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.
9
,
No
.
6
,
Dec
em
b
er
201
9
,
p
p
.
5
2
4
4
~5
2
5
2
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v9
i
6
.
p
p
5
2
4
4
-
5252
5244
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
M
o
dified
J
SEG
alg
o
rith
m
f
o
r r
educ
ing
ov
er
-
seg
m
en
t
a
tion
pro
ble
m
s
in
u
nde
r
w
a
ter
co
ra
l reef
i
m
a
g
es
M
o
ha
m
m
a
d Sa
m
ee
r
A
lo
un
1
,
M
uh
a
mm
a
d Suz
uri H
it
a
m
2
,
Wa
n Nura
lJ
a
w
a
hir
H
j
Wa
n Yus
s
o
f
3
,
Abdu
l
Az
iz
K
Abdu
l H
a
m
i
d
4
,
Z
a
in
ud
d
in B
a
cho
k
5
1,
2,
3,
4
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
c
s a
n
d
Ap
p
li
e
d
M
a
th
e
m
a
ti
c
s
,
Un
iv
e
rsiti
M
a
la
y
sia
T
e
re
n
g
g
a
n
u
,
M
a
lay
si
a
5
S
c
h
o
o
l
o
f
M
a
rin
e
S
c
ien
c
e
a
n
d
E
n
v
iro
n
m
e
n
t,
Un
iv
e
rsiti
M
a
lay
sia
T
e
re
n
g
g
a
n
u
,
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
u
n
9
,
2
0
1
9
R
ev
i
s
ed
A
p
r
1
8
,
2
0
1
9
A
cc
ep
ted
J
u
n
1
5
,
2
0
1
9
T
h
e
o
rig
in
a
l
JSE
G
a
lg
o
rit
h
m
h
a
s
p
ro
v
e
d
to
b
e
v
e
r
y
u
se
f
u
l
a
n
d
ro
b
u
st
i
n
v
a
riet
y
o
f
i
m
a
g
e
se
g
m
e
n
tatio
n
c
a
se
stu
d
ies
.
Ho
w
e
v
e
r
,
w
h
e
n
it
is
a
p
p
li
e
d
i
n
to
th
e
u
n
d
e
rw
a
ter
c
o
ra
l
re
e
f
i
m
a
g
e
s,
th
e
o
rig
in
a
l
JSE
G
a
lg
o
rit
h
m
p
ro
d
u
c
e
s
o
v
e
r
-
se
g
e
m
e
n
tatio
n
p
ro
b
lem
,
th
u
s
m
a
k
in
g
th
is
a
lg
o
rit
h
m
f
u
ti
le
in
su
c
h
a
situ
a
ti
o
n
.
In
th
is p
a
p
e
r,
a
n
a
p
p
r
o
a
c
h
to
re
d
u
c
e
th
e
o
v
e
r
-
se
g
m
e
n
tatio
n
p
ro
b
lem
o
c
c
u
rre
d
in
th
e
u
n
d
e
rw
a
ter
c
o
r
a
l
re
e
f
i
m
a
g
e
se
g
m
e
n
tatio
n
is
p
re
se
n
ted
.
T
h
e
a
p
p
ro
a
c
h
w
o
rk
s
b
y
re
p
lac
in
g
th
e
c
o
lo
r
h
ist
o
g
ra
m
c
o
m
p
u
tatio
n
in
re
g
io
n
m
e
rg
e
sta
g
e
o
f
th
e
o
rig
in
a
l
JSE
G
a
lg
o
rit
h
m
w
it
h
th
e
n
e
w
c
o
m
p
u
tatio
n
o
f
c
o
lo
r
a
n
d
tex
tu
re
f
e
a
tu
re
s
in
th
e
sim
il
a
rit
y
m
e
a
su
re
m
e
n
t.
Ba
se
d
o
n
th
e
p
e
rc
e
p
t
u
a
l
o
b
se
rv
a
ti
o
n
re
su
lt
s
o
f
th
e
tes
t
im
a
g
e
s,
th
e
p
r
o
p
o
se
d
m
o
d
if
ied
JSE
G
a
l
g
o
rit
h
m
c
o
u
ld
a
u
t
o
m
a
ti
c
a
ll
y
se
g
m
e
n
t
th
e
re
g
io
n
s
b
e
tt
e
r
th
a
n
th
e
o
rig
in
a
l
JSE
G
a
lg
o
rit
h
m
.
K
ey
w
o
r
d
s
:
J
SEG
alg
o
r
ith
m
Seg
m
en
tatio
n
Un
d
er
w
a
ter
co
r
al
r
ee
f
i
m
a
g
es
Co
p
y
rig
h
t
©
2
0
1
9
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Mu
h
a
m
m
ad
S
u
zu
r
iH
ita
m
,
Sch
o
o
l o
f
I
n
f
o
r
m
atic
s
an
d
A
p
p
lied
Ma
th
e
m
at
ics,
Un
i
v
er
s
iti Ma
la
y
s
ia
T
er
en
g
g
a
n
u
,
2
1
0
3
0
Ku
ala
Ner
u
s
,
T
er
en
g
g
a
n
u
,
Ma
la
y
s
ia.
E
m
ail: s
u
z
u
r
i@
u
m
t.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
W
ith
in
t
h
e
last
d
ec
ad
es
,
th
e
ap
p
licatio
n
i
m
ag
e
an
d
v
id
eo
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
,
an
al
y
s
i
s
an
d
u
n
d
er
s
ta
n
d
in
g
h
a
s
g
r
o
w
n
tr
e
m
en
d
o
u
s
l
y
.
T
h
ese
ap
p
licati
o
n
s
s
p
r
ea
d
r
an
g
i
n
g
f
r
o
m
r
e
m
o
te
s
e
n
s
in
g
to
m
icr
o
s
co
p
ic
b
io
m
ed
ical
i
m
a
g
i
n
g
[
1
]
.
A
lt
h
o
u
g
h
i
m
ag
e
a
n
a
l
y
s
is
ca
n
b
e
p
er
f
o
r
m
ed
m
a
n
u
all
y
b
u
t
s
u
ch
a
n
al
y
s
i
s
is
r
ath
er
d
if
f
icu
lt,
ti
m
e
-
co
n
s
u
m
i
n
g
a
n
d
p
ain
s
ta
k
in
g
ly
to
b
e
ca
r
r
ied
m
a
n
u
all
y
.
F
u
r
t
h
er
m
o
r
e
,
co
n
s
id
er
in
g
th
a
t
d
ata
ar
e
m
a
s
s
i
v
e
r
e
g
ar
d
in
g
th
e
a
m
o
u
n
t
a
n
d
th
e
v
o
lu
m
e
t
h
a
t
k
ee
p
s
i
n
cr
ea
s
i
n
g
ea
c
h
s
in
g
l
e
d
ay
,
t
h
e
m
a
n
u
a
l
an
al
y
s
is
ap
p
r
o
ac
h
m
a
y
ev
e
n
b
e
im
p
r
ac
ticab
le
to
d
o
.
T
h
er
ef
o
r
e,
a
s
y
s
te
m
th
at
co
u
ld
au
to
m
atica
l
l
y
a
n
d
ef
f
icien
tl
y
a
n
al
y
ze
i
m
ag
er
y
f
o
r
v
ar
io
u
s
ap
p
licatio
n
s
n
ee
d
s
to
b
e
estab
lis
h
ed
[1
].
I
n
th
e
p
ast
f
e
w
y
ea
r
s
,
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
et
h
o
d
s
h
a
s
b
ee
n
ap
p
lied
to
p
r
o
ce
s
s
u
n
d
er
w
a
t
er
i
m
ag
e
s
.
T
h
e
p
r
im
ar
y
r
ea
s
o
n
s
f
o
r
th
e
ch
alle
n
g
i
n
g
is
s
u
e
s
i
n
u
n
d
er
wate
r
i
m
a
g
e
p
r
o
ce
s
s
in
g
is
o
w
i
n
g
to
t
h
e
ab
s
o
r
p
tio
n
an
d
s
ca
tter
i
n
g
e
f
f
ec
ts
o
f
th
e
lig
h
t
i
n
an
u
n
d
er
w
ater
en
v
ir
o
n
m
e
n
t
a
n
d
th
e
u
n
d
er
w
ater
n
o
is
e
ex
h
ib
it
d
u
e
to
d
if
f
er
e
n
t
w
ater
q
u
alit
y
.
T
h
i
s
h
as
led
to
th
e
in
cr
ea
s
in
g
e
x
p
lo
r
atio
n
,
u
n
d
er
s
ta
n
d
in
g
an
d
in
v
esti
g
a
tio
n
o
f
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
f
o
r
u
n
d
e
r
w
ater
i
m
a
g
e
s
.
I
n
th
e
ca
s
e
o
f
m
o
n
ito
r
i
n
g
a
n
d
s
u
r
v
e
y
o
f
co
r
al
r
ee
f
d
is
tr
ib
u
tio
n
,
m
ar
in
e
s
cie
n
ti
s
ts
r
eq
u
ir
e
a
n
au
to
m
at
ic
ap
p
r
o
ac
h
to
e
s
ti
m
ate
th
e
co
r
al
r
ee
f
d
is
tr
ib
u
tio
n
.
C
u
r
r
en
t
m
et
h
o
d
in
v
o
l
v
es
ta
s
k
th
at
is
ti
m
e
co
n
s
u
m
in
g
,
ted
io
u
s
an
d
n
o
t
ac
c
u
r
ate.
T
h
u
s
,
au
to
m
atic
i
m
a
g
e
s
eg
m
e
n
tatio
n
t
h
at
co
u
ld
s
ep
ar
ate
a
p
ar
tic
u
lar
t
y
p
e
o
f
co
r
al
r
ee
f
s
p
ec
ies
f
r
o
m
o
th
er
i
s
s
o
u
g
h
t.
I
m
a
g
e
s
eg
m
en
tatio
n
is
o
n
e
o
f
th
e
v
ital
p
r
o
ce
s
s
th
at
i
n
v
o
l
v
es
th
e
p
ar
titi
o
n
in
g
an
i
m
a
g
e
in
to
n
o
n
-
o
v
er
lap
p
in
g
d
if
f
er
i
n
g
r
eg
io
n
s
w
it
h
id
en
tica
l
attr
ib
u
tes
t
h
at
h
av
e
h
o
m
o
g
en
o
u
s
f
ea
t
u
r
es
o
r
h
av
e
th
e
co
m
m
o
n
ch
ar
ac
ter
is
tic
s
[2
-
5
]
.
I
m
ag
e
s
eg
m
e
n
tatio
n
i
s
a
cr
itical
p
r
o
ce
s
s
i
n
m
a
n
y
i
m
ag
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
s
u
c
h
as s
h
ap
e
r
ec
o
g
n
itio
n
,
o
b
j
ec
t d
etec
tio
n
a
n
d
o
p
tica
l
ch
ar
ac
ter
r
ec
o
g
n
itio
n
[6
,
7]
.
T
h
e
p
r
i
m
ar
y
g
o
al
o
f
s
eg
m
e
n
t
atio
n
is
to
m
a
k
e
th
e
i
m
ag
e
m
o
r
e
s
i
m
p
le
an
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
Mo
d
ified
JS
E
G
a
lg
o
r
ith
m
fo
r
r
ed
u
cin
g
o
ve
r
-
s
eg
me
n
ta
tio
n
p
r
o
b
lems in
…
(
Mo
h
a
mma
d
S
a
mee
r
A
lo
u
n
)
5245
m
ea
n
in
g
f
u
l
[
8
].
Seg
m
e
n
tatio
n
o
f
co
lo
r
i
m
ag
e
h
a
s
b
ee
n
v
er
y
p
o
p
u
lar
f
o
r
v
ar
io
u
s
ap
p
licatio
n
s
a
n
d
o
w
i
n
g
t
o
it
s
d
iv
er
s
e
ap
p
licatio
n
t
y
p
es.
Sti
l
l
u
p
to
to
d
a
y
,
i
m
a
g
e
s
eg
m
e
n
tat
io
n
r
e
m
a
in
s
a
c
h
alle
n
g
in
g
s
u
b
j
ec
t
[
9,
10
].
On
e
o
f
th
e
m
o
s
t
r
o
b
u
s
t
m
eth
o
d
s
o
f
s
eg
m
e
n
ti
n
g
n
at
u
r
al
i
m
a
g
es
is
th
e
J
SEG
alg
o
r
ith
m
[
11
]
.
T
h
is
o
r
ig
in
al
J
SEG
alg
o
r
ith
m
h
as
b
ee
n
p
r
o
v
en
to
b
e
v
er
y
u
s
e
f
u
l
an
d
r
o
b
u
s
t
in
v
ar
iet
y
o
f
i
m
a
g
e
s
e
g
m
e
n
tatio
n
.
T
h
e
o
r
ig
in
al
J
SEG
alg
o
r
ith
m
is
a
f
u
ll
y
u
n
s
u
p
er
v
is
ed
s
eg
m
en
tatio
n
al
g
o
r
ith
m
ca
p
ab
le
to
p
r
o
p
er
ly
s
e
g
m
e
n
t
i
m
a
g
es
o
f
n
a
tu
r
al
s
ce
n
e
s
.
Ho
w
e
v
er
,
w
h
en
t
h
i
s
alg
o
r
ith
m
i
s
ap
p
lied
to
th
e
u
n
d
er
w
ater
i
m
a
g
e
en
v
ir
o
n
m
e
n
t,
i
t
p
r
o
d
u
ce
s
o
v
er
-
s
e
g
m
en
tatio
n
p
r
o
b
lem
.
T
h
e
m
ai
n
r
ea
s
o
n
f
o
r
t
h
is
p
r
o
b
le
m
to
o
cc
u
r
is
d
u
e
to
t
h
e
v
ar
y
i
n
g
s
h
ad
es
a
n
d
v
ar
y
i
n
g
illu
m
i
n
atio
n
i
n
an
u
n
d
er
w
ater
en
v
ir
o
n
m
e
n
t.
T
h
er
ef
o
r
e,
th
is
p
ap
er
p
r
o
p
o
s
ed
a
m
e
th
o
d
to
r
ed
u
ce
th
is
o
v
er
-
s
e
g
m
en
tatio
n
p
r
o
b
le
m
b
y
r
ep
lacin
g
t
h
e
co
lo
r
h
is
t
o
g
r
a
m
co
m
p
u
tatio
n
i
n
r
eg
io
n
m
er
g
e
s
ta
g
e
o
f
th
e
o
r
ig
i
n
al
J
SEG
alg
o
r
ith
m
w
it
h
th
e
n
e
w
co
m
p
u
tat
io
n
o
f
co
lo
r
an
d
tex
tu
r
e
f
ea
tu
r
e
s
in
th
e
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
in
th
is
p
ap
er
co
u
ld
au
to
m
at
icall
y
s
eg
m
e
n
t
th
e
r
eg
i
o
n
s
b
etter
th
an
t
h
e
o
r
ig
in
al
J
SEG
alg
o
r
ith
m
.
T
h
e
m
a
in
o
b
j
ec
tiv
e
in
th
is
p
ap
er
is
to
en
h
an
ce
th
e
s
e
g
m
en
tatio
n
p
r
o
ce
s
s
b
y
r
ed
u
cin
g
th
e
o
v
er
-
s
e
g
m
en
tatio
n
r
eg
io
n
w
h
e
n
ap
p
l
y
i
n
g
to
t
h
e
u
n
d
er
w
ater
co
r
al
r
ee
f
i
m
a
g
es
.
J
SEG
alg
o
r
ith
m
[
1
2
,
13
]
is
am
o
n
g
t
h
e
m
o
s
t
p
o
p
u
lar
an
d
ef
f
ec
tiv
e
m
et
h
o
d
s
f
o
r
co
lo
r
im
a
g
e
s
eg
m
e
n
tatio
n
th
at
is
e
n
tire
l
y
u
n
s
u
p
er
v
is
ed
.
J
SEG
au
to
m
ati
ca
ll
y
s
e
g
m
e
n
ts
t
h
e
co
lo
r
-
te
x
t
u
r
e
r
eg
io
n
w
it
h
i
n
a
g
iv
e
n
i
m
ag
e
o
r
v
id
eo
.
J
SEG
alg
o
r
ith
m
w
o
r
k
s
b
ased
o
n
th
e
p
r
em
i
s
e
th
at
an
i
m
a
g
e
co
n
s
i
s
ts
o
f
h
o
m
o
g
e
n
o
u
s
(
u
n
i
f
o
r
m
l
y
d
is
tr
ib
u
ted
)
co
lo
r
-
tex
tu
r
e
p
atter
n
s
o
r
r
eg
io
n
s
w
h
er
e
it
is
aim
ed
to
q
u
an
tize
co
lo
r
in
f
o
r
m
atio
n
i
n
to
s
ev
er
al
co
lo
r
r
eg
io
n
s
w
h
il
e
th
e
co
lo
r
w
ith
in
t
h
e
t
w
o
ad
j
ac
en
t
r
eg
io
n
s
i
s
d
is
tin
c
t
p
er
ce
p
tu
all
y
.
Su
c
h
p
r
e
s
u
m
p
tio
n
s
ca
u
s
e
i
n
a
b
ilit
y
to
J
SEG
alg
o
r
ith
m
i
n
m
ak
in
g
a
d
is
ti
n
ctio
n
b
et
w
ee
n
t
w
o
ad
j
ac
en
t
r
eg
io
n
s
wh
ic
h
s
h
ar
e
s
i
m
ilar
itie
s
in
co
l
o
r
b
u
t d
if
f
er
en
t i
n
ter
m
s
o
f
te
x
tu
r
e
[
14
].
J
SEG
alg
o
r
ith
m
h
a
s
p
r
o
v
en
it
s
s
tr
o
n
g
ca
p
ac
it
y
in
d
ea
lin
g
w
it
h
m
a
n
y
t
y
p
e
s
o
f
n
atu
r
al
i
m
ag
e
s
[
15
]
.
So
m
e
h
o
w
,
t
h
er
e
ar
e
s
e
v
er
al
m
aj
o
r
p
r
o
b
lem
s
r
elatin
g
to
th
is
a
lg
o
r
it
h
m
,
s
u
c
h
a
s
v
ar
y
in
g
s
h
ad
es
d
u
e
to
th
e
ill
u
m
i
n
atio
n
an
d
o
v
er
s
eg
m
e
n
tatio
n
p
r
o
b
lem
.
Fu
r
t
h
er
m
o
r
e
,
as
i
t
w
as
m
e
n
tio
n
ed
in
th
e
w
o
r
k
b
y
De
n
g
et
al
.
[
12
]
,
t
h
e
o
r
i
g
in
a
l
J
SEG
h
as
is
s
u
e
s
w
i
th
s
p
atiall
y
v
ar
y
i
n
g
ill
u
m
in
a
tio
n
.
A
lo
u
n
et
al
.
[
1
5
]
r
ep
o
r
ted
th
at
th
e
p
er
f
o
r
m
a
n
c
e
o
f
th
e
o
r
ig
i
n
al
J
SEG
m
et
h
o
d
w
as
p
o
o
r
f
o
r
u
n
d
er
w
ater
i
m
a
g
e
s
e
g
m
en
ta
tio
n
b
ec
au
s
e
o
f
th
e
af
o
r
e
m
en
tio
n
e
d
lim
i
tatio
n
s
an
d
it
ap
p
ea
r
s
to
h
av
e
d
if
f
ic
u
lt
y
i
n
m
a
k
i
n
g
a
d
is
tin
ct
io
n
b
et
w
e
e
n
r
eg
io
n
s
w
it
h
co
lo
r
te
x
t
u
r
es
.
I
t
s
h
o
u
ld
b
e
n
o
ted
t
h
at
w
it
h
i
n
t
h
e
u
n
d
er
w
ater
s
et
ti
n
g
,
as
t
h
e
w
ater
g
et
s
d
ee
p
er
,
th
e
lig
h
t
b
ec
o
m
es
m
o
r
e
ab
s
o
r
b
ed
an
d
s
ca
tter
ed
.
Hen
ce
th
er
e
is
a
p
r
ess
in
g
n
ee
d
f
o
r
a
r
o
b
u
s
t
an
d
r
eliab
le
m
et
h
o
d
f
o
r
u
n
d
er
w
ater
i
m
a
g
e
an
al
y
s
is
a
n
d
s
e
g
m
e
n
tat
io
n
[
1
6
,
17
].
T
h
e
p
r
o
b
lem
o
f
co
r
al
r
ee
f
th
r
i
v
es
i
n
co
u
n
tles
s
co
lo
r
s
,
tex
tu
r
es
an
d
s
h
ap
es
m
a
k
e
s
eg
m
e
n
ta
tio
n
ev
e
n
m
o
r
e
c
h
alle
n
g
i
n
g
.
Fu
r
t
h
er
m
o
r
e,
co
r
al
r
ee
f
s
o
f
th
e
s
a
m
e
s
p
ec
ies
w
ill
ap
p
ea
r
d
if
f
er
en
t
i
n
t
er
m
s
o
f
co
lo
r
at
a
d
if
f
er
i
n
g
d
ep
th
o
f
w
ater
.
[
1
8
,
19
]
.
T
h
e
p
r
o
b
lem
s
o
f
J
SEG
alg
o
r
ith
m
ar
e
o
p
en
l
y
r
ec
o
g
n
i
ze
d
in
th
e
o
r
ig
i
n
al
p
ap
er
[
1
2
]
,
i.e
.
o
v
er
-
s
eg
m
e
n
tatio
n
d
u
e
to
o
v
er
lap
p
in
g
co
lo
r
-
tex
t
u
r
e
s
i
m
ilar
it
y
i
n
n
eig
h
b
o
r
in
g
r
eg
io
n
.
A
cc
o
r
d
in
g
l
y
,
s
o
m
e
al
ter
atio
n
s
an
d
co
m
p
ar
is
o
n
s
w
er
e
m
ad
e
w
it
h
t
h
e
o
r
ig
i
n
al
J
SEG
al
g
o
r
it
h
m
w
it
h
in
th
e
la
s
t
d
ec
ad
e
.
J
in
g
et
al
.
[
2
0
]
ad
d
ed
th
e
H
m
ea
s
u
r
e
in
th
e
s
p
atial
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
o
f
t
h
e
o
r
ig
in
al
al
g
o
r
ith
m
a
n
d
ca
lled
th
e
m
HSEG
.
I
n
a
r
elate
d
s
tu
d
y
Z
h
en
g
et
al
.
[
2
1
]
ad
d
e
d
a
f
u
zz
y
m
ec
h
a
n
is
m
to
J
SEG
in
t
h
e
co
n
s
tr
u
ctio
n
o
f
a
s
o
f
t
c
lass
m
ap
.
T
h
is
s
o
f
t
c
lass
m
ap
s
tr
e
n
g
t
h
e
n
J
SEG
f
u
n
ctio
n
in
g
i
n
a
n
u
n
s
u
p
er
v
i
s
ed
i
m
ag
e
s
e
g
m
e
n
tat
io
n
.
C
h
a
n
g
et
al
.
[
22
]
p
r
esen
ted
an
o
th
er
m
o
d
i
f
ied
J
SEG
m
et
h
o
d
an
d
n
a
m
ed
it
as
th
e
i
m
p
r
o
v
ed
co
n
tr
ast
J
SEG
o
r
I
C
J
SEG.
T
h
e
m
et
h
o
d
p
r
o
p
o
s
ed
b
y
W
an
g
et
al
.
[
2
3
]
allo
w
s
t
h
e
s
e
g
m
en
tatio
n
o
f
t
h
e
i
m
ag
e
b
y
co
lo
r
an
d
tex
t
u
r
e.
F
u
r
th
er
m
o
r
e,
J
SEG
s
eg
m
e
n
tat
io
n
a
lg
o
r
it
h
m
h
a
d
b
ee
n
e
n
h
a
n
ce
d
b
y
Kib
r
ia
a
n
d
I
s
la
m
[
24
]
th
r
o
u
g
h
th
e
ad
d
itio
n
o
f
a
n
ed
g
e
d
etec
t
o
r
.
Ko
m
ati
et
al
.
[
2
5
]
in
tr
o
d
u
ce
d
a
m
et
h
o
d
w
h
ic
h
co
m
b
i
n
e
s
th
e
o
r
ig
i
n
al
J
SEG
alg
o
r
ith
m
w
it
h
a
lo
ca
l f
r
ac
tal
o
p
er
ato
r
.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
:
Sect
io
n
2
p
r
o
v
id
es
a
r
elate
d
w
o
r
k
s
.
Sectio
n
3
p
r
esen
ts
th
e
J
SEG
s
eg
m
e
n
tatio
n
alg
o
r
it
h
m
.
Sec
tio
n
4
p
r
esen
ts
i
m
p
le
m
en
tatio
n
o
f
p
r
o
p
o
s
ed
m
et
h
o
d
.
Sectio
n
5
p
r
esen
ts
th
e
ex
p
er
i
m
e
n
tal
r
esu
l
ts
a
n
d
d
is
cu
s
s
io
n
a
n
d
th
e
f
i
n
al
co
n
cl
u
s
i
o
n
is
g
i
v
e
n
in
Sectio
n
6
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
J
SEG
s
tan
d
s
f
o
r
J
-
s
eg
m
e
n
tat
io
n
,
is
an
u
n
s
u
p
er
v
is
ed
co
lo
r
-
tex
t
u
r
e
s
e
g
m
en
ta
tio
n
al
g
o
r
ith
m
[
1
2
]
.
I
t
co
m
p
r
is
es
o
f
t
w
o
co
m
p
u
ta
tio
n
al
p
h
ases
t
h
at
ar
e
s
u
cc
es
s
iv
el
y
ap
p
lied
w
h
ic
h
ar
e
co
lo
r
q
u
an
tizatio
n
a
n
d
s
p
atial
s
eg
m
e
n
tatio
n
.
T
h
e
f
ir
s
t
p
h
ase
en
tails
t
h
e
s
a
m
p
lin
g
o
f
th
e
co
lo
r
in
f
o
r
m
atio
n
o
f
t
h
e
in
p
u
t
i
m
ag
e
u
s
i
n
g
a
r
ed
u
ce
d
s
et
o
f
s
ig
n
i
f
ica
n
t
co
lo
r
s
(
r
an
g
i
n
g
f
r
o
m
1
0
-
2
0
p
r
o
to
t
y
p
es)
ac
q
u
ir
ed
f
o
llo
w
i
n
g
t
h
e
tec
h
n
iq
u
e
o
f
a
p
ee
r
-
g
r
o
u
p
f
ilter
i
n
g
co
lo
r
q
u
a
n
tizatio
n
.
T
h
is
p
r
o
ce
s
s
m
ap
s
o
u
t
t
h
e
i
m
ag
e
in
to
a
s
tr
u
ctu
r
e
w
it
h
i
n
w
h
ic
h
e
v
er
y
p
ix
el
is
p
r
o
v
id
ed
a
class
lab
el.
T
h
is
is
f
o
llo
w
ed
b
y
a
p
h
ase
w
h
er
e
th
e
al
g
o
r
ith
m
u
s
e
s
s
p
at
ial
co
m
p
o
s
i
tio
n
o
f
th
e
p
r
o
v
id
ed
class
lab
els
e
m
p
lo
y
i
n
g
a
s
eg
m
e
n
tatio
n
cr
iter
io
n
,
n
a
m
el
y
J
v
al
u
e
b
y
s
a
m
p
li
n
g
th
e
lo
ca
l
h
o
m
o
g
en
eit
y
.
A
p
p
l
y
i
n
g
th
e
cr
iter
io
n
to
lo
ca
l
im
a
g
e
w
i
n
d
o
w
s
r
esu
lt
s
in
t
h
e
J
-
i
m
ag
e
s
w
h
ic
h
ca
n
b
e
s
eg
m
e
n
ted
u
s
i
n
g
a
m
u
lti
-
s
ca
le
r
eg
io
n
g
r
o
w
i
n
g
m
e
th
o
d
.
I
n
th
is
p
r
o
ce
s
s
,
th
e
o
r
ig
i
n
al
s
ee
d
s
n
ee
d
ed
b
y
t
h
e
r
eg
io
n
g
r
o
w
in
g
p
r
o
ce
d
u
r
e
alig
n
w
it
h
m
i
n
i
m
a
o
f
lo
ca
l
J
v
alu
e
s
.
Mo
r
eo
v
er
,
th
e
g
r
o
w
i
n
g
p
r
o
ce
s
s
o
f
m
u
lti
-
s
ca
le
r
e
g
io
n
f
r
eq
u
en
tl
y
p
r
o
d
u
ce
s
a
n
o
v
er
-
s
eg
m
e
n
ted
o
u
tco
m
e
a
n
d
to
r
eso
lv
e
t
h
i
s
is
s
u
e,
a
m
et
h
o
d
o
f
p
o
s
t
-
p
r
o
ce
s
s
i
n
g
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
2
4
4
-
5
2
5
2
5246
u
s
ed
to
co
m
b
in
e
t
h
e
ad
j
ac
en
t
ar
ea
s
o
n
th
e
b
asis
o
f
co
lo
r
s
im
ilar
it
y
an
d
t
h
e
E
u
clid
ia
n
d
is
t
an
ce
.
I
t
is
i
m
p
o
r
tan
t
to
s
tate
th
at
t
h
e
ac
q
u
ir
ed
o
u
tc
o
m
e
s
h
in
g
e
o
n
t
h
e
o
p
ti
m
al
c
h
o
ice
o
f
th
r
ee
p
ar
a
m
eter
s
th
at
s
h
o
u
ld
b
e
a
p
r
io
r
i
u
s
er
-
s
p
ec
i
f
icatio
n
i
n
ter
m
s
o
f
co
lo
r
q
u
an
tizatio
n
t
h
r
esh
o
ld
,
n
u
m
b
er
o
f
s
ca
les
an
d
th
e
m
er
g
e
th
r
es
h
o
ld
[
1
2
,
26
].
T
h
e
g
en
er
al
f
lo
w
o
f
t
h
e
J
SEG
alg
o
r
ith
m
i
s
p
r
esen
ted
in
F
ig
u
r
e
1
.
2
.
1
.
Co
l
o
r
q
ua
ntiz
a
t
io
n
T
h
e
p
r
im
ar
y
a
i
m
o
f
t
h
e
co
lo
r
q
u
an
tizat
io
n
is
to
r
ed
u
ce
th
e
n
u
m
b
er
o
f
co
lo
r
s
in
t
h
e
o
r
ig
in
a
l
i
m
ag
e
to
d
ec
r
ea
s
e
th
e
co
m
p
le
x
it
y
o
f
t
h
e
al
g
o
r
ith
m
.
T
h
e
p
r
o
v
id
ed
i
m
a
g
e
co
lo
r
s
ar
e
d
ec
r
ea
s
ed
u
s
i
n
g
P
ee
r
Gr
o
u
p
Fil
ter
in
g
(
P
GF)
alg
o
r
it
h
m
[
13
,
2
7
]
w
h
er
e
t
h
e
r
e
g
io
n
is
q
u
a
n
ti
ze
d
w
i
th
s
i
m
i
lar
co
lo
r
an
d
d
i
f
f
er
en
tiated
t
h
r
o
u
g
h
cl
ass
es.
T
h
e
P
GF
alg
o
r
ith
m
is
d
escr
ib
ed
as
a
n
o
n
-
l
in
ea
r
alg
o
r
ith
m
u
s
ed
to
s
m
o
o
th
e
n
a
g
iv
e
n
i
m
ag
e
b
y
d
eletin
g
i
m
p
u
l
s
iv
e
n
o
i
s
e
w
h
il
e
m
ai
n
tai
n
i
n
g
th
e
ed
g
e
a
s
well
as
i
n
f
o
r
m
atio
n
d
etails.
L
e
t
x
o
(
n
)
i
n
d
icate
a
n
i
m
a
g
e
p
i
x
el
v
ec
to
r
,
th
e
co
lo
r
in
f
o
r
m
atio
n
at
p
o
s
itio
n
n
ce
n
te
r
ed
in
a
w
x
w
w
i
n
d
o
w
an
d
ar
r
an
g
e
all
th
e
p
ix
el
s
in
t
h
e
w
i
n
d
o
w
ac
co
r
d
in
g
to
th
eir
d
i
s
tan
ce
s
to
x
o
(
n
)
i
n
asce
n
d
i
n
g
o
r
d
er
an
d
i
n
d
ic
ate
th
e
m
a
s
x
i(
n
)
,
i =
0
,
.
.
.
,
k
=
w
2
-
1
.
T
h
e
E
u
cli
d
ea
n
d
is
tan
ce
m
ea
s
u
r
e
is
u
s
ed
w
h
er
e,
(
)
=
‖
0
(
)
−
(
)
‖
,
=
0
,
…
.
,
(
1
)
0
(
)
≤
1
(
)
≤
…
.
.
≤
(
n
)
(
2
)
T
h
e
p
ee
r
g
r
o
u
p
P
(
n
)
o
f
s
ize
m
(
n
)
f
o
r
x
o
(
n
)
is
d
ef
in
ed
as
f
o
llo
w
s
:
(
)
=
{
(
n
)
,
=
0
,
…
(
n
)
−
1
}
(
3
)
I
t c
o
n
s
is
t
s
o
f
0
(
n
)
its
elf
an
d
its
n
eig
h
b
o
r
in
g
p
o
in
ts
o
f
s
i
m
ilar
co
lo
r
s
[
27
].
T
h
er
ef
o
r
e,
th
e
n
e
x
t
co
lo
r
q
u
an
tizatio
n
s
tep
e
n
tails
th
e
ap
p
r
o
p
r
iatio
n
o
f
w
eig
h
t
to
e
v
er
y
p
ix
el
w
it
h
s
m
o
o
th
ar
ea
w
er
e
g
i
v
en
m
o
r
e
w
ei
g
h
t
th
a
n
th
e
te
x
t
u
r
ed
o
n
es.
I
n
t
h
e
th
ir
d
s
tep
,
a
m
o
d
if
ied
Gen
er
al
L
lo
y
d
A
l
g
o
r
ith
m
(
G
L
A
)
[
2
8
]
is
ap
p
lied
to
v
ec
to
r
q
u
a
n
tize
t
h
e
p
i
x
el
co
lo
r
s
.
L
as
tl
y
,
clu
s
ter
ce
n
tr
o
i
d
ar
e
ex
p
o
s
ed
to
ag
g
lo
m
er
ati
v
e
clu
s
ter
in
g
al
g
o
r
ith
m
[
2
9
]
to
co
m
b
i
n
e
clu
s
te
r
s
lo
ca
ted
in
th
e
n
ei
g
h
b
o
r
in
g
ar
ea
o
f
a
s
p
ec
if
ic
p
r
eset th
r
esh
o
ld
v
a
lu
e
t
h
at
i
s
u
s
er
-
d
ef
i
n
ed
.
2
.
2
.
Sp
a
t
ia
l
s
eg
m
ent
a
t
io
n a
lg
o
rit
h
m
I
n
th
i
s
s
p
atial
s
e
g
m
e
n
tatio
n
p
r
o
ce
s
s
,
th
e
J
-
v
al
u
e
co
n
ce
p
t
is
u
s
ed
.
Fo
r
in
s
tan
ce
,
i
f
Z
i
s
a
s
et
(
x
,
y
)
i
m
a
g
e
p
ix
els
i
n
a
p
ar
ticu
lar
class
m
ap
an
d
it
is
cla
s
s
i
f
ied
i
n
to
C
class
e
s
Z
i,
w
it
h
i
r
ep
r
esen
ti
n
g
1
,
….
C
,
m
d
en
o
tin
g
s
p
atial
m
ea
n
o
f
th
e
w
h
o
le
Z
p
o
in
ts
,
an
d
m
i
d
en
o
t
es
th
e
s
p
atia
l
m
ea
n
o
f
p
i
x
els
i
n
Z
i,
th
e
n
t
h
e
to
tal
v
ar
ian
ce
o
f
t
h
e
w
h
o
le
Z
p
o
in
ts
ar
e
r
ep
r
esen
ted
as f
o
llo
w
s
;
=
∑
|
|
−
∊
|
|
2
(
4
)
T
h
e
to
tal
v
ar
ian
ce
o
f
p
o
in
ts
t
h
at
b
elo
n
g
to
o
n
e
class
i
s
r
ep
r
esen
ted
as:
=
∑
∑
|
|
−
|
|
2
∊
=
1
(
5
)
A
d
is
tr
ib
u
tio
n
m
ea
s
u
r
e
o
f
co
lo
r
class
es is
g
i
v
en
b
y
J
-
v
al
u
e
is
d
ef
in
ed
as
f
o
llo
w
s
:
=
(
−
)
(
6
)
T
h
e
J
-
v
al
u
es
co
n
ce
p
t
is
u
s
ed
in
th
e
clas
s
m
ap
lo
ca
l
ar
ea
to
in
d
icate
a
s
p
ec
if
ic
ar
ea
in
t
h
e
r
eg
io
n
ce
n
ter
o
r
its
b
o
u
n
d
ar
ies.
J
-
i
m
ag
es
co
n
ce
p
t
r
ef
er
s
to
a
g
r
a
y
s
ca
le
i
m
ag
e
w
i
th
p
i
x
els
h
a
v
i
n
g
J
v
alu
es
ac
q
u
ir
ed
th
r
o
u
g
h
ca
lcu
lati
n
g
o
v
er
lo
c
al
w
in
d
o
w
s
f
o
cu
s
ed
o
n
t
h
e
p
ix
els.
T
h
e
J
v
al
u
es
ar
e
co
m
p
u
ted
at
d
if
f
er
e
n
t
s
ca
les.T
h
e
n
ex
t
s
tep
in
s
p
atia
l
s
eg
m
en
tatio
n
i
s
th
e
ap
p
licati
o
n
o
f
r
eg
io
n
g
r
o
w
i
n
g
alg
o
r
it
h
m
in
t
h
e
r
eg
io
n
an
d
r
eg
io
n
m
er
g
i
n
g
.
I
n
t
h
e
f
ir
s
t
o
n
e
(
r
eg
io
n
g
r
o
w
i
n
g
)
,
t
h
er
e
ar
e
t
w
o
i
n
ter
ac
ti
v
e
p
r
o
ce
s
s
i
n
v
o
lv
ed
n
a
m
el
y
v
a
lle
y
d
eter
m
in
at
io
n
a
n
d
v
alle
y
g
r
o
w
i
n
g
.
A
t
t
h
e
b
eg
in
n
i
n
g
o
f
t
h
e
r
eg
io
n
g
r
o
w
in
g
p
r
o
ce
s
s
,
t
h
er
e
is
o
n
e
i
n
itial
r
eg
io
n
(t
h
e
en
tire
i
m
a
g
e
)
.
Fig
u
r
e
2
s
h
o
w
s
t
h
e
s
p
atial
s
eg
m
e
n
tatio
n
s
tep
.
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
Mo
d
ified
JS
E
G
a
lg
o
r
ith
m
fo
r
r
ed
u
cin
g
o
ve
r
-
s
eg
me
n
ta
tio
n
p
r
o
b
lems in
…
(
Mo
h
a
mma
d
S
a
mee
r
A
lo
u
n
)
5247
Fig
u
r
e
1
.
T
h
e
o
r
ig
in
al
J
SEG
alg
o
r
ith
m
Fig
u
r
e
2
.
T
h
e
s
p
atial
s
eg
m
e
n
t
atio
n
s
tep
in
J
-
SEG
al
g
o
r
ith
m
2
.
3
.
T
he
pro
po
s
ed
m
et
ho
d
T
o
o
v
er
co
m
e
t
h
e
o
v
er
-
s
eg
m
en
tatio
n
p
r
o
b
le
m
i
n
an
u
n
d
e
r
w
ater
co
r
al
r
ee
f
i
m
a
g
e
s
,
w
e
r
ep
lace
d
th
e
m
er
g
e
s
ta
g
e
in
t
h
e
m
a
in
J
SEG
o
r
ig
in
al
al
g
o
r
ith
m
w
it
h
a
n
e
w
tec
h
n
iq
u
e
b
ased
o
n
th
e
s
i
m
ilar
it
y
m
ea
s
u
r
e
u
s
i
n
g
m
ea
n
an
d
co
v
ar
ia
n
ce
as
illu
s
tr
ated
in
Fi
g
u
r
e
3
.
Fig
u
r
e
3
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
if
i
ed
J
SEG
alg
o
r
ith
m
w
i
th
a
n
e
w
s
i
m
i
lar
it
y
m
ea
s
u
r
e
m
en
t
b
ased
o
n
m
ea
n
a
n
d
co
v
ar
ien
ce
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
2
4
4
-
5
2
5
2
5248
2
.
3
.
1
.
Reg
io
n
m
er
g
e
in t
he
o
rig
ina
l
J
SE
G
a
lg
o
rit
h
m
I
n
t
h
e
o
r
ig
in
al
J
SEG
al
g
o
r
it
h
m
,
r
eg
io
n
g
r
o
w
in
g
r
e
s
u
l
ts
i
n
a
n
i
n
it
ial
s
eg
m
e
n
tatio
n
o
f
th
e
i
m
a
g
e,
th
u
s
o
v
er
-
s
e
g
m
en
ted
r
e
g
io
n
s
ap
p
ea
r
to
b
e
an
is
s
u
e.
A
s
a
s
o
lu
tio
n
to
th
e
s
e
o
v
er
-
s
e
g
m
e
n
ted
r
eg
io
n
s
,
th
e
s
e
r
eg
io
n
s
ar
e
m
er
g
ed
ac
co
r
d
in
g
to
th
eir
co
lo
r
s
i
m
ilar
it
y
.
I
n
th
is
r
eg
ar
d
,
co
lo
r
h
is
to
g
r
a
m
ch
ar
ac
ter
ize
s
th
e
r
eg
io
n
’
s
co
lo
r
in
f
o
r
m
atio
n
.
Me
an
w
h
ile,
t
h
e
co
lo
r
h
is
t
o
g
r
a
m
b
in
s
ar
e
b
ased
o
n
th
e
q
u
an
tized
co
lo
r
s
ac
q
u
ir
ed
f
r
o
m
t
h
e
p
r
o
ce
s
s
o
f
co
lo
r
q
u
an
tizatio
n
.
T
h
e
E
u
clid
ea
n
d
is
tan
ce
b
et
w
ee
n
t
w
o
co
lo
r
h
is
to
g
r
a
m
s
,
DC
H
at
i a
n
d
j
ca
n
b
e
d
ef
in
ed
as f
o
ll
o
w
s
:
(
,
)
=
|
|
−
|
|
(7
)
w
h
er
e
P
r
ep
r
esen
ts
th
e
v
e
cto
r
o
f
co
lo
r
h
is
to
g
r
a
m
.
T
h
e
r
eg
io
n
m
er
g
e
m
et
h
o
d
is
g
r
o
u
n
d
ed
u
p
o
n
th
e
ag
g
lo
m
er
ati
v
e
m
et
h
o
d
in
Du
d
a
an
d
Har
t
[
2
9
]
.
B
y
u
s
in
g
th
is
m
et
h
o
d
,
f
ir
s
t
l
y
,
a
d
is
tan
c
e
tab
le
co
m
p
r
is
in
g
th
e
d
is
ta
n
ce
s
b
et
w
ee
n
th
e
co
lo
r
h
is
to
g
r
a
m
o
f
a
n
y
t
w
o
n
ea
r
b
y
r
eg
io
n
s
is
co
n
s
tr
u
cted
.
I
n
t
h
e
p
r
o
ce
s
s
,
th
e
p
air
o
f
r
eg
io
n
s
co
m
p
r
is
i
n
g
th
e
least
a
m
o
u
n
t
o
f
d
is
tan
ce
i
s
m
er
g
ed
t
o
g
eth
er
.
T
h
is
is
f
o
llo
w
ed
b
y
t
h
e
co
m
p
u
tatio
n
o
f
th
e
n
e
w
co
lo
r
f
ea
tu
r
e
v
ec
to
r
o
f
t
h
e
n
e
w
r
e
g
io
n
.
A
cc
o
r
d
in
g
l
y
,
th
e
d
is
ta
n
ce
tab
le
is
r
e
n
e
w
ed
to
g
eth
er
w
i
th
th
e
n
ea
r
b
y
ass
o
ciat
io
n
s
.
T
h
e
p
r
o
ce
s
s
o
f
r
eg
io
n
m
er
g
e
en
s
u
es
ti
ll
t
h
e
h
i
g
h
est
th
r
es
h
o
ld
f
o
r
th
e
d
is
tan
ce
i
s
attain
ed
[
12
].
2
.
3
.
2
.
T
he
pro
po
s
ed
re
g
io
n m
er
g
e
u
s
ing
s
i
m
ila
rit
y
m
ea
s
ure
S
eg
m
en
tatio
n
is
ex
ec
u
ted
to
s
eg
m
e
n
t
o
b
j
ec
ts
w
it
h
i
n
a
n
i
m
ag
e
t
h
at
is
v
er
y
m
u
ch
co
m
p
ar
ab
le
to
h
u
m
a
n
p
er
ce
p
tio
n
.
A
s
m
e
n
tio
n
ed
b
y
De
n
g
an
d
Ma
n
j
u
n
a
th
[
1
2
]
,
J
SEG
alg
o
r
ith
m
h
as
o
v
er
-
s
e
g
m
en
ta
tio
n
i
s
s
u
e
ca
u
s
ed
b
y
th
e
s
p
atial
l
y
f
lu
c
tu
atin
g
illu
m
i
n
atio
n
.
Su
c
h
p
r
o
b
l
e
m
ca
u
s
es
ch
a
n
g
e
to
co
lo
r
im
ag
e
co
m
p
o
n
en
ts
i
n
ter
m
s
o
f
i
n
te
n
s
it
y
a
n
d
c
h
r
o
m
i
n
an
ce
[
3
0
]
.
A
f
ter
th
e
s
ta
g
e
o
f
r
eg
io
n
g
r
o
w
in
g
,
i
n
t
h
e
o
r
ig
in
al
J
SEG
alg
o
r
it
h
m
,
th
e
f
o
llo
w
i
n
g
s
ta
g
e
is
r
eg
io
n
m
er
g
i
n
g
.
R
e
g
io
n
g
r
o
w
i
n
g
in
v
o
lv
es
th
e
ap
p
licatio
n
o
f
m
u
lti
p
le
s
ee
d
s
an
d
s
o
m
e
o
f
t
h
ese
s
ee
d
s
m
a
y
o
r
ig
i
n
ate
f
r
o
m
th
e
ex
ac
t
r
eg
io
n
.
A
cc
o
r
d
in
g
l
y
,
o
n
e
r
eg
io
n
m
a
y
co
n
t
ain
m
o
r
e
t
h
an
o
n
e
p
ar
titi
o
n
an
d
r
eg
io
n
l
ik
e
t
h
i
s
is
n
o
t
d
esira
b
le.
I
n
t
h
is
p
ap
er
,
th
e
is
s
u
e
o
f
o
v
er
-
s
eg
m
e
n
tati
o
n
is
r
ed
u
ce
d
v
ia
th
e
m
er
g
i
n
g
o
f
t
h
ese
p
ar
titi
o
n
s
i
n
ac
co
r
d
an
ce
to
t
h
e
ce
r
tai
n
cr
iter
io
n
o
f
s
i
m
ilar
it
y
.
T
h
e
p
r
o
ce
d
u
r
e
is
d
etailed
as
f
o
llo
w
s
:
a.
C
r
ea
te
th
e
m
ea
n
a
n
d
co
v
ar
ian
ce
m
ea
s
u
r
es o
f
all
r
e
g
io
n
s
alo
n
g
s
id
e
th
eir
ad
j
ac
en
t n
ei
g
h
b
o
r
s
.
b.
Me
r
g
e
r
eg
io
n
s
w
h
ic
h
co
n
tai
n
less
t
h
an
a
m
in
i
m
u
m
p
i
x
e
l
co
u
n
t
w
it
h
th
eir
n
ei
g
h
b
o
r
s
.
T
h
en
,
u
p
d
ate
th
e
n
e
w
r
e
g
io
n
-
n
eig
h
b
o
r
h
o
o
d
s
tatis
t
ics.
c.
C
alcu
late
th
e
s
i
m
ilar
it
y
m
ea
s
u
r
e,
S
o
f
t
w
o
r
eg
io
n
s
.
T
ak
in
g
i
n
to
ac
co
u
n
t
t
w
o
r
eg
io
n
s
n
a
m
el
y
r
eg
io
n
A
a
n
d
B
,
th
e
s
i
m
ilar
it
y
m
ea
s
u
r
e
b
et
w
ee
n
t
h
e
t
w
o
r
eg
io
n
s
w
it
h
co
lo
r
m
ea
n
,
µ
A
,
a
n
d
µ
B
,
an
d
th
e
co
lo
r
co
-
v
ar
ia
n
ce
s
,
co
v
A
a
n
d
co
v
B
.
T
h
e
s
i
m
i
lar
it
y
m
ea
s
u
r
e
o
f
t
w
o
r
eg
io
n
s
ca
n
b
e
m
at
h
e
m
atica
ll
y
ex
p
r
ess
ed
as f
o
llo
w
s
:
,
=
(
µ
−
µ
)
∗
(
+
)
∗
(
µ
−
µ
)
(
8
)
T
h
e
m
ea
s
u
r
e
o
f
s
i
m
ilar
it
y
e
lu
cid
ated
in
(
8
)
ap
p
ea
r
s
to
b
e
m
o
r
e
r
o
b
u
s
t
m
ea
s
u
r
e
as
o
p
p
o
s
ed
to
th
e
w
id
el
y
e
m
p
lo
y
ed
co
lo
r
m
ea
s
u
r
e
o
f
m
ea
n
s
.
T
h
is
o
w
es
to
th
e
f
ac
t
th
at
t
h
i
s
m
ea
s
u
r
e
o
f
s
i
m
ilar
it
y
e
m
p
lo
y
s
b
o
t
h
th
e
m
ea
n
an
d
th
e
co
-
v
ar
ian
ce
s
o
f
th
e
p
ix
els
w
it
h
i
n
th
e
r
eg
i
o
n
s
to
b
e
m
er
g
ed
.
Hen
ce
,
th
e
co
m
p
ar
is
o
n
is
m
ad
e
to
t
h
e
r
eg
io
n
s
n
o
t
o
n
l
y
f
o
r
t
h
eir
co
n
te
n
t
o
f
co
lo
r
b
u
t
al
s
o
to
th
eir
co
n
te
n
t
o
f
te
x
tu
r
e
p
r
io
r
to
th
e
estab
li
s
h
m
e
n
t o
f
t
h
e
m
er
g
i
n
g
d
ec
is
io
n
.
d.
Neig
h
b
o
r
in
g
r
e
g
io
n
s
co
n
tai
n
i
n
g
t
h
e
s
m
alle
s
t
S
v
al
u
e
m
atch
es
w
ith
t
h
e
h
i
g
h
l
y
s
i
m
i
lar
r
eg
i
o
n
s
.
Fo
r
th
ese
r
eg
io
n
s
,
t
h
e
y
ar
e
th
e
ea
r
lie
s
t
t
o
b
e
m
er
g
ed
.
Fo
r
th
e
n
e
x
t
s
te
p
o
f
r
eg
io
n
m
er
g
i
n
g
,
th
e
u
p
d
ate
is
p
er
f
o
r
m
ed
o
n
r
eg
io
n
-
n
ei
g
h
b
o
r
h
o
o
d
s
tati
s
tics
o
f
S
.
T
h
is
p
r
o
ce
s
s
iter
a
tiv
el
y
e
n
s
u
es
u
n
til
t
h
e
m
er
g
i
n
g
th
r
es
h
o
ld
,
M
Thresh
w
h
o
s
e
v
alu
e
d
eter
m
i
n
es
th
e
m
er
g
in
g
m
a
g
n
it
u
d
e,
is
attain
ed
.
Hig
h
er
v
al
u
es
o
f
M
Thresh
lead
to
m
o
r
e
r
eg
io
n
s
to
b
e
m
er
g
ed
,
an
d
v
ice
v
er
s
a.
T
h
e
o
u
tco
m
e
co
m
p
r
i
s
es t
h
e
f
in
al
s
eg
m
e
n
ted
i
m
ag
e.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
I
n
th
is
p
ap
er
,
th
e
ex
ec
u
t
io
n
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
b
ee
n
test
ed
o
n
th
e
co
r
al
r
e
ef
i
m
a
g
es
o
b
tain
ed
f
r
o
m
th
e
I
n
s
tit
u
te
o
f
Oce
a
n
o
g
r
ap
h
y
a
n
d
E
n
v
ir
o
n
m
en
t,
U
n
iv
er
s
it
i
Ma
la
y
s
ia
T
er
en
g
g
an
u
(
I
NO
S),
Ma
la
y
s
ia.
T
h
e
ex
p
er
i
m
en
t
ai
m
s
to
au
to
m
atica
l
l
y
r
ed
u
ce
t
h
e
o
v
er
-
s
e
g
m
en
tatio
n
in
th
e
co
r
al
r
ee
f
i
m
a
g
e.
Usu
al
l
y
,
t
h
is
s
e
g
m
en
ta
tio
n
p
r
o
ce
s
s
is
b
ein
g
ca
r
r
ied
o
u
t
m
a
n
u
all
y
b
y
th
e
m
ar
in
e
s
cie
n
ti
s
ts
to
esti
m
ate
t
h
e
co
r
al
r
ee
f
s
p
o
p
u
latio
n
g
r
o
w
th
.
Fi
g
u
r
e
4
an
d
Fig
u
r
e
5
s
h
o
w
t
h
e
r
es
u
lts
o
f
s
e
g
m
en
tatio
n
m
et
h
o
d
b
y
th
e
o
r
ig
i
n
al
J
SE
G
alg
o
r
ith
m
(
o
n
t
h
e
le
f
t
co
l
u
m
n
)
an
d
th
e
r
esp
ec
ti
v
e
m
o
d
if
ied
J
SEG
tech
n
iq
u
e
(
o
n
t
h
e
r
i
g
h
t
co
lu
m
n
)
.
Fi
g
u
r
e
6
s
h
o
w
s
t
h
e
r
es
u
lt
s
o
f
s
eg
m
e
n
tatio
n
m
et
h
o
d
b
y
t
h
e
o
r
ig
in
al
J
SEG
a
l
g
o
r
ith
m
(
o
n
t
h
e
f
ir
s
t
r
o
w
)
an
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
Mo
d
ified
JS
E
G
a
lg
o
r
ith
m
fo
r
r
ed
u
cin
g
o
ve
r
-
s
eg
me
n
ta
tio
n
p
r
o
b
lems in
…
(
Mo
h
a
mma
d
S
a
mee
r
A
lo
u
n
)
5249
th
e
r
esp
ec
tiv
e
m
o
d
if
ied
J
SE
G
tech
n
iq
u
e
(
o
n
th
e
s
ec
o
n
d
e
r
o
w
)
to
r
ed
u
ce
o
v
er
-
s
eg
m
e
n
tatio
n
p
r
o
b
lem
o
n
3
s
elec
ted
s
a
m
p
le
s
o
f
co
r
al
r
ee
f
s
i
m
a
g
es
at
d
if
f
er
en
t
u
n
d
er
w
a
ter
en
v
ir
o
n
m
e
n
t
.
B
y
ap
p
ly
in
g
th
e
o
r
ig
in
al
J
SEG
alg
o
r
ith
m
,
i
t
ca
n
b
e
ap
p
ar
en
tl
y
o
b
s
er
v
e
d
th
at
w
h
en
t
h
e
J
SE
G
s
ca
le
o
f
th
e
s
e
g
m
en
tatio
n
is
s
et
to
o
lo
w
,
it
lead
s
to
u
n
d
er
-
s
eg
m
e
n
tatio
n
.
W
h
er
ea
s
,
if
th
e
J
SEG
s
ca
le
i
s
s
et
to
to
o
h
ig
h
,
it
r
esu
lted
in
o
v
er
-
s
e
g
m
e
n
tat
io
n
of
th
e
co
r
al
r
ee
f
s
.
T
h
er
ef
o
r
e,
it
is
a
ch
al
len
g
i
n
g
p
r
o
ce
s
s
to
f
i
n
d
t
h
e
co
r
r
ec
t
J
SEG
s
ca
le
t
h
at
lead
s
to
th
e
b
es
t
s
eg
m
e
n
tatio
n
r
esu
lts
o
f
d
i
f
f
e
r
e
n
t
co
r
al
r
ee
f
t
y
p
es
b
y
u
s
i
n
g
th
e
o
r
ig
i
n
al
J
SEG
al
g
o
r
it
h
m
.
A
lt
h
o
u
g
h
th
is
alg
o
r
ith
m
ca
n
a
u
to
m
at
icall
y
s
eg
m
e
n
t
th
e
o
b
j
ec
ts
,
it
h
as
t
h
e
p
r
o
b
lem
o
f
eit
h
er
u
n
d
er
o
r
o
v
er
-
s
e
g
m
en
tatio
n
.
T
h
e
u
s
er
h
as to
f
in
d
t
h
e
co
r
r
ec
t setti
n
g
o
f
t
h
e
J
SEG
s
ca
le
to
b
e
u
s
ed
f
o
r
r
eg
i
o
n
s
e
g
m
en
tati
o
n
in
t
h
ese
f
ig
u
r
es
.
I
n
co
n
tr
ast
to
t
h
e
o
r
ig
i
n
al
J
SEG
alg
o
r
it
h
m
,
t
h
e
m
o
d
i
f
ie
d
J
SEG
alg
o
r
ith
m
o
p
er
ates
by
d
ir
ec
t
ly
r
ed
u
ce
s
th
e
n
u
m
b
er
o
f
r
eg
io
n
s
th
at
h
a
v
e
co
m
m
o
n
co
lo
r
-
te
x
tu
r
e
s
i
m
ilar
it
y
i
n
th
e
i
m
a
g
e.
T
h
e
m
er
g
e
d
r
eg
io
n
s
tag
e
i
n
o
r
ig
i
n
al
J
SEG
a
l
g
o
r
it
h
m
h
as
b
ee
n
r
ep
lace
d
w
i
th
r
eg
io
n
m
er
g
i
n
g
u
s
i
n
g
t
h
e
n
e
w
l
y
p
r
o
p
o
s
ed
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t.
T
h
e
r
est
o
f
t
h
e
alg
o
r
ith
m
i
s
s
till
f
o
llo
w
i
n
g
t
h
e
o
r
ig
in
al
J
SEG
al
g
o
r
ith
m
as
s
h
o
w
n
in
Fig
u
r
e
3
.
T
h
e
ef
f
ec
t
o
f
t
h
is
m
o
d
if
ied
m
et
h
o
d
is
,
it
r
ed
u
ce
s
th
e
n
u
m
b
er
o
f
r
eg
io
n
s
f
o
r
test
ed
i
m
ag
e
as
co
m
p
ar
ed
to
th
e
o
r
ig
in
al
J
SEG
al
g
o
r
ith
m
.
B
y
ap
p
l
y
i
n
g
t
h
e
co
lo
r
m
ea
n
s
a
n
d
co
v
ar
ia
n
ce
a
t
t
h
e
n
e
ig
h
b
o
r
in
g
r
e
g
io
n
s
,
it
m
an
a
g
ed
to
r
ed
u
ce
th
e
o
v
e
r
-
s
e
g
m
e
n
tat
io
n
is
s
u
e
i
n
th
e
o
r
ig
i
n
al
J
SEG
alg
o
r
ith
m
as
o
p
p
o
s
ed
to
th
e
w
id
el
y
e
m
p
lo
y
ed
m
ea
n
s
co
lo
r
m
ea
s
u
r
e.
As
ca
n
b
e
o
b
s
er
v
ed
f
r
o
m
t
h
ese
f
ig
u
r
es
,
th
e
n
u
m
b
er
o
f
r
e
g
io
n
s
ar
e
d
ep
en
d
o
n
th
e
p
r
eset
th
r
e
s
h
o
ld
v
al
u
es
,
w
h
ic
h
w
e
alr
ea
d
y
u
s
ed
to
m
er
g
e
t
h
e
r
eg
io
n
s
b
y
e
x
p
er
i
m
e
n
ts
.
T
h
e
f
i
n
al
i
m
ag
e
r
ef
er
s
to
th
e
las
t
s
e
g
m
e
n
ted
i
m
ag
e
a
n
d
ca
n
b
e
co
m
p
ar
ed
d
ir
ec
tl
y
to
th
eir
r
esp
ec
ti
v
e
co
u
n
t
er
p
ar
t
in
th
e
o
r
ig
i
n
al
J
SEG
alg
o
r
ith
m
.
Fig
u
r
e
3
.
T
h
e
s
eg
m
e
n
tatio
n
r
esu
lt
s
o
f
t
h
e
f
ir
s
t te
s
t
i
m
a
g
e
Fig
u
r
e
4
.
T
h
e
s
eg
m
e
n
tatio
n
r
esu
lt
s
o
f
t
h
e
s
ec
o
n
d
tes
t
i
m
a
g
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
2
4
4
-
5
2
5
2
5250
Fig
u
r
e
5
.
T
h
e
s
eg
m
e
n
tatio
n
r
esu
lt
s
o
f
t
h
e
th
ir
d
test
i
m
a
g
e
4.
CO
NCLU
SI
O
N
I
n
t
h
is
p
ap
er
,
a
m
o
d
i
f
ied
J
S
E
G
alg
o
r
it
h
m
h
a
s
b
ee
n
p
r
o
p
o
s
ed
w
h
er
e
t
h
e
m
er
g
e
r
eg
io
n
p
h
a
s
e
i
n
th
e
o
r
ig
i
n
al
J
SEG
al
g
o
r
ith
m
h
as
b
ee
n
r
ep
lace
d
w
it
h
r
eg
io
n
m
er
g
i
n
g
u
s
in
g
s
i
m
i
lar
it
y
m
ea
s
u
r
e
o
f
m
ea
n
an
d
co
v
ar
ian
ce
o
f
co
lo
r
s
tati
s
tics
.
T
h
e
m
o
d
i
f
ied
alg
o
r
it
h
m
co
u
ld
au
to
m
atica
ll
y
s
eg
m
e
n
t
t
h
e
r
eg
io
n
s
o
f
th
e
test
i
m
a
g
es
b
etter
t
h
a
n
t
h
e
o
r
ig
i
n
al
J
SEG
alg
o
r
it
h
m
.
T
h
e
n
e
w
i
m
p
le
m
e
n
tatio
n
h
a
s
alle
v
iat
ed
th
e
p
r
o
b
le
m
o
f
o
v
er
-
s
e
g
m
en
tatio
n
in
th
e
o
r
ig
in
a
l
J
SEG
al
g
o
r
ith
m
.
E
v
en
th
o
u
g
h
t
h
e
m
o
d
if
ied
al
g
o
r
it
h
m
p
r
o
v
id
e
d
ir
ec
t
s
eg
m
e
n
tatio
n
,
h
o
w
e
v
er
s
o
m
e
o
f
t
h
e
r
eg
io
n
s
s
till
b
ee
n
in
c
o
r
r
ec
tly
s
e
g
m
e
n
ted
.
T
h
is
p
r
o
b
le
m
ar
is
e
s
d
u
e
to
th
e
co
m
p
le
x
n
at
u
r
e
o
f
u
n
d
er
w
ater
co
r
al
r
ee
f
i
m
a
g
e
s
,
a
n
d
w
e
i
n
te
n
d
to
s
o
lv
e
th
is
p
r
o
b
lem
b
y
u
s
i
n
g
th
e
co
m
p
o
s
itio
n
o
f
te
x
tu
r
e,
co
l
o
r
,
an
d
s
h
ap
e
in
th
e
f
u
tu
r
e
r
es
ea
r
ch
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
e
au
th
o
r
o
f
t
h
i
s
p
ap
er
w
o
u
ld
li
k
e
to
ac
k
n
o
w
led
g
e
th
e
I
n
s
ti
tu
te
o
f
Oce
o
n
o
g
r
ap
h
y
a
n
d
E
n
v
ir
o
n
m
e
n
t,
U
n
iv
er
s
iti Ma
la
y
s
ia
T
er
en
g
g
an
u
f
o
r
s
u
p
p
l
y
i
n
g
th
e
d
ataset
u
s
ed
in
t
h
is
s
tu
d
y
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
R.
V
a
n
tara
m
a
n
d
E.
S
a
b
e
r,
"
S
u
rv
e
y
o
f
Co
n
te
m
p
o
ra
ry
T
r
e
n
d
s
in
Co
lo
r
Im
a
g
e
S
e
g
m
e
n
tatio
n
,
"
J
o
u
r
n
a
l
o
f
El
e
c
tro
n
ic
Ima
g
i
n
g
,
v
o
l
.
2
1
(
4
)
,
p
p
.
1
-
28
,
2
0
1
2
.
[2
]
G
.
K.
S
e
e
rh
a
a
n
d
R.
Ka
u
r
,
"
Re
v
ie
w
o
n
Re
c
e
n
t
Im
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
s,"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l
.
5
(2
),
p
p
.
1
0
9
,
2
0
1
3
.
[3
]
W
.
G
u
n
a
w
a
n
,
e
t
al
.
,
"
F
u
z
z
y
Re
g
io
n
M
e
rg
in
g
u
sin
g
F
u
z
z
y
S
i
m
il
a
rit
y
M
e
a
su
re
m
e
n
t
o
n
Im
a
g
e
S
e
g
m
e
n
tatio
n
,
"
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
,
v
o
l.
7
(6
),
p
p
.
3
4
0
2
-
3
4
1
0
,
De
c
.
2
0
1
7
.
[4
]
O.
S
a
li
m
a
,
e
t
a
l
.
,
"
S
p
a
ti
a
l
In
f
o
rm
a
ti
o
n
b
a
se
d
Im
a
g
e
Clu
ste
rin
g
w
it
h
a
S
w
a
rm
A
p
p
ro
a
c
h
"
,
IAE
S
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Arti
f
icia
l
I
n
telli
g
e
n
c
e
(
IJ
-
AI)
,
v
o
l.
1
(3
),
p
p
.
1
4
9
-
1
6
0
,
2
0
1
2
.
[5
]
Erw
in
,
S
a
p
a
ru
d
i
n
,
a
n
d
W
.
S
a
p
u
tr
i,
"
H
y
b
rid
M
u
lt
il
e
v
e
l
T
h
re
sh
o
ld
i
n
g
a
n
d
Im
p
ro
v
e
d
Ha
r
m
o
n
y
S
e
a
rc
h
A
lg
o
rit
h
m
f
o
r
S
e
g
m
e
n
tatio
n
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
),
v
o
l
.
8
(6
),
p
p
.
4
5
9
3
-
4
6
0
2
,
2
0
1
8
.
[6
]
U.
S
a
lam
a
h
,
e
t
a
l
.
,
"
In
c
o
r
p
o
ra
ti
n
g
In
d
e
x
o
f
F
u
z
z
in
e
ss
a
n
d
A
d
a
p
ti
v
e
T
h
re
sh
o
l
d
in
g
f
o
r
I
m
a
g
e
S
e
g
m
e
n
tatio
n
,
"
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
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l.
8
(4
)
,
p
p
.
2
4
0
6
,
2
0
1
8
.
[7
]
A
.
S
.
A
.
S
a
la
m
,
e
t
a
l
.
,
"
Co
mp
a
riso
n
o
f
Ed
g
e
De
tec
ti
o
n
T
e
c
h
n
iq
u
e
s
fo
r
M
7
S
u
b
typ
e
L
e
u
k
e
mic
Ce
ll
in
ter
ms
o
f
No
ise
Fi
lt
e
rs
a
n
d
T
h
re
sh
o
l
d
Va
l
u
e
,
"
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
p
p
li
e
d
P
h
o
to
n
ics
a
n
d
El
e
c
tro
n
ics
2
0
1
7
(In
CA
P
E2
0
1
7
),
Av
il
li
o
n
P
o
rt
Dic
k
so
n
,
M
a
lay
sia
,
Ed
it
e
d
b
y
M
o
h
a
m
a
d
Ha
li
m
A
b
d
.
W
a
h
id
;
E
P
J W
e
b
o
f
Co
n
f
e
re
n
c
e
s,
v
o
l.
1
6
2
,
2
0
1
7
.
[8
]
W
.
Kh
a
n
,
"
I
m
a
g
e
S
e
g
m
e
n
tatio
n
T
e
c
h
n
iq
u
e
s:
A
S
u
rv
e
y
,
"
J
o
u
rn
a
l
o
f
Ima
g
e
a
n
d
Gr
a
p
h
ics
,
v
o
l.
1
(4
),
p
p
.
1
6
6
-
1
7
0
,
2
0
1
3
.
[9
]
A
.
G
.
Kib
riaa
n
d
M
.
M
.
Isla
m
,
"
Co
lo
rIm
a
g
e
S
e
g
m
e
n
tatio
n
u
s
in
g
V
isi
b
le
C
o
lo
rDif
f
e
re
n
c
e
a
n
d
Ca
n
n
y
Ed
g
e
De
tec
to
r,
"
Co
mp
u
ter
a
n
d
I
n
f
o
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
(
ICCIT
).
IEE
E
,
p
p
.
1
3
8
-
1
4
3
,
2
0
1
2
.
[1
0
]
Y.
Be
n
-
S
h
a
b
a
t,
e
t
a
l
.
,
"
G
ra
p
h
Ba
s
e
d
Ov
e
r
-
se
g
m
e
n
tatio
n
M
e
t
h
o
d
s
f
o
r
3
D P
o
i
n
t
Cl
o
u
d
s,"
Co
mp
u
ter
V
isio
n
a
n
d
Im
a
g
e
Un
d
e
rs
t
a
n
d
in
g
,
vol
.
1
7
4
,
p
p
.
1
2
-
2
3
.
2
0
1
8
.
[1
1
]
A
.
Ka
u
r,
a
n
d
Y.
Ra
n
d
h
a
w
a
,
"
Im
a
g
e
S
e
g
m
e
n
tatio
n
u
sin
g
M
o
d
if
ied
k
-
M
e
a
n
s
A
lg
o
rit
h
m
a
n
d
JSE
G
M
e
th
o
d
"
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
a
n
d
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
3
(6
),
2
0
1
4
.
[1
2
]
Y.
De
n
g
a
n
d
B.
S
.
M
a
n
j
u
n
a
t
h
,
"
Un
su
p
e
rv
ise
d
S
e
g
m
e
n
tatio
n
o
f
Co
l
o
r
-
T
e
x
tu
re
Re
g
io
n
s
in
Im
a
g
e
s
a
n
d
V
id
e
o
"
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Pa
t
ter
n
An
a
lys
is a
n
d
M
a
c
h
in
e
In
telli
g
e
n
c
e
,
v
o
l.
2
3
(
8
),
p
p
.
8
0
0
-
8
1
0
,
2
0
0
1
.
[1
3
]
Y.
De
n
g
,
e
t
a
l
.,"
Pee
rG
ro
u
p
Fi
lt
e
rin
g
a
n
d
Per
c
e
p
tu
a
l
Co
l
o
rIm
a
g
e
Qu
a
n
t
iza
ti
o
n
,
"
I
n
Circu
i
ts
a
n
d
S
y
ste
m
s,
1
9
9
9
.
IS
CA
S
'
9
9
.
P
ro
c
e
e
d
in
g
s
o
f
th
e
1
9
9
9
IE
EE
In
ter
n
a
ti
o
n
a
l
S
y
m
p
o
siu
m
,
v
o
l.
4
,
p
p
.
2
1
-
2
4
,
1
9
9
9
.
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
Mo
d
ified
JS
E
G
a
lg
o
r
ith
m
fo
r
r
ed
u
cin
g
o
ve
r
-
s
eg
me
n
ta
tio
n
p
r
o
b
lems in
…
(
Mo
h
a
mma
d
S
a
mee
r
A
lo
u
n
)
5251
[1
4
]
Y.
W
.
Zh
a
n
g
,
e
t
a
l
.
,
"
I
m
a
g
e
S
e
g
m
e
n
tatio
n
w
it
h
T
e
x
tu
re
Clu
ste
rin
g
b
a
se
d
JSE
G
,
"
M
a
c
h
in
e
L
e
a
rn
i
n
g
a
n
d
Cy
b
e
rn
e
ti
c
s
(
ICM
L
C),
v
o
l.
2
,
p
p
.
5
9
9
-
6
0
3
,
2
0
1
5
.
[1
5
]
M
.
S
.
A
lo
u
n
,
e
t
a
l
.
,
"
Im
p
ro
v
e
d
Co
ra
l
Re
e
f
I
m
a
g
e
s
S
e
g
m
e
n
tatio
n
u
si
n
g
M
o
d
if
ied
JSE
G
A
lg
o
rit
h
m
,
"
J
o
u
rn
a
l
o
f
T
e
lec
o
mm
u
n
ica
ti
o
n
,
El
e
c
tro
n
ic a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
J
T
EC),
v
o
l.
9
(
3
-
5
)
,
p
p
.
2
1
-
2
6
,
2
0
1
7
.
[1
6
]
M
.
S
.
Hitam
,
e
t
a
l
.,
"
M
ix
tu
re
Co
n
tras
t
L
i
m
it
e
d
A
d
a
p
ti
v
e
Histo
g
ra
m
Eq
u
a
li
z
a
ti
o
n
f
o
r
Un
d
e
rw
a
ter
I
m
a
g
e
En
h
a
n
c
e
m
e
n
t,
"
2
0
1
3
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s
T
e
c
h
n
o
lo
g
y
(I
CCAT
)
.
IEE
E,
p
p
.
1
-
5
,
2
0
1
3
.
[1
7
]
K.
Iq
b
a
l,
e
t
a
l
.,
"
Un
d
e
rw
a
ter
I
m
a
g
e
En
h
a
n
c
e
m
e
n
t
u
sin
g
a
n
In
teg
ra
ted
Co
lo
u
r
M
o
d
e
l,
"
IAE
NG
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l.
3
4
(
2
).
2
0
0
7
.
[1
8
]
J.
Y.
Ch
ian
g
,
e
t
a
l
.
,
"
Un
d
e
rwa
t
e
rI
m
a
g
e
En
h
a
n
c
e
m
e
n
t
b
y
W
a
v
e
len
g
th
Co
m
p
e
n
sa
ti
o
n
a
n
d
De
h
a
z
in
g
(W
CID)"
,
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Ima
g
e
Pro
c
e
ss
in
g
,
v
o
l.
2
1
(
4
),
p
p
.
1
7
5
6
-
1
7
6
9
,
2
0
1
2
.
[1
9
]
A
.
M
a
h
m
o
o
d
,
e
t
a
l
.
,
"
D
e
e
p
L
e
a
rn
in
g
f
o
r
Co
ra
l
Clas
si
f
ica
ti
o
n
,
"
Ha
n
d
b
o
o
k
o
f
Ne
u
ra
l
Co
m
p
u
tatio
n
,
p
p
.
3
8
3
-
4
0
1
,
2
0
1
7
.
[2
0
]
F
.
,
L
i,
e
t
a
l
.
,
"
Un
su
p
e
rv
ise
d
Im
a
g
e
S
e
g
me
n
t
a
ti
o
n
u
sin
g
L
o
c
a
l
Ho
mo
g
e
n
e
it
y
An
a
lys
is,"
P
ro
c
e
e
d
in
g
s
o
f
th
e
2
0
0
3
In
tern
a
ti
o
n
a
l
S
y
m
p
o
siu
m
o
n
Circ
u
it
s a
n
d
S
y
ste
m
s,
v
o
l.
2
,
2
0
0
3
.
[2
1
]
Y.
Zh
e
n
g
,
e
t
a
l
.
,
"
Un
su
p
e
rv
ise
d
S
e
g
me
n
ta
ti
o
n
o
n
Ima
g
e
wit
h
J
S
EG
u
sin
g
S
o
ft
Cla
ss
M
a
p
,"
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
I
n
telli
g
e
n
t
Da
ta E
n
g
in
e
e
rin
g
a
n
d
A
u
to
m
a
ted
L
e
a
rn
in
g
,
S
p
ri
n
g
e
r,
Be
rli
n
,
He
id
e
lb
e
rg
,
p
p
.
1
9
7
-
2
0
2
,
2
0
0
4
.
[2
2
]
Y.
C.
Ch
a
n
g
,
e
t
a
l
.
,
"
Co
lo
r
-
T
e
x
tu
re
S
e
g
m
e
n
tatio
n
o
f
M
e
d
ica
l
I
m
a
g
e
s
B
a
se
d
o
n
L
o
c
a
l
Co
n
tr
a
st
In
f
o
r
m
a
ti
o
n
,
"
Co
mp
u
t
a
ti
o
n
a
l
I
n
telli
g
e
n
c
e
a
n
d
B
io
in
f
o
rm
a
ti
c
s
a
n
d
Co
m
p
u
t
a
ti
o
n
a
l
Bi
o
lo
g
y
,
p
p
.
4
8
8
-
4
9
3
,
2
0
0
7
.
[2
3
]
Y.
G
.
W
a
n
g
,
e
t
a
l
.
,
"
Co
lo
r
–
T
e
x
t
u
re
Im
a
g
e
S
e
g
m
e
n
tatio
n
b
y
In
teg
ra
ti
n
g
Dire
c
ti
o
n
a
l
O
p
e
ra
to
rs
i
n
to
JSE
G
M
e
th
o
d
,
"
Pa
tt
e
rn
Rec
o
g
n
it
io
n
L
e
tt
e
rs
,
v
o
l
2
7
(1
6
),
p
p
.
1
9
8
3
-
1
9
9
0
,
2
0
0
6
.
[2
4
]
A
.
G
.
Kib
riaa
n
d
M
.
M
.
Isla
m
,
"
Re
d
u
c
ti
o
n
o
f
Ov
e
r
-
S
e
g
m
e
n
tatio
n
in
J
S
EG
u
sin
g
Ca
n
n
y
Ed
g
e
De
tec
to
r
2
0
1
2
,"
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
I
n
fo
r
ma
ti
c
s,
El
e
c
tro
n
ics
&
Vi
sio
n
(
ICIEV
)
.
IEE
E
,
p
p
.
6
5
-
6
9
,
2
0
1
2
.
[2
5
]
K.
S
.
Ko
m
a
ti
,
e
t
a
l
.
,
"
F
ra
c
tal
-
JSE
G
:
JSE
G
u
sin
g
a
n
Ho
m
o
g
e
n
e
it
y
M
e
a
su
re
m
e
n
t
b
a
se
d
o
n
L
o
c
a
l
F
ra
c
tal
De
sc
rip
to
r,
"
XX
II
Bra
zili
a
n
S
y
mp
o
siu
m
o
n
Co
mp
u
ter
Gr
a
p
h
ics
a
n
d
Ima
g
e
Pro
c
e
ss
in
g
.
IEE
E,
p
p
.
2
5
3
-
2
6
0
.
2
0
0
9
.
[2
6
]
H.S
im
a
,
e
t
a
l
.
,
"
Bo
tt
o
m
-
Up
M
e
rg
in
g
S
e
g
m
e
n
tatio
n
f
o
r
Co
lo
r
Im
a
g
e
s
w
it
h
Co
m
p
lex
A
re
a
s,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
S
y
ste
ms
,
M
a
n
,
a
n
d
Cy
b
e
rn
e
ti
c
s: S
y
ste
ms
,
v
o
l
4
8
(3
)
,
p
p
.
3
5
4
-
3
6
5
,
2
0
1
8
.
[2
7
]
W
.
Ya
n
g
,
e
t
a
l
.,
"
I
m
a
g
e
Tac
ti
le
P
e
rc
e
p
ti
o
n
w
it
h
a
n
Im
p
ro
v
e
d
JSE
G
A
lg
o
rit
h
m
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Per
fo
rm
a
b
il
i
ty E
n
g
in
e
e
rin
g
,
v
o
l
1
4
(1
),
p
p
.
7
7
,
2
0
1
8
.
[2
8
]
G
.
A
ll
e
n
a
n
d
M
.
G
.
Ro
b
e
rt,
"
Vec
to
r Qu
a
n
ti
z
a
ti
o
n
a
n
d
S
i
g
n
a
l
C
o
mp
re
ss
io
n
,
"
S
p
i
n
g
e
r,
1
9
9
2
.
[2
9
]
R.
O.
Du
d
a
a
n
d
P
.
E.
Ha
rt,
"
P
a
tt
e
r
n
Clas
sif
ica
ti
o
n
a
n
d
S
c
e
n
e
A
n
a
l
y
sis,"
Ne
w
Yo
rk
:
Jo
h
n
W
il
e
y
a
n
d
S
o
n
s,
1
9
7
0
.
[3
0
]
G
.
P
.
Ba
las
u
b
r
a
m
a
n
ian
,
e
t
a
l
.,
"
Un
s
u
p
e
rv
ise
d
Co
l
o
rIm
a
g
e
S
e
g
me
n
ta
t
io
n
u
si
n
g
a
Dy
n
a
mic
Co
l
o
rG
ra
d
ien
t
T
h
re
sh
o
l
d
in
g
Al
g
o
rit
h
m,"
I
n
Hu
m
a
n
V
isio
n
a
n
d
El
e
c
tro
n
ic
Im
a
g
in
g
X
III,
v
o
l.
6
8
0
6
,
p
p
.
6
8
0
6
1
H
-
6
8
6
0
1
H9
.
In
tern
a
ti
o
n
a
l
S
o
c
iety
f
o
r
Op
ti
c
s a
n
d
P
h
o
to
n
ics
,
2
0
0
8
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
M
o
h
a
m
m
a
d
S
a
m
e
e
r
Al
o
u
n
re
c
e
iv
e
d
h
is M
a
ste
r
d
e
g
re
e
in
2
0
1
3
a
n
d
h
e
is cu
rre
n
tl
y
a
P
h
.
D
stu
d
e
n
t
a
t
th
e
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
c
s
a
n
d
A
p
p
li
e
d
M
a
t
h
e
m
a
ti
c
s,
U
n
iv
e
rsit
i
M
a
la
y
sia
Tere
n
g
g
a
n
u
.
His res
e
a
rc
h
in
tere
sts a
re
f
o
c
u
se
d
on
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
p
a
tt
e
rn
r
e
c
o
g
n
it
io
n
.
M
u
h
a
m
m
a
d
S
u
z
u
r
i
H
it
a
m
o
b
t
a
in
e
d
h
is
Ba
c
h
e
lo
r
o
f
In
d
u
stria
l
T
e
c
h
n
o
lo
g
y
(
B.
T
e
c
h
(Ho
n
s.)
f
ro
m
Un
iv
e
rsiti
S
a
in
s
M
a
la
y
sia
a
n
d
P
h
.
D
d
e
g
re
e
f
ro
m
Un
iv
e
rsity
o
f
L
e
e
d
s,
Un
it
e
d
Kin
g
d
o
m
.
He
is
c
u
rre
n
tl
y
a
P
ro
f
e
so
r
a
t
th
e
S
c
h
o
o
l
o
f
In
f
o
r
m
a
ti
c
s
a
n
d
A
p
p
li
e
d
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsiti
M
a
la
y
sia
T
e
r
e
n
g
g
a
n
u
.
His
re
se
a
rc
h
in
tere
sts
a
re
f
o
c
u
se
d
o
n
ima
g
e
p
ro
c
e
ss
in
g
,
c
o
m
p
u
tatio
n
a
l
in
telli
g
e
n
c
e
a
n
d
r
o
b
o
ti
c
s.
Wa
n
N
u
r
a
l
J
a
w
a
h
ir
H
j
Wa
n
Yu
ss
o
f
re
c
e
iv
e
d
h
e
r
B.
IT
in
S
o
f
tw
a
r
e
En
g
in
e
e
rin
g
a
n
d
M
.
S
c
.
in
A
rti
f
icia
l
In
telli
g
e
n
c
e
f
ro
m
Ko
lej
Un
iv
e
rsiti
S
a
in
s
d
a
n
T
e
k
n
o
lo
g
i
M
a
la
y
sia
.
In
2
0
1
4
,
sh
e
o
b
tain
e
d
h
e
r
P
h
.
D.
f
ro
m
Un
iv
e
rsiti
M
a
l
a
y
sia
T
e
re
n
g
g
a
n
u
.
S
h
e
is
c
u
rre
n
tl
y
a
s
e
n
io
r
lec
tu
re
r
a
t
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
c
s
a
n
d
A
p
p
li
e
d
M
a
th
e
m
a
ti
c
s,
Un
iv
e
rsiti
M
a
la
y
sia
T
e
r
e
n
g
g
a
n
u
.
He
r
re
se
a
rc
h
in
tere
sts
a
r
e
in
2
D/
3
D i
m
a
g
e
a
n
a
l
y
sis a
n
d
u
n
d
e
rwa
ter v
id
e
o
p
ro
c
e
ss
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
6
,
Dec
em
b
er
2
0
1
9
:
5
2
4
4
-
5
2
5
2
5252
Abd
u
l
Az
iz
K
Abd
u
l
H
a
m
i
d
is
a
se
n
io
r
l
e
c
tu
re
r
at
th
e
S
c
h
o
o
l
o
f
In
f
o
rm
a
ti
c
s
a
n
d
A
p
p
li
e
d
M
a
th
e
m
a
ti
c
s
,
Un
iv
e
rsiti
M
a
la
y
si
a
Tere
n
g
g
a
n
u
.
He
re
c
e
i
v
e
d
h
is
P
h
.
D
in
c
o
m
p
u
ter
sc
ien
c
e
f
ro
m
Un
iv
e
rsiti
Ke
b
a
n
g
sa
a
n
M
a
la
y
sia
in
2
0
1
4
a
n
d
h
e
is
a
c
ti
v
e
ly
in
v
o
lv
e
d
in
a
m
u
lt
it
u
d
e
o
f
tec
h
n
ica
l
p
ro
jec
ts
a
c
ro
ss
a
b
ro
a
d
ra
n
g
e
o
f
se
c
to
rs,
in
c
lu
d
i
n
g
f
in
a
n
c
ial,
m
a
n
u
fa
c
tu
rin
g
,
p
o
rt
m
a
n
a
g
e
m
e
n
t
a
n
d
e
d
u
c
a
ti
o
n
.
His res
e
a
rc
h
in
tere
st i
n
c
lu
d
e
im
a
g
e
p
ro
c
e
ss
in
g
,
p
a
tt
e
rn
r
e
c
o
g
n
it
io
n
a
n
d
d
a
ta s
c
ien
c
e
.
Za
in
u
d
d
i
n
B
a
c
h
o
k
re
c
e
iv
e
d
h
is
b
a
c
h
e
lo
r
d
e
g
re
e
in
f
ish
e
ries
sc
ien
c
e
f
ro
m
Un
iv
e
rsiti
P
u
tra
M
a
la
y
sia
a
n
d
P
h
.
D
in
m
a
rin
e
a
n
d
e
n
v
iro
n
m
e
n
tal
sc
ien
c
e
f
ro
m
U
n
iv
e
rsity
o
f
th
e
R
y
u
k
y
u
s,
J
a
p
a
n
.
His
c
u
rre
n
t
re
se
a
rc
h
in
tere
st
is
in
m
a
rin
e
sc
i
e
n
c
e
a
n
d
m
a
rin
e
b
io
lo
g
y
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
f
e
ss
o
r
a
t
th
e
Un
iv
e
rsiti
M
a
lay
s
ia T
e
re
n
g
g
a
n
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.