I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l
E
ng
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
3
,
Dec
em
b
er
20
21
,
p
p
.
1
5
1
5
~
1
5
2
2
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
2
4
.i
3
.
pp
1
5
1
5
-
1
5
2
2
1515
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
A review
of va
rio
us ima
g
e f
usio
n t
y
pes a
nd t
ra
nsfo
r
ms
Ay
o
dej
i O
la
leka
n Sa
la
u
1
,
Sh
rut
i J
a
in
2
,
J
o
y
Nnenna
E
neh
3
1
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l/
El
e
c
tro
n
ics
a
n
d
C
o
m
p
u
ter E
n
g
in
e
e
ri
n
g
,
Afe
Ba
b
a
lo
la Un
iv
e
rsit
y
,
A
d
o
Ek
i
ti
,
Nig
e
ria
2
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
,
Ja
y
p
e
e
Un
iv
e
rsity
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
S
o
lan
,
In
d
ia
3
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ic E
n
g
i
n
e
e
rin
g
,
Un
iv
e
rsity
o
f
Ni
g
e
ria,
Ns
u
k
k
a
,
Nig
e
ria
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
21
,
2
0
2
1
R
ev
is
ed
Oct
14
,
2
0
2
1
Acc
ep
ted
Oct
27
,
2
0
2
1
Util
izin
g
m
u
lt
ip
le
v
iew
s
o
f
a
n
i
m
a
g
e
is
a
n
imp
o
rtan
t
a
p
p
r
o
a
c
h
in
d
i
g
it
a
l
p
h
o
to
g
ra
p
h
y
,
v
id
e
o
e
d
it
i
n
g
,
a
n
d
m
e
d
ica
l
ima
g
e
fu
sio
n
a
p
p
li
c
a
ti
o
n
s.
Im
a
g
e
fu
sio
n
(Im
F
)
m
e
th
o
d
s
a
re
u
se
d
to
i
m
p
ro
v
e
a
n
ima
g
e
'
s
q
u
a
li
ty
a
n
d
re
m
o
v
e
n
o
ise
fro
m
th
e
ima
g
e
sig
n
a
l,
re
su
lt
in
g
i
n
a
h
ig
h
e
r
si
g
n
a
l
-
to
-
n
o
ise
ra
ti
o
.
A
c
o
m
p
lete
a
ss
e
ss
m
e
n
t
o
f
th
e
li
tera
tu
re
o
n
th
e
d
iffere
n
t
tran
sf
o
rm
k
i
n
d
s,
tec
h
n
iq
u
e
s,
a
n
d
ru
les
u
ti
li
z
e
d
i
n
Im
F
is
p
re
se
n
t
e
d
i
n
th
is
p
a
p
e
r.
T
o
a
ss
e
ss
th
e
o
u
tco
m
e
s,
a
wh
it
e
flo
we
r
ima
g
e
wa
s fu
se
d
u
sin
g
d
isc
re
te wa
v
e
let
tran
sfo
rm
(DWT
)
a
n
d
d
isc
re
te
c
o
sin
e
tran
sfo
rm
(DCT)
tec
h
n
iq
u
e
s.
F
o
r
v
a
li
d
a
ti
o
n
o
f
re
su
lt
s,
t
h
e
r
e
d
,
g
re
e
n
,
b
lu
e
(
RG
B
)
a
n
d
i
n
ten
sit
y
h
u
e
sa
t
u
ra
ti
o
n
(IHS)
v
a
lu
e
s
o
f
in
d
i
v
id
u
a
l
a
n
d
f
u
se
d
ima
g
e
s
we
re
e
v
a
lu
a
ted
.
T
h
e
re
su
l
ts
o
b
tain
e
d
fro
m
t
h
e
fu
se
d
ima
g
e
s
with
t
h
e
sp
a
ti
a
l
IHS
tran
sfo
rm
m
e
th
o
d
g
i
v
e
a
re
m
a
rk
a
b
le
p
e
rfo
rm
a
n
c
e
.
F
u
rth
e
rm
o
re
,
th
e
re
su
lt
s
o
f
t
h
e
p
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
u
si
n
g
DWT
a
n
d
D
CT
fu
sio
n
tec
h
n
iq
u
e
s
sh
o
w
th
a
t
t
h
e
sa
m
e
p
e
a
k
sig
n
a
l
t
o
n
o
ise
ra
ti
o
(P
S
NR)
o
f
1
1
4
.
0
4
wa
s
a
c
h
iev
e
d
fo
r
b
o
th
P
S
NR
1
a
n
d
P
S
NR
2
f
o
r
DCT,
a
n
d
d
iffere
n
t
re
su
lt
s
we
re
o
b
tai
n
e
d
f
o
r
DW
T.
F
o
r
sig
n
a
l
t
o
n
o
ise
ra
ti
o
(S
NR),
S
NR
1
a
n
d
S
NR
2
a
c
h
iev
e
d
slig
h
tl
y
sim
il
a
r
v
a
l
u
e
s
o
f
1
1
4
.
0
0
a
n
d
1
1
4
.
0
1
fo
r
DCT,
w
h
il
e
a
S
N
R
o
f
1
1
3
.
2
8
a
n
d
1
1
2
.
2
6
wa
s a
c
h
iev
e
d
f
o
r
S
N
R
1
a
n
d
S
NR
2
re
sp
e
c
ti
v
e
l
y
.
K
ey
w
o
r
d
s
:
Hy
p
er
s
p
ec
tr
al
I
m
ag
e
f
u
s
io
n
Mu
lti
-
m
o
d
al
Mu
lti
-
s
en
s
o
r
Mu
lti
-
s
p
ec
tr
al
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
:
Sh
r
u
ti Jain
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
e
n
g
in
ee
r
i
n
g
J
ay
p
ee
Un
iv
er
s
ity
o
f
I
n
f
o
r
m
at
io
n
T
ec
h
n
o
lo
g
y
So
lan
,
I
n
d
ia
E
m
ail:
s
h
r
u
ti.jain
@
ju
its
o
lan
.
in
1.
I
NT
RO
D
UCT
I
O
N
A
d
ig
ital
im
ag
e
is
a
g
r
id
o
f
s
m
all
elem
en
ts
ca
lled
a
p
ix
el.
An
im
ag
e
ca
n
b
e
r
e
p
r
esen
ted
in
b
o
th
t
h
e
s
p
atial
an
d
s
p
ec
tr
al
d
o
m
ain
s
.
T
o
o
b
tain
a
b
etter
q
u
ality
o
f
an
im
a
g
e
co
n
tain
in
g
b
o
t
h
s
p
ec
tr
al
an
d
s
p
atial
d
o
m
ain
s
,
m
u
ltip
le
in
p
u
t
im
ag
es
ar
e
f
u
s
ed
.
T
h
is
p
r
o
ce
s
s
is
k
n
o
wn
as
im
ag
e
f
u
s
io
n
[
1
]
-
[
3
]
.
Sp
ec
t
r
al
r
ep
r
esen
tatio
n
d
e
f
in
es
th
e
ed
g
e
f
ea
tu
r
es
o
f
th
e
im
ag
e
w
h
ile
s
p
atial
r
ep
r
esen
tatio
n
in
d
icat
es
s
p
ac
e.
Fo
r
a
2
D
im
ag
e
s
p
ac
e
(
x
,
y
-
p
lan
e
)
,
d
ir
ec
t
m
o
d
if
icatio
n
o
f
th
e
p
r
o
p
er
tie
s
o
f
th
e
p
ix
els
ca
n
b
e
ac
h
iev
e
d
.
M
u
lt
i
-
v
iew
f
u
s
io
n
,
m
u
lti
-
f
o
cu
s
f
u
s
io
n
,
m
u
lti
-
tier
f
u
s
io
n
,
m
u
lti
-
ex
p
o
s
u
r
e
f
u
s
io
n
,
m
u
lti
-
m
o
d
al
f
u
s
io
n
,
h
y
p
er
s
p
e
ctr
al
f
u
s
io
n
(
HSF),
s
in
g
le
s
en
s
o
r
f
u
s
io
n
,
an
d
m
u
lt
i
s
en
s
o
r
f
u
s
io
n
ar
e
th
e
d
if
f
e
r
en
t
ty
p
es
o
f
im
a
g
e
f
u
s
io
n
(
I
m
F)
tech
n
iq
u
es
[
4
]
,
[
5
]
.
W
h
en
d
if
f
er
en
t
v
ie
ws
o
f
th
e
s
am
e
s
ce
n
e
ar
e
tak
en
f
r
o
m
m
u
l
tip
le
ca
m
er
as
an
d
f
u
s
ed
,
th
e
p
r
o
ce
s
s
is
k
n
o
wn
as
m
u
lti
-
v
iew
f
u
s
io
n
.
Mu
lti
-
s
en
s
o
r
f
u
s
io
n
is
m
ain
ly
u
s
ed
in
r
em
o
te
s
en
s
in
g
wh
er
e
th
e
f
u
s
io
n
o
f
p
an
ch
r
o
m
atic
(
PAN)
m
o
d
e
(
h
i
g
h
s
p
atial
r
eso
lu
tio
n
im
a
g
e
wh
ich
h
as
n
o
co
lo
r
in
f
o
r
m
atio
n
:
g
r
a
y
)
an
d
m
u
ltis
p
ec
tr
al
(
MS)
m
o
d
e
(
lo
w
s
p
atial
r
eso
lu
tio
n
im
ag
e
in
wh
ich
co
lo
r
in
f
o
r
m
atio
n
is
p
r
esen
t)
[
6
]
,
[
7
]
.
PAN
an
d
MS
m
o
d
es
ar
e
u
s
u
ally
u
s
ed
s
im
u
ltan
eo
u
s
ly
in
o
r
d
er
f
o
r
s
o
m
e
i
n
f
o
r
m
atio
n
o
f
th
e
o
b
j
ec
t
n
o
t
to
b
e
lo
s
t.
M
u
lti
-
s
en
s
o
r
im
ag
e
f
u
s
i
o
n
is
th
e
f
u
s
io
n
o
f
d
if
f
er
e
n
t
s
atellite
im
ag
es
[
8
]
,
[
9
]
.
T
h
er
e
is
an
o
t
h
er
f
u
s
io
n
p
r
o
ce
d
u
r
e
ca
lled
HSF
in
wh
ich
m
u
ltis
p
ec
tr
al
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
5
1
5
-
1
5
2
2
1516
im
ag
es
with
h
ig
h
s
p
atial
r
eso
lu
tio
n
s
en
h
an
ce
s
p
atially
a
h
y
p
er
s
p
ec
tr
al
im
ag
e.
Hig
h
s
p
ec
tr
al
(
h
y
p
er
s
p
ec
tr
al
)
im
ag
es
h
av
e
a
lo
w
s
p
ati
al
r
eso
lu
tio
n
an
d
h
i
g
h
g
eo
m
etr
ic
(
m
u
ltis
p
ec
tr
al)
im
ag
es
h
a
v
e
a
h
i
g
h
s
p
atial
r
eso
lu
tio
n
[
1
0
]
.
W
h
en
im
ag
es
ar
e
o
b
tain
ed
f
r
o
m
d
iv
e
r
s
e
m
o
d
alities
o
f
a
s
im
ilar
s
ce
n
e
an
d
f
u
s
ed
,
th
is
is
k
n
o
wn
as
m
u
lti
-
m
o
d
al
im
ag
e
f
u
s
io
n
[
1
1
]
,
[
1
2
]
.
Mu
lti
-
m
o
d
al
im
ag
e
f
u
s
io
n
also
f
o
cu
s
es
o
n
d
if
f
e
r
en
t
s
ce
n
es
wh
eth
er
th
ey
ar
e
f
o
r
e
g
r
o
u
n
d
o
r
b
ac
k
g
r
o
u
n
d
s
ce
n
es.
Fo
r
m
u
lti
-
m
o
d
al
im
ag
e
f
u
s
io
n
,
m
ed
ical
im
ag
e
f
u
s
io
n
(
MI
F)
is
th
e
b
est ex
am
p
le.
No
wad
ay
s
,
a
wid
e
n
u
m
b
e
r
o
f
p
h
y
s
ician
s
f
u
s
e
th
e
lesi
o
n
s
tak
en
f
r
o
m
d
if
f
er
en
t
m
o
d
alities
o
f
m
ed
ical
im
ag
es
[
1
3
]
,
[
1
4
]
.
T
h
is
p
r
o
ce
s
s
es
m
o
s
t
t
im
es
in
v
o
lv
es
th
e
a
p
p
licatio
n
o
f
co
m
p
u
ter
v
is
io
n
,
im
ag
e
p
r
o
ce
s
s
in
g
,
m
ac
h
in
e
lear
n
in
g
,
p
atter
n
r
ec
o
g
n
itio
n
,
o
r
a
r
tific
ial
in
tellig
en
ce
[
1
1
]
.
MI
F
u
s
es
p
o
s
itro
n
em
is
s
io
n
to
m
o
g
r
ap
h
y
(
PET
)
,
s
in
g
le
p
h
o
to
n
e
m
is
s
io
n
co
m
p
u
ted
t
o
m
o
g
r
a
p
h
y
(
SP
E
C
T
)
,
co
m
p
u
ter
ize
d
to
m
o
g
r
a
p
h
y
(
C
T
)
,
m
ag
n
etic
r
eso
n
an
ce
im
a
g
in
g
(
MRI)
,
an
d
u
ltra
s
o
u
n
d
m
o
d
alities
.
T
h
er
e
ar
e
s
ev
er
al
a
d
v
an
ta
g
es
an
d
d
is
ad
v
an
tag
es
o
f
th
e
d
if
f
er
en
t
MI
F
tech
n
iq
u
es.
Fo
r
in
s
tan
ce
,
u
ltra
s
o
u
n
d
im
ag
in
g
is
ex
ten
s
iv
ely
u
s
ed
b
ec
au
s
e
o
f
it
s
lo
w
co
s
t
an
d
it
s
n
eg
lig
ib
le
s
id
e
ef
f
ec
t o
n
p
atie
n
ts
.
C
T
im
ag
es p
r
o
v
id
es a
3
D
im
ag
in
g
tech
n
i
q
u
e
with
a
h
ig
h
im
ag
in
g
r
eso
lu
tio
n
an
d
s
h
o
r
t
s
ca
n
tim
e
with
lim
it
ed
ch
ar
ac
ter
izatio
n
o
f
s
o
f
t
tis
s
u
es.
MRI
im
ag
es
en
co
m
p
ass
s
o
f
t
tis
s
u
es
an
d
h
ig
h
g
eo
m
etr
ic
im
a
g
es,
an
d
p
r
o
v
id
es
lim
ited
m
o
v
em
e
n
t
in
f
o
r
m
at
io
n
s
u
ch
as
b
o
d
y
m
eta
b
o
lis
m
.
SP
E
C
T
im
ag
es
g
iv
e
th
e
in
f
o
r
m
atio
n
o
f
b
lo
o
d
f
lo
w
in
tis
s
u
es
an
d
o
r
g
an
s
wh
il
e
PET
im
ag
es
h
av
e
a
h
i
g
h
s
en
s
itiv
ity
an
d
a
l
o
w
r
eso
lu
tio
n
[
1
5
]
.
T
h
er
e
ar
e
d
if
f
er
en
t
ty
p
es
o
f
im
ag
e
f
u
s
io
n
a
p
p
r
o
ac
h
e
s
t
h
at
ar
e
u
s
ed
to
f
u
s
e
two
o
r
m
o
r
e
im
a
g
es.
T
h
ey
ca
n
b
e
c
h
ar
ac
ter
ized
in
t
o
Mo
r
p
h
o
lo
g
ical,
k
n
o
wled
g
e
,
n
eu
r
al
n
etwo
r
k
,
wav
elet,
f
u
zz
y
lo
g
ic,
an
d
v
ar
io
u
s
o
th
er
ap
p
r
o
ac
h
es.
Au
th
o
r
s
in
[
4
]
,
[
5
]
,
p
r
esen
ted
a
PAN
s
h
ar
p
en
in
g
m
eth
o
d
wh
ich
em
p
lo
y
e
d
p
y
r
am
i
d
-
b
ase
d
I
m
F
an
d
wav
elet
-
b
ased
I
m
F.
I
n
th
is
ap
p
r
o
ac
h
,
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
with
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
m
eth
o
d
s
wer
e
co
m
b
in
ed
to
g
iv
e
a
b
etter
im
ag
e
f
u
s
io
n
o
u
tco
m
e.
Mif
d
al
et
a
l.
[
8
]
u
s
ed
an
Op
tim
a
l
T
r
an
s
p
o
r
t
m
et
h
o
d
wh
ich
was
u
s
ed
to
f
u
s
e
th
e
s
p
ec
tr
al
in
f
o
r
m
atio
n
o
f
a
h
y
p
er
im
a
g
e
with
s
p
atial
in
f
o
r
m
atio
n
.
T
h
e
m
eth
o
d
is
k
n
o
wn
as
th
e
h
y
p
er
s
p
ec
tr
al
an
d
m
u
ltis
p
ec
tr
al
W
as
s
er
s
tein
b
ar
y
ce
n
ter
(
HM
W
B
)
m
eth
o
d
.
Au
th
o
r
s
in
[
1
6
]
,
[
1
7
]
,
h
a
v
e
u
s
ed
wav
e
let
tr
an
s
f
o
r
m
to
f
u
s
e
h
ig
h
s
p
e
ctr
al
an
d
h
ig
h
g
eo
m
et
r
ic
im
ag
es,
wh
ile
th
e
non
-
s
am
p
le
co
n
to
u
r
let
tr
an
s
f
o
r
m
(
NSC
T
)
d
o
m
ain
was
u
s
ed
in
s
tead
o
f
wav
elet
tr
a
n
s
f
o
r
m
i
n
[
1
8
]
,
[
1
9
]
.
I
n
[
2
0
]
,
[
2
1
]
,
non
-
s
am
p
le
d
d
ir
ec
tio
n
al
f
ilter
b
an
k
(
NSDFB
)
an
d
n
on
-
s
a
m
p
led
d
ir
ec
tio
n
al
p
y
r
am
id
f
i
lter
b
an
k
(
NSPF
B
)
tech
n
iq
u
es
wer
e
a
d
o
p
te
d
.
A
p
u
ls
e
co
u
p
le
d
n
e
u
r
al
n
etwo
r
k
(
PC
NN)
m
o
d
el
was
p
r
esen
t
ed
in
[
2
2
]
.
I
n
[
2
3
]
,
Sh
ea
r
let
tr
an
s
f
o
r
m
was
in
tr
o
d
u
ce
d
f
o
r
th
e
f
u
s
io
n
p
r
o
ce
s
s
;
wh
ile
f
o
r
PC
NN
m
o
d
el
p
ar
am
eter
esti
m
atio
n
,
g
am
m
a
d
is
tr
ib
u
tio
n
in
Sh
ea
r
let
d
o
m
ai
n
was
u
s
ed
.
T
h
er
e
ar
e
s
ev
er
al
tech
n
iq
u
es
u
s
ed
f
o
r
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
b
ased
I
m
F.
T
h
ese
in
clu
d
e
g
am
m
a
en
h
an
ce
m
en
t
[
2
4
]
,
h
is
to
g
r
a
m
eq
u
aliza
tio
n
[
2
5
]
,
a
n
d
co
n
tr
ast
en
h
an
ce
m
e
n
t
u
s
in
g
g
a
m
m
a
c
o
r
r
elatio
n
(
GC
)
with
weig
h
te
d
f
u
n
ctio
n
s
[
2
6
]
.
Z
h
a
n
g
et
a
l.
[
1
4
]
u
s
ed
wav
elet
-
b
ased
B
ay
esian
f
u
n
ctio
n
an
d
[
2
7
]
em
p
lo
y
ed
th
e
u
s
e
o
f
b
lu
r
r
in
g
m
eth
o
d
an
d
q
u
ater
n
i
o
n
wav
elet
tr
an
s
f
o
r
m
(
QW
T
)
o
n
m
u
ltis
p
ec
tr
al
an
d
h
y
p
er
s
p
ec
tr
al
im
ag
es.
R
eid
et
a
l.
[
2
8
]
p
r
o
p
o
s
ed
a
m
eth
o
d
th
at
ca
n
p
r
o
p
ag
ate
in
f
o
r
m
atio
n
f
r
o
m
h
ig
h
-
r
eso
lu
t
io
n
i
m
ag
es
to
lo
w
-
r
eso
lu
tio
n
im
ag
es
u
s
in
g
d
if
f
e
r
en
t
s
p
ec
tr
al
ch
an
n
els.
I
n
th
is
ca
s
e,
b
o
th
r
eso
lu
tio
n
im
ag
es
ar
e
n
o
n
lin
ea
r
,
n
o
n
-
s
tatio
n
ar
y
,
a
n
d
n
o
n
-
d
eter
m
in
is
tic.
T
h
e
au
t
h
o
r
s
u
s
ed
Gau
s
s
ian
p
r
o
ce
s
s
(
GP)
r
eg
r
ess
io
n
as
th
e
m
ain
ap
p
r
o
ac
h
.
GP
is
a
n
o
n
-
p
ar
am
etr
ic
B
ay
e
s
ian
f
r
am
ewo
r
k
.
I
n
t
h
is
ap
p
r
o
ac
h
,
th
er
e
ar
e
two
ch
allen
g
es:
th
e
f
ir
s
t
is
to
d
ef
in
e
th
e
co
v
ar
ian
ce
f
u
n
ctio
n
an
d
th
e
s
ec
o
n
d
is
to
d
ef
in
e
im
ag
e
p
r
io
r
s
tr
u
ctu
r
e.
Yan
g
et
a
l
.
[
2
9
]
in
tr
o
d
u
ce
d
R
ed
b
lack
wav
elets
with
p
r
in
cip
al
c
o
m
p
o
n
en
t a
n
aly
s
is
(
PC
A)
f
o
r
m
u
lti
-
sp
ec
tr
al
im
ag
e
f
u
s
io
n
.
Fo
r
f
ea
tu
r
es
th
at
o
r
ig
in
ate
f
r
o
m
im
ag
e
s
en
s
o
r
s
,
f
u
s
io
n
is
r
eq
u
ir
ed
.
E
ac
h
attr
ib
u
te
in
a
m
u
ltimo
d
al
s
y
s
tem
is
co
m
p
o
s
ed
o
f
m
an
y
f
ea
tu
r
e
m
atr
ices.
Ho
wev
er
,
we
ca
n
n
o
t
p
r
o
ce
s
s
o
r
s
av
e
th
em
in
a
d
atab
ase
at
th
e
s
am
e
tim
e
b
ec
au
s
e
it
tak
es
a
lo
t
o
f
tim
e
to
c
o
m
p
u
te
a
n
d
it
is
also
tim
e
-
co
n
s
u
m
in
g
.
As
a
r
esu
lt
o
f
th
is
,
it
is
n
ec
ess
ar
y
to
m
er
g
e
f
ea
tu
r
e
m
a
tr
ices f
r
o
m
s
ev
er
al
s
o
u
r
ce
s
.
T
h
is
ap
p
r
o
ac
h
is
ca
lled
f
u
s
io
n
.
T
h
is
p
ap
er
p
r
esen
ts
a
r
ev
iew
o
f
th
e
d
if
f
er
en
t
im
a
g
e
f
u
s
io
n
a
p
p
r
o
ac
h
es
an
d
s
tep
s
u
s
ed
in
im
a
g
e
f
u
s
io
n
,
wh
ich
in
clu
d
e
p
r
e
-
p
r
o
ce
s
s
in
g
,
d
ec
o
m
p
o
s
itio
n
,
im
a
g
e
f
u
s
io
n
r
u
les,
r
ec
o
n
s
tr
u
ctio
n
,
a
n
d
in
ad
d
itio
n
,
a
p
er
f
o
r
m
an
ce
p
a
r
am
eter
ev
al
u
a
tio
n
was a
ls
o
p
r
esen
ted
.
T
h
e
s
p
atial
in
ten
s
ity
h
u
e
s
atu
r
atio
n
(
I
HS)
im
ag
e
f
u
s
io
n
o
n
wh
ite
f
l
o
wer
im
ag
es
(
in
d
o
o
r
an
d
o
u
td
o
o
r
)
was
test
ed
,
an
d
it
was
d
is
co
v
er
ed
th
at
t
h
e
b
est
r
esu
lts
ar
e
o
b
tain
ed
af
ter
f
u
s
in
g
th
e
im
ag
es
in
s
tead
o
f
u
s
in
g
th
e
s
in
g
le
im
ag
es.
T
h
e
r
em
ain
in
g
s
ec
tio
n
s
o
f
th
e
p
a
p
er
ar
e
ar
r
an
g
ed
as
f
o
llo
ws:
s
ec
tio
n
2
ex
p
lain
s
th
e
m
eth
o
d
o
lo
g
y
e
m
p
lo
y
e
d
in
th
is
p
ap
er
f
o
r
im
ag
e
f
u
s
io
n
.
I
n
s
ec
tio
n
3
,
th
e
ex
p
er
im
en
tal
r
esu
lts
ar
e
d
is
cu
s
s
ed
,
tab
u
lated
an
d
th
e
o
u
tp
u
t
im
ag
es
a
r
e
d
ep
icted
.
T
h
is
is
f
o
llo
wed
b
y
th
e
co
n
clu
d
in
g
r
em
a
r
k
s
an
d
f
u
tu
r
e
wo
r
k
in
s
ec
tio
n
4.
2.
M
E
T
H
O
DO
L
O
G
Y
W
ith
th
e
r
ap
id
ad
v
an
ce
m
en
t
o
f
im
ag
in
g
tech
n
i
q
u
es,
a
v
ar
iety
o
f
ap
p
r
o
ac
h
es
in
th
e
f
ield
o
f
I
m
F
ar
e
b
ein
g
u
s
ed
in
r
ec
en
t
tim
es.
I
m
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
(
im
ag
e
n
o
r
m
aliza
tio
n
an
d
im
ag
e
r
eg
i
s
tr
atio
n
)
[
3
0
]
,
im
a
g
e
d
ec
o
m
p
o
s
itio
n
[
6
]
,
s
ev
er
al
I
m
F
r
u
les
[
3
1
]
,
im
ag
e
r
ec
o
n
s
tr
u
c
tio
n
,
an
d
q
u
ality
e
v
alu
atio
n
p
a
r
am
eter
s
[
3
2
]
-
[
3
4
]
ar
e
all
in
clu
d
ed
i
n
I
m
F.
I
m
a
g
e
s
ar
e
n
o
r
m
alize
d
at
th
e
s
am
e
lev
el,
r
o
tated
in
to
s
m
all
s
u
b
-
im
ag
es,
an
d
th
en
I
m
F
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
ev
iew
o
f v
a
r
io
u
s
ima
g
e
fu
s
io
n
typ
es a
n
d
tr
a
n
s
fo
r
ms
(
A
yo
d
eji
Ola
leka
n
S
a
la
u
)
1517
r
u
les
ar
e
u
s
ed
to
co
alesce
th
e
v
ar
io
u
s
f
ea
t
u
r
es
o
f
th
e
s
u
b
-
im
ag
es
at
v
ar
i
o
u
s
r
eso
lu
tio
n
s
d
u
r
in
g
p
r
e
-
p
r
o
ce
s
s
in
g
.
Fu
s
ed
im
ag
es
ar
e
r
ec
o
n
s
tr
u
cted
u
s
in
g
s
ev
er
al
r
ec
o
n
s
tr
u
ctio
n
tech
n
iq
u
es,
an
d
th
en
ev
al
u
a
tio
n
p
ar
am
eter
s
ar
e
ca
lcu
lated
to
ch
ec
k
th
e
im
ag
e
q
u
ality
.
I
m
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
,
im
ag
e
d
ec
o
m
p
o
s
itio
n
an
d
r
ec
o
n
s
tr
u
ctio
n
,
f
u
s
io
n
r
u
les,
an
d
im
a
g
e
q
u
ality
m
ea
s
u
r
e
p
ar
a
m
eter
s
ar
e
all
p
ar
t
o
f
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
'
s
w
o
r
k
f
lo
w.
I
n
th
is
ap
p
r
o
ac
h
,
I
m
ag
e
n
o
r
m
aliza
tio
n
an
d
im
ag
e
r
eg
is
tr
atio
n
is
u
s
ed
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
im
ag
es
.
T
h
e
im
ag
es
h
a
v
e
d
if
f
er
en
t
c
h
a
r
ac
ter
is
tics
lik
e
d
y
n
am
ic
r
a
n
g
e
an
d
c
o
n
tr
ast
r
an
g
e.
No
r
m
aliza
tio
n
was
p
er
f
o
r
m
ed
b
y
ca
lcu
latin
g
th
e
s
tan
d
ar
d
d
e
v
iatio
n
(
σ
)
a
n
d
g
l
o
b
al
m
ea
n
(
m
)
f
o
r
ea
c
h
im
ag
e.
E
v
er
y
p
ix
el
(
i,
j)
was
n
o
r
m
alize
d
u
s
in
g
(
1
)
,
0
(
,
)
=
2
+
(
2
2
0
)
[
(
,
)
−
]
(
1
)
wh
er
e
p
0
is
th
e
o
u
tp
u
t,
p
i
is
th
e
in
p
u
t,
n
is
th
e
d
esire
d
n
u
m
b
er
o
f
b
its
o
f
d
y
n
am
ic
r
an
g
e
an
d
D
is
th
e
m
ax
im
u
m
r
an
g
e
o
f
th
e
d
ata.
Af
ter
p
r
e
-
p
r
o
ce
s
s
in
g
,
im
p
lem
en
tatio
n
o
f
f
u
s
io
n
m
eth
o
d
s
was
p
er
f
o
r
m
ed
.
T
h
e
d
i
f
f
er
en
t
d
ec
o
m
p
o
s
itio
n
alg
o
r
ith
m
s
ar
e
u
s
ed
to
d
iv
id
e
th
e
im
a
g
e
in
to
s
u
b
-
im
ag
e
s
.
I
m
F
m
eth
o
d
s
ar
e
class
if
ied
in
to
d
if
f
er
en
t
ca
teg
o
r
ies
co
n
s
is
tin
g
o
f
tr
an
s
f
o
r
m
d
o
m
ain
f
u
s
io
n
(
T
DF)
an
d
s
p
atial
d
o
m
ain
f
u
s
io
n
(
SDF)
[
3
5
]
,
[
3
6
]
.
Hig
h
p
ass
f
ilter
in
g
,
av
er
a
g
in
g
,
b
r
o
v
ey
m
eth
o
d
,
PC
A,
an
d
i
n
ten
s
ity
h
u
e
s
atu
r
atio
n
(
I
HS)
m
eth
o
d
s
ar
e
p
ar
t
o
f
SDF.
T
DF
ca
n
b
e
f
u
r
th
er
d
iv
id
ed
in
to
th
e
p
y
r
am
id
m
eth
o
d
an
d
wav
elet
tr
an
s
f
o
r
m
m
et
h
o
d
.
Mo
r
e
r
ec
en
tly
,
s
ev
er
al
p
ap
er
s
h
av
e
p
r
o
p
o
s
ed
d
if
f
er
en
t
Py
r
am
i
d
m
eth
o
d
s
s
u
ch
as
th
e
L
ap
lacia
n
p
y
r
am
i
d
,
Gau
s
s
ian
p
y
r
am
id
,
m
o
r
p
h
o
lo
g
ical
p
y
r
am
id
,
g
r
ad
i
en
t
p
y
r
a
m
id
,
an
d
r
atio
to
lo
w
p
ass
p
y
r
am
id
.
Dif
f
e
r
en
t
wav
elet
m
eth
o
d
s
h
a
v
e
also
b
ee
n
p
r
o
p
o
s
ed
s
u
c
h
as
DT
-
C
W
T
,
QW
T
,
D
W
T
,
Sh
ea
r
let
tr
an
s
f
o
r
m
(
ST
)
,
d
ir
ec
tio
n
al
c
o
n
t
r
ast
f
u
zz
y
tr
an
s
f
o
r
m
(
DC
-
FTR
)
,
r
ed
b
lack
wav
elet
tr
an
s
f
o
r
m
(
WT
)
,
co
u
n
ter
let
tr
an
s
f
o
r
m
,
cu
r
v
elet
tr
an
s
f
o
r
m
[
3
7
]
.
B
ased
o
n
th
e
r
ev
iew
o
f
I
m
F
m
eth
o
d
s
u
s
in
g
d
if
f
er
e
n
t
tr
an
s
f
o
r
m
tech
n
iq
u
es
,
T
ab
le
1
p
r
esen
ts
th
e
ad
v
an
tag
es
an
d
d
is
ad
v
an
tag
es o
f
t
h
e
ex
is
tin
g
a
p
p
r
o
ac
h
es.
T
ab
le
1
.
Me
r
its
an
d
d
em
er
its
o
f
ex
is
tin
g
ap
p
r
o
ac
h
es
A
p
p
r
o
a
c
h
e
s
A
u
t
h
o
r
’
s
M
e
r
i
t
s
D
e
meri
t
s
D
W
T
w
i
t
h
En
t
r
o
p
y
c
o
n
c
e
p
t
s
[
3
8
]
F
u
se
d
i
ma
g
e
s
a
r
e
n
o
i
s
e
-
f
r
e
e
a
n
d
c
o
n
t
a
i
n
b
e
t
t
e
r
q
u
a
l
i
t
y
i
n
f
o
r
mat
i
o
n
,
i
n
c
o
r
p
o
r
a
t
i
n
g
m
u
l
t
i
m
o
d
a
l
i
t
y
,
a
n
d
h
e
l
p
i
n
d
e
r
i
v
i
n
g
u
sef
u
l
i
n
f
o
r
ma
t
i
o
n
S
i
n
g
l
e
m
o
d
a
l
i
t
y
c
a
n
’
t
g
i
v
e
m
u
c
h
u
sef
u
l
i
n
f
o
r
ma
t
i
o
n
N
S
C
T
w
i
t
h
l
o
c
a
l
e
n
e
r
g
y
mat
c
h
,
N
S
P
F
B
,
a
n
d
N
S
D
F
B
[
2
0
]
U
ses
l
o
w
-
f
r
e
q
u
e
n
c
y
s
u
b
-
b
a
n
d
s
t
o
h
i
g
h
-
f
r
e
q
u
e
n
c
y
s
u
b
-
b
a
n
d
s
(
d
i
r
e
c
t
i
o
n
a
l
v
e
c
t
o
r
)
,
a
n
d
o
b
t
a
i
n
s a
b
e
t
t
e
r
d
i
r
e
c
t
i
o
n
a
l
d
e
c
o
mp
o
si
t
i
o
n
N
o
t
a
b
l
e
t
o
e
mp
l
o
y
n
o
t
i
c
e
a
b
l
e
i
n
f
o
r
mat
i
o
n
p
r
e
s
e
n
t
i
n
t
h
e
l
o
w
-
f
r
e
q
u
e
n
c
y
s
u
b
-
b
a
n
d
s
C
o
n
t
o
u
r
l
e
t
Tr
a
n
sf
o
r
m
d
i
r
e
c
t
i
o
n
a
l
w
i
n
d
o
w
s
[
3
0
]
C
a
p
t
u
r
e
s
d
i
r
e
c
t
i
o
n
a
l
i
n
f
o
r
m
a
t
i
o
n
o
f
n
a
t
u
r
a
l
i
ma
g
e
s
H
y
b
r
i
d
t
e
c
h
n
i
q
u
e
s
[
3
9
]
C
o
m
p
u
t
a
t
i
o
n
s
a
r
e
e
a
s
y
P
C
N
N
mo
d
e
l
e
mp
l
o
y
i
n
g
S
h
e
a
r
l
e
t
D
o
mai
n
[
2
1
]
P
r
o
v
i
d
e
s
m
u
l
t
i
-
sc
a
l
e
s
u
b
d
i
v
i
s
i
o
n
a
n
d
d
i
r
e
c
t
i
o
n
l
o
c
a
l
i
z
a
t
i
o
n
G
a
u
ss
i
a
n
P
r
o
c
e
ss
[
2
8
]
U
sed
f
o
r
n
o
n
-
d
e
t
e
r
mi
n
i
s
t
i
c
,
n
o
n
l
i
n
e
a
r
a
n
d
n
o
n
-
st
a
t
i
o
n
a
r
y
i
ma
g
e
s
P
C
A
a
n
d
R
e
d
B
l
a
c
k
W
a
v
e
l
e
t
[
2
9
]
En
h
a
n
c
e
s I
mag
e
p
e
r
f
o
r
ma
n
c
e
.
D
e
c
o
m
p
o
s
i
t
i
o
n
o
f
d
i
v
e
r
se
f
e
a
t
u
r
e
s
c
a
n
b
e
d
o
n
e
b
y
t
h
i
s
m
e
t
h
o
d
I
n
th
is
p
a
p
er
,
d
is
cr
ete
wav
ele
t
tr
an
s
f
o
r
m
an
d
d
is
cr
ete
c
o
s
in
e
tr
an
s
f
o
r
m
h
as
b
ee
n
u
s
ed
to
f
u
s
e
two
im
ag
es.
I
n
th
e
f
u
s
io
n
p
r
o
ce
s
s
,
d
if
f
er
e
n
t
m
u
ltip
le
im
a
g
es
ar
e
co
m
b
in
e
d
to
f
o
r
m
o
n
e
im
a
g
e
with
im
p
r
o
v
ed
r
eso
lu
tio
n
.
T
h
e
r
e
ar
e
th
r
ee
d
if
f
er
en
t
co
m
p
o
n
en
ts
f
o
r
im
ag
e
f
u
s
io
n
:
co
e
f
f
icien
t
g
r
o
u
p
in
g
,
ac
tiv
ity
-
le
v
el
m
ea
s
u
r
em
en
t,
an
d
co
n
s
is
ten
cy
v
er
if
icatio
n
.
C
o
ef
f
icien
t
g
r
o
u
p
in
g
:
T
h
is
m
eth
o
d
is
b
ased
o
n
s
ca
le
g
r
o
u
p
in
g
.
T
h
er
e
ar
e
d
if
f
er
e
n
t ty
p
es o
f
s
ca
les:
m
u
lti
-
s
ca
le,
s
in
g
le
s
ca
le,
an
d
n
o
s
ca
le.
I
f
th
e
g
r
o
u
p
in
g
i
s
d
o
n
e
u
s
in
g
m
u
lti
-
s
ca
le,
it
i
s
k
n
o
wn
as
a
m
u
lti
-
s
ca
le
g
r
o
u
p
in
g
(
MSG)
.
MSG
d
escr
ib
es
th
e
co
ef
f
icien
t
o
f
d
if
f
er
en
t
im
ag
es
o
f
m
u
ltip
le
s
ca
les u
s
in
g
th
e
s
am
e
m
eth
o
d
.
L
ik
ewise,
we
h
av
e
s
i
n
g
le
-
s
ca
le
g
r
o
u
p
in
g
an
d
n
o
s
c
ale
g
r
o
u
p
in
g
.
Activ
ity
-
lev
el
m
ea
s
u
r
em
en
t (
AL
M)
: A
s
th
e
n
am
e
s
u
g
g
ests
,
th
is
ty
p
e
o
f
m
eth
o
d
is
u
s
ed
o
n
a
d
if
f
er
en
t
ac
tiv
ity
lik
e
win
d
o
ws,
co
ef
f
ici
en
ts
,
o
r
r
eg
io
n
s
.
I
n
th
is
ap
p
r
o
a
ch
,
wh
en
d
if
f
e
r
en
t
win
d
o
ws
ar
e
f
u
s
ed
it
is
ca
lled
win
d
o
w
b
ased
.
Als
o
,
if
d
if
f
e
r
e
n
t
co
ef
f
icien
ts
ar
e
f
u
s
ed
,
it
is
c
alled
co
ef
f
icien
t
b
ased
an
d
if
d
if
f
er
en
t
r
eg
i
o
n
s
ar
e
f
u
s
ed
th
en
it
is
ca
lled
r
eg
io
n
-
b
ased
.
Dif
f
er
en
t
co
ef
f
icien
ts
o
f
im
ag
es,
I
I
an
d
I
2
at
th
e
i
th
lev
el
ar
e
ex
p
r
ess
ed
u
s
in
g
C
i
1
an
d
C
i
2
r
esp
ec
tiv
ely
.
T
h
er
e
ar
e
v
a
r
io
u
s
co
e
f
f
icien
t
co
m
b
i
n
atio
n
(
CC
)
m
eth
o
d
s
wh
ich
in
clu
d
e
av
er
a
g
e
r
u
les
(
AR
)
,
m
ax
im
u
m
r
u
les
(
MR),
an
d
weig
h
ted
av
er
a
g
e
r
u
les
(
W
AR
)
.
T
h
e
g
en
er
ally
co
m
b
in
ed
co
ef
f
icien
t
(
C
F
)
is
ex
p
r
ess
ed
b
y
(
2
)
.
=
{
1
1
>
2
2
1
<
2
(
2
)
T
h
e
co
m
m
o
n
co
e
f
f
icien
t f
o
r
A
R
is
ex
p
r
ess
ed
b
y
(
3
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
5
1
5
-
1
5
2
2
1518
=
1
2
(
1
+
2
)
(
3
)
In
W
AR
,
th
e
d
if
f
er
en
t w
eig
h
ts
,
w
i
1
an
d
w
i
2
o
f
an
im
ag
e
ar
e
c
o
n
s
id
er
ed
an
d
th
e
c
o
m
m
o
n
co
ef
f
icien
t o
f
W
AR
is
r
ep
r
esen
ted
b
y
(
4
)
.
=
1
2
(
1
×
1
+
2
×
2
)
(
4
)
C
o
n
s
is
ten
cy
v
er
if
icatio
n
:
I
n
th
is
tech
n
iq
u
e,
t
h
e
s
am
e
r
u
les
ar
e
u
s
ed
f
o
r
f
u
s
in
g
co
e
f
f
ici
en
ts
p
r
esen
t
in
th
e
n
eig
h
b
o
r
h
o
o
d
.
I
m
ag
e
f
u
s
io
n
i
s
ac
h
iev
ed
with
d
if
f
e
r
en
t
p
r
o
c
ess
in
g
lev
els
lik
e
f
ea
tu
r
e
lev
e
l
(
FL)
,
s
ig
n
al
lev
el
(
SL)
,
p
ix
el/d
ata
lev
el
(
PL)
,
an
d
d
ec
is
io
n
lev
el
(
DL
)
[
3
2
]
,
[
3
3
]
as
s
h
o
wn
in
Fig
u
r
e
1
.
T
h
e
v
ar
io
u
s
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
p
a
r
am
eter
s
u
s
ed
in
v
ar
io
u
s
r
esear
ch
w
o
r
k
s
ar
e
d
e
p
icted
in
Fig
u
r
e
2
[
3
4
]
.
Fig
u
r
e
1
.
Dif
f
e
r
en
t f
u
s
io
n
tech
n
iq
u
es b
ased
o
n
v
ar
i
o
u
s
p
r
o
ce
s
s
in
g
lev
els
Fig
u
r
e
2
.
Var
io
u
s
p
er
f
o
r
m
an
c
e
ev
alu
atio
n
p
ar
am
eter
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
ev
iew
o
f v
a
r
io
u
s
ima
g
e
fu
s
io
n
typ
es a
n
d
tr
a
n
s
fo
r
ms
(
A
yo
d
eji
Ola
leka
n
S
a
la
u
)
1519
Fo
r
s
p
ec
tr
al
ev
alu
atio
n
,
t
h
e
m
e
an
s
q
u
ar
e
er
r
o
r
(
MSE
)
ch
ar
ac
t
er
izes
g
r
ay
lev
el
n
o
is
e
o
f
an
i
m
ag
e
less
er
th
an
th
e
v
alu
e
o
f
MSE
an
d
l
o
wer
th
an
th
e
n
o
is
e
co
n
ten
t.
Peak
s
ig
n
al
to
n
o
is
e
r
atio
(
PS
NR
)
is
th
e
r
atio
o
f
o
r
ig
in
al
t
o
c
o
m
p
r
ess
ed
im
a
g
e
an
d
is
u
s
ed
to
co
m
p
u
te
th
e
p
e
ak
SNR
o
f
th
e
f
u
s
ed
im
ag
e.
I
f
th
e
v
alu
e
o
f
PS
NR
is
h
ig
h
,
th
e
q
u
ality
o
f
t
h
e
r
ec
o
n
s
tr
u
cted
im
ag
e
is
b
etter
an
d
n
o
is
e
is
less
.
T
h
e
a
v
er
ag
e
g
r
a
d
ien
t
(
AG)
ex
p
lain
s
th
e
s
p
atial
r
eso
lu
tio
n
o
f
an
i
m
ag
e,
wh
ile
t
h
e
s
p
ec
tr
al
d
is
cr
ep
an
cy
(
SD)
ex
p
lain
s
th
e
s
p
ec
tr
al
q
u
ality
o
f
t
h
e
am
alg
am
ated
im
ag
e.
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
Fo
r
ex
p
er
im
e
n
tatio
n
,
a
u
th
o
r
s
h
av
e
u
s
ed
th
e
in
d
o
o
r
a
n
d
o
u
t
d
o
o
r
im
a
g
es
o
f
wh
ite
f
lo
wer
s
.
All
th
e
s
im
u
latio
n
s
wer
e
ca
r
r
ied
o
u
t
u
s
in
g
Py
th
o
n
lan
g
u
ag
e
o
n
a
n
i7
-
1
0
7
0
0
C
PU
@
2
.
9
0
GHz
,
with
a
6
4
-
b
it
o
p
e
r
atin
g
s
y
s
tem
.
T
h
e
v
a
r
io
u
s
s
tep
s
ad
o
p
ted
in
th
is
p
ap
e
r
ar
e
s
h
o
wn
in
Fig
u
r
e
3
.
T
h
e
d
if
f
er
e
n
t
im
ag
e
s
o
f
th
e
s
am
e
o
b
ject
(
w
h
ite
f
lo
wer
)
at
d
if
f
er
en
t
p
la
ce
s
: o
u
td
o
o
r
an
d
in
d
o
o
r
ar
e
co
n
s
id
er
ed
.
Fig
u
r
e
4
(
a)
r
ep
r
esen
t
s
th
e
o
u
td
o
o
r
wh
ite
f
lo
wer
im
ag
e
a
n
d
Fig
u
r
e
4
(
b
)
s
h
o
ws th
e
in
d
o
o
r
wh
ite
f
lo
wer
im
ag
e.
T
h
e
im
a
g
es we
r
e
n
o
r
m
al
ized
.
I
n
th
is
p
a
p
er
,
s
p
atial
I
HS
tr
an
s
f
o
r
m
-
b
ased
i
m
ag
e
f
u
s
io
n
wa
s
co
n
s
id
er
ed
.
All
th
e
p
ictu
r
es
wh
ich
ar
e
tak
en
f
r
o
m
a
d
if
f
er
en
t
d
ev
ice
ar
e
r
eg
en
e
r
ated
in
to
th
e
s
am
e
f
o
r
m
at.
T
h
e
r
ed
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
an
d
I
HS v
alu
e
was
ca
lcu
lated
f
o
r
b
o
th
in
d
o
o
r
an
d
o
u
td
o
o
r
im
a
g
es
an
d
t
h
e
r
esu
lts
ar
e
ta
b
u
lated
in
T
ab
le
2
an
d
T
ab
le
3
r
esp
ec
tiv
ely
.
C
o
n
s
id
er
in
g
f
ea
tu
r
e
lev
el
f
u
s
io
n
,
f
ea
t
u
r
es
o
f
th
e
in
d
o
o
r
an
d
o
u
t
d
o
o
r
im
ag
es
a
r
e
f
u
s
ed
to
f
o
r
m
o
n
e
im
ag
e.
Fig
u
r
e
5
s
h
o
ws th
e
f
u
s
ed
im
ag
e
u
s
in
g
a
s
am
p
le
o
f
th
e
in
d
o
o
r
an
d
o
u
td
o
o
r
f
lo
w
er
i
m
ag
e.
Fig
u
r
e
3
.
Dif
f
e
r
en
t step
s
u
s
ed
f
o
r
im
ag
e
f
u
s
io
n
I
m
a
g
e
P
re
-
pro
ce
s
s
ing
I
m
a
g
e
Dec
o
m
po
s
it
io
n a
nd
Rec
o
ns
t
ruct
io
n
I
m
a
g
e
F
us
io
n Rules
P
er
f
o
rma
nce
E
v
a
lua
t
io
n P
a
r
a
m
et
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
5
1
5
-
1
5
2
2
1520
(
a)
(
b
)
Fig
u
r
e
4
.
W
h
ite
f
lo
wer
(
a)
o
u
t
d
o
o
r
im
a
g
e
(
b
)
in
d
o
o
r
im
ag
e
T
ab
le
2
.
R
GB
s
ca
le
o
f
in
d
o
o
r
an
d
o
u
t
d
o
o
r
wh
ite
f
lo
wer
R
G
B
c
o
m
p
o
n
e
n
t
I
n
d
o
o
r
w
h
i
t
e
f
l
o
w
e
r
O
u
t
d
o
o
r
w
h
i
t
e
f
l
o
w
e
r
R
1
7
3
2
0
5
G
1
6
4
1
9
0
B
1
4
2
1
5
1
T
ab
le
3
.
I
HS
s
ca
le
o
f
i
n
d
o
o
r
a
n
d
o
u
t
d
o
o
r
wh
ite
f
lo
wer
I
H
S
c
o
mp
o
n
e
n
t
I
n
d
o
o
r
w
h
i
t
e
f
l
o
w
e
r
O
u
t
d
o
o
r
w
h
i
t
e
f
l
o
w
e
r
N
o
r
mal
i
z
e
d
I
4
2
%
4
3
%
N
o
r
mal
i
z
e
d
H
1
3
5
%
3
5
%
N
o
r
mal
i
z
e
d
S
6
1
%
6
9
%
Fig
u
r
e
5
.
Fu
s
ed
im
a
g
e
o
f
in
d
o
o
r
an
d
o
u
td
o
o
r
w
h
ite
f
lo
wer
Fin
ally
,
af
ter
im
ag
e
f
u
s
io
n
,
im
ag
es
ar
e
r
ec
o
n
s
tr
u
cted
,
an
d
th
e
ev
alu
atio
n
o
f
I
HS
an
d
R
GB
v
alu
es
o
f
th
e
f
u
s
ed
im
a
g
es
wer
e
o
b
tain
e
d
an
d
tab
u
lated
in
T
a
b
le
4
.
T
h
e
r
esu
lts
p
r
esen
ted
in
T
ab
le
4
s
h
o
ws
th
at
th
e
f
u
s
ed
im
ag
e
g
iv
es
a
r
em
ar
k
ab
le
p
er
f
o
r
m
an
ce
c
o
n
s
id
er
in
g
t
h
e
R
GB
an
d
I
HS
co
m
p
o
n
en
t
o
f
in
d
o
o
r
an
d
o
u
t
d
o
o
r
im
ag
es.
T
h
e
ex
p
er
im
en
tal
r
esu
lts
illu
s
tr
ates
th
at
th
e
d
esig
n
ed
f
r
am
e
wo
r
k
attain
s
a
n
e
x
ce
llen
t
r
ec
o
g
n
itio
n
r
ate.
T
a
b
le
5
s
h
o
ws th
e
r
esu
lts
o
f
th
e
p
er
f
o
r
m
an
ce
p
ar
am
ete
r
s
u
s
in
g
DW
T
an
d
DC
T
f
u
s
io
n
tech
n
iq
u
es.
I
n
T
ab
le
5
,
PS
NR
1
an
d
SN
R
1
g
iv
e
t
h
e
ex
p
er
im
en
tal
r
e
s
u
lts
b
etwe
en
s
o
u
r
ce
im
a
g
e
1
an
d
th
e
co
r
r
esp
o
n
d
in
g
f
u
s
ed
im
ag
e
,
an
d
lik
ewise
f
o
r
PS
NR
2
an
d
SNR
2
.
SNR
is
a
m
etr
ic
u
s
ed
to
d
eter
m
in
e
t
h
e
in
f
o
r
m
atio
n
-
to
-
n
o
is
e
r
atio
o
f
a
f
u
s
ed
im
ag
e.
T
h
e
h
ig
h
er
th
e
v
alu
e,
th
e
m
o
r
e
id
en
tical
th
e
r
ef
er
en
ce
an
d
f
u
s
e
d
im
ag
es
ar
e,
wh
er
ea
s
,
in
th
e
ca
s
e
o
f
PS
N
R
,
it
's
a
co
m
m
o
n
m
etr
ic
th
at
is
ca
lcu
lated
b
y
d
iv
id
in
g
th
e
n
u
m
b
er
o
f
g
r
ey
lev
els
in
th
e
i
m
ag
e
b
y
th
e
p
ix
el
v
alu
es
in
th
e
s
o
u
r
c
e
a
n
d
f
u
s
ed
im
ag
e.
T
h
e
f
u
s
ed
an
d
r
e
f
er
en
ce
im
ag
es
ar
e
id
en
tical
wh
en
th
e
v
alu
e
is
h
ig
h
.
T
ab
le
4
.
Per
f
o
r
m
an
ce
p
ar
am
et
er
s
in
ter
m
s
o
f
R
GB
an
d
I
HS
R
G
B
I
H
S
1
9
0
(
R)
4
3
%
(
I
)
1
7
8
(
G
)
2
4
%
(
H
)
1
4
7
(
B
)
6
6
%
(
S
)
T
ab
le
5
.
R
esu
lts
o
f
th
e
p
e
r
f
o
r
m
an
ce
p
ar
am
ete
r
s
o
b
tain
ed
f
r
o
m
d
if
f
e
r
en
t f
u
s
io
n
alg
o
r
ith
m
s
P
e
r
f
o
r
ma
n
c
e
M
e
t
r
i
c
(
d
B
)
D
C
T
D
W
T
P
S
N
R
1
1
1
4
.
0
4
1
1
3
.
3
2
P
S
N
R
2
1
1
4
.
0
4
1
1
2
.
2
9
S
N
R
1
1
1
4
.
0
0
1
1
3
.
2
8
S
N
R
2
1
1
4
.
0
1
1
1
2
.
2
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
A
r
ev
iew
o
f v
a
r
io
u
s
ima
g
e
fu
s
io
n
typ
es a
n
d
tr
a
n
s
fo
r
ms
(
A
yo
d
eji
Ola
leka
n
S
a
la
u
)
1521
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
a
cr
itical
r
ev
ie
w
o
f
v
ar
io
u
s
im
ag
e
f
u
s
io
n
ap
p
r
o
ac
h
es
was
p
r
esen
ted
.
I
n
a
d
d
itio
n
,
two
m
eth
o
d
s
wer
e
p
r
o
p
o
s
ed
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
(
DW
T
)
m
eth
o
d
an
d
d
is
cr
ete
c
o
s
in
e
tr
an
s
f
o
r
m
(
DC
T
)
m
eth
o
d
)
f
o
r
f
u
s
in
g
im
a
g
es.
T
h
e
r
esu
lts
s
h
o
w
t
h
at
h
ig
h
s
p
at
ial
r
eso
lu
tio
n
is
o
b
tain
e
d
with
tr
ad
itio
n
al
I
m
F
tech
n
iq
u
es
wh
ich
r
esu
lts
in
im
ag
e
b
lu
r
r
in
g
p
r
o
b
lem
s
.
Var
i
o
u
s
I
m
F
s
tr
ateg
ies
h
av
e
b
ee
n
p
r
esen
ted
b
y
v
ar
io
u
s
r
esear
ch
er
s
to
tack
le
th
ese
i
s
s
u
es
in
liter
atu
r
e.
I
m
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
(
im
a
g
e
n
o
r
m
ali
za
tio
n
an
d
im
a
g
e
r
eg
is
tr
atio
n
)
,
im
ag
e
d
ec
o
m
p
o
s
itio
n
,
I
m
F r
u
les,
im
ag
e
r
ec
o
n
s
tr
u
ctio
n
,
an
d
im
ag
e
q
u
ality
ev
alu
atio
n
cr
iter
ia
ar
e
am
o
n
g
t
h
e
ap
p
r
o
ac
h
es u
s
ed
to
f
u
s
e
im
ag
es.
L
ater
i
n
th
is
p
ap
er
,
two
d
if
f
er
en
t
im
a
g
es
wer
e
f
u
s
ed
b
y
u
tili
zin
g
a
s
p
atial
I
HS
tr
an
s
f
o
r
m
-
b
ased
ap
p
r
o
a
c
h
.
T
h
e
r
esu
lts
s
h
o
w
th
at
th
e
f
u
s
ed
im
ag
e
p
r
o
d
u
ce
s
b
e
tter
o
u
tco
m
es
th
an
u
s
in
g
in
d
iv
id
u
al
im
ag
es f
o
r
b
o
th
m
eth
o
d
s
u
s
ed
.
R
E
FE
R
E
N
C
E
S
[
1
]
D
.
K
.
S
a
h
u
a
n
d
M
.
P
.
P
a
r
sa
i
,
“
D
iff
e
r
e
n
t
im
a
g
e
f
u
s
i
o
n
t
e
c
h
n
i
q
u
e
s
-
A
c
r
i
t
i
c
a
l
R
e
v
i
e
w
,”
I
n
te
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
M
o
d
e
r
n
E
n
g
i
n
e
e
r
i
n
g
R
e
s
e
a
r
c
h
(
IJ
M
E
R
)
,
v
o
l
.
2
,
n
o
.
5
,
p
p
.
4
2
9
8
-
4
3
0
1
,
2
0
1
2
.
[2
]
S.
M
a
h
a
jan
a
n
d
A.
S
in
g
h
,
“
A
c
o
m
p
a
ra
ti
v
e
a
n
a
ly
sis
o
f
d
iffere
n
t
i
m
a
g
e
fu
sio
n
tec
h
n
i
q
u
e
s
,”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
8
-
15
,
2
0
1
4
.
[3
]
Q.
Wan
g
,
Y.
S
h
e
n
,
a
n
d
J.
Jin
,
“
1
9
-
P
e
rfo
rm
a
n
c
e
e
v
a
lu
a
ti
o
n
o
f
ima
g
e
fu
sio
n
tec
h
n
i
q
u
e
s
,”
Ima
g
e
Fu
si
o
n
,
p
p
.
4
6
9
-
4
9
2
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
1
6
/
b
9
7
8
-
0
-
12
-
3
7
2
5
2
9
-
5
.
0
0
0
1
7
-
2
.
[4
]
B.
O.
Ad
a
m
e
,
A.
Ola
lek
a
n
S
a
lau
,
B.
C.
S
u
b
b
a
n
n
a
,
T
.
Ti
ru
p
a
l
a
n
d
S
.
F
.
S
u
lt
a
n
a
,
"
M
u
l
ti
m
o
d
a
l
M
e
d
ica
l
Im
a
g
e
F
u
sio
n
Ba
se
d
o
n
In
t
u
it
i
o
n
isti
c
F
u
z
z
y
S
e
ts
,
"
2
0
2
0
IEE
E
I
n
ter
n
a
ti
o
n
a
l
W
o
me
n
in
E
n
g
in
e
e
rin
g
(W
IE)
Co
n
fer
e
n
c
e
o
n
El
e
c
trica
l
a
n
d
Co
mp
u
ter
En
g
in
e
e
rin
g
(W
IE
CON
-
ECE
)
,
2
0
2
0
,
p
p
.
1
3
1
-
1
3
4
,
d
o
i:
1
0
.
1
1
0
9
/
WI
ECON
-
ECE
5
2
1
3
8
.
2
0
2
0
.
9
3
9
7
9
6
3
.
[5
]
C.
R.
S
o
m
a
n
a
n
d
A.
Ja
c
o
b
,
“
DWT
b
a
se
d
ima
g
e
fu
sio
n
o
f
p
a
n
c
h
ro
m
a
ti
c
a
n
d
m
u
lt
isp
e
c
tral
ima
g
e
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
S
c
ien
c
e
a
n
d
C
o
mp
u
ti
n
g
,
v
o
l.
6
,
n
o
.
9
,
p
p
.
2
1
7
9
-
2
1
8
4
,
2
0
1
6
.
[6
]
C.
P
o
h
l
a
n
d
J.
L.
V.
G
e
n
d
e
re
n
,
“
M
u
lt
ise
n
s
o
r
ima
g
e
fu
si
o
n
in
re
m
o
te
se
n
si
n
g
:
c
o
n
c
e
p
ts,
m
e
th
o
d
s
a
n
d
a
p
p
li
c
a
ti
o
n
s
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Rem
o
te
S
e
n
sin
g
,
v
o
l
.
1
9
,
n
o
.
5
,
p
p
.
8
2
3
-
8
5
4
,
1
9
9
8
,
d
o
i:
1
0
.
1
0
8
0
/0
1
4
3
1
1
6
9
8
2
1
5
7
4
8
.
[7
]
S.
Krish
n
a
m
o
o
rth
y
a
n
d
K.
P
.
S
o
m
a
n
,
“
Im
p
lem
e
n
tatio
n
a
n
d
c
o
m
p
a
ra
ti
v
e
stu
d
y
o
f
ima
g
e
fu
sio
n
a
lg
o
rit
h
m
s
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
Ap
p
l
ica
ti
o
n
s
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
2
5
-
3
5
,
2
0
1
0
,
d
o
i:
1
0
.
5
1
2
0
/
1
3
5
7
-
1
8
3
2
.
[8
]
J.
M
ifd
a
l,
B.
Co
ll
,
N.
Co
u
rty
,
J.
F
ro
m
e
n
t
a
n
d
B
.
Ve
d
e
l,
"
Hy
p
e
rsp
e
c
tral
a
n
d
m
u
lt
is
p
e
c
tral
wa
ss
e
rste
in
b
a
ry
c
e
n
ter
fo
r
ima
g
e
fu
sio
n
,
"
2
0
1
7
IEE
E
In
ter
n
a
ti
o
n
a
l
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
S
y
mp
o
si
u
m
(IGAR
S
S
)
,
2
0
1
7
,
p
p
.
3
3
7
3
-
3
3
7
6
,
d
o
i:
1
0
.
1
1
0
9
/IG
ARSS
.
2
0
1
7
.
8
1
2
7
7
2
1
.
[9
]
E.
Va
rg
a
s,
H.
Arg
u
e
ll
o
a
n
d
J.
To
u
rn
e
re
t,
"
S
p
e
c
tral
Im
a
g
e
F
u
sio
n
f
ro
m
Co
m
p
re
ss
iv
e
M
e
a
su
re
m
e
n
ts
Us
in
g
S
p
e
c
tral
Un
m
ix
in
g
a
n
d
a
S
p
a
rse
Re
p
re
se
n
tatio
n
o
f
A
b
u
n
d
a
n
c
e
M
a
p
s,"
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
,
v
o
l
.
5
7
,
n
o
.
7
,
p
p
.
5
0
4
3
-
5
0
5
3
,
J
u
ly
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/T
G
RS
.
2
0
1
9
.
2
8
9
5
8
2
2
.
[1
0
]
V.
R.
P
a
n
d
it
a
n
d
R.
J.
B
h
iwa
n
i,
“
Im
a
g
e
fu
sio
n
i
n
re
m
o
te
se
n
sin
g
a
p
p
li
c
a
ti
o
n
s:
A
re
v
iew
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
mp
u
ter
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
1
2
0
,
n
o
.
1
0
,
p
p
.
2
2
-
3
2
,
2
0
1
5
,
d
o
i:
1
0
.
5
1
2
0
/2
1
2
6
3
-
3
8
4
6
.
[1
1
]
B.
Ra
jalin
g
a
m
a
n
d
R.
P
ri
y
a
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
m
u
lt
imo
d
a
l
m
e
d
ica
l
ima
g
e
f
u
sio
n
u
sin
g
h
y
b
rid
f
u
sio
n
a
lg
o
rit
h
m
s
fo
r
d
ise
a
se
a
n
a
ly
sis
,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Pu
re
a
n
d
A
p
p
li
e
d
M
a
th
e
ma
t
ics
,
v
o
l.
1
1
7
,
n
o
.
1
5
,
p
p
.
5
9
9
-
6
1
9
,
2
0
1
7
.
[1
2
]
K.
M
i
k
o
łajc
z
y
k
,
J.
Ow
c
z
a
rc
z
y
k
,
a
n
d
W
.
Re
ć
ko
,
“
A
tes
t
-
b
e
d
f
o
r
c
o
m
p
u
ter
-
a
ss
isted
fu
si
o
n
o
f
m
u
lt
i
-
m
o
d
a
li
t
y
m
e
d
ica
l
ima
g
e
s
,
”
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
An
a
lys
is
o
f
I
ma
g
e
s
a
n
d
Pa
t
ter
n
s
,
p
p
.
6
6
4
–
6
6
8
,
1
9
9
3
,
d
o
i:
1
0
.
1
0
0
7
/
3
-
540
-
5
7
2
3
3
-
3_89
.
[1
3
]
B.
Alfa
n
o
,
M
.
Ciam
p
i,
a
n
d
G
.
D.
P
ietro
,
“
A
wa
v
e
let
-
b
a
se
d
a
lg
o
rit
h
m
fo
r
m
u
lt
imo
d
a
l
m
e
d
ica
l
ima
g
e
fu
sio
n
,
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
S
e
ma
n
ti
c
a
n
d
Di
g
it
a
l
M
e
d
ia
T
e
c
h
n
o
lo
g
ies
,
v
o
l
4
8
1
6
,
p
p
.
1
1
7
–
1
2
0
,
2
0
0
7
,
d
o
i:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
540
-
7
7
0
5
1
-
0_13
.
[1
4
]
X.
Zh
a
n
g
,
Y.
Zh
e
n
g
,
Y.
P
e
n
g
,
W.
Li
u
a
n
d
C.
Ya
n
g
,
"
Re
se
a
rc
h
o
n
M
u
lt
i
-
M
o
d
e
M
e
d
ica
l
Im
a
g
e
F
u
sio
n
Al
g
o
ri
th
m
Ba
se
d
o
n
Wav
e
let
Tra
n
sfo
rm
a
n
d
th
e
Ed
g
e
Ch
a
ra
c
teristics
o
f
Im
a
g
e
s,"
2
0
0
9
2
n
d
I
n
ter
n
a
t
io
n
a
l
C
o
n
g
re
ss
o
n
Ima
g
e
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
,
2
0
0
9
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/CI
S
P
.
2
0
0
9
.
5
3
0
4
4
8
3
.
[1
5
]
W.
G
e
,
G
.
Yu
a
n
,
C.
Li
,
Y.
W
u
,
Y.
Zh
a
n
g
,
a
n
d
X.
X
u
,
“
CT
ima
g
e
fu
sio
n
in
t
h
e
e
v
a
l
u
a
ti
o
n
o
f
ra
d
i
a
ti
o
n
trea
tme
n
t
p
lan
n
in
g
f
o
r
n
o
n
-
sm
a
ll
c
e
ll
lu
n
g
c
a
n
c
e
r
,
”
Ch
in
e
se
-
Ge
rm
a
n
J
o
u
rn
a
l
o
f
Cl
in
ica
l
O
n
c
o
lo
g
y
,
v
o
l.
7
,
n
o
.
6
,
p
p
.
3
1
5
–
3
1
8
,
2
0
0
8
,
d
o
i:
1
0
.
1
0
0
7
/s
1
0
3
3
0
-
0
0
8
-
0
0
2
1
-
3
.
[1
6
]
C.
P
a
v
it
h
ra
a
n
d
S
.
Bh
a
rg
a
v
i,
“
F
u
si
o
n
o
f
tw
o
ima
g
e
s
b
a
se
d
o
n
wa
v
e
le
t
tran
sfo
rm
,
”
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
I
n
n
o
v
a
ti
v
e
Res
e
a
rc
h
in
S
c
ien
c
e
,
En
g
in
e
e
rin
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
,
n
o
.
5
,
p
p
.
1
8
1
4
-
1
8
1
9
,
2
0
1
3
.
[1
7
]
L.
Li
u
,
H
.
Bian
a
n
d
G
.
S
h
a
o
,
"
An
e
ffe
c
ti
v
e
wa
v
e
let
-
b
a
se
d
sc
h
e
m
e
fo
r
m
u
lt
i
-
fo
c
u
s
ima
g
e
fu
si
o
n
,
"
2
0
1
3
IEE
E
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
e
c
h
a
tro
n
ics
a
n
d
A
u
t
o
ma
ti
o
n
,
2
0
1
3
,
p
p
.
1
7
2
0
-
1
7
2
5
,
d
o
i:
1
0
.
1
1
0
9
/IC
M
A.2
0
1
3
.
6
6
1
8
1
7
5
.
[1
8
]
S
.
S
.
S
ri
a
n
d
S
.
N.
S
a
n
th
a
la
k
sh
m
i
,
“
F
u
sio
n
o
f
h
y
p
e
r
sp
e
c
tral
a
n
d
m
u
lt
isp
e
c
tral
ima
g
e
s
u
sin
g
n
o
n
-
su
b
sa
m
p
led
c
o
n
to
u
rlet
tran
sf
o
rm
d
o
m
a
in
s
,
”
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
T
re
n
d
s
a
n
d
T
e
c
h
n
o
lo
g
y
,
v
o
l.
4
7
,
n
o
.
1
,
p
p
.
6
1
-
6
7
,
2
0
1
7
,
d
o
i:
1
0
.
1
4
4
4
5
/2
2
3
1
2
8
0
3
/IJ
CTT
-
V4
7
P
1
0
7
.
[1
9
]
G
.
Bh
a
tn
a
g
a
r,
Q.
M
.
J.
W
u
a
n
d
Z.
Li
u
,
"
Dire
c
ti
v
e
C
o
n
tras
t
Ba
se
d
M
u
lt
imo
d
a
l
M
e
d
ica
l
Im
a
g
e
F
u
sio
n
in
N
S
CT
Do
m
a
in
,
"
in
IE
EE
T
ra
n
sa
c
ti
o
n
s
o
n
M
u
lt
ime
d
i
a
,
v
o
l.
1
5
,
n
o
.
5
,
p
p
.
1
0
1
4
-
1
0
2
4
,
Au
g
.
2
0
1
3
,
d
o
i:
1
0
.
1
1
0
9
/
TM
M
.
2
0
1
3
.
2
2
4
4
8
7
0
.
[2
0
]
J.
G
o
n
g
,
B
.
Wan
g
,
L.
Qia
o
,
J.
Xu
a
n
d
Z.
Z
h
a
n
g
,
"
Im
a
g
e
F
u
si
o
n
M
e
th
o
d
Ba
se
d
o
n
Im
p
r
o
v
e
d
NSCT
Tran
sfo
rm
a
n
d
P
CNN
M
o
d
e
l,
"
2
0
1
6
9
t
h
I
n
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
Co
m
p
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
De
sig
n
(I
S
CID
)
,
2
0
1
6
,
p
p
.
2
8
-
3
1
,
d
o
i:
1
0
.
1
1
0
9
/I
S
CID.2
0
1
6
.
1
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
3
,
Dec
em
b
er
20
21
:
1
5
1
5
-
1
5
2
2
1522
[2
1
]
B.
Bisw
a
s,
B.
K.
S
e
n
,
a
n
d
R.
C
h
o
u
d
h
u
ri
,
“
Re
m
o
te
se
n
si
n
g
ima
g
e
f
u
sio
n
u
sin
g
p
c
n
n
m
o
d
e
l
p
a
ra
m
e
ter
e
stim
a
ti
o
n
b
y
g
a
m
m
a
d
istri
b
u
ti
o
n
i
n
sh
e
a
rlet
d
o
m
a
in
,
”
Pro
c
e
d
i
a
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
7
0
,
p
p
.
3
0
4
–
3
1
0
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
p
r
o
c
s.2
0
1
5
.
1
0
.
0
9
8
.
[2
2
]
W.
Li
a
n
d
X.
Z
h
u
,
“
A
n
e
w
a
lg
o
rit
h
m
o
f
m
u
lt
i
-
m
o
d
a
li
ty
m
e
d
ic
a
l
ima
g
e
fu
sio
n
b
a
se
d
o
n
p
u
lse
-
c
o
u
p
le
d
n
e
u
ra
l
n
e
two
rk
s
,
”
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
N
a
t
u
ra
l
C
o
mp
u
ta
t
io
n
,
p
p
.
9
9
5
–
1
0
0
1
,
2
0
0
5
,
d
o
i:
1
0
.
1
0
0
7
/
1
1
5
3
9
0
8
7
_
1
3
1
.
[2
3
]
Q.
M
iao
,
C.
S
h
i
,
P
.
Xu
,
M
.
Y
a
n
g
,
a
n
d
Y.
S
h
i
,
“
A
n
o
v
e
l
a
lg
o
rit
h
m
o
f
ima
g
e
fu
si
o
n
u
si
n
g
sh
e
a
rlets
,”
Op
ti
c
s
Co
mm
u
n
ica
ti
o
n
s
,
v
o
l
.
2
8
4
,
n
o
.
6
,
p
p
.
1
5
4
0
–
1
5
4
7
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
1
6
/j
.
o
p
tco
m
.
2
0
1
0
.
1
1
.
0
4
8
.
[
2
4
]
S
.
S
u
m
a
n
e
t
a
l
.
,
“
I
m
a
g
e
e
n
h
a
n
c
e
m
e
n
t
u
s
i
n
g
g
e
o
m
e
t
r
i
c
m
e
a
n
f
i
l
t
e
r
a
n
d
g
a
m
m
a
c
o
r
re
c
t
i
o
n
f
o
r
W
C
E
i
m
a
g
e
s
,
”
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
N
e
u
ra
l
I
n
f
o
r
m
a
t
i
o
n
P
r
o
c
e
s
s
i
n
g
,
p
p
.
2
7
6
–
2
8
3
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
1
2
6
4
3
-
2
_
3
4
.
[2
5
]
H.
D.
Ch
e
n
g
a
n
d
X.
J.
S
h
i
,
“
A
si
m
p
le
a
n
d
e
ffe
c
ti
v
e
h
ist
o
g
ra
m
e
q
u
a
li
z
a
ti
o
n
a
p
p
r
o
a
c
h
t
o
ima
g
e
e
n
h
a
n
c
e
m
e
n
t
,
”
Dig
it
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
1
4
,
n
o
.
2
,
p
p
.
1
5
8
–
1
7
0
,
2
0
0
4
,
d
o
i:
1
0
.
1
0
1
6
/j
.
d
sp
.
2
0
0
3
.
0
7
.
0
0
2
.
[2
6
]
A.
O.
S
a
lau
a
n
d
S
.
Ja
in
,
"
F
e
a
tu
re
Ex
trac
ti
o
n
:
A
S
u
rv
e
y
o
f
t
h
e
T
y
p
e
s,
Tec
h
n
i
q
u
e
s,
Ap
p
li
c
a
ti
o
n
s,"
2
0
1
9
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
a
n
d
Co
mm
u
n
ica
ti
o
n
(IC
S
C)
,
2
0
1
9
,
p
p
.
1
5
8
-
1
6
4
,
d
o
i:
1
0
.
1
1
0
9
/IC
S
C4
5
6
2
2
.
2
0
1
9
.
8
9
3
8
3
7
1
.
[2
7
]
H.
P
a
n
g
,
M
.
Z
h
u
a
n
d
L.
G
u
o
,
"
M
u
l
ti
fo
c
u
s
c
o
lo
r
ima
g
e
fu
si
o
n
u
sin
g
q
u
a
ter
n
io
n
wa
v
e
let
tran
sf
o
rm
,
"
2
0
1
2
5
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
g
re
ss
o
n
Ima
g
e
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
,
2
0
1
2
,
p
p
.
5
4
3
-
5
4
6
,
d
o
i:
1
0
.
1
1
0
9
/CI
S
P
.
2
0
1
2
.
6
4
6
9
8
8
4
.
[2
8
]
A.
Re
id
,
F
.
Ra
m
o
s,
a
n
d
S
.
S
u
k
k
a
rieh
,
“
Ba
y
e
sia
n
fu
sio
n
f
o
r
m
u
lt
i
-
m
o
d
a
l
a
e
rial
ima
g
e
s
,
”
Ro
b
o
ti
c
s:
S
c
ien
c
e
a
n
d
S
y
ste
ms
,
2
0
1
3
,
d
o
i:
1
0
.
1
5
6
0
7
/RS
S
.
2
0
1
3
.
IX.0
2
5
.
[2
9
]
W.
Ya
n
g
,
J.
He
,
H.
Wan
g
,
a
n
d
Y.
F
e
n
g
,
“
A
m
u
lt
i
-
sp
e
c
tral
ima
g
e
fu
sio
n
a
lg
o
rit
h
m
b
a
se
d
o
n
P
C
A
a
n
d
re
d
-
b
lac
k
wa
v
e
let
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
ig
n
a
l
Pro
c
e
ss
in
g
,
Ima
g
e
Pr
o
c
e
ss
in
g
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
,
v
o
l.
9
,
n
o
.
5
,
p
p
.
25
-
4
0
,
2
0
1
6
,
d
o
i:
1
0
.
1
4
2
5
7
/
ij
sip
.
2
0
1
6
.
9
.
5
.
0
3
.
[3
0
]
T.
P
e
li
,
E.
P
e
li
,
K.
K.
El
li
s,
a
n
d
R.
S
tah
l
,
“
M
u
lt
is
p
e
c
tral
ima
g
e
fu
si
o
n
fo
r
v
isu
a
l
d
is
p
lay
,”
S
e
n
so
r
Fu
si
o
n
:
Arc
h
it
e
c
tu
re
,
Al
g
o
rit
h
ms
a
n
d
Ap
p
li
c
a
t
io
n
s I
II
,
v
o
l.
3
7
1
9
,
p
p
.
3
5
9
-
3
6
8
,
1
9
9
9
,
d
o
i
:
1
0
.
1
1
1
7
/1
2
.
3
4
1
3
6
0
.
[3
1
]
C.
He
,
Q.
Li
u
,
H.
Li
,
a
n
d
H.
Wan
g
,
“
M
u
lt
imo
d
a
l
m
e
d
ica
l
ima
g
e
fu
sio
n
b
a
se
d
o
n
IHS
a
n
d
P
CA
,”
Pro
c
e
d
ia
En
g
i
n
e
e
rin
g
,
v
o
l.
7
,
p
p
.
2
8
0
-
2
8
5
,
2
0
1
0
,
d
o
i:
1
0
.
1
0
1
6
/
j.
p
r
o
e
n
g
.
2
0
1
0
.
1
1
.
0
4
5
.
[3
2
]
S
.
Klo
n
u
s
a
n
d
M
.
E
h
lers
,
“
P
e
rfo
r
m
a
n
c
e
o
f
e
v
a
lu
a
ti
o
n
m
e
th
o
d
s
i
n
i
m
a
g
e
fu
sio
n
,
”
2
0
0
9
1
2
th
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
ti
o
n
F
u
sio
n
,
2
0
0
9
,
p
p
.
1
4
0
9
-
1
4
1
6
.
[3
3
]
B.
P
a
l,
S
.
M
a
h
a
jan
,
a
n
d
S
.
Ja
in
,
“
A
Co
m
p
a
ra
ti
v
e
S
tu
d
y
o
f
Trad
i
ti
o
n
a
l
Im
a
g
e
F
u
sio
n
Tec
h
n
i
q
u
e
s
wit
h
a
No
v
e
l
Hy
b
rid
M
e
th
o
d
,
”
2
0
2
0
I
n
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Co
mp
u
t
a
ti
o
n
a
l
Per
fo
r
ma
n
c
e
Eva
lu
a
ti
o
n
(Co
mPE)
,
2
0
2
0
,
p
p
.
8
2
0
-
8
2
5
,
d
o
i:
1
0
.
1
1
0
9
/Co
m
P
E4
9
3
2
5
.
2
0
2
0
.
9
2
0
0
0
1
7
.
[3
4
]
A.
Vijan
,
P
.
Du
b
e
y
,
a
n
d
S
.
Ja
in
,
“
Co
m
p
a
ra
ti
v
e
An
a
ly
sis
o
f
Va
rio
u
s
Im
a
g
e
F
u
si
o
n
Tec
h
n
iq
u
e
s
fo
r
Bra
in
M
a
g
n
e
ti
c
Re
so
n
a
n
c
e
Im
a
g
e
s
,
”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
1
6
7
,
p
p
.
4
1
3
–
4
2
2
,
2
0
2
0
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
2
0
.
0
3
.
2
5
0
.
[3
5
]
L.
Ca
o
,
L.
Jin
,
H.
Tao
,
G
.
Li
,
Z.
Zh
u
a
n
g
,
a
n
d
Y.
Zh
a
n
g
,
“
M
u
lt
i
-
F
o
c
u
s
Im
a
g
e
F
u
sio
n
Ba
se
d
o
n
S
p
a
t
ial
F
re
q
u
e
n
c
y
i
n
Disc
re
te
Co
sin
e
Tran
sfo
rm
Do
m
a
in
,
”
in
IE
EE
S
ig
n
a
l
Pr
o
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
2
2
,
n
o
.
2
,
p
p
.
2
2
0
-
2
2
4
,
F
e
b
.
2
0
1
5
,
d
o
i:
1
0
.
1
1
0
9
/
LS
P
.
2
0
1
4
.
2
3
5
4
5
3
4
.
[3
6
]
S
.
P
.
Da
k
u
a
a
n
d
J.
Ab
i
-
Na
h
e
d
,
“
Co
n
tras
t
e
n
h
a
n
c
e
m
e
n
t
in
wa
v
e
let
d
o
m
a
in
fo
r
g
ra
p
h
-
b
a
se
d
se
g
m
e
n
t
a
ti
o
n
i
n
m
e
d
i
c
a
l
ima
g
in
g
,”
Pro
c
e
e
d
i
n
g
s
o
f
th
e
Ei
g
h
t
h
I
n
d
i
a
n
Co
n
fer
e
n
c
e
o
n
C
o
m
p
u
ter
V
isio
n
,
Gr
a
p
h
ics
a
n
d
Ima
g
e
Pro
c
e
ss
in
g
-
ICVGIP
’1
2
,
n
o
.
7
6
,
2
0
1
2
,
p
p
.
1
-
5
,
d
o
i:
1
0
.
1
1
4
5
/2
4
2
5
3
3
3
.
2
4
2
5
4
0
9
.
[3
7
]
Y.
Wan
-
q
ian
g
a
n
d
Z.
Ch
u
n
-
s
h
e
n
g
,
“
M
u
lt
i
sp
e
c
tral
ima
g
e
fu
si
o
n
m
e
th
o
d
b
a
se
d
o
n
wa
v
e
let
tran
sf
o
rm
a
ti
o
n
,”
T
h
e
In
ter
n
a
t
io
n
a
l
Arc
h
ive
s
o
f
t
h
e
Ph
o
t
o
g
ra
mm
e
try
,
Rem
o
te
S
e
n
si
n
g
a
n
d
S
p
a
ti
a
l
I
n
fo
rm
a
ti
o
n
S
c
ien
c
e
s
,
v
o
l
.
3
7
,
p
p
.
1
2
6
1
-
1
2
6
6
,
2
0
0
8
.
[3
8
]
R.
S
o
u
n
d
ra
p
a
n
d
iy
a
n
,
M
.
Ka
ru
p
p
iah
,
S
.
Ku
m
a
ri,
S
.
K
.
T
y
a
g
i,
F
.
Wu
,
a
n
d
K
-
H.
J
u
n
g
,
“
An
e
fficie
n
t
DWT
a
n
d
in
tu
i
ti
o
n
isti
c
fu
z
z
y
b
a
se
d
m
u
lt
i
m
o
d
a
li
ty
m
e
d
ica
l
ima
g
e
fu
si
o
n
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Im
a
g
in
g
S
y
ste
ms
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
7
,
n
o
.
2
,
p
p
.
1
1
8
-
13
2
,
2
0
1
7
,
d
o
i:
1
0
.
1
0
0
2
/i
m
a
.
2
2
2
1
6
.
[3
9
]
S
.
P
.
Da
k
u
a
,
J.
Ab
i
n
a
h
e
d
,
a
n
d
A.
Al
-
An
sa
ri
,
“
A
P
CA
-
b
a
se
d
a
p
p
ro
a
c
h
f
o
r
b
ra
i
n
a
n
e
u
ry
sm
se
g
m
e
n
tatio
n
,”
M
u
lt
i
d
ime
n
si
o
n
a
l
S
y
ste
ms
a
n
d
S
i
g
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
2
9
,
p
p
.
2
5
7
–
2
7
7
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
0
7
/s1
1
0
4
5
-
016
-
0
4
6
4
-
6
.
Evaluation Warning : The document was created with Spire.PDF for Python.