T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
2
0
1
8
~
2
0
2
6
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i4
.
1
4
6
1
4
2018
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Identifica
tion o
f
p
a
ddy
leaf disea
ses
bas
ed on tex
ture
a
na
ly
sis
of Blo
bs a
nd colo
r seg
m
e
n
tatio
n
Alex
We
nd
a
1
,
I
ng
g
ih P
er
m
a
na
2
,
Yus
m
a
r
3
,
Nuni
k
No
v
ia
na
K
urnia
w
a
t
i
4
1
,
2
De
p
a
rtm
e
n
t
o
f
E
lec
tri
c
a
l
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
tate
Isla
m
ic Un
iv
e
rsit
y
o
f
S
u
lt
a
n
S
y
a
ri
f
Ka
si
m
Ri
a
u
,
In
d
o
n
e
sia
3
De
p
a
rtme
n
t
o
f
A
g
ro
tec
h
n
o
l
o
g
y
,
F
a
c
u
lt
y
o
f
A
g
ricu
lt
u
re
a
n
d
A
n
ima
l
S
c
ien
c
e
,
S
tate
Isla
m
ic Un
iv
e
rsit
y
o
f
S
u
lt
a
n
S
y
a
ri
f
Ka
si
m
Ri
a
u
,
In
d
o
n
e
sia
4
Ed
u
c
a
ti
o
n
a
l
Q
u
a
li
ty
A
ss
u
ra
n
c
e
I
n
stit
u
t
io
n
s o
f
Riau
P
r
o
v
in
c
e
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
No
v
15
,
2019
R
ev
i
s
ed
Mar
29
,
2
0
2
0
A
cc
ep
ted
A
p
r
9
,
2
0
2
0
T
h
e
re
a
r
e
th
re
e
t
y
p
e
s
o
f
p
a
d
d
y
lea
f
d
ise
a
se
s
th
a
t
h
a
v
e
si
m
il
a
r
s
y
m
p
to
m
s,
m
a
k
in
g
it
d
if
f
icu
lt
f
o
r
f
a
r
m
e
rs
to
i
d
e
n
ti
f
y
th
e
m
,
n
a
m
e
l
y
b
las
t
,
b
ro
w
n
-
sp
o
t
,
a
n
d
n
a
rr
o
w
b
ro
w
n
-
sp
o
t
.
T
h
is
stu
d
y
a
i
m
s
to
id
e
n
ti
f
ica
ti
o
n
p
a
d
d
y
p
lan
t
d
ise
a
se
s
b
a
se
d
o
n
tex
tu
re
a
n
a
ly
sis
o
f
Blo
b
s
a
n
d
c
o
lo
r
se
g
m
e
n
tatio
n
.
Blo
b
s
a
n
a
ly
sis
is
u
se
d
to
g
e
t
t
h
e
n
u
m
b
e
r
o
f
o
b
jec
ts,
a
re
a
a
n
d
p
e
rime
ter.
Co
lo
r
se
g
m
e
n
tatio
n
is
u
se
d
t
o
f
in
d
o
u
t
s
o
m
e
c
o
lo
r
p
a
ra
m
e
ters
o
f
p
a
d
d
y
lea
f
d
ise
a
se
su
c
h
a
s
th
e
c
o
lo
r
o
f
th
e
les
io
n
b
o
u
n
d
a
ry
,
th
e
c
o
lo
r
o
f
th
e
sp
o
t
o
f
th
e
les
io
n
,
a
n
d
th
e
c
o
l
o
r
o
f
th
e
p
a
d
d
y
lea
f
les
io
n
.
T
o
g
e
t
th
e
b
e
st
re
su
lt
s,
f
o
u
r
m
e
th
o
d
s
h
a
v
e
b
e
e
n
c
h
o
se
n
to
o
b
tain
e
d
th
e
t
h
re
sh
o
ld
v
a
lu
e
,
Otsu
th
re
s
h
o
l
d
v
a
lu
e
,
v
a
riab
le
th
re
sh
o
ld
v
a
lu
e
,
lo
c
a
l
th
re
sh
o
ld
v
a
lu
e
a
n
d
g
lo
b
a
l
th
re
sh
o
ld
v
a
lu
e
.
T
h
e
b
e
st
a
c
c
u
ra
c
y
o
f
th
e
f
o
u
r
m
e
th
o
d
s
u
sin
g
th
re
sh
o
l
d
v
a
riab
les
is
9
0
.
7
%
.
T
h
e
re
su
lt
s
o
f
th
is
stu
d
y
in
d
ica
te
th
a
t
th
e
m
e
th
o
d
u
se
d
h
a
s
b
e
e
n
v
e
r
y
sa
ti
sfa
c
to
r
y
in
id
e
n
t
ify
in
g
p
a
d
d
y
p
lan
t
d
ise
a
se
.
K
ey
w
o
r
d
s
:
B
last
B
lo
b
s
B
r
o
w
n
-
s
p
o
t
C
o
lo
r
s
eg
m
en
ta
tio
n
Nar
r
o
w
b
r
o
w
n
-
s
p
o
t
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r
th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
le
x
W
en
d
a,
Dep
ar
t
m
en
t o
f
E
lectr
ical
E
n
g
i
n
ee
r
in
g
,
Fac
u
lt
y
o
f
Scie
n
ce
an
d
T
ec
h
n
o
lo
g
y
,
State
I
s
la
m
ic
Un
iv
er
s
it
y
o
f
S
u
ltan
S
y
ar
if
Ka
s
i
m
R
ia
u
,
155
HR
.
So
eb
r
an
tas
St.,
K
m
.
1
5
,
P
ek
an
b
ar
u
-
R
iau
,
I
n
d
o
n
e
s
ia
.
E
m
ail:
ale
x
w
e
n
d
a@
u
i
n
-
s
u
s
k
a.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
er
e
ar
e
v
ar
io
u
s
t
y
p
es
o
f
p
e
s
ts
a
n
d
d
is
ea
s
es
in
p
ad
d
y
p
lan
ts
,
in
cl
u
d
i
n
g
b
last
,
b
r
o
w
n
s
p
o
t,
n
ar
r
o
w
b
r
o
w
n
s
p
o
t,
s
h
ea
t
h
b
li
g
h
t,
b
a
cter
ial
leaf
b
lig
h
t,
t
u
n
g
r
o
,
w
h
ite
p
est,
s
te
m
b
o
r
er
,
r
at
p
est,
g
r
ee
n
lad
y
b
u
g
a
n
d
s
tin
k
b
u
g
[1
,
2]
.
T
h
is
s
tu
d
y
w
i
ll f
o
cu
s
o
n
3
t
y
p
es o
f
p
ad
d
y
p
l
an
t d
is
ea
s
es,
b
last
,
b
r
o
w
n
s
p
o
t a
n
d
n
ar
r
o
w
b
r
o
w
n
s
p
o
t.
T
h
r
ee
t
y
p
es
o
f
t
h
is
d
is
e
ases
h
a
v
e
c
h
ar
ac
ter
is
tics
t
h
at
ar
e
al
m
o
s
t
t
h
e
s
a
m
e
as
ea
ch
o
th
er
s
o
th
at
t
h
is
m
ak
e
s
it
d
if
f
ic
u
lt
f
o
r
f
ar
m
er
s
to
id
en
ti
f
y
t
h
e
d
is
ea
s
e
a
n
d
r
eq
u
ir
e
s
p
ec
ial
e
x
p
er
tis
e
to
b
e
ab
le
to
d
is
ti
n
g
u
i
s
h
th
e
t
h
r
ee
t
y
p
es
o
f
d
is
ea
s
es
[3
,
4]
.
A
p
ar
t
f
r
o
m
t
h
at,
t
h
e
t
h
r
ee
t
y
p
e
s
o
f
d
is
ea
s
e
s
ar
e
v
er
y
w
id
esp
r
ea
d
an
d
ca
n
b
e
f
o
u
n
d
in
m
o
r
e
th
a
n
8
0
co
u
n
tr
i
es
[2
,
5]
.
T
h
e
m
o
s
t
i
m
p
o
r
tan
t
th
i
n
g
o
f
th
e
th
r
ee
t
y
p
e
s
o
f
d
is
ea
s
es
is
t
h
e
r
es
u
lt
i
f
th
e
p
ad
d
y
p
la
n
t
h
a
s
b
ee
n
i
n
f
ec
ted
w
it
h
th
is
d
is
ea
s
e,
n
a
m
e
l
y
a
m
ar
k
ed
d
ec
r
ea
s
e
in
y
iel
d
,
b
ec
au
s
e
it
ca
u
s
e
s
th
e
p
an
icle
to
r
o
t o
r
b
r
ea
k
,
th
is
w
il
l in
h
ib
it t
h
e
p
r
o
ce
s
s
o
f
f
il
li
n
g
t
h
e
g
r
ain
,
ca
u
s
i
n
g
t
h
e
g
r
ai
n
to
b
ec
o
m
e
e
m
p
t
y
.
T
h
is
w
il
l
ce
r
tain
l
y
lead
to
a
d
ec
r
ea
s
e
in
p
ad
d
y
p
r
o
d
u
ctio
n
a
n
d
if
p
r
o
d
u
ctio
n
d
ec
r
ea
s
es,
it
w
il
l
ce
r
tain
l
y
h
a
v
e
an
i
m
p
ac
t
o
n
lo
s
s
e
s
.
T
h
e
d
is
e
ase
ca
u
s
ed
b
y
th
i
s
f
u
n
g
u
s
i
s
e
s
ti
m
ated
to
h
a
v
e
ca
u
s
ed
r
ed
u
c
tio
n
o
f
a
p
r
o
d
u
ctio
n
in
th
e
r
an
g
e
o
f
1
0
-
1
5
%
in
tr
o
p
ical
A
s
ia.
R
ed
u
ctio
n
ar
e
ev
en
h
i
g
h
er
in
th
e
E
as
t
Asi
a
r
eg
i
o
n
an
d
s
o
m
e
ar
ea
s
th
at
h
a
v
e
h
ig
h
er
cli
m
ate
te
m
p
er
atu
r
es
[2
,
6]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f
p
a
d
d
y
lea
f
d
is
ea
s
es b
a
s
ed
o
n
textu
r
e
a
n
a
lysi
s
o
f
…
(
A
lex
W
en
d
a
)
2019
A
t
th
is
tim
e
th
e
h
an
d
li
n
g
o
f
p
ad
d
y
d
i
s
e
a
s
es
w
i
th
c
o
n
v
en
t
i
o
n
al
m
e
th
o
d
s
is
t
o
m
ak
e
o
b
s
e
r
v
a
tio
n
s
u
s
in
g
d
i
r
e
c
t
o
b
s
e
r
v
at
i
o
n
o
f
th
e
n
ak
e
d
ey
e
b
y
e
x
p
e
r
t
s
.
I
f
th
is
is
d
o
n
e
i
n
a
v
e
r
y
l
a
r
g
e
p
l
an
t
in
g
a
r
e
a
,
it
c
e
r
t
ai
n
ly
r
e
q
u
i
r
es
a
l
a
r
g
e
n
u
m
b
e
r
o
f
e
x
p
e
r
t
s
a
n
d
r
e
q
u
i
r
es
a
l
o
t
o
f
t
im
e
t
o
m
o
n
i
t
o
r
a
n
d
o
b
s
e
r
v
e
i
t
,
b
es
i
d
es
th
at
th
e
l
ev
e
l
o
f
a
cc
u
r
a
cy
i
s
al
s
o
l
o
w
[7
,
8]
.
A
t
th
e
s
am
e
t
im
e
f
a
r
m
e
r
s
d
o
n
o
t
h
av
e
g
o
o
d
k
n
o
w
le
d
g
e
a
b
o
u
t
p
l
an
t
d
is
e
ase
s
an
d
if
th
ey
b
r
in
g
i
n
ex
p
e
r
t
s
,
o
f
c
o
u
r
s
e
,
r
e
q
u
i
r
e
la
r
g
e
c
o
s
ts
an
d
l
o
n
g
tim
e
.
Un
d
e
r
t
h
e
s
e
c
o
n
d
it
i
o
n
s
,
th
e
r
e
c
o
m
m
en
d
e
d
t
ec
h
n
i
q
u
e
p
r
o
v
e
d
u
s
ef
u
l
in
m
o
n
i
t
o
r
in
g
la
r
g
e
p
la
n
t
a
r
e
as
is
au
t
o
m
a
t
i
c
d
e
t
ec
t
i
o
n
o
f
p
l
an
t
d
is
e
as
es
b
y
l
o
o
k
in
g
a
t
s
y
m
p
t
o
m
s
o
n
p
l
a
n
t
l
e
av
es
b
y
u
t
i
l
iz
in
g
im
ag
e
p
r
o
c
e
s
s
in
g
an
d
c
o
m
p
u
t
e
r
v
is
i
o
n
t
e
ch
n
i
q
u
es
[
9
,
1
0
]
.
S
ev
e
r
a
l
s
tu
d
i
es
r
e
la
t
e
d
t
o
p
a
d
d
y
d
is
e
as
e
s
u
s
in
g
im
ag
e
p
r
o
c
e
s
s
i
n
g
te
ch
n
i
q
u
e
s
,
am
o
n
g
o
th
e
r
s
,
h
av
e
b
e
en
co
n
d
u
c
t
e
d
[
1
1
]
,
d
ev
e
l
o
p
m
en
t
o
f
r
i
c
e
p
l
an
t
d
is
e
as
e
s
y
s
t
em
d
i
a
g
n
o
s
i
s
,
w
it
h
an
a
c
cu
r
a
cy
r
a
t
e
o
f
7
9
.
5
%
[
1
2
]
.
I
d
e
n
t
if
i
c
a
ti
o
n
o
f
r
i
c
e
p
l
a
n
t
d
is
e
a
s
e
u
s
in
g
b
a
ck
p
r
o
p
ag
a
t
i
o
n
ar
t
i
f
i
c
i
al
n
eu
r
a
l
n
etw
o
r
k
,
w
ith
a
n
ac
cu
r
a
cy
r
a
t
e
o
f
9
3
%
[
1
3
]
.
E
x
p
e
r
t
s
y
s
t
em
f
o
r
m
an
a
g
e
m
e
n
t
o
f
r
ice
p
la
n
ts
w
i
th
le
v
el
s
ac
c
u
r
ac
y
o
f
8
5
%,
[
1
2
]
.
I
d
en
tif
icatio
n
o
f
r
ice
leaf
d
is
ea
s
e
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
w
it
h
an
ac
cu
r
ac
y
o
f
8
8
%
[
1
4
]
,
id
en
tif
icatio
n
o
f
r
ice
p
lan
t
d
is
ea
s
es
b
ased
o
n
tex
t
u
r
e
an
al
y
s
i
s
8
5
%
[
1
5
,
1
6
]
an
d
d
is
ea
s
es
id
en
ti
f
icat
io
n
s
y
s
te
m
i
n
p
ad
d
y
p
lan
t
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
w
it
h
lev
el
s
ac
cu
r
ac
y
o
f
9
4
.
7
%
[
1
7
]
.
Var
io
u
s
m
et
h
o
d
s
h
a
v
e
b
ee
n
d
ev
el
o
p
ed
in
th
e
r
esear
ch
m
en
tio
n
ed
ab
o
v
e,
th
e
d
ev
elo
p
m
en
t
o
f
t
h
is
m
et
h
o
d
to
g
et
ac
cu
r
ate
r
esu
l
ts
w
it
h
s
m
all
er
r
o
r
s
,
in
cl
u
d
in
g
u
s
i
n
g
th
e
r
u
le
b
ase
e
x
p
er
t
s
y
s
te
m
,
f
u
zz
y
e
x
p
er
t
s
y
s
te
m
an
d
ar
ti
f
i
cial
in
tell
ig
e
n
t.
B
ased
o
n
t
h
e
b
ac
k
g
r
o
u
n
d
ab
o
v
e,
th
is
s
t
u
d
y
ai
m
s
to
id
en
t
if
ica
tio
n
o
f
p
ad
d
y
lea
f
d
is
ea
s
es
n
a
m
el
y
b
last
,
b
r
o
w
n
s
p
o
t a
n
d
n
ar
r
o
w
b
r
o
w
n
s
p
o
t u
s
in
g
tex
t
u
r
e
an
al
y
s
is
o
f
B
lo
b
s
a
n
d
co
lo
r
s
eg
m
en
tatio
n
.
T
h
ese
te
ch
n
iq
u
es
u
s
ed
to
g
e
t
c
h
ar
ac
ter
is
tics
o
f
d
is
ea
s
ed
leaf
,
th
is
ch
ar
ac
ter
i
s
tic
is
t
h
e
n
u
s
ed
to
id
en
ti
f
y
t
h
e
t
y
p
e
o
f
d
is
ea
s
e
u
s
i
n
g
a
r
u
le
-
b
ased
ex
p
er
t s
y
s
te
m
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
2
.
1
.
Da
t
a
c
o
llect
io
n
C
ap
tu
r
i
n
g
i
m
a
g
es
o
f
d
is
ea
s
ed
p
ad
d
y
leaf
is
th
e
f
ir
s
t
p
ar
t
o
f
th
i
s
s
t
u
d
y
.
T
o
g
et
an
im
a
g
e
th
at
h
as
a
u
n
i
f
o
r
m
b
r
ig
h
t
n
es
s
lev
el,
t
h
e
en
v
ir
o
n
m
e
n
t
m
u
s
t
b
e
co
n
tr
o
lled
,
s
o
m
e
i
m
p
o
r
tan
t
p
ar
a
m
ete
r
s
ar
e,
f
lash
ca
m
er
a
an
d
d
is
tan
ce
o
f
th
e
o
b
j
ec
t
f
r
o
m
t
h
e
ca
m
er
a.
T
h
e
d
is
tan
ce
b
et
w
ee
n
t
h
e
o
b
j
ec
t
an
d
th
e
ca
m
er
a
is
b
et
w
ee
n
15
-
30
c
m
a
n
d
u
s
i
n
g
t
h
e
f
las
h
lig
h
t
o
n
t
h
e
ca
m
er
a.
T
h
e
i
m
a
g
e
w
a
s
ta
k
en
d
u
r
i
n
g
t
h
e
d
a
y
an
d
t
h
e
p
r
o
ce
s
s
o
f
tak
i
n
g
t
h
e
p
ad
d
y
lea
f
i
m
ag
e
m
u
s
t
b
e
ca
r
r
ied
o
u
t
q
u
ick
l
y
a
f
te
r
th
e
p
ad
d
y
leaf
ar
e
cu
t
f
r
o
m
t
h
e
tr
ee
.
Oth
er
w
is
e,
th
e
lea
f
w
ill
i
m
m
ed
iatel
y
r
o
ll.
I
m
a
g
e
o
f
p
ad
d
y
lea
f
is
r
esize
d
in
to
i
m
a
g
es
w
it
h
a
r
eso
l
u
tio
n
o
f
1
0
5
×3
0
5
an
d
s
to
r
ed
in
b
it
m
ap
f
o
r
m
at
(
*
.
B
MP
)
.
E
x
a
m
p
les
o
f
s
a
m
p
le
i
m
ag
es
a
n
d
c
h
ar
ac
ter
is
tic
s
o
f
t
h
e
lesi
o
n
to
d
is
ea
s
ed
p
ad
d
y
leaf
a
s
s
h
o
w
n
b
y
F
ig
u
r
e
1.
(
a)
(
b)
(
c)
Fig
u
r
e
1
.
(
a)
B
last
,
(
b
)
B
r
o
w
n
s
p
o
t
(
c)
N
ar
r
o
w
b
r
o
w
n
s
p
o
t
2
.
2
.
I
m
a
g
e
s
eg
m
e
nta
t
io
n
B
ef
o
r
e
d
o
in
g
t
h
e
i
m
a
g
e
s
e
g
m
en
tatio
n
p
r
o
ce
s
s
,
th
e
i
m
ag
e
is
p
r
ep
ar
ed
to
h
av
e
d
i
m
e
n
s
io
n
s
o
f
1
0
5
x
3
0
5
p
ix
els
i
n
t
h
e
R
GB
co
lo
r
f
o
r
m
at.
T
h
is
r
esear
ch
ap
p
li
es
f
o
u
r
m
et
h
o
d
s
to
o
b
tain
ed
th
e
th
r
es
h
o
ld
v
al
u
e:
g
lo
b
al
th
r
es
h
o
ld
v
al
u
e,
Ots
u
th
r
es
h
o
ld
v
alu
e
f
o
r
au
to
m
a
tic
th
r
esh
o
ld
v
a
lu
e
[
1
8
]
,
lo
ca
l
t
h
r
es
h
o
ld
v
alu
e
a
n
d
th
e
v
ar
iab
le
t
h
r
es
h
o
ld
v
al
u
e.
T
h
e
R
GB
i
m
a
g
e
as
i
n
s
h
o
w
n
b
y
Fi
g
u
r
e
2
(
a)
w
i
ll
b
e
co
n
v
e
r
ted
to
a
g
r
ay
lev
e
l
i
m
a
g
e.
Fu
r
t
h
er
m
o
r
e,
i
m
ag
e
s
e
g
m
e
n
tat
io
n
is
ap
p
lied
b
ased
o
n
g
r
a
y
lev
el
t
h
r
es
h
o
ld
s
eg
m
e
n
tatio
n
,
af
ter
w
h
ic
h
th
e
i
m
a
g
e
r
ep
air
p
r
o
ce
s
s
is
p
er
f
o
r
m
ed
u
s
i
n
g
a
m
ed
ian
f
i
lter
an
d
m
o
r
p
h
o
lo
g
ica
l
o
p
er
ato
r
s
ar
e
ap
p
lied
to
r
e
m
o
v
e
u
n
n
ec
es
s
ar
y
s
p
o
ts
b
y
u
s
i
n
g
a
r
eg
io
n
f
illi
n
g
tech
n
iq
u
e,
s
o
th
at
a
b
in
ar
y
i
m
a
g
e
th
at
i
s
f
r
ee
f
r
o
m
n
o
is
e
i
s
g
en
er
ated
as i
n
s
h
o
w
n
b
y
Fig
u
r
e
2
(
b
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
2
0
1
8
-
2
0
2
6
2020
(
a)
(
b)
Fig
u
r
e
2
.
(
a)
R
GB
im
a
g
e
,
(
b
)
B
in
ar
y
i
m
ag
e
2
.
3
.
B
lo
bs
a
na
ly
s
is
B
lo
b
s
an
al
y
s
i
s
i
s
u
s
ed
to
ex
tr
a
ct
th
e
f
ea
t
u
r
es
o
f
a
n
o
b
j
ec
t,
n
a
m
el
y
t
h
e
s
h
ap
e
o
f
th
e
o
b
j
ec
t,
th
e
o
b
j
ec
t
ar
ea
,
th
e
h
o
le
ar
ea
o
f
th
e
o
b
ject,
th
e
p
er
i
m
eter
.
Ob
j
ec
t
is
a
lesi
o
n
o
n
t
h
e
p
ad
d
y
lea
f
.
S
h
ap
e
tex
tu
r
e
an
a
l
y
s
is
u
s
e
s
B
lo
b
s
an
al
y
s
i
s
b
y
ca
lcu
l
atin
g
th
e
r
a
tio
o
f
th
e
b
o
u
n
d
ar
y
b
o
x
,
w
h
ich
is
h
eig
h
t/
w
id
th
.
T
h
e
b
o
u
n
d
ar
y
o
f
th
e
b
o
x
is
th
e
v
al
u
e
o
f
th
e
co
o
r
d
in
ates
o
f
th
e
u
p
p
er
lef
t
p
o
i
n
t,
th
e
w
id
t
h
an
d
h
ei
g
h
t
o
f
th
e
s
q
u
ar
e
b
o
r
d
e
r
o
f
th
e
o
b
j
ec
t,
as sh
o
w
n
in
Fi
g
u
r
e
3.
Fig
u
r
e
3
.
B
o
u
n
d
ar
y
b
o
x
B
ased
o
n
1
0
0
d
i
s
ea
s
ed
p
ad
d
y
leaf
i
m
a
g
es,
co
n
s
i
s
ti
n
g
o
f
2
0
i
m
ag
e
s
f
o
r
ea
ch
t
y
p
e
o
f
d
is
ea
s
e
,
an
al
y
ze
d
to
o
b
tain
h
e
ig
h
t
a
n
d
w
id
t
h
v
alu
es
an
d
t
h
e
n
o
b
tain
ed
r
u
les
to
d
eter
m
i
n
e
t
h
e
t
y
p
e
o
f
d
am
ag
e,
as
s
h
o
w
n
i
n
Fig
u
r
e
4.
I
f
v
al
u
e
o
f
h
eig
h
t
an
d
w
id
t
h
g
r
ea
th
er
-
t
h
an
o
r
eq
u
al
to
2
.
8
an
d
les
s
-
t
h
a
n
4
.
1
th
e
t
y
p
e
o
f
o
b
j
ec
t
s
h
ap
e
is
s
p
in
d
le.
I
f
v
alu
e
o
f
w
id
th
less
-
t
h
an
o
r
eq
u
al
to
2
.
8
th
e
t
y
p
e
o
f
o
b
j
ec
t
s
h
ap
e
is
tap
er
.
I
f
v
al
u
e
o
f
w
id
th
g
r
ea
th
er
-
t
h
an
o
r
eq
u
al
to
2
.
8
th
e
t
y
p
e
o
f
o
b
j
ec
t
s
h
ap
e
is
o
v
al.
I
f
v
al
u
e
o
f
h
ei
g
h
t
a
n
d
w
id
th
g
r
ea
th
er
-
th
a
n
o
r
eq
u
al
to
2
.
8
th
e
t
y
p
e
o
f
o
b
j
ec
t
s
h
ap
e
is
r
o
u
n
d
a
n
d
i
f
v
al
u
e
o
f
h
ei
g
h
t
an
d
w
id
t
h
less
-
t
h
an
o
r
eq
u
al
to
2
.
8
th
e
t
y
p
e
o
f
o
b
j
ec
t
s
h
ap
e
is
s
p
o
t.
Usu
all
y
t
h
er
e
is
m
o
r
e
t
h
an
o
n
e
t
y
p
e
o
f
les
io
n
o
n
t
h
e
p
ad
d
y
leaf
d
is
ea
s
e.
T
h
er
ef
o
r
e,
th
e
n
u
m
b
er
o
f
o
b
ject
f
o
r
m
n
u
m
b
er
s
is
a
n
i
m
p
o
r
tan
t
in
f
o
r
m
atio
n
to
d
eter
m
i
n
e
th
e
s
y
m
p
to
m
o
f
th
e
m
aj
o
r
lesi
o
n
t
y
p
e.
B
ase
d
o
n
Ma
la
y
s
ia
Ag
r
icu
l
tu
r
al
R
esear
ch
a
n
d
Dev
e
lo
p
m
en
t
I
n
s
tit
u
te
(
M
A
R
DI
)
ex
p
er
ts
,
s
eq
u
en
ce
o
f
t
y
p
es
o
f
d
is
ea
s
ed
leaf
lesi
o
n
f
o
r
m
s
as
f
o
llo
w
s
:
s
p
i
n
d
le
s
h
ap
e,
o
v
al
s
h
ap
e/r
o
u
n
d
s
h
ap
e/tap
er
ed
s
h
ap
e,
s
p
o
t sh
ap
e.
A
cc
o
r
d
in
g
to
MA
R
DI
ex
p
er
ts
,
if
th
er
e
is
a
f
o
r
m
o
f
s
p
in
d
le
o
n
a
d
is
ea
s
ed
leaf
,
th
en
th
e
t
y
p
e
o
f
s
p
o
ttin
g
is
s
p
in
d
le.
W
h
en
t
h
er
e
ar
e
o
v
al,
r
o
u
n
d
an
d
tap
er
s
h
ap
es,
th
e
clea
r
est
an
d
m
o
s
t
o
b
v
io
u
s
s
h
ap
es
w
ill
b
e
ch
o
s
en
,
as
s
h
o
w
n
in
Fig
u
r
e
5
.
I
f
n
u
m
b
er
o
f
o
b
j
ec
t
s
p
in
d
le
g
r
ea
th
er
th
a
n
0
,
t
y
p
e
o
f
lesi
o
n
i
s
s
p
in
d
le.
I
f
n
u
m
b
er
o
f
o
b
j
ec
t
o
v
al
g
r
ea
th
er
-
t
h
a
n
o
r
eq
u
al
to
n
u
m
b
er
o
f
o
b
j
ec
t
r
o
u
n
d
an
d
n
u
m
b
er
o
f
o
b
j
ec
t
o
v
al
g
r
e
ath
er
-
th
a
n
o
r
eq
u
al
to
n
u
m
b
er
o
f
o
b
j
ec
t
tap
er
th
e
t
y
p
e
o
f
lesi
o
n
is
o
v
al.
I
f
n
u
m
b
er
o
f
o
b
j
ec
t
r
o
u
n
d
g
r
ea
th
er
-
t
h
a
n
o
r
eq
u
al
to
n
u
m
b
er
o
f
o
b
j
ec
t
tap
er
th
e
ty
p
e
o
f
lesi
o
n
is
r
o
u
n
d
.
I
f
n
u
m
b
er
o
f
o
b
j
ec
t
o
v
al
eq
u
al
to
0
an
d
n
u
m
b
er
o
f
o
b
j
ec
t
r
o
u
n
d
eq
u
al
to
0
an
d
n
u
m
b
er
o
f
o
b
j
ec
t ta
p
er
e
q
u
al
to
0
th
e
t
y
p
e
o
f
les
io
n
i
s
s
p
o
t,
o
th
e
w
i
s
e
th
e
t
y
p
e
o
f
le
s
io
n
i
s
tap
er
.
I
n
d
is
ea
s
ed
r
ice
leaf
u
s
u
all
y
th
er
e
is
m
o
r
e
th
a
n
o
n
e
t
y
p
e
o
f
o
b
j
ec
t
th
at
is
in
th
e
r
ice
le
af
.
th
er
ef
o
r
e
to
g
et
th
e
s
h
ap
e
ch
ar
ac
ter
is
tics
it
is
n
ec
ess
ar
y
to
co
u
n
t
t
h
e
n
u
m
b
er
o
f
o
b
j
ec
ts
th
at
ap
p
ea
r
o
n
th
e
r
ice
lea
f
u
s
in
g
th
e
8
-
co
n
n
ec
ted
en
v
ir
o
n
m
e
n
t t
ec
h
n
iq
u
e,
as s
h
o
w
n
i
n
Fi
g
u
r
e
6.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f
p
a
d
d
y
lea
f
d
is
ea
s
es b
a
s
ed
o
n
textu
r
e
a
n
a
lysi
s
o
f
…
(
A
lex
W
en
d
a
)
2021
C
h
e
c
k
w
h
e
t
h
e
r
s
p
o
t
o
r
r
a
o
u
n
d
h
/
w
£
2
.
8
h
/
w
>
2
.
8
t
o
s
=
s
p
o
t
t
o
s
=
r
o
u
n
d
C
h
e
c
k
w
h
e
t
h
e
r
t
h
e
s
p
i
n
d
l
e
,
t
a
p
e
r
o
r
o
v
a
l
2
.
8
£
h
/
w
£
4
.
1
C
h
e
c
k
w
h
e
t
h
e
r
t
a
p
e
r
o
r
o
v
a
l
w
£
2
.
8
t
o
s
=
t
a
p
e
r
t
o
s
=
o
v
a
l
t
o
s
=
s
p
i
n
d
l
e
I
I
c
I
I
c
Y
N
Y
N
Y
N
N
Y
w
:
o
b
j
e
c
t
w
i
d
t
h
h
:
O
b
j
e
c
t
h
e
i
g
h
t
o
s
:
T
y
p
e
o
f
o
b
j
e
c
t
s
h
a
p
e
B
i
n
a
r
y
I
m
a
g
e
Fig
u
r
e
4
.
Flo
w
c
h
ar
t t
y
p
e
o
f
o
b
j
ec
t sh
ap
e
N
O
O
s
p
i
n
d
l
e
>
0
N
O
O
o
v
a
l
N
O
O
r
o
u
n
d
N
O
O
o
v
a
l
N
O
O
t
a
p
e
r
C
h
e
c
k
,
w
h
e
t
h
e
r
,
r
o
u
n
d
,
t
a
p
e
r
,
o
v
a
l
o
r
s
p
o
t
,
k
s
=
o
v
a
l
C
h
e
c
k
,
w
h
e
t
h
e
r
r
o
u
n
d
,
t
a
p
e
r
o
r
s
p
o
t
N
O
O
r
o
u
n
d
N
O
O
t
a
p
e
r
k
s
=
R
o
u
n
d
k
s
=
t
a
p
e
r
N
O
O
o
v
a
l
=
0
N
O
O
r
o
u
n
d
=
0
N
O
O
t
a
p
e
r
=
0
k
s
=
s
p
o
t
Y
N
Y
N
Y
N
N
Y
N
O
O
s
p
i
n
d
l
e
=
N
u
m
b
e
r
o
f
o
b
j
e
c
t
s
p
i
n
d
l
e
N
O
O
o
v
a
l
=
N
u
m
b
e
r
o
f
o
b
j
e
c
t
o
v
a
l
N
O
O
r
o
u
n
d
=
N
u
m
b
e
r
o
f
o
b
j
e
c
t
r
o
u
n
d
N
O
O
t
e
p
e
r
=
N
u
m
b
e
r
o
f
o
b
j
e
c
t
t
a
p
e
r
N
O
O
s
p
o
t
=
N
u
m
b
e
r
o
f
o
b
p
o
t
k
s
=
K
i
n
d
o
f
s
h
a
p
e
C
h
e
c
k
,
w
h
e
t
h
e
r
t
a
p
e
r
o
r
s
p
o
t
B
i
n
a
r
y
i
m
a
g
e
K
s
=
S
p
i
n
d
l
e
Ç
Ç
Ç
³
³
³
Fig
u
r
e
5
.
Flo
w
c
h
ar
t o
f
th
e
t
y
p
e
o
f
lesi
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
2
0
1
8
-
2
0
2
6
2022
T
h
e
last
p
ar
t
o
f
t
h
is
p
r
o
ce
s
s
i
s
ca
lcu
lati
n
g
t
h
e
ar
ea
o
f
t
h
e
o
b
j
ec
t.
T
h
e
ar
ea
o
f
th
e
o
b
j
ec
t
is
ca
lcu
lated
b
ased
o
n
th
e
b
in
ar
y
i
m
ag
e
as
s
h
o
w
n
i
n
Fi
g
u
r
e
6
(
b
)
.
f
o
r
ex
a
m
p
le
I
(
x
,
y
)
=
0
r
ep
r
esen
ts
t
h
e
p
ix
e
l
o
b
j
ec
t
an
d
I
(
x,
y
)
=
1
r
ep
r
esen
ts
t
h
e
p
ix
e
l b
ac
k
g
r
o
u
n
d
.
th
e
n
to
ca
lcu
lat
e
th
e
ar
ea
o
f
an
o
b
j
ec
t is:
=
∑
∑
(
,
)
,
=
1
,
(
1)
w
h
er
e
n
is
n
u
m
b
er
o
f
t
h
e
o
b
j
e
ct.
B
y
ca
lc
u
lat
in
g
t
h
e
p
er
ce
n
ta
g
e
o
f
le
s
io
n
p
ad
d
y
lea
f
,
w
e
g
e
t
th
e
ar
ea
as
s
h
o
w
n
in
(
2
)
an
d
(
3
)
,
=
ℎ
ℎ
ℎ
,
(
2)
w
h
er
e
ima
g
e
is
ar
ea
o
f
th
e
i
m
a
g
e
w
it
h
w
id
th
=
1
0
5
an
d
h
eig
h
t
=
3
0
5
,
an
d
=
(
)
100%
,
(
3)
T
o
g
et
th
e
h
ei
g
h
t
a
n
d
w
id
th
o
f
ea
ch
o
b
j
ec
t
s
h
ap
e,
m
ea
s
u
r
e
m
en
ts
w
e
r
e
tak
e
n
o
f
5
0
i
m
a
g
es
o
f
v
ar
io
u
s
t
y
p
es o
f
t
h
e
lesi
o
n
s
o
th
at
t
h
e
r
u
les
w
er
e
o
b
tain
ed
as
f
o
llo
w
s
;
Sp
o
t
:
w
id
t
h
<=
3
4
∩
h
eig
h
t<=
3
4
R
o
u
n
d
:
(
(
h
eig
h
t:
w
id
t
h
)
<=
2
.
8
)
∩
(
w
id
th
<=
4
6
)
Ov
al
:
(
(
h
ei
g
h
t:
w
id
t
h
)
<=
4
.
1
)
∩
(
w
id
t
h
<=
4
6
)
T
ap
e
r
:
(
(
h
eig
h
t:
w
id
t
h
)
>4
.
1
)
a
n
d
(
w
id
t
h
<
=1
5
.5
)
Sp
in
d
le
:
(
(
w
id
t
h
:
h
eig
h
t >
4
.
2
)
∩
(
w
id
th
>
1
5
.5
)
)
o
r
(
(
w
id
t
h
:
h
eig
h
t<=
4
.
1
)
∩
(
w
id
t
h
>
4
6
))
(
a)
(
b)
Fig
u
r
e
6
.
(
a)
8
-
C
o
n
n
ec
ted
n
e
i
g
h
b
o
u
r
h
o
o
d
p
ix
els
,
(
b)
b
in
ar
y
i
m
a
g
e
2
.
4
.
Co
l
o
r
s
eg
m
ent
a
t
io
n
C
o
lo
r
tex
tu
r
e
is
a
s
p
atio
-
c
h
r
o
m
atic
p
atter
n
,
w
h
ich
ca
n
b
e
d
ef
i
n
ed
as
a
"
s
u
r
f
ac
e
co
lo
r
d
is
tr
ib
u
tio
n
"
,
as
o
p
p
o
s
ed
to
a
g
r
a
y
-
s
ca
le
te
x
tu
r
e
t
h
at
f
o
cu
s
es
o
n
l
y
o
n
t
h
e
b
r
ig
h
tn
e
s
s
o
f
th
e
i
m
ag
e
[
1
8
]
.
C
o
lo
r
an
d
tex
tu
r
e
an
al
y
ze
s
h
a
v
e
b
ee
n
e
x
te
n
s
i
v
e
l
y
s
t
u
d
ied
[
1
9
]
.
I
t
i
s
u
s
ed
to
class
i
f
y
i
m
a
g
e
s
b
u
t
t
h
e
r
es
u
lt
s
ar
e
n
o
t
th
e
b
est.
So
m
e
r
esear
c
h
er
s
ar
e
p
r
o
p
o
s
in
g
to
co
m
b
i
n
e
co
lo
r
a
n
d
te
x
tu
r
e
an
al
y
s
is
to
i
m
p
r
o
v
e
cl
ass
i
f
icatio
n
r
es
u
lts
.
I
n
a
s
t
u
d
y
co
n
d
u
cted
[
2
0
-
22]
,
tex
t
u
r
e
ch
ar
ac
ter
izatio
n
w
as
f
i
r
s
t
ca
lcu
la
ted
o
n
a
g
r
a
y
s
ca
le
an
d
th
e
n
co
m
b
i
n
ed
w
it
h
co
lo
r
h
is
to
g
r
a
m
s
a
n
d
m
o
m
e
n
t
s
v
al
u
es.
W
h
ile
[
2
3
]
class
if
ied
i
m
ag
e
s
in
to
d
if
f
er
en
t
co
lo
r
s
p
ac
es
in
d
ep
en
d
en
tl
y
o
r
in
d
ep
en
d
en
tl
y
u
s
in
g
e
n
er
g
y
p
ar
a
m
eter
s
to
s
elec
t th
e
s
p
ac
e
th
a
t b
est r
ated
th
e
class
if
icati
o
n
.
T
h
e
u
s
e
o
f
R
GB
co
lo
r
s
p
ac
e
to
r
ep
r
esen
t
i
m
ag
e
d
ata
is
v
er
y
co
m
m
o
n
i
n
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
s
tu
d
ie
s
,
esp
ec
iall
y
s
i
n
ce
i
m
ag
e
s
g
e
n
e
r
ated
f
r
o
m
ca
m
er
as
ar
e
in
th
e
f
o
r
m
o
f
R
GB
i
m
a
g
es.
B
u
t
R
GB
co
lo
r
s
p
ac
e
is
n
o
t
a
u
n
if
o
r
m
s
p
ac
e
o
f
p
er
c
ep
tio
n
th
a
t
ca
n
d
is
t
in
g
u
is
h
b
et
w
ee
n
co
lo
r
s
(
f
o
r
ex
a
m
p
le,
E
u
clid
ea
n
d
is
ta
n
ce
)
i
n
th
r
ee
-
d
i
m
e
n
s
io
n
alit
y
.
R
GB
co
lo
r
s
p
ac
e
is
n
o
t
s
u
itab
le
f
o
r
co
lo
r
d
if
f
er
en
ce
s
as
p
er
h
u
m
a
n
p
er
ce
p
tio
n
[
2
1
,
2
4
]
.
Fo
r
th
is
r
ea
s
o
n
,
t
h
e
in
ter
n
atio
n
al
co
m
m
is
s
io
n
o
n
co
lo
r
i
m
et
r
y
(
C
o
m
m
is
s
io
n
i
n
ter
n
a
tio
n
al
e
d
e
o
n
ly
éc
la
ir
ag
e
-
C
I
E
)
d
ef
i
n
es
t
w
o
u
n
i
f
o
r
m
co
l
o
r
s
p
ac
es
o
f
p
er
ce
p
tio
n
,
n
a
m
el
y
L
*
a
*
b
*
a
n
d
L
*
u
*
v
*
[
2
3
]
.
Un
if
o
r
m
co
lo
r
s
p
ac
e
p
er
ce
p
tio
n
s
h
a
v
e
b
ee
n
w
id
el
y
u
s
ed
i
n
i
m
ag
e
p
r
o
ce
s
s
i
n
g
s
t
u
d
ies
[
7
]
.
Ho
w
e
v
er
,
n
o
s
t
u
d
ies
h
av
e
a
llo
w
ed
s
u
c
h
u
s
e
o
f
co
lo
r
s
p
ac
e
i
n
t
er
m
s
o
f
its
ef
f
ec
ti
v
e
n
es
s
co
m
p
ar
ed
to
R
GB
co
lo
r
s
p
ac
e
[
2
5
]
.
C
o
lo
r
tex
t
u
r
e
an
al
y
s
is
i
n
t
h
is
s
t
u
d
y
w
a
s
u
s
ed
to
o
b
tain
th
e
s
y
m
p
to
m
s
o
f
lesi
o
n
b
o
u
n
d
ar
y
co
lo
r
,
lesi
o
n
s
p
o
ts
co
lo
r
an
d
th
e
le
s
io
n
leaf
co
lo
r
as
s
h
o
wn
i
n
F
ig
u
r
e
7
.
T
h
e
co
lo
r
o
f
t
h
e
le
s
io
n
b
o
u
n
d
ar
y
is
t
h
e
co
l
o
r
o
f
th
e
ed
g
e
o
r
th
e
b
o
u
n
d
ar
y
o
f
t
h
e
les
io
n
s
p
o
t
as
s
h
o
w
n
i
n
Fi
g
u
r
e
7
(
a)
an
d
t
h
e
co
lo
r
o
f
t
h
e
le
s
io
n
s
p
o
t
is
t
h
e
co
lo
r
o
f
th
e
ce
n
ter
o
f
t
h
e
les
io
n
s
p
o
t
as
s
h
o
w
n
in
Fig
u
r
e
7
(
b
)
.
W
h
ile
th
e
co
lo
r
o
f
lesi
o
n
leaf
i
s
th
e
co
lo
r
o
f
d
is
ea
s
ed
p
ad
d
y
leaf
e
a
s
s
h
o
w
n
i
n
Fi
g
u
r
e
7
(
c)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f
p
a
d
d
y
lea
f
d
is
ea
s
es b
a
s
ed
o
n
textu
r
e
a
n
a
lysi
s
o
f
…
(
A
lex
W
en
d
a
)
2023
(
a)
(
b)
(
c)
Fig
u
r
e
7
.
(
a)
L
esio
n
b
o
u
n
d
ar
y
co
lo
r
,
(
b
)
L
esio
n
s
p
o
t c
o
lo
r
,
(
c
)
L
esio
n
lea
f
co
lo
r
B
o
u
n
d
ar
y
co
lo
r
o
f
th
e
o
b
j
ec
t
is
o
b
tain
ed
b
y
s
p
ec
if
y
i
n
g
8
co
o
r
d
in
ates
at
d
if
f
er
en
t
lo
ca
tio
n
s
o
f
th
e
b
o
u
n
d
ar
y
o
b
j
ec
t,
i.e
.
lef
t
-
to
p
,
to
p
-
le
f
t,
to
p
-
r
i
g
h
t,
r
i
g
h
t
-
to
p
,
r
ig
h
t
-
b
o
tto
m
,
b
o
tto
m
-
r
ig
h
t,
b
o
tto
m
-
le
f
t
,
b
o
tto
m
-
le
f
t,
an
d
to
p
-
le
f
t
a
s
s
h
o
w
n
in
Fi
g
u
r
e
8
(
a)
.
A
cc
o
r
d
in
g
to
e
x
p
er
ts
,
f
o
r
s
p
i
n
d
le
s
h
a
p
es,
o
v
al
an
d
r
o
u
n
d
s
h
ap
es,
t
h
e
b
o
u
n
d
ar
y
co
lo
r
o
f
th
e
lesi
o
n
lea
f
s
h
o
u
ld
b
e
d
eter
m
in
ed
,
w
h
er
ea
s
f
o
r
t
h
e
tap
er
ed
s
h
ap
e
an
d
th
e
s
p
o
t
b
o
n
d
ar
y
co
lo
r
th
e
s
h
a
p
e
is
n
o
t
r
eq
u
ir
ed
.
T
h
e
co
lo
r
o
f
lesi
o
n
s
p
o
ts
is
o
b
tai
n
ed
b
y
d
ef
in
i
n
g
t
h
e
ce
n
ter
co
o
r
d
in
ates o
f
th
e
o
b
j
ec
t
as s
h
o
w
n
i
n
Fig
u
r
e
8
(
b
)
.
W
h
ile
t
h
e
co
lo
r
o
f
t
h
e
le
s
io
n
lea
f
i
s
o
b
ta
in
ed
b
y
s
p
ec
i
f
y
in
g
th
e
co
o
r
d
in
ates o
f
ea
c
h
p
ix
el
o
n
th
e
lea
f
i
m
a
g
e
ex
ce
p
t f
o
r
p
ix
els o
n
th
e
o
b
j
ec
t
as sh
o
w
n
in
Fig
u
r
e
8
(
c)
.
(
a)
(
b)
(
c)
Fig
u
r
e
8
.
(
a)
B
o
u
n
d
ar
y
co
o
r
d
in
ate
,
(
b
)
S
p
o
t c
o
o
r
d
in
ate
,
(
c)
L
ea
f
co
o
r
d
in
ate
T
h
is
s
tu
d
y
u
s
es
C
I
E
co
lo
r
s
p
ac
e
L
*
a
*
b
*
an
d
E
u
clid
ea
n
d
is
ta
n
ce
ca
lcu
la
tio
n
s
to
o
b
tain
s
i
m
ila
r
co
lo
r
s
.
T
h
e
f
o
llo
w
i
n
g
is
a
n
al
g
o
r
ith
m
(
al
g
o
r
ith
m
2
.
1
)
f
o
r
co
n
v
er
ti
n
g
R
GB
co
lo
r
s
p
ac
e
in
to
C
I
E
L
*
a
*
b
*
co
lo
r
s
p
ac
e
w
h
ile
t
h
e
f
o
r
m
u
la
f
o
r
ca
lcu
lati
n
g
E
u
clid
ea
n
d
is
ta
n
ce
is
s
h
o
w
n
in
(
4
),
∆
∗
=
[
(
∆
∗
)
2
+
(
∆
∗
)
2
+
(
∆
∗
)
2
]
1
2
,
(
4)
w
h
er
e
∆
∗
is
th
e
d
if
f
er
en
ce
in
b
r
ig
h
tn
ess
b
etw
ee
n
tw
o
c
o
l
o
r
s
,
∆
∗
an
d
∆
∗
is
th
e
ch
r
o
m
atic
d
if
f
er
en
ce
b
etw
ee
n
th
e
tw
o
c
o
l
o
r
s
.
Algorit
h
m 2
.1
.
Color model algorithm
CIE L*a*b*
Input:
color space RGB
(
,
,
)
Output:
color space
CIE L*a*b*
1:
Convert
the
RGB
value
(
,
,
)
into
CIE XYZ
color model
(
5
).
[
]
=
[
.
4124
.
3576
.
1805
.
2126
.
7152
.
0722
.
0193
.
1192
.
9505
]
[
]
(
5
)
2:
Convert
XYZ
value into
CIE L*a*b*
color model
by
calculate
L*, a*
dan
b*
(
6.a
)
and
(
6.6b
).
The value of
L*
(
luminance
)
is derived from
(
6.
a
)
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
2
0
1
8
-
2
0
2
6
2024
∗
=
{
116
(
)
1
1
3
,
>
0
.
008856
903
.
3
(
)
,
≤
0
.
008856
(
6.
a)
The chroma coordinate
a*
dan
b*
are obtained from
(
6.
b
)
:
∗
=
500
[
(
)
−
(
)
]
,
∗
=
200
[
(
)
−
(
)
]
,
(
6.
b)
where
(
)
=
√
3
,
>
0
.
008856
,
(
)
=
7
.
87
+
16
116
,
≤
0
.
008856
α
represents
X, Y dan Z
by using the white point
D
65
(
X
n
, Y
n
,
Z
n
)=
(
95.0155, 100, 108.8259)
T
h
e
co
lo
r
d
if
f
er
en
ce
*
ab
E
b
et
w
ee
n
t
w
o
co
lo
r
s
,
in
ter
m
s
o
f
*
*
*
,
,
b
a
L
is
g
i
v
en
b
y
t
h
e
E
u
clid
ea
n
m
etr
ic
in
(
4
)
.
T
h
e
s
m
alles
t d
is
tan
ce
(
*
ab
E
)
r
ep
r
es
en
ts
t
h
e
p
ix
el
m
o
s
t c
lo
s
e
l
y
m
a
tch
to
th
e
co
lo
r
m
ar
k
er
.
E
x
p
e
r
ts
h
av
e
v
is
u
a
l
ly
d
e
t
e
r
m
in
e
d
t
h
e
c
o
l
o
r
s
in
v
o
lv
e
d
in
d
e
t
e
r
m
in
in
g
l
es
i
o
n
b
o
u
n
d
a
r
y
c
o
l
o
r
,
l
e
s
i
o
n
s
p
o
t
c
o
l
o
r
a
n
d
l
es
i
o
n
l
ea
f
c
o
l
o
r
as
s
h
o
w
n
in
F
ig
u
r
e
9
.
T
h
es
e
c
o
lo
r
s
w
e
r
e
o
b
t
a
in
e
d
f
r
o
m
p
r
ev
io
u
s
r
e
s
ea
r
ch
e
r
[
1
3
]
.
T
h
e
r
e
a
r
e
t
h
r
ee
c
a
t
eg
o
r
i
es
f
o
r
t
h
e
le
s
i
o
n
b
o
u
n
d
a
r
y
c
o
l
o
r
,
n
am
e
ly
b
r
o
w
n
,
o
r
an
g
e
an
d
y
e
l
l
o
w
as
s
h
o
w
n
in
F
ig
u
r
e
9
.
I
n
t
h
e
l
e
s
i
o
n
s
p
o
t
c
o
lo
r
,
t
h
e
r
e
a
r
e
tw
o
c
o
l
o
r
c
a
t
eg
o
r
ie
s
,
n
am
ely
g
r
ay
an
d
b
r
o
w
n
as
s
h
o
w
n
in
F
ig
u
r
e
10
.
W
h
i
l
e
th
e
l
es
i
o
n
l
e
af
c
o
l
o
r
,
th
er
e
a
r
e
f
o
u
r
c
o
l
o
r
c
a
t
eg
o
r
i
es
,
n
am
e
ly
b
r
o
w
n
,
o
r
a
n
g
e
,
y
e
l
l
o
w
an
d
g
r
e
e
n
as
s
h
o
w
n
in
F
ig
u
r
e
11
.
(
a)
(
a)
(
b)
(
b)
(
c)
Fig
u
r
e
9
.
L
esio
n
b
o
u
n
d
ar
y
co
l
o
r
;
(
a)
b
r
o
w
n
;
(
b
)
o
r
a
n
ge
;
(
c)
y
ell
o
w
Fig
u
r
e
10
.
L
esio
n
s
p
o
t c
o
lo
r
;
(
a)
g
r
ay
;
(
b
)
b
r
o
w
n
(
a)
(
c)
(
b)
(
d)
Fig
u
r
e
11
.
lesi
o
n
leaf
co
lo
r
(
a)
b
r
o
w
n
;
(
b
)
o
r
an
g
e
;
(
c)
y
ello
w
;
(
d
)
g
r
ee
n
2
.
5
.
Cla
s
s
if
ica
t
io
n
T
h
e
f
in
al
p
ar
t
o
f
th
e
id
e
n
ti
f
ica
tio
n
o
f
p
ad
d
y
lea
f
d
is
ea
s
e
is
cl
ass
i
f
icatio
n
.
I
t
is
an
i
m
p
o
r
tan
t
s
tep
af
ter
th
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
as
well
as
te
x
tu
r
e
an
al
y
s
is
.
A
r
u
le
-
b
ased
s
y
s
te
m
b
ec
o
m
e
s
v
er
y
u
s
ef
u
l
f
o
r
clas
s
i
f
y
i
n
g
i
m
a
g
es
if
t
h
e
n
u
m
b
er
o
f
cla
s
s
es
i
s
f
i
x
ed
a
n
d
k
n
o
w
n
.
B
as
ed
o
n
i
n
ter
v
ie
w
s
w
it
h
e
x
p
er
ts
,
r
u
le
s
h
av
e
b
ee
n
d
ev
elo
p
ed
b
ased
o
n
ch
ar
ac
ter
is
tics
s
u
c
h
as a
r
ea
,
n
u
m
b
er
o
f
o
b
j
ec
ts
,
co
lo
r
,
s
h
ap
e,
an
d
p
er
im
eter
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
I
d
en
tifi
ca
tio
n
o
f
p
a
d
d
y
lea
f
d
is
ea
s
es b
a
s
ed
o
n
textu
r
e
a
n
a
lysi
s
o
f
…
(
A
lex
W
en
d
a
)
2025
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
o
g
et
th
e
b
est
r
es
u
lt
s
,
f
o
u
r
m
et
h
o
d
s
h
a
v
e
b
ee
n
ch
o
s
en
to
d
eter
m
in
e
t
h
e
t
h
r
es
h
o
ld
v
alu
e,
Ot
s
u
th
r
es
h
o
ld
v
al
u
e,
v
ar
iab
le
t
h
r
es
h
o
ld
v
al
u
e,
lo
ca
l
th
r
es
h
o
ld
v
al
u
e
a
n
d
g
lo
b
al
th
r
es
h
o
ld
v
alu
e.
T
h
e
Ots
u
m
et
h
o
d
to
o
b
tain
th
r
es
h
o
ld
v
a
lu
e
s
a
u
to
m
at
icall
y
b
y
s
ep
ar
atin
g
u
n
iv
ar
ia
te
d
ata
in
to
t
w
o
g
r
o
u
p
s
b
y
co
n
s
id
er
in
g
v
ar
ian
ce
b
et
w
ee
n
cla
s
s
e
s
.
T
h
e
s
ec
o
n
d
m
eth
o
d
ap
p
lies
g
lo
b
al
th
r
es
h
o
ld
v
al
u
es
f
o
r
all
i
m
ag
e
s
.
T
h
r
esh
o
ld
v
alu
e
s
ar
e
s
et
a
t
9
5
f
o
r
all
i
m
a
g
es,
th
i
s
i
s
t
h
e
a
v
er
a
g
e
v
alu
e
o
f
t
h
e
v
ar
iab
le
t
h
r
es
h
o
ld
v
al
u
e.
T
h
e
th
ir
d
m
et
h
o
d
u
s
e
s
t
h
e
v
ar
iab
le
t
h
r
es
h
o
ld
v
alu
e.
T
h
is
is
ch
o
s
e
n
m
a
n
u
all
y
to
g
et
th
e
b
est
r
esu
lts
.
An
d
th
e
last
m
eth
o
d
i
s
th
e
lo
ca
l
th
r
es
h
o
ld
v
al
u
e
b
y
m
ak
in
g
f
ix
ed
-
s
ized
b
lo
ck
s
i
n
th
e
i
m
a
g
e
an
d
th
e
n
ea
ch
b
l
o
ck
is
lo
o
k
in
g
f
o
r
th
e
th
r
e
s
h
o
ld
v
al
u
e.
Sev
e
n
t
y
-
f
i
v
e
s
a
m
p
le
s
co
n
s
i
s
ti
n
g
o
f
2
6
i
m
a
g
es
o
f
b
last
,
1
8
im
ag
e
s
o
f
b
r
o
w
n
s
p
o
t
an
d
3
1
i
m
ag
e
s
o
f
n
ar
r
o
w
b
r
o
w
n
s
p
o
t
w
er
e
tes
te
d
u
s
i
n
g
f
o
u
r
t
h
r
es
h
o
ld
m
et
h
o
d
s
an
d
co
m
p
ar
ed
w
it
h
ex
p
er
ts
.
So
th
at
t
h
e
ac
c
u
r
ac
y
o
f
th
e
f
o
u
r
m
et
h
o
d
s
is
4
9
.
3
%
,
5
6
%,
6
0
%
an
d
9
0
.
7
%
f
o
r
th
e
Ots
u
m
e
th
o
d
,
g
lo
b
al
t
h
r
esh
o
ld
,
lo
ca
l
th
r
esh
o
ld
an
d
v
ar
iab
le
th
r
e
s
h
o
ld
r
esp
ec
t
iv
el
y
as
s
h
o
w
n
i
n
T
ab
le
1.
B
ec
au
s
e
th
e
i
n
ten
s
it
y
v
al
u
es
ar
e
d
if
f
er
en
t
f
o
r
ea
c
h
i
m
a
g
e,
g
lo
b
al
t
h
r
es
h
o
ld
v
al
u
e
s
,
lo
ca
l
th
r
e
s
h
o
ld
v
alu
e
s
a
n
d
au
to
m
at
ic
t
h
r
esh
o
ld
v
al
u
es
u
s
i
n
g
th
e
Ots
u
m
et
h
o
d
ca
n
n
o
t
p
er
f
o
r
m
s
e
g
m
en
ta
tio
n
task
s
ac
c
u
r
atel
y
.
T
h
is
is
ca
u
s
ed
b
y
d
if
f
er
en
ce
s
i
n
ti
m
e
an
d
d
is
tan
ce
w
h
e
n
s
h
o
o
tin
g
.
S
h
o
o
tin
g
d
ep
en
d
s
o
n
th
e
li
g
h
t
s
o
u
r
ce
.
T
h
is
p
a
p
er
u
s
es
s
u
n
li
g
h
t
a
s
a
li
g
h
t
s
o
u
r
ce
.
T
h
at
m
a
k
es
th
e
s
o
u
r
ce
o
f
il
lu
m
i
n
atio
n
ca
n
n
o
t
b
e
co
n
tr
o
lled
s
o
th
at
it
is
p
er
f
ec
tl
y
ce
n
ter
ed
to
th
e
s
u
r
f
ac
e
o
f
t
h
e
i
m
ag
e
b
ein
g
s
ee
n
a
n
d
it a
f
f
ec
ts
t
h
e
i
n
ten
s
i
t
y
v
al
u
e
o
f
th
e
i
m
a
g
e.
T
h
e
er
r
o
r
r
ate
f
o
r
ea
ch
d
if
f
er
en
t
t
h
r
es
h
o
ld
v
al
u
e
m
et
h
o
d
is
s
h
o
w
n
i
n
T
ab
le
2
.
I
n
co
r
r
ec
t
a
m
o
u
n
ts
i
n
T
ab
le
1
h
av
e
b
ee
n
an
al
y
ze
d
t
o
g
et
th
e
er
r
o
r
r
ate.
E
r
r
o
r
s
ca
n
o
cc
u
r
in
th
e
p
r
o
ce
s
s
o
f
s
e
g
m
en
tatio
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
,
o
r
class
i
f
icatio
n
.
Dete
r
m
i
n
atio
n
o
f
th
e
t
h
r
es
h
o
ld
v
alu
e
is
a
n
i
m
p
o
r
tan
t
s
tep
i
n
th
e
s
eg
m
e
n
tatio
n
p
r
o
ce
s
s
.
I
n
ac
cu
r
ate
d
eter
m
in
a
tio
n
o
f
th
r
es
h
o
ld
v
a
lu
e
s
ca
n
r
esu
lt
in
in
ac
c
u
r
ate
s
eg
m
e
n
tati
o
n
r
esu
lts
a
n
d
lead
s
to
in
co
r
r
ec
t c
lass
i
f
icatio
n
.
T
ab
le
1
.
A
cc
u
r
ac
y
r
ates
f
o
r
th
r
esh
o
ld
v
al
u
e
T
h
r
e
sh
o
l
d
t
y
p
e
C
o
r
r
e
c
t
I
n
c
o
r
r
e
c
t
A
c
c
u
r
a
c
y
r
a
t
e
(
%
C
o
r
r
e
c
t
)
V
a
r
i
a
b
l
e
6
8
7
90
.
7
%
G
l
o
b
a
l
4
2
3
3
5
6
%
L
o
c
a
l
46
29
6
0
%
O
t
su
37
38
4
9
.
3
%
T
ab
le
2
.
E
r
r
o
r
r
ates f
o
r
th
r
esh
o
ld
m
et
h
o
d
Er
r
o
r
V
a
r
i
a
b
l
e
G
l
o
b
a
l
L
o
c
a
l
O
t
su
S
e
g
me
n
t
a
t
i
o
n
-
-
-
4
4
.
4
%
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
9
.
3
%
6
1
.
5
%
6
2
.
8
%
3
3
.
4
%
C
l
a
ssi
f
i
c
a
t
i
o
n
90
.
7
%
3
8
.
5
%
3
7
.
2
%
2
2
.
2
%
4.
CO
NCLU
SI
O
N
T
h
e
im
a
g
e
p
r
o
ce
s
s
i
n
g
tec
h
n
i
q
u
es
w
er
e
u
s
ed
to
estab
lis
h
t
h
e
id
en
ti
f
icat
io
n
o
f
p
ad
d
y
le
af
d
is
ea
s
e
s
b
ased
o
n
tex
t
u
r
e
an
al
y
s
i
s
o
f
b
lo
b
s
an
d
co
lo
r
s
eg
m
e
n
tatio
n
.
Fiv
e
c
h
ar
ac
ter
is
tic
s
;
lesi
o
n
p
er
ce
n
tag
e,
lesi
o
n
t
y
p
e,
b
o
u
n
d
ar
y
le
s
io
n
co
lo
r
,
s
p
o
t
lesi
o
n
co
lo
r
,
an
d
lesi
o
n
p
ad
d
y
lea
f
co
lo
r
w
er
e
tes
ted
f
o
r
th
e
class
i
f
icat
io
n
task
.
T
h
e
r
atio
o
f
h
eig
h
t
a
n
d
w
id
t
h
o
f
t
h
e
lesi
o
n
o
b
j
ec
t
p
r
o
v
id
ed
a
u
n
iq
u
e
s
h
ap
e
c
h
ar
ac
ter
is
tic
f
o
r
d
eter
m
i
n
e
t
y
p
e
o
f
th
e
lesi
o
n
.
Fo
u
r
t
h
r
esh
o
ld
in
g
m
et
h
o
d
s
h
av
e
b
ee
n
ap
p
lied
to
g
et
th
e
b
est
r
e
s
u
lt
s
i
n
id
e
n
ti
f
y
in
g
s
ev
e
n
t
y
-
f
i
v
e
i
m
a
g
e
s
o
f
d
is
ea
s
ed
p
ad
d
y
leaf
.
T
h
e
b
est
ac
cu
r
ac
y
o
f
th
e
f
o
u
r
m
et
h
o
d
s
u
s
i
n
g
th
r
esh
o
ld
v
ar
iab
les
is
ar
o
u
n
d
9
0
.
7
%.
T
h
at'
s
b
ec
a
u
s
e
t
h
e
i
n
ten
s
it
y
v
al
u
es
ar
e
d
i
f
f
er
en
t
f
o
r
ea
ch
i
m
a
g
e,
s
o
t
h
e
g
l
o
b
al
th
r
esh
o
ld
a
n
d
au
to
m
at
ic
th
r
es
h
o
ld
v
al
u
es
u
s
i
n
g
t
h
e
Ot
s
u
m
et
h
o
d
ca
n
n
o
t se
g
m
e
n
t ta
s
k
s
ac
cu
r
atel
y
.
RE
F
E
R
E
NC
E
S
[1
]
S
.
S
a
v
a
r
y
,
A
.
Ne
lso
n
,
L
.
W
il
lo
c
q
u
e
t,
I.
P
a
n
g
g
a
,
a
n
d
J.
A
u
n
a
rio
,
“
M
o
d
e
li
n
g
a
n
d
m
a
p
p
in
g
p
o
ten
ti
a
l
e
p
id
e
m
ics
o
f
ric
e
d
ise
a
se
s g
lo
b
a
ll
y
,
”
Cro
p
Pro
t.
,
v
o
l.
3
4
,
p
p
.
6
-
1
7
,
2
0
1
2
.
[2
]
S
c
a
rd
a
c
i,
“
Rice
Blas
t:
A
Ne
w
Dise
a
se
in
Ca
li
f
o
rn
ia,”
Ag
r
o
n
o
my
Fa
c
t
S
h
e
a
t
S
e
rie
s.
De
p
a
rtme
n
t
o
f
Ag
ro
m
o
my
a
n
d
Ra
n
g
e
S
c
ien
c
e
,
1
9
9
7
.
[3
]
Z.
L
iu
,
J.
Hu
a
n
g
,
J.
S
h
i
,
R.
T
a
o
,
W
.
Zh
o
u
,
a
n
d
L
.
Zh
a
n
g
,
“
Ch
a
ra
c
teriz
in
g
a
n
d
e
stim
a
ti
n
g
rice
b
ro
w
n
sp
o
t
d
ise
a
se
se
v
e
rit
y
u
sin
g
ste
p
w
ise
re
g
r
e
ss
io
n
,
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
re
g
re
ss
io
n
a
n
d
p
a
rti
a
l
lea
st
-
sq
u
a
re
re
g
re
ss
i
o
n
,
”
J
.
Z
h
e
ji
a
n
g
Un
iv.
S
c
i.
B
,
v
o
l
.
8
,
n
o
.
1
0
,
p
p
.
7
3
8
-
7
4
4
,
2
0
0
7
.
[
4
]
T
.
K
o
b
a
y
a
s
h
i
,
E
.
K
a
n
d
a
,
K
.
K
i
t
a
d
a
,
K
.
I
s
h
i
g
u
r
o
,
a
n
d
Y
.
T
o
r
i
g
o
e
,
“
D
e
t
e
c
t
i
o
n
o
f
r
i
c
e
p
a
n
i
c
l
e
b
l
a
s
t
w
i
t
h
m
u
l
t
i
s
p
e
c
t
r
a
l
r
a
d
i
o
m
e
t
e
r
a
n
d
t
h
e
p
o
t
e
n
t
i
a
l
o
f
u
s
i
n
g
a
i
r
b
o
r
n
e
m
u
l
t
i
s
p
e
c
t
r
a
l
s
c
a
n
n
e
r
s
,
”
Ph
y
t
o
p
a
t
h
o
l
o
g
y
,
v
o
l
.
9
1
,
n
o
.
3
,
p
p
.
3
1
6
-
3
2
3
,
2
0
0
1
.
[5
]
S
.
S
a
v
a
r
y
e
t
a
l.
,
“
In
tern
a
ti
o
n
a
l
a
g
ricc
lt
u
ra
l
re
se
a
r
c
h
tac
k
li
n
g
th
e
e
ff
e
c
ts
o
f
g
lo
b
a
l
a
n
d
c
li
m
a
te
c
h
a
n
g
e
s
o
n
p
la
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
2
0
1
8
-
2
0
2
6
2026
d
ise
a
se
s in
th
e
d
e
v
e
lo
p
in
g
w
o
rld
,
”
Pl
a
n
t
Dis.
,
v
o
l
.
9
5
,
n
o
.
1
0
,
p
p
.
1
2
0
4
-
1
2
1
6
,
2
0
1
1
.
[6
]
S
.
S
a
v
a
r
y
,
A
.
M
il
a
,
L
.
W
il
lo
c
q
u
e
t,
P
.
D.
Esk
e
r,
O.
Ca
risse
,
a
n
d
N.
M
c
Ro
b
e
rts,
“
Risk
f
a
c
to
rs
f
o
r
c
r
o
p
h
e
a
lt
h
u
n
d
e
r
g
lo
b
a
l
c
h
a
n
g
e
a
n
d
a
g
ricu
lt
u
ra
l
sh
if
ts:
A
f
ra
m
e
w
o
r
k
o
f
a
n
a
l
y
se
s
u
sin
g
rice
in
tro
p
ica
l
a
n
d
su
b
tro
p
ica
l
a
sia
a
s
a
m
o
d
e
l,
”
Ph
y
to
p
a
th
o
l
o
g
y
,
v
o
l
.
1
0
1
,
n
o
.
6
,
p
p
.
6
9
6
-
7
0
9
,
2
0
1
1
.
[7
]
V
.
S
in
g
h
a
n
d
A
.
K.
M
isra
,
“
De
tec
ti
o
n
o
f
p
lan
t
lea
f
d
ise
a
se
s
u
sin
g
im
a
g
e
se
g
m
e
n
tatio
n
a
n
d
so
f
t
c
o
m
p
u
ti
n
g
tec
h
n
iq
u
e
s,”
In
f.
Pro
c
e
ss
.
Ag
ric
.
,
v
o
l.
4
,
n
o
.
1
,
p
p
.
4
1
-
4
9
,
2
0
1
7
.
[8
]
P
.
No
,
M
.
S
u
re
sh
a
,
K.
N.
S
h
re
e
k
a
n
th
,
a
n
d
B.
V
T
h
iru
m
a
l
e
sh
,
“
Re
se
a
rh
A
rti
c
le
Dia
g
n
o
sis
a
n
d
Clas
sif
ic
a
ti
o
n
o
f
Dise
a
se
s in
P
a
d
d
y
Lea
v
e
s
,
”
v
o
l.
6
,
n
o
.
1
0
,
p
p
.
6
4
4
8
–
6
4
5
2
,
2
0
1
7
.
[
9
]
S
.
A
r
i
v
a
z
h
a
g
a
n
,
R
.
N
.
S
h
e
b
i
a
h
,
S
.
A
n
a
n
t
h
i
,
a
n
d
S
.
V
i
s
h
n
u
V
a
r
t
h
i
n
i
,
“
D
e
t
e
c
t
i
o
n
o
f
u
n
h
e
a
l
t
h
y
r
e
g
i
o
n
o
f
p
l
a
n
t
l
e
a
v
e
s
a
n
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
p
l
a
n
t
l
e
a
f
d
i
s
e
a
s
e
s
u
s
i
n
g
t
e
x
t
u
r
e
f
e
a
t
u
r
e
s
,
”
A
g
r
i
c
.
E
n
g
.
I
n
t
.
C
I
G
R
J
.
,
v
o
l
.
1
5
,
n
o
.
1
,
p
p
.
2
1
1
-
2
1
7
,
2
0
1
3
.
[1
0
]
N.
P
.
Dh
a
y
g
u
d
e
,
S
B.
,
&
Ku
m
b
h
a
r,
“
A
g
ri
c
u
lt
u
ra
l
P
lan
t
L
e
a
f
Dis
e
a
se
D
e
tec
ti
o
n
Us
in
g
Im
a
g
e
P
ro
c
e
ss
in
g
,
”
In
t.
J
.
Ad
v
.
Res
.
El
e
c
tr.
El
e
c
tro
n
.
In
stru
m.
En
g
.
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
5
9
9
-
6
0
2
,
2
0
1
3
.
[1
1
]
Ro
ss
il
a
w
a
ti
S
.
e
t
a
l.
,
“
T
h
e
d
e
v
e
lo
p
m
e
n
t
o
f
d
ise
a
se
s
d
iag
n
o
si
n
g
s
y
ste
m
in
p
a
d
d
y
p
lan
t
(
E
-
P
a
d
d
y
),
”
Pro
s.
An
ta
r
a
b
a
n
g
sa
T
e
k
n
o
l.
M
k
lm.
,
p
p
.
4
2
4
-
4
3
2
,
2
0
0
3
.
[1
2
]
S
.
P
h
a
d
ik
a
r
a
n
d
J.
S
il
,
“
Rice
d
i
se
a
se
id
e
n
ti
f
ica
ti
o
n
u
si
n
g
p
a
tt
e
r
n
re
c
o
g
n
it
i
o
n
tec
h
n
i
q
u
e
s,”
Pr
o
c
.
1
1
th
I
n
t.
Co
n
f.
Co
mp
u
t
.
In
f.
T
e
c
h
n
o
l
.
ICCIT
2
0
0
8
,
p
p
.
4
2
0
-
4
2
3
,
2
0
0
8
.
[1
3
]
T
N
A
U
“
E
x
p
e
rt
s
y
ste
m
f
o
r
p
a
d
d
y
,
”
2
0
1
4
.
[
O
n
li
n
e
]
.
A
v
a
il
a
b
l
e
:
h
tt
p
:/
/w
ww
.
a
g
rit
e
c
h
.
tn
a
u
.
a
c
.
in
/ex
p
e
rt_
sy
ste
m
/
p
a
d
d
y
/In
d
e
x
.
h
tm
l
[1
4
]
S
.
P
h
a
d
ik
a
r,
“
Clas
sif
ica
ti
o
n
o
f
Rice
L
e
a
f
Dis
e
a
se
s
Ba
se
d
o
n
M
o
r
p
h
o
lo
g
ica
l
Ch
a
n
g
e
s,”
In
t
.
J
.
I
n
f.
El
e
c
tro
n
.
En
g
.
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
4
6
0
-
4
6
3
,
2
0
1
2
.
[1
5
]
N.
N.
Ku
rn
iaw
a
ti
,
S
.
N.
H.
S
.
A
b
d
u
ll
a
h
,
S
.
A
b
d
u
ll
a
h
,
a
n
d
S
.
A
b
d
u
ll
a
h
,
“
T
e
x
tu
re
a
n
a
l
y
sis
f
o
r
d
iag
n
o
sin
g
p
a
d
d
y
d
ise
a
se
,
”
Pro
c
.
2
0
0
9
In
t.
Co
n
f.
El
e
c
tr.
En
g
.
In
f
o
rm
a
ti
c
s,
ICE
EI
2
0
0
9
,
p
p
.
2
3
-
2
7
,
2
0
0
9
.
[1
6
]
N.
N.
Ku
r
n
iaw
a
ti
,
S
.
N
.
H.
S
.
A
b
d
u
ll
a
h
,
S
.
A
b
d
u
ll
a
h
,
a
n
d
S
.
A
b
d
u
ll
a
h
,
“
In
v
e
stig
a
ti
o
n
o
n
i
m
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s
f
o
r
d
iag
n
o
sin
g
p
a
d
d
y
d
ise
a
se
s,”
2
0
0
9
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
f
S
o
ft
Co
m
p
u
t
in
g
a
n
d
Pa
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
0
9
.
[1
7
]
A
.
W
e
n
d
a
,
N.
P
.
M
ief
th
a
w
a
ti
,
a
n
d
M
.
Zei
n
,
“
T
h
e
De
v
e
lo
p
m
e
n
t
o
f
Dise
a
se
s
Id
e
n
ti
f
ic
a
ti
o
n
S
y
ste
m
in
P
a
d
d
y
P
lan
t
Us
in
g
I
m
a
g
e
P
ro
c
e
ss
in
g
Tec
h
n
iq
u
e
,
”
Pro
c
e
e
d
in
g
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
,
v
o
l.
2
,
p
p
.
2
3
1
-
2
3
6
,
2
0
1
9
.
[1
8
]
M
.
S
z
p
rin
g
e
r,
“
P
o
u
ra
z
o
w
e
z
n
ie
k
sz
ta?
?
c
e
n
ie
p
rz
e
d
n
ich
z
e
b
?
?
w
st
a
?
?
y
c
h
i
z
w
iaz
a
n
e
z
t
y
m
tru
d
n
o
?
?
c
i
lec
z
n
icz
e
.
,
”
Cza
s.
S
t
o
ma
t
o
l.
,
v
o
l.
2
6
,
n
o
.
8
,
p
p
.
8
5
5
-
8
6
0
,
1
9
7
3
.
[1
9
]
H.
P
e
rm
u
ter,
J.
F
ra
n
c
o
s,
a
n
d
I
.
Je
rm
y
n
,
“
A
stu
d
y
o
f
G
a
u
ss
ian
m
i
x
t
u
re
m
o
d
e
ls
o
f
c
o
lo
r
a
n
d
tex
tu
re
f
e
a
tu
re
s
f
o
r
im
a
g
e
c
las
si
f
ica
ti
o
n
a
n
d
se
g
m
e
n
tatio
n
,
”
Pa
tt
e
rn
Rec
o
g
n
it
.
,
v
o
l.
3
9
,
n
o
.
4
,
p
p
.
6
9
5
-
7
0
6
,
2
0
0
6
.
[2
0
]
M
.
M
.
P
.
,
P
e
tro
u
,
a
n
d
C.
P
e
tro
u
,
"
Im
a
g
e
P
ro
c
e
ss
in
g
:
T
h
e
F
u
n
d
a
m
e
n
tals,
2
n
d
E
d
it
i
o
n
,
"
2
n
d
e
d
.
W
il
e
y
,
2
0
1
0
.
[2
1
]
G
.
P
a
sc
h
o
s,
“
P
e
rc
e
p
tu
a
ll
y
u
n
if
o
rm
c
o
lo
r
sp
a
c
e
s
f
o
r
c
o
lo
r
tex
tu
re
a
n
a
ly
sis:
A
n
e
m
p
iri
c
a
l
e
v
a
lu
a
ti
o
n
,
”
IEE
E
T
ra
n
s.
Ima
g
e
Pro
c
e
ss
.
,
v
o
l.
1
0
,
n
o
.
6
,
p
p
.
9
3
2
-
9
3
7
,
2
0
0
1
.
[2
2
]
A
.
A
s
f
a
rian
,
Y.
He
rd
iy
e
n
i,
A
.
Ra
u
f
,
a
n
d
K.
H.
M
u
taq
in
,
“
P
a
d
d
y
d
ise
a
se
s
id
e
n
ti
f
ica
ti
o
n
w
it
h
tex
tu
r
e
a
n
a
ly
sis
u
sin
g
f
ra
c
tal
d
e
sc
rip
to
rs
b
a
se
d
o
n
f
o
u
ri
e
r
sp
e
c
tru
m
,
”
Pro
c
e
e
d
in
g
-
2
0
1
3
I
n
t.
Co
n
f.
C
o
mp
u
t.
C
o
n
tr
o
l.
I
n
fo
r
ma
ti
c
s
Its
Ap
p
l.
“
Rec
e
n
t
Ch
a
ll
e
n
g
e
s C
o
mp
u
t.
C
o
n
tro
l
In
fo
rm
a
t
ics
”
,
IC3
INA
2
0
1
3
,
p
p
.
7
7
-
8
1
,
2
0
1
3
.
[2
3
]
S
.
N.
G
h
a
iw
a
t
a
n
d
P
.
A
ro
ra
,
“
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
f
P
lan
t
L
e
a
f
Dis
e
a
se
s
U
sin
g
Im
a
g
e
p
ro
c
e
ss
in
g
T
e
c
h
n
iq
u
e
s: A
Re
v
ie
w
,
”
In
t.
J
.
Rec
e
n
t
Ad
v
.
E
n
g
.
T
e
c
h
n
o
l.
,
v
o
l.
2,
n
o
.
3
,
p
p
.
2
3
4
7
-
2
8
1
2
,
2
0
1
4
.
[2
4
]
K.
M
.
Ch
e
n
a
n
d
S
.
Y.
Ch
e
n
,
“
Co
lo
r
tex
tu
re
se
g
m
e
n
tatio
n
u
si
n
g
f
e
a
tu
re
d
istri
b
u
t
io
n
s,”
Pa
tt
e
rn
Rec
o
g
n
it
.
L
e
tt
.
,
v
o
l.
2
3
,
n
o
.
7
,
p
p
.
7
5
5
-
7
7
1
,
2
0
0
2
.
[2
5
]
M
.
S
a
rif
u
d
d
i
n
a
n
d
R.
M
issa
o
u
i,
“
A
n
e
w
p
e
r
c
e
p
tu
a
ll
y
u
n
if
o
r
m
c
o
lo
r
sp
a
c
e
w
it
h
a
ss
o
c
iate
d
c
o
lo
r
sim
il
a
rit
y
m
e
a
su
re
f
o
r
c
o
n
ten
t
-
b
a
se
d
im
a
g
e
a
n
d
v
id
e
o
re
tri
e
v
a
l,
”
Pro
c
.
ACM
S
IGIR
2
0
0
5
W
o
rk
.
M
u
l
ti
me
d
.
I
n
f.
Retr.
,
2
0
0
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.