
i
s
t
o
r
t
io
n
[
2
7
]
.
T
h
i
s
s
t
u
d
y
u
s
e
d
s
ev
e
r
a
l
m
e
t
r
ic
s
t
o
e
v
a
l
u
a
t
e
t
h
e
i
m
ag
e
d
e
n
o
i
s
i
n
g
an
d
co
n
tr
a
s
t
en
h
an
c
e
m
en
t
.
M
S
E
,
S
S
I
M
,
P
S
N
R
,
C
E
I
Q
,
en
t
r
o
p
y
,
e
n
h
a
n
c
em
e
n
t
m
e
a
s
u
r
e
e
s
t
im
at
i
o
n
(
E
M
E
)
,
M
i
ch
e
l
s
o
n
co
n
tr
a
s
t
(
M
C
)
,
an
d
r
o
o
t
m
e
a
n
s
q
u
ar
e
(
R
M
S
)
co
n
tr
a
s
t
w
e
r
e
u
s
e
d
.
T
h
e
s
e
m
e
t
r
i
c
s
ev
a
l
u
a
te
i
m
ag
e
c
l
a
r
i
ty
,
d
e
t
a
i
l
p
r
e
s
er
v
a
t
io
n
,
an
d
c
o
n
tr
a
s
t
i
m
p
r
o
v
em
e
n
t.
T
h
e
p
r
o
p
o
s
e
d
a
p
p
r
o
a
ch
o
p
er
a
t
e
s
in
t
h
e
C
I
E
L
A
B
co
l
o
r
m
o
d
e
l
o
f
p
ap
-
s
m
ea
r
im
a
g
e
s
a
n
d
o
f
f
e
r
s
s
ev
e
r
a
l
co
n
tr
i
b
u
t
i
o
n
s
.
F
i
r
s
t
,
h
y
b
r
i
d
S
M
O
P
M
D
-
C
L
A
H
E
p
r
o
v
id
e
s
t
h
e
a
d
v
a
n
t
ag
e
s
o
f
r
e
d
u
c
in
g
n
o
i
s
e
an
d
i
n
c
r
e
a
s
in
g
c
o
n
tr
a
s
t
b
e
c
au
s
e
m
o
s
t
p
a
p
-
s
m
e
a
r
i
m
ag
e
s
ar
e
n
o
i
s
y
an
d
h
a
v
e
l
o
w
c
o
n
t
r
a
s
t
[
2
8
]
.
S
ec
o
n
d
,
B
R
I
S
Q
U
E
an
d
C
E
I
Q
ar
e
t
h
e
n
e
w
o
b
je
c
t
i
v
e
f
u
n
c
t
i
o
n
s
f
o
r
th
e
P
M
D
f
il
t
e
r
a
n
d
C
L
A
H
E
o
p
t
i
m
iz
a
t
io
n
.
B
R
I
S
Q
U
E
wa
s
s
t
a
t
i
s
t
i
c
a
l
l
y
b
e
t
t
er
t
h
a
n
P
S
N
R
a
n
d
S
S
I
M
[
2
5
]
.
C
E
I
Q
c
an
ev
a
l
u
a
te
i
m
ag
e
c
o
n
t
r
a
s
t
d
e
f
o
r
m
a
t
i
o
n
[
2
7
]
.
T
h
ir
d
,
t
h
e
S
M
O
-
P
M
D
f
i
l
t
er
an
d
S
M
O
C
L
A
H
E
o
u
t
p
e
r
f
o
r
m
e
d
s
t
a
t
e
-
of
-
th
e
-
ar
t
m
e
t
h
o
d
s
.
T
h
i
s
s
t
u
d
y
o
f
f
er
s
a
n
e
w
p
e
r
s
p
ec
t
i
v
e
f
o
r
i
m
p
r
o
v
i
n
g
c
e
r
v
i
ca
l
i
m
a
g
e
q
u
a
l
i
t
y
a
n
d
c
o
n
t
r
ib
u
t
e
s
to
m
o
r
e
a
cc
u
r
a
t
e
c
er
v
i
c
a
l
c
an
c
e
r
d
e
t
e
c
t
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Op
timiz
ed
p
a
p
-
s
mea
r
ima
g
e
e
n
h
a
n
ce
men
t
:
h
yb
r
id
P
ero
n
a
-
Ma
lik
d
iffu
s
io
n
filt
er
-
C
LAHE
…
(
A
ch
K
h
o
z
a
imi)
2767
2.
M
E
T
H
O
D
Fig
u
r
e
1
illu
s
tr
ates
th
e
p
r
o
ce
d
u
r
e
f
o
r
en
h
an
cin
g
ce
r
v
ical
i
m
ag
es
u
s
in
g
a
h
y
b
r
id
PMD
f
ilter
-
C
L
AHE
o
p
tim
ized
u
s
in
g
th
e
SMO
alg
o
r
ith
m
.
T
h
e
in
p
u
t
was
a
co
lo
r
im
ag
e
f
r
o
m
t
h
e
SIPaK
Me
D
d
ataset.
T
h
e
SIPaK
Me
D
d
ataset
co
n
tain
s
4
,
0
4
9
an
n
o
tated
ce
r
v
ical
ce
ll
im
ag
es
in
f
iv
e
class
es.
E
ac
h
class
r
ep
r
esen
ts
d
is
tin
ct
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
v
ital
f
o
r
m
ed
ical
clas
s
if
icatio
n
.
I
ts
p
r
im
ar
y
c
h
ar
ac
ter
is
tics
in
clu
d
e
h
ig
h
v
ar
iab
ilit
y
in
ce
ll
s
h
ap
es,
te
x
tu
r
es,
n
o
is
e,
an
d
co
n
t
r
ast
lev
e
ls
.
T
h
is
v
ar
iab
ilit
y
p
o
s
es
ch
al
len
g
es
in
ac
c
u
r
ate
class
if
icatio
n
[
2
9
]
.
T
h
e
c
o
lo
r
im
ag
e
is
s
p
lit
in
to
lig
h
tn
ess
(
L
)
,
g
r
ee
n
-
r
ed
(
A
)
,
an
d
b
lu
e
-
y
ello
w
(
B
)
co
l
o
r
ch
an
n
els
in
th
e
C
I
E
L
AB
co
l
o
r
s
p
ac
e.
T
h
e
C
I
E
L
AB
co
lo
r
s
p
ac
e
is
d
esig
n
ed
to
r
esem
b
l
e
th
e
h
u
m
a
n
v
is
u
al
s
y
s
tem
(
HVS)
[
3
0
]
.
E
ac
h
ch
an
n
el
u
n
d
e
r
wen
t sep
ar
ate
p
r
o
ce
s
s
in
g
s
tep
s
:
‒
Den
o
is
in
g
:
th
e
A,
B
,
an
d
L
c
h
an
n
els
ar
e
in
d
i
v
id
u
ally
d
en
o
i
s
ed
u
s
in
g
th
e
SMO
-
PMD
f
ilte
r
,
wh
ich
aim
s
to
r
ed
u
ce
n
o
is
e
wh
ile
p
r
eser
v
i
n
g
im
p
o
r
tan
t im
ag
e
f
ea
tu
r
es su
ch
as e
d
g
es;
‒
C
o
n
tr
ast
en
h
an
ce
m
en
t:
af
ter
d
en
o
is
in
g
,
th
e
L
ch
an
n
el
was
f
u
r
th
er
en
h
a
n
ce
d
u
s
in
g
SMO
-
C
L
AHE
,
wh
ich
im
p
r
o
v
e
d
th
e
lo
ca
l c
o
n
tr
ast an
d
h
ig
h
lig
h
ted
f
in
e
r
d
etails.
On
ce
all
ch
an
n
els
(
L
,
A,
an
d
B
)
wer
e
p
r
o
ce
s
s
ed
(
d
en
o
is
ed
an
d
co
n
tr
ast
-
en
h
an
ce
d
)
,
th
ey
wer
e
r
ec
o
m
b
in
ed
in
to
th
e
f
in
al
en
h
an
ce
d
p
ap
-
s
m
ea
r
im
ag
e.
T
h
is
en
h
an
ce
d
im
ag
e
s
h
o
u
ld
ex
h
ib
it
an
im
p
r
o
v
ed
v
is
u
al
q
u
ality
,
r
ed
u
ce
d
n
o
is
e,
an
d
b
etter
co
n
t
r
ast.
Fig
u
r
e
1
.
Flo
wch
ar
t
o
f
p
ap
-
s
m
ea
r
im
ag
e
en
h
an
ce
m
e
n
t u
s
in
g
SMO
PMD
f
ilter
-
C
L
A
HE
T
h
e
h
y
b
r
id
PMD
-
C
L
AHE
p
r
o
ce
s
s
was
o
p
tim
ized
u
s
in
g
th
e
SMO
alg
o
r
ith
m
.
T
h
e
SMO
o
p
tim
izer
was
co
n
f
ig
u
r
e
d
with
1
0
iter
atio
n
s
an
d
a
p
o
p
u
latio
n
s
ize
o
f
5
0
to
b
alan
ce
ex
p
lo
r
atio
n
an
d
co
m
p
u
tatio
n
a
l
ef
f
icien
cy
.
T
h
e
n
u
m
b
er
o
f
iter
atio
n
s
(
Niter
)
was
s
et
b
etwe
en
5
a
n
d
3
0
to
co
n
tr
o
l
th
e
d
e
g
r
e
e
o
f
d
en
o
is
in
g
.
T
h
e
d
if
f
u
s
io
n
c
o
ef
f
icien
t
(
κ
)
r
an
g
e
d
f
r
o
m
1
0
t
o
1
0
0
to
a
d
ju
s
t
th
e
s
m
o
o
th
in
g
in
te
n
s
ity
,
wh
ile
th
e
g
r
ad
ien
t
th
r
esh
o
ld
(
λ
)
was
s
et
b
etwe
en
0
.
1
an
d
0
.
2
5
to
p
r
eser
v
e
im
ag
e
e
d
g
es
.
T
h
e
clip
lim
it
was
s
et
b
etw
ee
n
0
.
0
1
an
d
4
t
o
m
an
ag
e
c
o
n
tr
ast
en
h
an
ce
m
e
n
t,
an
d
th
e
tile
s
ize
r
an
g
ed
f
r
o
m
2
to
1
6
t
o
d
ete
r
m
in
e
t
h
e
lo
ca
l
co
n
tr
ast
r
e
g
io
n
s
.
T
h
is
co
n
f
ig
u
r
atio
n
ef
f
ec
tiv
ely
b
alan
ce
s
th
e
n
o
is
e
r
ed
u
ctio
n
a
n
d
co
n
t
r
ast en
h
an
ce
m
e
n
t.
2
.
1
.
P
er
o
na
-
M
a
lik
diff
us
io
n
f
ilte
r
A
PMD
f
ilter
was
em
p
lo
y
ed
t
o
m
in
im
ize
im
a
g
e
n
o
is
e
wh
il
e
p
r
eser
v
in
g
th
e
e
d
g
es.
T
h
is
a
n
is
o
tr
o
p
ic
d
if
f
u
s
io
n
p
r
o
ce
s
s
ad
ju
s
ts
th
e
d
if
f
u
s
i
o
n
c
o
ef
f
icien
t
ac
co
r
d
i
n
g
to
th
e
g
r
a
d
ien
t
o
f
th
e
im
ag
e,
th
u
s
f
ac
ilit
atin
g
ed
g
e
-
p
r
eser
v
in
g
s
m
o
o
th
in
g
[
8
]
.
Giv
en
an
im
a
g
e
(
,
,
)
,
wh
er
e
x
a
n
d
y
ar
e
s
p
atial
co
o
r
d
in
ates
a
n
d
t
is
th
e
d
if
f
u
s
io
n
tim
e
(
o
r
iter
atio
n
)
.
T
h
e
p
ar
tial
d
if
f
er
e
n
tial
in
(
1
)
g
o
v
e
r
n
ed
th
e
e
v
o
lu
tio
n
o
f
t
h
e
im
ag
e
u
n
d
e
r
th
e
PMD.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t
20
25
:
2
7
6
5
-
2
7
7
5
2768
=
⋅
(
(
∥
∥
)
)
(
1
)
w
h
er
e
r
ep
r
esen
ts
th
e
ch
an
g
e
in
p
ix
el
in
ten
s
ity
o
v
er
tim
e.
(
∥
∥
)
is
th
e
d
if
f
u
s
io
n
co
ef
f
icien
t,
wh
ich
co
n
tr
o
ls
th
e
a
m
o
u
n
t
o
f
d
if
f
u
s
io
n
b
ased
o
n
t
h
e
g
r
ad
ien
t
m
ag
n
itu
d
e.
T
h
e
c
r
itical
asp
ec
t
o
f
th
e
PMD
is
th
e
ch
o
ice
o
f
d
if
f
u
s
io
n
(
∥
∥
)
.
T
h
e
two
co
m
m
o
n
f
o
r
m
s
o
f
d
if
f
u
s
io
n
co
ef
f
icien
ts
ar
e
ex
p
o
n
e
n
tial
a
n
d
in
v
er
s
e
q
u
ad
r
atic
[
3
1
]
.
T
h
is
s
tu
d
y
u
s
ed
th
e
ex
p
o
n
e
n
tial f
o
r
m
o
f
(
2
)
.
(
∥
∥
)
=
−
(
|
|
)
2
(
2
)
w
h
er
e
K
is
a
p
ar
am
eter
t
h
at
c
o
n
tr
o
ls
th
e
s
en
s
itiv
ity
o
f
th
e
d
i
f
f
u
s
io
n
p
r
o
ce
s
s
to
ed
g
es.
Sm
al
l
v
alu
es
o
f
K
r
esu
lt
in
m
o
r
e
ag
g
r
ess
iv
e
ed
g
e
p
r
eser
v
atio
n
,
wh
ile
lar
g
er
v
alu
es
allo
w
m
o
r
e
s
m
o
o
th
in
g
.
T
h
i
s
iter
ativ
e
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
u
n
til
a
co
n
v
e
r
g
en
c
e
co
n
d
itio
n
is
r
ea
ch
ed
o
r
a
ce
r
tain
n
u
m
b
er
o
f
iter
atio
n
s
is
d
eter
m
in
ed
[
3
2
]
.
T
h
e
ed
g
e
-
p
r
eser
v
in
g
p
r
o
p
e
r
ty
o
f
t
h
e
PMD
f
ilter
co
m
es
f
r
o
m
th
e
b
eh
av
io
r
o
f
th
e
d
i
f
f
u
s
io
n
c
o
ef
f
icien
t
(
∥
∥
)
.
No
is
e
r
ed
u
ctio
n
is
d
esire
d
wit
h
o
u
t b
l
u
r
r
in
g
cr
itical
s
tr
u
ctu
r
a
l f
ea
tu
r
es,
s
u
ch
as
ed
g
es
[
3
3
]
.
2
.
2
.
Co
ntr
a
s
t
-
lim
it
ed
a
da
pti
v
e
his
t
o
g
ra
m e
qu
a
liza
t
io
n
C
L
AHE
is
a
p
o
p
u
lar
im
ag
e
en
h
an
ce
m
e
n
t
tech
n
iq
u
e
th
at
i
m
p
r
o
v
es
lo
ca
l
co
n
tr
ast
b
y
d
i
v
id
in
g
an
im
ag
e
in
to
s
m
aller
r
eg
io
n
s
(
tiles
)
an
d
ap
p
ly
in
g
HE
to
ea
ch
tile
in
d
ep
en
d
en
tly
.
T
h
is
ap
p
r
o
ac
h
en
h
a
n
ce
s
co
n
tr
ast
in
ar
ea
s
with
d
if
f
er
e
n
t
b
r
ig
h
tn
ess
lev
els.
T
o
p
r
ev
en
t
ex
ce
s
s
iv
e
am
p
lific
atio
n
in
u
n
if
o
r
m
r
eg
io
n
s
,
C
L
AHE
u
s
es
a
lim
i
tin
g
m
ec
h
an
is
m
th
at
p
r
eser
v
es
f
in
e
d
e
tails
wh
ile
r
ed
u
cin
g
ar
tifa
cts
[
3
4
]
.
T
h
e
ad
ju
s
ted
g
r
ay
s
ca
le
v
alu
e
r
esu
ltin
g
f
r
o
m
th
e
h
is
to
g
r
am
eq
u
aliza
tio
n
p
r
o
ce
s
s
is
co
m
p
u
ted
u
s
in
g
(
3
)
.
=
(
(
2
−
1
)
ℎ
)
(
3
)
w
h
er
e
d
en
o
tes
th
e
cu
m
u
lativ
e
d
is
tr
ib
u
tio
n
f
u
n
ctio
n
(
C
DF)
o
f
th
e
i
-
th
g
r
ay
s
ca
le
v
alu
e
i
n
th
e
o
r
ig
in
al
im
a
g
e,
k
r
ep
r
esen
ts
th
e
n
u
m
b
e
r
o
f
g
r
ay
s
ca
le
in
ten
s
ity
lev
els,
an
d
w
an
d
h
ar
e
th
e
wid
th
an
d
h
eig
h
t
o
f
t
h
e
im
ag
e,
r
esp
ec
tiv
ely
.
I
n
C
L
AHE
,
two
m
ain
p
ar
am
eter
s
g
o
v
e
r
n
th
e
c
o
n
tr
ast q
u
ality
o
f
th
e
r
esu
ltin
g
im
ag
e:
tile size
an
d
th
e
clip
lim
it.
T
h
e
tile
s
ize
d
ef
in
es
th
e
d
im
e
n
s
io
n
s
o
f
ea
ch
s
u
b
-
r
eg
io
n
,
w
h
ile
th
e
clip
lim
it
r
estricts
th
e
m
ax
im
u
m
s
lo
p
e
o
f
th
e
C
DF to
av
o
id
o
v
er
-
e
n
h
an
ce
m
en
t o
f
n
o
is
e.
T
h
e
clip
lim
it
β
is
d
ef
in
e
d
as
(
4
)
.
=
(
1
+
100
(
−
1
)
)
(
4
)
w
h
er
e
P
is
th
e
tile
ar
ea
,
Q
is
th
e
to
t
al
n
u
m
b
er
o
f
g
r
a
y
s
ca
le
lev
els
(
ty
p
ically
2
5
6
)
,
max
r
ep
r
esen
ts
th
e
m
ax
im
u
m
allo
wab
le
s
lo
p
e
in
th
e
C
DF,
an
d
α
is
th
e
clip
f
ac
to
r
r
an
g
in
g
f
r
o
m
0
to
1
0
0
.
T
h
is
m
ec
h
an
is
m
ef
f
ec
tiv
ely
r
ed
u
ce
s
n
o
is
e
am
p
l
if
icatio
n
an
d
p
r
ev
e
n
ts
th
e
f
o
r
m
atio
n
o
f
a
r
tifa
cts in
th
e
en
h
a
n
ce
d
im
ag
e
[
3
5
]
.
2
.
3
.
Sp
ider
m
o
n
k
ey
o
p
t
i
m
iz
a
t
io
n
T
h
e
SMO
alg
o
r
ith
m
is
a
g
lo
b
al
o
p
tim
izatio
n
m
eth
o
d
in
s
p
ir
ed
b
y
t
h
e
s
o
cial
b
eh
a
v
io
r
o
f
s
p
id
e
r
m
o
n
k
e
y
s
d
u
r
i
n
g
f
o
r
ag
i
n
g
a
n
d
ex
p
lo
r
atio
n
.
SMO
s
ee
k
s
an
o
p
tim
al
s
o
lu
tio
n
to
c
o
m
p
lex
o
p
tim
izatio
n
p
r
o
b
lem
s
b
y
m
im
ic
k
in
g
s
p
id
er
m
o
n
k
ey
s
’
co
llab
o
r
ativ
e
a
n
d
ad
ap
tiv
e
b
eh
av
io
r
s
[
3
6
]
.
I
n
SMO,
ea
c
h
s
p
id
er
m
o
n
k
ey
i
n
a
g
r
o
u
p
is
r
ep
r
esen
ted
as
(
=
1
,
2
,
…
,
)
,
s
er
v
es
as
a
p
o
ten
tial
s
o
lu
tio
n
.
E
ac
h
p
o
s
itio
n
v
ec
to
r
o
f
in
a
D
-
d
im
en
s
io
n
al
s
p
ac
e
r
e
p
r
esen
ts
p
o
s
s
ib
le
s
o
lu
tio
n
s
,
in
itialize
d
u
s
in
g
(
5
)
.
,
=
,
+
(
,
−
,
)
(
5
)
R
is
a
r
an
d
o
m
v
alu
e
b
etwe
e
n
0
an
d
1
,
an
d
an
d
u
p
p
e
r
an
d
lo
wer
b
o
u
n
d
s
ar
e
f
o
r
ea
ch
d
im
en
s
io
n
.
I
n
th
e
L
L
p
h
ase,
e
ac
h
m
o
n
k
ey
'
s
p
o
s
itio
n
is
u
p
d
a
ted
b
ased
o
n
th
e
lo
ca
l le
ad
e
r
'
s
g
u
id
an
ce
as in
(
6
)
.
,
=
,
+
(
,
−
,
)
+
(
,
−
,
)
(
6
)
w
h
er
e
,
is
th
e
lo
ca
l
lead
er
,
r
is
a
r
an
d
o
m
ly
s
elec
ted
g
r
o
u
p
m
em
b
er
,
an
d
U
is
a
u
n
if
o
r
m
r
an
d
o
m
v
ar
iab
le
in
th
e
r
an
g
e
[
-
1
,
1
]
.
I
f
th
e
n
ew
p
o
s
itio
n
im
p
r
o
v
es
th
e
s
o
lu
tio
n
,
it
is
ac
ce
p
te
d
;
o
th
e
r
wis
e,
it
is
d
is
ca
r
d
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Op
timiz
ed
p
a
p
-
s
mea
r
ima
g
e
e
n
h
a
n
ce
men
t
:
h
yb
r
id
P
ero
n
a
-
Ma
lik
d
iffu
s
io
n
filt
er
-
C
LAHE
…
(
A
ch
K
h
o
z
a
imi)
2769
T
h
e
g
lo
b
al
lead
er
s
h
ip
(
GL
)
p
h
ase
u
p
d
ates
p
o
s
itio
n
s
b
ased
o
n
g
lo
b
al
lead
er
,
wh
er
e
th
e
p
r
o
b
ab
ilit
y
is
ca
lcu
la
ted
u
s
in
g
(
7
)
.
=
0
.
9
×
+
0
.
1
(
7
)
w
ith
th
e
h
ig
h
est
-
f
itn
ess
m
o
n
k
ey
s
er
v
in
g
as
th
e
g
lo
b
al
lead
er
.
Af
ter
ea
ch
iter
atio
n
,
lead
er
s
ar
e
u
p
d
ated
th
r
o
u
g
h
g
r
ee
d
y
s
elec
tio
n
in
th
e
L
an
d
GL
p
h
ases
.
T
h
e
lo
ca
l
lead
er
d
ec
is
io
n
(
LLD
)
p
h
ase
p
r
e
v
en
ts
lo
ca
l
lead
er
s
f
r
o
m
s
tag
n
atio
n
b
y
e
n
f
o
r
ci
n
g
r
a
n
d
o
m
p
o
s
itio
n
u
p
d
ates
if
a
th
r
esh
o
ld
(
L
o
ca
lLe
a
d
er
L
im
it)
is
r
ea
ch
ed
.
Similar
ly
,
th
e
g
lo
b
al
lead
e
r
d
ec
is
io
n
(
GL
D
)
p
h
ase
s
p
lits
th
e
g
r
o
u
p
if
th
e
Glo
b
alL
ea
d
er
L
im
it
th
r
esh
o
ld
is
m
et,
th
u
s
en
co
u
r
a
g
in
g
f
u
r
th
e
r
ex
p
l
o
r
atio
n
.
2
.
4
.
I
ma
g
e
qu
a
lity
a
s
s
ess
m
ent
I
QA
is
th
e
p
r
o
ce
s
s
o
f
ass
ess
in
g
o
r
ev
alu
atin
g
th
e
q
u
ality
o
f
a
d
ig
ital
im
ag
e.
T
h
r
ee
I
QA
m
o
d
els
ca
n
b
e
u
s
ed
:
r
ed
u
ce
d
r
ef
er
en
ce
(
R
R
-
I
QA)
,
FR
-
I
QA,
an
d
NR
-
I
QA
[
3
7
]
.
T
h
is
s
tu
d
y
u
s
ed
MSE
,
SS
I
M,
an
d
PS
NR
to
ev
alu
ate
im
ag
e
d
en
o
is
in
g
[
3
8
]
.
C
E
I
Q,
p
r
ac
tical
m
ea
s
u
r
e
o
f
E
ME
,
MC,
R
MS
co
n
tr
ast,
an
d
en
tr
o
p
y
ar
e
also
u
s
ed
to
ev
al
u
ate
im
ag
e
co
n
t
r
ast
en
h
an
ce
m
e
n
t.
E
ME
is
a
p
p
lied
to
q
u
a
n
tify
c
o
n
tr
ast
-
im
ag
e
en
h
an
ce
m
en
t,
p
ar
ticu
lar
ly
f
o
r
lo
ca
l
co
n
tr
as
t.
I
t
was
ca
lc
u
lated
b
y
d
iv
id
in
g
th
e
im
ag
e
in
to
b
lo
c
k
s
a
n
d
c
o
n
s
id
er
in
g
th
e
lo
g
ar
ith
m
ic
r
atio
o
f
th
e
m
ax
im
u
m
an
d
m
in
im
u
m
in
ten
s
ities
with
in
ea
ch
b
lo
c
k
.
=
1
×
∑
∑
20
(
(
,
)
(
,
)
)
=
1
=
1
(
8
)
M
an
d
N
ar
e
th
e
n
u
m
b
er
o
f
b
lo
ck
s
in
th
e
v
er
tical
an
d
h
o
r
izo
n
tal
d
ir
ec
tio
n
s
,
r
esp
ec
tiv
e
ly
.
(
(
,
)
)
an
d
(
(
,
)
)
th
e
m
ax
im
u
m
an
d
m
in
im
u
m
p
ix
el
i
n
ten
s
ities
in
th
e
i
an
d
j
b
lo
ck
o
f
th
e
im
ag
e.
T
h
e
lo
g
a
r
ith
m
ic
ter
m
h
elp
s
m
ea
s
u
r
e
c
o
n
tr
ast e
n
h
an
ce
m
e
n
t
[
3
9
]
.
MC
is
a
s
im
p
le
co
n
tr
ast
m
e
asu
r
e
d
ef
i
n
ed
as
th
e
d
if
f
er
e
n
ce
b
etwe
en
an
im
ag
e'
s
m
ax
im
u
m
a
n
d
m
in
im
u
m
i
n
ten
s
ity
,
d
iv
i
d
ed
b
y
th
eir
s
u
m
(
)
an
d
(
)
ar
e
t
h
e
im
a
g
e'
s
m
ax
im
u
m
an
d
m
in
im
u
m
p
ix
el
in
ten
s
ity
[
3
9
]
.
MC
=
−
+
(
9
)
T
h
e
R
MS
co
n
tr
ast
m
ea
s
u
r
es
t
h
e
o
v
e
r
all
co
n
tr
ast
in
an
im
a
g
e
b
y
ca
lcu
latin
g
t
h
e
s
tan
d
ar
d
d
ev
iatio
n
o
f
p
ix
el
in
ten
s
ities
.
(
,
)
is
th
e
in
ten
s
ity
at
t
h
e
p
ix
el
lo
ca
tio
n
(
,
)
.
̅
is
th
e
m
ea
n
in
ten
s
ity
o
f
th
e
en
tire
im
ag
e
,
an
d
M
an
d
N
ar
e
th
e
im
a
g
e
d
im
e
n
s
io
n
s
.
T
h
e
R
MS
co
n
tr
ast
p
r
o
v
id
e
s
a
s
in
g
le
n
u
m
b
e
r
th
at
r
e
p
r
ese
n
ts
th
e
co
n
tr
ast
in
an
im
ag
e,
c
o
n
s
id
er
in
g
th
e
v
ar
i
ab
ilit
y
in
in
ten
s
ity
v
alu
es
[
3
9
]
.
=
√
1
∑
∑
(
(
,
)
−
̅
)
2
−
=
(
1
0
)
T
h
e
en
tr
o
p
y
m
ea
s
u
r
es
th
e
a
m
o
u
n
t
o
f
in
f
o
r
m
ati
o
n
o
r
r
a
n
d
o
m
n
ess
in
a
n
im
ag
e.
I
t
is
o
f
ten
u
s
ed
t
o
ass
es
s
tex
tu
r
e
o
r
co
m
p
lex
ity
.
=
∑
2
(
)
−
1
=
0
(
1
1
)
L
is
th
e
to
tal
n
u
m
b
er
o
f
p
o
s
s
ib
le
in
ten
s
ity
lev
els.
is
th
e
p
r
o
b
ab
ilit
y
(
n
o
r
m
alize
d
h
is
to
g
r
am
)
o
f
th
e
o
cc
u
r
r
e
n
ce
o
f
in
ten
s
ity
lev
el
(
)
.
T
h
e
en
tr
o
p
y
v
alu
es
r
an
g
e
f
r
o
m
0
to
l
og
2
(
)
,
with
h
ig
h
er
v
al
u
es
in
d
icatin
g
m
o
r
e
co
m
p
lex
ity
an
d
r
a
n
d
o
m
n
ess
in
th
e
im
ag
e
[
1
6
]
.
T
h
e
co
e
f
f
icien
t
o
f
c
o
r
r
elatio
n
(
C
o
C
)
m
ea
s
u
r
es
th
e
c
o
r
r
elatio
n
b
etwe
en
p
ix
el
in
ten
s
ities
in
an
o
r
i
g
in
al
im
ag
e
an
d
a
p
r
o
ce
s
s
ed
im
ag
e
.
A
h
ig
h
co
r
r
elatio
n
in
d
icate
s
th
at
th
e
p
r
o
ce
s
s
ed
im
ag
e
r
etain
s
th
e
s
tr
u
ctu
r
al
in
f
o
r
m
atio
n
o
f
th
e
o
r
ig
in
al.
C
o
C
d
eter
m
in
es
h
o
w
well
im
ag
e
en
h
an
ce
m
e
n
t
p
r
eser
v
es
th
e
o
r
ig
in
al
s
tr
u
ctu
r
al
d
etails
as in
(
1
2
)
.
=
∑
(
−
μ
x
)
(
−
μ
y
)
√
∑
(
−
μ
x
)
2
(
−
μ
y
)
2
(
1
2
)
I
x
an
d
I
y
ar
e
p
ix
el
in
ten
s
ities
in
th
e
o
r
ig
in
al
a
n
d
en
h
an
ce
d
im
ag
es.
μ
x
an
d
μ
y
ar
e
m
ea
n
i
n
te
n
s
ities
o
f
th
e
o
r
ig
in
al
an
d
en
h
a
n
ce
d
im
a
g
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t
20
25
:
2
7
6
5
-
2
7
7
5
2770
Stan
d
ar
d
d
ev
iatio
n
(
Std
-
d
e
v
)
m
ea
s
u
r
es
th
e
s
p
r
ea
d
o
f
in
ten
s
i
ty
v
alu
es
ar
o
u
n
d
th
e
m
ea
n
,
r
ef
lectin
g
th
e
co
n
tr
ast v
ar
iab
ilit
y
in
t
h
e
im
ag
e.
Std
-
d
ev
q
u
an
tif
y
in
ten
s
ity
v
ar
iatio
n
an
d
c
o
n
tr
ast.
−
=
√
1
∑
(
−
μ
)
2
=
1
(
1
3
)
N
is
th
e
to
tal
p
ix
els in
th
e
im
ag
e.
I
i
is
th
e
in
ten
s
ity
o
f
th
e
i
-
th
p
ix
el.
μ
is
th
e
m
ea
n
in
ten
s
ity
o
f
th
e
im
ag
e
.
2
.
5
.
Co
ntr
a
s
t
enha
ncem
ent
-
ba
s
ed
im
a
g
e
qu
a
lity
C
E
I
Q
is
an
im
a
g
e
q
u
ality
ass
ess
m
en
t
tech
n
iq
u
e
th
at
le
v
er
a
g
es
co
n
tr
ast
e
n
h
an
ce
m
en
t
f
o
r
ev
alu
atio
n
[
2
6
]
.
T
h
is
m
eth
o
d
em
p
lo
y
s
h
is
to
g
r
am
eq
u
aliza
tio
n
to
a
n
aly
ze
an
d
q
u
an
tif
y
im
ag
e
co
n
tr
ast.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
d
i
v
id
in
g
th
e
im
a
g
e
h
is
to
g
r
am
in
to
m
u
ltip
le
b
in
s
an
d
ca
lcu
latin
g
th
e
a
v
er
ag
e
in
te
n
s
ity
v
alu
e
f
o
r
ea
ch
b
in
.
Su
b
s
eq
u
en
tly
,
th
ese
av
er
a
g
e
v
al
u
es
ass
ig
n
n
ew
in
ten
s
ity
v
alu
es
t
o
p
ix
els
with
in
ea
ch
co
r
r
esp
o
n
d
in
g
b
in
.
Fig
u
r
e
2
s
h
o
ws
th
e
C
E
I
Q
ev
al
u
atio
n
m
o
d
el.
C
E
I
Q
h
as two
a
s
p
ec
ts
o
f
im
ag
e
q
u
ality
ass
ess
m
en
t
:
‒
T
h
e
im
ag
e
s
im
ilar
ity
m
ea
s
u
r
es
th
e
s
im
ilar
ity
o
f
th
e
o
r
i
g
in
al
im
ag
e
to
th
at
o
f
th
e
co
n
tr
ast
-
en
h
an
ce
d
im
ag
e.
T
h
e
i
m
a
g
e
s
im
ilar
ity
was SSI
M.
‒
His
to
g
r
am
en
tr
o
p
y
an
d
cr
o
s
s
-
en
tr
o
p
y
m
ea
s
u
r
e
an
ev
en
d
is
tr
ib
u
tio
n
o
f
t
h
e
im
ag
e
h
is
to
g
r
a
m
.
T
h
e
en
tr
o
p
y
(E)
eq
u
atio
n
is
d
ef
in
ed
as
(
1
1
)
.
C
r
o
s
s
-
en
tr
o
p
y
(
E
xy
)
ca
n
b
e
p
er
f
o
r
m
ed
u
s
in
g
th
e
h
is
to
g
r
a
m
eq
u
aliza
tio
n
m
eth
o
d
.
T
h
e
cr
o
s
s
-
en
tr
o
p
y
v
al
u
es we
r
e
ca
lcu
lated
u
s
in
g
(
1
4
)
.
,
=
−
∑
ℎ
(
)
=
0
ℎ
(
)
(
1
4
)
h
x
is
th
e
h
is
to
g
r
am
o
f
th
e
o
r
ig
i
n
al
im
ag
e
an
d
h
y
th
e
h
is
to
g
r
a
m
o
f
th
e
c
o
n
tr
ast
-
en
h
an
ce
d
im
ag
e.
Fig
u
r
e
2
.
C
E
I
Q
ev
alu
atio
n
m
o
d
el
2
.
6
.
B
lin
d/ref
er
ence
-
less
im
a
g
e
s
pa
t
ia
l qua
lity
ev
a
lua
t
o
r
B
R
I
SQ
UE
is
a
m
o
d
el
th
at
ca
l
cu
lates
f
ea
tu
r
es
d
ir
ec
tly
f
r
o
m
im
ag
e
p
ix
els,
u
n
lik
e
o
th
e
r
m
e
th
o
d
s
th
at
r
ely
o
n
tr
an
s
f
o
r
m
atio
n
s
to
d
if
f
er
en
t
s
p
ac
es,
s
u
c
h
as
wav
elets
o
r
d
is
cr
ete
co
s
in
e
t
r
an
s
f
o
r
m
atio
n
s
(
DC
T
)
.
I
ts
ef
f
icien
cy
d
o
es
n
o
t
r
eq
u
ir
e
th
ese
tr
an
s
f
o
r
m
atio
n
s
to
e
x
tr
a
ct
f
ea
tu
r
es.
B
R
I
SQUE
ass
e
s
s
e
s
th
e
im
ag
e
q
u
ality
b
y
c
o
m
p
ar
in
g
t
h
e
in
p
u
t
im
a
g
e
to
a
m
o
d
el
t
r
ain
ed
o
n
im
ag
es
with
s
im
ilar
d
is
to
r
tio
n
s
.
I
t
is
tr
ain
e
d
o
n
a
d
atab
ase
o
f
n
atu
r
al
s
ce
n
e
im
a
g
es
with
k
n
o
wn
d
is
to
r
tio
n
s
a
n
d
in
co
r
p
o
r
ates
s
u
b
jectiv
e
q
u
ali
ty
s
co
r
es,
m
ak
in
g
it
o
p
in
io
n
-
awa
r
e.
L
o
we
r
B
R
I
SQ
UE
v
alu
es in
d
icate
b
etter
p
er
c
ep
tu
al
im
ag
e
q
u
ality
[
2
5
]
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
th
e
p
er
f
o
r
m
an
ce
r
esu
lts
o
f
th
e
SMO
-
PMD
f
ilter
,
SMO
-
C
L
AHE
,
a
n
d
h
y
b
r
id
o
p
tim
izatio
n
o
f
th
e
PMD
f
ilter
an
d
C
L
AHE
wi
th
SMO,
r
ef
er
r
ed
to
as SMO
-
PM
D
-
C
L
AHE
.
E
ac
h
m
eth
o
d
was
s
p
ec
if
ically
o
p
tim
ized
to
im
p
r
o
v
e
im
a
g
e
-
q
u
ality
m
etr
ics
f
o
r
ef
f
ec
tiv
e
n
o
is
e
r
ed
u
ctio
n
,
im
p
r
o
v
ed
co
n
t
r
ast,
an
d
en
h
an
c
ed
im
ag
e
clar
ity
.
3
.
1
.
Sp
ider
m
o
n
k
ey
o
pti
m
iz
a
t
io
n
-
P
er
o
na
-
M
a
lik
diff
us
io
n f
ilte
r
T
ab
le
1
s
h
o
ws
th
e
PMD
f
ilte
r
o
p
tim
izatio
n
s
im
u
latio
n
r
es
u
lts
u
s
in
g
PS
O
an
d
SMO
o
n
ten
im
ag
es
f
r
o
m
SIPaK
Me
D.
Ov
er
all,
th
e
SMO
o
p
tim
izer
d
em
o
n
s
tr
ated
s
u
p
er
io
r
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
s
ev
er
al
k
ey
m
etr
ics
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Op
timiz
ed
p
a
p
-
s
mea
r
ima
g
e
e
n
h
a
n
ce
men
t
:
h
yb
r
id
P
ero
n
a
-
Ma
lik
d
iffu
s
io
n
filt
er
-
C
LAHE
…
(
A
ch
K
h
o
z
a
imi)
2771
co
m
p
ar
ed
with
th
e
PS
O
o
p
t
im
izer
.
R
eg
ar
d
in
g
MSE
,
S
MO
ac
h
iev
ed
a
lo
wer
a
v
er
a
g
e
er
r
o
r
o
f
0
.
0
4
5
6
co
m
p
ar
ed
with
0
.
0
5
7
2
f
o
r
PS
O,
in
d
icatin
g
th
at
SMO
is
m
o
r
e
ef
f
ec
tiv
e
in
o
p
tim
izin
g
th
e
PMD
f
ilter
an
d
m
in
im
izin
g
th
e
er
r
o
r
b
etwe
en
th
e
o
r
ig
in
a
l
an
d
d
en
o
is
ed
im
ag
es.
Similar
ly
,
SS
I
M
is
s
lig
h
tly
h
ig
h
er
f
o
r
SMO
(
0
.
9
9
8
4
co
m
p
ar
ed
to
0
.
9
9
8
1
f
o
r
PS
O)
,
s
u
g
g
esti
n
g
th
at
SMO
p
r
o
d
u
ce
s
im
ag
es
with
s
t
r
u
ctu
r
al
q
u
ality
th
at
clo
s
ely
r
esem
b
le
th
e
o
r
i
g
in
al
i
m
ag
es.
R
eg
ar
d
in
g
PS
NR
,
SMO
ag
ain
o
u
tp
er
f
o
r
m
s
PS
O
in
o
p
tim
izin
g
th
e
PMD
f
ilter
,
with
an
av
e
r
ag
e
o
f
6
2
.
2
6
d
B
,
in
d
icatin
g
th
at
SMO
y
ield
s
im
ag
es
with
less
n
o
is
e,
wh
er
ea
s
PS
O’
s
av
er
ag
e
is
6
1
.
0
0
d
B
.
B
o
th
m
eth
o
d
s
ex
h
ib
ited
n
ea
r
l
y
id
en
tical
en
tr
o
p
y
v
alu
es,
in
d
icatin
g
th
at
th
e
in
f
o
r
m
atio
n
al
co
n
ten
t
an
d
d
e
tails
wi
th
in
th
e
im
ag
es
wer
e
well
-
p
r
eser
v
ed
in
b
o
th
ca
s
es.
I
n
th
e
B
R
I
S
QUE
s
co
r
e
as
an
o
b
jectiv
e
f
u
n
cti
o
n
,
SMO
p
r
o
d
u
ce
s
a
s
lig
h
tly
lo
wer
v
alu
e
(
3
6
.
8
5
6
1
)
th
a
n
PS
O
(
3
7
.
3
0
7
3
)
,
s
ig
n
if
y
in
g
th
at
SMO
p
r
o
v
id
es
a
m
ar
g
in
ally
b
etter
s
u
b
jectiv
e
v
is
u
al
q
u
ality
.
T
ab
le
1
.
R
esu
lt si
m
u
l
atio
n
in
o
p
tim
izin
g
PMD
f
ilter
u
s
in
g
P
SO a
n
d
SMO
I
mag
e
s
M
e
t
h
o
d
s
M
S
E
S
S
I
M
P
S
N
R
En
t
r
o
p
y
B
R
I
S
Q
U
E
0
1
3
_
0
2
PSO
0
.
0
4
3
9
4
7
6
4
5
0
.
9
9
6
2
5
8
4
3
9
6
1
.
7
0
1
4
4
7
5
6
4
.
5
7
1
8
4
3
1
3
1
0
.
6
8
6
6
9
8
7
7
5
S
M
O
0
.
0
4
3
3
8
9
4
5
5
0
.
9
9
6
3
0
5
8
9
8
6
1
.
7
5
6
9
6
1
6
3
4
.
5
7
1
8
5
7
2
8
8
0
.
6
4
4
8
3
8
0
2
4
0
1
8
_
0
3
PSO
0
.
0
5
8
3
8
3
5
9
9
0
.
9
9
8
4
9
2
2
7
5
6
0
.
4
6
7
8
9
4
9
9
5
.
3
1
1
1
0
7
0
2
8
5
9
.
5
6
5
5
6
0
3
1
S
M
O
0
.
0
2
5
0
3
1
8
6
6
0
.
9
9
9
3
1
8
2
7
2
6
4
.
1
4
5
8
7
1
3
4
5
.
3
1
1
2
3
4
3
2
6
5
7
.
9
5
7
2
2
1
4
5
0
1
9
_
0
1
PSO
0
.
1
2
6
3
8
9
1
6
5
0
.
9
9
6
2
5
0
4
3
4
5
7
.
1
1
3
7
0
5
1
8
5
.
4
9
8
2
9
7
9
2
8
5
4
.
4
6
5
7
4
5
2
4
S
M
O
0
.
1
2
6
7
8
5
3
9
2
0
.
9
9
6
2
2
9
5
6
7
5
7
.
1
0
0
1
1
1
4
5
5
.
4
9
8
2
8
6
5
8
8
5
4
.
3
0
5
2
1
2
1
3
0
2
0
_
0
6
PSO
0
.
0
7
1
5
9
2
7
7
4
0
.
9
9
7
5
1
9
7
5
3
5
9
.
5
8
2
1
1
1
6
8
4
.
9
1
8
4
5
7
3
5
2
1
6
.
1
6
0
9
4
1
8
9
S
M
O
0
.
0
7
1
4
4
6
8
6
5
0
.
9
9
7
5
2
7
5
5
5
9
.
5
9
0
9
7
1
8
7
4
.
9
1
8
4
4
4
5
9
6
1
6
.
1
4
6
9
7
5
6
8
0
2
3
_
0
1
PSO
0
.
0
5
3
8
8
2
4
7
1
0
.
9
9
8
7
9
7
8
0
8
6
0
.
8
1
6
3
2
8
5
8
5
.
7
0
5
4
3
2
8
9
5
8
2
.
8
7
2
6
7
0
4
7
S
M
O
0
.
0
4
4
8
3
2
7
3
0
.
9
9
8
9
8
3
6
4
7
6
1
.
6
1
4
8
5
1
7
8
5
.
7
0
5
4
9
0
0
0
5
8
2
.
2
8
3
4
9
8
2
3
0
2
9
_
0
1
PSO
0
.
0
2
7
9
4
4
3
5
9
0
.
9
9
9
2
8
3
5
4
9
6
3
.
6
6
7
8
6
2
1
3
5
.
7
7
0
4
8
0
6
8
3
3
8
.
1
6
0
8
1
0
1
9
S
M
O
0
.
0
2
6
2
3
7
6
6
1
0
.
9
9
9
3
2
7
6
8
2
6
3
.
9
4
1
5
5
2
4
7
5
.
7
7
0
4
8
3
5
6
8
3
8
.
0
9
6
2
0
7
8
3
0
3
9
_
0
1
PSO
0
.
0
3
5
3
0
5
2
3
1
0
.
9
9
8
5
9
6
6
5
6
2
.
6
5
2
4
1
3
0
1
5
.
4
3
0
6
6
1
3
9
1
3
3
.
7
9
1
1
5
1
1
2
S
M
O
0
.
0
1
9
0
0
0
4
1
7
0
.
9
9
9
2
4
2
8
1
8
6
5
.
3
4
3
1
7
2
2
8
5
.
4
3
0
6
3
1
5
3
4
3
3
.
0
4
4
5
4
1
8
1
0
4
3
_
0
1
PSO
0
.
0
7
1
3
5
5
0
1
5
0
.
9
9
8
4
2
5
3
8
5
5
9
.
5
9
6
5
5
8
5
9
5
.
9
6
0
7
7
5
2
3
9
4
9
.
3
4
3
8
4
2
9
9
S
M
O
0
.
0
3
9
9
0
4
7
7
9
0
.
9
9
9
0
9
4
2
0
2
6
2
.
1
2
0
5
5
4
5
1
5
.
9
6
1
4
6
0
5
5
4
8
.
2
0
3
7
4
5
6
9
0
4
8
_
0
1
PSO
0
.
0
5
6
7
3
0
4
9
7
0
.
9
9
9
2
3
0
1
2
5
6
0
.
5
9
2
6
3
7
7
6
6
.
3
1
6
7
8
7
8
0
2
3
4
.
8
9
8
8
2
0
1
2
S
M
O
0
.
0
3
5
7
4
6
3
2
6
0
.
9
9
9
5
2
3
0
8
7
6
2
.
5
9
8
4
8
9
4
9
6
.
3
1
6
8
7
3
7
5
2
3
4
.
8
5
0
2
8
1
9
1
0
5
0
_
0
6
PSO
0
.
0
2
6
8
6
8
8
1
1
0
.
9
9
8
1
9
8
1
4
2
6
3
.
8
3
8
3
1
9
0
7
4
.
7
6
6
5
7
8
4
4
9
3
.
1
2
6
5
6
6
9
4
2
S
M
O
0
.
0
2
3
8
2
4
1
8
2
0
.
9
9
8
4
0
4
5
1
4
6
4
.
3
6
0
6
2
3
5
5
4
.
7
6
6
5
5
3
0
6
7
3
.
0
2
8
7
0
2
5
0
3
A
v
e
r
a
g
e
PSO
0
.
0
5
7
2
3
9
9
5
7
0
.
9
9
8
1
0
5
2
5
6
6
1
.
0
0
2
9
2
7
8
6
5
.
4
2
5
0
4
2
1
9
3
7
.
3
0
7
2
8
0
8
S
M
O
0
.
0
4
5
6
1
9
9
6
7
0
.
9
9
8
3
9
5
7
2
4
6
2
.
2
5
7
3
1
6
0
4
5
.
4
2
5
1
3
1
5
2
7
3
6
.
8
5
6
1
2
2
5
3
T
h
ese
r
esu
lts
s
u
g
g
est
th
at
SM
O
g
en
er
ally
d
eliv
er
s
a
b
etter
i
m
ag
e
q
u
ality
th
an
PS
O
wh
en
o
p
tim
izin
g
th
e
PMD
f
ilter
.
SMO
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
PS
O
in
cr
i
tical
m
etr
ics,
s
u
ch
as
MSE
,
SS
I
M,
PS
NR
,
an
d
B
R
I
SQ
UE
.
SMO
-
PMD
f
ilter
o
f
f
er
s
n
ew
in
s
ig
h
t
f
o
r
a
p
p
lica
tio
n
s
r
eq
u
ir
i
n
g
h
ig
h
im
ag
e
p
r
o
ce
s
s
in
g
ac
cu
r
ac
y
.
Alth
o
u
g
h
t
h
e
en
tr
o
p
y
v
alu
es
a
r
e
s
im
ilar
b
etw
ee
n
th
e
two
m
eth
o
d
s
,
SMO’
s
co
n
s
is
ten
t
s
u
p
er
io
r
ity
in
r
ed
u
ci
n
g
er
r
o
r
a
n
d
n
o
is
e.
3
.
2
.
Sp
ider
m
o
n
k
ey
o
pti
m
iz
a
t
io
n
-
co
ntr
a
s
t
-
li
m
it
ed
a
da
pt
iv
e
his
t
o
g
ra
m
equa
liza
t
io
n
T
h
e
s
im
u
latio
n
r
esu
lts
f
o
r
C
L
AHE
o
p
tim
izatio
n
u
s
in
g
th
e
P
OA
an
d
SMO
alg
o
r
ith
m
s
o
n
1
0
im
ag
es
fr
o
m
t
h
e
SIPaK
Me
D
d
ataset
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
T
h
es
e
r
esu
lts
s
h
o
w
r
elativ
ely
s
m
all
d
if
f
er
e
n
ce
s
ac
r
o
s
s
k
ey
m
etr
ics
s
u
ch
as
en
tr
o
p
y
,
E
ME
,
R
MS
co
n
tr
ast,
C
o
C
,
Std
-
d
ev
,
C
E
I
Q,
an
d
p
r
o
ce
s
s
i
n
g
tim
e.
R
eg
ar
d
in
g
en
tr
o
p
y
,
th
e
r
esu
lts
wer
e
alm
o
s
t
id
en
tical
f
o
r
b
o
th
m
eth
o
d
s
ac
r
o
s
s
all
im
ag
es,
s
u
g
g
esti
n
g
th
at
th
e
POA
an
d
SMO
m
ain
tain
ed
s
im
ilar
lev
els
o
f
p
ix
el
in
ten
s
ity
in
f
o
r
m
ati
o
n
.
A
s
im
ilar
tr
en
d
is
o
b
s
er
v
ed
in
th
e
E
ME
an
d
R
MS
co
n
tr
ast
s
,
wh
er
e
th
er
e
is
n
o
s
ig
n
if
ican
t
d
if
f
er
en
ce
b
et
wee
n
th
e
two
m
eth
o
d
s
,
in
d
icatin
g
th
at
b
o
th
h
an
d
le
co
n
tr
ast en
h
an
ce
m
en
t similar
ly
.
On
e
o
f
th
e
p
r
im
a
r
y
d
if
f
er
e
n
ce
s
b
etwe
en
th
e
two
m
eth
o
d
s
is
th
e
p
r
o
ce
s
s
in
g
tim
e.
SMO
c
o
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
ed
POA
in
ter
m
s
o
f
s
p
ee
d
.
T
h
e
av
er
a
g
e
p
r
o
ce
s
s
in
g
tim
e
f
o
r
SMO
was
7
.
5
4
7
0
s
,
co
m
p
ar
ed
with
7
.
7
6
5
0
s
.
T
h
is
h
ig
h
lig
h
ts
th
e
ef
f
icien
cy
o
f
SMO
in
ter
m
s
o
f
co
m
p
u
tatio
n
al
tim
e,
m
ak
i
n
g
it
p
r
ef
er
ab
le
in
s
ce
n
ar
io
s
in
wh
ich
r
ap
i
d
i
m
ag
e
p
r
o
ce
s
s
in
g
is
ess
en
tia
l,
p
ar
ticu
lar
ly
f
o
r
lar
g
e
-
s
ca
le
im
ag
e
d
atasets
.
T
h
e
s
im
u
latio
n
r
esu
lts
p
r
o
v
i
d
e
v
alu
ab
le
in
s
ig
h
ts
in
to
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
POA
an
d
SMO
in
o
p
tim
izin
g
C
L
AHE
o
n
ce
r
v
ical
im
ag
es.
B
o
th
m
eth
o
d
s
s
h
o
wed
c
o
m
p
a
r
ab
le
r
esu
lts
in
m
ain
tain
in
g
th
e
im
ag
e
q
u
ality
,
as
r
ef
lecte
d
in
th
e
n
ea
r
-
id
en
tical
v
alu
es
o
f
en
tr
o
p
y
,
E
ME
,
an
d
R
MS
co
n
tr
ast.
T
h
ese
m
etr
ics
co
n
f
ir
m
th
at
b
o
th
POA
an
d
SMO
ca
n
e
f
f
ec
tiv
ely
en
h
an
ce
th
e
c
o
n
tr
ast
wit
h
o
u
t
s
ig
n
if
ican
t
l
o
s
s
o
f
in
f
o
r
m
atio
n
.
Ho
wev
er
,
f
o
r
p
r
ac
tical
im
p
lem
e
n
tatio
n
,
p
r
o
ce
s
s
in
g
tim
e
is
a
cr
u
ci
al
f
ac
to
r
.
T
h
er
e
f
o
r
e,
SMO
-
C
L
AHE
was
m
o
r
e
ef
f
ec
tiv
e
f
o
r
ce
r
v
ical
ca
n
ce
r
d
etec
tio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t
20
25
:
2
7
6
5
-
2
7
7
5
2772
Fig
u
r
e
3
.
Av
e
r
ag
e
r
esu
lts
o
f
C
L
AHE
o
p
tim
izatio
n
u
s
in
g
PO
A
an
d
SMO
3
.
2
.
1
.
H
y
brid
SM
O
P
M
D
-
C
L
AH
E
T
h
e
av
er
ag
e
r
esu
lts
f
o
r
ea
c
h
ev
alu
atio
n
m
etr
ic
o
n
1
0
ce
r
v
ical
im
ag
es
u
s
in
g
th
e
SMO
-
PMD,
SMO
-
C
L
AHE
,
an
d
h
y
b
r
id
S
MO
PMD
-
C
L
AHE
alg
o
r
ith
m
s
ca
n
b
e
s
ee
n
in
Fig
u
r
e
4
.
T
h
e
m
etr
ics
u
s
ed
in
th
is
ev
alu
atio
n
ar
e
E
ME
,
MC,
R
MS
co
n
tr
ast,
en
tr
o
p
y
,
an
d
C
E
I
Q.
T
h
e
SMO
PMD
m
eth
o
d
ac
h
iev
ed
th
e
lo
west
E
ME
v
alu
e
o
f
1
.
2
3
,
in
d
icati
n
g
lim
ited
ef
f
ec
tiv
en
ess
in
en
h
an
cin
g
illu
m
in
atio
n
q
u
ali
ty
.
SMO
C
L
AH
E
d
em
o
n
s
tr
ated
a
s
ig
n
i
f
ican
t
i
m
p
r
o
v
e
m
en
t
with
an
E
ME
v
alu
e
o
f
3
.
8
5
,
w
h
ile
th
e
co
m
b
in
atio
n
o
f
SMO
PMD
-
C
L
AHE
ac
h
iev
ed
th
e
h
ig
h
est
v
alu
e
o
f
5
.
4
5
.
T
h
is
co
n
f
ir
m
s
th
at
co
m
b
in
in
g
PMD
an
d
C
L
AHE
h
as
a
s
y
n
er
g
is
tic
ef
f
ec
t,
r
esu
ltin
g
i
n
im
ag
es
with
s
u
p
e
r
io
r
illu
m
in
a
tio
n
q
u
ality
.
Fo
r
Mic
h
elso
n
co
n
tr
ast
,
SMO
PMD
an
d
SMO
PMD
-
C
L
AHE
ac
h
i
ev
ed
n
ea
r
ly
o
p
tim
al
v
alu
es
o
f
1
.
0
0
a
n
d
0
.
9
9
,
r
esp
ec
tiv
ely
,
i
n
d
icatin
g
e
x
ce
llen
t
co
n
tr
ast
d
is
tr
ib
u
tio
n
.
On
th
e
o
th
er
h
an
d
,
SMO
C
L
AHE
p
r
o
d
u
ce
d
a
lo
wer
MC
v
alu
e
o
f
0
.
8
5
,
in
d
icatin
g
s
lig
h
tly
r
ed
u
ce
d
co
n
tr
ast co
m
p
ar
ed
to
t
h
e
d
if
f
e
r
en
t m
eth
o
d
s
.
Fig
u
r
e
4
.
T
h
e
av
er
a
g
e
r
esu
lt o
n
PMD,
C
L
AHE
,
an
d
Hy
b
r
id
PMD
-
C
L
AHE
o
p
tim
izatio
n
u
s
in
g
SMO
T
h
e
SMO
PMD
m
eth
o
d
h
ad
th
e
lo
west
R
MS
co
n
tr
ast
v
alu
e
o
f
3
0
.
3
6
,
s
u
g
g
esti
n
g
lim
it
ed
en
h
an
ce
m
e
n
t
ca
p
a
b
ilit
y
.
I
n
co
n
tr
ast,
SMO
C
L
AHE
s
h
o
wed
a
s
ig
n
if
ican
t
im
p
r
o
v
e
m
en
t
wit
h
a
v
alu
e
o
f
5
5
.
8
3
,
wh
ile
SMO
PMD
-
C
L
AHE
ac
h
iev
ed
t
h
e
h
i
g
h
est
v
alu
e
o
f
6
0
.
4
5
.
T
h
is
d
em
o
n
s
tr
ates
th
at
c
o
m
b
in
in
g
PMD
an
d
C
L
AHE
p
r
o
v
id
es
r
ich
er
an
d
m
o
r
e
o
p
tim
al
co
n
tr
ast
in
t
h
e
r
esu
ltin
g
im
ag
es.
T
h
e
en
tr
o
p
y
v
alu
es
r
ef
lect
th
e
d
iv
er
s
ity
o
f
in
f
o
r
m
atio
n
in
th
e
im
ag
es.
SMO
PMD
r
ec
o
r
d
ed
th
e
lo
west
v
alu
e
o
f
5
.
4
2
,
in
d
icatin
g
less
d
etailed
im
ag
es.
SMO
C
L
AHE
ac
h
iev
ed
a
h
i
g
h
er
en
tr
o
p
y
v
alu
e
o
f
6
.
5
9
.
At
th
e
s
am
e
tim
e,
th
e
c
o
m
b
in
atio
n
o
f
SMO
PMD
-
C
L
AHE
ex
ce
lled
with
t
h
e
h
ig
h
est
en
tr
o
p
y
v
alu
e
o
f
6
.
8
0
,
in
d
icatin
g
th
at
th
is
m
eth
o
d
p
r
o
d
u
ce
d
im
ag
es
with
th
e
r
ich
est
in
f
o
r
m
atio
n
d
etails.
R
eg
ar
d
in
g
C
E
I
Q,
SM
O
PMD
h
ad
th
e
l
o
west
v
alu
e
o
f
3
.
3
9
,
in
d
icatin
g
s
u
b
o
p
tim
al
en
h
an
ce
m
en
t
o
f
c
o
n
tr
ast
q
u
ality
.
SM
O
C
L
AHE
ac
h
iev
ed
a
h
ig
h
er
C
E
I
Q
v
alu
e
o
f
3
.
8
7
,
wh
ile
th
e
co
m
b
in
atio
n
o
f
SMO
PMD
-
C
L
AHE
d
eliv
er
ed
th
e
b
est r
esu
lts
with
a
C
E
I
Q
v
alu
e
o
f
3
.
9
7
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
t
h
e
co
m
b
in
atio
n
o
f
SMO
PMD
-
C
L
AHE
d
eliv
er
s
th
e
b
est
p
er
f
o
r
m
a
n
ce
ac
r
o
s
s
alm
o
s
t
all
ev
alu
at
io
n
m
etr
ics.
T
h
is
co
m
b
in
atio
n
ef
f
ec
t
iv
ely
im
p
r
o
v
es
illu
m
in
atio
n
,
c
o
n
tr
ast,
an
d
im
ag
e
in
f
o
r
m
atio
n
d
etails.
I
t
o
u
t
p
er
f
o
r
m
s
b
o
t
h
SMO
PMD
an
d
S
MO
C
L
AHE
wh
en
ap
p
lied
in
d
iv
id
u
ally
.
I
n
m
ed
ical
im
ag
e
an
aly
s
is
,
o
p
tim
al
im
ag
e
q
u
ality
is
cr
u
cial
f
o
r
s
u
p
p
o
r
tin
g
m
o
r
e
a
cc
u
r
ate
d
iag
n
o
s
tic
p
r
o
ce
s
s
es,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Op
timiz
ed
p
a
p
-
s
mea
r
ima
g
e
e
n
h
a
n
ce
men
t
:
h
yb
r
id
P
ero
n
a
-
Ma
lik
d
iffu
s
io
n
filt
er
-
C
LAHE
…
(
A
ch
K
h
o
z
a
imi)
2773
p
ar
ticu
lar
ly
f
o
r
p
a
p
-
s
m
ea
r
i
m
ag
es.
T
h
er
ef
o
r
e,
th
e
SMO
PMD
-
C
L
AHE
co
m
b
in
atio
n
is
r
ec
o
m
m
en
d
e
d
to
en
h
an
ce
o
v
er
all
im
ag
e
q
u
ality
.
T
h
is
ap
p
r
o
ac
h
ca
n
p
o
ten
tiall
y
b
e
ap
p
lied
to
o
th
e
r
s
ce
n
ar
io
s
in
m
ed
ical
im
ag
e
p
r
o
ce
s
s
in
g
,
wh
er
e
im
p
r
o
v
in
g
i
m
ag
e
q
u
ality
p
lay
s
a
v
ital r
o
le
in
s
u
p
p
o
r
tin
g
clin
ical
d
ec
is
io
n
-
m
ak
in
g
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
p
r
esen
ts
a
p
r
ac
tica
l
n
o
is
e
-
r
ed
u
ctio
n
an
d
c
o
n
tr
ast
-
en
h
an
ce
m
e
n
t
f
r
a
m
ewo
r
k
f
o
r
p
ap
-
s
m
ea
r
im
ag
es.
T
h
e
p
r
o
p
o
s
ed
m
eth
o
d
th
o
r
o
u
g
h
ly
e
v
alu
ates
im
ag
e
q
u
ality
im
p
r
o
v
em
e
n
t
b
y
f
o
cu
s
in
g
o
n
clar
ity
,
d
etail
p
r
eser
v
atio
n
,
a
n
d
co
n
t
r
ast
en
h
an
ce
m
en
t.
A
h
y
b
r
id
PMD
-
C
L
AHE
m
eth
o
d
was
o
p
tim
ized
u
s
in
g
th
e
SMO
alg
o
r
ith
m
to
o
v
er
co
m
e
t
h
e
co
m
m
o
n
p
r
o
b
lem
s
o
f
n
o
is
e
an
d
lo
w
co
n
tr
ast
in
th
e
p
ap
-
s
m
ea
r
im
ag
es.
T
h
e
h
y
b
r
id
SMO
-
PMD
-
C
L
A
HE
lev
er
a
g
e
s
th
e
n
o
is
e
r
ed
u
ctio
n
c
ap
ab
ilit
ies
o
f
th
e
PMD
f
ilter
wh
ile
m
ax
im
izin
g
co
n
tr
ast
en
h
an
ce
m
e
n
t
th
r
o
u
g
h
C
L
AHE
.
T
h
e
SMO
alg
o
r
ith
m
co
n
s
is
ten
tly
p
r
o
v
id
es
s
u
p
er
io
r
r
esu
lts
in
o
p
tim
izin
g
th
e
PMD
f
ilter
an
d
C
L
AHE
co
m
p
ar
ed
with
th
e
PS
O
an
d
POA
alg
o
r
ith
m
s
.
B
R
I
SQUE
i
s
i
n
tr
o
d
u
ce
d
as
a
n
ew
o
b
jectiv
e
f
u
n
ctio
n
f
o
r
PMD
f
ilter
o
p
tim
izatio
n
.
B
R
I
SQUE
p
er
f
o
r
m
s
s
ig
n
if
ican
tly
b
etter
th
an
tr
a
d
itio
n
al
m
etr
ics,
s
u
ch
as
PS
NR
an
d
SS
I
M.
S
i
m
i
l
a
r
l
y
,
C
E
I
Q
i
s
u
s
e
d
a
s
a
n
e
w
o
b
j
e
c
t
i
v
e
f
u
n
c
t
i
o
n
f
o
r
C
L
A
H
E
o
p
t
i
m
i
z
a
ti
o
n
.
C
E
I
Q
is
a
c
o
m
p
r
e
h
e
n
s
i
v
e
ass
e
s
s
m
e
n
t
o
f
c
o
n
t
r
a
s
t
e
n
h
a
n
c
e
m
e
n
t
u
s
i
n
g
a
c
o
m
b
i
n
a
t
i
o
n
o
f
e
n
t
r
o
p
y
,
c
r
o
s
s
-
e
n
t
r
o
p
y
,
a
n
d
SS
I
M
.
T
h
e
S
M
O
-
P
M
D
-
C
L
AH
E
h
y
b
r
i
d
ap
p
r
o
a
c
h
a
c
h
i
e
v
e
d
t
h
e
h
i
g
h
e
s
t
p
e
r
f
o
r
m
a
n
c
e
a
c
r
o
s
s
a
l
l
e
v
al
u
a
t
e
d
m
e
t
r
i
cs
c
o
m
p
a
r
e
d
w
i
t
h
SM
O
-
PM
D
o
r
SM
O
-
C
L
A
H
E
.
T
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
,
SM
O
P
M
D
-
C
L
A
H
E
,
s
i
g
n
i
f
i
c
a
n
t
l
y
i
m
p
r
o
v
e
d
t
h
e
p
a
p
-
s
m
e
a
r
i
m
a
g
e
q
u
a
li
t
y
wi
t
h
n
o
i
s
e
r
e
d
u
c
t
i
o
n
a
n
d
c
o
n
t
r
a
s
t
e
n
h
a
n
ce
m
e
n
t
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
f
i
n
an
cially
s
u
p
p
o
r
ted
b
y
th
e
Mi
n
is
tr
y
o
f
Hig
h
er
E
d
u
ca
tio
n
,
Scien
ce
,
an
d
T
ec
h
n
o
lo
g
y
o
f
th
e
R
ep
u
b
lic
o
f
I
n
d
o
n
esia
in
co
llab
o
r
ati
o
n
with
th
e
I
n
d
o
n
esian
E
n
d
o
wm
en
t
Fu
n
d
f
o
r
E
d
u
ca
tio
n
(
L
PDP).
T
h
e
f
u
n
d
i
n
g
was
p
r
o
v
id
e
d
th
r
o
u
g
h
th
e
I
n
d
o
n
esian
E
d
u
ca
tio
n
Sch
o
lar
s
h
ip
(
B
PI)
p
r
o
g
r
am
,
wh
ich
is
ad
m
in
is
ter
ed
b
y
th
e
C
en
ter
f
o
r
Hig
h
e
r
E
d
u
ca
ti
o
n
Fu
n
d
in
g
an
d
Ass
ess
m
en
t
(
PP
APT)
.
B
PI
I
D:
2
0
2
3
2
7
0
9
1
0
3
4
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ach
Kh
o
za
im
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
I
s
n
an
i D
ar
ti
✓
✓
✓
✓
✓
✓
✓
✓
✓
W
u
r
y
an
s
ar
i
Mu
h
a
r
in
i
Ku
s
u
m
awin
ah
y
u
✓
✓
✓
✓
✓
✓
✓
Sy
aif
u
l A
n
am
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
r
e
is
n
o
co
n
f
lict o
f
in
ter
est r
eg
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
a
p
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
SIPaK
Me
D
d
ataset
u
tili
ze
d
in
th
is
s
tu
d
y
is
av
ailab
le
at
h
ttp
s
://b
it.ly
/SIPaKM
e
D
.
RE
F
E
R
E
NC
E
S
[
1
]
G
.
C
u
r
i
g
l
i
a
n
o
e
t
a
l
.
,
“
M
a
n
a
g
e
me
n
t
o
f
c
a
r
d
i
a
c
d
i
s
e
a
s
e
i
n
c
a
n
c
e
r
p
a
t
i
e
n
t
s
t
h
r
o
u
g
h
o
u
t
o
n
c
o
l
o
g
i
c
a
l
t
r
e
a
t
m
e
n
t
:
e
smo
c
o
n
se
n
s
u
s
r
e
c
o
m
me
n
d
a
t
i
o
n
s,
”
A
n
n
a
l
s
o
f
O
n
c
o
l
o
g
y
,
v
o
l
.
3
1
,
n
o
.
2
,
p
p
.
1
7
1
–
1
9
0
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
o
n
c
.
2
0
1
9
.
1
0
.
0
2
3
.
[
2
]
B
.
A
.
T
j
o
k
r
o
p
r
a
w
i
r
o
,
K
.
N
o
v
i
t
a
sari
,
W
.
S
a
r
a
sw
a
t
i
,
I
.
Y
u
l
i
a
t
i
,
R
.
A
.
U
l
h
a
q
,
a
n
d
H
.
A
.
S
u
l
i
s
t
y
a
,
“
T
h
e
c
h
a
l
l
e
n
g
i
n
g
j
o
u
r
n
e
y
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
a
n
d
t
r
e
a
t
m
e
n
t
a
t
t
h
e
se
c
o
n
d
l
a
r
g
e
st
h
o
s
p
i
t
a
l
i
n
i
n
d
o
n
e
s
i
a
,
”
G
y
n
e
c
o
l
o
g
i
c
O
n
c
o
l
o
g
y
Re
p
o
rt
s
,
v
o
l
.
5
1
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
g
o
r
e
.
2
0
2
4
.
1
0
1
3
2
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2252
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
14
,
No
.
4
,
Au
g
u
s
t
20
25
:
2
7
6
5
-
2
7
7
5
2774
[
3
]
D
.
S
a
mb
y
a
l
a
n
d
A
.
S
a
r
w
a
r
,
“
R
e
c
e
n
t
d
e
v
e
l
o
p
me
n
t
s
i
n
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
a
g
n
o
s
i
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
o
n
w
h
o
l
e
sl
i
d
e
i
ma
g
e
s
:
a
n
o
v
e
r
v
i
e
w
o
f
mo
d
e
l
s,
t
e
c
h
n
i
q
u
e
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
f
u
t
u
r
e
d
i
r
e
c
t
i
o
n
s,”
M
i
c
r
o
n
,
v
o
l
.
1
7
3
,
O
c
t
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
mi
c
r
o
n
.
2
0
2
3
.
1
0
3
5
2
0
.
[
4
]
A
.
D
.
Ji
a
,
B
.
Zh
e
n
g
y
i
L
i
,
a
n
d
C
.
C
.
Z
h
a
n
g
,
“
D
e
t
e
c
t
i
o
n
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
c
e
l
l
s
b
a
s
e
d
o
n
s
t
r
o
n
g
f
e
a
t
u
r
e
C
N
N
-
S
V
M
n
e
t
w
o
r
k
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
4
1
1
,
p
p
.
1
1
2
–
1
2
7
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
2
0
.
0
6
.
0
0
6
.
[
5
]
L.
A
l
l
a
h
q
o
l
i
e
t
a
l
.
,
“
D
i
a
g
n
o
s
i
s
o
f
c
e
r
v
i
c
a
l
c
a
n
c
e
r
a
n
d
p
r
e
-
c
a
n
c
e
r
o
u
s
l
e
s
i
o
n
s
b
y
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
:
a
s
y
s
t
e
mat
i
c
r
e
v
i
e
w
,
”
D
i
a
g
n
o
s
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
1
1
,
N
o
v
.
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
d
i
a
g
n
o
s
t
i
c
s1
2
1
1
2
7
7
1
.
[
6
]
M
.
Z
h
a
o
e
t
a
l
.
,
“
S
EEN
S
:
n
u
c
l
e
i
s
e
g
me
n
t
a
t
i
o
n
i
n
p
a
p
sm
e
a
r
i
ma
g
e
s
w
i
t
h
s
e
l
e
c
t
i
v
e
e
d
g
e
e
n
h
a
n
c
e
me
n
t
,
”
Fu
t
u
r
e
G
e
n
e
r
a
t
i
o
n
C
o
m
p
u
t
e
r
S
y
st
e
m
s
,
v
o
l
.
1
1
4
,
p
p
.
1
8
5
–
1
9
4
,
Ja
n
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
f
u
t
u
r
e
.
2
0
2
0
.
0
7
.
0
4
5
.
[
7
]
V
.
K
a
ma
l
a
v
e
n
i
,
R
.
A
.
R
a
j
a
l
a
k
s
h
m
i
,
a
n
d
K
.
A
.
N
a
r
a
y
a
n
a
n
k
u
t
t
y
,
“
I
mag
e
d
e
n
o
i
s
i
n
g
u
si
n
g
v
a
r
i
a
t
i
o
n
s
o
f
P
e
r
o
n
a
-
M
a
l
i
k
m
o
d
e
l
w
i
t
h
d
i
f
f
e
r
e
n
t
e
d
g
e
s
t
o
p
p
i
n
g
f
u
n
c
t
i
o
n
s,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
5
8
,
p
p
.
6
7
3
–
6
8
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
5
.
0
8
.
0
8
7
.
[
8
]
S
.
A
n
a
m,
Z.
F
i
t
r
i
a
h
,
a
n
d
N
.
S
h
o
f
i
a
n
a
h
,
“
H
y
b
r
i
d
o
f
t
h
e
P
M
D
f
i
l
t
e
r
,
t
h
e
k
-
mea
n
s
c
l
u
st
e
r
i
n
g
met
h
o
d
a
n
d
t
h
e
l
e
v
e
l
s
e
t
me
t
h
o
d
f
o
r
e
x
u
d
a
t
e
s
se
g
me
n
t
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ma
t
h
e
m
a
t
i
c
s
a
n
d
I
s
l
a
m
,
S
C
I
TEPRE
S
S
-
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
P
u
b
l
i
c
a
t
i
o
n
s
,
2
0
1
8
,
p
p
.
1
0
8
–
1
1
6
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
8
5
1
7
9
0
1
0
8
0
1
1
6
.
[
9
]
S
.
V
.
Ez
h
i
l
r
a
m
a
n
a
,
“
B
i
l
a
t
e
r
a
l
P
e
r
o
n
a
-
M
a
l
i
k
d
i
f
f
u
s
i
o
n
f
i
l
t
e
r
i
n
g
b
a
se
d
t
o
p
o
l
o
g
i
c
a
l
m
u
l
t
i
t
u
d
e
f
e
a
t
u
r
e
v
e
c
t
o
r
f
o
r
b
r
e
a
st
c
a
n
c
e
r
d
e
t
e
c
t
i
o
n
,
”
J
o
u
rn
a
l
o
f
R
e
se
a
rc
h
o
n
t
h
e
L
e
p
i
d
o
p
t
e
r
a
,
v
o
l
.
5
1
,
n
o
.
1
,
p
p
.
1
1
0
–
1
2
8
,
F
e
b
.
2
0
2
0
,
d
o
i
:
1
0
.
3
6
8
7
2
/
LEPI
/
V
5
1
I
1
/
3
0
1
0
1
0
.
[
1
0
]
M
.
M
.
R
a
h
a
ma
n
e
t
a
l
.
,
“
A
su
r
v
e
y
f
o
r
c
e
r
v
i
c
a
l
c
y
t
o
p
a
t
h
o
l
o
g
y
i
ma
g
e
a
n
a
l
y
si
s
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
,
”
I
EE
E
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
6
1
6
8
7
–
6
1
7
1
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
8
3
1
8
6
.
[
1
1
]
C
.
Ts
i
o
t
si
o
s
a
n
d
M
.
P
e
t
r
o
u
,
“
O
n
t
h
e
c
h
o
i
c
e
o
f
t
h
e
p
a
r
a
me
t
e
r
s
f
o
r
a
n
i
s
o
t
r
o
p
i
c
d
i
f
f
u
si
o
n
i
n
i
m
a
g
e
p
r
o
c
e
ssi
n
g
,
”
Pa
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
,
v
o
l
.
4
6
,
n
o
.
5
,
p
p
.
1
3
6
9
–
1
3
8
1
,
M
a
y
2
0
1
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
1
2
.
1
1
.
0
1
2
.
[
1
2
]
A
.
Jee
l
a
n
i
a
n
d
M
.
B
.
V
e
e
n
a
,
“
H
y
b
r
i
d
i
z
a
t
i
o
n
o
f
P
S
O
a
n
d
a
n
i
s
o
t
r
o
p
i
c
d
i
f
f
u
si
o
n
i
n
d
e
n
o
i
s
i
n
g
t
h
e
i
m
a
g
e
s,
”
i
n
Mi
c
r
o
e
l
e
c
t
r
o
n
i
c
s,
El
e
c
t
r
o
m
a
g
n
e
t
i
c
s
a
n
d
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
,
S
p
r
i
n
g
e
r
,
S
i
n
g
a
p
o
r
e
,
2
0
1
8
,
p
p
.
4
6
3
–
473
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
10
-
7
3
2
9
-
8
_
4
7
.
[
1
3
]
E.
A
.
T
j
o
a
,
I
.
P
.
Y
.
N
.
S
u
p
a
r
t
a
,
R
.
M
a
g
d
a
l
e
n
a
,
a
n
d
N
.
K
.
C
P
,
“
T
h
e
u
s
e
o
f
c
l
a
h
e
f
o
r
i
mp
r
o
v
i
n
g
a
n
a
c
c
u
r
a
c
y
o
f
C
N
N
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
d
e
t
e
c
t
i
n
g
p
n
e
u
mo
n
i
a
,
”
S
H
S
We
b
o
f
C
o
n
f
e
r
e
n
c
e
s
,
v
o
l
.
1
3
9
,
M
a
y
2
0
2
2
,
d
o
i
:
1
0
.
1
0
5
1
/
s
h
sc
o
n
f
/
2
0
2
2
1
3
9
0
3
0
2
6
.
[
1
4
]
M
.
H
a
y
a
t
i
e
t
a
l
.
,
“
I
mp
a
c
t
o
f
C
LA
H
E
-
b
a
s
e
d
i
ma
g
e
e
n
h
a
n
c
e
m
e
n
t
f
o
r
d
i
a
b
e
t
i
c
r
e
t
i
n
o
p
a
t
h
y
c
l
a
ssi
f
i
c
a
t
i
o
n
t
h
r
o
u
g
h
d
e
e
p
l
e
a
r
n
i
n
g
,
”
Pro
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
1
6
,
p
p
.
5
7
–
6
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s
.
2
0
2
2
.
1
2
.
1
1
1
.
[
1
5
]
A
.
D
e
s
i
a
n
i
,
Er
w
i
n
,
B
.
S
u
p
r
i
h
a
t
i
n
,
S
.
Y
a
h
d
i
n
,
A
.
I
.
P
u
t
r
i
,
a
n
d
F
.
R
.
H
u
s
e
i
n
,
“
B
i
-
p
a
t
h
a
r
c
h
i
t
e
c
t
u
r
e
o
f
C
N
N
s
e
g
m
e
n
t
a
t
i
o
n
a
n
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
m
e
t
h
o
d
f
o
r
c
e
r
v
i
c
a
l
c
a
n
c
e
r
d
i
s
o
r
d
e
r
s
b
a
se
d
o
n
p
a
p
-
sme
a
r
i
ma
g
e
s,
”
I
AE
N
G
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
8
,
n
o
.
3
,
2
0
2
1
.
[
1
6
]
H
.
M
.
Q
a
s
si
m,
N
.
M
.
B
a
s
h
e
e
r
,
a
n
d
M
.
N
.
F
a
r
h
a
n
,
“
B
r
i
g
h
t
n
e
ss
p
r
e
s
e
r
v
i
n
g
e
n
h
a
n
c
e
me
n
t
f
o
r
d
e
n
t
a
l
d
i
g
i
t
a
l
x
-
r
a
y
i
ma
g
e
s
b
a
se
d
o
n
e
n
t
r
o
p
y
a
n
d
h
i
st
o
g
r
a
m
a
n
a
l
y
s
i
s,”
J
o
u
r
n
a
l
o
f
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
1
,
p
p
.
1
8
7
–
1
9
4
,
2
0
1
9
,
d
o
i
:
1
0
.
6
1
8
0
/
j
a
se.
2
0
1
9
0
3
_
2
2
(
1
)
.
0
0
1
9
.
[
1
7
]
L.
G
.
M
o
r
e
,
M
.
A
.
B
r
i
z
u
e
l
a
,
H
.
L.
A
y
a
l
a
,
D
.
P
.
P
i
n
t
o
-
R
o
a
,
a
n
d
J.
L
.
V
.
N
o
g
u
e
r
a
,
“
P
a
r
a
m
e
t
e
r
t
u
n
i
n
g
o
f
C
LA
H
E
b
a
se
d
o
n
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
o
p
t
i
m
i
z
a
t
i
o
n
t
o
a
c
h
i
e
v
e
d
i
f
f
e
r
e
n
t
c
o
n
t
r
a
st
l
e
v
e
l
s
i
n
me
d
i
c
a
l
i
m
a
g
e
s,”
i
n
2
0
1
5
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
m
a
g
e
Pro
c
e
ssi
n
g
(
I
C
I
P)
,
I
EEE,
S
e
p
.
2
0
1
5
,
p
p
.
4
6
4
4
–
4
6
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
P
.
2
0
1
5
.
7
3
5
1
6
8
7
.
[
1
8
]
A
.
F
a
w
z
i
,
A
.
A
c
h
u
t
h
a
n
,
a
n
d
B
.
B
e
l
a
t
o
n
,
“
A
d
a
p
t
i
v
e
c
l
i
p
l
i
mi
t
t
i
l
e
si
z
e
h
i
st
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
f
o
r
n
o
n
-
h
o
m
o
g
e
n
i
z
e
d
i
n
t
e
n
s
i
t
y
i
ma
g
e
s,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
6
4
4
6
6
–
1
6
4
4
9
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
3
4
1
7
0
.
[
1
9
]
U
.
K
u
r
a
n
a
n
d
E.
C
.
K
u
r
a
n
,
“
P
a
r
a
m
e
t
e
r
s
e
l
e
c
t
i
o
n
f
o
r
c
l
a
h
e
u
si
n
g
m
u
l
t
i
-
o
b
j
e
c
t
i
v
e
c
u
c
k
o
o
s
e
a
r
c
h
a
l
g
o
r
i
t
h
m
f
o
r
i
m
a
g
e
c
o
n
t
r
a
s
t
e
n
h
a
n
c
e
me
n
t
,
”
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
,
N
o
v
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
sw
a
.
2
0
2
1
.
2
0
0
0
5
1
.
[
2
0
]
U
.
K
u
r
a
n
,
E
.
C
.
K
u
r
a
n
,
a
n
d
M
.
B
.
Er
,
“
P
a
r
a
met
e
r
se
l
e
c
t
i
o
n
o
f
c
o
n
t
r
a
st
l
i
m
i
t
e
d
a
d
a
p
t
i
v
e
h
i
st
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
u
si
n
g
mu
l
t
i
-
o
b
j
e
c
t
i
v
e
f
l
o
w
e
r
p
o
l
l
i
n
a
t
i
o
n
a
l
g
o
r
i
t
h
m,”
i
n
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
-
(
I
C
EC
E
N
G
2
0
2
2
)
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
2
,
p
p
.
1
0
9
–
123
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
0
1
9
8
4
-
5
_
9
.
[
2
1
]
S
.
S
u
r
y
a
a
n
d
A
.
M
u
t
h
u
k
u
m
a
r
a
v
e
l
,
“
A
d
a
p
t
i
v
e
s
a
i
l
f
i
s
h
o
p
t
i
mi
z
a
t
i
o
n
-
c
o
n
t
r
a
st
l
i
m
i
t
e
d
a
d
a
p
t
i
v
e
h
i
st
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
(ASFO
-
C
LA
H
E)
f
o
r
h
y
p
e
r
p
a
r
a
me
t
e
r
t
u
n
i
n
g
i
n
i
m
a
g
e
e
n
h
a
n
c
e
m
e
n
t
,
”
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
f
o
r
C
l
i
n
i
c
a
l
D
i
a
g
n
o
s
i
s
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
3
,
p
p
.
5
7
–
76
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
3
6
8
3
-
9
_
5
.
[
2
2
]
S
.
R
.
B
o
r
r
a
,
N
.
P
.
Te
j
a
sw
i
n
i
,
V
.
M
a
l
a
t
h
y
,
B
.
M
.
K
u
m
a
r
,
a
n
d
M
.
I
.
H
a
b
e
l
a
l
ma
t
e
e
n
,
“
C
o
n
t
r
a
s
t
l
i
mi
t
e
d
a
d
a
p
t
i
v
e
h
i
s
t
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
b
a
s
e
d
m
u
l
t
i
-
o
b
j
e
c
t
i
v
e
i
mp
r
o
v
e
d
c
a
t
sw
a
r
m
o
p
t
i
mi
z
a
t
i
o
n
f
o
r
i
ma
g
e
c
o
n
t
r
a
s
t
e
n
h
a
n
c
e
me
n
t
,
”
i
n
2
0
2
3
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
g
r
a
t
e
d
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s
(
I
C
I
I
C
S
)
,
I
EEE,
2
0
2
3
,
p
p
.
1
–
5
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
I
C
S
5
9
9
9
3
.
2
0
2
3
.
1
0
4
2
0
9
5
9
.
[
2
3
]
Y
.
R
.
H
a
d
d
a
d
i
,
B
.
M
a
n
s
o
u
r
i
,
a
n
d
F
.
Z.
I
.
K
h
o
d
j
a
,
“
A
n
o
v
e
l
me
d
i
c
a
l
i
ma
g
e
e
n
h
a
n
c
e
me
n
t
a
l
g
o
r
i
t
h
m
b
a
se
d
o
n
c
l
a
h
e
a
n
d
p
e
l
i
c
a
n
o
p
t
i
m
i
z
a
t
i
o
n
,
”
Mu
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
4
2
,
p
p
.
9
0
0
6
9
–
9
0
0
8
8
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
0
2
4
-
1
9
0
7
0
-
6.
[
2
4
]
H
.
Zh
u
,
Y
.
W
a
n
g
,
Z.
M
a
,
a
n
d
X
.
Li
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
sw
a
r
m
i
n
t
e
l
l
i
g
e
n
c
e
a
l
g
o
r
i
t
h
ms
f
o
r
U
C
A
V
p
a
t
h
-
p
l
a
n
n
i
n
g
p
r
o
b
l
e
ms,
”
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
9
,
n
o
.
2
,
J
a
n
.
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
mat
h
9
0
2
0
1
7
1
.
[
2
5
]
A
.
M
i
t
t
a
l
,
A
.
K
.
M
o
o
r
t
h
y
,
a
n
d
A
.
C
.
B
o
v
i
k
,
“
N
o
-
r
e
f
e
r
e
n
c
e
i
ma
g
e
q
u
a
l
i
t
y
a
ssessme
n
t
i
n
t
h
e
sp
a
t
i
a
l
d
o
ma
i
n
,
”
I
EE
E
T
ra
n
sa
c
t
i
o
n
s
o
n
I
m
a
g
e
Pr
o
c
e
ssi
n
g
,
v
o
l
.
2
1
,
n
o
.
1
2
,
p
p
.
4
6
9
5
–
4
7
0
8
,
D
e
c
.
2
0
1
2
,
d
o
i
:
1
0
.
1
1
0
9
/
TI
P
.
2
0
1
2
.
2
2
1
4
0
5
0
.
[
2
6
]
J.
Y
a
n
,
J.
Li
,
a
n
d
X
.
F
u
,
“
N
o
-
r
e
f
e
r
e
n
c
e
q
u
a
l
i
t
y
a
ssessm
e
n
t
o
f
c
o
n
t
r
a
s
t
-
d
i
st
o
r
t
e
d
i
ma
g
e
s
u
si
n
g
c
o
n
t
r
a
st
e
n
h
a
n
c
e
me
n
t
,
”
a
rX
i
v
-
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
p
p
.
1
-
1
5
,
A
p
r
.
2
0
1
9
.
[
2
7
]
R
.
K
u
m
a
r
a
n
d
A
.
K
.
B
h
a
n
d
a
r
i
,
“
N
o
i
s
e
r
e
d
u
c
t
i
o
n
d
e
e
p
C
N
N
-
b
a
se
d
r
e
t
i
n
a
l
f
u
n
d
u
s
i
m
a
g
e
e
n
h
a
n
c
e
m
e
n
t
u
si
n
g
r
e
c
u
r
si
v
e
h
i
s
t
o
g
r
a
m,”
N
e
u
ra
l
C
o
m
p
u
t
i
n
g
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
6
,
n
o
.
2
7
,
p
p
.
1
7
2
2
1
–
1
7
2
4
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s0
0
5
2
1
-
0
2
4
-
0
9
9
9
6
-
1.
[
2
8
]
K
.
P
.
W
i
n
,
Y
.
K
i
t
j
a
i
d
u
r
e
,
K
.
H
a
mam
o
t
o
,
a
n
d
T.
M
y
o
A
u
n
g
,
“
C
o
m
p
u
t
e
r
-
a
s
si
st
e
d
s
c
r
e
e
n
i
n
g
f
o
r
c
e
r
v
i
c
a
l
c
a
n
c
e
r
u
s
i
n
g
d
i
g
i
t
a
l
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
o
f
p
a
p
sm
e
a
r
i
ma
g
e
s
,
”
Ap
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
0
0
5
1
8
0
0
.
[
2
9
]
M
.
E
.
P
l
i
ssi
t
i
,
P
.
D
i
m
i
t
r
a
k
o
p
o
u
l
o
s,
G
.
S
f
i
k
a
s
,
C
.
N
i
k
o
u
,
O
.
K
r
i
k
o
n
i
,
a
n
d
A
.
C
h
a
r
c
h
a
n
t
i
,
“
S
i
p
a
k
me
d
:
a
n
e
w
d
a
t
a
s
e
t
f
o
r
f
e
a
t
u
r
e
a
n
d
im
a
g
e
b
a
s
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
n
o
r
m
a
l
a
n
d
p
a
t
h
o
l
o
g
i
c
a
l
c
e
r
v
i
c
a
l
c
e
l
l
s
i
n
p
a
p
sm
e
a
r
i
ma
g
e
s
,
”
i
n
2
0
1
8
2
5
t
h
I
E
EE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
m
a
g
e
Pro
c
e
ss
i
n
g
(
I
C
I
P)
,
I
EEE,
O
c
t
.
2
0
1
8
,
p
p
.
3
1
4
4
–
3
1
4
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
P
.
2
0
1
8
.
8
4
5
1
5
8
8
.
[
3
0
]
S
.
R
a
y
,
K
.
G
.
D
h
a
l
,
a
n
d
P
.
K
.
N
a
s
k
a
r
,
“
P
a
r
t
i
c
l
e
sw
a
r
m
o
p
t
i
mi
z
e
r
b
a
se
d
e
p
i
t
h
e
l
i
a
l
l
a
y
e
r
s
e
g
m
e
n
t
a
t
i
o
n
i
n
C
I
El
a
b
c
o
l
o
r
sp
a
c
e
,
”
i
n
2
0
2
2
I
EEE
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Re
c
e
n
t
A
d
v
a
n
c
e
s
a
n
d
I
n
n
o
v
a
t
i
o
n
s
i
n
En
g
i
n
e
e
ri
n
g
(
I
C
RAIE)
,
I
EEE
,
D
e
c
.
2
0
2
2
,
p
p
.
3
3
1
–
3
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
A
I
E5
6
4
5
4
.
2
0
2
2
.
1
0
0
5
4
2
6
1
.
[
3
1
]
P
.
P
e
r
o
n
a
a
n
d
J.
M
a
l
i
k
,
“
S
c
a
l
e
-
s
p
a
c
e
a
n
d
e
d
g
e
d
e
t
e
c
t
i
o
n
u
s
i
n
g
a
n
i
s
o
t
r
o
p
i
c
d
i
f
f
u
s
i
o
n
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s o
n
Pa
t
t
e
r
n
An
a
l
y
s
i
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
2
,
n
o
.
7
,
p
p
.
6
2
9
–
6
3
9
,
Ju
l
.
1
9
9
0
,
d
o
i
:
1
0
.
1
1
0
9
/
3
4
.
5
6
2
0
5
.
[
3
2
]
A
.
V
.
N
a
so
n
o
v
,
N
.
V
.
M
a
ma
e
v
,
O
.
S
.
V
o
l
o
d
i
n
a
,
a
n
d
A
.
S
.
K
r
y
l
o
v
,
“
A
u
t
o
mat
i
c
c
h
o
i
c
e
o
f
d
e
n
o
i
s
i
n
g
p
a
r
a
m
e
t
e
r
i
n
P
e
r
o
n
a
-
M
a
l
i
k
mo
d
e
l
,
”
i
n
2
9
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
G
ra
p
h
i
c
s,
I
m
a
g
e
P
ro
c
e
ssi
n
g
a
n
d
C
o
m
p
u
t
e
r
V
i
si
o
n
,
Vi
s
u
a
l
i
za
t
i
o
n
S
y
st
e
m
s
a
n
d
t
h
e
V
i
rt
u
a
l
E
n
v
i
r
o
n
m
e
n
t
G
ra
p
h
i
C
o
n
'
2
0
1
9
,
N
o
v
.
2
0
1
9
,
p
p
.
1
4
4
–
1
4
7
,
d
o
i
:
1
0
.
3
0
9
8
7
/
g
r
a
p
h
i
c
o
n
-
2
0
1
9
-
2
-
1
4
4
-
1
4
7
.
[
3
3
]
B
.
M
a
i
se
l
i
,
“
N
o
n
l
i
n
e
a
r
a
n
i
s
o
t
r
o
p
i
c
d
i
f
f
u
si
o
n
me
t
h
o
d
s
f
o
r
i
ma
g
e
d
e
n
o
i
si
n
g
p
r
o
b
l
e
ms:
c
h
a
l
l
e
n
g
e
s
a
n
d
f
u
t
u
r
e
r
e
s
e
a
r
c
h
o
p
p
o
r
t
u
n
i
t
i
e
s,
”
A
rra
y
,
v
o
l
.
1
7
,
M
a
r
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
2
.
1
0
0
2
6
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.