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.
8
,
No
.
6
,
Dec
em
b
er
201
8
,
p
p
.
5
0
3
2
~
5
0
4
0
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v8
i
6
.
pp
50
3
2
-
50
4
0
5032
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Sha
pe and Lev
el
Bo
tt
les De
tec
tion
U
sing
Lo
ca
l St
a
n
da
rd
Dev
ia
tion a
nd
H
o
ug
h Tra
nsfo
r
m
No
r
Na
bil
a
h Sy
a
za
na
Abdu
l R
a
h
m
a
n
1
,
No
rha
s
hi
m
a
h
M
o
hd
Sa
a
d
2
,
Abd
ul Ra
hi
m
A
bd
ull
a
h
3
1,
2
F
a
c
u
lt
y
o
f
El
e
c
tro
n
ic an
d
Co
m
p
u
ter E
n
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
lay
sia
M
e
lak
a
,
M
a
la
y
sia
2,
3
Ce
n
ter f
o
r
Ro
b
o
ti
c
s a
n
d
I
n
d
u
str
ial
A
u
to
m
a
ti
o
n
,
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
lay
sia
M
e
lak
a
,
M
a
la
y
sia
3
F
a
c
u
lt
y
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
si
a
M
e
lak
a
,
M
a
la
y
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Feb
2
3
,
2
0
1
8
R
ev
i
s
ed
J
u
l
19
,
2
0
1
8
A
cc
ep
ted
J
u
l 2
2
,
2
0
1
8
T
h
is
p
a
p
e
r
p
re
se
n
ts
sh
a
p
e
a
n
d
le
v
e
l
a
n
a
l
y
sis
u
sin
g
lo
c
a
l
sta
n
d
a
rd
d
e
v
iatio
n
a
n
d
Ho
u
g
h
tran
sf
o
rm
tec
h
n
iq
u
e
t
o
d
e
tec
t
th
e
sh
a
p
e
a
n
d
lev
e
l
o
f
th
e
b
o
tt
le.
A
1
5
5
sa
m
p
le
im
a
g
e
s
a
re
u
se
d
a
s
a
tes
t
p
r
o
d
u
c
t
t
o
d
e
tec
t
sh
a
p
e
a
n
d
l
e
v
e
l.
L
o
c
a
l
sta
n
d
a
rd
d
e
v
iatio
n
is u
se
d
c
o
n
tras
t
g
a
in
tec
h
n
iq
u
e
to
se
g
m
e
n
t
th
e
sh
a
p
e
o
f
th
e
b
o
tt
le
b
y
e
n
h
a
n
c
in
g
th
e
c
o
n
tras
t
o
f
th
e
i
m
a
g
e
.
T
h
e
ra
ti
o
o
f
t
h
e
a
re
a
is
c
a
lcu
late
d
f
ro
m
th
e
e
x
ten
t
p
a
ra
m
e
ter.
T
h
e
m
a
x
i
m
u
m
a
n
d
m
in
im
u
m
w
a
ter
lev
e
l
is
c
re
a
ted
b
y
u
si
n
g
Ho
u
g
h
tran
sf
o
r
m
tec
h
n
iq
u
e
t
o
id
e
n
ti
fy
th
e
lev
e
l
o
f
th
e
w
a
ter.
De
c
isio
n
tree
is
a
p
p
li
e
d
to
c
las
sify
th
e
sh
a
p
e
a
n
d
lev
e
l
o
f
th
e
b
o
tt
le
e
it
h
e
r
g
o
o
d
o
r
d
e
f
e
c
t
c
o
n
d
it
io
n
.
F
ro
m
e
x
p
e
ri
m
e
n
tal
re
su
lt
,
9
7
%
a
n
d
9
3
%
a
c
c
u
ra
c
y
o
f
sh
a
p
e
a
n
d
lev
e
l
is
a
c
h
iev
e
d
w
h
ich
sh
o
w
s
th
a
t
t
h
e
p
ro
p
o
se
d
a
n
a
ly
sis
tec
h
n
iq
u
e
is
p
o
te
n
ti
a
l
to
b
e
a
p
p
li
e
d
f
o
r
b
e
v
e
ra
g
e
s
p
ro
d
u
c
t
in
sp
e
c
ti
o
n
s
y
ste
m
.
K
ey
w
o
r
d
:
Au
to
m
a
ted
in
s
p
ec
tio
n
Ho
u
g
h
tr
an
s
f
o
r
m
L
e
v
el
d
etec
tio
n
L
o
ca
l sta
n
d
ar
d
d
ev
ia
tio
n
Sh
ap
e
d
etec
tio
n
Co
p
y
rig
h
t
©
2
0
1
8
I
n
stit
u
te o
f
Ad
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
:
No
r
h
ash
i
m
a
h
Mo
h
d
Saad
,
Facu
lt
y
o
f
E
lectr
o
n
ic
an
d
C
o
m
p
u
ter
E
n
g
i
n
ee
r
i
n
g
,
Un
i
v
er
s
iti
T
ek
n
ik
al
Ma
la
y
s
ia
Me
lak
a
,
Han
g
T
u
ah
J
a
y
a,
7
6
1
0
0
Du
r
ian
T
u
n
g
g
al,
Me
la
k
a,
Ma
la
y
s
ia
.
E
m
ail:
n
o
r
h
as
h
i
m
a
h
@
u
te
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
u
s
tr
ie
s
s
u
c
h
as
tex
tile,
s
e
m
ico
n
d
u
cto
r
,
f
o
o
d
an
d
b
ev
er
ag
es
h
a
v
e
ag
r
ee
d
th
at
a
s
y
s
t
e
m
b
ased
ap
p
r
o
ac
h
is
m
o
r
e
e
f
f
icien
t
an
d
s
u
s
tain
ab
le
to
b
e
ap
p
lied
in
m
a
n
u
f
ac
t
u
r
i
n
g
p
r
o
ce
s
s
[
1
]
.
Vis
u
a
l
i
n
s
p
ec
tio
n
is
ca
teg
o
r
ized
in
to
t
w
o
,
w
h
ic
h
ar
e
m
a
n
u
al
in
s
p
ec
tio
n
a
n
d
au
to
m
atic
i
n
s
p
ec
tio
n
.
Ma
n
u
al
in
s
p
ec
tio
n
is
co
m
m
o
n
l
y
u
s
ed
h
u
m
an
as
i
n
s
p
ec
to
r
f
o
r
p
r
o
d
u
ct
q
u
alit
y
[
2
]
.
T
h
e
s
tu
d
y
m
ad
e
b
y
[
3
]
h
av
e
s
h
o
w
n
th
e
m
a
n
u
al
in
s
p
ec
tio
n
p
er
f
o
r
m
ed
b
y
h
u
m
an
o
p
er
ato
r
is
in
e
f
f
icien
t
an
d
co
n
s
u
m
e
m
o
r
e
tim
e
d
u
e
to
w
o
r
k
i
n
g
co
n
d
iti
o
n
.
T
h
e
task
g
iv
e
n
b
y
in
d
u
s
tr
y
is
r
ep
etiti
v
e
a
n
d
d
if
f
icu
lt
to
d
o
if
n
o
p
r
o
p
er
tr
ain
in
g
is
co
n
d
u
cted
.
A
n
a
u
to
m
ati
c
in
s
p
ec
tio
n
s
ee
m
s
to
b
e
b
etter
co
m
p
ar
ed
to
m
a
n
u
al
i
n
s
p
ec
tio
n
.
Fo
r
th
ese
r
e
aso
n
,
th
e
ap
p
licatio
n
o
f
a
n
a
u
to
m
ated
i
n
s
p
ec
tio
n
s
y
s
te
m
f
o
r
d
etec
tio
n
an
d
class
if
icatio
n
o
f
d
ef
ec
t
is
d
esira
b
le
[
4
]
.
T
h
e
ap
p
licatio
n
o
f
an
au
t
o
m
a
ted
in
s
p
ec
tio
n
h
as r
ed
u
ce
d
ex
ec
u
tio
n
t
i
m
e,
c
o
m
p
u
tatio
n
al
co
s
t a
n
d
h
ig
h
p
e
r
ce
n
tag
e
er
r
o
r
f
r
ee
[
5
]
.
So
m
e
r
e
v
ie
w
s
ar
e
m
ad
e
f
r
o
m
p
r
ev
io
u
s
r
e
s
ea
r
ch
to
co
m
p
ar
e
th
e
i
n
s
p
ec
tio
n
s
y
s
te
m
tech
n
iq
u
e.
R
esear
ch
er
i
n
[
6
]
p
r
o
p
o
s
ed
s
h
ap
e
d
etec
tio
n
u
s
i
n
g
a
p
ar
tial
er
o
s
io
n
-
b
ased
tec
h
n
iq
u
e
to
a
u
to
m
ate
th
e
s
h
ap
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
o
f
p
last
ic
b
o
ttle.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
in
v
o
l
v
ed
m
o
r
p
h
o
lo
g
ical
an
d
er
o
s
io
n
p
r
o
ce
s
s
to
s
eg
m
e
n
t
t
h
e
b
o
ttle
s
h
ap
e
a
n
d
ex
tr
ac
t
t
h
e
f
ea
t
u
r
es
f
r
o
m
t
h
e
s
eg
m
e
n
ted
i
m
a
g
e.
T
h
e
ac
cu
r
a
c
y
o
f
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
s
m
o
r
e
t
h
an
8
0
%.
Ho
w
e
v
er
,
th
e
p
ar
tial
er
o
s
io
n
-
b
ased
tech
n
iq
u
e
i
s
i
n
e
f
f
icien
t
an
d
g
i
v
e
b
ad
e
f
f
ec
t
to
th
e
i
m
a
g
e
w
h
en
t
h
e
p
ar
tial
er
o
s
io
n
is
s
et
le
s
s
t
h
an
5
0
%
o
r
m
o
r
e
th
an
1
0
0
%
.
T
h
e
s
tatis
tic
al
h
is
to
g
r
a
m
b
ase
d
Fu
zz
y
C
-
m
ea
n
s
(
SHF
C
M)
is
s
u
g
g
e
s
ted
b
y
[
3
]
to
id
en
tify
th
e
ap
p
le
d
ef
ec
t
f
o
r
f
r
u
it
q
u
alit
y
in
s
p
ec
tio
n
.
SHFC
M
is
u
s
ed
to
class
i
f
y
th
e
h
ea
lt
h
y
a
n
d
d
ef
ec
t
ap
p
le.
T
h
e
ex
p
er
i
m
en
ta
l
r
esu
lt
s
h
o
w
s
t
h
e
ac
cu
r
ac
y
ac
h
iev
ed
b
y
h
ea
lth
y
ap
p
le
is
9
6
%
an
d
d
ef
ec
t
ap
p
le
is
9
1
%.
Nev
er
th
ele
s
s
,
SHF
C
M
is
t
h
e
co
m
b
i
n
atio
n
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
h
a
p
e
a
n
d
Leve
l B
o
ttles
Dete
ctio
n
u
s
in
g
Lo
ca
l
S
ta
n
d
a
r
d
Dev
ia
tio
n
a
n
d
Ho
u
g
h
…
(
N
o
r
h
a
s
h
ima
h
M
.
S
.
)
5033
s
tatis
t
ical
h
i
s
to
g
r
a
m
an
d
f
u
zz
y
c
-
m
ea
n
s
w
h
ic
h
m
ak
e
s
t
h
e
alg
o
r
ith
m
m
o
r
e
co
m
p
lex
a
n
d
p
r
o
n
e
to
m
i
s
clas
s
i
f
ied
h
ea
lt
h
y
a
n
d
d
ef
ec
t a
p
p
le.
Fo
r
lev
el
d
etec
tio
n
,
liq
u
id
le
v
el
i
n
s
p
ec
tio
n
s
y
s
te
m
h
a
s
b
e
en
d
ev
elo
p
ed
b
y
[
7
]
b
ased
o
n
i
n
f
in
ite
s
y
m
m
etr
ical
ed
g
e
f
ilter
(
I
SEF)
d
etec
tio
n
tech
n
i
q
u
e
to
r
ep
lace
tr
ad
itio
n
al
q
u
alit
y
i
n
s
p
e
ctio
n
p
er
f
o
r
m
b
y
a
h
u
m
a
n
o
p
er
ato
r
.
T
h
e
p
r
o
ce
s
s
in
cl
u
d
es
i
m
ag
e
cr
o
p
p
in
g
a
n
d
n
o
r
m
alizi
n
g
,
f
il
ter
in
g
an
d
d
et
ec
tin
g
.
T
h
e
an
al
y
s
is
r
esu
lt
s
s
h
o
w
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
i
s
b
etter
d
etec
tio
n
o
f
o
v
er
f
il
l
an
d
u
n
d
er
f
ill
f
o
r
liq
u
id
lev
el.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
is
n
o
t
s
u
itab
le
f
o
r
th
e
q
u
alit
y
i
m
ag
e
b
ec
a
u
s
e
it
w
il
l
o
v
er
s
eg
m
e
n
t
t
h
e
i
m
a
g
e.
Fu
r
th
er
m
o
r
e,
[
8
]
p
r
o
p
o
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
ed
g
e
d
etec
tio
n
alg
o
r
it
h
m
t
o
in
s
p
ec
t
f
ill
le
v
el
a
n
d
ca
p
in
b
o
ttli
n
g
m
ac
h
i
n
e
.
C
las
s
i
f
icatio
n
o
f
li
q
u
id
le
v
el
a
n
d
ca
p
clo
s
u
r
e
is
d
o
n
e
b
y
u
s
i
n
g
n
e
u
r
al
n
e
t
w
o
r
k
(
NN)
tech
n
i
q
u
e.
T
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
p
r
o
v
es
th
a
t
it
ca
n
i
n
s
p
ec
t
liq
u
id
le
v
el
an
d
ca
p
o
f
b
o
ttle
ac
cu
r
atel
y
.
Nev
er
t
h
ele
s
s
,
lo
w
er
o
r
e
m
p
t
y
liq
u
id
lev
el
ca
n
n
o
t b
e
d
etec
ted
an
d
to
o
m
a
n
y
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
w
i
ll r
ed
u
ce
th
e
i
m
a
g
e
q
u
alit
y
.
B
ased
o
n
liter
atu
r
e,
t
w
o
m
ai
n
p
r
o
b
le
m
s
t
h
at
o
cc
u
r
d
u
r
i
n
g
b
ev
er
ag
e
b
o
ttle
q
u
a
lit
y
i
n
s
p
ec
tio
n
ar
e
h
ig
h
li
g
h
ted
.
First,
t
h
e
u
s
ed
o
f
m
an
u
al
i
n
s
p
ec
tio
n
is
h
i
g
h
l
y
p
r
o
n
e
to
h
u
m
an
er
r
o
r
.
Seco
n
d
is
an
i
n
ap
p
r
o
p
r
iate
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
tech
n
iq
u
e
c
h
o
s
en
is
h
i
g
h
l
y
p
r
o
n
e
to
u
n
d
e
r
o
r
o
v
er
s
eg
m
e
n
tatio
n
,
o
n
t
h
e
o
th
er
h
a
n
d
lead
to
lo
s
s
o
f
p
r
ec
is
io
n
.
Hen
ce
,
t
h
is
p
ap
er
p
r
o
p
o
s
ed
a
n
ew
a
n
al
y
s
is
tech
n
iq
u
e
o
f
s
h
ap
e
an
d
lev
el
f
o
r
b
ev
er
ag
e
s
q
u
alit
y
in
s
p
ec
tio
n
s
y
s
te
m
u
s
i
n
g
lo
ca
l
s
ta
n
d
ar
d
d
ev
iatio
n
a
n
d
Ho
u
g
h
tr
a
n
s
f
o
r
m
.
T
h
e
co
n
tr
ast
e
n
h
an
ce
m
e
n
t
tech
n
iq
u
e
p
r
o
v
id
e
b
y
L
SD
w
il
l
g
i
v
e
d
if
f
er
en
t
co
n
tr
as
t
lev
el
in
o
r
d
er
to
p
r
ev
en
t
f
r
o
m
u
n
d
er
an
d
o
v
er
s
eg
m
e
n
tatio
n
o
f
t
h
e
i
m
a
g
e.
T
h
u
s
,
t
h
e
s
h
ap
e
o
f
th
e
i
m
a
g
e
ca
n
b
e
s
e
g
m
en
ted
ac
c
u
r
atel
y
co
m
p
ar
ed
to
p
r
ev
io
u
s
tech
n
iq
u
e
,
an
d
p
r
ac
ticall
y
ap
p
r
o
p
r
iated
f
o
r
in
d
u
s
tr
ial
r
ea
l
-
ti
m
e
i
n
s
p
ec
tio
n
s
y
s
te
m
[9
]
.
Me
an
w
h
ile,
Ho
u
g
h
tr
an
s
f
o
r
m
i
s
p
r
o
p
o
s
ed
b
ec
au
s
e
o
f
its
r
o
b
u
s
t
n
ess
to
n
o
is
e
an
d
ca
p
ab
ilit
y
to
d
etec
t
l
in
e
w
ith
o
u
t
e
n
o
u
g
h
in
f
o
r
m
atio
n
,
in
ac
co
r
d
an
ce
ac
h
iev
ed
b
etter
ac
c
u
r
ac
y
i
n
d
etec
tin
g
m
u
ltip
le
o
b
j
ec
t
co
m
p
ar
ed
to
o
th
er
s
p
r
ev
io
u
s
tech
n
iq
u
e
[
1
0
]
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
an
al
y
s
i
s
o
f
s
h
ap
e
an
d
lev
el
d
ef
ec
t
d
etec
tio
n
is
d
o
n
e
u
s
in
g
th
e
M
A
T
L
A
B
s
o
f
t
w
ar
e.
T
h
e
f
r
a
m
e
w
o
r
k
an
a
l
y
s
i
s
o
f
s
h
ap
e
a
n
d
lev
el
d
etec
tio
n
is
s
h
o
w
n
i
n
Fig
u
r
e
1
.
A
1
0
0
s
am
p
le
i
m
a
g
e
s
is
u
s
ed
f
o
r
s
h
ap
e
d
ef
ec
t
d
etec
tio
n
an
d
5
5
s
am
p
l
e
i
m
ag
e
s
f
o
r
lev
el
d
ef
ec
t
d
ete
ctio
n
.
T
h
e
s
a
m
p
le
i
m
a
g
e
is
ca
p
tu
r
ed
u
s
in
g
C
a
n
o
n
D3
1
0
0
d
ig
ital
ca
m
er
a
w
i
th
1
2
m
e
g
ap
ix
el
s
.
T
h
en
,
t
h
e
ca
p
t
u
r
ed
i
m
a
g
e
is
p
r
e
-
p
r
o
ce
s
s
ed
to
eli
m
i
n
ate
th
e
n
o
is
e
an
d
en
h
a
n
ce
t
h
e
b
r
ig
h
tn
e
s
s
o
f
th
e
i
m
ag
e
f
o
r
f
u
r
th
er
an
a
l
y
s
is
.
Fig
u
r
e
1
.
Fra
m
e
w
o
r
k
an
a
l
y
s
is
2
.
1
.
P
re
-
P
ro
ce
s
s
ing
P
r
e
-
p
r
o
ce
s
s
in
g
is
a
co
m
m
o
n
o
p
er
atio
n
to
s
tan
d
ar
d
ized
th
e
i
m
a
g
e
in
o
r
d
er
to
m
i
n
i
m
ize
t
h
e
co
m
p
le
x
it
y
o
f
th
e
al
g
o
r
ith
m
[
1
1
]
.
T
h
e
n
o
is
e
o
cc
u
r
o
n
th
e
i
m
ag
e
m
a
y
g
i
v
e
co
m
p
lex
it
y
d
u
r
in
g
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
.
B
esid
es,
th
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e
is
g
i
v
e
n
s
i
m
ilar
g
r
a
y
lev
e
l
v
a
lu
e
s
w
it
h
ce
r
ta
in
b
o
ttle
s
tr
u
ct
u
r
es.
T
h
er
ef
o
r
e,
p
r
e
-
p
r
o
ce
s
s
in
g
is
c
ar
r
ied
o
u
t to
co
r
r
ec
t th
e
i
m
a
g
e
f
o
r
f
u
r
t
h
er
an
al
y
s
is
.
S
h
a
p
e
L
e
v
e
l
S
a
mp
l
e
i
mag
e
Pre
-
p
r
o
c
e
ssi
n
g
S
e
g
me
n
t
a
t
i
o
n
(
L
S
D
)
H
e
i
g
h
t
W
i
d
t
h
A
r
e
a
Ex
t
e
n
t
H
o
u
g
h
T
r
a
n
sf
o
r
m
M
a
x
i
m
u
m
l
e
v
e
l
M
i
n
i
m
u
m
l
e
v
e
l
L
e
v
e
l
D
e
c
i
si
o
n
T
r
e
e
C
l
a
ssi
f
i
e
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
6
,
Dec
em
b
er
2
0
1
8
:
5
0
3
2
-
50
4
0
5034
2
.
2
.
Seg
m
e
nta
t
io
n us
ing
L
o
c
a
l St
a
nd
a
rd
Dev
ia
t
io
n
T
h
e
L
o
ca
l
Stan
d
ar
d
Dev
iatio
n
(
L
SD)
is
p
ar
t
o
f
th
e
A
d
ap
ti
v
e
C
o
n
tr
ast
E
n
h
a
n
ce
m
e
n
t
(
A
C
E
)
f
u
n
c
tio
n
to
s
eg
m
e
n
t
t
h
e
s
h
ap
e
o
f
th
e
i
m
ag
e.
A
C
E
is
k
n
o
w
n
a
s
a
n
u
n
s
h
ar
p
m
a
s
k
i
n
g
tec
h
n
iq
u
e
w
h
er
e
th
e
f
u
n
ctio
n
i
s
ap
p
lied
at
th
e
u
n
s
h
ar
p
m
as
k
t
o
am
p
li
f
y
t
h
e
i
m
a
g
e
w
h
ic
h
h
as
lo
w
-
f
r
eq
u
e
n
c
y
co
m
p
o
n
e
n
t
s
.
B
esid
es,
A
C
E
w
ill
ad
j
u
s
t th
e
co
n
tr
ast
g
ai
n
o
f
t
h
e
i
m
a
g
e
in
to
s
u
itab
le
v
alu
e.
T
h
e
g
en
er
al
eq
u
at
io
n
[
1
2
]
is
d
ef
in
ed
as
(
,
)
(
,
)
(
,
)
(
,
)
(
,
)
xx
f
i
j
m
i
j
G
i
j
x
i
j
m
i
j
=
+
−
(
1
)
w
h
er
e
(
,
)
x
m
i
j
=
is
th
e
lo
ca
l
m
ea
n
,
(
,
)
G
i
j
=
is
th
e
co
n
tr
ast
g
ain
an
d
(
,
)
x
i
j
=
is
g
r
a
y
s
c
ale
v
al
u
e
at
an
y
p
o
in
t o
f
th
e
i
m
a
g
e
p
ix
el.
I
n
th
e
AC
E
,
th
e
f
u
n
c
tio
n
o
f
L
SD
is
to
en
h
a
n
ce
t
h
e
co
n
tr
ast
g
ain
o
f
t
h
e
i
m
ag
e
f
r
o
m
lo
w
to
h
ig
h
a
n
d
h
ig
h
to
lo
w
[
1
3
]
.
T
h
e
r
in
g
i
n
g
an
d
n
o
is
e
r
es
u
lt
m
a
y
o
cc
u
r
i
f
t
h
e
co
n
tr
a
s
t
g
ain
is
s
et
m
a
n
u
a
ll
y
.
AC
E
f
u
n
cti
o
n
i
s
in
v
er
s
el
y
p
r
o
p
o
r
tio
n
al
to
L
S
D
m
a
k
e
t
h
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e
ca
n
b
e
id
e
n
ti
f
ied
an
d
e
li
m
i
n
ated
at
t
h
e
ed
g
e
o
f
b
o
ttle.
T
h
e
u
n
w
an
ted
co
n
tr
ast
g
ain
in
t
h
e
i
m
a
g
e
is
el
i
m
in
ate
d
b
y
e
n
h
a
n
ci
n
g
th
e
co
n
tr
ast
g
a
in
f
r
o
m
lo
w
to
h
i
g
h
u
s
i
n
g
L
SD f
u
n
ctio
n
[
1
4
]
.
T
h
e
f
u
n
ctio
n
o
f
L
SD i
s
ex
p
r
ess
ed
as
(
,
)
(
,
)
(
,
)
(
,
)
(
,
)
xx
x
D
f
i
j
m
i
j
x
i
j
m
i
j
ij
=
+
−
(
2
)
w
h
er
e
D
is
a
co
n
s
tan
t
v
al
u
e
f
o
r
co
n
tr
ast
an
d
(
,
)
X
ij
is
a
f
u
n
ct
i
o
n
o
f
L
SD.
Fro
m
eq
u
atio
n
(
1
)
,
th
e
co
n
tr
ast
g
ai
n
is
a
u
to
m
a
ticall
y
co
n
tr
o
lled
b
y
t
h
e
(
,
)
X
ij
.
T
h
er
ef
o
r
e,
f
o
r
th
e
r
eg
io
n
th
at
h
as
s
m
al
l
(
,
)
x
m
i
j
=
lead
s
t
o
an
u
n
e
x
p
ec
ted
l
y
h
i
g
h
v
alu
e
o
f
L
SD a
n
d
v
ice
v
er
s
a
.
2
.
3
.
H
o
ug
h T
ra
ns
f
o
r
m
Ho
u
g
h
tr
an
s
f
o
r
m
is
ap
p
lied
f
o
r
th
e
b
in
ar
y
i
m
a
g
e
to
d
etec
t
th
e
lin
e
s
o
f
th
e
w
a
ter
lev
el
in
th
e
b
o
ttle.
T
h
e
w
h
ite
p
i
x
els
i
n
th
e
i
m
ag
e
h
as
cr
ea
ted
a
lo
cu
s
o
f
r
ef
er
en
ce
p
o
in
ts
t
h
at
ac
cu
m
u
lated
in
ac
cu
m
u
lato
r
ar
r
a
y
o
f
Ho
u
g
h
s
p
ac
e.
T
h
e
v
o
tin
g
p
r
o
ce
s
s
is
in
v
o
lv
ed
f
o
r
lin
e
d
ete
ctio
n
w
h
er
e
ev
er
y
p
i
x
el
in
t
h
e
i
m
a
g
e
v
o
tes
f
o
r
all
p
o
s
s
ib
le
lin
e
co
r
r
esp
o
n
d
in
g
to
r
ef
er
en
ce
p
o
in
t.
A
li
n
e
is
p
as
s
in
g
t
h
r
o
u
g
h
s
ev
er
al
f
ea
tu
r
e
p
o
in
ts
a
n
d
m
a
x
i
m
u
m
p
o
in
t
w
h
ic
h
h
a
v
e
i
n
d
icate
d
as
r
ef
er
en
ce
p
o
in
ts
i
n
t
h
e
Ho
u
g
h
s
p
ac
e.
Gen
er
all
y
,
(
,
)
s
p
ac
e
is
co
n
v
er
ted
in
to
(
,
)
s
p
ac
e
w
h
ich
ca
n
b
e
ex
p
r
ess
ed
as
c
o
s
s
i
n
xy
=+
(
3
)
w
h
er
e
is
th
e
len
g
t
h
o
f
th
e
lin
e
f
r
o
m
t
h
e
o
r
ig
in
.
is
t
h
e
a
n
g
le
o
f
th
e
w
it
h
r
esp
ec
t
to
t
h
e
x
d
i
r
ec
tio
n
.
Fi
g
u
r
e
2
s
h
o
w
s
th
e
co
n
v
er
s
io
n
o
f
s
p
ac
e
in
to
(
,
)
s
p
ac
e
w
h
er
e
th
e
li
n
e
s
ar
e
cr
ea
ted
b
ased
o
n
s
ev
er
al
p
o
in
ts
in
o
r
d
er
t
o
f
in
d
th
e
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
v
al
u
e
.
Fig
u
r
e
2
.
C
r
ea
ted
lin
es
u
s
i
n
g
Ho
u
g
h
tr
an
s
f
o
r
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
h
a
p
e
a
n
d
Leve
l B
o
ttles
Dete
ctio
n
u
s
in
g
Lo
ca
l
S
ta
n
d
a
r
d
Dev
ia
tio
n
a
n
d
Ho
u
g
h
…
(
N
o
r
h
a
s
h
ima
h
M
.
S
.
)
5035
2
.
4
.
F
e
a
t
ure
E
x
t
ra
ct
io
n
I
n
i
m
ag
e
a
n
al
y
s
i
s
,
f
ea
tu
r
e
e
x
tr
ac
tio
n
is
r
eq
u
ir
ed
to
b
e
in
p
u
t
f
o
r
class
i
f
icat
io
n
p
r
o
ce
s
s
.
A
s
et
o
f
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
t
h
e
s
e
g
m
en
ted
i
m
a
g
e
s
b
ased
o
n
th
e
s
h
ap
e
an
d
le
v
el.
Fo
r
th
e
s
h
ap
e
f
ea
t
u
r
es,
p
ar
am
eter
s
s
u
c
h
as
h
ei
g
h
t,
w
id
t
h
,
ar
ea
an
d
ex
te
n
t
ar
e
ex
tr
ac
ted
.
Me
an
w
h
ile,
th
e
w
a
ter
lev
el
f
ea
t
u
r
e
i
s
ex
tr
ac
ted
b
y
f
in
d
i
n
g
t
h
e
m
a
x
i
m
u
m
an
d
m
i
n
i
m
u
m
v
al
u
e
o
f
w
ater
lev
el.
T
h
ese
f
ea
t
u
r
es
ar
e
im
p
o
r
tan
t
t
o
class
i
f
y
th
e
d
ef
ec
t o
f
t
h
e
i
m
a
g
e.
2
.
4
.
1.
Sh
a
pe
Det
ec
t
io
n
Fo
u
r
p
ar
a
m
eter
s
ar
e
ex
tr
ac
ted
in
s
h
ap
e
f
ea
t
u
r
es,
w
h
ic
h
ar
e
h
eig
h
t,
w
id
t
h
,
ar
ea
an
d
ex
ten
t
.
Fig
u
r
e
3
s
h
o
w
s
th
e
d
i
m
e
n
s
io
n
o
f
t
h
e
b
o
u
n
d
i
n
g
b
o
x
i
n
t
h
e
b
i
n
ar
y
i
m
ag
e
t
h
at
is
u
s
ed
to
o
b
tain
th
e
ar
ea
o
f
th
e
b
o
ttle
.
B
ased
o
n
Fig
u
r
e
3
,
th
e
h
eig
h
t
o
f
th
e
i
m
ag
e
is
d
eter
m
i
n
ed
as
4
1
6
0
p
ix
els
w
h
ile
th
e
w
id
t
h
is
o
b
tain
ed
as
3
1
2
0
p
ix
els.
T
h
e
ar
ea
o
f
th
e
b
o
ttle
is
ca
lcu
lated
b
ased
o
n
th
e
w
h
it
e
p
ix
el.
I
n
d
eter
m
i
n
in
g
t
h
e
ex
t
en
t
v
al
u
e,
t
h
e
ar
ea
o
f
th
e
o
b
j
ec
t
is
d
iv
id
ed
w
i
th
t
h
e
ar
ea
o
f
th
e
b
o
u
n
d
i
n
g
b
o
x
i
n
o
r
d
er
to
class
if
y
th
e
s
h
ap
e
d
ef
ec
t
o
f
t
h
e
b
o
ttle.
T
h
e
ex
ten
t
v
alu
e
i
s
ca
lcu
lated
as f
o
llo
w
s
A
r
e
a
o
f
o
b
j
e
t
E
x
t
e
n
t
A
r
e
a
o
f
b
o
u
n
d
x
c
i
n
g
b
o
=
(
4
)
T
h
e
w
h
ite
p
i
x
el
h
as
r
ep
r
ese
n
ted
th
e
s
h
ap
e
o
f
t
h
e
b
o
ttle
wh
ile
t
h
e
b
lac
k
p
ix
e
l
is
t
h
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e
as
illu
s
tr
ated
in
Fig
u
r
e
3
.
Hen
ce
,
th
e
ar
ea
o
f
th
e
o
b
j
ec
t
is
d
eter
m
i
n
ed
b
y
th
e
v
al
u
e
o
f
th
e
w
h
ite
p
ix
el.
I
n
ad
d
itio
n
,
th
e
ar
ea
o
f
th
e
b
o
u
n
d
in
g
b
o
x
is
o
b
tain
ed
f
r
o
m
m
u
ltip
licatio
n
v
al
u
e
o
f
h
ei
g
h
t
an
d
w
id
t
h
th
at
ca
n
b
e
ex
p
r
ess
ed
as
A
re
a
of
bo
un
ding
bo
x
he
ight
x
wi
dth
=
(
5
)
Fig
u
r
e
3
.
B
o
u
n
d
i
n
g
b
o
x
d
i
m
e
n
s
io
n
2
.
4
.
2.
L
ev
el
Det
ec
t
io
n
T
h
e
w
ater
le
v
el
f
ea
t
u
r
e
h
as
b
ee
n
ex
tr
ac
ted
u
s
i
n
g
Ho
u
g
h
tr
an
s
f
o
r
m
t
h
at
cr
ea
ted
th
e
tan
g
en
t
lin
e
f
o
r
th
e
m
ea
s
u
r
e
m
e
n
t
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
m
a
x
i
m
u
m
a
n
d
m
in
i
m
u
m
v
al
u
es.
Fi
g
u
r
e
4
s
h
o
w
s
th
e
m
ax
i
m
u
m
an
d
m
i
n
i
m
u
m
li
n
e
o
f
t
h
e
w
ater
lev
el.
E
ac
h
lev
el
o
f
w
a
ter
h
as b
ee
n
lab
eled
th
at
is
il
lu
s
tr
ated
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
L
ab
el
f
o
r
lev
el
o
f
w
a
ter
3
1
2
0
4
1
6
0
0
ℎ
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
6
,
Dec
em
b
er
2
0
1
8
:
5
0
3
2
-
50
4
0
5036
T
h
e
lev
el
o
f
w
a
ter
is
class
i
f
ie
d
in
th
r
ee
co
n
d
itio
n
s
,
w
h
ich
ar
e
g
o
o
d
,
o
v
er
f
illed
an
d
u
n
d
er
f
i
lled
.
Fro
m
Fig
u
r
e
4
,
th
e
lev
el
o
f
w
ater
,
y
is
ca
lcu
lated
f
r
o
m
th
e
d
is
tan
ce
b
et
w
ee
n
m
a
x
i
m
u
m
(
)
an
d
m
i
n
i
m
u
m
(
)
as
f
o
r
m
u
lated
i
n
eq
u
at
io
n
(
6
)
.
T
h
e
an
d
v
alu
e
ar
e
s
e
t
b
ased
o
n
th
e
g
o
o
d
co
n
d
itio
n
v
a
lu
e
o
f
t
h
e
b
o
ttle.
T
h
e
co
n
d
itio
n
is
g
o
o
d
w
h
e
n
th
e
lev
e
l
is
b
et
w
ee
n
t
h
e
an
d
,
I
f
th
e
le
v
el
i
s
ab
o
v
e
t
h
a
n
,
it
w
il
l c
o
n
s
id
er
as o
v
er
f
illed
.
Ot
h
er
w
is
e,
i
f
th
e
le
v
el
i
s
b
elo
w
t
h
an
,
th
e
co
n
d
itio
n
i
s
u
n
d
er
f
il
l
ed
.
m
a
x
m
in
y
x
x
=−
(
6
)
2
.
5
.
Dec
is
io
n T
re
e
Cla
s
s
if
ier
I
n
o
r
d
er
to
class
if
y
th
e
d
e
f
ec
t
o
f
s
h
ap
e
a
n
d
lev
el,
d
ec
is
io
n
tr
ee
is
i
m
p
le
m
e
n
ted
in
t
h
i
s
s
t
u
d
y
.
T
h
e
tr
ee
co
n
s
is
ts
o
f
b
r
an
c
h
es,
n
o
d
es
an
d
leav
es
th
at
ar
e
u
s
ed
f
o
r
t
h
e
class
i
f
icatio
n
p
r
o
ce
s
s
.
B
r
an
ch
es
o
f
th
e
tr
ee
ar
e
in
d
icate
d
as
v
alu
e
s
w
h
i
le
n
o
d
es
ar
e
r
ep
r
e
s
en
ted
as
th
e
n
a
m
e
o
f
d
ata.
T
h
e
lab
els
o
f
th
e
class
ar
e
s
h
o
w
n
b
y
t
h
e
leaf
[
1
5
]
.
Fig
u
r
e
5
illu
s
tr
ate
s
th
e
tr
ain
i
n
g
s
et
o
f
d
ec
is
io
n
tr
ee
p
r
o
ce
s
s
th
at
in
clu
d
e
s
s
h
ap
e
an
d
lev
el
c
lass
i
f
icatio
n
.
B
ased
o
n
Fig
u
r
e
5
,
th
e
d
ec
is
io
n
tr
ee
m
o
d
el
lear
n
s
th
e
ex
tr
ac
ted
f
ea
t
u
r
es
o
f
t
h
e
b
o
ttle,
w
h
ic
h
ar
e
ex
ten
t v
a
lu
ea
n
d
lev
e
l.
I
f
t
h
e
f
e
atu
r
e
is
th
e
e
x
te
n
t
v
al
u
e,
th
e
s
h
ap
e
o
f
t
h
e
b
o
ttle
w
ill
b
e
class
if
ied
eit
h
er
g
o
o
d
o
r
d
ef
ec
t
co
n
d
itio
n
.
W
h
en
th
e
f
e
atu
r
e
is
th
e
lev
el
v
al
u
e,
th
e
w
a
ter
lev
el
is
class
i
f
ied
in
to
th
r
ee
co
n
d
itio
n
s
s
u
c
h
as
g
o
o
d
,
o
v
er
f
illed
an
d
u
n
d
er
f
ille
d
.
Fig
u
r
e
5
.
Dec
is
io
n
tr
ee
p
r
o
ce
s
s
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
Fig
u
r
e
6
s
h
o
w
s
f
o
u
r
d
if
f
er
en
t
co
lo
r
s
o
f
b
o
ttles
w
ith
th
e
s
a
m
e
s
ize
an
d
le
v
el
ar
e
u
s
ed
in
t
h
is
an
al
y
s
is
as r
ef
er
en
ce
i
m
a
g
e.
Fig
u
r
e
6
.
R
ef
er
en
ce
i
m
a
g
e
L
o
ca
l
s
ta
n
d
ar
d
d
ev
iatio
n
(
L
S
D)
u
s
e
s
co
n
tr
ast
e
n
h
an
ce
m
e
n
t
tech
n
iq
u
e
to
s
e
g
m
e
n
t
t
h
e
s
h
ap
e
o
f
th
e
b
o
ttle.
T
h
e
s
eg
m
en
tatio
n
o
f
t
h
e
b
o
ttle
is
ap
p
lied
to
class
if
y
t
h
e
s
h
ap
e
co
n
d
itio
n
eit
h
er
g
o
o
d
o
r
d
ef
ec
t.
Fig
u
r
e
F
e
a
tu
re
Ex
trac
ti
o
n
Ex
ten
t
v
a
lu
e
L
e
v
e
l
v
a
lu
e
≤
Ex
ten
t
≤
Ex
ten
t
<
Ex
ten
t
>
L
e
v
e
l
G
o
o
d
Un
d
e
rf
il
led
Ov
e
r
f
il
led
L
e
v
e
l
<
≤
L
e
v
e
l
≤
L
e
v
e
l
>
S
h
a
p
e
G
o
o
d
De
fe
c
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
h
a
p
e
a
n
d
Leve
l B
o
ttles
Dete
ctio
n
u
s
in
g
Lo
ca
l
S
ta
n
d
a
r
d
Dev
ia
tio
n
a
n
d
Ho
u
g
h
…
(
N
o
r
h
a
s
h
ima
h
M
.
S
.
)
5037
7
(
a)
to
Fig
u
r
e
7
(
d
)
s
h
o
w
s
th
e
s
h
ap
e
an
al
y
s
is
p
r
o
c
ess
f
o
r
th
e
d
ef
ec
t
b
o
ttle.
T
h
e
p
r
o
ce
s
s
is
s
tar
ted
w
it
h
th
e
co
n
v
er
s
io
n
o
f
r
ed
,
g
r
ee
n
an
d
b
lu
e
(
R
GB
)
co
lo
r
i
m
ag
e
in
Fi
g
u
r
e
7
(
a)
in
to
a
g
r
a
y
s
ca
le
i
m
ag
e
i
n
Fi
g
u
r
e
7
(
b
)
.
T
h
e
co
n
v
er
s
io
n
p
r
o
ce
s
s
is
ap
p
lied
to
r
ed
u
ce
th
e
co
m
p
le
x
i
t
y
f
r
o
m
3
-
d
i
m
en
s
io
n
al
p
i
x
el
in
to
2
-
d
i
m
en
s
io
n
al
p
ix
el.
T
h
e
g
r
ay
s
ca
le
i
m
ag
e
is
th
en
tr
a
n
s
f
o
r
m
ed
in
to
s
ta
n
d
ar
d
d
ev
iatio
n
i
m
a
g
e
as
s
h
o
w
n
in
Fig
u
r
e
7
(
c)
.
I
n
th
i
s
p
r
o
ce
s
s
,
s
tan
d
ar
d
d
ev
iatio
n
al
g
o
r
ith
m
is
ap
p
lied
to
s
eg
m
en
t
th
e
s
h
ap
e
o
f
th
e
b
o
ttle
b
y
s
e
p
ar
atin
g
t
h
e
b
o
ttle
an
d
th
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e.
T
h
e
b
ac
k
g
r
o
u
n
d
n
o
is
e
at
t
h
e
ed
g
e
o
f
t
h
e
b
o
ttle
ca
n
b
e
r
e
m
o
v
ed
b
y
i
n
cr
ea
s
i
n
g
t
h
e
v
al
u
e
o
f
L
S
D
r
esu
lti
n
g
th
e
r
ed
u
ctio
n
o
f
co
n
tr
ast
g
ai
n
o
f
th
e
i
m
a
g
e.
T
h
er
ef
o
r
e,
th
e
s
h
ap
e
o
f
t
h
e
b
o
ttle
is
o
u
tlin
ed
u
s
i
n
g
t
h
e
w
h
ite
li
n
e
to
s
ep
ar
ate
b
etw
ee
n
th
e
s
h
ap
e
o
f
th
e
b
o
ttle
an
d
th
e
b
ac
k
g
r
o
u
n
d
i
m
a
g
e.
T
h
e
s
tan
d
ar
d
d
ev
iatio
n
i
m
a
g
e
is
co
n
v
er
ted
in
to
a
b
in
ar
y
i
m
ag
e
as
r
ep
r
esen
ted
in
Fig
u
r
e
7
(
d
)
,
in
w
h
ic
h
th
e
s
h
ap
e
o
f
th
e
b
o
ttle
is
p
r
esen
ted
in
w
h
ite
p
ix
el
(
1
)
w
h
ile
t
h
e
b
ac
k
g
r
o
u
n
d
i
m
ag
e
i
n
t
h
e
b
lack
p
ix
el
(
0
)
.
Fin
all
y
,
t
h
e
p
ar
a
m
eter
s
ex
tr
ac
ted
f
r
o
m
Fi
g
u
r
e
7
(
d
)
ar
e
u
s
ed
as
an
in
p
u
t
f
o
r
th
e
cla
s
s
i
f
icati
o
n
p
r
o
ce
s
s
.
Fo
u
r
p
ar
am
eter
s
n
a
m
el
y
h
ei
g
h
t,
w
id
th
,
ar
ea
,
an
d
ex
te
n
t
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
g
o
o
d
an
d
d
e
f
ec
t
s
h
ap
e
i
m
a
g
es.
T
h
e
ex
ten
t
p
ar
a
m
eter
i
s
ca
lcu
l
ated
b
ased
o
n
th
e
r
atio
o
f
th
e
b
o
ttle
ar
ea
an
d
th
e
b
o
u
n
d
i
n
g
b
o
x
ar
ea
th
at
s
tated
in
t
h
e
eq
u
atio
n
(
4
)
.
Fo
r
th
e
ar
ea
o
f
b
o
u
n
d
in
g
b
o
x
,
eq
u
atio
n
(
5
)
is
u
s
ed
b
y
m
u
ltip
l
y
i
n
g
th
e
h
ei
g
h
t
a
n
d
w
id
t
h
v
alu
e.
As
e
x
p
ec
ted
,
b
o
th
s
a
m
p
le
i
m
ag
e
s
h
av
e
s
i
m
ilar
ar
ea
o
f
b
o
u
n
d
i
n
g
b
o
x
b
u
t
d
if
f
er
e
n
t
v
alu
e
o
f
t
h
e
b
o
ttle
ar
ea
.
T
h
e
ar
ea
v
alu
e
f
o
r
g
o
o
d
b
o
ttle
w
as
h
ig
h
er
co
m
p
ar
ed
t
o
d
ef
ec
t
b
o
ttle
w
h
ic
h
th
e
n
in
f
lu
en
ce
d
th
e
ex
ten
t
v
alu
e.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
7
.
Sh
ap
e
d
etec
tio
n
p
r
o
ce
s
s
: (
a)
I
n
p
u
t s
tag
e,
(
b
)
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e,
(
c)
L
S
Dst
a
g
e,
(
d
)
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
e
T
h
e
i
m
p
le
m
e
n
tatio
n
o
f
Ho
u
g
h
tr
a
n
s
f
o
r
m
m
a
k
es
t
h
e
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
o
f
w
a
ter
lev
el
is
esti
m
ated
u
s
i
n
g
v
o
tin
g
p
r
o
ce
s
s
.
T
h
e
lev
el
d
ef
ec
t
d
etec
tio
n
p
r
o
ce
s
s
is
in
d
icate
d
in
Fig
u
r
e
8(
a)
to
Fig
u
r
e
8
(
d
)
.
T
h
e
s
a
m
p
le
o
f
r
ef
er
e
n
ce
i
m
a
g
e
i
n
F
ig
u
r
e
8
(
a)
is
co
n
v
er
te
d
i
n
to
g
r
a
y
s
ca
le
i
m
a
g
e.
T
h
en
,
L
SD
tech
n
iq
u
e
i
s
ap
p
lied
to
s
eg
m
en
t
t
h
e
le
v
el
o
f
t
h
e
w
a
ter
th
a
t
is
s
h
o
w
n
in
Fi
g
u
r
e
8
(
b
)
.
Fi
g
u
r
e
8
(
c)
ill
u
s
tr
at
es
t
h
e
s
e
v
er
al
li
n
e
s
cr
ea
ted
u
s
in
g
Ho
u
g
h
tr
an
s
f
o
r
m
tech
n
iq
u
e
to
f
in
d
t
h
e
m
a
x
i
m
u
m
a
n
d
m
i
n
i
m
u
m
le
v
el
v
a
lu
e
b
ased
o
n
th
e
w
h
it
e
p
ix
el
o
f
th
e
i
m
a
g
e.
T
h
e
lin
e
d
etec
tio
n
im
a
g
e
is
s
h
o
w
n
i
n
Fig
u
r
e
8
(
d
)
,
in
w
h
ic
h
th
e
b
lu
e
lin
e
p
r
esen
ts
m
i
n
i
m
u
m
le
v
el
a
n
d
t
h
e
r
ed
lin
e
i
n
d
icate
s
m
a
x
i
m
u
m
le
v
el.
T
h
e
p
r
o
ce
s
s
is
r
ep
ea
ted
f
o
r
o
v
er
f
i
lled
an
d
u
n
d
er
f
illed
co
n
d
itio
n
a
s
g
r
a
p
h
icall
y
s
h
o
w
s
i
n
Fi
g
u
r
e
9
(
a)
an
d
Fig
u
r
e
9
(
b
)
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
8
.
Go
o
d
lev
el
i
m
ag
e:
(
a
)
Sa
m
p
le
i
m
a
g
e,
(
b
)
s
eg
m
en
te
d
im
a
g
e,
(
c)
Ho
u
g
h
tr
an
s
f
o
r
m
i
m
a
g
e,
(
d
)
lin
e
d
etec
tio
n
i
m
a
g
e
Def
ec
t
Def
ec
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
6
,
Dec
em
b
er
2
0
1
8
:
5
0
3
2
-
50
4
0
5038
(
a)
(
b
)
Fig
u
r
e
9
.
L
ev
el
i
m
a
g
e:
(
a)
Un
d
er
f
illed
,
(
b
)
o
v
er
f
illed
I
n
o
b
tain
i
n
g
t
h
e
t
h
r
es
h
o
ld
v
a
lu
e
o
f
t
h
e
w
ater
le
v
el,
t
h
e
d
is
tan
ce
o
f
th
e
w
ater
lev
el
is
ca
lcu
lated
b
et
w
ee
n
t
h
e
m
a
x
i
m
u
m
an
d
m
in
i
m
u
m
lin
e
s
u
s
i
n
g
th
e
eq
u
ati
o
n
(
6
)
.
Fig
u
r
e
1
0
s
h
o
w
s
t
h
r
ee
m
is
c
lass
if
ied
o
f
x
n
o
d
e
(
r
ed
co
l
o
r
)
th
at
p
lo
tted
in
s
ca
tter
d
iag
r
a
m
.
I
n
d
ef
e
ct
co
n
d
itio
n
,
th
er
e
i
s
ca
s
e
w
h
er
e
d
ec
is
io
n
tr
ee
m
is
c
lass
if
ied
t
h
e
s
h
ap
e
o
f
t
h
e
b
o
ttle
as
g
o
o
d
co
n
d
itio
n
.
T
h
is
ca
s
e
w
ill
lead
to
in
ac
cu
r
ac
y
th
at
i
n
ap
p
r
o
p
r
iate
f
o
r
r
ea
l
ti
m
e
ap
p
licatio
n
.
Fig
u
r
e
1
1
illu
s
tr
ates
t
h
e
s
ca
tter
p
l
o
t
d
iag
r
a
m
s
th
a
t
class
i
f
y
th
e
s
a
m
p
le
i
m
a
g
e
b
ased
o
n
lev
el
co
n
d
itio
n
,
w
h
ic
h
ar
e
g
o
o
d
,
o
v
er
f
illed
an
d
u
n
d
er
f
illed
.
B
ased
o
n
Fig
u
r
e
1
1
,
th
e
d
ec
is
io
n
tr
ee
is
m
is
c
lass
i
f
ied
o
f
x
n
o
d
e
(
b
lu
e
co
lo
r
)
as
g
o
o
d
co
n
d
itio
n
.
T
h
e
ac
tu
al
class
o
f
th
e
m
i
s
class
i
f
ied
n
o
d
e
is
u
n
d
er
f
illed
an
d
o
v
er
f
illed
co
n
d
itio
n
.
Fig
u
r
e
1
0
.
Scatter
p
lo
t d
iag
r
a
m
o
f
s
h
ap
e
d
ef
ec
t c
las
s
i
f
icatio
n
u
s
in
g
L
SD te
c
h
n
iq
u
e
Fig
u
r
e
1
1
.
Scatter
p
lo
t d
iag
r
a
m
o
f
le
v
el
d
ef
ec
t
cla
s
s
i
f
icatio
n
u
s
i
n
g
Ho
u
g
h
tr
a
n
s
f
o
r
m
T
h
e
co
m
p
ar
is
o
n
in
ter
m
o
f
ac
cu
r
ac
y
f
o
r
s
h
ap
e
an
d
lev
el
d
e
tectio
n
tech
n
iq
u
e
s
ar
e
s
h
o
w
n
in
Fi
g
u
r
e
12
.
Fro
m
th
e
f
i
n
d
in
g
s
,
L
SD
te
ch
n
iq
u
e
s
h
o
w
s
t
h
e
h
ig
h
es
t
p
er
ce
n
tag
e
w
it
h
ac
cu
r
ac
y
9
7
%
f
o
llo
w
ed
b
y
S
HF
C
M
w
it
h
9
1
%
an
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
w
ith
8
0
%.
I
n
th
i
s
ca
s
e,
th
e
o
u
tco
m
e
u
s
i
n
g
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
is
er
r
o
r
p
r
o
n
e
,
n
o
t
to
m
e
n
tio
n
a
lar
g
e
d
if
f
er
e
n
t
o
f
1
7
%
co
m
p
ar
ed
to
L
SD
.
T
h
e
ai
m
f
o
r
lev
el
d
etec
tio
n
is
G
o
o
d
O
v
e
r
f
i
l
l
ed
M
i
s
c
l
a
ssi
f
i
e
d
U
n
d
e
r
f
i
l
l
e
d
D
e
f
e
c
t
G
o
o
d
M
i
s
c
l
a
ssi
f
i
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec&
C
o
m
p
E
n
g
I
SS
N:
2
0
8
8
-
8708
S
h
a
p
e
a
n
d
Leve
l B
o
ttles
Dete
ctio
n
u
s
in
g
Lo
ca
l
S
ta
n
d
a
r
d
Dev
ia
tio
n
a
n
d
Ho
u
g
h
…
(
N
o
r
h
a
s
h
ima
h
M
.
S
.
)
5039
fi
n
d
in
g
an
ap
p
r
o
p
r
iate
an
al
y
s
i
s
w
h
ic
h
ca
n
d
etec
t
le
v
el
o
f
liq
u
id
b
o
ttle
ac
cu
r
atel
y
.
He
n
ce
,
Ho
u
g
h
tr
a
n
s
f
o
r
m
h
a
s
p
r
o
v
en
th
at
it
ca
n
p
er
f
o
r
m
ab
s
o
lu
tel
y
w
e
ll
in
d
etec
ti
n
g
l
iq
u
i
d
lev
el
b
y
ac
h
ie
v
i
n
g
9
3
%
ac
cu
r
ac
y
u
s
i
n
g
d
ec
is
io
n
tr
ee
class
i
f
ier
.
Fig
u
r
e
1
2
.
P
er
f
o
r
m
an
ce
a
n
al
y
s
is
f
o
r
s
h
ap
e
an
d
lev
el
d
ef
ec
t d
etec
tio
n
4.
CO
NCLU
SI
O
N
I
n
th
is
p
ap
er
,
th
e
an
al
y
s
i
s
o
f
s
h
ap
e
an
d
lev
el
o
f
b
o
ttle
is
p
r
es
en
ted
u
s
i
n
g
lo
ca
l
s
tan
d
ar
d
d
ev
iatio
n
an
d
Ho
u
g
h
tr
an
s
f
o
r
m
.
T
h
e
an
al
y
s
i
s
in
v
o
lv
ed
p
r
e
-
p
r
o
ce
s
s
i
n
g
,
s
e
g
m
e
n
tat
io
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
class
i
f
icatio
n
.
T
h
e
s
a
m
p
le
i
m
a
g
e
i
s
p
r
e
-
p
r
o
ce
s
s
ed
to
eli
m
i
n
ate
t
h
e
n
o
is
e
t
h
at
o
cc
u
r
s
o
n
th
e
i
m
a
g
e
w
h
ic
h
g
iv
e
s
co
m
p
le
x
it
y
d
u
r
in
g
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
.
I
n
s
eg
m
e
n
ti
n
g
th
e
i
m
a
g
e,
L
S
D
tech
n
iq
u
e
i
s
ap
p
lied
b
y
e
n
h
an
cin
g
t
h
e
co
n
tr
as
t
g
ain
o
f
t
h
e
i
m
ag
e
f
r
o
m
lo
w
to
h
ig
h
.
Fo
r
s
h
ap
e
f
ea
t
u
r
es,
e
x
te
n
t
p
ar
a
m
eter
i
s
ca
lcu
la
ted
to
d
eter
m
i
n
e
th
e
r
atio
o
f
th
e
b
o
ttle
ar
ea
.
Me
an
w
h
il
e,
Ho
u
g
h
tr
a
n
s
f
o
r
m
is
u
s
ed
t
o
ex
tr
ac
t
th
e
f
ea
t
u
r
es
o
f
t
h
e
w
ater
le
v
el
s
u
ch
a
s
m
ax
i
m
u
m
a
n
d
m
i
n
i
m
u
m
lev
e
l.
T
h
e
d
ec
is
io
n
tr
ee
class
i
f
ier
is
ap
p
lied
to
class
i
f
y
t
h
e
s
h
a
p
e
an
d
lev
el
eit
h
er
g
o
o
d
o
r
d
ef
ec
t.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
o
p
o
s
ed
tech
n
iq
u
es
is
v
er
if
ied
in
ter
m
s
o
f
ac
cu
r
ac
y
.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lt
s
h
o
w
s
9
7
%
an
d
9
3
%
ac
c
u
r
ac
y
i
s
ac
h
iev
ed
b
y
s
h
ap
e
a
n
d
lev
e
l
d
etec
tio
n
.
T
h
u
s
,
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
s
d
e
m
o
n
s
tr
ate
th
e
p
o
ten
tial to
d
etec
t th
e
s
h
ap
e
an
d
lev
el
f
o
r
b
ev
er
ag
es p
r
o
d
u
ct
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
s
w
o
u
l
d
li
k
e
to
th
an
k
t
h
e
Un
i
v
er
s
iti
T
ek
n
i
k
al
Ma
la
y
s
ia
Me
la
k
a
(
UT
eM
)
,
U
T
e
M
Z
a
m
ala
h
Sch
e
m
e,
R
e
h
ab
ilit
atio
n
E
n
g
i
n
ee
r
in
g
&
Ass
i
s
ti
v
e
T
ec
h
n
o
lo
g
y
(
R
E
A
T
)
r
esear
ch
g
r
o
u
p
u
n
d
er
C
en
ter
o
f
R
o
b
o
tics
&
I
n
d
u
s
tr
ial
A
u
to
m
atio
n
(
C
e
R
I
A
)
,
A
d
v
a
n
ce
d
Dig
ital
Sig
n
al
P
r
o
ce
s
s
in
g
(
A
DSP
)
R
esear
ch
L
ab
o
r
ato
r
y
a
n
d
Mi
n
is
tr
y
o
f
Hig
h
er
E
d
u
ca
tio
n
(
MO
HE
)
,
Ma
la
y
s
ia
f
o
r
s
p
o
n
s
o
r
in
g
th
is
w
o
r
k
u
n
d
er
p
r
o
j
ec
t
GL
u
ar
/ST
E
VI
A
/2
0
1
6
/FKE
-
C
eRI
A
/l0
0009
an
d
th
e
u
s
e
o
f
t
h
e
ex
is
ti
n
g
f
ac
i
liti
es to
co
m
p
let
e
th
is
p
r
o
j
ec
t.
RE
F
E
R
E
NC
E
S
[1
]
K.B.
Kim
,
H.J
.
P
a
rk
a
n
d
D
.
H.
S
o
n
g
.
V
isio
n
-
b
a
se
d
Cra
c
k
Id
e
n
ti
f
i
c
a
ti
o
n
o
n
t
h
e
Co
n
c
re
te
S
lab
S
u
rf
a
c
e
u
sin
g
F
u
z
z
y
Re
a
so
n
in
g
Ru
les
a
n
d
S
e
lf
-
Org
a
n
izin
g
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
6
(
4
),
p
p
.
1
5
7
7
-
1
5
8
6
,
2
0
1
6
.
[2
]
N.N.S
.
A
.
Ra
h
m
a
n
,
S
a
a
d
,
N.M
.
S
a
a
d
,
A
.
R.
A
b
d
u
ll
a
h
,
M
.
R.
M
.
Ha
ss
a
n
,
M
.
S
.
S
.
M
.
Ba
sir
a
n
d
N.S
.
M
.
N
o
o
r.
A
u
to
m
a
ted
Re
a
l
-
T
i
m
e
V
isio
n
Qu
a
li
ty
In
sp
e
c
ti
o
n
M
o
n
i
to
ri
n
g
S
y
st
e
m
.
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ie
n
c
e
,
11
(
2
),
p
p
.
7
7
5
-
7
8
3
,
2
0
1
8
[3
]
G
.
M
o
ra
d
i,
M
.
S
h
a
m
si,
M
.
H.
S
e
d
a
a
g
h
i,
a
n
d
S
.
M
o
ra
d
i,
“
A
p
p
le
d
e
fe
c
t
d
e
tec
ti
o
n
u
si
n
g
sta
ti
stica
l
h
isto
g
ra
m
b
a
se
d
F
u
z
z
y
C
-
m
e
a
n
s a
lg
o
rit
h
m
”
,
In
st.
El
e
c
tr.
El
e
c
tro
n
.
En
g
.
,
p
p
.
1
1
–
1
5
,
2
0
1
1
.
[4
]
M
.
P
a
rk
,
J.S
.
Jin
,
S
.
L
.
A
u
,
S
.
Lu
o
,
a
n
d
Y.
Cu
i,
“
A
u
to
m
a
ted
De
fe
c
t
In
sp
e
c
ti
o
n
S
y
ste
m
b
y
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
”
,
Pro
c
.
5
t
h
I
n
t.
C
o
n
f
.
Ima
g
e
Gr
a
p
h
.
ICIG 2
0
0
9
,
v
o
l.
2
,
n
o
.
2
,
p
p
.
7
6
8
–
7
7
3
,
2
0
0
9
.
[5
]
M
.
A
.
M
.
F
u
a
d
,
M
.
R.
A
b
G
h
a
n
i.
,
R.
G
h
a
z
a
li
,
M
.
F
.
S
u
laim
a
,
M
.
H.
Ja
li
,
T
.
S
u
t
ik
n
o
,
T
.
A
.
Iz
z
u
d
d
in
a
n
d
Z.
Ja
n
o
.
“
A
Re
v
ie
w
o
n
M
e
th
o
d
s
o
f
Id
e
n
ti
fy
in
g
a
n
d
C
o
u
n
ti
n
g
A
e
d
e
s
A
e
g
y
p
ti
L
a
r
v
a
e
u
sin
g
Im
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
”
.
T
EL
KOM
NIKA
(
T
e
lec
o
mm
u
n
ica
ti
o
n
Co
mp
u
ti
n
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tro
l)
,
15
(3
),
p
p
.
1
1
9
9
-
1
2
0
6
,
2
0
1
7
.
[6
]
S
.
Ra
m
li
,
M
.
M
.
M
u
sta
f
a
,
A
.
Hu
ss
a
in
,
a
n
d
D.A
.
W
a
h
a
b
,
“
P
las
ti
c
B
o
tt
le
S
h
a
p
e
C
las
sif
ica
ti
o
n
Us
in
g
P
a
rti
a
l
Ero
si
o
n
-
b
a
se
d
A
p
p
ro
a
c
h
”
,
M
o
d
.
A
p
p
l
.
S
c
i.
,
v
o
l.
6
,
n
o
.
4
,
p
p
.
7
7
–
8
3
,
2
0
1
2
.
[7
]
K.J.
P
it
h
a
d
iy
a
,
C.
K.
M
o
d
i,
a
n
d
J.
D.
Ch
a
u
h
a
n
,
“
M
a
c
h
in
e
V
isi
o
n
B
a
se
d
L
iq
u
id
L
e
v
e
l
In
sp
e
c
ti
o
n
S
y
ste
m
u
sin
g
IS
EF
Ed
g
e
d
e
tec
ti
o
n
T
e
c
h
n
i
q
u
e
”
,
I
n
t.
Co
n
f.
W
o
rk
.
Eme
rg
.
T
re
n
d
s T
e
c
h
n
o
l.
(
ICW
ET
)
,
n
o
.
Ic
w
e
t,
p
p
.
6
0
1
–
6
0
5
,
2
0
1
0
.
[8
]
L
.
Ya
z
d
i,
A
.
S
.
P
ra
b
u
w
o
n
o
,
a
n
d
E
.
G
o
lk
a
r,
“
F
e
a
tu
re
e
x
trac
ti
o
n
a
lg
o
rit
h
m
f
o
r
f
il
l
lev
e
l
a
n
d
c
a
p
i
n
sp
e
c
ti
o
n
i
n
b
o
t
tl
in
g
m
a
c
h
in
e
”
,
Pro
c
.
2
0
1
1
I
n
t.
C
o
n
f
.
Pa
tt
e
rn
A
n
a
l.
I
n
tell.
R
o
b
o
t.
ICPA
IR
2
0
1
1
,
v
o
l.
1
,
n
o
.
Ju
n
e
,
p
p
.
4
7
–
5
2
,
2
0
1
1
.
80
91
97
93
0
20
40
60
80
1
0
0
M
o
r
p
h
o
l
o
g
i
c
a
l
O
p
e
r
a
t
i
o
n
…
S
H
F
C
M
[
3
]
LSD
H
o
u
g
h
Tr
a
n
sf
o
r
m
P
e
r
c
e
n
t
a
g
e
(
%)
A
c
c
u
ra
c
y
o
f
S
h
a
p
e
a
n
d
L
e
v
e
l
De
tec
ti
o
n
T
e
c
h
n
iq
u
e
s
S
h
a
p
e
Le
v
e
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2088
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
8
,
No
.
6
,
Dec
em
b
er
2
0
1
8
:
5
0
3
2
-
50
4
0
5040
[9
]
Y.
Ya
n
g
a
n
d
Z.
Zh
o
u
,
“
Re
se
a
rc
h
a
n
d
Im
p
lem
e
n
tatio
n
o
f
Im
a
g
e
En
h
a
n
c
e
m
e
n
t
A
lg
o
rit
h
m
Ba
se
d
o
n
L
o
c
a
l
M
e
a
n
a
n
d
S
tan
d
a
rd
De
v
iatio
n
”
,
IEE
E
S
y
mp
.
El
e
c
tr.
El
e
c
tro
n
.
En
g
.
,
p
p
.
3
7
5
–
3
7
8
,
2
0
1
2
.
[1
0
]
O.
Ba
rin
o
v
a
,
V
.
L
e
m
p
it
sk
y
,
a
n
d
P
.
Ko
h
li
,
“
On
d
e
tec
ti
o
n
o
f
m
u
lt
ip
le o
b
jec
t
in
sta
n
c
e
s u
si
n
g
Ho
u
g
h
tr
a
n
sf
o
r
m
”
,
IEE
E
T
ra
n
s.
Pa
tt
e
rn
An
a
l.
M
a
c
h
.
I
n
tell.
,
v
o
l.
3
4
,
n
o
.
9
,
p
p
.
1
7
7
3
–
1
7
8
4
,
2
0
1
0
.
[1
1
]
R.
P
e
re
ra
a
n
d
S
.
P
re
m
a
siri,
“
Ha
rd
w
a
r
e
I
m
p
le
m
e
n
tatio
n
o
f
Esse
n
ti
a
l
P
re
-
P
ro
c
e
ss
in
g
&
M
o
r
p
h
o
lo
g
ica
l
Op
e
ra
ti
o
n
s
i
n
Im
a
g
e
P
ro
c
e
ss
in
g
”
,
Na
tl
.
C
o
n
f
.
T
e
c
h
n
o
l.
M
a
n
a
g
.
,
p
p
.
3
–
7
,
2
0
1
7
.
[1
2
]
J.
X
ie,
Y.
Zh
o
u
a
n
d
L
.
Di
n
g
.
L
o
c
a
l
sta
n
d
a
rd
d
e
v
iatio
n
s
p
e
c
tral
c
lu
ste
rin
g
.
In
Bi
g
D
a
ta
a
n
d
S
ma
rt
Co
mp
u
ti
n
g
(
Bi
g
Co
mp
),
2
0
1
8
I
EE
E
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
(
p
p
.
2
4
2
-
2
5
0
).
IEE
E.
2
0
1
8
,
Ja
n
u
a
ry
.
[1
3
]
B.
S
.
P
ra
k
o
so
,
I.
K
.
T
im
o
ti
u
s,
a
n
d
I.
S
e
ty
a
w
a
n
,
“
P
a
lm
p
rin
t
Id
e
n
t
if
ica
ti
o
n
f
o
r
Us
e
r
V
e
rif
i
c
a
ti
o
n
b
a
se
d
o
n
L
in
e
De
tec
ti
o
n
a
n
d
L
o
c
a
l
S
tan
d
a
rd
De
v
iatio
n
”
,
2
0
1
4
1
st
In
t.
Co
n
f.
In
f
.
T
e
c
h
n
o
l
.
C
o
mp
u
t.
E
lec
tr.
En
g
.
Gr
e
e
n
T
e
c
h
n
o
l.
I
ts
Ap
p
l
.
a
Better
Fu
t
u
r.
ICI
T
ACE
E
2
0
1
4
-
Pro
c
.
,
p
p
.
1
5
5
–
1
5
9
,
2
0
1
4
.
[1
4
]
A
.
Ka
u
r
a
n
d
C.
S
i
n
g
h
.
C
o
n
tras
t
e
n
h
a
n
c
e
m
e
n
t
f
o
r
c
e
p
h
a
lo
m
e
tri
c
im
a
g
e
s
u
sin
g
w
a
v
e
let
-
b
a
se
d
m
o
d
if
ied
a
d
a
p
ti
v
e
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
.
A
p
p
li
e
d
S
o
ft
C
o
mp
u
ti
n
g
,
51
,
p
p
.
1
8
0
-
1
9
1
,
2
0
1
7
.
[1
5
]
V
.
S
.
T
a
ll
a
p
ra
g
a
d
a
,
D.M
.
Re
d
d
y
,
P
.
S
.
Kira
n
a
n
d
D.
V
.
Re
d
d
y
.
A
No
v
e
l
M
e
d
ica
l
I
m
a
g
e
S
e
g
m
e
n
tatio
n
a
n
d
Clas
sif
ic
a
ti
o
n
u
sin
g
Co
m
b
in
e
d
F
e
a
tu
re
S
e
t
a
n
d
De
c
isio
n
T
re
e
Clas
sif
ier.
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Res
e
a
rc
h
in
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
,
4
(
9
),
p
p
.
8
3
-
8
6
,
2
0
1
6
.
[1
6
]
S
.
A
.
L
u
d
w
ig
,
S
.
P
ice
k
a
n
d
D.
Ja
k
o
b
o
v
ic.
Clas
sif
ica
ti
o
n
o
f
Ca
n
c
e
r
Da
ta:
A
n
a
l
y
z
in
g
G
e
n
e
Ex
p
re
ss
io
n
Da
ta
Us
in
g
a
F
u
z
z
y
De
c
isio
n
T
re
e
A
lg
o
rit
h
m
.
In
Op
e
ra
ti
o
n
s
Res
e
a
rc
h
A
p
p
li
c
a
ti
o
n
s
in
He
a
l
th
C
a
re
M
a
n
a
g
e
me
n
t
(p
p
.
3
2
7
-
3
4
7
).
S
p
rin
g
e
r,
C
h
a
m
,
2
0
1
8
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
No
r
Na
b
il
a
h
S
y
a
z
a
n
a
b
in
ti
A
b
d
u
l
Ra
h
m
a
n
h
a
s
re
c
e
iv
e
d
h
e
r
B.
E
n
g
.
f
ro
m
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
sia
in
2
0
1
6
.
S
h
e
is
c
u
rre
n
t
ly
p
u
rsu
in
g
h
e
r
M
a
ste
r
E
n
g
.
in
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
sia
.
He
r
re
se
a
rc
h
a
re
a
s
a
re
in
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
c
o
m
p
u
ter
v
isio
n
f
o
r
p
ro
d
u
c
t
q
u
a
li
ty
in
sp
e
c
ti
o
n
s
y
ste
m
.
Dr.
No
rh
a
sh
im
a
h
b
i
n
ti
M
o
h
d
S
a
a
d
is
c
u
rre
n
tl
y
w
o
rk
in
g
a
s
a
s
e
n
io
r
lec
tu
re
r
i
n
De
p
a
rtm
e
n
t
Co
m
p
u
ter,
F
KEKK
,
UT
e
M
.
S
h
e
f
in
ish
e
d
h
e
r
stu
d
y
in
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
,
M
a
ste
r
o
f
En
g
in
e
e
rin
g
a
n
d
P
h
D
in
M
e
d
ica
l
Im
a
g
e
P
ro
c
e
ss
in
g
f
ro
m
UT
M
,
M
a
la
y
sia
.
A
s
so
c
iate
P
r
o
f
.
Dr.
A
b
d
u
l
Ra
h
i
m
b
in
A
b
d
u
ll
a
h
h
a
s
re
c
e
iv
e
d
h
i
s
B.
En
g
.
,
M
a
ste
r
E
n
g
.
,
P
h
D
De
g
re
e
f
ro
m
Un
iv
e
rsiti
T
e
k
n
o
lo
g
i
M
a
lay
si
a
in
2
0
0
1
,
2
0
0
4
a
n
d
2
0
1
1
i
n
El
e
c
tri
c
a
l
E
n
g
in
e
e
rin
g
a
n
d
Dig
it
a
l
S
ig
n
a
l
P
r
o
c
e
ss
in
g
re
sp
e
c
ti
v
e
l
y
.
He
is
c
u
rre
n
tl
y
a
n
A
s
so
c
iate
P
r
o
f
e
ss
o
r
w
it
h
th
e
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
f
o
r
Un
iv
e
rsiti
T
e
k
n
ik
a
l
M
a
la
y
sia
M
e
lak
a
(U
T
e
M
).
Evaluation Warning : The document was created with Spire.PDF for Python.