I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
,
p
p
.
1177
~
1
1
9
0
I
SS
N:
2
5
02
-
4752,
DOI
: 1
0
.
1
1
5
9
1
/i
j
ee
cs.v
2
2
.i
2
.
pp
1
1
7
7
-
1
1
9
0
1177
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
A co
m
pa
ra
tive a
n
a
ly
sis
of i
m
a
g
e co
py
-
m
o
v
e
forg
ery detec
tion
a
lg
o
rith
m
s ba
sed
o
n han
d and
m
a
c
hine
-
craf
ted
featu
res
I
s
m
a
il
T
a
ha
Ah
m
e
d
1
,
B
a
ra
a
T
a
re
q H
a
mm
a
d
2
,
No
rz
ia
na
J
a
m
il
3
1
,2
Co
ll
e
g
e
o
f
Co
m
p
u
ter S
c
ien
c
e
s an
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
Un
iv
e
rsit
y
o
f
A
n
b
a
r,
A
n
b
a
r,
Ira
q
3
Co
ll
e
g
e
o
f
Co
m
p
u
ti
n
g
a
n
d
I
n
f
o
rm
a
ti
c
s,
Un
iv
e
rsiti
T
e
n
a
g
a
Na
sio
n
a
l,
M
a
lay
si
a
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
9
,
2
0
2
1
R
ev
i
s
ed
Mar
22
,
2
0
2
1
A
cc
ep
ted
A
p
r
11
,
2
0
2
1
Dig
it
a
l
i
m
a
g
e
f
o
rg
e
r
y
(DIF)
i
s
th
e
a
c
t
o
f
d
e
li
b
e
ra
te
a
lt
e
r
a
ti
o
n
o
f
a
n
im
a
g
e
to
c
h
a
n
g
e
th
e
d
e
tails
tran
sm
it
ted
b
y
it
.
T
h
e
m
a
n
ip
u
latio
n
m
a
y
e
it
h
e
r
a
d
d
,
d
e
lete
o
r
a
lt
e
r
a
n
y
o
f
th
e
i
m
a
g
e
f
e
a
tu
re
s
o
r
c
o
n
ten
ts,
w
it
h
o
u
t
lea
v
in
g
a
n
y
h
in
t
o
f
th
e
c
h
a
n
g
e
in
d
u
c
e
d
.
I
n
g
e
n
e
ra
l
,
c
o
p
y
-
m
o
v
e
f
o
rg
e
r
y
,
a
lso
re
fe
r
re
d
to
a
s
re
p
li
c
a
ti
o
n
,
is
th
e
m
o
st
c
o
m
m
o
n
o
f
th
e
v
a
rio
u
s
k
in
d
s
o
f
p
a
s
siv
e
i
m
a
g
e
f
o
rg
e
r
y
tec
h
n
iq
u
e
s.
In
th
e
c
o
p
y
-
m
o
v
e
f
o
rg
e
r
y
,
th
e
b
a
sic
p
ro
c
e
ss
is
c
o
p
y
/p
a
ste
f
ro
m
o
n
e
a
re
a
to
a
n
o
th
e
r
i
n
t
h
e
sa
m
e
i
m
a
g
e
.
Ov
e
r
th
e
p
a
st
f
e
w
d
e
c
a
d
e
s
v
a
rio
u
s
im
a
g
e
c
o
p
y
-
m
o
v
e
f
o
rg
e
r
y
d
e
tec
ti
o
n
(IC
-
M
F
Ds
)
su
rv
e
y
s
h
a
v
e
b
e
e
n
e
x
isted
.
Ho
w
e
v
e
r,
th
e
se
su
rv
e
y
s a
re
n
o
t
c
o
v
e
re
d
f
o
r
b
o
th
IC
-
M
F
D alg
o
rit
h
m
s
b
a
se
d
h
a
n
d
-
c
ra
f
ted
f
e
a
tu
re
s
a
n
d
IC
-
M
F
Ds
a
lg
o
rit
h
m
s
b
a
se
d
m
a
c
h
i
n
e
-
c
ra
f
ted
f
e
a
tu
re
s.
T
h
e
re
f
o
re
,
T
h
e
p
a
p
e
r
p
re
se
n
ted
a
c
o
m
p
a
ra
ti
v
e
a
n
a
l
y
sis
o
f
IC
-
M
F
Ds
b
y
c
o
ll
e
c
t
v
a
rio
u
s
ty
p
e
s
o
f
IC
-
M
F
Ds
a
n
d
g
ro
u
p
th
e
m
re
l
y
o
n
th
e
ir
f
e
a
tu
re
s
u
se
d
.
T
w
o
g
ro
u
p
s,
i.
e
.
IC
-
M
F
Ds
b
a
se
d
h
a
n
d
-
c
ra
f
ted
f
e
a
tu
re
s
a
n
d
IC
-
M
F
Ds
b
a
se
d
m
a
c
h
in
e
-
c
ra
f
ted
f
e
a
tu
re
s
.
IC
-
MF
D
a
lg
o
rit
h
m
s
b
a
se
d
h
a
n
d
-
c
ra
f
ted
f
e
a
tu
re
s
a
r
e
th
e
a
lg
o
rit
h
m
s
th
a
t
d
e
tec
t
th
e
f
a
k
e
d
im
a
g
e
d
e
p
e
n
d
in
g
o
n
m
a
n
u
a
l
f
e
a
tu
re
e
x
tr
a
c
ti
o
n
w
h
il
e
IC
-
M
F
D
a
lg
o
rit
h
m
s
b
a
se
d
m
a
c
h
in
e
-
c
ra
f
te
d
f
e
a
tu
re
s
a
re
th
e
a
lg
o
rit
h
m
s
th
a
t
d
e
tec
t
th
e
f
a
k
e
d
i
m
a
g
e
a
u
to
m
a
ti
c
a
ll
y
f
ro
m
ima
g
e
.
O
u
r
h
o
p
e
th
a
t
t
h
is
p
re
se
n
ted
a
n
a
ly
sis
w
il
l
to
k
e
e
p
u
p
-
to
-
d
a
te t
h
e
re
se
a
rc
h
e
rs i
n
th
e
f
ield
o
f
IC
-
MFD
.
K
ey
w
o
r
d
s
:
Dee
p
lean
in
g
m
eth
o
d
s
Dig
ital I
m
a
g
e
f
o
r
g
er
y
Han
d
-
cr
a
f
ted
f
ea
t
u
r
es
I
m
ag
e
co
p
y
-
m
o
v
e
f
o
r
g
er
y
d
etec
tio
n
alg
o
r
ith
m
s
Ma
ch
i
n
e
-
cr
a
f
ted
f
ea
t
u
r
es
T
h
is
is
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
I
s
m
ail
T
ah
a
A
h
m
ed
C
o
lleg
e
o
f
C
o
m
p
u
ter
Scie
n
ce
s
an
d
I
n
f
o
r
m
a
tio
n
T
ec
h
n
o
lo
g
y
Un
i
v
er
s
it
y
o
f
An
b
ar
,
An
b
ar
,
I
r
aq
An
b
ar
,
I
r
aq
E
m
ail: i
s
m
a
il.tah
a
@
u
o
an
b
ar
.
ed
u
.
iq
1.
I
NT
RO
D
UCT
I
O
N
I
m
ag
e
s
p
la
y
a
n
i
m
p
o
r
tan
t
r
o
le
as
e
f
f
ec
ti
v
e
ca
r
r
ier
s
o
f
in
f
o
r
m
at
io
n
in
tech
n
o
lo
g
y
.
T
h
r
o
u
g
h
u
s
in
g
v
ar
io
u
s
ad
v
a
n
ce
d
i
m
ag
i
n
g
d
ev
ices
li
k
e
s
m
ar
tp
h
o
n
es,
h
u
g
e
a
m
o
u
n
t
o
f
h
i
g
h
-
r
eso
l
u
tio
n
d
ig
it
al
i
m
a
g
e
s
ar
e
ta
k
e
n
an
d
ex
c
h
a
n
g
ed
t
h
r
o
u
g
h
p
eo
p
le
d
ail
y
.
T
h
e
i
m
ag
e
s
ar
e
i
n
f
lu
e
n
ce
d
b
y
v
ar
io
u
s
k
i
n
d
s
o
f
m
a
n
ip
u
latio
n
s
t
h
at
m
a
y
n
o
t
b
e
ea
s
il
y
id
en
ti
f
ied
.
T
h
e
m
an
ip
u
latio
n
m
a
y
eit
h
er
ad
d
,
d
elete
o
r
alter
an
y
o
f
th
e
p
r
o
p
er
ties
o
f
th
e
i
m
ag
e,
w
it
h
o
u
t o
f
f
er
in
g
an
y
h
in
t a
s
to
th
e
u
p
d
ate.
T
h
e
o
r
ig
in
al
an
d
f
o
r
g
er
y
i
m
a
g
e
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
Me
th
o
d
s
f
o
r
t
h
e
d
etec
tio
n
o
f
f
o
r
g
er
y
i
m
a
g
es
ar
e
clas
s
if
ied
i
n
to
t
w
o
g
r
o
u
p
s
,
ac
tiv
e
an
d
p
ass
i
v
e.
T
h
e
ac
tiv
e
m
e
th
o
d
s
ar
e
clo
s
el
y
ass
o
ciate
d
w
it
h
in
f
o
r
m
at
io
n
th
at
b
elo
n
g
s
to
th
e
o
r
ig
i
n
al
i
m
a
g
e
s
u
ch
a
s
w
ater
m
ar
k
i
n
g
o
r
s
teg
an
o
g
r
ap
h
ic
d
ata.
Ho
w
ev
er
,
th
e
ab
s
en
ce
o
f
th
is
in
f
o
r
m
at
io
n
ca
n
li
m
it
ac
ti
v
e
m
et
h
o
d
s
ap
p
licatio
n
s
.
T
h
er
ef
o
r
e,
to
ass
es
s
it
s
au
t
h
e
n
ticit
y
,
p
as
s
iv
e
m
et
h
o
d
s
m
a
y
n
o
t
d
ep
en
d
o
n
p
r
ev
io
u
s
d
etails
co
n
ce
r
n
i
n
g
t
h
e
o
r
ig
i
n
al
i
m
ag
e.
P
ass
iv
e
i
m
a
g
e
f
o
r
g
er
y
d
etec
ti
o
n
ca
n
b
e
n
ar
r
o
w
l
y
d
iv
id
ed
i
n
to
a
f
e
w
ca
teg
o
r
ies
s
u
ch
a
s
c
o
p
y
-
m
o
v
e,
r
esa
m
p
li
n
g
,
an
d
ca
m
er
a
s
o
u
r
c
e
id
en
ti
f
icatio
n
.
A
co
p
y
-
m
o
v
e
f
o
r
g
er
y
i
s
o
n
e
o
f
t
h
e
e
s
s
e
n
ti
al
w
a
y
s
o
f
p
as
s
i
v
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
:
1
1
7
7
-
1
1
9
0
1178
f
o
r
g
er
y
d
etec
tio
n
w
h
er
e
it
h
a
s
b
ee
n
co
p
ied
an
d
p
asted
in
to
t
h
e
s
a
m
e
i
m
ag
e
in
o
n
e
o
r
m
o
r
e
r
eg
io
n
s
.
C
o
p
y
-
m
o
v
e
f
o
r
g
er
y
is
ea
s
il
y
ca
n
b
e
ex
ec
u
ted
a
n
d
r
ea
s
o
n
ab
l
y
s
u
c
ce
s
s
f
u
l
in
m
a
n
ip
u
la
tin
g
i
m
a
g
es,
esp
ec
iall
y
w
h
e
n
th
e
p
r
o
p
er
ties
o
f
t
h
e
s
o
u
r
ce
a
n
d
tar
g
et
r
e
g
io
n
s
ar
e
o
f
t
h
e
s
a
m
e
i
m
a
g
e
ar
e
n
o
r
m
all
y
w
el
l
-
m
atc
h
ed
b
et
w
ee
n
t
h
e
r
eg
io
n
an
d
t
h
e
i
m
ag
e
b
ei
n
g
m
an
ip
u
lated
.
Fi
g
u
r
e
2
s
h
o
w
s
t
h
e
o
r
ig
in
al
a
n
d
co
p
y
-
m
o
v
e
i
m
ag
e
f
o
r
g
er
y
.
(
a)
(
b
)
Fig
u
r
e
1
.
(
a)
Or
ig
in
al
i
m
ag
e,
(
b
)
f
o
r
g
er
y
i
m
a
g
e
(
a)
(
b
)
Fig
u
r
e
2
.
(
a)
Or
ig
in
al
i
m
ag
e,
(
b
)
co
p
y
-
m
o
v
e
i
m
a
g
e
f
o
r
g
er
y
[
1
]
T
h
er
e
ar
e
s
o
m
e
liter
atu
r
e
s
u
r
v
e
y
s
ab
o
u
t
I
C
-
M
FDs
.
I
n
[
2
]
,
A
s
u
r
v
e
y
w
a
s
p
r
esen
ted
o
n
r
ec
en
t
d
ev
elo
p
m
en
t
s
i
n
C
MFD
a
n
d
e
x
p
lain
s
t
h
e
w
h
o
le
p
r
o
ce
s
s
i
n
v
o
lv
ed
in
C
MF
D.
I
n
[
3
]
,
a
b
r
ief
r
ev
ie
w
o
n
p
as
s
i
v
e
d
ig
ital
i
m
a
g
e
f
o
r
en
s
ic
ap
p
r
o
ac
h
es
i
s
d
is
c
u
s
s
ed
.
Var
io
u
s
t
y
p
es
o
f
tr
ac
es
f
o
r
p
ass
iv
e
d
i
g
it
al
i
m
a
g
e
f
o
r
e
n
s
ic
s
:
tr
ac
es
lef
t
in
i
m
a
g
e
ac
q
u
is
i
ti
o
n
,
tr
ac
es
lef
t
in
i
m
a
g
e
s
to
r
ag
e,
an
d
tr
ac
es
lef
t
i
n
i
m
a
g
e
ed
itin
g
.
I
n
[
4
]
,
a
liter
atu
r
e
r
ev
ie
w
o
f
d
ig
ital
i
m
ag
e
f
o
r
en
s
ic
s
,
co
v
er
in
g
ac
tiv
e
an
d
p
ass
i
v
e
m
et
h
o
d
s
as
w
ell
as
r
elev
a
n
t
d
is
cu
s
s
io
n
s
r
eg
ar
d
in
g
d
ee
p
lea
r
n
in
g
.
I
n
[
5
]
,
th
e
s
u
r
v
e
y
co
v
er
s
d
if
f
er
e
n
t
f
o
r
g
er
y
d
etec
t
io
n
te
ch
n
iq
u
es,
d
if
f
er
en
t
t
y
p
es
o
f
f
ea
tu
r
e
-
m
atc
h
in
g
m
et
h
o
d
s
.
I
n
[
6
]
,
a
s
u
r
v
e
y
w
as
p
r
esen
ted
a
s
tate
o
f
t
h
e
ar
t
o
n
k
e
y
p
o
i
n
t
b
ased
co
p
y
-
m
o
v
e
f
o
r
g
er
y
d
etec
tio
n
.
I
n
[
7
]
,
a
s
u
r
v
e
y
w
a
s
p
r
esen
ted
o
n
th
e
in
n
o
v
ati
v
e
ex
p
er
i
m
e
n
ts
i
n
th
e
f
o
r
g
er
y
r
ec
o
g
n
itio
n
tactic
s
b
u
ilt
o
n
t
h
e
lik
e
n
es
s
a
n
d
co
n
n
ec
tio
n
b
et
w
ee
n
t
h
e
p
a
s
ted
p
ar
t
an
d
th
e
r
ea
l
i
m
a
g
e
an
d
t
h
eir
co
m
p
ar
ati
v
e
s
tu
d
y
.
I
n
[
8
]
,
a
s
u
r
v
e
y
w
a
s
p
r
esen
te
d
o
n
v
ar
io
u
s
k
i
n
d
s
o
f
d
i
g
ital
i
m
a
g
e
f
o
r
g
er
ies
d
etec
tio
n
m
et
h
o
d
s
,
t
h
is
s
u
r
v
e
y
f
o
cu
s
i
n
g
o
n
t
h
e
c
u
r
r
en
t
m
eth
o
d
s
f
o
r
f
o
r
g
ed
i
m
a
g
e.
I
n
[
9
]
,
s
h
o
r
t
r
ev
ie
w
o
f
C
M
FD
d
em
o
n
s
tr
ate
th
at
th
e
w
o
r
k
i
s
s
till
s
ta
te
o
f
ar
t
a
n
d
t
h
er
e
is
p
le
n
t
y
o
f
r
o
o
m
f
o
r
f
u
t
u
r
e
s
t
u
d
y
.
I
n
[
1
0
]
,
a
s
tate
-
of
-
th
e
-
ar
t
r
ev
ie
w
a
n
d
an
a
l
y
s
is
o
f
r
ec
en
t
C
MFD
tech
n
iq
u
es
ar
e
p
r
esen
ted
.
I
n
[
1
1
]
,
a
s
u
r
v
e
y
o
f
f
er
s
a
n
o
v
er
v
ie
w
o
f
co
m
m
o
n
f
o
r
m
s
o
f
i
m
ag
e
ta
m
p
er
in
g
,
p
u
b
li
s
h
ed
d
atasets
o
f
i
m
a
g
e
ta
m
p
er
in
g
a
n
d
r
ec
en
t
a
p
p
r
o
ac
h
es
to
d
etec
t
ta
m
p
er
in
g
.
I
n
[
1
2
]
,
A
r
esear
ch
o
n
r
ec
en
t
d
e
v
elo
p
m
e
n
ts
i
n
C
MFD
m
et
h
o
d
s
w
as
p
r
esen
te
d
to
id
en
tify
f
ac
to
r
s
th
at
h
i
n
d
er
th
e
d
etec
tio
n
o
f
f
o
r
g
er
y
an
d
ev
al
u
ate
th
e
ac
cu
r
a
c
y
o
f
v
ar
io
u
s
m
et
h
o
d
s
p
r
o
p
o
s
ed
.
Ho
w
e
v
er
,
th
e
y
d
id
n
o
t
p
r
o
v
id
es
an
ex
te
n
s
i
v
e
r
ev
ie
w
o
f
m
aj
o
r
I
C
-
MFD
alg
o
r
ith
m
s
d
ev
elo
p
ed
f
o
r
(
1
)
h
an
d
-
cr
af
ted
f
ea
t
u
r
es
,
(
2
)
m
ac
h
i
n
e
-
cr
af
ted
f
ea
t
u
r
es.
So
t
h
e
y
d
id
n
o
t
co
v
er
b
o
t
h
o
f
t
h
e
m
.
T
h
er
ef
o
r
e,
th
e
p
ap
er
p
r
esen
ted
a
co
m
p
r
e
h
en
s
iv
e
r
e
v
ie
w
o
f
I
C
-
MFD
alg
o
r
it
h
m
s
b
y
co
llect
v
ar
io
u
s
t
y
p
es
o
f
I
C
-
MFD
al
g
o
r
ith
m
s
a
n
d
g
r
o
u
p
th
e
m
ac
co
r
d
in
g
to
th
e
ir
f
ea
t
u
r
es
u
s
ed
.
T
w
o
g
r
o
u
p
s
,
i.e
.
I
C
-
MFD
al
g
o
r
ith
m
s
b
a
s
ed
h
a
n
d
-
cr
af
ted
f
ea
t
u
r
es
a
n
d
IC
-
M
FD
alg
o
r
it
h
m
s
b
ased
m
a
ch
in
e
-
c
r
a
f
ted
f
ea
t
u
r
es.
I
C
-
MF
D
alg
o
r
ith
m
s
b
ased
h
a
n
d
-
cr
a
f
t
ed
f
ea
tu
r
es
ar
e
th
e
alg
o
r
ith
m
s
th
a
t
d
etec
t
t
h
e
f
a
k
ed
i
m
ag
e
d
ep
en
d
in
g
o
n
m
a
n
u
al
f
ea
tu
r
e
e
x
tr
ac
tio
n
w
h
ile
I
C
-
M
FD
al
g
o
r
ith
m
s
b
ased
m
ac
h
i
n
e
-
cr
af
ted
f
ea
t
u
r
e
s
ar
e
th
e
al
g
o
r
it
h
m
s
t
h
at
d
etec
t
th
e
f
a
k
ed
i
m
a
g
e
a
u
to
m
at
icall
y
f
r
o
m
i
m
ag
e.
Ou
r
h
o
p
e
th
at
t
h
is
p
r
ese
n
ted
s
u
r
v
e
y
w
ill
to
k
ee
p
u
p
-
to
-
d
ate
t
h
e
r
esear
ch
er
s
i
n
t
h
e
f
ie
ld
o
f
I
C
-
MFD.
T
h
e
r
e
m
ain
d
er
o
f
t
h
is
p
ap
er
is
f
o
r
m
u
lated
a
s
f
o
llo
w
s
.
I
n
Sectio
n
2
,
clas
s
if
y
th
e
cu
r
r
e
n
t
I
C
-
M
FD
Alg
o
r
it
h
m
s
an
d
g
r
o
u
p
t
h
e
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
co
mp
a
r
a
tive
a
n
a
lysi
s
o
f ima
g
e
co
p
y
-
m
o
ve
fo
r
g
ery
d
etec
tio
n
a
lg
o
r
ith
ms …
(
I
s
ma
il Ta
h
a
A
h
med
)
1179
ac
co
r
d
in
g
to
th
eir
f
ea
t
u
r
es
u
s
e
d
.
I
n
Sectio
n
3
,
I
C
-
MFD
Alg
o
r
ith
m
s
b
ased
h
an
d
-
cr
af
ted
f
ea
t
u
r
es
ar
e
p
r
esen
ted
.
I
n
Sectio
n
4
,
I
C
-
M
FD
A
l
g
o
r
ith
m
s
B
ased
Ma
c
h
i
n
e
-
C
r
a
f
te
d
Featu
r
es
ar
e
p
r
ese
n
ted
.
Fin
all
y
,
i
n
S
ec
tio
n
5
,
co
n
clu
s
io
n
s
ca
n
b
e
d
r
a
w
n
.
2.
E
XI
ST
I
N
G
I
C
-
M
F
D
AL
G
O
RIT
H
M
S (
I
C
-
M
F
Ds)
Ma
n
y
I
C
-
MFD
tec
h
n
iq
u
es
ar
e
b
ased
o
n
d
if
f
er
e
n
t
t
y
p
e
s
o
f
f
ea
t
u
r
es
w
h
ich
ar
e
a
v
ailab
le
i
n
d
if
f
er
en
t
d
o
m
ai
n
s
.
Su
c
h
a
s
m
an
y
f
ea
t
u
r
es
th
a
t
ca
n
b
e
ex
tr
ac
ted
i
n
t
h
e
s
p
atial
o
r
tr
an
s
f
o
r
m
d
o
m
ai
n
.
Gen
er
all
y
s
p
ea
k
in
g
,
th
e
ch
ar
ac
ter
is
t
ics
ex
tr
ac
ted
in
th
e
s
p
atial
d
o
m
ai
n
ar
e
r
elativ
el
y
lo
w
i
n
co
m
p
lex
i
t
y
,
w
h
er
ea
s
th
o
s
e
ex
tr
ac
ted
in
th
e
tr
an
s
f
o
r
m
d
o
m
ain
b
etter
r
ep
r
esen
t
th
e
m
u
l
tis
ca
le
a
n
d
m
u
lti
o
r
ien
tatio
n
ch
ar
ac
ter
is
ti
cs
o
f
HVS;
a
f
air
co
m
b
i
n
atio
n
o
f
d
if
f
er
e
n
t
f
ea
t
u
r
es
w
ill
e
f
f
ec
ti
v
el
y
i
m
p
r
o
v
e
ef
f
icien
c
y
.
C
o
p
y
-
m
o
v
e
i
s
t
h
e
m
o
s
t
w
id
el
y
u
s
ed
i
m
a
g
e
ta
m
p
er
in
g
tech
n
iq
u
e
t
h
at
at
te
m
p
t
s
to
k
ee
p
h
id
in
g
o
r
m
o
d
if
y
t
h
e
i
m
ag
e
co
n
te
n
t.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
g
en
er
al
tax
o
n
o
m
y
o
f
i
m
a
g
e
f
o
r
g
er
y
d
etec
tio
n
tec
h
n
iq
u
es.
M
o
s
t
c
o
n
v
en
t
io
n
al
I
C
-
MFDs
d
ep
en
d
o
n
f
o
u
r
s
tag
e
s
s
u
c
h
as: p
r
e
-
p
r
o
ce
s
s
i
n
g
(
o
p
tio
n
al)
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
m
atc
h
in
g
a
n
d
v
i
s
u
a
lizatio
n
(
o
p
tio
n
al
)
.
Her
e,
co
llect
v
ar
io
u
s
t
y
p
e
s
o
f
I
C
-
M
FDs
al
g
o
r
ith
m
s
a
n
d
g
r
o
u
p
th
e
m
ac
co
r
d
in
g
to
th
eir
f
ea
t
u
r
es
u
s
ed
.
T
w
o
g
r
o
u
p
s
,
i.e
.
I
C
-
M
FDs
al
g
o
r
ith
m
s
b
ased
h
an
d
-
cr
af
ted
f
ea
tu
r
es
a
n
d
I
C
-
M
FDs
al
g
o
r
ith
m
s
b
ased
n
on
-
h
a
n
d
c
r
af
ted
f
ea
t
u
r
es.
Mo
s
t
C
o
n
v
en
tio
n
al
I
C
-
MFD
s
alg
o
r
it
h
m
s
r
el
y
o
n
th
e
e
x
tr
ac
tio
n
o
f
ce
r
tain
f
ea
tu
r
es
to
d
if
f
er
e
n
tiate
th
e
o
r
i
g
in
a
l
i
m
ag
e
f
r
o
m
t
h
e
f
a
k
e
o
n
e.
W
h
ile
I
C
-
M
FDs
b
ased
d
ee
p
lear
n
in
g
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
m
atc
h
i
n
g
i
n
te
g
r
ated
in
to
o
n
e
o
p
ti
m
izatio
n
s
tep
as s
h
o
w
n
in
Fi
g
u
r
e
4
.
Fig
u
r
e
3
.
I
m
a
g
e
f
o
r
g
er
y
d
etec
t
io
n
tech
n
iq
u
e
s
tax
o
n
o
m
y
Fig
u
r
e
4
.
Gen
er
al
ar
ch
itect
u
r
e
o
f
i
m
a
g
e
f
o
r
g
er
y
d
etec
tio
n
tec
h
n
iq
u
es
2
.
1
.
E
x
is
t
ing
pu
bli
c
ly
da
t
a
ba
s
es
I
n
o
r
d
er
to
v
alid
ate
t
h
e
r
es
u
lts
o
f
d
i
f
f
er
en
t
i
m
a
g
e
C
M
FD
al
g
o
r
ith
m
s
,
d
i
f
f
er
en
t
p
u
b
lic
i
m
a
g
e
d
atab
ases
ar
e
u
s
ed
to
test
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
e
al
g
o
r
ith
m
s
.
T
ab
le
1
p
r
o
v
id
es
in
f
o
r
m
at
io
n
o
n
t
h
e
s
e
d
atab
ases
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
:
1
1
7
7
-
1
1
9
0
1180
T
ab
le
1
.
E
x
is
tin
g
p
u
b
licall
y
a
v
a
ilab
le
i
m
ag
e
co
p
y
-
m
o
v
e
f
o
r
g
er
y
d
ataset
s
D
a
t
a
s
e
t
Y
e
a
r
To
t
a
l
I
mag
e
s
N
o
A
u
t
h
e
n
t
i
c
I
mag
e
s
N
o
.
Ta
mp
e
r
e
d
I
mag
e
s
N
o
.
P
o
st
-
P
r
o
c
e
ss
i
n
g
O
p
e
r
a
t
i
o
n
s
I
mag
e
F
o
r
mat
R
e
s
o
l
u
t
i
o
n
M
I
C
C
-
F
2
2
0
[
1
3
]
2
0
1
1
2
2
0
1
1
0
1
1
0
No
JP
EG
7
2
2
×
4
8
0
t
o
8
0
0
×
6
0
0
I
M
D
[
1
4
]
2
0
1
2
-
48
87
4
JP
EG
1
6
3
2
x
1
2
2
4
M
I
C
C
-
F
6
0
0
[
1
5
]
2
0
1
3
6
0
0
4
4
0
1
6
0
y
e
s
JP
EG
/
P
N
G
8
0
0
×
5
3
2
t
o
3
8
8
8
×
2
5
9
2
C
o
M
o
F
o
D
[
1
6
]
2
0
1
3
-
5
2
0
0
5
2
0
0
6
JP
EG
/
P
N
G
5
1
2
x
5
1
2
C
A
S
I
A
v
1
.
0
[
1
7
]
2
0
1
3
1
7
2
1
8
0
0
9
2
1
No
JP
EG
3
8
4
×
2
5
6
C
A
S
I
A
v
2
.
0
[
1
7
]
2
0
1
3
1
2
6
1
4
7
4
9
1
5
1
2
3
y
e
s
JP
EG
/
TI
F
F
2
4
0
×
1
6
0
-
9
0
0
×
600
M
I
C
C
-
F
2
0
0
0
[
1
8
]
2
0
1
4
2
0
0
0
1
3
0
0
7
0
0
No
JP
EG
2
0
4
8
x
1
5
3
6
G
R
I
P
[
1
9
]
2
0
1
5
80
80
-
6
-
7
6
8
×
1
0
2
4
C
O
V
ER
A
G
E
[
2
0
]
2
0
1
6
-
1
0
0
-
No
TI
F
F
V
a
r
i
o
u
s
2
.
2
.
P
er
f
o
rm
a
nce
ev
a
lua
t
io
n
C
MFD
ev
al
u
atio
n
at
i
m
ag
e
le
v
el
i
s
p
er
f
o
r
m
ed
af
ter
th
e
i
m
a
g
es
o
f
t
h
e
d
ata
s
ets
ar
e
clas
s
i
f
i
ed
in
to
t
w
o
g
r
o
u
p
s
:
f
a
k
ed
a
n
d
o
r
ig
i
n
al.
T
h
er
e
is
t
w
o
m
etr
ic
s
:
tr
u
e
p
o
s
itiv
e
r
ate
(
T
P
R
)
an
d
f
al
s
e
p
o
s
i
tiv
e
r
ate
(
FP
R
)
ar
e
u
s
ed
to
ev
alu
ate
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
d
if
f
er
en
t
C
M
FD
m
e
th
o
d
.
T
y
p
icall
y
t
h
ese
m
etr
ics
ar
e
u
s
ed
to
m
ea
s
u
r
e
th
e
ac
cu
r
ac
y
.
A
s
u
cc
es
s
f
u
l
d
etec
t
io
n
m
et
h
o
d
m
u
s
t
estab
li
s
h
a
h
ig
h
T
P
R
w
h
ile
a
m
i
n
i
m
u
m
FP
R
le
v
el
s
h
o
u
ld
r
e
m
ain
.
B
o
th
t
h
e
T
P
R
an
d
F
PR
eq
u
atio
n
s
ar
e
d
escr
ib
ed
in
(
2
)
an
d
(
3
)
.
(
)
(
)
(
1
)
(
)
(
2
)
(
)
(
3
)
W
h
er
e
th
e
n
u
m
b
er
o
f
f
o
r
g
ed
i
m
ag
e
s
id
e
n
ti
f
ied
as
f
o
r
g
ed
is
t
r
u
e
p
o
s
itiv
e
(
T
P)
;
th
e
n
u
m
b
er
o
f
f
o
r
g
ed
i
m
a
g
es id
en
tifie
d
as a
u
t
h
e
n
tic
is
f
al
s
e
n
e
g
ati
v
e
(
FN)
; t
h
e
n
u
m
b
er
o
f
au
t
h
e
n
tic
i
m
ag
e
s
id
en
tif
ied
as a
u
t
h
en
t
ic
is
tr
u
e
n
eg
at
iv
e
(
T
N)
;
an
d
th
e
n
u
m
b
er
o
f
a
u
t
h
en
t
ic
i
m
a
g
es
id
en
ti
f
ied
as
f
o
r
g
ed
o
n
es
is
f
alse
p
o
s
itiv
e
(
FP
)
.
T
P
R
is
th
e
n
u
m
b
er
o
f
m
an
ip
u
late
d
im
a
g
es
co
r
r
ec
tl
y
d
etec
ted
,
an
d
FP
R
r
ef
er
s
to
th
e
p
er
ce
n
tag
e
o
f
th
e
o
r
ig
i
n
al
i
m
a
g
es t
h
at
ar
e
w
r
o
n
g
l
y
r
ep
o
r
ted
as
m
an
ip
u
lated
.
3.
IC
-
M
F
D
AL
G
O
RI
T
H
M
S B
ASE
D
H
AN
D
-
CRAF
T
E
D
F
E
AT
URE
S
T
h
e
I
C
-
MFD
ap
p
r
o
ac
h
is
ap
p
lied
to
d
etec
t
th
e
f
o
r
g
er
y
i
m
a
g
e
r
el
y
o
n
t
h
e
ex
tr
ac
ted
f
ea
tu
r
es
w
h
ic
h
ar
e
r
elate
d
to
f
o
r
g
er
y
d
etec
ti
o
n
.
Fo
r
an
i
m
a
g
e,
it
is
p
o
s
s
i
b
le
to
ca
p
tu
r
e
t
h
e
f
ea
t
u
r
es
eit
h
er
g
lo
b
all
y
f
o
r
t
h
e
en
tire
i
m
a
g
e
o
r
lo
ca
ll
y
f
o
r
r
eg
io
n
s
o
r
o
b
j
ec
ts
.
Selecti
n
g
g
o
o
d
f
ea
t
u
r
es
ca
n
h
av
e
a
p
o
w
er
f
u
l
i
m
p
ac
t
o
n
f
o
r
g
er
y
i
m
a
g
e
d
etec
tio
n
.
C
MFD
m
et
h
o
d
s
ca
n
b
e
clas
s
if
ied
i
n
to
t
h
r
ee
g
r
o
u
p
s
i
n
t
er
m
s
o
f
i
m
a
g
e
d
iv
id
in
g
:
b
lo
ck
-
b
a
s
ed
ap
p
r
o
ac
h
es
[
2
1
]
,
s
eg
m
e
n
ted
r
eg
io
n
-
b
ased
ap
p
r
o
ac
h
es
[
2
2
]
,
an
d
lo
ca
l
k
e
y
p
o
in
t
-
b
ased
ap
p
r
o
ac
h
es
[
2
3
]
.
I
n
th
e
b
lo
ck
-
b
ased
i
m
ag
e
is
s
p
lit
i
n
t
o
a
v
ar
iet
y
o
f
s
u
b
-
b
lo
c
k
s
t
h
at
ar
e
o
v
er
lap
p
in
g
o
r
n
o
n
-
o
v
er
l
ap
p
in
g
b
lo
ck
i
n
g
as
s
h
o
w
n
i
n
f
i
g
u
r
e
5
.
Fig
u
r
e
5
s
h
o
w
s
t
h
at
(
m
y
lo
v
e
i
m
a
g
e)
d
iv
i
d
ed
in
to
a
v
ar
iety
o
f
n
o
n
-
o
v
er
lap
p
in
g
s
u
b
-
b
lo
ck
s
.
C
o
m
p
ar
ed
to
an
ex
h
au
s
ti
v
e
s
ea
r
ch
,
th
e
b
lo
ck
d
iv
is
io
n
w
ill
m
i
n
i
m
ize
th
e
p
r
o
ce
s
s
i
n
g
ti
m
e
o
f
th
e
m
atc
h
in
g
p
r
o
ce
s
s
to
f
in
d
a
s
i
m
ilar
f
ea
t
u
r
e
v
ec
to
r
in
a
n
i
m
a
g
e.
Si
m
il
ar
l
y
,
th
e
s
e
g
m
en
ted
-
b
ased
ap
p
r
o
ac
h
atte
m
p
ts
to
s
eg
m
e
n
t
th
e
i
m
a
g
e
i
n
to
v
ar
io
u
s
ar
ea
s
th
at
co
m
p
le
tel
y
co
v
er
ed
th
e
f
o
r
g
ed
o
b
j
ec
ts
in
th
e
i
m
a
g
e.
I
n
co
n
tr
ast,
t
h
e
k
e
y
p
o
in
t
b
ased
ap
p
r
o
ac
h
d
ete
cts
u
n
iq
u
e
lo
ca
l
c
h
ar
ac
ter
is
tic
s
in
cl
u
d
in
g
co
r
n
er
s
,
b
lo
b
s
,
an
d
ed
g
e
in
th
e
i
m
a
g
e
(
w
it
h
o
u
t
an
y
t
y
p
e
o
f
s
e
g
m
e
n
t
atio
n
)
.
T
h
e
co
m
m
o
n
t
y
p
es
i
n
th
e
k
e
y
p
o
i
n
t
b
ased
ap
p
r
o
ac
h
ar
e
s
ca
le
i
n
v
ar
ia
n
t
f
ea
t
u
r
e
tr
an
s
f
o
r
m
(
SIFT
)
[
2
4
]
an
d
s
p
ee
d
ed
u
p
r
o
b
u
s
t f
ea
tu
r
e
s
(
SUR
F
)
[
2
5
]
.
Han
d
-
cr
a
f
ted
f
ea
tu
r
e
s
is
d
esig
n
ed
m
a
n
u
all
y
b
y
h
u
m
an
s
u
ch
as
n
at
u
r
al
s
ce
n
e
s
tati
s
tic
s
(
NS
S),
i
m
a
g
e
g
r
ad
ien
ts
,
i
m
a
g
e
h
is
to
g
r
a
m
,
i
m
ag
e
e
n
tr
o
p
ies
an
d
i
m
a
g
e
f
ilt
er
r
esp
o
n
s
es.
C
M
FD
m
e
th
o
d
s
ar
e
ca
teg
o
r
ize
in
to
t
w
o
g
r
o
u
p
s
,
r
el
y
o
n
t
h
e
t
y
p
e
o
f
f
ea
t
u
r
es:
s
p
atial
d
o
m
ain
a
n
d
f
r
eq
u
en
c
y
d
o
m
ai
n
m
et
h
o
d
s
.
T
h
e
p
r
ev
io
u
s
I
C
-
MFDs a
r
e
class
if
ied
d
ep
en
d
in
g
o
n
t
h
e
f
o
r
m
o
f
d
o
m
ain
i
n
w
h
ich
th
e
f
ea
t
u
r
es a
r
e
ex
tr
ac
ted
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
co
mp
a
r
a
tive
a
n
a
lysi
s
o
f ima
g
e
co
p
y
-
m
o
ve
fo
r
g
ery
d
etec
tio
n
a
lg
o
r
ith
ms …
(
I
s
ma
il Ta
h
a
A
h
med
)
1181
3
.
1
.
IC
-
M
F
D
a
lg
o
rit
hm
s
ba
s
ed
s
pa
t
ia
l do
m
a
in
T
ec
h
n
iq
u
es
b
ased
o
n
s
p
atial
d
o
m
a
in
r
el
y
o
n
t
h
e
o
r
ig
in
al
i
m
ag
e
d
ata
in
s
p
atial
d
o
m
ai
n
(
i.e
.
an
i
m
ag
e
p
lan
e)
.
Un
iq
u
e
lo
ca
l
ch
ar
ac
te
r
is
tics
ar
e
d
etec
ted
b
y
t
h
e
k
e
y
p
o
i
n
t
b
ased
ap
p
r
o
ac
h
.
T
h
e
co
m
m
o
n
t
y
p
e
s
ar
e
s
ca
le
in
v
ar
ian
t
f
ea
t
u
r
e
tr
an
s
f
o
r
m
(
SIF
T
)
[
2
4
]
an
d
SUR
F
(
s
p
ee
d
ed
u
p
r
o
b
u
s
t
f
ea
tu
r
es)
[
2
5
]
.
T
ab
le
2
lis
ts
th
e
p
r
ev
io
u
s
r
ec
en
t
l
y
I
C
-
M
FD a
lg
o
r
ith
m
s
ac
co
r
d
in
g
to
f
ea
t
u
r
e
e
x
tr
ac
ted
f
r
o
m
s
p
atia
l d
o
m
ain
Fro
m
T
ab
le
2
,
it
ca
n
s
ee
th
at
m
o
s
t
o
f
th
e
e
x
i
s
ti
n
g
m
et
h
o
d
s
r
el
y
o
n
k
e
y
p
o
in
t
b
ased
ap
p
r
o
a
ch
.
I
t
also
s
ee
th
at
t
h
e
m
o
s
t
p
o
p
u
lar
k
e
y
p
o
in
t
f
ea
t
u
r
es
tech
n
iq
u
e
in
C
MFD
is
s
ca
le
i
n
v
ar
ian
t
f
ea
t
u
r
e
tr
an
s
f
o
r
m
(
SIFT
)
b
ased
tech
n
iq
u
e.
SIFT
f
ea
t
u
r
e
s
h
a
v
e
t
h
e
p
o
w
er
to
g
eo
m
etr
i
c
tr
an
s
f
o
r
m
at
io
n
s
th
at
ar
e
co
n
s
tan
t
to
s
ca
li
n
g
a
n
d
r
o
tatio
n
.
Ho
w
e
v
er
th
e
s
e
m
et
h
o
d
s
ca
n
f
ail
w
h
e
n
id
en
t
if
y
i
n
g
s
m
all
d
u
p
licate
r
e
g
io
n
s
;
a
ls
o
it
ca
n
b
e
f
ail
to
d
is
tin
g
u
is
h
b
et
w
ee
n
co
p
y
-
m
o
v
e
ar
ea
s
v
er
s
u
s
n
at
u
r
all
y
eq
u
iv
ale
n
t
ar
ea
s
;
f
e
w
p
r
ec
is
e
in
lab
elin
g
t
h
e
ex
ac
t
f
o
r
g
er
y
[
2
6
]
T
h
er
e
is
an
o
th
e
r
d
r
aw
b
ac
k
o
f
th
ese
m
et
h
o
d
s
,
k
e
y
p
o
in
t
-
b
ased
tec
h
n
iq
u
es
ca
n
n
o
t
d
etec
t
th
i
s
f
o
r
g
er
y
if
th
e
f
o
r
g
er
y
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
w
i
th
lo
w
co
n
tr
ast
r
eg
io
n
s
,
s
in
ce
th
e
y
ar
e
u
n
ab
le
to
g
et
e
n
o
u
g
h
k
e
y
p
o
in
ts
f
o
r
th
ese
ar
ea
s
[
2
7
]
.
An
y
o
f
th
e
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
(
J
P
E
G
co
m
p
r
ess
io
n
,
ill
u
m
i
n
atio
n
c
h
a
n
g
e,
n
o
is
e
,
co
n
tr
ast
ch
an
g
e,
b
lu
r
r
in
g
,
an
d
co
m
b
in
ed
o
f
th
e
m
)
,
an
d
/o
r
g
eo
m
e
tr
i
c
tr
an
s
f
o
r
m
atio
n
s
(
tr
an
s
latio
n
,
r
o
tatio
n
,
s
ca
lin
g
)
ap
p
lied
to
th
e
i
m
ag
e
m
a
k
e
th
e
f
o
r
g
ed
i
m
ag
e
m
o
r
e
r
ea
lis
tic
an
d
m
o
r
e
d
if
f
ic
u
lt
to
d
is
ti
n
g
u
i
s
h
d
u
p
licated
ar
ea
s
.
T
h
e
o
p
tim
al
C
M
FD
ca
n
b
e
m
ea
s
u
r
ed
in
ter
m
s
o
f
th
e
r
o
b
u
s
t
to
all
p
o
s
t
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
,
all
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
atio
n
,
d
etec
t
m
u
lt
ip
le
f
o
r
g
er
ies,
An
d
Hig
h
ac
cu
r
a
c
y
o
f
d
etec
tio
n
.
Fro
m
T
ab
le
2
,
it
can
be
s
ee
th
e
f
o
llo
w
in
g
o
b
s
er
v
atio
n
s
:
a)
T
h
e
C
MFD
th
a
t
p
r
o
p
o
s
ed
in
[
2
8
]
,
[
2
9
]
,
[
3
0
]
,
[
3
1
]
,
a
r
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
.
Ho
w
e
v
er
,
it f
ail
f
o
r
o
th
er
o
p
er
atio
n
s
esp
ec
iall
y
co
n
tr
a
s
t c
h
a
n
g
e.
b)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
in
[
3
2
]
,
[
2
9
]
,
[
3
0
]
,
[
3
3
]
,
[3
1]
ar
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
t
h
e
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
Ho
w
e
v
er
,
it f
a
il f
o
r
o
th
er
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
atio
n
s
u
c
h
as tr
a
n
s
lat
io
n
.
c)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
3
2
]
,
[
3
4
]
,
[
3
5
]
,
[
3
3
]
,
ar
e
r
o
b
u
s
t to
s
o
m
e
o
f
p
o
s
t p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
.
d)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
2
8
]
,
[
3
5
]
,
[
3
4
]
ar
e
r
o
b
u
s
t to
s
o
m
e
o
f
g
eo
m
etr
ic
tr
a
n
s
f
o
r
m
atio
n
.
e)
I
n
[
3
3
]
,
o
n
l
y
g
eo
m
etr
ic
tr
an
s
f
o
r
m
at
io
n
ar
e
ap
p
lied
.
I
n
[
3
5
]
,
o
n
l
y
p
o
s
t p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
ar
e
ap
p
lied
3
.
2
.
IC
-
M
F
D
a
lg
o
rit
hm
s
ba
s
ed
t
ra
ns
f
o
r
m
do
m
a
in
I
n
g
e
n
er
al,
m
o
s
t
p
r
ev
ale
n
t
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
e
th
o
d
s
f
o
r
b
lo
ck
-
b
ased
m
et
h
o
d
s
is
Fre
q
u
en
c
y
tr
an
s
f
o
r
m
.
T
h
e
t
w
o
p
r
i
m
ar
y
r
ea
s
o
n
s
ar
e
n
o
i
s
e
r
o
b
u
s
t
n
e
s
s
a
n
d
r
o
tatio
n
al
an
d
tr
an
s
l
atio
n
al
co
m
p
o
n
en
t
s
s
ep
ar
ab
ilit
y
[
3
6
]
.
T
ec
h
n
iq
u
e
s
b
ased
o
n
tr
an
s
f
o
r
m
atio
n
i
n
c
lu
d
e
co
n
v
er
ti
n
g
t
h
e
o
r
ig
in
al
i
m
a
g
e
d
ata
f
r
o
m
a
s
p
atial
d
o
m
ain
(
i.e
.
an
i
m
a
g
e
p
lan
e)
in
to
a
f
r
eq
u
e
n
c
y
o
r
s
p
atial
f
r
eq
u
e
n
c
y
d
o
m
a
in
.
Uses
t
h
e
Fre
q
u
e
n
c
y
Do
m
ain
to
clas
s
if
y
r
eg
io
n
s
t
h
at
ar
e
lik
el
y
to
b
e
ta
m
p
er
ed
in
i
m
a
g
es.
B
lo
ck
-
b
ased
tec
h
n
iq
u
e
s
s
ep
ar
ate
th
e
i
m
a
g
e
in
to
o
v
er
lap
p
in
g
o
r
n
o
n
-
o
v
er
lap
p
in
g
s
q
u
ar
es
o
r
b
lo
ck
s
o
f
cir
cle
s
h
ap
es
a
s
s
h
o
w
n
in
F
i
g
u
r
e
5
.
T
h
en
u
s
i
n
g
an
ef
f
ec
ti
v
e
f
ea
t
u
r
e
tr
an
s
f
o
r
m
,
f
ea
t
u
r
es
ca
n
b
e
ex
t
r
ac
ted
f
r
o
m
ea
ch
b
lo
ck
s
u
c
h
as
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
[
3
7
,
3
8
]
,
d
is
cr
ete
w
av
elet
tr
an
s
f
o
r
m
[
3
9
]
,
cu
r
v
ele
t
tr
an
s
f
o
r
m
[
4
0
]
,
f
o
u
r
ier
tr
an
s
f
o
r
m
[
4
1
,
4
2
,
4
3
]
,
f
ast
w
al
s
h
-
h
ad
a
m
ar
d
tr
an
s
f
o
r
m
(
f
w
h
t)
,
s
in
g
u
lar
v
al
u
e
d
ec
o
m
p
o
s
i
tio
n
[
4
4
]
,
p
r
in
cip
al
c
o
m
p
o
n
en
t
a
n
al
y
s
i
s
,
in
te
n
s
it
y
,
ze
r
n
i
k
e
m
o
m
e
n
ts
[
4
5
]
,
an
d
co
m
b
in
atio
n
s
o
f
t
h
e
m
.
So
m
e
o
f
m
u
lti
s
ca
le
d
ec
o
m
p
o
s
itio
n
tr
an
s
f
o
r
m
(
MSD)
lik
e
p
y
r
a
m
id
a
n
d
w
a
v
elet
tr
a
n
s
f
o
r
m
lac
k
s
d
ir
ec
tio
n
alit
y
.
Ho
w
ev
er
,
m
u
ltis
ca
le
g
eo
m
e
tr
ical
an
a
l
y
s
is
(
MG
A
)
tr
a
n
s
f
o
r
m
s
[
4
6
]
w
er
e
p
r
esen
ted
to
r
eso
lv
e
th
is
i
s
s
u
e.
On
e
o
f
t
h
ese
tr
a
n
s
f
o
r
m
s
is
cu
r
v
ele
t
tr
an
s
f
o
r
m
(
C
T
)
w
h
ich
d
ec
o
m
p
o
s
es
t
h
e
i
n
itial
i
m
a
g
e
in
to
a
g
r
o
u
p
o
f
s
u
b
b
an
d
f
r
eq
u
en
c
y
co
e
f
f
icien
ts
u
n
d
er
v
ar
io
u
s
s
ize
s
,
o
r
ien
tatio
n
a
n
d
p
o
s
itio
n
[
4
7
]
.
C
u
r
v
elet
h
as
a
co
m
m
o
n
c
h
ar
a
cter
is
tics
t
h
at
d
i
s
ti
n
g
u
i
s
h
e
s
it
f
r
o
m
th
e
o
t
h
er
t
y
p
e
s
o
f
tr
an
s
f
o
r
m
s
ar
e
h
ig
h
er
d
ir
ec
tio
n
al
s
en
s
iti
v
it
y
an
d
lo
w
er
r
ed
u
n
d
a
n
c
y
[
4
8
]
.
T
ab
le
3
lis
ts
th
e
p
r
ev
io
u
s
r
ec
en
tl
y
IC
-
M
FD a
lg
o
r
it
h
m
s
ac
co
r
d
in
g
to
f
ea
tu
r
e
ex
tr
ac
ted
f
r
o
m
tr
an
s
f
o
r
m
d
o
m
a
in
.
Fig
u
r
e
5
.
M
y
lo
v
e
i
m
ag
e
i
s
s
p
l
it in
to
n
o
n
-
o
v
er
lap
p
in
g
s
u
b
-
b
l
o
ck
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
:
1
1
7
7
-
1
1
9
0
1182
T
ab
le
2
.
P
r
ev
io
u
s
o
f
I
C
-
MFD
s
class
i
f
ied
ac
co
r
d
in
g
to
f
ea
t
u
r
e
ex
tr
ac
ted
f
r
o
m
s
p
atial
d
o
m
a
in
(
2
0
1
5
-
2
0
2
0
)
.
R
e
f
.
Y
e
a
r
D
e
scri
p
t
i
o
n
F
e
a
t
u
r
e
s
F
e
a
t
u
r
e
M
a
t
c
h
i
n
g
D
a
t
a
b
a
se
C
M
F
D
C
a
t
e
g
o
r
i
e
s
L
i
mi
t
a
t
i
o
n
s
D
i
a
a
e
t
a
l
.
,
[
3
2
]
,
2
0
1
5
.
C
M
F
D
b
a
se
d
o
n
H
e
ssi
a
n
f
e
a
t
u
r
e
s
a
n
d
a
c
e
n
t
e
r
-
sy
mm
e
t
r
i
c
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
(
C
S
L
B
P
)
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
s
:
R
o
b
u
st
t
o
JP
E
G
c
o
mp
r
e
ssi
o
n
,
t
r
a
n
sl
a
t
i
o
n
,
s
c
a
l
e
.
H
e
ssi
a
n
F
e
a
t
u
r
e
s
C
e
n
t
e
r
-
S
y
mm
e
t
r
i
c
L
o
c
a
l
B
i
n
a
r
y
P
a
t
t
e
r
n
(
C
S
L
B
P
)
M
I
C
C
-
F
2
2
0
S
e
g
me
n
t
e
d
-
B
a
se
d
M
e
t
h
o
d
s
N
o
t
R
o
b
u
st
t
o
R
o
t
a
t
i
o
n
,
B
l
u
r
a
n
d
C
o
n
t
r
a
s
t
C
h
a
n
g
e
.
S
mal
l
d
u
p
l
i
c
a
t
e
d
r
e
g
i
o
n
n
o
t
d
e
t
e
c
t
e
d
.
G
u
z
i
n
e
t
a
l
.
[
2
8
]
,
2
0
1
6
.
C
M
F
D
t
e
c
h
n
i
q
u
e
b
a
se
d
o
n
A
K
A
Z
E
f
e
a
t
u
r
e
s
a
n
d
n
o
n
l
i
n
e
a
r
sca
l
e
sp
a
c
e
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
s:
R
o
b
u
st
t
o
r
o
t
a
t
e
d
,
b
l
u
r
r
e
d
,
A
W
G
N
a
d
d
e
d
,
o
r
JP
EG
c
o
mp
r
e
sse
d
.
A
K
A
Z
E
F
e
a
t
u
r
e
s
H
a
mm
i
n
g
D
i
st
a
n
c
e
G
o
o
g
l
e
I
mag
e
,
C
o
M
o
F
o
D
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
T
h
e
S
c
a
l
i
n
g
a
n
d
c
o
n
t
r
a
st
c
h
a
n
g
e
i
s
n
o
t
c
o
v
e
r
e
d
.
F
a
n
e
t
a
l
.
[
2
9
]
,
2
0
1
7
A
C
M
F
D
r
e
l
y
o
n
h
y
b
r
i
d
f
e
a
t
u
r
e
s i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
s:
R
o
b
u
st
t
o
r
o
t
a
t
i
o
n
,
s
c
a
l
i
n
g
,
JP
EG
c
o
mp
r
e
ssi
o
n
a
n
d
a
d
d
i
n
g
n
o
i
se
.
K
A
Z
E
&
S
I
F
T
F
e
a
t
u
r
e
s
I
mp
r
o
v
e
d
n
-
b
e
st
M
a
t
c
h
i
n
g
S
t
r
a
t
e
g
y
I
M
D
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
B
l
u
r
a
n
d
C
o
n
t
r
a
s
t
C
h
a
n
g
e
i
s
n
o
t
c
o
v
e
r
e
d
.
.
S
a
j
j
a
d
e
t
a
l
.
[
3
0
]
,
2
0
1
7
.
C
M
F
D
w
i
t
h
3
l
e
v
e
l
s
o
f
W
a
r
d
l
i
n
k
a
g
e
b
a
se
d
c
l
u
s
t
e
r
i
n
g
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
s:
R
o
b
u
st
t
o
r
o
t
a
t
i
o
n
,
s
c
a
l
e
,
mu
l
t
i
l
e
v
e
l
f
o
r
g
e
r
i
e
s,
n
o
i
se
,
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
.
T
h
e
S
c
a
l
e
I
n
v
a
r
i
a
n
t
F
e
a
t
u
r
e
T
r
a
n
sf
o
r
m (S
I
F
T
)
W
a
r
d
-
b
a
se
d
c
l
u
st
e
r
i
n
g
M
I
C
C
-
F
2
2
0
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
F
a
l
s
e
p
o
si
t
i
v
e
st
i
l
l
h
i
g
h
e
r
.
C
a
n
n
o
t
d
e
t
e
c
t
s
p
l
i
c
i
n
g
f
o
r
g
e
r
i
e
s.
C
o
n
t
r
a
st
C
h
a
n
g
e
i
s
n
o
t
c
o
v
e
r
e
d
H
e
sh
a
m
e
t
a
l
.
,
[
3
3
]
,
20
1
8
.
C
M
F
D
b
a
se
d
S
I
F
T
a
n
d
f
u
z
z
y
c
-
me
a
n
s
(
F
C
M
)
c
l
u
st
e
r
i
n
g
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
M
i
n
i
m
a
l
e
x
e
c
u
t
i
o
n
t
i
me
.
R
o
b
u
st
t
o
r
o
t
a
t
i
o
n
,
s
c
a
l
i
n
g
.
S
I
F
T
F
u
z
z
y
C
-
me
a
n
s
(
F
C
M
)
M
I
C
C
-
F
2
2
0
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
F
a
l
s
e
p
o
si
t
i
v
e
st
i
l
l
h
i
g
h
e
r
.
B
l
u
r
a
n
d
C
o
n
t
r
a
s
t
C
h
a
n
g
e
i
s
n
o
t
c
o
v
e
r
e
d
.
P
r
i
y
a
e
t
a
l
.
,
[3
5]
,
2
0
1
8
.
C
M
F
D
b
a
se
d
o
n
c
o
m
b
i
n
i
n
g
t
h
e
t
r
a
d
i
t
i
o
n
a
l
b
l
o
c
k
-
b
a
se
d
a
n
d
k
e
y
p
o
i
n
t
-
b
a
se
d
t
e
c
h
n
i
q
u
e
s
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
M
i
n
i
m
a
l
e
x
e
c
u
t
i
o
n
t
i
me
.
R
o
b
u
st
t
o
B
r
i
g
h
t
n
e
ss
c
h
a
n
g
e
s,
c
o
n
t
r
a
s
t
a
d
j
u
s
t
me
n
t
s
,
c
o
l
o
r
r
e
d
u
c
t
i
o
n
a
n
d
b
l
u
r
r
i
n
g
.
B
i
n
a
r
y
F
e
a
t
u
r
e
s
B
i
n
a
r
y
D
i
scri
m
i
n
a
t
i
v
e
F
e
a
t
u
r
e
s
(
B
D
F
)
C
o
M
o
F
o
D
,
I
M
D
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s &
b
l
o
c
k
-
b
a
se
d
me
t
h
o
d
s
T
r
u
e
&F
a
l
se
p
o
si
t
i
v
e
me
t
r
i
c
s
i
s
n
o
t
c
o
v
e
r
e
d
.
N
o
i
se
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
i
s
n
o
t
c
o
v
e
r
e
d
.
A
y
a
e
t
a
l
.
,
[
3
1
]
,
2
0
1
9
.
C
M
F
D
r
e
l
y
o
n
d
e
n
si
t
y
-
b
a
se
d
c
l
u
st
e
r
i
n
g
a
n
d
G
u
a
r
a
n
t
e
e
d
O
u
t
l
i
e
r
R
e
mo
v
a
l
a
l
g
o
r
i
t
h
m
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
r
o
t
a
t
i
o
n
,
s
c
a
l
i
n
g
,
JP
EG
c
o
mp
r
e
ssi
o
n
a
n
d
n
o
i
se
.
l
o
w
f
a
l
s
e
p
o
si
t
i
v
e
r
a
t
e
S
I
F
T
D
B
S
C
A
N
M
I
C
C
-
F
2
2
0
,
I
M
D
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
B
l
u
r
a
n
d
C
o
n
t
r
a
s
t
C
h
a
n
g
e
i
s
n
o
t
c
o
v
e
r
e
d
.
V
a
i
sh
n
a
v
i
e
t
a
l
.
,
[
3
4
]
,
2
0
1
9
.
C
M
F
D
b
a
se
d
o
n
me
a
n
s
o
f
sy
mm
e
t
r
y
b
a
se
d
l
o
c
a
l
f
e
a
t
u
r
e
s
a
r
e
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
JP
EG
c
o
mp
r
e
ssi
o
n
a
n
d
u
n
c
o
mp
r
e
sse
d
.
L
o
c
a
l
sy
mm
e
t
r
y
R
a
n
d
o
m
S
a
mp
l
i
n
g
C
o
n
se
n
s
u
s
(
R
A
N
S
A
C
)
M
I
C
C
-
F
2
2
0
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
T
h
e
r
e
su
l
t
s n
e
e
d
t
o
b
e
e
n
h
a
n
c
e
d
.
O
n
l
y
t
e
st
e
d
w
i
t
h
JP
EG
c
o
mp
r
e
ssi
o
n
.
B
l
u
r
,
n
o
i
se
,
C
o
n
t
r
a
st
C
h
a
n
g
e
,
a
n
d
t
r
a
n
sl
a
t
i
o
n
a
r
e
n
o
t
c
o
v
e
r
e
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
co
mp
a
r
a
tive
a
n
a
lysi
s
o
f ima
g
e
co
p
y
-
m
o
ve
fo
r
g
ery
d
etec
tio
n
a
lg
o
r
ith
ms …
(
I
s
ma
il Ta
h
a
A
h
med
)
1183
T
ab
le
3
.
P
r
ev
io
u
s
o
f
I
C
-
MFD
s
class
i
f
ied
ac
co
r
d
in
g
to
f
ea
t
u
r
e
ex
tr
ac
ted
f
r
o
m
tr
an
s
f
o
r
m
d
o
m
ain
R
e
f
.
Y
e
a
r
D
e
scri
p
t
i
o
n
C
M
F
D
C
a
t
e
g
o
r
i
e
s
F
e
a
t
u
r
e
s
F
e
a
t
u
r
e
M
a
t
c
h
i
n
g
D
a
t
a
b
a
se
L
i
mi
t
a
t
i
o
n
s
M
a
h
mo
o
d
e
t
a
l
.
,
[
4
0
]
,
2
0
1
6
.
C
M
F
D
b
a
se
d
o
n
D
C
T
a
n
d
G
a
u
ss
i
a
n
R
B
F
k
e
r
n
e
l
P
C
A
i
s p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
n
o
i
se
,
c
o
m
p
r
e
ssi
o
n
,
a
n
d
b
l
u
r
r
i
n
g
.
L
o
w
e
r
f
e
a
t
u
r
e
l
e
n
g
t
h
.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
D
C
T
a
n
d
K
P
C
A
Eu
c
l
i
d
e
a
n
d
i
s
t
a
n
c
e
DV
M
M
C
o
l
u
mb
i
a
a
n
d
I
n
t
e
r
n
e
t
C
o
n
t
r
a
st
c
h
a
n
g
e
a
n
d
sca
l
i
n
g
i
s
n
o
t
c
o
v
e
r
e
d
.
T
h
e
f
i
n
d
i
n
g
s
o
n
l
y
r
e
f
e
r
t
o
a
f
e
w
o
f
t
h
e
p
o
st
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
.
K
h
i
z
a
r
a
n
d
Q
a
z
i
,
[
4
2
]
,
2
0
1
7
.
C
M
F
D
b
a
se
d
o
n
t
h
e
D
W
T
a
s
w
e
l
l
a
s
t
h
e
D
C
T
f
o
r
f
e
a
t
u
r
e
r
e
d
u
c
t
i
o
n
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
e
d
u
c
e
d
f
e
a
t
u
r
e
v
e
c
t
o
r
.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
D
W
T
c
o
e
f
f
i
c
i
e
n
t
s
B
l
o
c
k
S
i
mi
l
a
r
i
t
y
T
h
r
e
sh
o
l
d
I
mag
e
samp
l
e
s
P
o
st
-
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
a
r
e
n
o
t
c
o
v
e
r
e
d
.
T
h
e
f
i
n
d
i
n
g
s
f
o
r
P
o
st
-
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
a
r
e
n
o
t
a
p
p
l
i
e
d
.
T
o
q
e
e
r
e
t
a
l
.
,
[
3
8
]
,
2
0
1
7
.
C
M
F
D
b
a
se
d
o
n
l
o
c
a
l
b
i
n
a
r
y
p
a
t
t
e
r
n
v
a
r
i
a
n
c
e
(
L
B
P
V
)
a
n
d
st
a
t
i
o
n
a
r
y
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
t
r
a
n
sl
a
t
i
o
n
,
f
l
i
p
p
i
n
g
,
b
l
u
r
r
i
n
g
,
r
o
t
a
t
i
o
n
,
sc
a
l
i
n
g
,
c
o
l
o
r
r
e
d
u
c
t
i
o
n
,
b
r
i
g
h
t
n
e
ss
c
h
a
n
g
e
,
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
.
L
o
w
e
r
f
e
a
t
u
r
e
l
e
n
g
t
h
a
n
d
c
o
mp
u
t
a
t
i
o
n
a
l
t
i
me
.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
b
l
o
c
k
-
w
i
se
q
u
a
n
t
i
z
e
d
D
C
T
c
o
e
f
f
i
c
i
e
n
t
s
S
h
i
f
t
D
i
st
a
n
c
e
C
r
i
t
e
r
i
o
n
C
o
M
o
F
o
D
,
K
L
T
CI
N
o
i
se
,
C
o
n
t
r
a
st
c
h
a
n
g
e
a
n
d
sc
a
l
i
n
g
i
s
n
o
t
c
o
v
e
r
e
d
.
T
h
e
f
i
n
d
i
n
g
s
f
o
r
N
o
i
se
,
C
o
n
t
r
a
st
c
h
a
n
g
e
a
n
d
sca
l
i
n
g
a
r
e
n
o
t
a
p
p
l
i
e
d
.
T
o
q
e
e
r
e
t
a
l
.
,
[
3
9
]
,
2
0
1
8
.
C
M
F
D
b
a
se
d
o
n
t
h
e
st
a
t
i
o
n
a
r
y
w
a
v
e
l
e
t
t
r
a
n
sf
o
r
m (S
W
T
)
a
n
d
D
C
T
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
t
r
a
n
sl
a
t
i
o
n
,
b
l
u
r
r
i
n
g
,
JP
EG
c
o
mp
r
e
ssi
o
n
,
c
o
l
o
r
r
e
d
u
c
t
i
o
n
,
a
n
d
,
b
r
i
g
h
t
n
e
ss c
h
a
n
g
e
.
L
o
w
e
r
f
e
a
t
u
r
e
v
e
c
t
o
r
s
l
e
n
g
t
h
a
n
d
c
o
mp
u
t
a
t
i
o
n
a
l
t
i
me
.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
D
W
T
c
o
e
f
f
i
c
i
e
n
t
s
B
l
o
c
k
d
i
s
t
a
n
c
e
a
n
d
b
l
o
c
k
si
mi
l
a
r
i
t
y
t
h
r
e
sh
o
l
d
.
C
oM
o
F
o
D
a
n
d
U
C
I
D
R
o
t
a
t
i
o
n
,
l
a
r
g
e
r
sca
l
i
n
g
,
a
d
d
i
t
i
v
e
N
o
i
se
,
a
n
d
C
o
n
t
r
a
st
c
h
a
n
g
e
a
r
e
n
o
t
c
o
v
e
r
e
d
.
B
a
d
a
l
e
t
a
l
.
,
[
3
7
]
,
2
0
1
9
.
C
M
F
D
b
a
se
d
o
n
h
y
b
r
i
d
l
o
c
a
l
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
(
S
U
R
F
a
n
d
M
S
E
R
)
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
R
o
t
a
t
i
o
n
a
n
d
S
c
a
l
i
n
g
.
L
o
w
e
r
D
i
me
n
si
o
n
F
e
a
t
u
r
e
s.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
S
U
R
F
f
e
a
t
u
r
e
s
Tw
o
n
e
a
r
e
st
n
e
i
g
h
b
o
r
s
(
2
N
N
)
p
r
o
c
e
d
u
r
e
M
I
C
C
-
F
2
2
0
,
M
I
C
C
-
F
2
0
0
0
a
n
d
M
I
C
C
-
F
6
0
0
F
a
l
s
e
p
o
si
t
i
v
e
st
i
l
l
h
i
g
h
e
r
.
A
l
g
o
r
i
t
h
m
n
e
e
d
s
t
o
e
n
h
a
n
c
e
e
sp
e
c
i
a
l
l
y
f
o
r
h
i
g
h
l
y
si
mi
l
a
r
r
e
g
i
o
n
s.
N
o
i
se
,
C
o
n
t
r
a
st
c
h
a
n
g
e
,
b
l
u
r
r
i
n
g
,
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
a
r
e
n
o
t
c
o
v
e
r
e
d
.
T
h
e
f
i
n
d
i
n
g
s
o
n
l
y
r
e
f
e
r
to
a
f
e
w
o
f
t
h
e
p
o
st
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
.
K
u
n
j
e
t
a
l
.
,
[
2
6
]
,
2
0
2
0
.
C
M
F
D
b
a
se
d
o
n
T
e
t
r
o
l
e
t
t
r
a
n
sf
o
r
m
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
b
l
u
r
r
i
n
g
,
b
r
i
g
h
t
n
e
ss
a
d
j
u
s
t
me
n
t
,
c
o
n
t
r
a
st
,
r
o
t
a
t
i
o
n
,
sca
l
i
n
g
,
JP
EG
c
o
mp
r
e
ssi
o
n
.
D
e
t
e
c
t
v
e
r
y
smal
l
d
u
p
l
i
c
a
t
e
d
r
e
g
i
o
n
s.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
4
l
o
w
-
p
a
ss
a
n
d
1
2
h
i
g
h
-
p
a
ss
c
o
e
f
f
i
c
i
e
n
t
s
B
l
o
c
k
S
i
mi
l
a
r
i
t
y
T
h
r
e
sh
o
l
d
a
n
d
Eu
c
l
i
d
e
a
n
d
i
s
t
a
n
c
e
G
R
I
P
a
n
d
C
o
M
o
F
o
D
N
o
i
se
i
s n
o
t
c
o
v
e
r
e
d
.
T
r
u
e
&F
a
l
se
p
o
si
t
i
v
e
me
t
r
i
c
s
i
s
n
o
t
c
o
v
e
r
e
d
.
S
h
i
l
p
a
e
t
a
l
.
,
[
3
6
]
,
2
0
2
0
.
C
M
F
D
b
a
se
d
o
n
d
o
u
b
l
y
st
o
c
h
a
s
t
i
c
mo
d
e
l
(
d
sm)
i
s
p
r
o
p
o
se
d
.
Fi
n
d
i
n
g
:
R
o
b
u
st
t
o
b
l
u
r
r
i
n
g
,
n
o
i
se
,
r
o
t
a
t
i
o
n
,
sca
l
i
n
g
,
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
.
S
p
l
i
c
i
n
g
a
n
d
c
o
p
y
-
mo
v
e
a
r
e
u
se
d
.
U
se
f
e
w
f
e
a
t
u
r
e
s.
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
b
l
o
c
k
-
w
i
se
q
u
a
n
t
i
z
e
d
D
C
T
c
o
e
f
f
i
c
i
e
n
t
s
EL
M
/
S
V
M
C
A
S
I
A
v
1
.
0
a
n
d
v
2
.
0
C
o
n
t
r
a
st
c
h
a
n
g
e
i
s n
o
t
c
o
v
e
r
e
d
.
T
r
u
e
&F
a
l
se
p
o
si
t
i
v
e
me
t
r
i
c
s
i
s
n
o
t
c
o
v
e
r
e
d
.
T
h
er
e
is
r
elativ
el
y
lit
tle
co
m
p
lex
it
y
i
n
t
h
e
f
ea
tu
r
e
s
d
er
iv
ed
in
t
h
e
s
p
atial
d
o
m
ai
n
.
Ho
w
ev
er
,
as
th
e
co
m
p
u
tatio
n
al
p
o
w
er
o
f
co
m
p
u
ter
s
in
cr
ea
s
e
s
o
v
er
ti
m
e,
in
s
p
ite
o
f
th
eir
r
elativ
el
y
h
ig
h
co
m
p
lex
i
t
y
,
f
ea
tu
r
e
s
ex
tr
ac
ted
in
o
th
er
d
o
m
ai
n
s
b
ec
o
m
e
m
o
r
e
co
m
m
o
n
b
ec
au
s
e
th
e
f
o
llo
w
in
g
i
n
ter
esti
n
g
is
s
u
e:
a)
T
h
e
m
u
lti
s
ca
le
an
d
m
u
lt
i
-
o
r
ie
n
tatio
n
f
ea
t
u
r
es
o
f
t
h
e
h
u
m
an
v
is
u
al
s
y
s
te
m
(
HV
S)
ar
e
b
ette
r
r
ef
lecte
d
b
y
th
ese
tr
a
n
s
f
o
r
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
:
1
1
7
7
-
1
1
9
0
1184
b)
A
v
er
y
in
ter
e
s
ti
n
g
i
s
s
u
e
ca
n
b
e
n
o
ted
w
h
e
n
u
s
i
n
g
th
e
f
r
eq
u
e
n
c
y
d
o
m
ain
,
s
i
g
n
at
u
r
es
f
o
r
th
e
i
m
a
g
e
b
lo
ck
s
ar
e
p
r
o
v
id
ed
v
ia
s
ig
n
al
tr
a
n
s
f
o
r
m
,
en
ab
li
n
g
d
u
p
lica
te
r
eg
io
n
s
to
b
e
id
en
tif
ied
.
c)
I
n
th
e
b
lo
ck
-
b
a
s
ed
ap
p
r
o
ac
h
,
p
o
p
u
lar
tech
n
iq
u
es
ar
e
f
r
eq
u
en
c
y
tr
a
n
s
f
o
r
m
.
T
h
e
n
o
i
s
e,
b
lu
r
r
in
g
,
a
n
d
J
P
E
G
c
o
m
p
r
ess
io
n
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
ar
e
i
n
v
ar
ia
n
t
b
y
f
r
eq
u
e
n
c
y
tr
a
n
s
f
o
r
m
.
T
h
e
f
o
llo
w
i
n
g
p
o
in
ts
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
T
ab
le
3:
a)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
i
n
[
26
,
36
,
4
9
]
,
ar
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
.
Ho
w
e
v
er
,
it f
ail
f
o
r
o
th
er
o
p
er
atio
n
s
esp
ec
iall
y
co
n
tr
a
s
t c
h
a
n
g
e.
b)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
37
,
26
,
36
,
38
]
ar
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
t
h
e
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
atio
n
.
Ho
w
e
v
er
,
it f
ail
f
o
r
o
th
er
g
eo
m
etr
ic
tr
a
n
s
f
o
r
m
atio
n
s
u
c
h
as
tr
an
s
latio
n
.
c)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
38
,
39
]
a
r
e
r
o
b
u
s
t
to
s
o
m
e
o
f
p
o
s
t
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
.
I
n
th
e
d
etec
tio
n
o
f
m
a
n
ip
u
latio
n
s
,
esp
ec
iall
y
f
o
r
J
P
E
G
co
m
p
r
ess
io
n
,
D
C
T
is
v
er
y
co
m
m
o
n
tr
a
n
s
f
o
r
m
d
u
e
to
its
h
i
g
h
co
m
p
ac
t
e
n
er
g
y
ab
il
it
y
(
m
o
s
t
o
f
th
e
in
f
o
r
m
atio
n
in
a
m
in
i
m
al
n
u
m
b
er
o
f
co
ef
f
ic
ien
t
s
)
.
T
h
er
ef
o
r
e,
th
e
f
i
n
d
i
n
g
r
o
b
u
s
t to
J
P
E
G
co
m
p
r
ess
io
n
.
d)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
4
0
]
,
ar
e
r
o
b
u
s
t to
s
o
m
e
o
f
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
e)
I
n
[
3
7
]
,
o
n
l
y
g
eo
m
etr
ic
tr
an
s
f
o
r
m
at
io
n
ar
e
ap
p
lied
.
f)
I
n
[
3
6
]
,
o
n
l
y
p
o
s
t p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
ar
e
ap
p
lied
.
g)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
in
[
2
6
]
,
ar
e
v
er
y
r
o
b
u
s
t
to
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
a
n
d
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
A
cc
o
r
d
in
g
to
t
h
e
liter
at
u
r
e
s
u
r
v
e
y
,
T
etr
o
let
tr
an
s
f
o
r
m
w
a
s
f
ir
s
t u
s
ed
in
t
h
e
f
ield
o
f
i
m
a
g
e
f
o
r
g
er
y
d
etec
tio
n
.
I
n
co
n
tr
a
s
t
to
o
th
er
s
im
ilar
m
et
h
o
d
s
s
u
ch
as
DW
T
an
d
c
o
n
to
u
r
let
tr
an
s
f
o
r
m
,
th
e
f
ea
t
u
r
es
d
er
iv
ed
u
s
in
g
T
etr
o
let
tr
an
s
f
o
r
m
ar
e
m
o
r
e
r
o
b
u
s
t
d
u
e
to
im
p
r
o
v
ed
d
ir
ec
tio
n
s
e
n
s
i
ti
v
it
y
.
An
o
t
h
er
tr
an
s
f
o
r
m
is
C
u
r
v
elet
h
as
a
co
m
m
o
n
ch
ar
ac
ter
is
t
ics
t
h
a
t
d
is
tin
g
u
is
h
es
i
t
f
r
o
m
t
h
e
o
th
er
t
y
p
es
o
f
T
r
an
s
f
o
r
m
s
ar
e
Hig
h
er
d
ir
ec
tio
n
al
s
en
s
iti
v
it
y
a
n
d
lo
w
er
r
ed
u
n
d
a
n
c
y
[
4
1
]
.
T
h
er
e
is
a
v
er
y
s
ig
n
i
f
ica
n
t
an
d
in
s
p
ir
i
n
g
a
s
p
ec
t,
w
h
ich
i
s
t
h
at
th
e
c
u
r
v
elet
tr
a
n
s
f
o
r
m
is
i
n
v
a
r
ian
t
to
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
,
s
u
c
h
as
n
o
is
e,
b
l
u
r
r
in
g
,
an
d
J
P
E
G
co
m
p
r
ess
io
n
.
T
h
er
e
is
r
elativ
el
y
lit
tle
co
m
p
lex
it
y
i
n
t
h
e
f
ea
tu
r
e
s
d
er
iv
ed
in
t
h
e
s
p
atial
d
o
m
ai
n
.
Ho
w
ev
er
,
as
th
e
co
m
p
u
tatio
n
al
p
o
w
er
o
f
co
m
p
u
ter
s
in
cr
ea
s
e
s
o
v
er
ti
m
e,
in
s
p
ite
o
f
th
eir
r
elativ
el
y
h
ig
h
co
m
p
lex
i
t
y
,
f
ea
tu
r
e
s
ex
tr
ac
ted
in
o
th
er
d
o
m
ai
n
s
b
ec
o
m
e
m
o
r
e
co
m
m
o
n
b
ec
au
s
e
th
e
f
o
llo
w
in
g
i
n
ter
esti
n
g
is
s
u
e:
a)
T
h
e
m
u
lti
s
ca
le
an
d
m
u
lt
i
-
o
r
ie
n
tatio
n
f
ea
t
u
r
es
o
f
t
h
e
h
u
m
an
v
is
u
al
s
y
s
te
m
(
HV
S)
ar
e
b
ette
r
r
ef
lecte
d
b
y
th
ese
tr
a
n
s
f
o
r
m
s
.
b)
A
v
er
y
in
ter
e
s
ti
n
g
i
s
s
u
e
ca
n
b
e
n
o
ted
w
h
e
n
u
s
i
n
g
th
e
f
r
eq
u
e
n
c
y
d
o
m
ain
,
s
i
g
n
at
u
r
es
f
o
r
th
e
i
m
a
g
e
b
lo
ck
s
ar
e
p
r
o
v
id
ed
v
ia
s
ig
n
al
tr
a
n
s
f
o
r
m
,
en
ab
li
n
g
d
u
p
lica
te
r
eg
io
n
s
to
b
e
id
en
tif
ied
.
c)
I
n
th
e
b
lo
ck
-
b
a
s
ed
ap
p
r
o
ac
h
,
p
o
p
u
lar
tech
n
iq
u
es
ar
e
f
r
eq
u
en
c
y
tr
a
n
s
f
o
r
m
.
T
h
e
n
o
i
s
e,
b
lu
r
r
in
g
,
a
n
d
J
P
E
G
c
o
m
p
r
ess
io
n
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
a
tio
n
s
ar
e
i
n
v
ar
ia
n
t
b
y
f
r
eq
u
e
n
c
y
tr
a
n
s
f
o
r
m
.
T
h
e
f
o
llo
w
i
n
g
p
o
in
t
s
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
T
ab
le
3:
a)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
in
[
2
6
]
,
[
3
6
]
,
[
4
0
]
,
ar
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
.
Ho
w
e
v
er
,
it f
ail
f
o
r
o
th
er
o
p
er
atio
n
s
esp
ec
iall
y
co
n
tr
a
s
t c
h
a
n
g
e.
b)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
i
n
[
3
7
]
,
[
2
6
]
,
[
3
6
]
,
[
3
8
]
a
r
e
v
er
y
r
o
b
u
s
t
to
m
o
s
t
o
f
t
h
e
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
Ho
w
e
v
er
,
it f
a
il f
o
r
o
th
er
g
eo
m
e
t
r
ic
tr
an
s
f
o
r
m
atio
n
s
u
c
h
as tr
a
n
s
lat
io
n
.
c)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
in
[
3
8
]
,
[
3
9
]
ar
e
r
o
b
u
s
t to
s
o
m
e
o
f
p
o
s
t p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
.
I
n
th
e
d
etec
tio
n
o
f
m
a
n
ip
u
latio
n
s
,
esp
ec
iall
y
f
o
r
J
P
E
G
co
m
p
r
ess
io
n
,
D
C
T
is
v
er
y
co
m
m
o
n
tr
a
n
s
f
o
r
m
d
u
e
to
its
h
i
g
h
co
m
p
ac
t
e
n
er
g
y
ab
il
it
y
(
m
o
s
t
o
f
th
e
in
f
o
r
m
atio
n
in
a
m
in
i
m
al
n
u
m
b
er
o
f
co
ef
f
ic
ien
t
s
)
.
T
h
er
ef
o
r
e,
th
e
f
i
n
d
in
g
r
o
b
u
s
t to
J
P
E
G
co
m
p
r
ess
io
n
.
d)
T
h
e
C
MFD
th
at
p
r
o
p
o
s
ed
in
[
4
0
]
,
ar
e
r
o
b
u
s
t to
s
o
m
e
o
f
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
e)
I
n
[
3
7
]
,
o
n
l
y
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
at
io
n
ar
e
ap
p
lied
.
f)
I
n
[
3
9
]
,
o
n
l
y
p
o
s
t
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
ar
e
ap
p
lied
.
g)
T
h
e
C
MFD
t
h
at
p
r
o
p
o
s
ed
in
[
2
6
]
,
ar
e
v
er
y
r
o
b
u
s
t
to
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
a
n
d
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
.
A
cc
o
r
d
in
g
to
t
h
e
liter
at
u
r
e
s
u
r
v
e
y
,
T
etr
o
let
tr
an
s
f
o
r
m
w
a
s
f
ir
s
t u
s
ed
in
t
h
e
f
ield
o
f
i
m
a
g
e
f
o
r
g
er
y
d
etec
tio
n
.
I
n
co
n
tr
a
s
t
to
o
th
er
s
im
ilar
m
et
h
o
d
s
s
u
ch
as
DW
T
an
d
c
o
n
to
u
r
let
tr
a
n
s
f
o
r
m
,
th
e
f
ea
t
u
r
es
d
er
iv
ed
u
s
in
g
T
etr
o
let
tr
an
s
f
o
r
m
ar
e
m
o
r
e
r
o
b
u
s
t
d
u
e
to
im
p
r
o
v
ed
d
ir
ec
tio
n
s
e
n
s
i
ti
v
it
y
.
An
o
t
h
er
tr
an
s
f
o
r
m
i
s
c
u
r
v
elet
h
a
s
a
co
m
m
o
n
c
h
ar
ac
ter
is
tics
t
h
at
d
is
tin
g
u
is
h
es
it
f
r
o
m
th
e
o
th
er
t
y
p
e
s
o
f
T
r
an
s
f
o
r
m
s
ar
e
Hig
h
er
d
ir
ec
tio
n
al
s
en
s
iti
v
it
y
a
n
d
lo
w
er
r
ed
u
n
d
a
n
c
y
[
4
1
]
.
T
h
er
e
is
a
v
er
y
s
ig
n
i
f
ica
n
t
an
d
in
s
p
ir
i
n
g
a
s
p
ec
t,
w
h
ich
i
s
t
h
at
th
e
c
u
r
v
elet
tr
a
n
s
f
o
r
m
is
i
n
v
a
r
ian
t
to
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
,
s
u
c
h
as
n
o
is
e,
b
lu
r
r
in
g
,
an
d
J
P
E
G
co
m
p
r
ess
io
n
.
3
.
3
.
C
o
m
pa
riso
n o
f
I
C
-
M
F
D
t
ec
hn
iqu
e
s
T
h
e
m
o
s
t
o
f
cu
r
r
en
t
C
MFD
tech
n
iq
u
es
ai
m
to
o
b
tain
th
e
f
o
llo
w
i
n
g
is
s
u
e
s
:
r
o
b
u
s
t
n
es
s
to
p
o
s
t
-
p
r
o
ce
s
s
in
g
o
p
er
atio
n
s
,
g
eo
m
e
tr
ic
tr
an
s
f
o
r
m
at
io
n
s
,
d
etec
t
m
u
ltip
le
f
o
r
g
er
ies,
Hi
g
h
d
ete
ctio
n
ac
cu
r
ac
y
.
Fo
r
co
m
p
ar
is
o
n
,
T
ab
le
4
d
is
p
lay
s
th
e
r
es
u
lts
o
f
s
o
m
e
I
C
-
M
FDs
b
ase
d
o
n
s
p
atial/f
r
eq
u
e
n
c
y
d
o
m
ai
n
.
T
h
e
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
1
5
I
C
-
M
FDs
m
e
th
o
d
s
i
n
m
u
ltip
le
d
o
m
ai
n
s
i
n
ter
m
o
f
tr
u
e
&
f
a
ls
e
p
o
s
itiv
e
m
etr
ic
s
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
co
mp
a
r
a
tive
a
n
a
lysi
s
o
f ima
g
e
co
p
y
-
m
o
ve
fo
r
g
ery
d
etec
tio
n
a
lg
o
r
ith
ms …
(
I
s
ma
il Ta
h
a
A
h
med
)
1185
co
m
p
ar
ed
.
I
t c
an
b
e
o
b
s
er
v
ed
th
at
I
C
-
M
FDs
b
ased
o
n
s
p
atia
l d
o
m
ain
[
3
1
]
ten
d
s
to
lo
w
f
al
s
e
p
o
s
iti
v
e
r
ate
t
h
an
th
e
r
est
m
eth
o
d
s
.
Ho
w
e
v
er
,
[
2
9
]
ten
d
s
to
h
ig
h
f
a
l
s
e
p
o
s
iti
v
e
r
ate
th
an
t
h
e
r
est
m
eth
o
d
s
.
T
ab
le
4
.
T
h
e
co
m
p
ar
ativ
e
r
es
u
lts
b
y
d
etec
tio
n
ac
c
u
r
ac
y
f
o
r
v
ar
io
u
s
IC
-
MFD
s
ac
r
o
s
s
d
if
f
er
e
n
t d
o
m
ai
n
s
.
D
o
mai
n
IC
-
M
F
D
C
M
F
D
C
a
t
e
g
o
r
i
e
s
D
a
t
a
b
a
se
A
c
c
u
r
a
c
y
T
P
R
(
%)
F
P
R
(
%)
F1
(
%)
S
p
a
t
i
a
l
[
3
5
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
C
o
M
o
F
o
D
,
I
M
D
N
/
A
N
/
A
8
8
:
3
5
[
2
9
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
I
M
D
7
8
.
3
3
9
.
7
9
8
7
.
0
4
[
3
1
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
2
0
,
I
M
D
1
0
0
3
.
6
3
9
7
.
5
6
[
3
4
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
2
0
8
3
.
6
4
5
.
4
5
9
0
.
2
[
3
3
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
ds
M
I
C
C
-
F
2
2
0
9
9
.
0
9
9
.
0
9
N
/
A
[
3
0
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
2
0
9
7
.
8
5
.
6
N
/
A
[
3
2
]
S
e
g
me
n
t
e
d
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
2
0
92
8
N
/
A
[
2
8
]
K
e
y
p
o
i
n
t
-
B
a
se
d
M
e
t
h
o
d
s
G
o
o
g
l
e
i
mag
e
,
C
o
M
o
F
o
D
0
,
8
0
0
,
0
2
N
/
A
T
r
a
n
sf
o
r
m
[
2
6
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
G
R
I
P
a
n
d
C
o
M
o
F
o
D
N
/
A
N
/
A
0
.
9
7
[
3
6
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
C
A
S
I
A
v
1
.
0
a
n
d
v
2
.
0
N
/
A
N
/
A
9
6
.
5
6
[
4
2
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
V
a
r
i
o
u
s
i
mag
e
s
N
/
A
N
/
A
73
.
6
2
[
3
7
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
2
0
,
M
I
C
C
-
F
2
0
0
0
a
n
d
M
I
C
C
-
F
6
0
0
9
7
.
5
5
8
.
4
0
N
/
A
[
4
3
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
C
A
S
I
A
v
1
.
0
a
n
d
v
2
.
0
N
/
A
N
/
A
93
[
4
4
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
C
o
M
o
F
o
D
N
/
A
N
/
A
7
9
.
3
3
[
4
5
]
B
l
o
c
k
-
B
a
se
d
M
e
t
h
o
d
s
M
I
C
C
-
F
2
0
0
0
a
n
d
M
I
C
C
-
F
2
2
0
N
/
A
N
/
A
0
.
9
1
T
h
e
i
m
a
g
e
m
a
y
b
e
e
x
p
o
s
ed
to
b
o
th
o
r
ei
th
er
o
f
t
h
e
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
an
d
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
s
,
w
h
ic
h
m
a
y
d
is
tu
r
b
t
h
e
co
r
r
elatio
n
b
et
w
ee
n
co
p
y
-
m
o
v
ed
r
eg
io
n
s
th
e
n
m
a
k
e
it
m
o
r
e
d
if
f
ic
u
lt
to
d
is
tin
g
u
is
h
d
u
p
lica
ted
ar
ea
s
.
I
n
o
r
d
er
to
d
etec
t
m
u
ltip
l
e
f
o
r
g
er
ies
p
r
esen
t
i
n
t
h
e
i
m
a
g
e
a
n
d
to
d
etec
t
p
r
ec
is
e
f
o
r
g
er
y
in
e
x
tr
e
m
el
y
s
a
m
e
ar
e
as,
I
C
-
MFD
s
i
n
[
3
7
]
,
[
4
2
]
n
ee
d
s
to
s
o
m
e
i
m
p
r
o
v
e
m
e
n
t.
Ne
v
er
th
eles
s
,
s
ele
cti
n
g
th
e
b
est f
ea
tu
r
e
e
x
tr
ac
tio
n
m
et
h
o
d
s
an
d
ef
f
ec
ti
v
e
m
atch
in
g
te
ch
n
iq
u
e
w
ill ea
s
il
y
u
n
v
e
il f
o
r
g
er
y
.
I
t
ca
n
al
s
o
b
e
o
b
s
er
v
ed
t
h
at
d
etec
tio
n
ac
c
u
r
ac
y
o
f
I
C
-
M
F
Ds
b
ased
o
n
f
r
eq
u
en
c
y
d
o
m
ai
n
b
ased
o
n
T
etr
o
let
tr
an
s
f
o
r
m
[
2
6
]
o
u
tp
er
f
o
r
m
s
t
h
e
o
th
er
f
r
eq
u
e
n
c
y
d
o
m
ai
n
in
cl
u
d
in
g
W
av
elet,
DC
T
,
an
d
Fo
u
r
ier
.
B
ased
o
n
all
p
o
s
s
ib
le
d
ir
ec
tio
n
s
at
ea
ch
b
lo
ck
lev
el,
a
n
i
m
ag
e
ca
n
b
e
r
ep
r
esen
ted
v
er
y
well
b
y
th
e
T
etr
o
let
tr
an
s
f
o
r
m
.
T
h
is
m
o
ti
v
ate
s
u
s
to
m
e
n
tio
n
th
e
c
u
r
v
ele
t
tr
an
s
f
o
r
m
.
C
u
r
v
elet
h
a
s
a
co
m
m
o
n
ch
ar
ac
ter
is
tic
s
th
a
t
d
is
tin
g
u
is
h
es
it
f
r
o
m
t
h
e
o
th
e
r
ty
p
es
o
f
tr
an
s
f
o
r
m
s
ar
e
h
i
g
h
er
d
ir
ec
tio
n
al
s
en
s
iti
v
it
y
an
d
lo
w
er
r
ed
u
n
d
an
c
y
[
4
1
]
.
A
cc
o
r
d
in
g
to
th
e
ab
o
v
e
-
m
en
t
io
n
ed
d
is
ti
n
g
u
i
s
h
in
g
f
e
atu
r
es,
t
h
is
m
a
k
es
t
h
e
C
u
r
v
e
let
tr
an
s
f
o
r
m
i
s
a
n
in
ter
esti
n
g
ca
n
d
id
ate
f
o
r
I
C
-
MFDs
.
Ma
n
y
I
C
-
MFD
a
lg
o
r
i
th
m
s
b
a
s
ed
o
n
b
lo
c
k
-
b
ased
m
et
h
o
d
s
h
a
v
e
b
ee
n
p
r
o
p
o
s
ed
d
u
r
in
g
t
h
e
p
r
ev
io
u
s
d
ec
ad
e.
Fu
r
t
h
er
m
o
r
e,
t
h
eir
g
r
ea
test
d
r
a
w
b
ac
k
is
th
e
co
n
s
u
m
p
tio
n
o
f
ti
m
e
a
n
d
r
eso
u
r
ce
s
,
u
n
d
etec
tab
le
b
i
g
s
c
alin
g
d
is
to
r
tio
n
,
w
h
ich
m
ak
e
s
th
e
m
i
n
ap
p
r
o
p
r
iate
f
o
r
ap
p
licatio
n
s
s
u
ch
as
s
o
cial
n
et
w
o
r
k
s
,
w
h
er
e
a
lar
g
e
n
u
m
b
er
o
f
p
h
o
to
s
ar
e
ex
ch
an
g
ed
ev
er
y
d
a
y
.
4.
IC
-
M
F
D
AL
G
O
RI
T
H
M
S B
ASE
D
M
ACH
I
NE
-
CRAF
T
E
D
F
E
A
T
UR
E
S
T
h
er
e
ar
e
m
a
n
y
tec
h
n
iq
u
es
b
ased
o
n
m
a
n
u
al
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
.
I
n
o
r
d
er
to
r
ed
u
ce
th
e
u
s
e
o
f
m
an
u
a
l
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
a
n
e
w
ter
m
h
a
s
e
m
er
g
e
d
w
h
ic
h
is
a
u
to
m
atic
f
ea
tu
r
e
e
x
tr
ac
tio
n
.
d
ee
p
lear
n
in
g
is
a
n
au
to
m
at
ic
f
ea
t
u
r
e
ex
tr
ac
tio
n
co
n
d
u
cted
au
to
m
a
ticall
y
to
lear
n
f
ea
t
u
r
es
f
r
o
m
r
a
w
d
ata
(
i
m
ag
es).
Ma
n
y
o
f
th
e
tr
ad
itio
n
al
I
C
-
M
FDs
r
el
y
o
n
f
o
u
r
p
h
ases
li
k
e
p
r
e
-
p
r
o
ce
s
s
in
g
(
o
p
tio
n
al)
,
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
,
m
atc
h
i
n
g
a
n
d
v
is
u
aliza
t
io
n
(
o
p
tio
n
al)
,
W
h
ile
I
C
-
MFD
s
b
ased
d
ee
p
lear
n
in
g
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
m
atc
h
in
g
i
n
teg
r
ated
i
n
to
o
n
e
o
p
ti
m
izatio
n
s
tep
as s
h
o
wn
in
Fig
u
r
e
4
.
C
o
n
v
en
t
io
n
al
i
m
a
g
e
f
o
r
g
er
y
d
etec
tio
n
m
et
h
o
d
s
f
o
r
th
e
b
o
th
b
lo
ck
b
ased
an
d
k
e
y
p
o
in
t
b
ased
m
et
h
o
d
s
u
s
e
h
a
n
d
cr
af
ted
f
ea
tu
r
es.
h
o
w
e
v
er
,
th
e
m
o
s
t
o
f
th
e
co
n
v
e
n
tio
n
al
i
m
a
g
e
m
an
i
p
u
latio
n
d
etec
tio
n
tech
n
iq
u
es
h
as
w
ea
k
n
es
s
p
o
in
ts
s
u
ch
a
s
:
(
i)
h
i
g
h
co
m
p
u
tatio
n
al
co
m
p
le
x
it
y
,
(
ii)
li
m
ited
to
d
ef
in
e
a
p
ar
tic
u
lar
k
in
d
o
f
m
a
n
ip
u
lat
io
n
b
y
id
en
tify
i
n
g
a
p
ar
ticu
lar
f
ea
t
u
r
es
i
n
t
h
e
i
m
a
g
e,
(
iii)
t
h
e
s
m
o
o
t
h
in
g
f
o
r
g
er
y
s
ec
tio
n
ca
n
n
o
t
b
e
co
v
er
ed
b
y
t
h
e
k
e
y
p
o
in
t
-
b
ased
tech
n
iq
u
e.
Dee
p
lear
n
in
g
ap
p
r
o
ac
h
es
h
a
v
e
latel
y
b
ee
n
p
r
o
p
o
s
ed
f
o
r
th
e
i
m
a
g
e
ta
m
p
er
in
g
d
etec
tio
n
.
B
ec
au
s
e
o
f
it
’
s
a
o
w
in
g
t
h
e
ca
p
ac
it
y
to
e
x
tr
ac
t
c
o
m
p
licate
d
f
ea
tu
r
e
s
f
r
o
m
t
h
e
i
m
a
g
e,
it
also
co
n
s
u
m
es
les
s
ti
m
e
an
d
en
er
g
y
n
ee
d
ed
to
d
eter
m
in
e
h
an
d
-
cr
af
ted
f
ea
tu
r
es,
th
ese
m
et
h
o
d
s
ac
h
iev
ed
b
etter
p
er
f
o
r
m
a
n
ce
t
h
an
co
n
v
e
n
tio
n
a
l
m
et
h
o
d
s
.
T
h
e
t
y
p
es
o
f
d
ee
p
lear
n
in
g
(
DL
)
m
o
d
els
ar
e
co
n
v
o
lu
tio
n
a
l
n
e
u
r
al
n
e
t
w
o
r
k
s
(
C
NN)
,
d
e
ep
n
eu
r
al
n
et
w
o
r
k
(
DNN)
,
r
ec
u
r
r
en
t
n
e
u
r
al
n
et
w
o
r
k
(
R
NN)
,
d
ee
p
b
elief
n
et
w
o
r
k
[
5
6
]
,
an
d
d
ee
p
au
to
en
co
d
er
[
5
7
]
.
Am
o
n
g
t
h
ese
D
L
m
o
d
els,
c
o
n
v
o
l
u
tio
n
al
n
e
u
r
al
n
et
w
o
r
k
s
(
C
NN)
[
5
8
]
is
co
m
m
o
n
.
C
o
n
v
o
l
u
tio
n
la
y
er
is
i
m
p
o
r
tan
t
C
NN
la
y
er
t
h
at
is
c
o
n
s
id
er
ed
as
d
is
ti
n
g
u
i
s
h
i
n
g
a
n
d
f
ea
tu
r
e
e
x
tr
ac
to
r
.
Usi
n
g
t
h
e
v
ar
io
u
s
la
y
er
s
,
t
h
e
C
NN
p
ip
eli
n
e
s
tar
t
t
h
e
f
ea
t
u
r
e
s
ex
tr
ac
tio
n
p
r
o
ce
s
s
to
e
x
tr
ac
t
th
e
b
est
f
ea
t
u
r
e
f
r
o
m
t
h
e
i
m
a
g
e
a
n
d
t
h
en
in
p
u
ts
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
22
,
No
.
2
,
Ma
y
2
0
2
1
:
1
1
7
7
-
1
1
9
0
1186
th
e
m
i
n
to
th
e
b
asic
clas
s
i
f
ier
to
d
etec
t
th
e
co
p
y
-
m
o
v
e
f
o
r
g
er
y
i
f
it
o
cc
u
r
.
T
ab
le
5
lis
ts
v
ar
io
u
s
p
r
ev
io
u
s
r
ec
en
tl
y
o
f
I
C
-
MFD
s
class
if
ie
d
b
ased
o
n
m
ac
h
i
n
e
-
cr
a
f
ted
f
e
atu
r
es.
T
ab
le
5
.
P
r
ev
io
u
s
o
f
I
C
-
MFD
s
class
i
f
ied
b
ased
o
n
m
ac
h
in
e
-
c
r
af
ted
f
ea
t
u
r
es
R
e
f
.
Y
e
a
r
D
e
scri
p
t
i
o
n
D
e
e
p
L
e
a
r
n
i
n
g
M
e
t
h
o
d
L
i
mi
t
a
t
i
o
n
L
a
y
e
r
s
No
DB
R
a
o
a
n
d
N
i
,
[
4
6
]
,
2
0
1
6
.
C
M
F
D
b
a
se
d
o
n
C
N
N
s
i
s
p
r
o
p
o
se
d
.
C
N
N
T
h
e
r
e
su
l
t
s st
i
l
l
n
e
e
d
t
o
i
mp
r
o
v
e
.
10
C
A
S
I
A
v
1
.
0
,
C
A
S
I
A
v
2
.
0
,
C
o
l
u
mb
i
a
g
r
a
y
DVM
M
Z
h
a
n
g
e
t
a
l
.
,
[
4
7
]
,
2
0
1
6
.
C
M
F
D
b
a
se
d
o
n
S
t
a
c
k
e
d
-
A
u
t
o
e
n
c
o
d
e
r
s (S
A
E)
i
s p
r
o
p
o
se
d
.
S
t
a
c
k
e
d
-
A
u
t
o
e
n
c
o
d
e
r
s
(
S
A
E)
T
h
e
r
e
su
l
t
s
st
i
l
l
n
e
e
d
t
o
i
mp
r
o
v
e
.
7
C
A
S
I
A
v
1
.
0
,
C
A
S
I
A
v
2
.
0
,
C
o
l
u
mb
i
a
Ju
n
l
i
n
e
t
a
l
.
,
[
4
8
]
,
2
0
1
7
.
C
M
F
D
b
a
se
d
o
n
C
N
N
s
i
s
p
r
o
p
o
se
d
.
C
N
N
A
l
e
x
N
e
t
P
o
o
r
p
e
r
f
o
r
man
c
e
i
n
v
a
r
i
o
u
s re
a
l
sce
n
a
r
i
o
s.
T
h
e
r
e
su
l
t
s
n
e
e
d
t
o
i
mp
r
o
v
e
.
8
U
C
I
D
,
O
X
F
O
R
D
f
l
o
w
e
r
,
a
n
d
C
M
F
D
D
a
v
i
d
e
e
t
a
l
.
,
[
4
9
]
,
2
0
1
7
.
C
M
F
D
b
a
se
d
o
n
si
m
p
l
e
c
o
n
st
r
a
i
n
e
d
C
N
N
i
s
p
r
o
p
o
se
d
.
C
o
n
st
r
a
i
n
e
d
C
N
N
F
e
w
t
r
a
i
n
i
n
g
se
t
,
r
o
b
u
s
t
t
o
me
d
i
a
n
f
i
l
t
e
r
i
n
g
,
G
a
u
ssi
a
n
b
l
u
r
r
i
n
g
,
n
o
i
se
,
r
e
si
z
i
n
g
,
a
n
d
JP
EG
c
o
mp
r
e
ssi
o
n
.
-
S
y
n
t
h
e
t
i
c
W
u
e
t
a
l
.
,
[
5
0
]
,
2
0
1
8
.
C
M
F
D
b
a
se
d
o
n
B
u
st
e
r
N
e
t
a
n
e
n
d
t
o
e
n
d
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
i
s
p
r
o
p
o
se
d
.
B
u
s
t
e
r
N
e
t
(
D
e
e
p
N
e
u
r
a
l
N
e
t
w
o
r
k
)
W
e
a
k
i
n
p
u
r
e
t
e
x
t
u
r
e
i
mag
e
.
-
C
A
S
I
A
v
2
.
0
,
C
o
M
o
F
o
D
d
a
t
a
se
t
Y
u
e
e
t
a
l
.
,
[
5
1
]
,
2
0
1
8
C
M
F
D
b
a
se
d
o
n
a
n
e
n
d
-
to
-
e
n
d
D
N
N
i
s
p
r
o
p
o
se
d
.
D
e
e
p
N
e
u
r
a
l
N
e
t
w
o
r
k
T
h
e
r
e
su
l
t
s
st
i
l
l
n
e
e
d
t
o
i
mp
r
o
v
e
.
-
C
A
S
I
A
T
I
D
E
v
2
.
0
D
a
t
a
se
t
Y
o
u
n
i
s
e
t
a
l
.
,
[
5
2
]
,
2
0
1
9
.
C
M
F
D
b
a
se
d
o
n
sca
l
e
v
a
r
i
a
n
t
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
(
S
V
C
N
N
s)
i
s
p
r
o
p
o
se
d
.
C
N
N
O
v
e
r
a
l
l
e
f
f
e
c
t
i
v
e
n
e
ss
w
a
s rel
a
t
i
v
e
l
y
p
o
o
r
.
P
o
st
-
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
n
o
t
c
o
v
e
r
e
d
.
15
I
M
D
M
I
C
C
-
F
6
0
0
C
I
F
A
R
-
10
C
a
l
t
e
c
h
-
1
0
1
W
a
n
g
e
t
a
l
.
,
[
5
3
]
,
2
0
1
9
.
C
M
F
D
b
a
se
d
o
n
m
a
sk
r
e
g
i
o
n
a
l
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
(
M
a
s
k
R
-
C
N
N
)
i
s
p
r
o
p
o
se
d
.
M
a
s
k
R
e
g
i
o
n
a
l
C
N
N
O
n
l
y
r
o
b
u
st
t
o
JP
EG
c
o
mp
r
e
ssi
o
n
a
n
d
R
e
si
z
i
n
g
.
-
C
o
v
e
r
,
C
o
l
u
mb
i
a
M
o
h
a
me
d
e
t
a
l
.
,
[
5
4
]
,
2
0
2
0
.
C
M
F
D
b
a
se
d
o
n
C
N
N
s
i
s
p
r
o
p
o
se
d
.
C
N
N
P
o
st
-
p
r
o
c
e
ssi
n
g
o
p
e
r
a
t
i
o
n
s
n
o
t
c
o
v
e
r
e
d
.
14
M
I
C
C
-
F
2
2
0
,
M
I
C
C
-
F
2
0
0
0
,
a
n
d
M
I
C
C
-
F
6
0
0
Ju
n
-
L
i
u
a
n
d
P
u
n
,
[
5
5
]
,
2
0
2
0
.
C
M
F
D
b
a
se
d
o
n
a
D
e
n
se
-
I
n
c
e
p
t
i
o
n
N
e
t
i
s
p
r
o
p
o
se
d
.
D
e
e
p
N
e
u
r
a
l
N
e
t
w
o
r
k
(DNN)
T
h
e
r
e
su
l
t
s
st
i
l
l
n
e
e
d
t
o
i
mp
r
o
v
e
.
24
F
A
U
,
C
A
S
I
A
C
M
F
D
,
a
n
d
C
o
mo
f
o
d
n
e
w
4
.
1
.
C
o
nv
o
lutio
na
l neura
l net
w
o
rk
s
(
CNN
)
o
v
er
v
ie
w
C
NN
h
as
latel
y
b
ec
o
m
e
v
er
y
s
u
cc
e
s
s
f
u
l
b
ased
o
n
i
ts
lear
n
i
n
g
ab
ilit
ies
to
ex
tr
ac
t
th
e
ch
ar
ac
ter
is
tics
o
f
a
n
i
m
a
g
e.
T
h
ese
ab
ilit
ies
m
ak
e
it
C
NN
m
o
r
e
s
u
itab
le
t
o
b
e
u
s
ed
in
i
m
a
g
e
r
ec
o
g
n
itio
n
,
p
r
o
ce
s
s
i
n
g
tas
k
s
,
an
d
I
C
-
MFDs.
T
h
e
co
m
p
o
n
e
n
ts
o
f
m
an
y
C
NN
m
o
d
els
ar
e
(
1
)
a
co
m
b
in
a
tio
n
o
f
o
n
e
i
n
p
u
t
an
d
o
u
tp
u
t
la
y
er
,
(
2
)
a
f
e
w
co
n
v
o
l
u
tio
n
la
y
er
s
,
an
d
(
3
)
f
u
ll
y
co
n
n
ec
ted
la
y
e
r
s
.
Her
e
a
b
r
ief
l
y
ex
p
lai
n
t
h
e
m
ec
h
a
n
i
s
m
o
f
t
h
e
C
NN
ar
e
p
r
esen
ted
.
Firstl
y
,
a
n
i
m
a
g
e
i
s
d
escr
ib
ed
as
p
ix
el
m
atr
i
x
an
d
f
ed
t
h
e
m
to
t
h
e
in
p
u
t
la
y
er
.
T
h
e
o
u
tp
u
t
m
atr
i
x
is
g
e
n
er
ated
b
y
t
h
e
s
u
m
m
atio
n
o
f
m
u
ltip
l
y
th
e
i
n
p
u
t
m
atr
ix
a
n
d
f
il
ter
v
al
u
es.
A
f
t
e
r
w
a
r
d
s
,
a
p
o
o
l
i
n
g
o
p
e
r
a
t
i
o
n
i
s
p
e
r
f
o
r
m
e
d
.
M
a
x
,
a
v
e
r
a
g
e
o
r
g
l
o
b
a
l
-
p
o
o
l
i
n
g
c
a
n
b
e
u
s
e
d
f
o
r
p
o
o
l
i
n
g
.
T
h
e
f
e
a
t
u
r
e
m
a
p
t
h
a
t
i
s
p
a
s
s
e
d
i
n
t
o
t
h
e
i
n
p
u
t
a
n
d
t
h
e
o
u
t
p
u
t
l
a
y
e
r
i
s
g
e
n
e
r
a
t
e
d
b
y
a
p
p
l
y
i
n
g
t
h
e
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
t
o
t
h
e
i
n
p
u
t
.
T
h
e
r
e
a
r
e
c
o
m
m
o
n
l
y
u
s
e
d
a
c
t
i
v
a
t
i
o
n
f
u
n
c
t
i
o
n
s
s
u
c
h
a
s
r
e
l
u
,
s
i
g
m
o
i
d
,
a
n
d
t
a
n
h
.
I
n
C
N
N
,
t
h
e
p
o
o
l
i
n
g
l
a
y
e
r
t
h
a
t
b
e
e
n
u
s
e
d
t
o
m
i
n
i
m
i
z
e
t
h
e
d
a
t
a
d
i
m
e
n
s
i
o
n
.
T
h
e
n
t
h
e
o
u
t
p
u
t
p
a
s
s
e
d
t
o
t
h
e
n
e
x
t
i
n
p
u
t
l
a
y
e
r
a
n
d
s
o
l
v
i
n
g
t
h
e
p
r
o
b
l
e
m
o
f
o
v
e
r
f
i
t
t
i
n
g
b
y
l
o
s
i
n
g
s
o
m
e
i
n
f
o
r
m
a
t
i
o
n
.
A
f
t
e
r
a
l
l
t
h
e
s
e
s
e
q
u
e
n
c
e
s
o
f
h
i
d
d
e
n
a
n
d
p
o
o
l
i
n
g
l
a
y
e
r
s
,
t
h
e
d
a
t
a
p
a
s
s
e
s
t
h
r
o
u
g
h
a
v
a
r
i
o
u
s
f
u
l
l
y
c
o
n
n
e
c
t
e
d
l
a
y
e
r
s
w
h
e
n
c
l
a
s
s
i
f
i
c
a
t
i
o
n
i
s
d
o
n
e
.
F
i
n
a
l
l
y
,
t
h
e
e
r
r
o
r
i
s
m
e
a
s
u
r
e
d
i
n
t
h
e
o
u
t
p
u
t
l
a
y
e
r
,
w
h
i
c
h
i
s
t
h
e
n
p
r
o
p
a
g
a
t
e
d
b
a
c
k
w
a
r
d
t
h
r
o
u
g
h
t
h
e
n
e
t
w
o
r
k
t
o
c
h
a
n
g
e
t
h
e
f
i
l
t
e
r
w
e
i
g
h
t
s
.
T
h
u
s
,
t
o
m
i
n
i
m
i
z
e
t
h
e
e
r
r
o
r
a
n
d
t
r
a
i
n
t
h
e
n
e
t
w
o
r
k
,
a
s
e
q
u
e
n
c
e
o
f
f
e
e
d
f
o
r
w
a
r
d
a
n
d
b
a
c
k
p
r
o
p
a
g
a
t
i
o
n
i
s
p
e
r
f
o
r
m
e
d
.
4
.
2
.
C
o
m
pa
riso
n o
f
ic
-
m
f
d t
ec
hn
iq
ues
F
o
r
c
o
m
p
a
r
i
s
o
n
,
T
a
b
l
e
6
d
i
s
p
l
a
y
s
t
h
e
r
e
s
u
l
t
s
f
o
r
I
C
-
M
F
D
s
r
e
l
y
o
n
m
a
c
h
i
n
e
-
c
r
a
f
t
e
d
f
e
a
t
u
r
e
s
.
I
t
c
a
n
b
e
n
o
t
e
d
t
h
a
t
I
C
-
M
F
D
s
r
e
l
y
o
n
C
N
N
S
u
r
p
a
s
s
e
d
a
l
l
p
r
e
v
i
o
u
s
s
t
a
t
e
o
f
t
h
e
a
r
t
I
C
-
M
F
D
s
m
e
t
h
o
d
s
t
h
a
t
r
e
l
i
e
d
o
n
m
a
c
h
i
n
e
-
Evaluation Warning : The document was created with Spire.PDF for Python.