I
n
t
ern
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
ces
i
n
A
p
p
l
i
ed
S
ci
en
ces
(
I
J
A
A
S
)
V
o
l
.
7
,
N
o
.
1
,
M
ar
ch
20
1
8
,
p
p
.
38
~
45
I
S
S
N
:
225
2
-
88
14
,
D
O
I
:
10.
115
9
1/
i
ja
a
s
.
v
7.
i
1.
pp
38
-
45
38
Jo
u
r
n
al
h
om
e
pa
ge
:
h
t
t
p
:
/
/
i
a
e
s
co
r
e
.
c
o
m/
o
n
l
i
n
e
/
i
n
d
e
x
.
p
h
p
/
I
J
A
A
S
A
Fu
s
io
n
B
a
s
e
d
V
is
ib
ilit
y
E
n
h
an
cem
en
t
of
Si
ng
l
e
U
nde
rw
a
t
e
r
H
azy
I
m
a
ge
S
am
ar
t
h
B
or
k
ar
,
S
a
nj
i
v
V
.
B
o
nde
D
e
pa
rt
m
e
nt
o
f E
l
e
c
t
roni
c
s
a
nd
T
e
l
e
c
om
m
uni
c
a
t
i
on E
ngi
n
e
e
ri
ng
,
S
hri
.
G
uru G
obi
nd
S
i
nghj
i
Ins
t
i
t
ut
e
of
E
ng
i
ne
e
r
i
ng a
nd
T
e
c
hn
ol
o
g
y
,
S
RT
M
U
N
U
ni
ve
rs
i
t
y
,
Indi
a
A
rt
i
cl
e
I
n
f
o
A
B
S
T
RA
C
T
Ar
t
i
c
l
e
h
i
s
t
o
r
y
:
R
ecei
v
ed
Ma
y
2
1,
2
017
Re
v
i
s
e
d
J
an
2
3
,
201
7
A
ccep
t
e
d
F
eb
11
,
2
01
8
U
nde
rw
a
t
e
r i
m
a
ge
s
a
re
prone
t
o c
ont
ra
s
t
l
o
s
s
,
l
i
m
i
t
e
d vi
s
i
bi
l
i
t
y
,
a
nd
unde
s
i
ra
bl
e
c
ol
or c
a
s
t
.
F
or
unde
rw
a
t
e
r
c
o
m
put
e
r vi
s
i
on a
nd pa
t
t
e
r
n
re
c
ogni
t
i
on a
l
go
ri
t
hm
s
,
t
he
s
e
i
m
a
ge
s
ne
e
d t
o
be
pre
-
pro
c
e
s
s
e
d.
W
e
ha
ve
a
ddre
s
s
e
d a
nov
e
l
s
ol
ut
i
on t
o
t
hi
s
probl
e
m
b
y pr
opos
i
ng ful
l
y a
ut
om
a
t
e
d
unde
rw
a
t
e
r
i
m
a
ge
de
ha
z
i
ng us
i
ng m
ul
t
i
m
oda
l
D
W
T
fus
i
on.
Input
s
for t
he
c
om
bi
na
t
i
on
a
l
i
m
a
ge
fus
i
on s
c
he
m
e
a
r
e
de
r
i
ve
d from
S
i
ngul
a
r V
a
l
u
e
D
e
c
om
pos
i
t
i
on (
S
V
D
) a
nd D
i
s
c
re
t
e
W
a
v
e
l
e
t
T
r
a
ns
form
(D
W
T
) for c
ont
ra
s
t
e
nha
nc
e
m
e
nt
i
n
H
S
V
c
ol
or s
pa
c
e
a
nd
c
ol
or
c
ons
t
a
nc
y
us
i
ng
S
ha
de
s
of G
ra
y
a
l
gori
t
hm
re
s
pe
c
t
i
v
e
l
y
.
T
o a
pp
ra
i
s
e
t
h
e
w
ork c
onduc
t
e
d,
t
h
e
vi
s
ua
l
a
nd
qua
nt
i
t
a
t
i
v
e
a
n
a
l
y
s
i
s
i
s
pe
rform
e
d.
T
he
re
s
t
ore
d i
m
a
ge
s
de
m
ons
t
ra
t
e
i
m
prove
d c
ont
ra
s
t
a
nd e
ffe
c
t
i
ve
e
nha
nc
e
m
e
nt
i
n ove
ra
l
l
i
m
a
ge
qua
l
i
t
y
a
n
d
vi
s
i
bi
l
i
t
y
.
T
h
e
propos
e
d a
l
g
ori
t
hm
pe
rform
s
on pa
r w
i
t
h t
he
re
c
e
nt
unde
rw
a
t
e
r
de
h
a
z
i
ng t
e
c
hn
i
que
s
.
Ke
y
wo
r
d
:
C
ol
or
c
o
ns
t
a
nc
y
C
ont
r
a
s
t
e
n
ha
n
c
e
m
e
nt
I
m
ag
e
d
eh
azi
n
g
I
m
a
ge
f
us
i
on
U
n
d
e
r
w
at
er
i
m
ag
e
r
es
t
o
r
at
i
o
n
Copy
r
i
ght
©
201
8
Ins
t
i
t
ut
e
o
f
A
d
v
anc
e
d
E
ngi
n
e
e
r
i
ng and S
c
i
e
nc
e
.
A
l
l
ri
g
h
t
s re
se
rv
e
d
.
C
or
r
e
s
po
n
di
n
g
A
u
t
h
or
:
S
a
m
a
rt
h
B
o
r
k
a
r,
Co
m
p
u
t
e
r
V
i
s
i
o
n
a
n
d
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
l
a
b
.
D
e
pa
r
t
m
e
nt
of
E
l
e
c
t
r
oni
c
s
a
n
d
T
e
l
e
c
om
m
uni
c
a
t
i
on
E
ngi
ne
e
r
i
n
g,
S
h
r
i
.
Gur
u
Gob
ind
S
i
n
ghj
i
I
n
s
t
i
t
ut
e
of
E
n
gi
ne
e
r
i
ng
a
n
d
T
e
c
hn
ol
o
gy
,
V
is
hn
upu
r
i
-
N
a
nde
d,
M
a
ha
r
a
s
ht
r
a
,
4
3
16
0
6,
I
n
di
a
.
E
m
a
i
l
:
bor
ka
r
s
a
m
a
r
t
h@
s
ggs
.
a
c
.
i
n
1.
I
N
T
R
O
D
U
C
T
I
O
N
U
n
de
r
w
a
t
e
r
i
m
a
ge
s
a
r
e
i
n
h
e
r
e
nt
l
y
da
r
k i
n na
t
ur
e
a
r
e
a
l
s
o pl
a
gue
d
b
y
va
r
i
o
us
s
m
a
l
l
s
us
pe
ndi
ng
pa
r
t
i
c
l
e
s
a
n
d
m
a
r
i
ne
s
n
ow
i
n a
n a
q
ue
o
us
m
e
di
um
.
T
o i
nc
r
e
a
s
e
t
he
vi
s
i
bi
l
i
t
y
r
a
nge
a
nd
vi
s
i
o
n
de
pt
h,
a
n
a
r
t
i
f
i
c
i
a
l
l
i
g
h
t
i
s
u
t
i
l
i
z
e
d
.
T
h
e
r
a
y
s
o
f
l
i
g
h
t
a
r
e
s
c
a
t
t
e
r
e
d
by
pa
r
t
i
c
l
e
s
i
n
t
he
un
de
r
w
a
t
e
r
m
e
di
um
a
nd
a
l
o
ng
wi
t
h
c
ol
o
r
a
t
t
e
nua
t
i
on
r
e
s
ul
t
s
i
n p
r
o
bl
e
m
s
s
uc
h a
s
c
o
nt
r
a
s
t
r
e
du
c
t
i
on,
bl
u
r
r
i
n
g
of
a
n i
m
a
ge
a
nd c
ol
or
l
os
s
dr
i
vi
n
g
t
he
im
a
ge
s
be
y
on
d r
e
c
o
gni
t
i
on
.
F
or
u
nde
r
wa
t
e
r
a
ppl
i
c
a
t
i
ons
s
uc
h a
s
obs
e
r
va
t
i
on
o
f
t
he
oc
e
a
ni
c
fl
o
o
r,
m
oni
t
or
i
ng
of
f
i
s
h,
s
t
u
dy
of
c
or
a
l
r
e
e
f
e
t
c
.
de
m
a
nds
de
h
a
z
i
ng
of
i
m
a
ge
s
s
o a
s
t
o r
e
c
ove
r
c
ol
or
,
e
nha
nc
e
v
i
s
i
b
i
l
i
t
y
a
n
d
i
n
c
r
e
a
s
e
v
i
s
u
a
l
d
e
t
a
i
l
s
p
r
e
s
e
n
t
i
n
t
h
e
d
e
g
r
a
d
e
d
i
m
a
g
e
f
o
r
c
o
m
p
u
t
e
r
v
i
s
i
o
n
a
n
d
o
b
j
e
c
t
r
e
c
o
g
n
i
t
i
o
n
.
I
n
ab
s
e
n
ce
o
f
a
n
y
d
eh
azi
n
g
t
ec
hni
que
,
t
he
pe
r
f
o
r
m
a
nc
e
a
nd
us
a
bi
l
i
t
y
of
a
s
t
a
nda
r
d
e
n
ha
nc
e
m
e
nt
a
l
g
o
r
i
t
h
m
m
a
y
f
a
i
l
t
o
p
r
o
d
u
c
e
d
e
s
i
r
a
b
l
e
r
e
s
u
l
t
s
.
B
as
i
cal
l
y
,
d
eh
azi
n
g
i
s
a
p
r
o
ces
s
t
o
r
es
t
o
r
e
t
h
e c
o
n
t
r
as
t
o
f
an
i
m
ag
e.
T
r
ad
i
t
i
o
n
al
a
p
p
r
o
ac
h
es
l
i
k
e
h
i
s
t
o
g
r
a
m
e
q
u
a
l
i
z
a
t
i
o
n
,
h
i
s
t
o
g
r
a
m
s
p
e
c
i
f
i
c
a
t
i
on,
a
n
d
va
r
i
o
us
ot
he
r
c
ont
r
a
s
t
e
n
ha
nc
e
m
e
nt
t
e
c
h
ni
q
ue
s
do
n
ot
de
l
i
ve
r
de
s
i
r
e
d
out
p
ut
im
a
ge
s
.
Ove
r
t
he
l
a
s
t
f
e
w y
e
a
r
s
,
di
v
e
r
s
e
t
e
c
hni
que
s
ha
ve
be
e
n p
r
op
os
e
d t
o r
e
s
t
or
e
t
he
u
n
d
e
r
w
at
er
h
a
zy
i
m
ag
es
.
T
h
e d
eh
azi
n
g
ap
p
r
o
ac
h
es
can
b
e
g
r
o
u
p
ed
i
n
t
o
s
o
f
t
w
ar
e b
as
ed
an
d
ha
r
dwa
r
e
ba
s
e
d.
H
a
r
d
w
a
r
e
b
a
s
e
d
t
e
c
h
n
i
q
u
e
s
r
e
f
e
r
t
o
u
t
i
l
i
z
a
t
i
o
n
o
f
p
o
l
a
r
i
z
a
t
i
o
n
f
i
l
t
e
r
[1
]
,
r
a
nge
ga
t
e
d i
m
a
gi
n
g
[2
]
a
nd
u
s
i
ng
m
ult
i
pl
e
unde
r
wa
t
e
r
i
m
a
ge
s
[3
]
,
w
h
er
eas
s
o
f
t
w
a
r
e
ba
s
e
d
t
e
c
hni
que
s
a
r
e
f
u
r
t
he
r
gr
o
upe
d
i
nt
o
a
p
hy
s
i
c
a
l
m
ode
l
b
a
s
e
d
a
n
d
non
-
phy
s
i
c
a
l
m
ode
l
s
.
I
n
p
hy
s
i
c
a
l
m
ode
l
u
nde
r
w
a
t
e
r
i
m
a
ge
pr
oc
e
s
s
i
ng
,
pa
r
a
m
e
t
e
r
s
o
f
t
he
m
ode
l
a
r
e
e
s
t
im
a
te
d a
nd
t
he
n
r
e
s
t
o
r
a
t
i
on i
s
a
c
hi
e
ve
d.
E
s
t
i
m
a
t
i
ng t
he
de
pt
h o
f
u
nde
r
w
a
t
e
r
ha
z
e
i
s
t
he
m
a
jor
hi
n
d
r
a
nc
e
i
n s
uc
h m
ode
l
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
A
A
S
I
S
S
N
:
225
2
-
88
14
A
F
u
s
i
o
n
bas
e
d
V
i
s
i
bi
l
i
t
y
E
n
ha
nc
e
m
e
nt
of
S
i
ngl
e
U
n
de
r
w
a
t
e
r
H
az
y
I
m
a
g
e
(
Sa
m
ar
t
h
B
o
r
k
ar
)
39
R
ecen
t
l
y
p
h
y
s
i
cal
m
o
d
el
-
b
as
e
d
t
ech
n
i
q
u
es
ha
v
e
ga
i
ne
d
wi
d
e
a
t
t
e
nt
i
on.
A
pi
o
ne
e
r
i
ng
w
or
k
i
n
t
hi
s
di
r
e
c
t
i
on
by
H
e
e
t
a
l
.
,
b
a
s
e
d o
n
da
r
k c
ha
n
ne
l
p
r
i
o
r
(
D
C
P
)
us
i
ng
m
i
nim
um
pi
xe
l
i
nt
e
n
s
i
t
y
f
or
e
a
c
h
of
t
he
t
h
r
e
e
c
ha
n
ne
l
s
i
n
l
o
cal
p
at
ch
es
t
o
o
b
t
ai
n
t
h
e
d
ep
t
h
o
f
h
aze
ch
an
g
e
d
t
h
e
f
u
t
u
r
e co
u
r
s
e o
f
r
es
ea
r
ch
i
n
i
m
ag
e d
eh
a
zi
n
g
[4
]
.
Ca
r
l
e
v
a
r
i
s
-
Bi
a
n
c
o
et
al
.
p
r
op
os
e
d de
ha
z
i
ng
ba
s
e
d o
n
t
he
a
t
t
e
nua
t
i
o
n
d
i
f
f
e
r
en
ce
b
et
w
ee
n
R
G
B
co
l
o
r
ch
an
n
el
s
[5
]
.
C
hi
a
n
g a
n
d C
he
n
pr
e
s
e
nt
e
d
wa
ve
l
e
n
gt
h
c
om
pe
ns
a
t
i
on
a
nd de
ha
z
i
n
g
ba
s
e
d on
m
odi
f
i
e
d
D
CP
[6
]
.
F
o
l
l
o
w
i
n
g
t
h
i
s
m
e
t
h
o
d
,
u
n
d
e
r
w
a
t
e
r
i
m
a
g
e
r
e
s
t
o
r
a
t
i
o
n
u
s
i
n
g
j
o
i
n
t
t
r
i
l
a
t
e
r
a
l
f
i
l
t
e
r
[7
]
,
ba
s
e
d on l
e
a
s
t
a
t
t
e
nua
t
i
n
g
c
ol
or
c
ha
nne
l
[8
]
,
co
n
t
r
as
t
en
h
a
n
ce
m
en
t
f
o
r
u
n
d
er
w
at
er
t
u
r
b
i
d
i
m
ag
es
[9
]
w
a
s
p
r
e
s
e
n
t
e
d
.
B
u
t
s
t
i
l
l
,
un
de
r
wa
t
e
r
de
ha
z
i
n
g
ba
s
e
d
on t
he
phy
s
i
c
a
l
f
o
un
da
t
i
o
n
f
r
om
a
n or
i
gi
na
l
i
m
a
ge
i
s
a
c
ha
l
l
e
n
gi
n
g p
r
o
bl
e
m
o
w
i
n
g
t
o
s
t
a
t
i
s
t
i
c
a
l
p
r
i
o
r
a
s
s
u
m
p
t
i
o
n
s
.
M
e
t
ho
ds
ba
s
e
d o
n t
he
n
on
-
p
h
y
s
i
cal
m
o
d
el
ar
e p
r
e
s
en
t
e
d
b
y
v
ar
i
o
u
s
r
e
s
ear
ch
e
r
s
.
I
n
t
eg
r
at
e
d c
ol
or
m
ode
l
ba
s
e
d
u
nde
r
wa
t
e
r
i
m
a
ge
e
n
ha
nc
e
m
e
nt
i
s
pr
e
s
e
nt
e
d
i
n
[
10
]
a
n
d
u
ns
upe
r
vi
s
e
d
c
ol
o
r
c
o
r
r
e
c
t
i
o
n
t
e
c
hni
qu
e
ba
s
e
d o
n hi
s
t
o
gr
a
m
s
t
r
e
t
c
hi
ng a
n
d c
ol
or
b
a
l
a
nc
e
wa
s
pr
op
os
e
d i
n
[1
1
]
.
Ba
z
e
i
l
l
e
et
a
l
.
pr
op
os
e
d s
e
r
i
e
s
o
f
f
i
l
t
e
r
s
t
o
e
nha
n
c
e
c
o
nt
r
a
s
t
,
a
dj
us
t
c
ol
or
s
a
n
d
s
up
p
r
e
s
s
noi
s
e
[
12
]
.
A
nc
ut
i
e
t
a
l
.
pr
e
s
e
nt
e
d
i
ns
pi
r
i
n
g
w
o
r
k
i
n
t
h
e
f
i
e
l
d of
un
de
r
w
a
t
e
r
i
m
a
ge
e
nha
nc
e
m
e
nt
us
i
n
g L
a
pl
a
c
i
a
n py
r
a
m
i
d de
c
om
pos
i
t
i
o
n t
he
r
e
by
i
nc
r
e
a
s
i
ng
co
n
t
r
as
t
[1
3
]
.
I
n
t
hi
s
m
e
t
hod,
t
wo
i
np
ut
s
t
o
f
us
i
o
n
f
r
a
m
e
wo
r
k
a
r
e
de
r
i
ve
d
f
r
om
t
he
or
i
gi
n
a
l
un
de
r
w
a
t
e
r
i
m
a
ge
us
i
n
g w
hi
t
e
ba
l
a
nc
i
ng t
e
c
h
ni
que
a
n
d c
ol
or
c
or
r
e
c
t
i
on t
e
c
h
ni
q
ue
a
p
pl
i
e
d
t
o s
i
n
gl
e
ha
z
y
un
de
r
wa
t
e
r
i
m
a
ge
s
.
W
e
i
g
h
t
s
f
o
r
t
h
e f
u
s
i
o
n
p
r
o
ces
s
i
n
cl
u
d
e
d
L
ap
l
aci
an
c
o
n
t
r
as
t
,
l
o
cal
co
n
t
r
as
t
,
S
al
i
en
cy
an
d
d
e
g
r
ee
o
f
e
x
p
o
se
d
n
e
ss.
A
m
e
t
hod
ba
s
e
d o
n R
e
t
i
ne
x
w
a
s
p
r
o
p
os
e
d
by
F
u
e
t
a
l
.
t
o ha
n
dl
e
bl
u
r
r
i
n
g a
n
d u
nde
r
e
x
pos
u
r
e
o
f
u
n
d
e
r
w
at
er
i
m
ag
es
[1
4
]
.
S
he
ng
e
t
a
l
.
r
e
s
t
o
r
e
d bl
ur
r
e
d a
n
d
de
f
oc
us
s
e
d
und
e
r
w
a
te
r
im
a
g
e
s
u
s
ing
B
ior
tho
gon
a
l
w
a
v
e
l
e
t
t
ra
n
s
fo
rm
[
15]
.
A
m
i
ds
t
a
l
l
t
he
s
e
un
de
r
wa
t
e
r
de
ha
z
i
ng a
l
g
or
i
t
hm
s
i
t
i
s
a
r
d
u
ous
t
o pi
c
k
t
he
be
s
t
of
t
he
a
va
i
l
a
bl
e
a
l
go
r
i
t
hm
s
on a
c
c
ou
nt
o
f
t
he
a
bs
e
nc
e
of
g
r
ou
n
d t
r
ut
h i
m
a
ge
s
.
T
he
r
e
i
s
a
n i
nhe
r
e
nt
n
e
e
d f
or
c
r
e
a
t
i
o
n o
f
a
s
t
an
d
a
r
d
d
at
ab
as
e i
n
u
n
d
e
r
w
at
er
i
m
ag
i
n
g
s
ci
en
ce.
O
ur
s
t
r
a
t
e
gy
i
s
ba
s
e
d
on m
ul
t
i
-
r
e
s
ol
ut
i
o
n
D
W
T
f
us
i
on
f
r
a
m
e
wor
k.
T
h
e
t
w
o i
n
p
ut
s
t
o
f
us
i
on a
r
e
de
r
i
ve
d
us
i
n
g e
f
f
e
c
t
i
ve
c
ont
r
a
s
t
e
nha
nc
e
m
e
nt
a
l
go
r
i
t
hm
a
nd r
ob
us
t
c
ol
o
r
c
o
ns
t
a
nc
y
a
l
gor
i
t
hm
.
T
he
f
us
e
d im
a
ge
i
s
t
he
n s
u
b
je
c
t
e
d t
o c
o
nt
r
a
s
t
s
t
r
e
t
c
hi
ng
o
p
e
r
a
t
i
on t
o
im
pr
ove
t
he
g
l
o
b
a
l
c
o
n
t
r
a
s
t
a
n
d
v
i
s
i
b
i
l
i
t
y
o
f
d
a
r
k
r
e
g
i
o
n
s
.
T
he
r
e
m
a
i
nde
r
of
t
hi
s
a
r
t
i
c
l
e
i
s
a
s
or
ga
ni
z
e
d.
I
n S
e
c
t
i
on
2,
we
d
e
s
c
r
i
be
t
he
pr
o
p
os
e
d un
de
r
w
a
t
e
r
d
eh
azi
n
g
al
g
o
r
i
t
h
m
i
n
d
et
ai
l
r
eg
ar
d
i
n
g
t
h
e c
h
o
i
ce o
f
s
el
ect
i
o
n
o
f
co
l
o
r
co
n
s
t
an
cy
al
g
o
r
i
t
h
m
,
d
i
s
cr
et
e w
av
el
et
t
r
a
ns
f
o
r
m
(
D
W
T
)
f
us
i
o
n,
a
nd
c
ol
or
e
n
ha
nc
e
m
e
nt
.
I
n
S
e
c
t
i
on
3,
we
r
e
po
r
t
t
he
o
ut
c
om
e
s
of
qua
l
i
t
a
t
i
ve
a
n
d
qua
nt
i
t
a
t
i
ve
a
n
a
l
y
s
i
s
a
nd
l
a
s
t
l
y
,
c
o
nc
l
us
i
ons
a
r
e
out
l
i
ne
d
i
n
S
e
c
t
i
on
4.
2.
P
R
O
P
O
SE
D
R
ES
EA
R
C
H
M
ETH
O
D
I
n t
hi
s
pa
pe
r
,
we
pr
op
os
e
t
h
e
e
n
ha
nc
e
m
e
n
t
o
f
s
i
n
g
l
e
u
n
d
e
r
w
a
t
e
r
i
m
a
g
e
s
b
a
s
e
d
o
n
m
u
l
t
i
r
e
s
o
l
u
t
i
o
n
D
WT
fu
s
i
o
n
.
We
g
e
n
er
at
e
t
he
t
wo i
np
ut
s
f
or
t
h
e
f
u
s
i
o
n f
r
a
m
e
w
o
r
k
f
r
om
c
ont
r
a
s
t
e
nha
nc
e
d a
n
d
c
ol
or
c
on
s
t
a
nc
y
a
l
g
o
r
i
t
hm
f
r
om
t
he
or
i
gi
na
l
i
n
p
ut
im
a
ge
.
T
he
r
e
s
t
or
a
t
i
o
n o
f
t
he
ha
z
y
i
m
a
ge
i
s
s
t
r
o
ngl
y
de
pe
n
de
n
t
on t
he
s
e
l
e
c
t
i
on
of
i
n
put
s
.
T
he
ne
e
d f
or
t
he
s
e
l
e
c
t
i
on of
t
he
s
e
t
w
o i
np
ut
s
i
s
a
s
e
xpl
a
i
ne
d i
n f
ol
l
ow
i
n
g
s
ub
s
e
c
t
i
on
s
.
T
he
bl
oc
k
di
a
g
r
a
m
of
t
he
pr
op
os
e
d
a
l
g
or
i
t
hm
i
s
a
s
s
ho
w
n
i
n
F
i
gu
r
e
1.
F
i
gu
r
e
1.
S
ch
em
a
t
i
c
D
i
ag
r
am
of
P
r
o
p
os
e
d
A
l
go
r
i
t
hm
fo
r
S
i
ngl
e
U
nde
r
wa
t
e
r
I
m
a
ge
E
nha
nc
e
m
e
nt
2
.
1
O
b
t
a
i
n
i
ng
C
o
n
t
r
as
t
E
n
h
an
c
e
d
I
m
age
U
n
d
e
r
w
a
t
e
r
i
m
a
g
e
s
s
u
f
f
e
r
f
r
o
m
l
o
w
c
o
n
t
r
a
s
t
d
u
e
t
o
d
i
m
i
n
i
s
h
e
d
i
l
l
u
m
i
n
a
t
i
o
n
.
T
h
e
t
r
a
d
i
t
i
o
n
a
l
c
o
n
t
r
a
s
t
e
nha
nc
e
m
e
nt
t
e
c
hni
que
s
e
x
hi
bi
t
s
e
ve
r
e
l
im
it
a
t
i
ons
i
n
un
de
r
w
a
t
e
r
i
m
a
gi
n
g.
S
o i
n
t
hi
s
w
o
r
k
we
a
d
opt
e
d a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
252
-
88
14
IJ
A
A
S
V
o
l
.
7
,
N
o
.
1
,
Ma
r
c
h
20
18
:
3
8
–
45
40
m
odi
f
i
e
d S
V
D
a
nd
D
W
T
ba
s
e
d t
e
c
h
ni
q
ue
a
s
pr
e
s
e
nt
e
d i
n
[
16]
.
W
e
t
a
r
g
e
t
i
l
l
u
m
i
n
a
t
i
o
n
c
o
m
p
o
n
e
n
t
o
f
t
h
e
un
de
r
wa
t
e
r
i
m
a
ge
.
W
e
a
p
pl
y
c
o
nt
r
a
s
t
e
nha
nc
e
m
e
nt
t
o D
W
T
L
L
s
ub
-
ba
n
d of
V
p
la
ne
u
s
ing
t
h
e
S
V
D a
nd
D
W
T
c
om
bi
na
t
i
ona
l
m
e
t
hod t
o s
ol
ve
t
he
pr
o
bl
e
m
of
l
ow c
o
nt
r
a
s
t
.
T
hi
s
i
l
lum
i
na
t
i
on i
nf
o
r
m
a
ti
on i
s
e
xhi
bi
t
e
d
i
n s
i
ng
ul
a
r
va
l
ue
m
a
t
r
i
x of
S
V
D
.
W
e
m
o
di
f
y
t
he
c
oe
f
f
i
c
i
e
nt
s
of
s
i
ng
ul
a
r
va
l
ue
m
a
tr
i
x t
o
obt
a
i
n
de
s
i
r
e
d
e
n
h
a
n
c
e
m
e
n
t
i
n
i
l
l
u
m
i
n
a
t
i
on
c
om
pone
nt
a
nd
ot
he
r
de
t
a
i
l
s
i
n
S
V
D
a
r
e
not
a
l
t
e
r
e
d.
A
l
s
o
,
i
n
t
h
e u
n
d
er
w
at
er
s
c
en
ar
i
o
,
t
he
f
o
r
m
a
t
ion
of
ha
z
e
i
s
a
uni
f
o
r
m
i
nt
e
ns
i
t
y
f
unc
t
i
o
n,
a
nd t
he
ha
z
e
af
f
ect
ed
ar
eas
h
a
v
e an
al
o
g
o
u
s
l
y
m
o
r
e b
r
i
g
h
t
n
es
s
.
T
h
i
s
m
ak
es
w
a
v
el
et
o
r
s
cal
e s
p
a
ce r
ep
r
es
e
n
t
at
i
o
n
as
pr
o
vi
de
d by
D
W
T
,
a
us
e
f
u
l
t
ool
t
o m
od
e
l
ha
z
y
r
e
gi
o
n
s
.
T
he
a
p
p
r
o
x
im
a
ti
on c
oe
f
f
i
c
i
e
nt
s
(
L
L
s
u
b
-
b
a
nd)
co
r
r
el
at
es
t
o
l
o
cal
i
zed
h
aze
i
n
f
o
r
m
at
i
o
n
,
w
h
e
r
eas
d
et
ai
l
co
ef
f
i
ci
e
n
t
s
(
L
H
,
H
L
,
a
n
d
H
H
)
em
b
ed
ed
g
e
i
nf
or
m
a
t
i
on.
S
o
by
a
p
pl
y
i
ng
t
he
e
n
ha
nc
e
m
e
nt
ope
r
a
t
i
o
n
on
l
y
on
L
L
s
ub
-
b
a
nd
r
e
s
ul
t
s
i
n
e
nha
nc
e
d
im
a
ge
wi
t
h
s
ha
r
p
e
d
ge
s
.
I
n
o
u
r
p
r
es
en
t
ed
w
o
r
k
,
w
e
h
av
e ap
p
l
i
ed
co
n
t
r
as
t
en
h
an
ce
m
en
t
t
e
c
hni
qu
e
us
i
ng S
V
D
a
nd
D
W
T
o
n
V
c
ha
nne
l
of
HS
V c
ol
or
s
p
a
c
e
,
t
he
r
e
by
n
ot
a
f
f
e
c
t
i
ng t
h
e
c
ol
o
r
c
om
po
s
i
t
i
o
n o
f
or
i
gi
na
l
i
n
put
ha
z
y
im
a
g
e.
T
h
e
V
c
ha
n
ne
l
i
s
pr
oc
e
s
s
e
d
by
hi
s
t
og
r
a
m
e
q
ua
l
i
z
a
t
i
on t
o
obt
a
i
n
v
H
E
.
T
he
t
w
o i
m
a
ge
s
V
a
nd
vH
E
a
r
e
de
c
om
pos
e
d
b
y
D
W
T
i
n
f
ou
r
s
ub
-
ba
n
ds
.
T
he
s
i
ng
ul
a
r
va
l
ue
m
a
t
r
i
x c
o
r
r
e
c
t
i
on c
oe
f
f
i
c
i
e
nt
i
s
obt
a
i
ne
d
us
i
n
g
t
h
e
e
q
u
a
t
i
o
n
:
=
m
ax
(
)
m
ax
(
)
(1)
w
h
e
re
a
nd
a
r
e
S
V
D
va
l
ue
s
of
t
he
i
np
ut
i
m
a
ge
a
n
d
t
he
r
e
s
ul
t
i
ng
i
m
a
ge
of
t
he
hi
s
t
og
r
a
m
e
q
ua
l
i
z
e
d
t
e
c
hni
q
ue
.
T
he
m
odi
f
i
e
d
L
L
b
a
nd
i
s
gi
ve
n
by
:
=
.
(2
)
=
∪
.
.
(3
)
B
y
a
p
p
lying
I
DW
T
to
,
,
a
nd
s
ub
-
ba
nd
s
,
t
he
ne
w
e
q
ua
l
i
z
e
d
V
ch
a
n
n
el
i
m
ag
e
i
s
g
e
n
er
a
t
ed
=
ID
WT
(
,
,
,
)
(
4)
T
h
e
c
om
pone
nt
i
s
t
he
n
c
on
c
a
t
e
na
t
e
d
w
i
t
h
H
a
nd
S
c
om
po
ne
nt
i
n
HS
V c
ol
o
r
s
p
ace
t
o
o
b
t
ai
n
co
n
t
r
as
t
en
h
a
n
ced
R
G
B
i
m
ag
e.
2
.
2
.
O
b
t
a
i
n
i
n
g
W
h
i
t
e
B
al
a
n
c
e
d
I
m
age
A
pa
r
t
f
r
om
dim
i
ni
s
he
d c
o
nt
r
a
s
t
pr
o
bl
e
m
s
,
un
de
r
w
a
t
e
r
i
m
a
ge
s
a
r
e
p
r
o
ne
t
o c
ol
or
l
os
s
a
t
t
r
i
but
e
d t
o
w
a
ve
l
e
ngt
h a
t
t
e
nua
t
i
o
n
[1
7
]
.
A
l
s
o,
due
t
o a
n a
r
t
i
f
i
c
i
a
l
s
o
u
r
c
e
o
f
l
i
g
h
t
a
t
a
p
p
r
e
c
i
a
b
l
e
d
e
p
t
h
,
u
n
w
a
n
t
e
d
c
o
l
o
r
c
a
s
t
s
a
r
i
s
e
s
.
T
u
r
bi
di
t
y
i
s
not
a
bi
g
p
r
obl
e
m
a
t
de
e
pe
r
de
pt
h
s
a
s
c
om
pa
r
e
d
t
o
s
ha
l
l
ow
w
a
t
e
r
s
due
t
o
t
he
a
b
s
e
nc
e
of
m
a
r
i
ne
s
no
w a
n
d n
o
a
p
p
r
eci
ab
l
e u
n
d
er
w
at
er
f
l
o
w
m
o
v
e
m
en
t
.
S
o
w
h
i
t
e b
al
an
ci
n
g
t
ech
n
i
q
u
e i
s
a n
eces
s
i
t
y
.
A
l
ar
g
e
n
u
m
b
er
o
f
w
h
i
t
e b
a
l
an
ci
n
g
t
ec
h
n
i
q
u
e
s
ar
e av
ai
l
ab
l
e i
n
t
h
e l
i
t
er
at
u
r
e
[
18
]
.
W
e
t
r
i
e
d
,
w
h
i
t
e
p
a
t
c
h
a
l
g
o
r
i
t
h
m
,
M
a
x
RG
B a
l
g
o
r
i
t
h
m
,
G
r
a
y
-
E
d
g
e
a
l
g
o
r
i
t
h
m
[
19]
a
nd S
h
a
de
s
of
Gr
a
y a
lg
or
ithm
[
20]
.
W
e
o
b
t
ai
n
ed
t
h
e
b
e
s
t
p
o
s
s
i
b
l
e
r
e
s
u
l
t
s
f
o
r
S
h
a
d
e
s
o
f
G
r
a
y
a
l
g
o
r
i
t
h
m
.
A
s
l
i
s
t
e
d
i
n
[
13
]
t
h
e
p
r
o
ba
bl
e
r
e
a
s
ons
f
or
t
he
f
a
i
l
ur
e
o
f
w
h
i
t
e
p
a
t
c
h
a
l
g
o
r
i
t
h
m
a
r
e
a
t
t
r
i
b
u
t
e
d
t
o
l
i
m
i
t
e
d
s
p
e
c
u
l
a
r
r
e
f
l
e
c
t
i
o
n
a
n
d
f
a
i
l
u
r
e
o
f
G
r
a
y
E
d
g
e
a
l
g
o
r
i
t
h
m
i
s
o
n
a
c
c
ou
nt
of
l
o
w
c
o
nt
r
a
s
t
a
nd
di
m
i
ni
s
he
d
e
d
ge
s
a
s
c
om
pa
r
e
d
t
o
o
ut
d
o
or
i
m
a
ge
s
.
F
i
n
l
ay
s
o
n
an
d
T
r
ezzi
p
r
es
en
t
ed
s
h
a
d
es
o
f
G
r
e
y
a
l
go
r
i
t
hm
ba
s
e
d o
n t
he
a
s
s
um
pt
i
on t
ha
t
im
a
ge
s
c
e
ne
av
er
a
g
e i
s
a
f
u
n
ct
i
o
n
o
f
s
o
m
e
s
ha
de
s
of
Gr
e
y
.
I
t
c
a
l
c
ul
a
t
e
s
t
he
w
e
i
g
h
t
e
d a
ve
r
a
ge
of
t
he
pi
xe
l
i
nt
e
ns
i
t
y
by
a
s
s
i
gni
ng
hi
gh
e
r
w
e
i
g
h
t
t
o
pi
xe
l
w
i
t
h
hi
gh
e
r
i
nt
e
ns
i
t
y
,
ba
s
e
d
on
M
i
n
ko
ws
ki
-
n
o
r
m
p
a
n
d
i
s
gi
ve
n
a
s
:
∫
(
(
)
)
∫
1
=
(
5)
w
h
er
e
(
)
i
s
t
h
e
i
n
p
u
t
i
m
a
g
e
,
i
s
t
h
e
s
p
at
i
al
c
o
o
r
d
i
n
at
e i
n
t
h
e i
m
ag
e an
d
k
i
s
c
o
ns
t
a
nt
.
S
ha
de
s
of
Gr
e
y
a
l
g
o
r
i
t
h
m
i
s
t
r
a
d
e
-
o
f
f
b
e
t
w
e
e
n
G
r
a
y
Wo
rl
d
(
=
1
)
a
nd
M
a
xR
G
B
a
l
go
r
i
t
hm
(
=
∞
)
.
2
.
3
.
M
u
l
t
i
m
o
d
a
l
Im
a
g
e
Fu
si
o
n
U
si
n
g
D
WT
T
he
w
a
ve
l
e
t
b
a
s
e
d f
us
i
o
n t
e
c
hni
que
s
a
r
e
w
i
de
l
y
us
e
d i
n
m
e
di
c
a
l
im
a
ge
r
e
s
t
or
a
t
i
on
[
21]
,
s
a
t
e
l
l
i
t
e
im
a
gi
ng
[2
2
]
,
out
do
o
r
s
c
e
n
e
im
a
gi
ng
[2
3
]
et
c.
T
h
e t
r
a
n
s
f
o
r
m
co
ef
f
i
ci
en
t
s
o
f
D
W
T
ar
e r
e
p
r
e
s
en
t
at
i
v
es
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
A
A
S
I
S
S
N
:
225
2
-
88
14
A
F
u
s
i
o
n
bas
e
d
V
i
s
i
bi
l
i
t
y
E
n
ha
nc
e
m
e
nt
of
S
i
ngl
e
U
n
de
r
w
a
t
e
r
H
az
y
I
m
a
g
e
(
Sa
m
ar
t
h
B
o
r
k
ar
)
41
i
m
a
g
e
p
i
x
e
l
s
.
I
t
t
r
a
n
s
f
o
r
m
s
t
h
e
i
n
p
u
t
s
e
r
i
e
s
0
,
1
,
2
…
,
i
nt
o
hi
g
h
pa
s
s
wa
ve
l
e
t
c
oe
f
f
i
c
i
e
nt
s
a
nd
l
ow
pa
s
s
c
o
e
f
f
i
c
i
e
n
t
s
s
e
r
i
e
s
o
f
l
e
n
g
t
h
2
e
a
c
h
gi
ve
n
by
(
6)
a
n
d
(
7
)
=
∑
2
−
.
(
)
−
1
=
0
(
6)
=
∑
2
−
.
(
)
−
1
=
0
(
7)
w
h
e
re
(
)
a
nd
(
)
ar
e
cal
l
ed
w
a
v
el
et
f
i
l
t
er
s
a
n
d
=
0
,
…
,
(
2
-
1)
a
nd
k
i
s
t
h
e
l
e
n
g
t
h
o
f
t
h
e
f
i
l
t
e
r
[2
4
]
[
2
9
].
A
s
di
s
c
us
s
e
d
e
a
r
l
i
e
r
,
t
he
r
e
a
r
e
t
w
o
c
om
pone
nt
s
i
n
D
W
T
,
a
pp
r
oxi
m
a
t
i
on,
a
nd
de
t
a
i
l
s
u
b
-
b
a
nd
s
.
I
n
our
a
ppl
i
c
a
t
i
o
n,
w
e
pr
o
po
s
e
t
o
f
us
e
c
ont
r
a
s
t
e
nha
nc
e
d a
nd
whi
t
e
ba
l
a
nc
e
d
im
a
ge
,
i
n
or
d
e
r
t
o
o
bt
a
i
n a
de
ha
z
e
d
un
de
r
wa
t
e
r
s
i
n
gl
e
im
a
ge
.
F
or
t
he
a
p
pr
o
xi
m
a
t
i
on s
ub
-
b
a
n
d
s
w
e u
s
e,
t
h
e c
o
r
r
es
p
o
n
d
i
n
g
m
ean
co
e
f
f
i
ci
e
n
t
s
an
d
f
o
r
r
e
t
a
i
ni
n
g e
dge
s
we
us
e
m
a
xi
m
u
m
c
oe
f
f
i
c
i
e
nt
s
of
t
he
t
w
o (
c
o
nt
r
a
s
t
e
nha
nc
e
d a
n
d w
h
i
t
e
b
al
an
ced
)
d
et
ai
l
ed
su
b
-
ba
n
ds
.
W
e
de
c
om
pos
e
t
h
e
f
i
r
s
t
i
n
p
ut
a
n
d s
e
c
o
n
d i
n
p
ut
i
nt
o
i
n
di
vi
dua
l
a
p
pr
o
xi
m
a
t
i
on s
u
b
-
ba
nds
1
a
nd
2
w
h
e
r
e
n
o
t
a
t
i
o
n
1
an
d
2
c
or
r
e
s
p
ond
s
to
f
ir
s
t
i
n
pu
t
a
n
d
s
e
c
ond
inpu
t
a
nd
a
s
i
gni
f
i
e
s
a
p
pr
ox
im
a
ti
on
s
ub
-
ba
nd
.
S
i
m
i
l
a
r
l
y
w
e
d
e
c
om
pos
e
t
w
o
i
n
put
i
m
a
ge
s
i
nt
o
1
a
nd
1
,
w
h
e
re
d
s
i
gni
f
i
e
s
c
or
r
e
s
po
n
di
n
g
d
e
t
a
i
l
s
ub
-
b
a
nds
(
LH
,
H
L
an
d
H
H
)
.
A
l
g
o
r
i
t
h
m
f
o
r
D
W
T
i
m
a
g
e
f
u
s
i
o
n
i
s
a
s
f
o
l
l
o
w
s
:
S
t
e
p
1:
C
om
pu
t
e
a
pp
r
oxi
m
a
t
ion
c
oe
f
f
i
c
i
e
nt
f
or
f
us
e
d
i
m
a
ge
,
us
i
n
g
f
u
s
i
o
n
r
ul
e
a
s
:
=
1
2
(
1
+
2
)
(
8)
S
t
e
p
2:
C
om
pu
t
e
de
t
a
i
l
e
d
c
oe
f
f
i
c
i
e
nt
f
or
f
us
e
d
i
m
a
ge
,
us
ing
f
u
s
ion
r
u
le
a
s
:
=
(
1
,
2
)
(
9)
S
t
e
p
3:
F
ol
l
ow
S
t
e
p
1
a
nd
S
t
e
p
2
f
o
r
t
he
de
s
i
r
e
d
l
e
ve
l
of
r
e
s
ol
ut
i
o
n.
S
t
ep
4
:
R
eco
n
s
t
r
u
ct
t
h
e
en
h
a
n
ced
i
m
ag
e
u
s
i
n
g
i
n
v
e
r
s
e
d
i
s
cr
et
e
w
av
el
et
t
r
a
n
s
f
o
r
m
as
:
=
,
(
10
)
T
h
i
s
p
r
o
c
e
s
s
p
r
e
s
e
r
v
e
s
t
h
e
d
o
m
i
n
a
n
t
f
e
a
t
u
r
e
s
w
i
t
h
o
u
t
i
n
t
r
o
d
u
c
i
n
g
a
n
y
a
r
t
i
f
a
c
t
s
.
2
.
4
.
P
o
st
-
P
ro
c
es
s
i
n
g
U
s
i
n
g
C
o
n
t
r
a
s
t
S
t
ret
ch
i
n
g
T
h
e i
m
ag
e af
t
er
f
u
s
i
o
n
n
eed
s
t
o
b
e
pos
t
-
p
r
o
ces
s
e
d
u
s
i
n
g
co
n
t
r
as
t
s
t
r
et
ch
i
n
g
s
o
as
t
o
i
n
cr
eas
e t
h
e
dy
na
m
i
c
r
a
nge
of
pi
xe
l
s
a
n
d
e
nha
nc
e
c
o
nt
r
a
s
t
.
A s
i
m
pl
i
f
ie
d c
o
nt
r
a
s
t
s
t
r
e
t
c
hi
ng a
l
go
r
i
t
hm
[
11]
[
3
0]
u
s
e
s
a
l
i
n
ear
s
cal
i
n
g
f
u
n
ct
i
o
n
o
f
t
h
e
n
o
r
m
al
i
zed
p
i
x
el
v
al
u
e.
T
h
e
i
m
ag
e
r
es
t
o
r
e
d
(
,
)
i
s
g
i
ve
n
a
s
(
,
)
=
(
(
,
)
−
)
−
−
+
(
11
)
w
h
e
re
(
,
)
i
s
t
h
e
n
o
r
m
a
l
i
z
e
d
p
i
x
e
l
i
n
t
e
n
s
i
t
y
a
f
t
e
r
c
o
n
t
r
a
s
t
s
t
r
e
t
c
h
i
n
g
,
i
s
t
h
e
l
o
w
e
s
t
i
n
t
e
n
s
i
t
y
i
n
t
h
e
e
x
i
s
t
i
n
g
i
m
a
g
e
,
i
s
t
h
e
h
i
g
h
e
s
t
i
n
t
e
n
s
i
t
y
i
n
t
h
e
e
x
i
s
t
i
n
g
i
m
a
g
e
,
i
s
t
h
e
m
i
n
i
m
u
m
p
i
x
e
l
i
n
t
e
n
s
i
t
y
i
n
t
h
e
d
es
i
r
e
d
i
m
ag
e an
d
i
s
t
h
e
m
a
x
i
m
u
m
p
i
x
e
l
i
n
t
e
n
s
i
t
y
i
n
t
h
e
d
e
s
i
r
e
d
i
m
a
g
e
.
3.
E
X
P
ER
I
M
EN
TA
L
R
ES
U
L
TS
A
N
D
A
NA
L
Y
S
I
S
A
s
w
e
d
o
n
o
t
h
a
v
e a
g
r
o
u
n
d
t
r
u
t
h
o
r
s
e
p
ar
at
e
r
ef
e
r
en
ce i
m
a
g
e as
s
u
ch
,
t
h
e
ch
o
i
c
e o
f
i
m
ag
e
a
s
s
e
s
s
m
e
n
t
f
o
r
q
u
a
n
t
i
t
a
t
i
v
e
a
s
w
e
l
l
a
s
q
u
a
l
i
t
a
t
i
v
e
a
n
a
l
y
s
i
s
b
e
c
o
m
e
s
a
d
i
f
f
i
c
u
l
t
t
a
s
k
.
F
i
g
u
r
e
2
,
s
h
o
w
s
t
h
e
hi
s
t
o
gr
a
m
of
i
m
a
ge
s
be
f
or
e
a
nd a
f
t
e
r
r
e
s
t
o
r
a
t
i
on
.
I
t
i
s
s
e
e
n t
ha
t
ou
r
p
r
o
p
os
e
d m
e
t
hod i
s
a
bl
e
t
o e
nha
n
c
e
t
he
co
n
t
r
as
t
ra
n
g
e
.
W
e
ha
ve
c
om
pa
r
e
d
ou
r
p
r
o
p
os
e
d m
e
t
hods
wi
t
h c
o
nt
e
m
por
a
r
y
m
e
t
hods
s
uc
h a
s
A
nc
ut
i
e
t
a
l
.
[
13
]
,
Ba
z
e
i
l
l
e
et
a
l
.
[
12
]
,
Ca
r
l
e
v
a
r
i
s
e
t
a
l
.
[5
]
,
C
h
i
a
ng a
nd C
he
n
[6
]
,
G
a
l
d
ra
n
et
a
l
.
[8
]
,
an
d
S
er
i
k
a
w
a &
L
u
[
25
]
.
O
f
t
he
s
e
m
e
t
h
ods
,
[5
-
6
]
a
nd
[
25
]
a
r
e
ba
s
e
d
o
n i
m
a
ge
r
e
s
t
or
a
t
i
o
n m
ode
l
a
nd
e
m
pl
oy
m
odi
f
i
e
d da
r
k
c
ha
n
ne
l
pr
i
or
a
s
p
r
op
os
e
d i
n
[4
]
,
a
nd
[1
2
-
13]
a
r
e
r
e
p
r
e
s
e
nt
a
t
i
ve
s
o
f
e
nha
nc
e
m
e
nt
m
e
t
hods
.
O
ur
wo
r
k i
s
ba
s
e
d
on t
he
n
on
-
p
hy
s
i
c
a
l
m
ode
l
,
but
w
e
ha
ve
c
om
pa
r
e
d
o
ur
w
o
r
k
wi
t
h
b
ot
h
r
e
s
t
or
a
t
i
o
n a
s
we
l
l
a
s
e
nha
n
c
e
m
e
nt
t
ech
n
i
q
u
es
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
252
-
88
14
IJ
A
A
S
V
o
l
.
7
,
N
o
.
1
,
Ma
r
c
h
20
18
:
3
8
–
45
42
3.
1.
Q
u
a
l
i
t
a
t
i
v
e
Ev
a
l
u
a
t
i
o
n
A
s
s
h
o
wn i
n F
i
g 2
-
5
,
w
e
h
av
e co
m
p
ar
ed
o
u
r
r
es
u
l
t
s
w
i
t
h
t
h
e s
t
an
d
ar
d
m
et
h
o
d
s
.
I
t
can
b
e s
een
t
h
at
ou
r
m
e
t
hod i
s
a
bl
e
t
o r
e
s
t
o
r
e
vi
s
i
bi
l
i
t
y
a
nd r
e
m
ove
c
ol
or
c
a
s
t
a
l
ong
w
i
t
h
[
12
]
,
[
13]
a
nd
[8
]
w
o
rk
,
w
h
e
re
a
s
i
n
t
h
e
r
e
s
u
l
t
s
o
f
[5
],
[6
],
[2
5
]
,
t
he
c
ol
or
a
n
d
d
e
t
a
i
l
s
a
r
e
not
i
m
pr
ove
d.
A
nc
ut
i
e
t
a
l
.
’s
m
e
t
h
o
d
r
e
m
ove
t
h
e h
aze
c
om
pl
e
t
e
l
y
e
xhi
bi
t
i
ng
opt
i
m
um
vi
s
i
bi
l
i
t
y
but
r
e
n
de
r
i
ng
a
n
o
ve
r
s
a
t
ur
a
t
e
d
a
ppe
a
r
a
nc
e
,
w
he
r
e
a
s
B
a
z
e
i
l
l
e
e
t
a
l
.
’
s
m
e
t
h
o
d
,
t
h
e
c
o
l
o
r
f
i
d
e
l
i
t
y
l
o
s
s
i
s
p
r
o
m
i
n
e
n
t
.
T
he
m
e
t
hod
of
G
al
d
r
an
e
t
a
l
.
i
s
ab
l
e t
o
r
eco
v
e
r
an
d
r
es
t
o
r
e t
h
e
n
at
u
r
al
ap
p
ear
an
ce o
f
t
h
e
u
n
de
r
wa
t
e
r
s
c
e
ne
but
w
i
t
h l
e
s
s
e
r
b
r
i
g
ht
ne
s
s
a
s
c
om
pa
r
e
d t
o
o
ur
wo
r
k.
T
he
m
e
t
hod
of
S
e
r
i
ka
w
a
a
n
d
L
u
a
l
s
o
f
a
i
l
s
t
o
p
r
od
uc
e
t
he
e
nha
nc
e
d
vi
s
i
b
i
l
i
ty
,
a
s
i
s
t
he
c
a
s
e
wi
t
h
C
hi
a
n
g
a
nd
C
he
n
m
e
t
ho
d.
F
i
gu
r
e
2.
Vi
s
u
a
l
c
om
pa
r
i
s
o
n
on
i
m
a
ge
F
i
s
h
w
i
t
h
s
i
z
e
5
12
x
38
4:
(a
)
i
n
p
u
t
i
m
a
g
e
;
(b
)
b
y
[
1
3
]
;
(c
)
b
y
[
1
2
]
;
(d
)
by
[
5]
;
(
e
)
by
[
6]
;
(
f
)
by
[
2
5]
;
(
g
)
by
[
8]
;
a
n
d
(
h
)
wi
t
h
pr
o
po
s
e
d
m
e
t
hod
F
i
gu
r
e
3.
Vi
s
u
a
l
c
om
pa
r
i
s
o
n
on
i
m
a
ge
C
or
a
l
wi
t
h
s
i
z
e
5
12
x3
8
4:
(
a
)
i
n
p
ut
im
a
ge
;
(
b
)
by
[
13
]
;
(
c
)
b
y
[1
2
]
;
(
d)
b
y
[5
]
;
(
e
)
b
y
[6
]
;
(f
)
b
y
[
25]
;
(
g)
b
y
[8
]
;
a
nd
(
h)
w
ith
pr
opo
s
e
d
m
e
th
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
A
A
S
I
S
S
N
:
225
2
-
88
14
A
F
u
s
i
o
n
bas
e
d
V
i
s
i
bi
l
i
t
y
E
n
ha
nc
e
m
e
nt
of
S
i
ngl
e
U
n
de
r
w
a
t
e
r
H
az
y
I
m
a
g
e
(
Sa
m
ar
t
h
B
o
r
k
ar
)
43
F
i
gu
r
e
4.
Vi
s
u
a
l
c
om
pa
r
i
s
o
n
on
i
m
a
ge
S
hi
p
wr
e
c
k
wi
t
h
s
i
z
e
5
12
x
38
4:
(
a
)
i
np
ut
i
m
a
ge
;
(
b
)
by
[
13]
;
(c
)
b
y
[
12
]
;
(d
)
b
y
[5
]
;
(e
)
b
y
[6
]
;
(f
)
b
y
[2
5
]
;
(
g)
b
y
[8
]
;
a
n
d
(
h
)
w
i
t
h
pr
o
po
s
e
d
m
e
t
hod
F
i
gu
r
e
5.
Vi
s
u
a
l
c
om
pa
r
i
s
o
n
on
i
m
a
ge
Di
ve
r
wi
t
h
s
i
z
e
51
2
x3
8
4:
(
a
)
i
n
p
ut
im
a
ge
;
(
b
)
by
[
13
]
;
(
c
)
b
y
[1
2
]
;
(
d
)
b
y
[5
]
;
(
e
)
b
y
[6
]
;
(f
)
b
y
[2
5
]
;
(
g)
b
y
[8
]
;
a
n
d
(
h
)
w
i
t
h
pr
o
po
s
e
d
m
e
t
hod
3.
1.
Q
u
an
t
i
t
a
t
i
ve
e
v
al
u
at
i
on
F
o
r
q
u
a
n
t
i
t
at
i
v
e an
al
y
s
i
s
,
w
e
r
ef
e
r
r
e
d
t
o
ea
r
l
i
er
w
o
r
k
s
t
o
s
e
l
ect
t
h
e as
s
es
s
m
en
t
p
ar
am
et
e
r
s
.
W
e
h
av
e
u
s
e
d
q
u
al
i
t
y
m
et
r
i
cs
s
u
c
h
as
a m
eas
u
r
e o
f
a
b
i
l
i
t
y
t
o
r
es
t
o
r
e ed
g
es
&
g
r
a
d
i
en
t
m
ean
r
at
i
o
o
f
t
h
e e
d
g
es
[
26
]
,
im
a
ge
e
nt
r
opy
[
21
]
,
s
t
r
u
c
t
u
r
a
l
s
i
m
i
l
a
r
i
t
y
i
n
d
e
x
[2
7
]
,
a
n
d
P
S
NR
[2
8
]
.
T
a
b
l
e
1
s
h
o
w
s
t
h
e
v
i
s
i
b
i
l
i
t
y
r
e
c
o
v
e
r
y
i
n
t
e
r
m
s
o
f
a
m
e
a
s
u
r
e
o
f
a
b
i
l
i
t
y
t
o
r
e
s
t
o
r
e
e
d
g
e
s
‘
e
’
a
n
d
T
a
bl
e
2
s
ho
ws
t
he
g
r
a
di
en
t
m
ean
r
a
t
i
o
o
f
t
h
e
ed
g
es
‘
r
’.
T
ab
l
e
1
:
M
e
a
s
u
r
e
o
f
A
b
i
l
i
t
y
t
o
Re
s
t
o
r
e
E
d
g
es
‘
e
’
M
e
t
hods
Fis
h
C
o
ra
l
Sh
ip
wr
eck
Div
er
An
cu
ti
et a
l.
[
13]
1.
723
-
0.
05
0.
462
10.
34
B
azeille
et
a
l
.
[
12]
0.
928
-
0.
11
0.
228
3.
728
C
ar
lev
ar
is
et
a
l
. [
5
]
0.
147
-
0.
13
0.
326
0.
486
C
hi
a
ng a
nd C
he
n
[
6]
0.
275
0.
025
0.
070
0.
839
Gald
r
an
et a
l.
[
8]
1.
276
0.
163
0.
458
6.
648
Ser
ik
awa
an
d
L
u
[
2
5
]
0.
621
-
0.
01
-
0.
02
1.
414
P
r
opos
e
d M
e
t
hod
1.
108
0.
100
0.
457
5.
483
T
ab
l
e
2
:
M
e
a
s
u
re
o
f
Gra
d
i
e
n
t
M
ean
R
a
t
i
o
o
f
t
h
e
E
dg
e
s
‘
r
’
M
e
t
hods
Fis
h
C
o
ra
l
Sh
ip
wr
eck
Div
er
An
cu
ti
et a
l.
[
13]
4.
624
1.
602
2.
972
4.
103
B
azeille
et
a
l
.
[
12]
5.
939
3.
575
5.
196
5.
264
C
ar
lev
ar
is
et
a
l
. [
5
]
1.
124
2.
872
2.
568
1.
310
C
hi
a
ng a
nd C
he
n
[
6]
1.
405
1.
385
1.
992
1.
352
Gald
r
an
et a
l.
[
8]
2.
202
1.
152
2.
343
2.
081
Ser
ik
awa
a
nd L
u [
25]
1.
861
1.
662
2.
033
1.
715
P
r
opos
e
d M
e
t
hod
2.
419
1.
499
1.
401
1.
942
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
SN
:
2
252
-
88
14
IJ
A
A
S
V
o
l
.
7
,
N
o
.
1
,
Ma
r
c
h
20
18
:
3
8
–
45
44
A
s
c
a
n
be
s
e
e
n i
n T
a
bl
e
3
,
t
he
pr
o
pos
e
d
m
e
t
hod s
u
r
p
a
s
s
ot
he
r
m
e
tho
ds
i
n t
e
r
m
s
of
e
nt
r
o
py
.
F
ur
t
he
r
m
or
e
,
o
ur
m
e
t
ho
d
pe
r
f
or
m
s
on
pa
r
wi
t
h,
C
a
r
l
e
va
r
i
s
e
t
a
l
.
,
C
hi
a
n
g
&
C
he
n
a
n
d
S
e
r
i
k
a
w
a
&
L
u
i
n
t
e
r
m
s
o
f
s
t
r
u
c
t
u
r
a
l
s
i
m
i
l
a
r
i
t
y
i
n
d
e
x
(
S
S
I
M
)
.
T
h
e P
eak
s
i
g
n
al
-
t
o
-
n
o
i
s
e
r
a
t
i
o
,
a
l
t
h
o
u
g
h
n
o
t
t
h
e
b
e
s
t
i
n
t
h
e
l
i
s
t
,
s
t
i
l
l
e
xhi
bi
t
hi
ghe
r
va
l
ue
s
.
T
he
r
e
s
ul
t
s
ove
r
a
l
l
de
m
ons
t
r
a
t
e
t
ha
t
our
m
e
t
hod
wor
ks
e
f
f
i
c
i
e
nt
l
y
t
o r
e
m
ove
t
he
u
n
d
e
r
w
at
er
h
az
e.
T
ab
l
e
3
:
A
ve
r
a
ge
va
l
ue
s
i
n
t
e
r
m
s
of
e
nt
r
o
py
,
S
S
I
M
,
a
n
d
P
S
NR
I
ma
g
e
M
e
t
hods
E
nt
r
opy
SSI
M
PSNR
Fig
.
2
to
5
An
cu
ti
et a
l.
[
13]
7.
65
0.
50
21.
29
B
azeille
et
a
l
.
[
12]
7.
50
0.
19
18.
72
C
ar
lev
ar
is
et
a
l
. [
5
]
7.
41
0.
89
29.
29
C
hi
a
ng a
nd C
he
n
[
6]
7.
63
0.
86
27.
93
Gald
r
an
et a
l.
[
8]
7.
57
0.
29
19.
40
Ser
ik
awa
an
d
L
u
[
2
5
]
7.
51
0.
83
25.
87
P
r
opos
e
d M
e
t
hod
7.
75
0.
82
24.
33
4.
C
O
N
CL
U
S
I
O
N
I
n
t
h
i
s
p
r
o
p
o
s
ed
w
o
r
k
w
e
h
av
e i
m
p
l
em
en
t
ed
s
i
m
p
l
e y
et
ef
f
ect
i
v
e u
n
d
er
w
at
er
s
i
n
g
l
e i
m
ag
e
e
nha
nc
e
m
e
nt
te
c
hni
que
t
o a
dd
r
e
s
s
t
he
pr
obl
e
m
of
vi
s
i
bi
l
i
t
y
r
e
s
t
or
a
t
i
on a
n
d u
nwa
nt
e
d c
ol
or
c
a
s
t
.
T
h
e
pr
o
pos
e
d t
e
c
h
ni
q
ue
ha
s
be
e
n e
va
l
ua
t
e
d f
o
r
vi
s
ua
l
a
nd
q
ua
nt
i
t
a
t
i
ve
a
na
l
y
s
i
s
.
E
x
p
e
r
i
m
e
n
t
a
l
o
u
t
c
o
m
e
r
e
v
e
a
l
s
t
h
at
o
u
r
r
es
u
l
t
s
ar
e co
m
p
ar
ab
l
e t
o
an
d
p
er
f
o
r
m
an
ce w
i
s
e ef
f
ect
i
v
e as
co
m
p
ar
ed
t
o
o
t
h
er
r
ecen
t
t
ech
n
i
q
u
es
.
T
h
e p
r
o
p
o
s
e
d
w
o
r
k
g
r
eat
l
y
en
h
a
n
ce t
h
e
v
i
s
u
al
d
et
ai
l
s
i
n
an
i
m
ag
e,
en
h
a
n
ce t
h
e cl
ar
i
t
y
f
r
o
m
a
co
n
t
r
as
t
poi
nt
of
vi
e
w
a
nd
p
r
e
s
e
r
ve
t
he
na
t
ur
a
l
c
ol
or
wi
t
ho
ut
l
os
i
ng i
m
a
ge
i
nf
or
m
a
ti
on a
s
ob
s
e
r
ve
d i
n s
t
a
t
e
o
f
t
he
a
r
t
t
e
c
hni
q
ue
s
.
Al
s
o,
u
s
i
n
g t
hi
s
p
r
o
p
os
e
d m
e
t
hod w
e
a
r
e
a
bl
e
t
o o
ve
r
c
om
e
t
h
e
l
im
i
t
a
ti
ons
e
nc
o
u
nt
e
r
e
d i
n a
p
at
ch
ba
s
e
d un
de
r
w
a
t
e
r
i
m
a
ge
de
ha
z
i
ng p
r
o
bl
e
m
s
s
u
c
h
a
s
c
o
m
p
u
t
a
t
i
o
n
o
f
a
t
m
o
s
p
h
e
r
i
c
l
i
g
h
t
v
a
l
u
e
,
d
i
f
f
i
c
u
l
t
y
w
i
t
h
l
ar
g
e
o
b
j
ect
s
s
i
m
i
l
ar
t
o
t
h
e
c
o
l
o
r
o
f
h
aze
a
n
d
cr
i
t
er
i
a
f
o
r
s
el
ect
i
o
n
o
f
ed
g
e
p
r
es
er
v
i
n
g
s
m
o
o
t
h
i
n
g
o
p
e
r
at
o
r
s
.
A
C
K
N
O
W
L
E
D
G
E
ME
NT
S
T
he
a
ut
ho
r
s
w
oul
d l
i
ke
t
o t
h
a
nk
A.
Ga
l
d
ra
n
f
or
s
e
t
t
i
ng
u
p a
n o
nl
i
ne
r
e
pos
i
t
or
y
w
hi
c
h
he
l
pe
d
us
t
o
im
pr
o
ve
e
va
l
u
a
t
i
on a
n
d c
o
m
pa
r
i
s
on a
n
d
Ni
c
h
ol
a
s
C
a
r
l
e
va
r
i
s
-
B
i
a
nc
o f
o
r
s
u
pp
or
t
i
ng us
by
p
r
ovi
di
n
g
a
l
go
r
i
t
hm
f
unc
t
i
ons
.
R
EF
ER
E
N
C
ES
[1]
Y
.Y
. S
ch
ech
n
er
an
d
Y
. A
v
er
b
u
ch
,
“
R
eg
u
l
ar
i
z
ed
i
m
ag
e r
e
co
v
er
y
i
n
s
ca
t
t
er
i
n
g
m
ed
i
a,”
I
E
E
E
T
r
ans
ac
t
i
ons
o
n
P
at
t
e
r
n
A
nal
y
s
i
s
and Mac
h
i
ne
In
t
e
l
l
i
ge
n
c
e
,
vol
.
2
9,
no
.
9
,
pp
.
1655
-
1660,
2007
.
[2]
D
. M
. H
e
an
d
G
.
L
.
S
ee
t
,
“
D
i
ve
rg
e
nt
b
e
a
m
l
i
da
r
i
m
a
gi
ng i
n
t
urbi
d
w
a
t
e
r
,
”
O
pt
i
c
s
a
nd L
as
e
r
s
i
n E
ng
i
ne
e
r
i
ng
,
2004
.
[3]
S
. N
ar
as
i
m
h
an
a
n
d
S
. N
a
y
ar
,
“
C
ont
ra
s
t
r
e
s
t
o
ra
t
i
on of w
e
a
t
he
r
d
e
gra
de
d
i
m
a
ge
s
,
”
IE
E
E
T
r
ans
ac
t
i
ons
on P
a
t
t
e
r
n
A
nal
y
s
i
s
and
Ma
c
hi
ne
Int
e
l
l
i
g
e
nc
e
,
vo
l
.
25,
no.
6,
pp.
713
-
724,
200
3.
[4]
K
. H
e,
e
t
al
.,
“
S
i
ngl
e
i
m
a
ge
h
a
z
e
re
m
ova
l
us
i
ng da
rk c
ha
nne
l
pri
or,
”
T
r
ans
ac
t
i
ons
on P
at
t
e
r
n A
nal
y
s
i
s
and
Mac
hi
ne
Int
e
l
l
i
g
en
ce
.,
vol
.
33
,
n
o.
12
,
pp
.
2341
-
2353,
2011
.
[5]
N
. C
ar
l
ev
ar
i
s
-
B
i
an
co
,
e
t
al
.,
“
Ini
t
i
a
l
re
s
ul
t
s
i
n unde
rw
a
t
e
r s
i
ngl
e
i
m
a
g
e
de
ha
z
i
ng
,
”
i
n
IE
E
E
Int
e
r
nat
i
on
al
Conf
e
r
e
nc
e
on
O
c
e
ans
, p
p
.1
-
8,
2010.
[6]
J
.
Y
.
Chi
a
ng a
nd
Y
.
C.
Che
n,
“
U
nde
rw
a
t
e
r
i
m
a
ge
e
nha
nc
e
m
e
nt
b
y
w
a
ve
l
e
ng
t
h c
o
m
pe
ns
a
t
i
on a
nd
de
ha
z
i
ng,
”
I
E
EE
T
r
ans
ac
t
i
ons
on
Im
age
P
r
oc
e
s
s
i
ng,
vol
.
21
,
no
.
4
,
pp.
1756
-
1769
,
2012.
[7]
H
. L
u
,
et
a
l
.
, “
U
nde
rw
a
t
e
r
i
m
a
ge
e
nha
nc
e
m
e
nt
us
i
ng gui
de
d t
r
i
go
nom
e
t
ri
c
bi
l
a
t
e
r
a
l
fi
l
t
e
r
a
nd fa
s
t
a
ut
om
a
t
i
c
c
ol
or
c
orre
c
t
i
on
,
”
i
n
I
E
E
E
I
n
t
er
n
at
i
on
al
Conf
e
r
e
nc
e
o
n Im
age
P
r
oc
e
s
s
i
ng,
M
e
l
bour
ne
,
pp.
3412
-
3416
,
2013.
[8]
A
. G
al
d
r
an
,
e
t
a
l
.,
“
A
ut
om
a
t
i
c
re
d
-
c
h
a
nne
l
unde
rw
a
t
e
r i
m
a
ge
re
s
t
ora
t
i
o
n,
”
E
l
s
e
vi
er
J
our
nal
of
V
i
s
ual
Com
m
uni
c
at
i
on and
Im
age
R
e
pr
e
s
e
nt
at
i
on
,
vo
l
.
26,
pp
.
132
-
145
,
2015.
[9]
H
. L
u
,
e
t
a
l
.
,
“
Cont
ra
s
t
e
nha
n
c
e
m
e
nt
for i
m
a
ge
s
i
n t
urbi
d w
a
t
e
r
,
”
J
our
nal
of
O
pt
i
c
al
Soc
i
e
t
y
of
A
m
e
r
i
c
a A
,
vol
.
32,
no.
5
,
pp
.
886
-
8
93,
2015
.
[10]
K
.
Iqba
l
,
et
a
l
.,
“
U
nde
rw
a
t
e
r i
m
a
ge
e
nha
nc
e
m
e
nt
us
i
ng a
n i
nt
e
gra
t
e
d c
ol
or m
ode
l
,
”
IA
E
NG
Int
e
r
nat
i
onal
J
our
nal
of
Com
put
e
r
Sc
i
e
n
c
e
,
vol
.
34
,
no
.
2
,
pp
.
239
-
244,
2
007.
[11]
K
.
Iqba
l
,
e
t
a
l
.
,
“
E
nha
nc
i
ng t
he
l
ow
qua
l
i
t
y
i
m
a
ge
s
us
i
ng un
s
upe
rvi
s
e
d c
ol
o
r c
orre
c
t
i
on m
e
t
hods
,
”
i
n
I
E
E
E
Int
e
r
nat
i
onal
Co
nf
e
r
e
nc
e
on
Sy
s
t
e
m
s
Man and C
y
be
r
ne
t
i
c
s
(
SMC),
Is
t
anbul
,
pp
.
17
03
-
1709,
2010
.
[12]
S
. B
azei
l
l
e
,
e
t
al
.
,
“
A
ut
om
a
t
i
c
unde
rw
a
t
e
r i
m
a
ge
proc
e
s
s
i
ng,
”
i
n P
r
oc
e
e
d
i
ngs
of
Car
ac
t
e
r
i
s
at
i
on
D
u
M
ilie
u
Mar
i
n,
2006.
[13]
C.
A
nc
ut
i
,
e
t
a
l
.,
“
E
nha
nc
i
ng un
de
rw
a
t
e
r
i
m
a
ge
s
a
nd v
i
de
os
b
y
F
us
i
on,
”
i
n
P
r
o
ceed
i
n
g
s
o
f
I
E
EE
Conf
e
r
e
nc
e
o
n
Com
put
e
r
V
i
s
i
on
and
P
at
t
e
r
n R
e
c
ogni
t
i
on,
p
p.
81
-
88,
2012
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
A
A
S
I
S
S
N
:
225
2
-
88
14
A
F
u
s
i
o
n
bas
e
d
V
i
s
i
bi
l
i
t
y
E
n
ha
nc
e
m
e
nt
of
S
i
ngl
e
U
n
de
r
w
a
t
e
r
H
az
y
I
m
a
g
e
(
Sa
m
ar
t
h
B
o
r
k
ar
)
45
[14]
X
. F
u
,
e
t
al
.
,
“
A
re
t
i
ne
x ba
s
e
d e
nha
nc
i
ng a
ppro
a
c
h for
s
i
ngl
e
un
de
rw
a
t
e
r i
m
a
ge
,
”
in
Int
e
r
nat
i
on
al
Conf
e
r
e
nc
e
on
Im
age
P
r
oc
e
s
s
i
ng (
ICIP
)
,
P
ar
i
s
,
pp.
4572
-
4576
,
2014.
[15]
M
. S
h
en
g
, Y
. P
an
g
, L
. W
an
, H
. H
u
an
g
, “
U
n
d
er
w
at
er
i
m
ag
e
e
nha
nc
e
m
e
nt
us
i
ng m
ul
t
i
-
w
a
ve
l
e
t
t
ra
ns
form
a
nd
m
e
di
a
n fi
l
t
e
r,
”
T
E
K
O
M
N
IK
A
Indone
s
i
a
n J
ourna
l
of E
l
e
c
t
ri
c
a
l
E
n
gi
ne
e
r
i
ng
,
vol
.
1
2,
no
.
3
,
pp
.
230
6
-
2313,
2014
.
[16]
H
. D
em
i
r
el
,
e
t
a
l
.,
“
S
at
e
l
l
i
t
e
i
m
ag
e co
n
t
r
as
t
e
n
h
an
cem
en
t
u
s
i
n
g
di
s
c
re
t
e
w
a
v
e
l
e
t
t
r
a
ns
form
a
nd s
i
ngul
a
r v
a
l
u
e
de
c
om
pos
i
t
i
on,
”
I
E
E
E
G
eo
s
c
i
en
ce a
n
d
R
em
o
t
e
S
e
ns
i
ng
L
et
t
er
s
,
vo
l
.
7,
n
o.
2,
p
p.
33
3
-
337,
2010
.
[17]
R.
S
c
he
t
t
i
ni
a
nd
S
.
Corc
hs
,
“
U
nde
rw
a
t
e
r
i
m
a
ge
proc
e
s
s
i
ng:
s
t
a
t
e
of t
he
a
r
t
of re
s
t
ora
t
i
on
a
nd
i
m
a
g
e en
h
an
cem
en
t
m
e
t
hods
,
”
E
U
R
A
SIP
J
our
nal
of
A
dv
anc
e
d Si
gn
al
P
r
oc
e
ssi
n
g
-
Spe
c
i
a
l
i
s
s
ue
on adv
anc
e
s
i
n Si
g
nal
P
r
oc
e
s
s
i
ng f
or
m
ar
i
t
i
m
e
appl
i
c
at
i
ons
,
vo
l
.
14.
p
p.
1
-
14
,
2010
.
[18]
M
.
E
bne
r
,
Co
l
or
Cons
t
a
nc
y
,
W
i
l
e
y
1s
t
e
d
i
t
i
on
,
H
o
boke
n,
N
J
,
2007.
[19]
J.
Va
n
d
e
We
i
j
e
r
,
e
t
a
l
.
,
“
E
dge
b
a
s
e
d c
ol
or
c
ons
t
a
nc
y
,
”
I
E
EE
T
r
ans
ac
t
i
ons
on Im
age
P
r
o
ces
s
i
n
g
,
vol
.
16,
no.
9
,
p
p.
2207
–
2214,
200
7.
[20]
G
. D
. F
i
n
l
a
y
s
o
n
an
d
E
. T
r
ez
z
i
, “
S
h
ad
es
o
f
g
ra
y
a
nd c
ol
or c
ons
t
a
nc
y
,
”
i
n
IS
&
T
/
SID
T
we
l
f
t
h Col
or
Im
agi
n
g
Conf
e
r
e
nc
e
: Col
or
Sc
i
e
nc
e
,
Sy
s
t
e
m
s
and A
ppl
i
c
at
i
ons
,
Soc
i
e
t
y
f
or
Im
agi
ng
Sc
i
e
nc
e
and T
e
c
hno
l
ogy
,
pp
.
37
-
41
,
2004.
[21]
Y
. Y
an
g
,
e
t
al
.,
“
M
ed
i
cal
i
m
ag
e
f
u
s
i
o
n
v
i
a an
ef
f
ect
i
v
e w
av
e
l
et
-
b
a
s
e
d a
pproa
c
h”
,
E
U
R
A
SIP
J
our
nal
on
A
dv
anc
e
s
i
n Si
gnal
P
r
oc
e
s
s
i
ng,
vol
.
44
,
p
p.
1
-
13,
2010
.
[22]
Y.
Du
,
e
t
al
., “
H
aze
de
t
e
c
t
i
on
a
nd re
m
ova
l
i
n hi
gh re
s
ol
ut
i
o
n
s
at
el
l
i
t
e i
m
ag
e w
i
t
h
w
av
el
et
an
a
l
y
si
s,
”
I
E
E
E
T
r
ans
ac
t
i
ons
on
G
eo
s
ci
en
c
e
a
n
d
R
em
o
t
e
S
e
ns
i
ng,
vol
.
40,
no.
1,
p.
210
–
216,
2002.
[23]
W
. W
an
g
,
et
a
l
.,
“
M
u
l
t
i
s
cal
e s
i
n
g
l
e i
m
ag
e d
eh
a
zi
n
g
b
as
ed
o
n
a
da
pt
i
v
e
w
a
ve
l
e
t
fus
i
on,
”
H
i
ndaw
i
Mat
he
m
at
i
c
al
P
r
obl
e
m
s
i
n E
ng
i
ne
e
r
i
ng
,
vol
.
1
,
pp.
1
-
14,
2015.
[24]
B
. M
am
a
t
ha
a
nd
V
.
V
.
K
um
a
r,
“
I
S
A
R I
m
a
ge
c
l
a
s
s
i
fi
c
a
t
i
on w
i
t
h w
a
ve
l
e
t
s
a
nd w
a
t
e
rs
he
d t
ra
ns
form
s
,
”
Int
e
r
nat
i
onal
J
our
nal
of
E
l
e
c
t
r
i
c
al
and
Com
put
e
r
E
ng
i
ne
e
r
i
ng
(
IJ
E
CE
)
,
vol
.
6,
no.
6
,
p
.
3087
–
3
093,
2016
.
[25]
S.
S
er
i
k
aw
a an
d
H
. L
u
, “
U
n
d
er
w
at
er
i
m
ag
e
de
ha
z
i
ng us
i
ng j
oi
nt
t
ri
l
a
t
e
r
a
l
fi
l
t
e
r
,
”
E
l
s
ev
i
er
Com
put
e
r
s
a
nd
Ele
c
tr
ic
a
l En
g
in
e
e
r
in
g
,
vol
.
40
,
no.
1
,
pp
.
41
-
50,
2014.
[26]
N
. H
au
t
i
er
e,
e
t a
l.
,
“
Bl
i
nd
c
ont
r
a
s
t
e
nha
nc
e
m
e
nt
a
s
s
e
s
s
m
e
nt
by
g
ra
di
e
n
t
ra
t
i
oi
ng
a
t
vi
s
i
bl
e
e
dge
s
,
”
Im
age
A
n
a
l
y
s
i
s
and St
e
r
e
o
l
ogy
,
vol
.
2
7,
n
o.
2,
p
p.
87
-
95
,
2011
.
[27]
Z
. W
an
g
,
e
t
al
.,
“
Im
a
ge
qua
l
i
t
y
a
s
s
e
s
s
m
e
nt
:
from
e
rror m
e
a
s
ure
m
e
nt
t
o s
t
ru
c
t
ur
a
l
s
i
m
i
l
a
ri
t
y
,
”
I
E
E
E
T
r
ans
ac
t
i
o
ns
on
Im
age
P
r
oc
e
s
s
i
ng,
vol
.
13,
no.
1,
pp
.
600
-
612
,
2004.
[28]
S
. S
ah
u
,
e
t
al
.
,
“
Com
pa
ra
t
i
ve
a
n
a
l
y
s
i
s
of i
m
a
ge
e
nha
nc
e
m
e
nt
t
e
c
hni
que
s
for ul
t
r
a
s
ound l
i
ve
r i
m
a
g
e
,
”
In
t
e
r
nat
i
ona
l
J
our
nal
of
E
l
e
c
t
r
i
c
al
and
Com
put
e
r
E
ng
i
ne
e
r
i
ng
(
IJ
E
CE
)
,
vol
.
2,
no.
6
,
p
.
792
–
79
7,
2016
.
[29]
L
.
Chi
ro
e
n,
“
M
e
di
c
a
l
i
m
a
ge
fus
i
on ba
s
e
d on
di
s
c
re
t
e
w
a
ve
l
e
t
t
ra
ns
form
us
i
ng
J
A
V
A
t
e
c
hnol
og
y
,
”
P
r
oc
e
e
di
ngs
o
f
t
he
IT
I 2009
,
In
t
e
r
nat
i
onal
Conf
e
r
e
nc
e
on
Inf
or
m
at
i
on T
e
c
hnol
og
y
Int
e
r
f
ac
e
s
,
200
9.
[30]
J
. B
an
er
j
ee
,
e
t
al
., “
R
ea
l
t
i
m
e
u
n
d
er
w
at
er
i
m
a
ge
e
nha
n
c
e
m
e
nt
:
A
n i
m
prove
d a
pproa
c
h for
i
m
a
gi
ng w
i
t
h A
U
V
-
150,
”
Sadhana
,
vol
.
41
,
2016
.
Evaluation Warning : The document was created with Spire.PDF for Python.