I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
201
7
,
p
p
.
3
39
5
~
3
4
0
1
I
SS
N:
2
0
8
8
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/i
j
e
ce
.
v
7
i6
.
p
p
3
39
5
-
340
1
3395
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Cha
ng
e Detectio
n
fro
m
Re
m
o
tely S
ensed I
m
a
g
es Ba
sed o
n
Statio
na
ry
Wav
elet
Tra
nsfo
r
m
Abhi
s
he
k
S
ha
r
m
a
1
,
T
a
run
G
ula
t
i
2
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
De
p
a
rtme
n
t,
M
a
h
a
rish
i
M
a
rk
a
n
d
e
sh
w
a
r
Un
iv
e
rsit
y
,
M
u
ll
a
n
a
,
Am
b
a
la,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
1
7
,
2
0
1
7
R
ev
i
s
ed
J
u
n
2
1
,
2
0
1
7
A
cc
ep
ted
J
u
l
10
,
2
0
1
7
T
h
e
m
a
jo
r
issu
e
o
f
c
o
n
c
e
rn
in
c
h
a
n
g
e
d
e
tec
ti
o
n
p
ro
c
e
ss
is
th
e
a
c
c
u
r
a
c
y
o
f
th
e
a
lg
o
rit
h
m
to
re
c
o
v
e
r
c
h
a
n
g
e
d
a
n
d
u
n
c
h
a
n
g
e
d
p
ix
e
ls.
T
h
e
f
u
sio
n
ru
les
p
re
se
n
ted
in
t
h
e
e
x
isti
n
g
m
e
th
o
d
s
c
o
u
ld
n
o
t
i
n
teg
ra
te
th
e
f
e
a
tu
re
s
a
c
c
u
ra
tel
y
w
h
ich
re
su
lt
s
in
m
o
re
n
u
m
b
e
r
o
f
f
a
ls
e
a
lar
m
s
a
n
d
sp
e
c
k
le
n
o
ise
in
th
e
o
u
t
p
u
t
im
a
g
e
.
T
h
is
p
a
p
e
r
p
ro
p
o
se
s
a
n
a
lg
o
rit
h
m
w
h
ich
f
u
se
s
t
w
o
m
u
lt
i
-
tem
p
o
ra
l
im
a
g
e
s
th
ro
u
g
h
p
ro
p
o
se
d
se
t
o
f
fu
sio
n
r
u
les
in
sta
ti
o
n
a
ry
wa
v
e
l
e
t
tran
sf
o
r
m
.
In
t
h
e
f
irst
ste
p
,
t
h
e
so
u
rc
e
im
a
g
e
s
o
b
tain
e
d
f
ro
m
lo
g
ra
ti
o
a
n
d
m
e
a
n
ra
ti
o
o
p
e
ra
to
rs
a
re
d
e
c
o
m
p
o
se
d
in
to
th
re
e
h
ig
h
f
re
q
u
e
n
c
y
su
b
-
b
a
n
d
s
a
n
d
o
n
e
lo
w
f
re
q
u
e
n
c
y
su
b
-
b
a
n
d
b
y
sta
ti
o
n
a
ry
w
a
v
e
let
tran
s
f
o
r
m
.
T
h
e
n
,
p
ro
p
o
se
d
f
u
sio
n
ru
les
f
o
r
lo
w
a
n
d
h
ig
h
f
re
q
u
e
n
c
y
su
b
-
b
a
n
d
s
a
re
a
p
p
li
e
d
o
n
t
h
e
c
o
e
ff
icie
n
t
m
a
p
s to
g
e
t
th
e
f
u
se
d
w
a
v
e
let
c
o
e
ff
icie
n
ts
m
a
p
.
T
h
e
f
u
se
d
i
m
a
g
e
is
re
c
o
v
e
re
d
b
y
a
p
p
ly
in
g
th
e
i
n
v
e
rs
e
sta
ti
o
n
a
ry
w
a
v
e
let
tran
s
f
o
r
m
(IS
WT
)
o
n
th
e
f
u
se
d
c
o
e
ff
icie
n
t
m
a
p
.
F
in
a
ll
y
,
th
e
c
h
a
n
g
e
d
a
n
d
u
n
c
h
a
n
g
e
d
a
re
a
s
a
re
c
las
si
f
ied
u
sin
g
F
u
z
z
y
c
m
e
a
n
s
c
lu
ste
rin
g
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
a
lg
o
r
it
h
m
is
c
a
lcu
late
d
in
ter
m
s
o
f
p
e
rc
e
n
tag
e
c
o
rre
c
t
c
las
si
f
ica
ti
o
n
(P
CC),
o
v
e
ra
ll
e
rro
r
(OE)
a
n
d
Ka
p
p
a
c
o
e
f
f
icie
n
t
(K
c
).
T
h
e
q
u
a
li
tativ
e
a
n
d
q
u
a
n
ti
tati
v
e
re
su
lt
s
p
ro
v
e
th
a
t
t
h
e
p
r
o
p
o
se
d
m
e
th
o
d
o
f
f
e
rs
le
a
st
e
rro
r,
h
ig
h
e
st
a
c
c
u
ra
c
y
a
n
d
Ka
p
p
a
v
a
lu
e
a
s co
m
p
a
re
to
it
s p
re
e
x
isten
c
e
s.
K
ey
w
o
r
d
:
C
h
a
n
g
e
d
etec
tio
n
Statio
n
ar
y
w
av
ele
t
t
r
an
s
f
o
r
m
I
m
ag
e
f
u
s
io
n
L
o
g
r
atio
Me
an
r
atio
Fu
zz
y
c
lu
s
ter
in
g
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
b
h
is
h
ek
Sh
ar
m
a,
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icat
i
o
n
Dep
ar
t
m
en
t,
Ma
h
ar
is
h
i M
ar
k
a
n
d
es
h
w
ar
Un
iv
er
s
it
y
,
Mu
lla
n
a,
Am
b
ala,
I
n
d
ia.
E
m
ail: a
b
h
is
h
ek
.
k
au
s
h
ik
1
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
C
h
a
n
g
e
d
etec
tio
n
is
a
p
r
o
ce
s
s
in
w
h
ic
h
t
h
e
m
u
lti
-
te
m
p
o
r
al
i
m
ag
e
s
ar
e
co
m
p
ar
ed
to
d
etec
t
th
e
n
u
m
b
er
o
f
p
ix
el
s
t
h
at
h
a
v
e
u
n
d
er
g
o
n
e
c
h
a
n
g
e
w
it
h
t
i
m
e
[
1
]
.
T
h
e
m
o
s
t
b
asic
tech
n
iq
u
e
s
u
s
ed
f
o
r
ch
a
n
g
e
d
etec
tio
n
ar
e
d
if
f
er
en
c
in
g
an
d
r
atio
in
g
.
I
n
i
m
a
g
e
d
if
f
er
e
n
cin
g
,
t
h
e
co
r
r
esp
o
n
d
in
g
p
i
x
e
l
in
o
n
e
i
m
ag
e
i
s
s
u
b
tr
ac
ted
f
r
o
m
th
e
s
ec
o
n
d
i
m
ag
e
to
g
e
n
er
ate
a
d
if
f
er
en
ce
i
m
ag
e.
I
n
i
m
ag
e
r
atio
i
n
g
,
th
e
c
o
r
r
esp
o
n
d
in
g
v
a
lu
e
s
o
f
p
ix
el
s
i
n
m
u
lti
-
te
m
p
o
r
al
i
m
ag
e
s
ar
e
d
i
v
id
ed
to
g
et
t
h
e
o
u
tp
u
t
i
m
ag
e.
Ou
t
o
f
th
e
s
e
tech
n
iq
u
es,
r
atio
in
g
tech
n
iq
u
es
ar
e
m
o
r
e
p
o
p
u
lar
b
ec
au
s
e
o
f
t
h
eir
r
o
b
u
s
t
n
es
s
to
ca
lib
r
atio
n
er
r
o
r
s
[
2
]
-
[
3
]
.
Ho
w
ev
er
,
ev
er
y
c
h
an
g
e
d
etec
tio
n
m
eth
o
d
s
h
a
v
e
it
s
o
w
n
ad
v
an
ta
g
es
an
d
d
r
a
w
b
ac
k
s
in
ter
m
s
o
f
t
h
e
f
alse
alar
m
s
g
e
n
er
atio
n
an
d
ac
cu
r
ac
y
o
f
th
e
ch
a
n
g
e
d
etec
tio
n
.
So
,
it
is
d
if
f
icu
l
t
to
o
b
tai
n
all
th
e
f
ea
t
u
r
es
f
r
o
m
o
n
e
c
h
an
g
e
d
etec
to
r
.
T
o
o
v
er
co
m
e
t
h
is
d
i
f
f
ic
u
lt
y
,
th
e
o
u
tp
u
t
o
f
d
i
f
f
er
e
n
t c
h
a
n
g
e
d
ete
ctio
n
m
eth
o
d
s
ca
n
b
e
co
m
b
i
n
e
d
to
g
eth
er
to
o
b
tai
n
a
h
ig
h
q
u
alit
y
o
u
tp
u
t.
S
u
ch
te
ch
n
iq
u
e
o
f
in
te
g
r
ati
n
g
t
h
e
d
if
f
er
en
t
i
m
ag
e
s
to
g
et
h
er
is
ca
lled
as
im
a
g
e
f
u
s
io
n
[
4
]
.
T
h
e
o
u
tp
u
t
o
f
m
ea
n
r
atio
an
d
lo
g
r
at
io
ca
n
b
e
f
u
s
ed
to
g
eth
er
t
h
r
o
u
g
h
d
i
f
f
er
en
t
f
u
s
io
n
r
u
les
to
p
r
o
d
u
ce
a
n
o
u
tp
u
t
w
h
ic
h
co
n
tai
n
f
ea
tu
r
es
o
f
b
o
th
th
e
o
p
er
ato
r
s
.
I
n
th
e
l
iter
atu
r
e,
m
a
n
y
i
m
a
g
e
f
u
s
io
n
m
et
h
o
d
s
h
a
v
e
b
ee
n
p
r
esen
ted
l
ik
e
d
is
cr
ete
w
a
v
el
et
tr
an
s
f
o
r
m
(
DW
T
)
[
5
]
an
d
Statio
n
ar
y
w
av
elet
tr
a
n
s
f
o
r
m
[
6
]
-
[
7
]
.
H
o
w
ev
er
,
SW
T
is
th
e
p
o
p
u
lar
tech
n
iq
u
es
f
o
r
i
m
ag
e
f
u
s
io
n
b
ec
au
s
e
it
is
s
h
if
t
in
v
ar
ia
n
t
w
h
ic
h
d
o
es
n
o
t
allo
w
t
h
e
alter
atio
n
in
co
e
f
f
ic
ien
t
m
ap
i
f
th
er
e
is
an
y
s
m
all
m
i
s
m
a
tch
b
et
w
ee
n
t
h
e
p
ix
el
s
o
f
s
o
u
r
ce
i
m
ag
e
[
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
3
9
5
–
3
4
0
1
3396
I
n
Statio
n
ar
y
w
a
v
elet
tr
an
s
f
o
r
m
b
ased
i
m
a
g
e
f
u
s
io
n
,
t
h
e
s
o
u
r
ce
i
m
a
g
es
ar
e
d
ec
o
m
p
o
s
ed
in
to
f
o
u
r
eq
u
al
s
ized
i
m
a
g
e
s
.
O
n
e
i
m
a
g
e
r
ep
r
esen
ts
th
e
lo
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
co
n
ta
in
i
n
g
t
h
e
ap
p
r
o
x
i
m
ate
p
o
r
tio
n
o
f
th
e
i
m
a
g
e
w
h
ile
t
h
e
t
h
r
ee
i
m
ag
es
r
ep
r
ese
n
ti
n
g
t
h
e
h
ig
h
f
r
e
q
u
en
c
y
s
u
b
-
b
an
d
co
n
ta
in
in
f
o
r
m
atio
n
h
o
r
izo
n
tal,
v
er
tical
a
n
d
d
iag
o
n
al
co
m
p
o
n
en
ts
r
e
s
p
ec
tiv
el
y
.
I
n
th
e
n
e
x
t
s
tep
,
th
e
co
e
f
f
ic
ien
t
s
o
f
lo
w
a
n
d
h
i
g
h
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
o
f
t
h
e
d
ec
o
m
p
o
s
ed
i
m
ag
e
s
ar
e
f
u
s
ed
s
ep
ar
atel
y
to
o
b
tain
a
f
u
s
ed
co
e
f
f
icien
t
m
ap
w
h
ic
h
h
a
s
f
ea
t
u
r
e
s
o
f
b
o
th
th
e
i
m
a
g
es.
T
h
e
co
ef
f
icie
n
ts
ar
e
f
u
s
ed
b
ased
u
p
o
n
ce
r
tain
f
u
s
io
n
r
u
le
s
d
if
f
er
en
t
f
o
r
lo
w
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
an
d
h
i
g
h
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
.
T
h
e
f
u
s
ed
i
m
ag
e
is
g
en
er
ated
b
y
ap
p
l
y
i
n
g
i
n
v
er
s
e
s
tatio
n
ar
y
w
a
v
elet
tr
an
s
f
o
r
m
o
n
t
h
e
f
u
s
ed
co
ef
f
icien
t
s
m
ap
.
Ma
n
y
w
a
v
elet
t
r
an
s
f
o
r
m
b
ased
i
m
a
g
e
f
u
s
io
n
m
et
h
o
d
h
a
s
b
ee
n
p
r
esen
ted
in
th
e
liter
at
u
r
e
w
h
ich
f
i
n
d
w
av
ele
t
tr
an
s
f
o
r
m
ap
p
licab
le
in
to
m
an
y
ar
ea
s
lik
e
m
ed
ical
d
iag
n
o
s
is
,
i
m
a
g
e
an
al
y
s
i
s
an
d
r
eso
lu
tio
n
en
h
a
n
ce
m
en
t
[9
]
-
[
1
5
]
.
Fin
all
y
,
C
lu
s
ter
i
n
g
tech
n
iq
u
e
is
ap
p
lied
o
n
th
e
o
u
tp
u
t
o
f
i
m
a
g
e
f
u
s
io
n
w
h
ich
clas
s
i
f
ies
th
e
c
h
a
n
g
ed
a
n
d
u
n
c
h
a
n
g
ed
ar
ea
s
in
to
d
i
f
f
er
en
t
clu
s
ter
s
.
T
h
e
ch
an
g
ed
ar
ea
s
b
elo
n
g
to
o
n
e
cl
u
s
ter
w
h
i
le
th
e
u
n
c
h
a
n
g
ed
ar
ea
s
b
elo
n
g
to
t
h
e
o
th
er
.
T
h
er
e
ar
e
m
a
n
y
cl
u
s
ter
in
g
tech
n
iq
u
e
s
i
n
th
e
li
ter
atu
r
e
li
k
e
Fu
zz
y
C
m
ea
n
s
clu
s
ter
in
g
[
1
6
]
-
[
1
7
]
,
k
m
ea
n
s
c
lu
s
ter
in
g
[
1
8
]
a
n
d
No
n
s
u
b
s
a
m
p
led
co
n
to
u
r
let
tr
an
s
f
o
r
m
(
NSC
T
)
b
ased
clu
s
ter
i
n
g
[
1
9
]
.
T
h
is
p
ap
er
p
r
o
p
o
s
es
n
e
w
f
u
s
io
n
r
u
les
f
o
r
s
tatio
n
ar
y
w
a
v
e
let
tr
an
s
f
o
r
m
.
T
h
e
co
ef
f
icie
n
ts
o
f
lo
w
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
h
a
s
b
ee
n
f
u
s
ed
b
y
ap
p
l
y
i
n
g
p
r
o
p
o
s
ed
av
er
ag
e
b
ased
r
u
le
s
w
h
ile
t
h
e
co
ef
f
icie
n
t
s
o
f
h
i
g
h
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
ar
e
f
u
s
ed
b
y
p
r
o
p
o
s
ed
n
eig
h
b
o
r
h
o
o
d
m
e
an
d
if
f
er
en
ci
n
g
r
u
le.
T
h
e
o
r
g
an
izatio
n
o
f
th
e
p
ap
er
in
cl
u
d
es
f
o
u
r
s
ec
tio
n
s
.
T
h
e
n
ex
t
s
ec
tio
n
in
tr
o
d
u
ce
s
t
h
e
m
et
h
o
d
o
lo
g
y
u
s
ed
f
o
r
ch
a
n
g
e
d
etec
tio
n
.
T
h
ir
d
s
ec
tio
n
i
n
tr
o
d
u
ce
s
t
h
e
d
atasets
a
n
d
p
ar
am
eter
s
u
s
ed
in
th
e
e
x
p
er
i
m
e
n
t.
R
es
u
lts
a
n
d
d
is
cu
s
s
io
n
h
a
s
b
ee
n
p
r
esen
ted
in
t
h
e
f
o
u
r
t
h
s
ec
ti
o
n
.
Fif
t
h
s
ec
t
io
n
p
r
esen
t
s
t
h
e
co
n
clu
s
io
n
.
2.
P
RO
P
O
SE
D
AL
G
O
R
I
T
H
M
C
o
n
s
id
er
t
w
o
co
-
r
e
g
is
ter
ed
im
ag
e
s
I
m1
=
{
1
(
,
)
,
1
<
<
,
1
<
<
}
an
d
I
m2
=
{
2
(
,
)
,
1
<
<
,
1
<
<
}
o
f
s
ize
R
×
C
,
i.e
.
,
o
f
a
s
ce
n
e
t
ak
en
at
t
w
o
d
i
f
f
er
en
t
ti
m
e
s
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
in
v
o
lv
e
s
th
e
th
r
ee
m
a
in
s
tep
s
as
s
h
o
w
n
in
f
i
g
u
r
e
1
.
I
n
th
e
f
ir
s
t
s
tep
,
L
o
g
r
atio
an
d
Me
an
r
atio
o
p
er
ato
r
s
ar
e
ap
p
lied
o
n
t
w
o
m
u
lti
-
te
m
p
o
r
al
i
m
a
g
e
s
r
e
s
p
ec
tiv
el
y
to
g
e
n
er
ate
t
w
o
s
o
u
r
ce
i
m
ag
e
s
.
I
n
th
e
s
ec
o
n
d
s
t
ep
s
,
b
o
th
th
e
s
o
u
r
ce
i
m
a
g
es
ar
e
f
u
s
ed
b
y
s
tatio
n
ar
y
w
a
v
elet
tr
an
s
f
o
r
m
w
it
h
p
r
o
p
o
s
ed
f
u
s
io
n
r
u
le
s
.
I
n
th
e
last
s
tep
,
t
h
e
d
i
f
f
er
e
n
ce
i
m
a
g
e
is
class
if
ied
in
to
ch
an
g
ed
an
d
u
n
ch
a
n
g
ed
ar
ea
s
b
y
f
u
zz
y
c
m
ea
n
s
cl
u
s
ter
i
n
g
alg
o
r
ith
m
to
g
e
n
er
ate
a
ch
an
g
e
m
ap
.
Fig
u
r
e
1
.
Me
th
o
d
o
lo
g
y
o
f
p
r
o
p
o
s
ed
ch
an
g
e
d
etec
tio
n
ap
p
r
o
ac
h
I
n
L
o
g
R
atio
o
p
er
ato
r
,
n
atu
r
al
lo
g
ar
ith
m
s
o
f
t
h
e
r
atio
o
f
p
ix
els
in
t
h
e
i
m
a
g
es
ar
e
ca
lcu
late
d
as
g
iv
e
n
in
eq
u
atio
n
1
.
A
p
p
l
y
in
g
L
o
g
o
p
er
ato
r
o
n
an
i
m
ag
e
e
n
h
a
n
ce
s
th
e
lo
w
f
r
eq
u
e
n
c
y
co
m
p
o
n
e
n
t
s
w
h
ile
s
u
p
p
r
ess
t
h
e
h
ig
h
f
r
eq
u
en
c
y
f
ea
t
u
r
es in
t
h
e
o
u
tp
u
t i
m
ag
e.
I
l
(
i
,
j
)
=
l
og
I
m1
(
i
,
j
)
I
m2
(
i
,
j
)
(
1
)
Im
ag
e
2
Im
ag
e
1
Im
ag
e
Fu
si
o
n
Fu
sio
n
Clu
ste
rin
g
Ch
an
g
e
M
ap
M
ean R
atio
L
o
g
R
atio
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
C
h
a
n
g
e
Dete
ctio
n
fr
o
m
R
emo
t
ely
S
en
s
ed
I
ma
g
es B
a
s
ed
o
n
S
ta
tio
n
a
r
y
W
a
ve
let
Tr
a
n
s
fo
r
m
(
A
b
h
is
h
ek
S
h
a
r
ma
)
3397
I
n
ca
s
e
o
f
Me
an
R
atio
o
p
er
ato
r
,
th
e
lo
ca
l
m
ea
n
o
f
th
e
p
ix
e
l
in
o
n
e
i
m
ag
e
i
s
d
i
v
id
ed
w
it
h
t
h
e
lo
ca
l
m
ea
n
o
f
th
e
co
r
r
esp
o
n
d
in
g
p
ix
el
in
th
e
s
ec
o
n
d
i
m
ag
e
as
g
i
v
e
n
in
eq
u
a
tio
n
2
.
I
m
(
i
,
j
)
=
1
−
min
(
μ
1
μ
2
,
μ
2
μ
1
)
(
2
)
w
h
er
e
1
2
in
eq
u
atio
n
2
r
ep
r
es
en
ts
th
e
lo
ca
l
m
ea
n
v
al
u
e
o
f
th
e
p
ix
el
in
t
h
e
n
ei
g
h
b
o
r
h
o
o
d
o
f
f
ir
s
t
a
n
d
s
ec
o
n
d
i
m
a
g
e
r
esp
ec
ti
v
el
y
.
T
h
e
s
tatio
n
ar
y
w
a
v
elet
tr
a
n
s
f
o
r
m
o
f
ea
ch
o
f
t
h
e
s
o
u
r
ce
i
m
a
g
es
is
co
m
p
u
ted
w
h
ic
h
g
i
v
es
th
e
w
a
v
elet
co
ef
f
icie
n
t
o
f
b
o
th
t
h
e
i
m
ag
es.
T
h
e
f
u
s
io
n
r
u
les
ar
e
th
e
n
a
p
p
lied
in
o
r
d
er
t
o
f
u
s
e
t
h
e
co
r
r
esp
o
n
d
in
g
co
ef
f
icie
n
t
s
o
f
t
h
e
d
ec
o
m
p
o
s
e
d
s
o
u
r
ce
i
m
ag
e
s
.
Di
f
f
er
en
t
f
u
s
io
n
r
u
les
ar
e
ap
p
lied
o
n
t
h
e
lo
w
f
r
eq
u
e
n
c
y
an
d
h
ig
h
f
r
eq
u
e
n
c
y
co
e
f
f
ic
ien
t
s
.
I
n
t
h
e
n
e
x
t
s
tep
,
in
v
er
s
e
s
tat
i
o
n
ar
y
le
v
el
tr
an
s
f
o
r
m
(
I
SW
T
)
is
ap
p
lied
o
n
th
e
f
u
s
ed
r
ep
r
esen
tatio
n
to
g
et
th
e
f
u
s
ed
i
m
a
g
e.
T
h
e
f
ir
s
t
s
tep
i
n
v
o
lv
ed
i
n
th
e
p
r
o
ce
s
s
is
th
e
d
ec
o
m
p
o
s
i
tio
n
o
f
I
l
an
d
I
m
i
n
to
f
o
u
r
i
m
ag
e
s
o
f
t
h
e
eq
u
a
l
s
ize.
T
h
e
im
a
g
e
co
r
r
esp
o
n
d
in
g
to
lo
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
r
ep
r
esen
ts
th
e
ap
p
r
o
x
i
m
a
te
p
o
r
tio
n
o
f
th
e
i
m
a
g
e
w
h
ile
o
th
er
i
m
a
g
es
co
r
r
esp
o
n
d
in
g
to
h
i
g
h
f
r
eq
u
en
c
y
s
u
b
-
b
a
n
d
r
ep
r
esen
ts
th
e
in
f
o
r
m
a
tio
n
ab
o
u
t
th
e
lin
es
a
n
d
ed
g
es
in
th
e
i
m
a
g
e
w
h
ic
h
in
cl
u
d
e
h
o
r
izo
n
tal,
v
er
tical
an
d
d
iag
o
n
al
co
m
p
o
n
e
n
ts
.
I
n
SW
T
,
th
e
in
f
o
r
m
atio
n
o
f
lo
w
a
n
d
h
ig
h
p
as
s
ch
a
n
n
el
i
s
ap
p
lied
at
ev
er
y
le
v
el
a
n
d
t
wo
s
eq
u
en
ce
s
ar
e
p
r
o
d
u
ce
d
at
t
h
e
n
ex
t
s
ta
g
e.
T
h
e
len
g
th
o
f
th
e
n
e
w
s
eq
u
en
ce
s
will b
e
s
a
m
e
as t
h
at
o
f
th
e
f
ir
s
t
g
r
o
u
p
in
g
.
I
n
SW
T
,
th
e
ze
r
o
s
ar
e
in
s
er
ted
b
et
w
ee
n
f
ilter
co
ef
f
icie
n
ts
s
o
as to
u
p
-
s
a
m
p
le
th
e
f
ilter
.
As
th
e
lo
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
a
n
d
an
d
h
ig
h
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
s
r
ep
r
esen
ts
d
if
f
er
en
t
f
ea
t
u
r
es
s
o
it
is
n
ec
es
s
ar
y
to
f
u
s
e
t
h
e
m
th
r
o
u
g
h
d
if
f
er
en
t
f
u
s
io
n
r
u
les.
Her
e
t
w
o
f
u
s
io
n
r
u
le
s
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
:
Fu
s
io
n
R
u
le
f
o
r
L
o
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
I
LL
f
=
α
×
ma
x
(
I
LL
l
,
I
LL
m
)
+
(
1
+
α
)
×
(
I
LL
l
+
I
LL
m
)
2
(
3
)
Fu
s
io
n
R
u
le
f
o
r
h
i
g
h
f
r
eq
u
e
n
c
y
S
u
b
-
b
an
d
I
ϵ
f
=
ma
x
(
μ
ϵ
l
,
μ
ϵ
m
)
−
min
(
μ
ϵ
l
,
μ
ϵ
m
)
(
4
)
Her
e
in
eq
u
atio
n
3
is
a
p
o
s
itiv
e
n
u
m
b
er
.
I
m
,
I
l
an
d
I
f
r
ep
r
es
en
ts
t
h
e
m
ea
n
r
atio
,
lo
g
r
atio
an
d
f
u
s
ed
i
m
a
g
es
r
esp
ec
ti
v
el
y
.
I
LL
r
ep
r
esen
t
s
t
h
e
co
ef
f
icie
n
t
s
o
f
lo
w
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
w
h
ile
I
ɛ(
ɛ=
HL
,
L
H
an
d
HH
)
r
ep
r
esen
ts
th
e
co
ef
f
icie
n
ts
o
f
h
ig
h
f
r
eq
u
en
c
y
s
u
b
-
ba
n
d
,
μ
ϵ
r
ep
r
esen
ts
t
h
e
lo
ca
l
m
ea
n
o
f
t
h
e
co
ef
f
icie
n
t
s
o
f
th
e
n
eig
h
b
o
r
h
o
o
d
w
in
d
o
w
i
n
th
e
h
i
g
h
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
.
A
w
in
d
o
w
s
ize
o
f
3
×3
h
a
s
b
ee
n
co
n
s
id
er
ed
in
th
e
alg
o
r
ith
m
.
A
s
th
e
lo
w
a
n
d
h
i
g
h
f
r
eq
u
e
n
c
y
co
m
p
o
n
e
n
ts
ar
e
o
b
tain
ed
b
y
co
m
b
i
n
i
n
g
th
e
s
p
atial
an
d
g
r
a
y
lev
e
l
in
f
o
r
m
atio
n
o
f
t
h
e
n
ei
g
h
b
o
r
s
,
s
o
,
th
e
f
u
s
io
n
r
u
les
f
u
r
t
h
er
r
ed
u
ce
s
th
e
ef
f
ec
t
o
f
s
p
ec
k
le
n
o
is
e.
T
h
e
p
r
o
p
o
s
ed
r
u
les
f
o
r
lo
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
an
d
en
h
an
ce
th
e
ed
g
e
f
ea
t
u
r
es
o
f
ch
a
n
g
ed
r
e
g
io
n
s
o
f
t
h
e
s
o
u
r
ce
i
m
a
g
e
w
h
ile
i
n
h
ig
h
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
,
th
e
f
u
s
io
n
r
u
le
is
s
elec
ted
in
s
u
c
h
a
w
a
y
to
s
u
p
p
r
ess
th
e
b
ac
k
g
r
o
u
n
d
in
f
o
r
m
a
tio
n
an
d
m
ak
e
t
h
e
i
m
a
g
e
s
m
o
o
t
h
er
.
So
b
ased
u
p
o
n
t
h
e
p
r
o
p
o
s
ed
f
u
s
io
n
r
u
les,
th
e
c
h
an
g
e
d
ete
ctio
n
o
u
tp
u
t
r
esu
lt
s
in
m
a
x
i
m
u
m
b
ac
k
g
r
o
u
n
d
s
u
p
p
r
ess
io
n
a
n
d
en
h
a
n
ce
d
f
ea
t
u
r
es
in
th
e
c
h
a
n
g
ed
i
m
a
g
e.
3.
DATAS
E
T
AND
P
ARAM
E
T
E
R
S
T
h
e
im
a
g
e
d
ataset
u
s
ed
f
o
r
ca
lcu
lati
n
g
th
e
e
f
f
ec
tiv
e
n
es
s
o
f
alg
o
r
ith
m
s
b
elo
n
g
s
to
th
e
cit
y
o
f
B
er
n
,
S
w
itzer
lan
d
ca
p
tu
r
ed
b
y
E
u
r
o
p
ea
n
R
e
m
o
te
Sen
s
i
n
g
2
s
a
telli
te
in
t
h
e
m
o
n
t
h
o
f
A
p
r
il
an
d
Ma
y
1
9
9
9
as
s
h
o
w
n
in
F
ig
u
r
e
2
(
a)
an
d
2
(
b
)
.
B
et
w
ee
n
t
h
e
t
w
o
d
ates,
t
h
e
B
er
n
c
it
y
a
n
d
air
p
o
r
t
w
as
f
lo
o
d
ed
b
y
A
ar
e
R
i
v
er
.
T
h
e
g
r
o
u
n
d
tr
u
th
h
as b
ee
n
s
h
o
w
n
i
n
F
i
g
u
r
e
2
(
c)
.
T
h
e
im
a
g
e
s
ize
o
f
(
3
2
9
×3
2
9
)
h
as b
ee
n
u
s
ed
in
th
is
e
x
p
er
i
m
e
n
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
3
9
5
–
3
4
0
1
3398
(
a)
(
b
)
(
c)
Fig
u
r
e
2
.
Mu
lti
-
te
m
p
o
r
al
i
m
ag
es o
f
B
er
n
cit
y
(
a)
I
m
a
g
e
ca
p
tu
r
ed
in
A
p
r
il 1
9
9
9
b
ef
o
r
e
f
lo
o
d
in
g
(
b
)
I
m
ag
e
ca
p
tu
r
ed
in
Ma
y
1
9
9
9
af
ter
f
lo
o
d
in
g
(
c)
Gr
o
u
n
d
tr
u
t
h
[
5
]
I
n
th
is
p
ap
er
,
th
e
r
e
s
u
l
ts
o
b
tai
n
ed
f
r
o
m
p
r
o
p
o
s
ed
m
e
th
o
d
h
a
v
e
b
ee
n
co
m
p
ar
ed
w
ith
th
e
r
es
u
lts
o
f
lo
g
r
atio
,
m
ea
n
r
atio
o
p
er
ato
r
s
,
Di
s
cr
ete
W
av
elet
T
r
an
s
f
o
r
m
(
D
W
T
)
b
ased
i
m
a
g
e
f
u
s
io
n
[
5
]
,
Neig
h
b
o
r
h
o
o
d
b
ased
r
atio
ap
p
r
o
ac
h
[
2
0
]
an
d
L
o
g
ar
ith
m
ic
r
atio
b
ased
T
h
r
es
h
o
ld
in
g
[
2
1
]
.
T
h
e
co
m
p
ar
is
o
n
is
d
o
n
e
o
n
th
e
b
asis
o
f
v
ar
io
u
s
p
ar
a
m
eter
s
a
n
d
ch
a
n
g
e
i
m
a
g
e
m
ap
g
e
n
er
ated
b
y
th
e
alg
o
r
ith
m
s
.
T
h
e
p
ar
a
m
eter
s
u
s
ed
f
o
r
ca
lcu
lat
io
n
o
f
ef
f
ec
ti
v
en
e
s
s
i
n
cl
u
d
e
p
er
ce
n
tag
e
co
r
r
ec
t c
lass
if
icatio
n
(
P
C
C
)
an
d
Kap
p
a
C
o
ef
f
icie
n
t (
K
c
)
[
2
2
]
.
P
C
C
=
(
T
p
+
T
n
)
(
T
p
+
T
n
+
F
p
+
F
n
)
(
5
)
I
f
A
=
(
(
Tp
+
Fn
)
x
(
Tp
+
Fp
)
+
(
Fp
+
Tn
)
x
(
Tn
+
Fn
)
)
(
Tp
+
Tn
+
Fp
+
Tn
)
2
(
6
)
K
c
=
PC
C
−
A
1
−
A
(
7
)
T
P
r
ep
r
esen
ts
t
h
e
ch
a
n
g
ed
p
ix
els
w
h
ic
h
h
a
s
b
ee
n
id
en
tifie
d
co
r
r
ec
tl
y
as
c
h
an
g
ed
p
ix
el
s
.
T
h
e
v
alu
e
o
f
T
P
is
1
if
th
e
v
al
u
e
o
f
co
r
r
esp
o
n
d
in
g
p
ix
els
i
n
o
u
tp
u
t
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
an
d
g
r
o
u
n
d
tr
u
th
ar
e
b
o
th
1
.
Oth
er
w
is
e
T
P
w
i
ll
b
e
ze
r
o
.
T
n
r
ep
r
esen
ts
th
e
u
n
c
h
a
n
g
ed
p
ix
e
ls
w
h
ic
h
h
a
v
e
b
ee
n
co
r
r
ec
tly
id
en
tif
ied
as
u
n
c
h
a
n
g
ed
.
T
h
e
v
al
u
e
o
f
T
n
is
1
if
t
h
e
co
r
r
esp
o
n
d
in
g
p
ix
el
s
v
al
u
e
i
n
o
u
tp
u
t o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
a
n
d
g
r
o
u
n
d
tr
u
th
ar
e
b
o
th
0
.
Oth
er
w
i
s
e
T
n
w
il
l
b
e
ze
r
o
.
F
P
r
ep
r
esen
ts
th
o
s
e
p
ix
els
w
h
ic
h
ar
e
ac
tu
all
y
ch
a
n
g
ed
b
u
t
id
en
ti
f
ied
as
u
n
c
h
an
g
ed
p
ix
el
s
.
T
h
e
v
alu
e
o
f
F
P
is
1
if
t
h
e
p
i
x
els
v
al
u
e
in
o
u
tp
u
t
o
f
alg
o
r
i
th
m
is
1
an
d
t
h
e
v
alu
e
o
f
co
r
r
esp
o
n
d
in
g
p
ix
el
i
n
g
r
o
u
n
d
tr
u
th
i
s
0
.
Oth
er
w
i
s
e
F
P
w
i
ll
b
e
ze
r
o
.
F
n
r
ep
r
esen
ts
th
o
s
e
u
n
ch
a
n
g
ed
p
ix
els
w
h
ic
h
h
a
v
e
b
ee
n
id
en
ti
f
ied
w
r
o
n
g
l
y
as
ch
a
n
g
ed
.
T
h
e
v
al
u
e
o
f
F
n
is
1
i
f
t
h
e
p
i
x
els
v
a
lu
e
i
n
t
h
e
o
u
tp
u
t
o
f
alg
o
r
ith
m
is
0
an
d
th
e
v
alu
e
o
f
co
r
r
esp
o
n
d
in
g
p
ix
el
i
n
g
r
o
u
n
d
tr
u
t
h
is
1
.
Oth
er
w
is
e
F
n
w
il
l
b
e
ze
r
o
.
Ov
er
all
E
r
r
o
r
(
OE
)
is
th
e
s
u
m
o
f
F
P
an
d
F
n
.
P
C
C
g
i
v
es
t
h
e
p
er
ce
n
ta
g
e
o
f
p
ix
el
s
co
r
r
ec
tl
y
id
en
t
if
ied
b
y
th
e
c
h
a
n
g
e
d
etec
tio
n
al
g
o
r
ith
m
.
K
c
r
ep
r
esen
ts
t
h
e
a
g
r
ee
m
e
n
t
b
et
w
ee
n
t
h
e
o
u
tp
u
t
o
f
ch
a
n
g
e
d
etec
tio
n
alg
o
r
it
h
m
w
it
h
th
e
g
r
o
u
n
d
tr
u
th
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
o
f
in
d
th
e
ef
f
ec
ti
v
e
n
es
s
,
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
a
s
b
ee
n
ap
p
lied
o
n
th
e
i
m
ag
e
d
ataset
o
f
cit
y
o
f
B
er
n
.
T
h
e
q
u
alitativ
e
an
a
l
y
s
i
s
h
as
b
ee
n
d
o
n
e
b
y
g
en
er
ati
n
g
t
h
e
ch
a
n
g
e
m
a
p
as
s
h
o
wn
in
F
i
g
u
r
e
3
.
T
h
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
C
h
a
n
g
e
Dete
ctio
n
fr
o
m
R
emo
t
ely
S
en
s
ed
I
ma
g
es B
a
s
ed
o
n
S
ta
tio
n
a
r
y
W
a
ve
let
Tr
a
n
s
fo
r
m
(
A
b
h
is
h
ek
S
h
a
r
ma
)
3399
q
u
an
tita
tiv
e
a
n
al
y
s
is
h
as
b
ee
n
o
b
tain
ed
b
y
co
m
p
ar
in
g
th
e
o
u
tp
u
t
w
it
h
g
r
o
u
n
d
tr
u
t
h
th
r
o
u
g
h
v
ar
io
u
s
p
ar
am
eter
s
li
k
e
f
alse
alar
m
s
,
p
er
ce
n
tag
e
co
r
r
ec
t
cla
s
s
i
f
icatio
n
,
o
v
er
all
er
r
o
r
an
d
Kap
p
a
co
e
f
f
icien
t
as
g
i
v
e
n
i
n
T
ab
le
1
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
y
ield
ed
h
i
g
h
e
s
t
P
C
C
e
q
u
al
to
9
9
.
6
8
%
w
h
ile
P
C
C
f
o
r
Dis
cr
ete
w
av
ele
t
tr
an
s
f
o
r
m
b
ased
i
m
a
g
e
f
u
s
io
n
is
9
9
.
3
7
%,
P
C
C
f
o
r
n
e
ig
h
b
o
r
h
o
o
d
r
atio
b
ased
m
et
h
o
d
is
9
9
.
6
6
%
an
d
P
C
C
f
o
r
L
o
g
ar
it
h
m
ic
m
ea
n
b
ased
T
h
r
esh
o
ld
in
g
i
s
9
7
.
3
2
%.
T
h
e
lo
g
r
atio
o
p
er
ato
r
i
m
p
r
o
v
es
th
e
c
h
a
n
g
e
d
etec
tio
n
r
es
u
l
t
b
y
co
n
v
er
ti
n
g
t
h
e
m
u
l
tip
licati
v
e
s
p
ec
k
le
n
o
is
e
i
n
to
ad
d
itiv
e.
So
,
th
e
o
u
tp
u
t
o
f
lo
g
r
atio
o
p
er
ato
r
co
n
tain
s
les
s
s
p
ec
k
le
n
o
is
e.
B
u
t,
t
h
e
lo
g
r
a
tio
o
p
er
ato
r
r
esu
lts
in
lar
g
e
n
u
m
b
er
o
f
f
al
s
e
alar
m
s
w
h
ic
h
m
ea
n
s
t
h
at
it
i
s
n
o
t
ca
p
ab
le
o
f
r
ec
o
v
er
in
g
th
e
m
ax
i
m
u
m
u
n
c
h
a
n
g
ed
p
i
x
els.
O
n
t
h
e
o
t
h
er
h
an
d
,
m
ea
n
r
atio
o
p
er
ato
r
r
esu
lt
s
i
n
lar
g
e
a
m
o
u
n
t
o
f
s
p
ec
k
le
n
o
is
e
b
u
t
i
t
r
ec
o
v
er
s
th
e
m
a
x
i
m
u
m
n
u
m
b
er
o
f
u
n
c
h
an
g
ed
p
ix
el
s
.
T
h
e
o
u
tp
u
t
o
f
b
o
th
th
e
o
p
er
ato
r
s
h
as
b
ee
n
f
u
s
ed
to
g
eth
er
to
r
ec
o
v
er
m
a
x
i
m
u
m
n
u
m
b
er
o
f
ch
a
n
g
ed
an
d
u
n
ch
an
g
ed
p
ix
e
ls
.
B
y
in
tr
o
d
u
ci
n
g
n
ei
g
h
b
o
r
h
o
o
d
m
e
an
f
o
r
t
h
e
w
a
v
elet
co
ef
f
icie
n
t
s
,
th
e
ch
a
n
g
e
d
etec
tio
n
h
as
r
e
s
u
lted
i
n
d
etec
tio
n
o
f
m
o
r
e
c
h
a
n
g
ed
a
n
d
u
n
ch
a
n
g
e
d
p
ix
els.
A
ls
o
,
t
h
e
n
eig
h
b
o
r
h
o
o
d
r
atio
co
m
b
i
n
es
t
h
e
g
r
ay
le
v
el
an
d
s
p
atial
in
f
o
r
m
atio
n
i
n
t
h
e
n
ei
g
h
b
o
r
in
g
p
ix
el
s
w
h
ic
h
r
es
u
lt
s
in
f
u
r
t
h
er
r
ed
u
ctio
n
o
f
s
p
ec
k
le
n
o
is
e.
As
s
h
o
w
n
in
f
i
g
u
r
e
3
(
f
)
,
th
e
ch
an
g
e
m
ap
g
en
er
ated
b
y
p
r
o
p
o
s
ed
m
eth
o
d
h
as
lea
s
t
s
p
o
ts
an
d
m
ax
i
m
u
m
r
ese
m
b
la
n
ce
w
it
h
t
h
e
g
r
o
u
n
d
tr
u
th
as
co
m
p
ar
e
t
o
th
e
o
th
er
m
et
h
o
d
s
u
s
ed
f
o
r
co
m
p
ar
is
o
n
.
T
h
e
ch
an
g
e
m
ap
g
en
er
ated
b
y
lo
g
r
atio
m
et
h
o
d
h
a
s
le
s
s
s
p
ec
k
l
e
n
o
is
e
b
u
t
it
co
u
ld
n
o
t
r
ec
o
v
er
th
e
c
h
a
n
g
ed
a
n
d
u
n
c
h
a
n
g
ed
p
ix
e
ls
m
o
r
e
e
f
f
ec
tiv
el
y
.
On
th
e
o
t
h
er
h
a
n
d
,
m
ea
n
r
atio
h
as
r
es
u
lted
i
n
lar
g
e
n
u
m
b
er
o
f
f
alse
alar
m
s
w
h
ic
h
ca
n
al
s
o
b
e
s
ee
n
in
f
i
g
u
r
e
3
(
b
)
w
h
er
e
lar
g
e
n
u
m
b
er
o
f
w
h
ite
s
p
o
ts
e
x
is
t
s
.
Dis
cr
ete
w
av
e
let
tr
an
s
f
o
r
m
h
a
s
b
ee
n
ef
f
ec
ti
v
e
in
r
ec
o
v
er
in
g
th
e
m
a
x
i
m
u
m
u
n
ch
a
n
g
ed
p
ix
els
b
u
t
it
h
a
s
n
o
t
b
ee
n
ef
f
ec
ti
v
e
i
n
r
ec
o
v
er
in
g
t
h
e
ch
a
n
g
ed
p
ix
e
ls
.
if
th
e
c
h
an
g
e
m
ap
o
f
p
r
o
p
o
s
ed
a
lg
o
r
ith
m
is
co
m
p
ar
ed
w
ith
t
h
e
o
th
er
tech
n
iq
u
es
t
h
e
n
it
is
f
o
u
n
d
t
h
at
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
h
as
r
es
u
lted
in
m
ax
i
m
u
m
r
e
s
e
m
b
la
n
ce
w
it
h
th
e
g
r
o
u
n
d
tr
u
t
h
.
T
h
e
p
r
o
p
o
s
ed
a
lg
o
r
ith
m
h
a
s
also
y
ield
ed
h
i
g
h
est
v
alu
e
o
f
Kap
p
a
co
ef
f
icie
n
t
eq
u
al
to
0
.
9
9
5
8
w
h
ile
it
i
s
0
.
9
9
5
2
f
o
r
L
o
g
R
atio
,
0
.
7
5
1
5
f
o
r
Me
an
R
atio
,
0
.
7
9
0
f
o
r
Dis
cr
ete
W
av
elet
tr
an
s
f
o
r
m
,
0
.
8
5
0
f
o
r
Neig
h
b
o
r
h
o
o
d
R
atio
m
et
h
o
d
an
d
0
.
6
9
2
8
f
o
r
L
o
g
ar
ith
m
ic
m
e
an
T
h
r
esh
o
ld
in
g
b
ased
c
h
an
g
e
d
etec
tio
n
m
et
h
o
d
.
T
h
is
m
ea
n
s
th
at
t
h
e
o
u
tp
u
t
o
f
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
th
e
m
o
s
t
ag
r
e
e
m
e
n
t
w
it
h
th
e
g
r
o
u
n
d
tr
u
th
w
h
ic
h
m
a
k
es
i
t
m
o
s
t a
cc
u
r
ate
a
m
o
n
g
t
h
e
o
th
er
m
eth
o
d
s
m
e
n
tio
n
ed
i
n
th
i
s
p
ap
er
.
T
ab
le
1
.
R
esu
lts
o
f
C
h
an
g
e
De
tectio
n
Fig
u
r
e
3
s
h
o
w
t
h
e
ch
a
n
g
e
m
ap
o
f
B
er
n
d
ataset
a
s
o
b
tain
e
d
b
y
lo
g
r
atio
,
m
ea
n
r
at
io
,
DW
T
-
FC
M,
n
eig
h
b
o
r
h
o
o
d
r
atio
ap
p
r
o
ac
h
,
lo
g
ar
ith
m
ic
m
ea
n
th
r
es
h
o
ld
in
g
an
d
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
I
t
ca
n
b
e
s
ee
n
t
h
at
t
h
e
ch
an
g
e
m
ap
o
b
tain
ed
f
r
o
m
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
h
as
r
ec
o
v
er
ed
th
e
m
a
x
i
m
u
m
tar
g
et
p
ix
els
an
d
r
ed
u
ce
t
h
e
sp
ec
k
le
n
o
i
s
e.
(
a)
(
b
)
(
c)
C
r
i
t
e
r
i
o
n
M
e
t
h
o
d
L
o
g
R
a
t
i
o
M
e
a
n
R
a
t
i
o
D
i
scre
t
e
W
a
v
e
l
e
t
T
r
a
n
sf
o
r
m
N
e
i
g
h
b
o
r
h
o
o
d
R
a
t
i
o
L
o
g
a
r
i
t
h
mi
c
M
e
a
n
T
h
r
e
sh
o
l
d
i
n
g
P
r
o
p
o
se
d
F
p
37
1
7
1
1
5
5
0
7
1
1
0
6
7
7
1
3
9
F
n
2
9
3
6
61
1
9
9
1
0
7
7
1
5
0
OE
3
3
0
1
7
1
2
1
5
6
8
3
0
9
1
7
5
4
2
8
9
P
C
C
9
9
.
6
4
%
8
1
.
2
3
%
9
9
.
3
7
%
9
9
.
6
6
%
9
7
.
3
2
%
9
9
.
6
8
%
K
a
p
p
a
0
.
9
9
5
2
0
.
7
5
1
5
0
.
7
9
0
0
.
8
5
9
0
.
6
9
2
8
0
.
9
9
5
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
6
,
Dec
em
b
er
2
0
1
7
:
3
3
9
5
–
3
4
0
1
3400
(
d
)
(
e)
(
f
)
Fig
u
r
e
3
.
C
h
a
n
g
e
m
ap
g
e
n
er
at
ed
b
y
.
(
a)
L
o
g
R
atio
(
b
)
Me
an
R
atio
(
c)
DW
T
-
FC
M
(
d
)
Neig
h
b
o
r
h
o
o
d
R
atio
ap
p
r
o
ac
h
(
e)
L
o
g
ar
ith
m
ic
Me
an
T
h
r
esh
o
ld
in
g
(
f
)
P
r
o
p
o
s
ed
M
eth
o
d
5.
CO
NCLU
SI
O
N
T
h
is
p
ap
er
p
r
esen
ted
an
ap
p
r
o
ac
h
b
ased
o
n
Statio
n
ar
y
w
av
el
et
tr
an
s
f
o
r
m
w
it
h
n
e
w
f
u
s
io
n
r
u
les.
T
h
e
s
o
u
r
ce
i
m
a
g
es
g
e
n
er
ated
b
y
lo
g
r
atio
a
n
d
m
ea
n
r
atio
o
p
er
ato
r
ar
e
f
u
s
ed
w
i
th
n
e
w
s
et
o
f
f
u
s
io
n
r
u
le
s
p
r
o
p
o
s
ed
in
t
h
i
s
p
ap
er
.
T
h
e
f
u
s
io
n
r
u
les
f
o
r
lo
w
f
r
eq
u
e
n
c
y
s
u
b
-
b
a
n
d
en
h
a
n
ce
th
e
ed
g
e
f
ea
t
u
r
es
o
f
t
h
e
c
h
an
g
ed
r
eg
io
n
.
T
h
e
f
u
s
io
n
r
u
le
f
o
r
h
i
g
h
f
r
eq
u
en
c
y
s
u
b
-
b
a
n
d
co
m
b
in
e
s
th
e
s
p
atia
l
an
d
g
r
a
y
le
v
el
in
f
o
r
m
atio
n
o
f
t
h
e
n
eig
h
b
o
r
in
g
p
ix
e
l
w
h
ich
r
esu
lts
i
n
r
ed
u
ctio
n
o
f
s
p
ec
k
le
n
o
is
e
f
r
o
m
th
e
i
m
ag
e
s
.
So
,
t
h
e
f
u
s
ed
i
m
a
g
e
g
e
t
en
h
a
n
ce
s
a
n
d
co
n
tai
n
les
s
a
m
o
u
n
t
o
f
s
p
ec
k
le
n
o
is
e.
T
h
e
q
u
an
t
itati
v
e
an
al
y
s
i
s
p
r
o
v
es
th
at
th
e
ac
cu
r
ac
y
an
d
k
ap
p
a
v
alu
e
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
b
etter
t
h
an
i
ts
p
r
ee
x
is
te
n
ce
s
.
As
f
ar
as
q
u
alita
tiv
e
co
m
p
ar
is
o
n
is
co
n
ce
r
n
ed
,
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
o
f
f
er
t
h
e
lea
s
t
o
v
er
al
l
e
r
r
o
r
an
d
m
ax
i
m
u
m
r
ese
m
b
la
n
ce
w
ith
t
h
e
g
r
o
u
n
d
tr
u
th
.
So
,
b
ased
u
p
o
n
th
e
an
al
y
s
i
s
o
f
r
es
u
lt
s
it
i
s
co
n
cl
u
d
ed
th
at
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
m
o
r
e
ac
cu
r
ate
a
s
co
m
p
ar
e
to
th
e
o
t
h
er
s
i
m
ilar
m
et
h
o
d
s
.
RE
F
E
R
E
NC
E
S
[1
]
R.
J.
Ra
d
k
e
,
e
t
a
l
.
,
“
Im
a
g
e
Ch
a
n
g
e
De
tec
ti
o
n
A
lg
o
rit
h
m
s:
A
S
y
ste
m
a
ti
c
S
u
rv
e
y
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
.
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l
/
issu
e
:
14
(
3
)
,
p
p
.
2
9
4
–
3
0
7
,
2
0
0
5
.
[2
]
A
S
in
g
h
,
“
Dig
it
a
l
Ch
a
n
g
e
D
e
tec
t
io
n
T
e
c
h
n
iq
u
e
s
Us
in
g
Re
m
o
tel
y
S
e
n
se
d
Da
ta
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Rem
o
te
S
e
n
sin
g
,
v
o
l
/
issu
e
:
10
(
6
)
,
p
p
.
9
8
9
-
1
0
0
3
,
1
9
8
9
.
[3
]
A
.
S
h
a
r
m
a
a
n
d
T
.
G
u
lati,
“
Re
v
ie
w
o
f
Ch
a
n
g
e
D
e
tec
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
Re
m
o
tel
y
S
e
n
se
d
I
m
a
g
e
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
c
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l
/i
ss
u
e
:
5
(
1
)
,
p
p
.
2
2
-
2
5
,
2
0
1
7
.
[4
]
H.
Zh
a
n
g
a
n
d
X
.
Ca
o
,
“
A
Wa
y
o
f
Im
a
g
e
F
u
s
io
n
Ba
se
d
o
n
W
a
v
e
let
T
ra
n
s
f
o
r
m
,
”
IEE
E
9
th
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
o
b
il
e
A
d
-
h
o
c
a
n
d
S
e
n
so
r Ne
t
wo
rk
s
,
Da
li
a
n
,
p
p
.
4
9
8
-
5
0
1
,
2
0
1
3
.
[5
]
M
.
G
o
n
g
,
e
t
a
l.
,
“
Ch
a
n
g
e
De
tec
ti
o
n
in
S
y
n
th
e
ti
c
A
p
e
rtu
re
Ra
d
a
r
Im
a
g
e
s
Ba
s
e
d
o
n
Im
a
g
e
F
u
sio
n
a
n
d
F
u
z
z
y
C
lu
ste
rin
g
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
Ima
g
e
Pr
o
c
e
ss
in
g
,
v
o
l
/i
ss
u
e
:
2
1(
4
)
,
p
p
.
2
1
4
1
-
2
1
5
1
,
2
0
1
2
.
[6
]
M
.
Be
a
u
li
e
u
,
e
t
a
l.
,
“
M
u
lt
i
-
S
p
e
c
t
ra
l
Im
a
g
e
Re
so
lu
ti
o
n
Re
f
in
e
m
e
n
t
Us
in
g
S
tatio
n
a
ry
Wav
e
let
T
ra
n
s
fo
rm
,
”
IGARS
S
2
0
0
3
,
2
0
0
3
IEE
E
In
ter
n
a
ti
o
n
a
l
G
e
o
sc
ien
c
e
a
n
d
Rem
o
te S
e
n
sin
g
S
y
mp
o
siu
m
,
v
o
l.
6
,
p
p
.
4
0
3
2
-
4
0
3
4
,
2
0
0
3
.
[7
]
J
.
E.
F
o
w
ler,
“
T
h
e
Re
d
u
n
d
a
n
t
Disc
re
te
Wav
e
let
T
ra
n
s
f
o
r
m
a
n
d
A
d
d
it
iv
e
No
is
e
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
i
g
n
a
l
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
12
,
p
p
.
6
2
9
-
6
3
2
,
2
0
0
5
.
[8
]
S
a
ra
n
y
a
G
.
a
n
d
S
.
N.
De
v
i,
“
P
e
rfo
rm
a
n
c
e
Ev
a
lu
a
ti
o
n
f
o
r
Im
a
g
e
F
u
sio
n
T
e
c
h
n
iq
u
e
in
M
e
d
ica
l
Im
a
g
e
s
Us
in
g
S
p
a
ti
a
l
a
n
d
T
ra
n
sf
o
r
m
M
e
th
o
d
,
”
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
W
ire
l
e
ss
Co
mm
u
n
ica
ti
o
n
s,
S
i
g
n
a
l
Pro
c
e
ss
in
g
a
n
d
Ne
two
rk
in
g
,
C
h
e
n
n
a
i,
p
p
.
4
4
6
-
4
5
0
,
2
0
1
6
.
[9
]
K.
K.
Ku
m
a
r,
e
t
a
l.
,
“
Re
so
lu
ti
o
n
En
h
a
n
c
e
m
e
n
t
Us
in
g
D
WT
a
n
d
S
WT
b
y
F
u
sio
n
T
e
c
h
n
iq
u
e
s
w
it
h
W
a
ter
m
a
rk
in
g
,
”
IEE
E
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ta
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
C
o
mp
u
ti
n
g
Res
e
a
rc
h
,
C
o
im
b
a
to
re
,
p
p
.
1
-
5
,
2
0
1
4
.
[1
0
]
P
.
Bo
rw
o
n
w
a
tan
a
d
e
lo
k
,
e
t
a
l.
,
“
M
u
lt
i
F
o
c
u
s
Im
a
g
e
F
u
sio
n
Ba
se
d
o
n
S
tatio
n
a
ry
W
a
v
e
let
T
ra
n
s
f
o
rm
a
n
d
Ex
ten
d
e
d
S
p
a
ti
a
l
F
re
q
u
e
n
c
y
M
e
a
su
re
m
e
n
t
,
”
IEE
E
T
r
a
n
sa
c
ti
o
n
o
n
El
e
c
tro
n
ic
Co
mp
u
ter
T
e
c
h
n
o
lo
g
y
,
p
p
.
7
7
-
8
1
,
2
0
0
9
.
[1
1
]
F
.
N.
Ja
m
a
lu
d
d
in
,
e
t
a
l
.
,
“
P
e
rf
o
rm
a
n
c
e
o
f
D
W
T
a
n
d
S
W
T
in
M
u
s
c
le
F
a
ti
g
u
e
De
tec
ti
o
n
,
”
IEE
E
S
t
u
d
e
n
t
S
y
mp
o
si
u
m
in
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
&
S
c
i
e
n
c
e
s
,
S
h
a
h
A
lam
,
p
p
.
5
0
-
5
3
,
2
0
1
5
.
[1
2
]
H.
S
h
i
a
n
d
M
.
F
a
n
g
,
“
M
u
lt
i
-
f
o
c
u
s
Co
lo
r
Im
a
g
e
F
u
sio
n
Ba
se
d
o
n
S
W
T
a
n
d
IHS,
”
Fo
u
rth
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
F
u
zz
y
S
y
ste
ms
a
n
d
Kn
o
wled
g
e
Disc
o
v
e
ry
,
Ha
ik
o
u
,
p
p
.
4
6
1
-
4
6
5
,
2
0
0
7
.
[1
3
]
T
.
L
i
a
n
d
Y.
Wan
g
,
“
Bio
lo
g
ica
l
I
m
a
g
e
F
u
sio
n
Us
in
g
A
S
WT
B
a
se
d
V
a
riab
le
-
W
e
ig
h
ts
S
e
lec
ti
o
n
S
c
h
e
m
e
,
”
3
rd
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
B
io
i
n
fo
rm
a
t
ics
a
n
d
Bi
o
me
d
ica
l
En
g
i
n
e
e
rin
g
,
Be
ij
i
n
g
,
p
p
.
1
-
4
,
2
0
0
9
.
[1
4
]
B
.
T
ian
,
e
t
a
l.
,
“
Re
m
o
te
S
e
n
sin
g
Im
a
g
e
F
u
sio
n
S
c
h
e
m
e
u
sin
g
Dir
e
c
ti
o
n
a
l
V
e
c
to
r
i
n
N
S
CT
Do
m
a
in
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ic
a
ti
o
n
,
C
o
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l
/
issu
e
:
14
(
2
)
,
p
p
.
5
9
8
-
6
0
6
,
2
0
1
6
.
[1
5
]
Yu
h
e
n
d
ra
a
n
d
J
.
T
.
S
.
S
u
m
a
n
ty
o
,
“
A
Qu
a
li
t
y
o
f
I
m
a
g
e
s
F
u
sio
n
f
o
r
Re
m
o
te
S
e
n
sin
g
A
p
p
li
c
a
ti
o
n
,
”
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
t
in
g
,
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l
,
v
o
l
/i
ss
u
e
:
14
(
1
)
,
p
p
.
3
7
8
-
3
8
6
,
2
0
1
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
C
h
a
n
g
e
Dete
ctio
n
fr
o
m
R
emo
t
ely
S
en
s
ed
I
ma
g
es B
a
s
ed
o
n
S
ta
tio
n
a
r
y
W
a
ve
let
Tr
a
n
s
fo
r
m
(
A
b
h
is
h
ek
S
h
a
r
ma
)
3401
[1
6
]
J.
C.
Be
z
d
e
k
,
“
P
a
tt
e
r
n
Re
c
o
g
n
it
i
o
n
w
it
h
F
u
z
z
y
Ob
jec
ti
v
e
F
u
n
c
ti
o
n
,”
Ne
w
Yo
rk
,
P
le
n
u
m
,
1
9
8
1
.
[1
7
]
J.
C.
Du
n
n
,
“
A
F
u
z
z
y
Re
lativ
e
o
f
th
e
IS
OD
ATA
P
ro
c
e
ss
a
n
d
Its
Us
e
in
De
tec
ti
n
g
Co
m
p
a
c
t
W
e
ll
-
S
e
p
a
ra
ted
Clu
ste
rs
,
”
J
o
u
rn
a
l
o
f
Cy
b
e
rn
e
ti
c
s
,
v
o
l.
3
,
p
p
.
3
2
-
5
7
,
1
9
7
3
.
[1
8
]
T
.
Ce
li
k
,
“
Un
su
p
e
rv
ise
d
Ch
a
n
g
e
De
tec
ti
o
n
i
n
S
a
telli
te
Im
a
g
e
s
Us
i
n
g
P
rin
c
i
p
a
l
C
o
m
p
o
n
e
n
t
A
n
a
l
y
si
s
a
n
d
k
M
e
a
n
s
Clu
ste
rin
g
,
”
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te
S
e
n
sin
g
L
e
tt
e
rs
,
v
o
l
/
issu
e
:
6
(
4
)
,
p
p
.
7
7
2
-
7
7
6
,
2
0
0
9
.
[1
9
]
A
.
L
.
d
a
Cu
n
h
a
,
e
t
a
l
.
,
“
T
h
e
No
n
su
b
sa
m
p
led
Co
n
to
u
rlet
T
ra
n
sfo
rm
:
T
h
e
o
ry
,
D
e
sig
n
,
a
n
d
A
p
p
li
c
a
ti
o
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
.
,
v
o
l
/i
ss
u
e
:
15
(
10
)
,
p
p
.
3
0
8
9
–
3
1
0
1
,
2
0
0
6
.
[2
0
]
M
.
G
o
n
g
,
e
t
a
l
.
,
“
A
N
e
ig
h
b
o
u
rh
o
o
d
Ba
se
d
Ra
ti
o
A
p
p
ro
a
c
h
fo
r
Ch
a
n
g
e
De
tec
ti
o
n
in
S
A
R
I
m
a
g
e
s
,
”
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te S
e
n
si
n
g
L
e
tt
e
rs
,
v
o
l
/i
ss
u
e
:
9
(
2
)
,
p
p
.
3
0
7
-
3
1
1
,
2
0
1
2
.
[2
1
]
M
.
N.
S
u
m
a
i
y
a
a
n
d
R.
S
.
S
.
Ku
m
a
ri,
“
L
o
g
a
rit
h
m
ic
M
e
a
n
Ba
s
e
d
T
h
re
sh
o
ld
i
n
g
f
o
r
S
A
R
I
m
a
g
e
Ch
a
n
g
e
D
e
tec
ti
o
n
,
”
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te S
e
n
sin
g
L
e
tt
e
rs
,
v
o
l
/i
ss
u
e
:
13
(
11
)
,
p
p
.
1
7
2
6
-
1
7
2
8
,
2
0
1
6
.
[2
2
]
G
.
H.
Ro
se
n
f
ield
a
n
d
A
.
F.
L
in
s,
“
A
Co
e
ff
icie
n
t
o
f
A
g
r
e
e
m
e
n
t
a
s
a
M
e
a
su
re
o
f
T
h
e
m
a
ti
c
Clas
si
f
ic
a
ti
o
n
A
c
c
u
ra
c
y
,
”
Ph
o
t
o
g
r
a
mm
e
tric E
n
g
i
n
e
e
rin
g
a
n
d
Rem
o
te
S
e
n
sin
g
,
v
o
l
/i
ss
u
e
:
52
(
2
)
,
p
p
.
2
2
3
-
2
2
7
,
1
9
8
6
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
r.
A
b
h
ish
e
k
S
h
a
rm
a
d
id
Ba
c
h
e
lo
rs
o
f
T
e
c
h
n
o
lo
g
y
f
ro
m
Ku
ru
k
sh
e
tra
Un
iv
e
rsity
,
Ku
ru
k
sh
e
tra
in
2
0
0
9
a
n
d
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
f
ro
m
M
a
h
a
rish
i
M
a
rk
a
n
d
e
sh
wa
r
Un
iv
e
rsit
y
in
y
e
a
r
2
0
1
1
.
He
is
c
u
rre
n
tl
y
p
u
rsu
in
g
P
h
.
D.
in
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ic
a
n
d
Co
m
m
u
n
ica
ti
o
n
,
M
a
h
a
rish
i
M
a
rk
a
n
d
e
sh
w
a
r
Un
iv
e
rsit
y
,
M
u
ll
a
n
a
,
Am
b
a
la.
His
m
a
in
re
se
a
r
c
h
w
o
rk
f
o
c
u
se
s
o
n
c
h
a
n
g
e
d
e
tec
ti
o
n
in
re
m
o
tely
s
e
n
se
d
im
a
g
e
s.
He
h
a
s 8
.
5
y
e
a
rs o
f
te
a
c
h
in
g
a
n
d
re
se
a
rc
h
e
x
p
e
rien
c
e
.
Dr.
T
a
ru
n
G
u
lati
d
id
Ba
c
h
e
lo
rs
o
f
T
e
c
h
n
o
lo
g
y
f
ro
m
Ku
ru
k
sh
e
tra
Un
iv
e
rsi
t
y
,
Ku
ru
k
sh
e
tra
a
n
d
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
f
ro
m
N
ITT
T
R,
Ch
a
n
d
ig
a
rh
.
He
d
id
P
h
.
D
f
ro
m
M
.
M
.
Un
iv
e
rsity
a
n
d
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
As
so
c
iate
P
ro
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
E
lec
tro
n
ics
&
Co
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
,
M
.
M
.
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
M
a
h
a
rish
i
M
a
rk
a
n
d
e
sh
w
a
r
Un
iv
e
rsit
y
,
M
u
ll
a
n
a
,
Am
b
a
la,
In
d
ia.
His
a
re
a
o
f
r
e
se
a
rc
h
is
i
m
a
g
e
p
ro
c
e
ss
in
g
a
n
d
h
e
h
a
s
1
4
.
5
y
e
a
rs
o
f
te
a
c
h
in
g
e
x
p
e
rien
c
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.