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.
6
,
No
.
6
,
Dec
em
b
er
201
6
,
p
p
.
2
7
8
9
~
2
7
9
6
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
1
5
6
4
2789
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Ana
ly
z
ing
the
O
p
ti
m
a
l
P
er
for
m
a
nc
e
o
f
P
est I
m
a
g
e
Seg
m
en
tatio
n usi
ng
Non Linea
r
O
bject
iv
e
Asses
s
m
e
nts
Siv
a
Sa
ng
a
ri
A
1
,
Sa
ra
s
wa
dy
D
2
1
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
G
M
R
In
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
V
isa
k
a
p
a
tt
in
a
m
,
In
d
ia
2
De
p
a
rt
m
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
,
P
o
n
d
ich
e
rry
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
P
o
n
d
ich
e
rry
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
1
5
,
2
0
1
6
R
ev
i
s
ed
Oct
3
1
,
201
6
A
cc
ep
ted
No
v
1
4
,
2
0
1
6
In
m
o
d
e
rn
a
g
ricu
lt
u
ra
l
f
ield
,
p
e
st
d
e
tec
ti
o
n
is
a
m
a
jo
r
ro
le
in
p
la
n
t
c
u
lt
iv
a
ti
o
n
.
I
n
o
rd
e
r
to
i
n
c
re
a
se
t
h
e
P
r
o
d
u
c
ti
o
n
ra
te
o
f
a
g
ricu
lt
u
ra
l
f
ield
,
th
e
p
re
se
n
c
e
o
f
w
h
it
e
f
l
y
p
e
sts
w
h
ich
c
a
u
se
lea
f
d
isc
o
lo
ra
ti
o
n
is
th
e
m
a
jo
r
p
ro
b
le
m
.
T
h
is
e
m
p
h
a
siz
e
s
th
e
n
e
c
e
ss
it
y
o
f
i
m
a
g
e
se
g
m
e
n
tat
io
n
,
w
h
ich
d
iv
id
e
s
a
n
im
a
g
e
in
to
p
a
rts
th
a
t
h
a
v
e
stro
n
g
c
o
rre
latio
n
s
w
it
h
o
b
jec
ts
to
re
f
le
c
t
th
e
a
c
tu
a
l
in
f
o
r
m
a
ti
o
n
c
o
ll
e
c
ted
f
ro
m
th
e
re
a
l
w
o
rld
.
I
m
a
g
e
p
ro
c
e
ss
in
g
is
a
ff
e
c
ted
b
y
il
lu
m
in
a
ti
o
n
c
o
n
d
it
io
n
s,
r
a
n
d
o
m
n
o
ise
a
n
d
e
n
v
iro
n
m
e
n
tal
d
istu
r
b
a
n
c
e
s
d
u
e
to
a
tm
o
sp
h
e
ric
p
re
ss
u
re
o
r
tem
p
e
ra
tu
re
f
lu
c
tu
a
ti
o
n
.
T
h
e
q
u
a
li
ty
o
f
p
e
st
i
m
a
g
e
s
is
d
irec
tl
y
a
ffe
c
ted
b
y
a
t
m
o
sp
h
e
re
m
e
d
iu
m
,
p
re
ss
u
re
a
n
d
tem
p
e
ra
tu
re
.
T
h
e
f
u
z
z
y
c
m
e
a
n
s
(F
CM
)
h
a
v
e
b
e
e
n
p
ro
p
o
se
d
to
id
e
n
ti
f
y
a
c
c
u
ra
te
lo
c
a
ti
o
n
o
f
w
h
it
e
f
l
y
p
e
s
ts.
T
h
e
w
a
ters
h
e
d
tran
sf
o
r
m
h
a
s
in
tere
stin
g
p
ro
p
e
rti
e
s
th
a
t
m
a
k
e
it
u
se
f
u
l
f
o
r
m
a
n
y
d
iff
e
re
n
t
i
m
a
g
e
se
g
m
e
n
tatio
n
a
p
p
li
c
a
ti
o
n
s:
it
is
sim
p
le
a
n
d
i
n
tu
it
iv
e
,
c
a
n
b
e
p
a
ra
ll
e
li
z
e
d
,
a
n
d
a
lw
a
y
s
p
ro
d
u
c
e
s
a
c
o
m
p
lete
d
iv
isio
n
o
f
th
e
im
a
g
e
.
Ho
w
e
v
e
r,
w
h
e
n
a
p
p
li
e
d
to
p
e
st
im
a
g
e
a
n
a
l
y
sis,
it
h
a
s
i
m
p
o
rtan
t
d
ra
w
b
a
c
k
s
(o
v
e
r
se
g
m
e
n
tatio
n
,
se
n
siti
v
it
y
to
n
o
ise
).
In
th
is
p
a
p
e
r,
p
e
st
ima
g
e
s
e
g
m
e
n
tatio
n
u
sin
g
m
a
r
k
e
r
c
o
n
tro
ll
e
d
w
a
t
e
rsh
e
d
se
g
m
e
n
tatio
n
is
p
re
se
n
ted
.
Ob
jec
ti
v
e
o
f
th
is
p
a
p
e
r
is
s
e
g
m
e
n
ti
n
g
t
h
e
p
e
st
i
m
a
g
e
a
n
d
c
o
m
p
a
rin
g
t
h
e
re
su
lt
s
o
f
f
u
z
z
y
c
m
e
a
n
s
a
lg
o
rit
h
m
a
n
d
m
a
rk
e
r
c
o
n
tro
ll
e
d
w
a
ters
h
e
d
tran
sf
o
rm
a
ti
o
n
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
a
n
i
m
a
g
e
se
g
m
e
n
tatio
n
a
lg
o
rit
h
m
s
a
re
c
o
m
p
a
re
d
u
sin
g
n
o
n
li
n
e
a
r
o
b
jec
ti
v
e
a
ss
e
ss
m
e
n
t
o
r
t
h
e
q
u
a
n
ti
tativ
e
m
e
a
su
re
s
li
k
e
stru
c
tu
ra
l
c
o
n
ten
t
,
p
e
a
k
sig
n
a
l
to
n
o
ise
ra
ti
o
,
n
o
rm
a
li
z
e
d
c
o
rre
latio
n
c
o
e
f
f
ici
e
n
t,
a
v
e
ra
g
e
d
i
ff
e
re
n
c
e
a
n
d
n
o
rm
a
li
z
e
d
a
b
so
lu
te
e
rro
r.
Ou
t
o
f
th
e
a
b
o
v
e
m
e
th
o
d
s
th
e
e
x
p
e
rime
n
tal
re
su
lt
s
sh
o
w
th
a
t
f
u
z
z
y
c
m
e
a
n
s
a
lg
o
rit
h
m
p
e
rf
o
rm
s
b
e
tt
e
r
th
a
n
w
a
ters
h
e
d
tran
sf
o
r
m
a
ti
on
a
lg
o
rit
h
m
in
p
r
o
c
e
ss
in
g
p
e
st i
m
a
g
e
s.
K
ey
w
o
r
d
:
Fu
zz
y
c
m
ea
n
s
cl
u
s
ter
i
n
g
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
s
eg
m
e
n
tatio
n
No
n
-
l
in
ea
r
o
b
j
ec
tiv
e
ass
es
s
m
en
t
s
P
est d
etec
tio
n
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A.
Si
v
a
Sa
n
g
ar
i
,
Dep
ar
t
m
en
t o
f
E
lectr
o
n
ics a
n
d
C
o
m
m
u
n
icat
io
n
E
n
g
i
n
ee
r
in
g
,
GM
R
I
n
s
tit
u
te
o
f
T
ec
h
n
o
lo
g
y
,
G
MR Na
g
ar
,
R
aj
a
m
,
Srik
a
k
u
l
a
m
Dt.
Viza
g
,
A
n
d
h
r
a
P
r
ad
esh
,
I
n
d
ia.
E
m
ail:
s
iv
a
k
_
s
a
n
0
4
@
y
a
h
o
o
.
co
.
in
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
ia
is
t
h
e
“L
an
d
o
f
a
g
r
ic
u
lt
u
r
e”
w
h
ic
h
h
as
m
a
n
y
tr
ad
itio
n
al
a
n
d
ev
e
n
a
lar
g
e
v
ar
iet
y
o
f
cu
lt
u
r
es.
A
p
p
r
o
x
i
m
atel
y
7
5
%
o
f
t
h
e
I
n
d
ian
p
o
p
u
latio
n
i
s
co
n
n
ec
t
ed
w
i
th
ag
r
ic
u
lt
u
r
e.
Ne
w
m
o
d
er
n
ag
r
icu
ltu
r
a
l
tech
n
iq
u
e
i
s
e
s
tab
lis
h
ed
i
n
o
r
d
er
to
th
e
q
u
a
n
tit
y
a
n
d
q
u
al
it
y
o
f
t
h
e
y
ield
.
B
u
t
t
h
e
p
r
o
d
u
ctio
n
is
r
ed
u
ce
d
n
o
w
ad
a
y
s
d
u
e
to
r
ed
u
c
tio
n
in
lan
d
s
ca
p
e
a
n
d
al
s
o
in
cr
ea
s
in
g
o
f
d
if
f
er
en
t
k
in
d
s
o
f
p
est
,
t
h
er
e
is
n
o
p
o
s
s
ib
le
w
a
y
to
in
cr
ea
s
e
th
e
lan
d
s
ca
p
e
b
u
t th
er
e
i
s
a
p
o
s
s
ib
ilit
y
to
r
ed
u
ce
th
e
e
f
f
ec
ts
o
f
p
est.
I
n
m
o
s
t
o
f
th
e
ca
s
es
,
p
est
s
o
r
d
is
ea
s
es a
r
e
s
ee
n
o
n
th
e
lea
v
es o
r
s
te
m
s
o
f
t
h
e
p
lan
t
s
li
k
e
to
m
ato
p
lan
t,
co
tto
n
,
s
u
g
ar
ca
n
e
an
d
cr
o
p
y
ield
i
n
g
ar
e
also
r
ed
u
ce
d
d
u
e
to
m
ea
l
y
b
u
g
.
T
h
e
id
e
n
ti
f
icatio
n
o
f
p
lan
ts
lea
v
es
w
it
h
p
est
s
o
r
d
is
ea
s
e
s
,
s
y
m
p
to
m
s
o
f
th
e
p
est
o
r
d
is
ea
s
e
attac
k
,
p
la
y
s
a
k
e
y
r
o
le
in
s
u
cc
ess
f
u
l
c
u
lti
v
a
tio
n
o
f
cr
o
p
s
.
He
n
ce
to
co
n
d
u
ct
h
i
g
h
th
r
o
u
g
h
p
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
n
a
lyzi
n
g
th
e
Op
ti
ma
l P
erfo
r
ma
n
ce
o
f P
est I
ma
g
e
S
eg
men
t
a
tio
n
u
s
in
g
N
o
n
Lin
ea
r
…
(
S
iva
S
a
n
g
a
r
i A
)
2790
ex
p
er
i
m
e
n
ts
,
p
la
n
t
b
io
lo
g
i
s
t
n
ee
d
ef
f
icien
t
co
m
p
u
ter
s
o
f
t
w
a
r
e
to
au
to
m
a
ticall
y
e
x
tr
ac
t
a
n
d
an
al
y
ze
s
ig
n
i
f
ica
n
t
co
n
ten
t
[
1
]
r
esp
ec
tiv
el
y
,
th
e
ap
p
licatio
n
s
o
f
co
lo
r
tr
an
s
f
o
r
m
atio
n
a
n
d
Neu
r
al
Net
w
o
r
k
s
(
NNs)
h
av
e
b
ee
n
f
o
r
m
u
lated
f
o
r
class
if
icatio
n
o
f
d
is
ea
s
es
t
h
at
a
f
f
ec
t
o
n
p
lan
t
leav
e
s
[
2
]
.
B
o
d
h
e,
T
.
S
w
o
r
k
s
u
g
g
est
s
E
n
tr
o
p
y
b
ased
th
r
esh
o
ld
in
g
i
n
w
h
ic
h
th
e
m
a
x
i
m
u
m
i
n
f
o
r
m
atio
n
co
n
ten
t
i
s
u
s
ed
to
d
ec
id
e
th
e
s
eg
m
en
ta
tio
n
r
u
l
e
d
ep
en
d
en
t
u
p
o
n
a
co
lo
r
s
p
ac
e
s
elec
tio
n
.
His
s
u
g
g
ested
s
eg
m
e
n
tatio
n
al
g
o
r
ith
m
i
s
ap
p
lied
f
o
r
im
a
g
es
of
p
est
in
f
ec
ted
leav
es
a
n
t
th
eir
r
esu
lt
s
ar
e
co
m
p
ar
ed
w
it
h
t
h
e
r
esu
lt
s
o
f
Fu
zz
y
c
-
m
ea
n
m
eth
o
d
.
T
h
e
ap
p
licatio
n
o
f
d
if
f
er
en
t
i
m
a
g
e
s
eg
m
en
tatio
n
a
n
d
clu
s
ter
in
g
alg
o
r
it
h
m
ad
d
r
ess
e
s
to
s
o
l
v
e
th
e
p
r
o
b
le
m
o
f
ch
ec
k
i
n
g
th
e
co
n
s
i
s
ten
c
y
o
f
d
i
f
f
er
en
t
al
g
o
r
ith
m
s
b
ased
o
n
s
o
m
e
s
m
all
n
u
m
b
er
o
f
i
m
a
g
es
o
r
im
a
g
e
s
f
r
o
m
o
n
e
p
ar
ticu
lar
f
ield
[
3
]
an
d
[
4
]
c
o
n
s
id
er
g
en
er
ic
s
e
g
m
en
tatio
n
o
f
th
e
m
ed
ical
i
m
a
g
e
s
w
h
ic
h
is
ca
r
r
ied
o
u
t
f
o
r
d
if
f
er
e
n
t
t
y
p
e
s
o
f
m
ed
ical
i
m
ag
es
a
n
d
co
m
p
ar
ed
u
s
i
n
g
q
u
a
lit
y
m
ea
s
u
r
es
[
5
]
.
I
llu
s
tr
ate
th
e
co
n
s
is
ten
c
y
b
ased
o
n
th
e
s
t
u
d
y
o
f
m
u
l
ti
m
o
d
al
b
i
o
m
e
tr
ic
s
y
s
te
m
,
t
h
e
f
ea
t
u
r
e
o
f
f
ac
e
a
n
d
p
al
m
p
r
in
t a
r
e
e
x
tr
ac
t
ed
s
ep
ar
atel
y
u
s
i
n
g
Gab
o
r
w
av
ele
t
[
6
]
d
e
m
o
n
s
tr
ates
th
e
k
m
ea
n
s
clu
s
ter
i
n
g
m
et
h
o
d
is
a
u
s
e
f
u
l
tec
h
n
iq
u
e,
w
h
i
ch
ca
n
s
u
s
ta
in
e
x
ac
t
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
o
f
P
lan
t
p
ests
i
n
t
h
eir
v
ar
io
u
s
s
h
ap
es,
s
izes,
p
o
s
itio
n
s
,
an
d
o
r
ien
tatio
n
s
.
T
h
e
d
etec
tio
n
an
d
r
e
co
g
n
itio
n
o
f
cr
o
p
p
ests
b
y
m
an
y
f
ar
m
er
s
in
m
aj
o
r
p
ar
ts
o
f
th
e
w
o
r
ld
ac
co
r
d
in
g
to
[
7
]
is
o
b
s
er
v
atio
n
b
ased
o
n
t
h
e
n
a
k
ed
e
y
e.
T
h
is
m
et
h
o
d
r
eq
u
ir
es
co
n
ti
n
u
o
u
s
m
o
n
ito
r
i
n
g
o
f
th
e
cr
o
p
s
te
m
s
a
n
d
leav
es,
w
h
ic
h
ar
e
ex
p
e
n
s
i
v
e,
lab
o
r
in
te
n
s
i
v
e,
i
n
ac
c
u
r
ate
f
o
r
lar
g
e
f
ar
m
s
[
8
]
.
L
i
s
ted
v
ar
io
u
s
m
eth
o
d
s
to
in
cr
ea
s
i
n
g
th
r
o
u
g
h
p
u
t
&
r
ed
u
cin
g
t
h
e
lab
o
u
r
ar
is
i
n
g
f
r
o
m
h
u
m
a
n
e
x
p
er
ts
i
n
d
etec
ti
n
g
t
h
e
p
lan
t
d
is
ea
s
es.
Hi
s
r
esear
ch
w
o
r
k
r
ev
ea
l
s
th
at
d
i
f
f
er
en
t
m
eth
o
d
s
ar
e
u
s
ed
b
y
d
if
f
er
en
t
r
esear
ch
er
s
f
o
r
p
lan
t
d
is
ea
s
e
d
etec
tio
n
an
d
an
al
y
s
is
.
T
h
e
v
ar
io
u
s
tech
n
iq
u
es
d
e
m
o
n
s
tr
ated
Sel
f
o
r
g
an
i
zin
g
m
ap
s
&
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
s
w
it
h
g
en
et
ic
alg
o
r
it
h
m
s
f
o
r
o
p
ti
m
izat
io
n
&
s
u
p
p
o
r
t v
ec
to
r
m
ac
h
in
e
s
f
o
r
d
is
ea
s
e
s
clas
s
i
f
icat
io
n
[
9
]
.
I
d
en
tif
ied
t
h
e
r
ate
o
f
b
r
o
w
n
i
n
g
w
it
h
i
n
B
r
ae
b
u
r
n
ap
p
le
s
an
d
cr
ea
ted
an
i
m
a
g
e
r
ec
o
g
n
itio
n
s
y
s
te
m
to
d
etec
t
p
est
d
am
a
g
e
w
it
h
th
e
u
s
e
o
f
a
w
a
v
elet
b
ased
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
an
d
a
n
eu
r
al
n
et
w
o
r
k
[
10
]
.
M
ea
s
u
r
ed
t
h
e
p
es
t
d
etec
tio
n
a
n
d
p
o
s
itio
n
in
g
d
ep
en
d
s
o
n
b
in
o
cu
lar
s
ter
eo
to
g
et
t
h
e
lo
ca
tio
n
i
n
f
o
r
m
atio
n
o
f
p
est,
w
h
ic
h
i
s
u
s
ed
f
o
r
g
u
id
in
g
th
e
r
o
b
o
t
to
s
p
r
a
y
t
h
e
p
es
ticid
es
au
to
m
atica
l
l
y
,
i
f
t
h
er
e
ar
e
ch
an
g
es
in
th
e
o
r
ien
tatio
n
o
r
p
o
s
itio
n
o
f
th
e
p
ests
o
n
th
e
leaf
,
t
h
e
r
o
b
o
t
is
lik
el
y
to
m
i
s
s
t
h
e
tar
g
et
an
d
s
p
r
a
y
o
n
ar
ea
s
n
o
t
af
f
ec
ted
b
y
th
e
p
est
[
1
1
]
.
Star
ts
w
it
h
an
e
s
ti
m
ate
o
f
th
e
lo
ca
l
d
is
tr
ib
u
t
io
n
,
w
h
ich
ef
f
icien
t
l
y
a
v
o
id
s
p
r
e
-
ass
u
m
in
g
t
h
e
clu
s
ter
n
u
m
b
er
.
T
h
en
th
e
s
ee
d
cl
u
s
ter
s
th
at
co
m
e
f
r
o
m
a
s
i
m
ilar
d
is
tr
ib
u
tio
n
ar
e
m
er
g
ed
b
y
th
is
c
lu
s
ter
in
g
p
r
o
g
r
a
m
w
as a
p
p
lied
to
b
o
th
ar
tif
icial
an
d
b
e
n
ch
m
ar
k
d
ata
class
if
icatio
n
a
n
d
its
p
er
f
o
r
m
a
n
ce
is
p
r
o
v
en
b
etter
th
an
t
h
e
w
ell
-
k
n
o
w
n
k
-
m
ea
n
s
alg
o
r
it
h
m
[
1
3
]
.
De
m
o
n
s
tr
a
ted
a
co
g
n
it
iv
e
v
is
io
n
ap
p
r
o
ac
h
to
ea
r
ly
p
est
d
etec
tio
n
in
g
r
ee
n
h
o
u
s
e
cr
o
p
s
,
h
is
w
o
r
k
co
n
ce
n
tr
ated
o
n
lo
w
in
f
e
s
tati
o
n
ca
s
es,
w
h
ic
h
is
cr
u
cial
to
ag
r
o
n
o
m
ic
d
ec
is
io
n
m
a
k
in
g
,
p
ar
ticu
lar
l
y
o
n
w
h
i
te
f
lies
.
I
t
w
a
s
v
er
y
g
o
o
d
w
o
r
k
f
o
r
ea
r
ly
d
etec
tio
n
o
f
w
h
i
te
f
l
y
b
u
t
d
id
n
o
t
ex
ten
d
to
m
o
r
e
co
m
p
lex
ca
s
e
s
a
n
d
o
n
all
f
o
r
m
s
o
r
s
p
ec
ies
o
f
t
h
e
p
est,
esp
ec
iall
y
w
h
en
th
e
p
e
s
t
c
h
an
g
es
p
o
s
itio
n
o
r
o
r
ien
tatio
n
.
R
esear
ch
er
s
h
a
v
e
ex
ten
s
i
v
el
y
w
o
r
k
ed
o
v
er
t
h
is
f
u
n
d
a
m
e
n
tal
p
r
o
b
le
m
an
d
p
r
o
p
o
s
ed
v
ar
io
u
s
m
e
t
h
o
d
s
f
o
r
i
m
ag
e
s
eg
m
e
n
tati
on
.
T
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
.
I
n
Sectio
n
I
I
,
f
o
r
th
e
i
n
t
eg
r
it
y
o
f
t
h
is
p
ap
er
,
w
e
s
i
m
p
l
y
d
escr
ib
e
th
e
p
r
o
b
lem
id
e
n
ti
f
icatio
n
b
ased
u
p
o
n
th
e
w
h
ite
f
l
y
p
est.
I
n
Sec
tio
n
I
I
I
,
I
m
a
g
e
s
eg
m
e
n
tatio
n
b
ased
F
C
M
clu
s
ter
i
n
g
al
g
o
r
ith
m
i
s
d
is
c
u
s
s
ed
.
I
n
Sectio
n
I
V,
Ma
r
k
er
co
n
tr
o
l
b
ased
w
ater
s
h
ed
tr
a
n
s
f
o
r
m
at
io
n
is
p
r
esen
ted
.
I
n
Sectio
n
V
,
w
e
ev
al
u
ate
th
e
n
o
n
lin
ea
r
o
b
j
ec
tiv
e
m
ea
s
u
r
e
s
f
o
r
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
es
u
s
i
n
g
p
est
i
m
a
g
es
an
d
co
m
p
ar
e
th
e
lead
in
g
tech
n
iq
u
e
f
r
o
m
t
h
e
liter
atu
r
e.
Sec
tio
n
VI
p
r
esen
ts
t
h
e
ex
p
er
i
m
en
tal
r
es
u
lts
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
an
d
f
in
a
ll
y
c
o
n
clu
d
es t
h
is
p
ap
er
.
2.
P
RO
B
L
E
M
I
DE
NT
I
F
I
CA
T
I
O
N
T
h
er
e
is
th
e
g
r
ea
t
ec
o
n
o
m
ic
l
o
s
s
f
o
r
f
ar
m
er
s
b
ec
au
s
e
o
f
p
l
an
t
d
is
ea
s
es
a
n
d
i
n
s
ec
t
p
es
ts
ev
er
y
y
ea
r
.
T
in
y
p
e
s
ts
s
u
c
h
a
s
ap
h
id
s
,
w
h
i
tef
lie
s
,
an
d
s
p
id
er
m
ites
ar
e
m
o
r
e
lik
el
y
to
in
f
est
g
r
ee
n
h
o
u
s
e
cr
o
p
s
th
an
b
ee
tle
s
o
r
ca
ter
p
illar
s
T
h
er
ef
o
r
e,
it
is
o
f
g
r
ea
t
b
o
th
th
eo
r
etica
l
a
n
d
p
r
ac
tical
s
ig
n
i
f
ica
n
ce
to
d
ev
elo
p
th
e
au
to
m
atic
id
en
ti
f
icatio
n
an
d
d
ia
g
n
o
s
e
s
y
s
t
e
m
o
f
W
h
ite
f
lies
in
s
ec
t
ab
o
u
t
1
.
5
m
m
lo
n
g
;
f
o
u
n
d
i
n
co
n
j
u
n
ctio
n
w
it
h
t
in
y
y
ello
w
cr
a
w
ler
s
o
r
g
r
ee
n
,
o
v
a
l
o
f
te
n
p
r
ese
n
t
o
n
lea
v
es.
I
t
s
n
ac
k
s
o
n
f
o
lia
g
e,
co
ati
n
g
t
h
e
l
ea
v
es
w
it
h
a
s
tic
k
y
w
h
ite
r
es
id
u
e
t
h
at
s
h
r
i
v
els
th
e
m
a
n
d
attr
ac
ts
b
lac
k
m
o
ld
t
o
th
e
f
r
u
it.
U
s
i
n
g
th
e
w
h
i
tef
l
ies
as
t
h
e
r
es
ea
r
c
h
s
u
b
j
ec
t,
i
m
ag
e
o
f
i
n
s
ec
t
p
est
o
f
w
h
ite
f
lie
s
b
ased
o
n
F
u
z
z
y
C
m
ea
n
s
cl
u
s
ter
i
n
g
alg
o
r
ith
m
w
it
h
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
an
s
f
o
r
m
atio
n
w
a
s
p
r
o
p
o
s
ed
an
d
also
an
al
y
zi
n
g
t
h
e
p
er
f
o
r
m
an
ce
b
ased
o
n
n
o
n
lin
ea
r
o
b
j
ec
tiv
e
ass
e
s
s
m
en
ts
.
3.
I
M
AG
E
SE
G
M
E
NT
A
T
I
O
N
B
ASE
D
F
CM
CL
UST
E
RI
N
G
AL
G
O
R
I
T
H
M
Fu
zz
y
C
-
m
ea
n
s
[
1
1
]
,
[
1
5
]
is
an
al
g
o
r
ith
m
b
ased
o
n
o
n
e
o
f
t
h
e
s
e
g
m
en
tatio
n
m
et
h
o
d
s
w
h
i
ch
allo
w
s
d
ata
to
h
a
v
e
m
e
m
b
er
s
h
ip
o
f
m
u
ltip
le
clu
s
ter
s
,
ea
c
h
to
v
ar
y
i
n
g
d
eg
r
ee
s
.
T
h
is
m
et
h
o
d
,
u
s
ed
i
n
p
atter
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
8
9
–
2
7
9
6
2791
r
ec
o
g
n
itio
n
,
w
as
d
ev
elo
p
ed
in
1
9
7
3
b
y
D
u
n
n
an
d
i
m
p
r
o
v
ed
b
y
B
ez
d
ek
i
n
1
9
8
1
.
T
h
e
alg
o
r
ith
m
is
b
a
s
ed
o
n
m
i
n
i
m
izatio
n
o
f
th
e
f
o
llo
w
i
n
g
f
u
n
ctio
n
:
∑
∑
‖
‖
(
1
)
w
h
er
e
:
a.
is
an
y
r
ea
l
n
u
m
b
er
g
r
ea
ter
th
an
1
,
b.
is
th
e
d
eg
r
ee
o
f
m
e
m
b
er
s
h
ip
o
f
in
t
h
e
clu
s
ter
j
,
c.
is
th
e
d
-
d
i
m
e
n
s
io
n
al
m
ea
s
u
r
ed
d
ata,
d.
is
th
e
d
-
d
i
m
e
n
s
io
n
ce
n
ter
o
f
t
h
e
clu
s
ter
,
e.
||
|
|
is
a
n
y
n
o
r
m
e
x
p
r
ess
i
n
g
t
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
an
y
m
ea
s
u
r
ed
d
ata
an
d
th
e
ce
n
ter
.
T
h
is
alg
o
r
ith
m
r
ea
l
izes
an
iter
ativ
e
o
p
ti
m
izat
io
n
o
f
th
e
f
u
n
ct
io
n
,
u
p
d
atin
g
m
e
m
b
er
s
h
ip
an
d
th
e
clu
s
ter
ce
n
ter
s
u
s
in
g
t
h
e
f
o
llo
w
i
n
g
f
o
r
m
u
las
:
∑
∑
(
2
)
∑
(
‖
‖
‖
‖
)
(
3
)
T
h
e
m
i
n
i
m
izatio
n
o
f
is
ac
h
ie
v
ed
w
h
en
f
u
n
ctio
n
ar
e
s
atu
r
a
tes
th
at
is
,
t
h
e
s
to
p
cr
iter
io
n
is
g
iv
e
n
b
y
t
h
e
eq
u
atio
n
{
|
|
}
(
4
)
Fig
u
r
e
1
.
Flo
w
c
h
ar
t f
o
r
FC
M
clu
s
ter
i
n
g
A
lg
o
r
it
h
m
Fig
u
r
e
1
r
ep
r
esen
t
s
t
h
e
f
lo
w
c
h
ar
t
o
f
FC
M
al
g
o
r
ith
m
i
n
w
h
i
ch
t
h
e
f
ir
s
t
s
tep
i
s
to
ch
o
o
s
e
a
n
u
m
b
er
o
f
clu
s
ter
s
i
n
a
g
iv
e
n
i
m
a
g
e
an
d
s
et
th
e
iter
atio
n
v
al
u
e
ac
c
o
r
d
in
g
to
clu
s
ter
s
.
Seco
n
d
s
t
ep
r
elate
th
e
i
n
itia
l
clu
s
ter
i
n
g
ce
n
ter
,
w
h
er
e
is
t
h
e
n
u
m
b
er
o
f
d
ata
ite
m
.
T
h
ir
d
s
tep
,
I
n
itialize
th
e
m
e
m
b
er
s
h
i
p
m
atr
i
x
(
)
,
ca
lcu
late
t
h
e
c
c
lu
s
ter
ce
n
ter
s
w
ith
(
)
u
s
i
n
g
eq
u
atio
n
(
4
)
an
d
u
p
d
ate
t
h
e
m
e
m
b
er
s
h
i
p
S
e
t
n
o
o
f
c
l
u
st
e
r
I
n
i
t
i
a
l
i
z
e
t
h
e
c
l
u
st
e
r
i
n
g
c
e
n
t
e
r
I
n
i
t
i
a
l
i
z
e
t
h
e
me
mb
e
r
sh
i
p
m
a
t
r
i
x
(
)
U
p
d
a
t
e
t
h
e
c
l
u
s
t
e
r
i
n
g
c
e
n
t
e
r
u
s
i
n
g
ma
t
r
i
x
U
p
d
a
t
e
t
h
e
me
mb
e
r
sh
i
p
mat
r
i
x
{
|
|
}
S
t
o
p
Y
ES
NO
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
n
a
lyzi
n
g
th
e
Op
ti
ma
l P
erfo
r
ma
n
ce
o
f P
est I
ma
g
e
S
eg
men
t
a
tio
n
u
s
in
g
N
o
n
Lin
ea
r
…
(
S
iva
S
a
n
g
a
r
i A
)
2792
m
atr
i
x
(
)
u
s
in
g
eq
u
atio
n
(
5
)
.
Fin
all
y
C
o
m
p
ar
e
an
d
in
a
co
n
v
e
n
ien
t
m
atr
i
x
n
o
r
m
;
i
f
{
|
|
}
,
s
to
p
;
o
th
er
w
is
e,
s
et
K=
K
+
1
,
an
d
g
o
to
th
ir
d
s
tep
b
y
u
p
d
atin
g
t
h
e
cl
u
s
ter
ce
n
ter
s
iter
ati
v
el
y
a
n
d
also
t
h
e
m
e
m
b
er
s
h
ip
g
r
ad
es
f
o
r
d
ata
p
o
in
t [
1
6
]
.
4.
M
ARK
E
R
CO
NT
RO
L
L
E
D
B
ASE
D
WA
T
E
RSH
E
D
T
R
ANSF
O
RM
AT
I
O
N
AL
G
O
R
I
T
H
M
4
.
1
.
I
m
a
g
e
P
re
pro
ce
s
s
ing
:
T
h
e
o
r
ig
in
al
i
m
a
g
e
n
ee
d
s
r
ea
s
o
n
ab
le
p
r
ep
r
o
ce
s
s
in
g
to
m
a
k
e
it
s
u
itab
le
f
o
r
w
ater
s
h
ed
s
e
g
m
en
tatio
n
.
W
e
h
er
e
f
ir
s
t,
co
n
v
er
t
th
e
i
m
ag
e
i
n
to
g
r
a
y
s
ca
le
a
n
d
t
h
en
u
s
e
a
m
o
r
p
h
o
lo
g
ical
f
ilter
w
h
i
ch
co
m
b
i
n
es
d
i
s
k
-
s
h
ap
ed
s
tr
u
ct
u
r
in
g
ele
m
en
t
to
en
h
a
n
ce
th
e
co
n
tr
ast
o
f
t
h
e
i
m
ag
e
[
1
2
]
.
M
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ctio
n
i
s
a
v
er
y
u
s
e
f
u
l
o
p
er
ato
r
b
ased
o
n
m
ath
e
m
atica
l
m
o
r
p
h
o
lo
g
y
.
Mo
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
c
tio
n
ca
n
b
e
co
n
ce
p
tu
all
y
r
eg
ar
d
ed
as
r
ep
ea
ted
d
ilatio
n
s
o
f
an
i
m
ag
e
ca
lled
t
h
e
m
ar
k
er
i
m
a
g
e,
u
n
til
t
h
e
co
n
to
u
r
o
f
t
h
e
m
ar
k
er
i
m
ag
e
f
it
s
u
n
d
er
a
s
ec
o
n
d
i
m
a
g
e
ca
lled
th
e
m
a
s
k
i
m
ag
e.
Mo
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ctio
n
s
t
u
r
n
s
o
u
t
to
b
e
p
ar
tic
u
lar
l
y
ef
f
ec
tiv
e
to
ex
tr
ac
t
m
ar
k
ed
o
b
j
ec
ts
,
d
etec
t
o
r
r
em
o
v
e
o
b
j
ec
ts
to
u
ch
i
n
g
t
h
e
i
m
a
g
e
b
o
r
d
er
an
d
f
ilter
o
u
t
s
p
u
r
io
u
s
o
r
lo
w
p
o
in
ts
.
B
a
s
ed
o
n
t
h
e
m
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ct
io
n
,
a
f
ilter
co
m
b
in
i
n
g
o
p
en
in
g
b
y
-
r
ec
o
n
s
tr
u
ctio
n
o
p
er
atio
n
an
d
clo
s
in
g
b
y
r
ec
o
n
s
tr
u
c
tio
n
o
p
er
atio
n
is
u
tili
ze
d
to
s
m
o
o
t
h
im
ag
e
a
n
d
eli
m
i
n
ate
th
e
n
o
is
e.
T
h
e
o
p
en
in
g
-
by
-
r
ec
o
n
s
tr
u
ct
io
n
i
s
er
o
s
io
n
f
o
ll
o
w
ed
b
y
a
m
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ct
io
n
w
h
ile
clo
s
in
g
-
by
-
r
ec
o
n
s
tr
u
ctio
n
is
a
d
ilatio
n
f
o
llo
w
ed
b
y
a
m
o
r
p
h
o
lo
g
ical
r
ec
o
n
s
tr
u
ctio
n
.
C
o
m
p
ar
ed
to
s
i
m
p
le
o
p
en
in
g
a
n
d
clo
s
i
n
g
,
co
n
s
tr
u
c
tio
n
-
b
ased
o
p
en
i
n
g
an
d
clo
s
i
n
g
ca
n
r
esto
r
e
th
e
o
r
i
g
i
n
al
s
h
ap
es
o
f
th
e
o
b
j
ec
ts
af
ter
er
o
s
io
n
o
r
d
ilatio
n
[
1
2
]
.
4
.
2
.
M
a
rk
er
s
:
An
alter
n
a
tiv
e
ap
p
r
o
ac
h
to
wate
r
s
h
ed
is
to
i
m
ag
in
e
t
h
e
la
n
d
s
ca
p
e
b
ein
g
i
m
m
er
s
ed
i
n
a
lak
e
w
it
h
h
o
les
p
ier
ce
d
in
lo
ca
l
m
i
n
i
m
a.
B
asin
s
(
al
s
o
ca
lled
`
ca
tc
h
m
e
n
t
b
asi
n
s
'
)
w
i
ll
f
ill
u
p
w
it
h
w
a
ter
s
tar
tin
g
at
t
h
ese
lo
ca
l
m
in
i
m
a
a
n
d
at
p
o
in
ts
wh
er
e
w
a
ter
co
m
in
g
f
r
o
m
d
if
f
e
r
en
t
b
asin
s
w
o
u
ld
m
ee
t,
d
a
m
s
ar
e
b
u
ilt.
W
h
en
th
e
w
ater
le
v
el
h
as
r
ea
c
h
ed
th
e
h
i
g
h
e
s
t
p
e
ak
in
th
e
la
n
d
s
ca
p
e,
t
h
e
p
r
o
ce
s
s
is
s
to
p
p
ed
.
A
s
a
r
e
s
u
lt,
t
h
e
la
n
d
s
ca
p
e
i
s
p
ar
titi
o
n
ed
in
to
r
e
g
io
n
s
o
r
b
as
in
s
s
ep
ar
ated
b
y
d
a
m
s
ca
lled
w
ater
s
h
ed
li
n
e
s
o
r
s
i
m
p
l
y
w
at
er
s
h
ed
s
[
1
1
]
.
Hen
ce
,
to
f
in
d
o
u
t
ca
tch
m
e
n
t
b
asi
n
s
an
d
w
ater
s
h
ed
lin
e
s
,
m
ar
k
er
s
ar
e
u
s
ed
.
A
m
ar
k
er
is
a
co
n
n
ec
ted
co
m
p
o
n
e
n
t
b
elo
n
g
i
n
g
to
a
n
i
m
a
g
e.
I
n
ter
n
al
an
d
ex
ter
n
al
m
ar
k
er
s
ar
e
u
s
ed
to
f
in
d
o
u
t
r
e
g
io
n
o
f
i
n
ter
est.
I
n
ter
n
a
l
m
ar
k
er
s
ar
e
ass
o
ciate
d
w
it
h
o
b
j
ec
t o
f
in
ter
est a
n
d
ex
ter
n
a
l
m
ar
k
er
s
a
r
e
ass
o
ciate
d
w
it
h
b
ac
k
g
r
o
u
n
d
[
1
1
]
.
1
)
Fo
r
eg
r
o
u
n
d
m
ar
k
er
s
-
Fo
r
eg
r
o
u
n
d
m
ar
k
er
s
ca
n
b
e
d
ef
i
n
ed
as
r
eg
io
n
s
u
r
r
o
u
n
d
ed
b
y
p
o
in
t
s
o
f
h
i
g
h
er
altitu
d
e,
P
o
in
ts
i
n
r
eg
io
n
f
o
r
m
co
n
n
ec
ted
co
m
p
o
n
e
n
t
an
d
all
th
e
p
o
in
ts
i
n
t
h
e
r
eg
io
n
h
a
v
e
s
a
m
e
in
ten
s
it
y
[
1
1
]
.
W
e
co
m
p
u
te
t
h
e
f
o
r
eg
r
o
u
n
d
m
ar
k
er
s
b
y
ex
tr
ac
ti
n
g
t
h
e
l
o
ca
l
m
a
x
i
m
a
o
f
th
e
p
r
ep
r
o
c
ess
ed
i
m
ag
e.
L
o
ca
l
m
ax
i
m
a
ar
e
co
n
n
ec
ted
co
m
p
o
n
en
t
s
o
f
p
ix
els
w
i
th
a
co
n
s
t
an
t
in
te
n
s
it
y
v
al
u
e,
an
d
w
h
o
s
e
ex
ter
n
al
b
o
u
n
d
ar
y
p
ix
els all
h
av
e
a
lo
w
er
v
al
u
e.
2
)
B
ac
k
g
r
o
u
n
d
m
ar
k
er
s
-
E
ac
h
ex
ter
n
al
m
ar
k
er
co
n
s
is
ts
o
f
s
i
n
g
le
in
ter
n
al
m
ar
k
er
an
d
p
ar
t
o
f
b
ac
k
g
r
o
u
n
d
[
1
1
]
.
T
h
e
b
ac
k
g
r
o
u
n
d
m
ar
k
er
ex
tr
ac
tio
n
ca
n
b
e
ac
h
iev
ed
b
y
co
m
p
u
ti
n
g
t
h
e
w
ater
s
h
ed
tr
an
s
f
o
r
m
o
f
th
e
d
is
ta
n
ce
tr
an
s
f
o
r
m
o
f
t
h
e
f
o
r
eg
r
o
u
n
d
m
ar
k
er
i
m
ag
e.
T
h
e
d
is
tan
ce
tr
an
s
f
o
r
m
co
n
v
er
ts
a
b
in
ar
y
i
m
a
g
e
in
to
a
d
is
ta
n
ce
m
ap
w
h
er
e
ev
er
y
b
ac
k
g
r
o
u
n
d
p
ix
el
h
as
a
v
a
lu
e
co
r
r
esp
o
n
d
in
g
to
th
e
m
i
n
i
m
u
m
d
i
s
tan
ce
f
r
o
m
th
e
li
g
h
t
p
o
in
ts
.
T
h
e
b
ac
k
g
r
o
u
n
d
m
ar
k
er
e
x
tr
ac
tio
n
ca
n
b
e
ac
h
iev
ed
b
y
co
m
p
u
ti
n
g
th
e
w
at
er
s
h
ed
tr
an
s
f
o
r
m
o
f
th
e
d
is
ta
n
ce
m
ap
o
f
t
h
e
f
o
r
eg
r
o
u
n
d
m
ar
k
er
i
m
a
g
e
[
1
2
]
.
T
h
e
w
ater
s
h
ed
tr
an
s
f
o
r
m
is
i
m
p
le
m
e
n
ted
o
n
t
h
e
g
r
ad
ie
n
t
i
m
a
g
e.
T
h
e
g
r
ad
ien
t
d
ef
i
n
es
t
h
e
f
i
r
s
t
p
ar
tial
d
er
iv
ativ
e
o
f
a
n
i
m
a
g
e
a
n
d
co
n
tai
n
s
a
m
ea
s
u
r
e
m
e
n
t
f
o
r
t
h
e
v
ar
iatio
n
tr
en
d
o
f
g
r
a
y
lev
el
s
.
I
t
is
b
etter
to
r
e
f
lect
th
e
v
ar
iatio
n
tr
en
d
o
f
t
h
e
i
m
ag
e
t
h
an
t
h
e
o
r
ig
i
n
al
i
m
a
g
e
[
1
3
]
.
So
b
el
o
p
er
at
o
r
is
ad
o
p
t
ed
to
ca
lcu
late
th
e
g
r
ad
ien
t
m
a
g
n
itu
d
e
o
f
t
h
e
g
r
ay
i
m
ag
e.
T
h
e
e
x
tr
ac
ted
f
o
r
eg
r
o
u
n
d
m
ar
k
er
s
an
d
b
ac
k
g
r
o
u
n
d
m
ar
k
er
s
ar
e
i
m
p
o
s
ed
o
n
th
e
o
r
ig
i
n
al
g
r
ad
ien
t
m
a
g
n
it
u
d
e
i
m
a
g
e
s
o
t
h
at
its
r
eg
io
n
m
i
n
i
m
a
o
n
l
y
o
cc
u
r
at
f
o
r
eg
r
o
u
n
d
a
n
d
b
ac
k
g
r
o
u
n
d
m
ar
k
er
p
ix
el
s
.
Fi
n
all
y
,
th
e
id
ea
l
s
e
g
m
en
ta
tio
n
r
esu
lt
is
ac
h
ie
v
ed
b
y
co
m
p
u
tin
g
t
h
e
w
ater
s
h
ed
tr
an
s
f
o
r
m
o
n
t
h
e
m
o
d
i
f
ied
g
r
a
d
ien
t
m
a
g
n
it
u
d
e
i
m
a
g
e
[
1
2
]
.
5.
NO
N
L
I
N
E
AR
O
B
J
E
CT
I
V
E
ASS
E
S
SM
E
NT
S
A
g
o
o
d
o
b
j
ec
tiv
e
q
u
alit
y
m
ea
s
u
r
e
s
h
o
u
ld
r
ef
lect
t
h
e
d
is
to
r
ti
o
n
o
n
t
h
e
i
m
ag
e,
f
o
r
e
x
a
m
p
le
,
b
lu
r
r
in
g
,
n
o
is
e,
co
m
p
r
es
s
io
n
,
a
n
d
s
e
n
s
o
r
i
n
ad
eq
u
ac
y
.
Su
c
h
m
ea
s
u
r
es
co
u
ld
b
e
i
n
s
tr
u
m
en
tal
in
p
r
ed
icti
n
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
v
is
io
n
-
b
ased
alg
o
r
ith
m
s
s
u
ch
a
s
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
i
m
a
g
e
-
b
ased
m
ea
s
u
r
e
m
en
t
s
,
d
etec
tio
n
,
tr
ac
k
in
g
,
an
d
s
e
g
m
en
tatio
n
[
1
9
]
.
T
w
o
w
a
y
s
to
an
al
y
s
i
s
t
h
e
p
er
f
o
r
m
a
n
ce
1
.
P
ix
el
d
if
f
er
en
ce
-
b
ased
m
ea
s
u
r
es: (
e.
g
.
t
h
e
Me
an
Sq
u
ar
e
E
r
r
o
r
an
d
Ma
x
i
m
u
m
D
if
f
er
en
ce
)
.
2
.
C
o
r
r
elatio
n
-
b
ased
m
ea
s
u
r
e
s
:
A
v
ar
ia
n
t
o
f
co
r
r
elatio
n
b
ased
m
ea
s
u
r
es
ca
n
b
e
o
b
tain
ed
b
y
co
n
s
id
er
i
n
g
t
h
e
ab
s
o
lu
te
m
ea
n
a
n
d
v
ar
ian
ce
s
t
atis
tics
(
e.
g
.
Stru
ct
u
r
al
C
o
n
ten
t,
No
r
m
al
ized
C
r
o
s
s
C
o
r
r
elati
o
n
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
8
9
–
2
7
9
6
2793
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
h
a
v
e
b
ee
n
i
m
p
le
m
e
n
ted
u
s
i
n
g
MA
T
L
A
B
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
i
m
a
g
e
s
eg
m
e
n
tatio
n
ap
p
r
o
ac
h
es
ar
e
an
al
y
ze
d
a
n
d
d
is
cu
s
s
ed
.
1
)
Stru
ctu
r
al
C
o
n
te
n
t
(
S
C
)
2
)
P
e
ak
Si
g
n
a
l
to
No
is
e
R
atio
(
P
SNR
)
3
)
No
r
m
alize
d
C
o
r
r
elatio
n
C
o
ef
f
icie
n
t
(
NK)
4
)
No
r
m
al
ized
ab
s
o
lu
te
er
r
o
r
(
NA
E
)
5
)
Av
er
ag
e
Dif
f
er
en
ce
s
is
co
n
s
id
er
ed
f
o
r
s
tu
d
y
in
th
is
w
o
r
k
o
n
th
e
o
r
ig
in
al
i
m
a
g
e
an
d
o
n
th
e
s
eg
m
e
n
ted
i
m
a
g
e
.
5
.
1
.
Str
uct
ura
l C
o
nte
nt
(
SC)
C
o
r
r
elatio
n
,
a
f
a
m
iliar
co
n
ce
p
t
in
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
,
est
i
m
a
t
es
th
e
s
i
m
ilar
it
y
o
f
t
h
e
s
tr
u
ct
u
r
e
o
f
t
w
o
s
ig
n
al
s
.
T
h
is
m
ea
s
u
r
e
e
f
f
ec
tiv
el
y
co
m
p
ar
es
th
e
to
tal
w
ei
g
h
t
o
f
an
o
r
ig
i
n
al
s
ig
n
al
to
th
at
o
f
a
co
d
ed
o
r
g
iv
en
.
I
t
is
th
er
ef
o
r
e
a
g
lo
b
al
m
etr
ic;
l
o
ca
lized
d
is
t
o
r
tio
n
s
ar
e
m
is
s
ed
.
T
h
is
m
easu
r
e
is
also
called
a
s
s
tr
u
ctu
r
al
co
n
ten
t
.
T
h
e
St
r
u
c
tu
r
al
co
n
ten
t
is
g
iv
en
b
y
E
q
.
(
5
)
an
d
if
it
is
s
p
r
ead
at
1
,
th
en
th
e
d
eco
m
p
r
ess
ed
im
ag
e
is
o
f
b
etter
q
u
alit
y
an
d
lar
g
e v
alu
e o
f
SC
m
ean
s
t
h
at t
h
e im
ag
e is
o
f
p
o
o
r
q
u
alit
y
.
∑
∑
∑
∑
(
5
)
5
.
2
.
P
e
a
k
Sig
na
l t
o
No
is
e
Ra
t
io
(
P
SNR)
:
L
ar
g
er
S
NR
a
n
d
P
SNR
i
n
d
i
ca
te
a
s
m
a
ller
d
if
f
er
en
ce
b
et
w
ee
n
t
h
e
o
r
ig
i
n
al
(
w
it
h
o
u
t
n
o
is
e)
an
d
r
ec
o
n
s
tr
u
cted
i
m
a
g
e.
T
h
e
m
a
in
ad
v
a
n
ta
g
e
o
f
t
h
i
s
m
ea
s
u
r
e
is
ea
s
e
o
f
co
m
p
u
tatio
n
b
u
t
it
d
o
es
n
o
t
r
ef
lec
t
p
er
ce
p
tu
al
q
u
alit
y
.
An
i
m
p
o
r
t
an
t
p
r
o
p
er
ty
o
f
P
SNR
i
s
th
a
t
a
s
lig
h
t
s
p
atial
s
h
i
f
t
o
f
an
i
m
ag
e
ca
n
ca
u
s
e
a
lar
g
e
n
u
m
er
ical
d
is
to
r
tio
n
b
u
t
n
o
v
is
u
al
d
i
s
to
r
tio
n
a
n
d
co
n
v
er
s
el
y
a
s
m
all
av
er
a
g
e
d
is
to
r
tio
n
ca
n
r
es
u
lt
in
a
d
am
a
g
i
n
g
v
i
s
u
al
ar
ti
f
ac
t,
i
f
all
th
e
er
r
o
r
is
co
n
ce
n
tr
ated
in
a
s
m
all
i
m
p
o
r
ta
n
t
r
eg
io
n
.
T
h
is
m
etr
ic
n
e
g
lect
s
g
lo
b
al
an
d
co
m
p
o
s
ite
er
r
o
r
s
PS
NR
i
s
ca
lcu
lated
u
s
i
n
g
eq
u
ati
o
n
(
6
).
[
[
∑
∑
∑
∑
]
]
(
6
)
5
.
3
.
No
rm
a
lized
Co
rr
ela
t
io
n
Co
ef
f
icient
(
NK
)
:
T
h
e
clo
s
en
ess
b
et
w
ee
n
t
w
o
d
ig
ital
i
m
ag
e
s
ca
n
also
b
e
q
u
an
t
if
ied
in
ter
m
s
o
f
co
r
r
elatio
n
f
u
n
ct
io
n
.
I
t
m
ea
s
u
r
es
t
h
e
s
i
m
ilar
it
y
b
et
w
e
en
t
w
o
i
m
a
g
es
li
k
e
a
n
o
r
ig
i
n
al
co
lo
r
s
p
ac
e
in
t
h
e
i
m
ag
e
o
th
er
o
n
e
co
n
v
er
ted
co
lo
r
s
p
ac
e
im
ag
e,
h
en
ce
i
n
th
is
s
en
s
e
th
e
y
ar
e
co
m
p
le
m
en
tar
y
to
th
e
d
i
f
f
er
e
n
ce
b
ase
d
m
ea
s
u
r
e
s
.
A
l
l
th
e
co
r
r
elatio
n
b
ased
m
ea
s
u
r
es
t
en
d
to
1
,
as
t
h
e
d
i
f
f
er
e
n
ce
b
et
w
ee
n
t
w
o
i
m
a
g
e
s
te
n
d
to
ze
r
o
.
A
s
d
i
f
f
e
r
en
ce
m
ea
s
u
r
e
an
d
co
r
r
elatio
n
m
ea
s
u
r
es
co
m
p
le
m
e
n
t
ea
c
h
o
th
er
,
m
in
i
m
iz
in
g
Di
s
tan
ce
m
ea
s
u
r
es
ar
e
m
a
x
i
m
izi
n
g
co
r
r
elatio
n
m
ea
s
u
r
e
an
d
No
r
m
alize
d
C
o
r
r
elatio
n
is
ca
lcu
late
d
u
s
in
g
eq
u
at
io
n
(
7
).
∑
∑
[
]
∑
∑
(
7
)
5
.
4
.
No
rm
a
lized
A
bs
o
lute
E
r
ro
r
:
No
r
m
a
lized
ab
s
o
lu
te
er
r
o
r
c
o
m
p
u
ted
b
y
eq
u
atio
n
(
8
)
is
a
m
ea
s
u
r
e
o
f
h
o
w
f
ar
is
th
e
co
n
v
er
s
io
n
i
m
a
g
e
f
r
o
m
t
h
e
o
r
ig
in
a
l
i
m
a
g
e
w
it
h
th
e
v
alu
e
o
f
ze
r
o
b
ein
g
t
h
e
p
er
f
ec
t
f
it.
L
ar
g
e
v
al
u
e
o
f
NA
E
i
n
d
icate
s
p
o
o
r
q
u
alit
y
o
f
th
e
i
m
a
g
e.
∑
∑
|
|
∑
∑
|
|
(
8
)
5
.
5
.
Av
er
a
g
e
Dif
f
er
ence
(
AD
)
:
A
lo
w
er
v
al
u
e
o
f
Av
er
a
g
e
Di
f
f
er
en
ce
(
AD)
g
iv
e
s
a
“
clea
n
er
”
i
m
a
g
e
a
s
m
o
r
e
n
o
i
s
e
i
s
r
ed
u
ce
d
an
d
it
is
c
o
m
p
u
ted
u
s
i
n
g
eq
u
atio
n
(
9
)
∑
∑
[
]
(
9
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
n
a
lyzi
n
g
th
e
Op
ti
ma
l P
erfo
r
ma
n
ce
o
f P
est I
ma
g
e
S
eg
men
t
a
tio
n
u
s
in
g
N
o
n
Lin
ea
r
…
(
S
iva
S
a
n
g
a
r
i A
)
2794
6.
E
XP
E
R
I
M
E
NT
A
L
ANA
L
Y
SI
S AN
D
RE
S
UL
T
S
T
ab
le
1
s
h
o
w
s
t
h
e
e
x
p
er
i
m
e
n
t
al
r
esu
lt
s
co
n
d
u
cte
d
o
v
er
th
e
p
est
i
m
a
g
es.
FC
M
c
lu
s
ter
in
g
an
d
m
ar
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
an
s
f
o
r
m
atio
n
b
ased
i
m
a
g
e
s
eg
m
e
n
ta
tio
n
m
et
h
o
d
s
ar
e
ap
p
lied
to
i
m
ag
e
s
a
n
d
t
h
e
v
al
u
es
o
f
p
ar
am
e
ter
s
ar
e
ca
lcu
lated
.
T
a
b
le
1
.
I
n
p
u
t
I
m
a
g
e
a
n
d
P
r
o
c
ess
ed
Ou
tp
u
t
O
r
i
g
i
n
a
l
P
e
st
Im
a
g
e
F
C
M
P
r
o
c
e
sse
d
I
mag
e
M
a
r
k
e
r
C
o
n
t
r
o
l
l
e
d
W
a
t
e
r
sh
e
d
Im
a
g
e
T
ab
le
2
s
h
o
w
s
th
e
a
v
er
ag
e
r
es
u
lts
o
f
d
i
f
f
er
en
t p
ar
a
m
eter
s
.
T
h
e
v
alu
e
o
f
P
SN
R
s
h
o
u
ld
b
e
i
n
t
h
e
r
an
g
e
o
f
2
5
to
4
0
d
b
,
th
e
s
m
a
ll
v
al
u
e
o
f
P
SNR
m
ea
n
s
th
e
i
m
a
g
e
is
o
f
p
o
o
r
q
u
ality
[
2
]
[
3
]
,
SC
w
it
h
v
al
u
e
s
p
r
ea
d
at
1
,
in
d
icate
s
a
b
etter
q
u
alit
y
i
m
ag
e.
L
ar
g
e
v
al
u
e
o
f
N
A
E
,
N
K
an
d
AD
in
d
icate
s
p
o
o
r
q
u
ality
o
f
th
e
i
m
a
g
e
[
1
7
]
.
T
ab
le
2
.
C
o
m
p
ar
iti
v
e
P
er
f
o
r
m
an
ce
A
n
al
y
s
is
M
ET
H
O
D
S
P
ER
F
O
R
M
A
N
C
E
M
EA
S
U
R
ES
P
S
N
R
(
d
B
)
SC
NK
N
A
E
AD
M
a
r
k
e
r
C
o
n
t
r
o
l
l
e
d
w
a
t
e
r
sh
e
d
se
g
me
n
t
a
t
i
o
n
2
9
.
1
4
3
0
.
9
8
1
0
.
9
6
3
0
.
2
6
4
0
.
6
8
2
F
C
M
3
3
.
8
4
6
1
.
0
1
5
0
.
9
9
1
0
.
0
9
6
0
.
8
7
6
Fig
u
r
e
2
.
Gr
ap
h
ical
C
o
m
p
ar
is
o
n
o
f
P
er
f
o
r
m
an
ce
A
n
al
y
s
i
s
Fig
u
r
e
3
.
Gr
ap
h
ical
C
o
m
p
ar
is
o
n
o
f
P
SNR
Fig
u
r
e
2
s
h
o
w
s
a
v
er
ag
e
p
er
f
o
r
m
an
ce
a
n
al
y
s
i
s
ch
ar
t
f
o
r
p
est
i
m
a
g
e
r
ev
ea
l
s
th
at
t
h
e
p
ar
am
eter
s
f
o
r
FC
M
a
lg
o
r
it
h
m
ar
e
m
o
r
e
ap
p
r
o
p
r
iate
th
an
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
a
n
s
f
o
r
m
atio
n
.
S
tr
u
ctu
r
al
co
n
te
n
t
i
s
a
g
lo
b
al
m
ea
s
u
r
e,
w
h
ic
h
co
m
p
ar
es
th
e
to
tal
w
eig
h
t
o
f
t
h
e
s
eg
m
e
n
ted
i
m
ag
e
a
n
d
i
n
p
u
t
i
m
ag
e,
is
0
.
9
8
1
f
o
r
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
,
1
.
0
1
5
f
o
r
FC
M
.
T
h
e
s
tr
u
ctu
r
al
co
n
ten
t
w
it
h
v
al
u
e
s
p
r
ea
d
at
1
in
d
icate
s
a
b
etter
q
u
alit
y
i
m
ag
e
an
d
it
is
v
er
y
c
lo
s
e
to
1
f
o
r
o
u
tp
u
t.
No
r
m
aliz
ed
co
r
r
elatio
n
g
i
v
e
s
clo
s
en
e
s
s
b
et
w
ee
n
t
h
e
i
n
p
u
t
an
d
s
eg
m
e
n
ted
i
m
ag
e
a
n
d
i
s
o
b
tain
ed
as
0
.
9
6
3
f
o
r
Ma
r
k
er
C
o
n
tr
o
lled
w
ate
r
s
h
ed
an
d
0
.
9
9
1
f
o
r
FC
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
8
9
–
2
7
9
6
2795
alg
o
r
ith
m
r
esp
ec
ti
v
el
y
.
T
h
is
v
alu
e
ten
d
s
to
1
if
th
e
d
i
f
f
er
en
ce
b
et
w
ee
n
th
e
i
m
a
g
e
s
is
ze
r
o
an
d
f
r
o
m
t
h
e
co
m
p
u
ted
v
al
u
es,
it
is
o
b
s
er
v
e
d
th
at
f
o
r
th
e
FC
M
s
e
g
m
en
ted
i
m
ag
e
s
o
b
tain
ed
h
ig
h
l
y
co
r
r
el
ated
to
th
e
o
r
ig
in
al
i
m
a
g
es.
N
A
E
w
h
ic
h
i
s
a
m
ea
s
u
r
e
to
s
tu
d
y
t
h
e
q
u
alit
y
o
f
a
p
p
r
o
x
im
a
tio
n
o
f
t
h
e
i
m
a
g
es
i
s
0
.
2
6
4
,
0
.
0
9
6
f
o
r
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
an
d
FC
M
r
esp
ec
ti
v
el
y
.
T
h
e
Av
er
ag
e
d
if
f
er
e
n
ce
w
ith
lo
w
v
alu
e
in
d
icate
s
a
g
o
o
d
q
u
alit
y
i
m
ag
e
an
d
t
h
at
i
s
o
b
s
er
v
ed
w
it
h
t
h
e
v
alu
e
o
f
0
.
6
8
2
f
o
r
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
an
d
f
o
r
FC
M,
i
t is
th
e
m
a
x
i
m
u
m
w
it
h
0
.
8
7
6
in
d
i
ca
tin
g
th
e
p
o
o
r
q
u
alit
y
o
f
t
h
e
s
eg
m
e
n
ted
i
m
ag
e
s
.
Fig
u
r
e
3
s
h
o
w
s
t
h
e
s
e
g
m
en
te
d
im
a
g
e
f
o
r
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
an
s
f
o
r
m
atio
n
is
th
e
lo
w
e
s
t
v
alu
e
o
f
P
SNR
2
9
.
1
4
3
d
B
an
d
f
o
r
FC
M
s
eg
m
e
n
ted
i
m
a
g
e
i
s
3
3
.
8
3
6
d
B
.
Pra
ctica
ll
y
it
is
i
n
th
e
r
an
g
e
o
f
2
5
to
4
0
d
B
h
en
ce
F
C
M
s
h
o
w
s
h
ig
h
est
v
alu
e
t
h
an
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
a
n
s
f
o
r
m
at
io
n
.
Of
al
l
t
h
e
o
b
j
ec
tiv
e
q
u
alit
y
m
ea
s
u
r
es,
P
SNR
w
h
i
ch
is
th
e
m
o
s
t
co
m
m
o
n
l
y
u
s
ed
q
u
alit
y
m
ea
s
u
r
e
w
h
ic
h
r
e
f
lects
t
h
e
q
u
al
it
y
o
f
s
eg
m
e
n
ted
im
a
g
e
s
ap
p
r
o
x
i
m
atel
y
.
C
o
m
p
ar
ati
v
el
y
th
e
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
ed
tr
an
s
f
o
r
m
atio
n
p
r
o
v
id
es
b
etter
p
er
f
o
r
m
a
n
ce
in
i
m
a
g
e
s
eg
m
e
n
tat
io
n
w
h
en
co
m
p
ar
ed
t
o
FC
M
alg
o
r
it
h
m
.
7.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
T
h
is
p
ap
er
co
m
p
ar
es
t
h
e
p
er
f
o
r
m
a
n
c
e
o
f
i
m
ag
e
s
e
g
m
en
ta
ti
o
n
m
e
th
o
d
s
s
u
c
h
a
s
F
u
zz
y
c
-
Me
an
s
a
n
d
Ma
r
k
er
co
n
tr
o
lled
w
ater
s
h
e
d
tr
an
s
f
o
r
m
atio
n
al
g
o
r
ith
m
ar
e
d
is
cu
s
s
ed
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
is
m
ea
s
u
r
ed
u
s
i
n
g
s
eg
m
e
n
tatio
n
p
ar
a
m
e
ter
s
P
S
NR
,
S
C
,
NK,
N
A
E
a
n
d
A
D.
T
h
er
ef
o
r
e
f
r
o
m
t
h
e
co
m
p
u
tatio
n
al
r
esu
lts
co
n
c
lu
d
e
th
at
th
e
Ma
r
k
er
co
n
tr
o
lled
w
a
ter
s
h
ed
tr
an
s
f
o
r
m
at
io
n
p
er
f
o
r
m
s
b
etter
th
a
n
Fu
zz
y
c
-
m
ea
n
s
al
g
o
r
ith
m
i
n
t
er
m
s
o
f
p
er
f
o
r
m
an
ce
m
ea
s
u
r
e
s
a
n
d
b
etter
co
n
v
er
g
e
n
ce
r
ate.
I
n
f
u
t
u
r
e
w
o
r
k
,
th
e
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
w
il
l b
e
an
al
y
ze
d
b
ased
o
n
o
p
ti
m
izatio
n
tech
n
iq
u
es a
n
d
co
m
p
ar
is
o
n
w
il
l b
e
ex
te
n
d
ed
to
w
id
e
r
an
g
e
o
f
ap
p
licatio
n
s
.
RE
F
E
R
E
NC
E
S
[1
]
M
r.
P
ra
m
o
d
S
.
lan
d
g
e
,
S
u
sh
il
A.
P
a
ti
l
,
“
A
u
to
m
a
ti
c
d
e
tec
ti
o
n
a
n
d
c
las
si
f
ica
ti
o
n
o
f
p
lan
t
d
ise
a
se
th
ro
u
g
h
im
a
g
e
p
ro
c
e
ss
in
g
”,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
S
o
ft
wa
re
En
g
in
e
e
rin
g
.
V
o
lu
m
e
3
,
Iss
u
e
7
,
Ju
ly
2
0
1
3
.
[2
]
Ja
sk
irat
Ka
u
r
a
n
d
S
u
n
il
A
g
ra
w
a
l
“
A
m
e
th
o
d
o
lo
g
y
f
o
r
th
e
p
e
rf
o
r
m
a
n
c
e
a
n
a
l
y
sis
o
f
c
lu
ste
r
b
a
se
d
im
a
g
e
se
g
m
e
n
tatio
n
”
,
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
in
e
e
rin
g
Res
e
a
rc
h
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
Vo
l.
2
,
Iss
u
e
2
,
M
a
r
-
A
p
r
2
0
1
2
,
p
p
.
6
6
4
-
6
6
7
[3
]
R.
Ha
rik
u
m
a
r,
B.
V
in
o
th
Ku
m
a
r
a
n
d
,
G
.
Ka
rth
ick
a
n
d
I.
N
.
S
n
e
d
d
o
n
,
“
P
e
rf
o
rm
a
n
c
e
a
n
a
l
y
sis
f
o
r
q
u
a
li
ty
m
e
a
su
re
s
u
sin
g
k
m
e
a
n
s
c
lu
ste
rin
g
a
n
d
e
m
m
o
d
e
ls
in
se
g
m
e
n
tatio
n
o
f
m
e
d
ica
l
i
m
a
g
e
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
S
o
ft
c
o
mp
u
ti
n
g
a
n
d
En
g
in
e
e
rin
g
,
v
o
l.
1
,
Iss
u
e
6
,
p
p
.
74
-
8
0
,
Ja
n
u
a
ry
2
0
1
2
.
[4
]
F
a
it
h
p
ra
ise
F
i
n
a
,
P
h
il
ip
Birch
,
“
A
u
to
m
a
ti
c
p
lan
t
p
e
st
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
u
sin
g
k
-
m
e
a
n
s
c
lu
ste
rin
g
a
lg
o
rit
h
m
a
n
d
c
o
rre
sp
o
n
d
e
n
c
e
f
il
ters
”
,
in
I
n
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Bi
o
tec
h
n
o
lo
g
y
a
n
d
Res
e
a
rc
h
.
V
o
l
4
,
Iss
u
e
2
,
2
0
1
3
,
p
p
1
8
9
-
1
9
9
[5
]
Al
-
Hia
r
y
H.,
S
.
B
a
n
i
-
A
h
m
a
d
,
M
.
Re
y
a
lat,
M
.
,
Bra
i
k
a
n
d
Z.
A
l
R
a
h
a
m
n
e
h
(2
0
1
1
),
“
F
a
st
a
n
d
a
c
c
u
ra
te
d
e
tec
ti
o
n
a
n
d
c
las
si
f
ica
ti
o
n
o
f
p
lan
t
d
ise
a
se
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
c
o
mp
u
ter
Ap
p
l
ica
ti
o
n
(
0
9
7
5
-
8
8
8
7
)
,
v
o
l.
1
7
,
No
1
,
p
g
.
3
1
-
38
[6
]
Ja
y
a
m
a
la
K.
P
a
ti
l,
Ra
j
Ku
m
a
r
(2
0
1
1
),
“
A
d
v
a
n
c
e
s
in
i
m
a
g
e
p
ro
c
e
s
sin
g
f
o
r
d
e
tec
ti
o
n
o
f
p
lan
t
d
ise
a
s
e
s”
,
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Bi
o
in
f
o
rm
a
ti
c
s A
p
p
li
c
a
ti
o
n
s
a
n
d
Res
e
a
rc
h
,
IS
S
N
0
9
7
6
-
2
6
0
4
,
v
o
l.
2
,
No
2
,
p
g
.
1
3
5
-
1
4
1
[7
]
W
o
o
d
f
o
rd
B.
J.,
N.K.
Ka
sa
b
o
v
a
n
d
C.
Ho
w
a
rd
W
e
a
rin
g
(1
9
9
9
),
“
F
ru
it
im
a
g
e
a
n
a
l
y
sis
u
sin
g
w
a
v
e
let
s
”
,
Pro
c
e
e
d
in
g
s
o
f
t
h
e
ICONIP/A
NZ
II
S
/A
NNE
S
’9
9
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
,
Un
iv
e
r
sity
o
f
Ota
g
o
P
re
ss
,
p
g
.
88
-
91
[8
]
Ya
n
L
i
Ch
u
n
lei
&
X
ia
Ja
n
g
m
y
u
n
g
L
e
e
(2
0
0
9
),
“
V
isi
o
n
-
b
a
se
d
p
e
st
d
e
tec
ti
o
n
a
n
d
a
u
to
m
a
ti
c
sp
ra
y
o
f
g
re
e
n
h
o
u
se
p
lan
t”,
P
u
sa
n
Na
ti
o
n
a
l
Un
iv
e
rsit
y
In
telli
g
e
n
t
Ro
b
o
t
L
a
b
.
,
IEE
E
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m
o
n
I
n
d
u
st
ria
l
El
e
c
tro
n
ics
(IS
IE
2
0
0
9
)
S
e
o
u
l
Oly
m
p
ic
P
a
rk
tel,
S
e
o
u
l
,
Ko
re
a
J.
Clerk
M
a
x
we
ll
,
A
T
re
a
ti
se
o
n
El
e
c
tri
c
it
y
a
n
d
M
a
g
n
e
ti
sm
,
3
rd
e
d
.
,
v
o
l.
2
.
Ox
f
o
rd
:
Clare
n
d
o
n
,
1
8
9
2
,
p
p
.
68
-
73
[9
]
Am
r
e
e
n
Kh
a
n
a
n
d
P
r
o
f
.
Dr.
N.G
.
Ba
wa
n
e
,
“
A
n
a
n
a
l
y
sis
o
f
p
a
rti
c
le
sw
a
r
m
o
p
ti
m
iza
ti
o
n
w
it
h
d
a
ta
c
lu
ste
rin
g
-
tec
h
n
iq
u
e
f
o
r
o
p
ti
m
iza
ti
o
n
in
d
a
t
a
m
in
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
n
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
in
e
e
rin
g
,
V
o
l.
0
2
,
No
.
0
4
,
2
0
1
0
,
1
3
6
3
-
1
3
6
6
[1
0
]
P
a
u
l
Bo
issa
rd
,
V
in
c
e
n
t
M
a
rti
n
“
A
c
o
g
n
it
iv
e
v
isio
n
a
p
p
r
o
a
c
h
t
o
e
a
rly
p
e
st
d
e
tec
ti
o
n
in
g
re
e
n
h
o
u
se
c
ro
p
s”
,
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
Ag
ric
u
lt
u
re
,
6
2
,
2
(
2
0
0
8
)
8
1
-
93
,
DO
I
:
1
0
.
1
0
1
6
/j
.
c
o
m
p
a
g
.
2
0
0
7
.
1
1
.
0
0
9
[1
1
]
M
.
M
u
e
ll
e
r,
K.
S
e
g
l,
a
n
d
H.
Ka
u
fm
a
n
n
,
“
Ed
g
e
-
a
n
d
re
g
io
n
-
b
a
se
d
se
g
m
e
n
tatio
n
tec
h
n
iq
u
e
f
o
r
th
e
e
x
trac
ti
o
n
o
f
larg
e
,
m
a
n
-
m
a
d
e
o
b
jec
ts
in
h
i
gh
-
r
e
so
lu
ti
o
n
sa
telli
te
im
a
g
e
r
y
”
,
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
v
o
l.
3
7
,
n
o
.
8
,
p
p
.
1
6
1
9
–
1
6
2
8
,
2
0
0
4
.
[1
2
]
S.
Be
u
c
h
e
r,
F
.
M
e
y
e
r,
T
h
e
m
o
rp
h
o
l
o
g
ica
l
a
p
p
ro
a
c
h
t
o
se
g
m
e
n
tatio
n
:
T
h
e
w
a
ters
h
e
d
tran
sf
o
r
m
‖,
in
M
a
th
e
m
a
ti
c
a
l
M
o
rp
h
o
l
o
g
y
I
m
a
g
e
P
ro
c
e
ss
in
g
,
E
.
R.
Do
u
g
h
e
rty
,
Ed
.
Ne
w
Yo
rk
M
a
rc
e
l
De
k
k
e
r,
v
o
l.
1
2
,
p
p
.
4
3
3
–
4
8
1
,
1
9
9
3
.
[1
3
]
J.
T
il
to
n
,
“
Im
a
g
e
s
e
g
m
e
n
tatio
n
b
y
r
e
g
io
n
g
ro
w
in
g
a
n
d
sp
e
c
tral
c
lu
ste
rin
g
w
it
h
a
n
a
tu
ra
l
c
o
n
v
e
rg
e
n
c
e
c
rit
e
rio
n
”
,
in
IEE
E
Ge
o
sc
ien
c
e
a
n
d
Rem
o
te S
e
n
sin
g
S
y
mp
o
siu
m P
r
o
c
e
e
d
in
g
s
,
1
9
9
8
,
p
p
.
1
7
6
6
–
1
7
6
8
.
[1
4
]
Yi
M
o
u
a
n
d
Qin
g
Z
h
a
o
,
“
A
p
p
li
c
a
ti
o
n
o
f
sim
u
late
d
a
n
n
e
a
li
n
g
a
lg
o
rit
h
m
in
p
e
st
im
a
g
e
se
g
m
e
n
tatio
n
”
,
2
0
0
9
S
e
c
o
n
d
In
ter
n
a
t
io
n
a
l
S
y
mp
o
si
u
m o
n
C
o
m
p
u
t
a
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
De
sig
n
,
IEE
E
DO
I
1
0
.
1
1
0
9
/IS
CID
.
2
0
0
9
.
1
2
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
A
n
a
lyzi
n
g
th
e
Op
ti
ma
l P
erfo
r
ma
n
ce
o
f P
est I
ma
g
e
S
eg
men
t
a
tio
n
u
s
in
g
N
o
n
Lin
ea
r
…
(
S
iva
S
a
n
g
a
r
i A
)
2796
[1
5
]
G
o
n
z
a
lez
,
R.
,
R.
W
o
o
d
s
a
n
d
S
.
Ed
d
i
n
s,
2
0
0
4
.
Di
g
it
a
l
Ima
g
e
Pr
o
c
e
ss
in
g
u
si
n
g
M
AT
L
AB
.
1
st
E
d
n
.
,
P
ri
n
ti
c
e
Ha
ll
,
IS
BN:
0
1
3
0
0
8
5
1
9
7
,
p
p
:
6
2
4
[1
6
]
G
.
N.S
rin
iv
a
sa
n
,
“
S
e
g
m
e
n
tatio
n
tec
h
n
iq
u
e
s
f
o
r
targ
e
t
re
c
o
g
n
it
io
n
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
s
A
n
d
Co
mm
u
n
ica
ti
o
n
.
Iss
u
e
3
,
Vo
lu
m
e
1
,
2
0
0
7
.
[1
7
]
M
a
rio
G
.
C.
A
.
Ci
m
in
o
,
Be
a
tri
c
e
L
a
z
z
e
rin
i
a
n
d
F
ra
n
c
e
sc
o
M
a
rc
e
ll
o
n
i,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
to
f
u
z
z
y
c
lu
ste
rin
g
b
a
se
d
o
n
a
d
issim
il
a
rit
y
re
latio
n
e
x
trac
ted
f
ro
m
d
a
ta u
sin
g
a
T
S
s
y
ste
m
,
Pa
tt
e
rn
Rec
o
g
n
it
io
n
”
,
3
9
(
1
1
)
,
(2
0
0
6
)
,
2
0
7
7
-
2
0
9
1
.
[1
8
]
Ro
b
e
rt
L
.
Ca
n
n
o
n
,
Ji
ten
d
ra
V
.
Da
v
e
,
A
n
d
Ja
m
e
s
C.
Be
z
d
e
k
,
“
Eff
icie
n
t
Im
p
le
m
e
n
tatio
n
o
f
T
h
e
F
u
z
z
y
C
-
M
e
a
n
s
Clu
ste
n
g
A
lg
o
rn
th
m
s
”
,
IEE
E
tra
n
sa
c
ti
o
n
s
o
n
p
a
tt
e
rn
a
n
a
lys
is
a
n
d
ma
c
h
in
e
in
telli
g
e
n
c
e
.
Vo
l.
P
a
m
i
-
8
,
n
o
.
2
,
m
a
rc
h
1
9
8
6
.
[1
9
]
S
u
m
a
th
i
P
o
o
b
a
l
“
T
h
e
p
e
rf
o
r
m
a
n
c
e
o
f
f
r
a
c
tal
i
m
a
g
e
c
o
m
p
re
s
sio
n
o
n
d
if
fe
re
n
t
i
m
a
g
in
g
m
o
d
a
li
ti
e
s
u
sin
g
o
b
jec
ti
v
e
q
u
a
li
ty
m
e
a
su
re
s”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
V
o
l
.
3
No
.
1
Ja
n
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.