I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
,
p
p
.
1
3
~2
1
I
SS
N:
2252
-
8938
13
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
J
AI
G
ra
ding
of
So
y
bea
n Lea
f
D
isea
se
B
a
sed o
n Seg
m
ente
d I
m
a
g
e
U
sing
K
-
m
ea
ns C
lustering
Sa
chin B
J
a
dh
a
v
*
,
Sa
nja
y
B
.
P
a
t
il*
*
*
B
h
ar
ati
Vid
y
ap
ee
t
h
s
C
o
lle
g
e
o
f
E
n
g
i
n
ee
r
i
n
g
Ko
lh
a
p
u
r
M
.
S
(
In
d
ia),
P
h
.
D
S
c
h
o
lar V
T
U,
Be
lag
a
u
m
,
K.S
,
In
d
ia
,
*
*
P
rin
c
ip
a
l,
M
BT
Ca
m
p
u
s,
Isla
m
p
u
r,
M
.
S
.
In
d
ia
.
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
5
,
2
0
1
5
R
ev
i
s
ed
Feb
8
,
2
0
1
6
A
cc
ep
ted
Feb
2
6
,
2
0
1
6
T
ra
d
it
io
n
a
l
m
e
th
o
d
u
se
d
f
o
r
d
ise
a
se
sc
o
rin
g
sc
a
le
to
g
ra
d
e
th
e
p
lan
t
d
ise
a
se
s
is
m
a
in
ly
b
a
se
d
o
n
n
e
c
k
a
e
d
e
y
e
o
b
se
rv
a
ti
o
n
b
y
a
g
ricu
lt
u
re
e
x
p
e
rt
o
r
p
lan
t
p
a
th
l
o
g
ies
t.
In
th
is
m
e
th
o
d
p
e
rc
e
n
tag
e
sc
a
l
e
w
a
s
e
x
c
lu
siv
e
l
y
u
se
d
to
d
e
f
in
e
d
if
fe
re
n
t
d
ise
a
se
se
v
e
rit
ies
in
a
n
i
ll
u
stra
ted
se
ries
o
f
d
ise
a
se
a
ss
e
ss
m
e
n
t
k
e
y
s
f
o
r
f
ield
c
ro
p
s.T
h
e
a
ss
e
ss
m
e
n
t
o
f
p
lan
t
lea
f
d
ise
a
s
e
s
u
sin
g
th
is
a
a
p
ro
a
c
h
w
h
ich
m
a
y
b
e
su
b
jec
ti
v
e
,
ti
m
e
c
o
n
su
m
in
g
a
n
d
c
o
st
e
f
fe
c
ti
v
e
.
A
ls
o
a
a
c
u
ra
te
g
ra
d
in
g
o
f
l
e
a
f
d
ise
a
se
s
is
e
s
se
n
ti
a
l
to
th
e
d
e
term
in
a
ti
o
n
o
f
p
e
st
c
o
n
tro
l
m
e
a
su
re
s.
In
o
rd
e
r
to
im
p
ro
v
e
th
is
p
ro
c
e
ss
,
h
e
re
w
e
p
ro
p
o
se
a
tec
h
n
i
q
u
e
f
o
r
a
u
to
m
a
ti
c
a
ll
y
q
u
a
n
ti
fy
in
g
th
e
d
a
m
a
g
e
d
le
a
f
a
re
a
u
sin
g
k
m
e
a
n
s
c
lu
ste
rin
g
,
w
h
ich
u
se
s
sq
u
a
re
Eu
c
li
d
ian
d
istan
c
e
s
m
e
th
o
d
f
o
r
p
a
rti
ti
o
n
o
f
lea
f
im
a
g
e
.
F
o
r
g
ra
d
in
g
o
f
so
y
b
e
a
n
lea
f
d
ise
se
w
h
ich
a
p
p
e
a
r
o
n
lea
v
e
s
b
a
se
d
o
n
se
g
m
e
n
ted
d
ise
a
se
d
re
g
io
n
a
re
d
o
n
e
a
u
to
m
a
ti
c
a
ll
y
b
y
e
stia
m
ti
n
g
th
a
e
ra
ti
o
o
f
th
e
u
n
it
p
ix
e
l
e
x
p
re
ss
e
d
u
n
d
e
r
d
ise
a
se
d
re
g
io
n
a
re
a
a
n
d
u
n
it
p
ix
e
l
e
x
p
re
s
se
d
u
n
d
e
r
L
e
a
f
re
g
io
n
a
re
a
.
F
o
r
e
x
p
e
ri
m
e
n
t
p
u
rp
o
se
sa
m
p
les
o
f
B
a
c
teria
l
Le
a
f
Bli
g
h
t
S
e
p
to
ria
Bro
w
n
sp
o
t,
Be
a
n
P
o
d
M
o
tt
le
Viru
s
in
f
e
c
ted
so
y
b
e
a
n
le
a
f
i
m
a
g
e
s
w
e
r
e
ta
k
e
n
f
o
r
a
n
a
l
y
sis.F
in
a
ll
y
e
s
ti
a
m
a
ted
d
ise
a
se
d
se
v
e
rit
y
a
n
d
it
s g
ra
d
in
g
is
c
o
m
p
a
re
d
w
it
h
m
a
n
u
a
l
sc
o
rin
g
b
a
se
d
o
n
c
o
n
v
e
n
t
io
n
a
l
il
l
u
st
ra
ted
k
e
y
d
iag
ra
m
w
a
s
c
o
n
d
u
c
ted
.
C
o
m
p
a
ra
ti
v
e
a
ss
e
s
s
m
e
n
t
re
su
lt
s
sh
o
we
d
a
g
o
o
d
a
g
re
e
m
e
n
t
b
e
tw
e
e
n
th
e
n
u
m
b
e
rs
o
f
p
e
rc
e
n
tag
e
sc
a
le
g
ra
d
in
g
o
b
tain
e
d
b
y
m
a
n
u
a
l
sc
o
rin
g
a
n
d
b
y
i
m
a
g
e
a
n
a
ly
sis
T
h
e
r
e
su
lt
sh
o
w
s
th
a
t
th
e
p
ro
p
o
se
d
m
e
th
o
d
is
p
re
c
ise
a
n
d
re
li
a
b
l
e
th
a
n
v
isu
a
l
e
v
a
lu
a
ti
o
n
p
e
rf
o
rm
e
d
b
y
p
a
tah
lo
g
ies
t.
K
ey
w
o
r
d
:
C
I
E
L
*
a
*
b
Dis
ea
s
e
R
eg
io
n
A
r
ea
Dis
ea
s
e
Se
v
er
it
y
K
-
Me
a
n
s
L
ea
f
R
e
g
io
n
A
r
ea
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
:
Sach
i
n
B
alk
r
is
h
n
a
J
ad
h
av
,
B
h
ar
ati
Vid
y
ap
ee
th
s
C
o
lle
g
e
o
f
E
n
g
in
ee
r
i
n
g
,
Ko
lh
ap
u
r
.
P
h
.
D S
c
h
o
lar
V
T
U,
Be
lag
a
u
m
,
K.S
(In
d
ia),
E
m
ail: sac
h
i
n
b
j
ad
h
av
8
4
@
g
m
a
il.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
So
y
b
ea
n
L
ea
f
d
is
ea
s
e
s
lik
e
B
ac
ter
ial
L
ea
f
B
lig
h
t,
Sep
to
r
ia
B
r
o
w
n
Sp
o
t,
an
d
B
ea
n
L
ea
f
p
o
d
Mo
ttll
e
ar
e
ca
u
s
e
s
ig
n
i
f
ica
n
t
r
ed
u
ctio
n
in
y
ield
lo
s
s
an
d
lead
to
af
f
ec
t
q
u
alit
y
o
f
s
o
y
b
ea
n
P
r
o
d
u
cts
[
1
]
,
th
u
s
i
n
f
l
u
e
n
c
e
ec
o
n
o
m
y
a
n
d
f
ar
m
er
s
lif
e.
A
n
ef
f
ec
ti
v
e
w
a
y
to
co
n
tr
o
l
s
o
y
b
ea
n
f
o
liar
d
is
ea
s
es
i
s
b
y
ap
p
ly
in
g
f
u
n
g
icid
es.T
o
test
th
e
m
et
h
o
d
f
o
r
d
is
ea
s
e
as
s
ess
m
e
n
t,
b
lack
an
d
w
h
ite
d
r
aw
i
n
g
s
f
r
o
m
a
m
a
n
u
al
o
f
d
is
ea
s
e
ass
es
s
m
en
t
k
e
y
s
s
h
o
w
i
n
g
f
o
liar
d
is
ea
s
es
w
it
h
d
i
f
f
er
en
t
d
is
ea
s
e
s
e
v
er
itie
s
[
2
]
.
A
lth
o
u
g
h
t
h
er
e
i
s
a
n
in
d
u
s
tr
ial
r
ec
o
g
n
ized
co
r
r
esp
o
n
d
in
g
s
tan
d
ar
d
to
g
r
ad
e
th
e
leaf
s
p
o
t
d
is
ea
s
e
[
4
-
7
]
,
th
e
n
ak
ed
e
y
e
o
b
s
er
v
atio
n
m
et
h
o
d
is
m
a
in
l
y
ad
o
p
ted
in
th
e
p
r
o
d
u
ctio
n
p
r
ac
tice.
B
ec
au
s
e
o
f
t
h
e
d
i
f
f
er
e
n
c
e
o
f
p
er
s
o
n
al
k
n
o
w
led
g
e
a
n
d
p
r
ac
tical
ex
p
er
ien
ce
;
th
e
s
a
m
e
s
a
m
p
les
ar
e
class
i
f
i
ed
in
to
d
if
f
er
en
t
g
r
ad
es
b
y
d
if
f
er
en
t
e
x
p
er
ts
.
T
h
er
ef
o
r
e,
th
e
r
esu
lt
is
u
s
u
all
y
s
u
b
j
ec
tiv
e
a
n
d
it
i
s
i
m
p
o
s
s
ib
l
e
to
m
ea
s
u
r
e
t
h
e
d
i
s
ea
s
e
e
x
te
n
t
p
r
ec
is
el
y
.
A
lt
h
o
u
g
h
g
r
id
p
ap
er
m
e
th
o
d
ca
n
b
e
u
s
ed
to
i
m
p
r
o
v
e
th
e
ac
cu
r
ac
y
,
it
is
s
eld
o
m
u
s
ed
in
p
r
ac
tice
d
u
e
to
cu
m
b
er
s
o
m
e
o
p
er
atio
n
p
r
o
ce
s
s
an
d
tim
e
-
co
n
s
u
m
i
n
g
.
T
h
er
ef
o
r
e
lo
o
k
i
n
g
f
o
r
a
f
a
s
t
a
n
d
ac
c
u
r
ate
m
et
h
o
d
to
m
ea
s
u
r
e
p
la
n
t
d
i
s
ea
s
e
s
ev
er
it
y
is
o
f
g
r
ea
t
r
ea
lis
tic
s
i
g
n
if
ican
ce
.
Si
n
ce
th
e
late
1
9
7
0
s
,
co
m
p
u
ter
im
ag
e
p
r
o
ce
s
s
i
n
g
tech
n
o
lo
g
y
is
ap
p
lied
in
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
3
–
21
14
ag
r
icu
l
tu
r
al
e
n
g
in
ee
r
i
n
g
r
e
s
ea
r
ch
,
s
u
c
h
as
a
g
r
ic
u
lt
u
r
al
p
r
o
d
u
cts
q
u
alit
y
i
n
s
p
ec
tio
n
a
n
d
cla
s
s
i
f
icatio
n
,
th
e
cr
o
p
g
r
o
w
t
h
s
tate
m
o
n
ito
r
in
g
,
p
la
n
t
d
i
s
ea
s
e
a
n
d
i
n
s
ec
t
p
est
’
s
i
d
en
tific
atio
n
,
a
n
d
o
t
h
er
a
g
r
icu
lt
u
r
al
r
o
b
o
t
[
8
,
9
]
.
W
ith
th
e
r
ec
e
n
t
d
ev
e
lo
p
m
en
t
in
t
h
e
f
ield
o
f
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
a
n
d
p
atter
n
r
ec
o
g
n
itio
n
tech
n
iq
u
es,
i
t
is
p
o
s
s
ib
le
to
d
ev
elo
p
an
au
to
m
a
tio
n
s
y
s
te
m
f
o
r
d
is
ea
s
e
a
s
s
ee
s
m
en
t
o
f
p
la
n
t
lea
f
b
ased
o
n
t
h
e
v
is
u
al
s
y
m
p
to
m
s
o
n
leaf
i
m
a
g
e.
T
h
e
p
lan
t
d
is
ea
s
e
s
co
r
in
g
is
i
m
p
o
r
tan
t
p
r
o
ce
d
u
r
e
to
d
e
v
elo
p
d
iag
n
o
s
tic
p
lan
t
an
d
in
v
e
s
ti
g
at
e
r
esis
ta
n
t
v
ar
ietie
s
to
th
e
d
is
ea
s
e.
C
o
n
v
e
n
tio
n
all
y
,
p
lan
t
p
ath
o
l
o
g
is
t
s
s
co
r
e
th
e
d
is
ea
s
e
le
v
el
b
ased
o
n
th
eir
o
w
n
d
is
cr
etio
n
u
s
i
n
g
ill
u
s
tr
ated
d
iag
r
a
m
k
e
y
f
o
r
p
ar
ticu
lar
d
i
s
ea
s
e.
T
h
e
v
ar
io
u
s
r
esear
c
h
er
s
i
n
v
e
s
ti
g
ated
t
h
eir
m
et
h
o
d
s
f
o
r
ass
e
s
s
m
en
t k
e
y
o
f
d
is
ea
s
e
s
ev
er
it
ies
f
o
r
d
if
f
er
e
n
t
p
lan
t d
is
ea
s
es
w
h
ic
h
ar
e
o
u
tli
n
ed
as f
o
llo
w
s
:
W
.
C
I
iv
e
J
am
e
s
[
3
]
d
ev
elo
p
e
d
m
et
h
o
d
f
o
r
s
er
ies
o
f
ass
e
s
s
m
e
n
t
k
e
y
s
f
o
r
p
lan
t
d
is
ea
s
e
s
in
w
h
ich
p
er
ce
n
tag
e
s
ca
le
w
a
s
e
x
cl
u
s
i
v
el
y
u
s
ed
to
d
ef
i
n
e
d
i
f
f
er
e
n
t
d
i
s
ea
s
e
s
ev
er
it
ies
i
n
an
ill
u
s
tr
at
ed
s
er
ies
o
f
d
is
ea
s
e
ass
es
s
m
en
t
k
e
y
s
f
o
r
ce
r
ea
l,f
o
r
ag
e,
an
d
f
ie
ld
cr
o
p
s
.
T
h
e
s
tan
d
ar
d
ar
ea
d
iag
r
a
m
s
w
er
e
ac
c
u
r
atel
y
p
r
ep
ar
e
d
w
it
h
an
elec
tr
o
n
ic
s
ca
n
n
er
.
P
r
o
ce
d
u
r
es
f
o
r
ass
e
s
s
i
n
g
t
h
e
d
i
f
f
er
e
n
t
d
is
ea
s
es
ar
e
o
u
tlin
ed
i
n
o
r
d
er
to
ac
h
iev
e
s
o
m
e
d
eg
r
ee
o
f
s
ta
n
d
ar
d
izatio
n
in
d
is
ea
s
e
ass
e
s
s
m
en
t
m
et
h
o
d
s
.
P
au
l
Vi
n
ce
l
li
an
d
Do
n
ald
E
.
Her
s
h
m
a
n
[
4
]
d
ev
elo
p
ed
a
d
ia
g
r
a
m
k
e
y
f
o
r
c
lass
i
f
y
in
g
th
e
s
ev
er
it
y
o
f
s
o
y
b
ea
n
lea
f
d
is
ea
s
e
in
to
1
0
lev
els.
I
n
h
is
w
o
r
k
h
e
h
ad
in
v
e
s
tig
a
ted
p
r
o
ce
d
u
r
e
f
o
r
r
atin
g
d
is
ea
s
e
i
n
C
o
r
n
,
So
y
b
ea
n
,
an
d
W
h
ea
t.
Sh
e
n
W
eizh
en
g
an
d
W
u
Yac
h
u
n
[
5
]
d
ev
elo
p
ed
m
eth
o
d
f
o
r
s
e
g
m
e
n
tatio
n
m
eth
o
d
s
to
an
al
y
s
e
s
p
o
t
d
is
e
s
e
o
f
s
o
y
b
ea
n
i
n
w
h
ic
h
th
r
es
h
o
ld
in
g
is
d
o
n
e
b
y
Ot
s
u
m
eth
o
d
an
d
d
is
ea
s
e
s
p
o
t
r
eg
io
n
s
w
er
e
s
e
g
m
e
n
ted
b
y
u
s
i
n
g
So
b
el
o
p
er
ato
r
t
o
ex
a
m
in
e
d
is
ea
s
e
s
p
o
t
ed
g
es.
F
in
all
y
p
la
n
t
d
i
s
ea
s
e
s
ar
e
g
r
ad
ed
b
y
ca
lc
u
lati
n
g
t
h
e
q
u
o
tien
t
o
f
d
is
ea
s
e
s
p
o
t
an
d
leaf
ar
ea
s
.
San
j
a
y
p
atil
an
d
Dr
.
B
o
d
h
e
[
6
]
d
ev
elo
p
ed
His
to
g
r
a
m
b
as
ed
tr
ian
g
u
lar
s
eg
m
e
n
tatio
n
m
et
h
o
d
s
to
an
al
y
s
is
B
r
o
w
n
s
p
o
t
d
is
ea
s
e
o
n
s
u
g
ar
ca
n
e
p
lan
t
leaf
s
y
m
p
to
m
s
w
as
s
h
o
w
n
o
n
it.
T
h
u
s
Su
g
ar
ca
n
e
L
ea
f
,
d
is
ea
s
e
s
v
e
v
r
it
y
ar
e
a
s
s
es
s
d
b
y
ca
lc
u
lati
n
g
th
e
q
u
o
tien
t
o
f
l
esio
n
ar
ea
an
d
lea
f
ar
ea
s
.
E
v
y
Ka
m
ila
h
R
at
n
asar
i
&
o
th
er
s
[
7
]
d
ev
elo
p
ed
m
o
d
el
f
o
r
s
e
g
m
e
n
tatio
n
m
eth
o
d
s
in
w
h
ic
h
th
r
e
s
h
o
ld
i
n
g
a
*
c
o
m
p
o
n
en
t
o
f
co
lo
r
in
d
ep
en
d
en
t
L
*
a
*
b
co
lo
r
s
p
ac
e
to
an
al
y
s
i
s
B
r
o
w
n
s
p
o
t
d
is
ea
s
e
o
n
s
u
g
ar
ca
n
e
p
la
n
t
lea
f
s
y
m
p
to
m
s
w
as
s
h
o
wn
o
n
it.
Kittip
o
n
g
P
o
w
b
u
n
t
h
o
r
n
&
o
th
er
s
[
8
]
d
ev
elo
p
ed
s
eg
m
en
tatio
n
m
et
h
o
d
s
f
o
r
as
s
ess
m
en
t
o
f
b
r
o
w
n
lea
f
s
p
o
t
Dis
ea
s
e
i
n
C
as
s
av
a
i
n
w
h
ic
h
t
h
r
esh
o
ld
i
n
g
is
d
o
n
e
b
y
Ots
u
m
et
h
o
d
an
d
d
is
ea
s
e
s
p
o
t
r
eg
io
n
s
w
er
e
s
eg
m
e
n
ted
b
y
a
n
al
y
s
i
s
o
f
t
h
e
h
is
to
g
r
a
m
b
ased
o
n
HSI
co
lo
r
s
p
ac
e.
T
h
u
s
th
e
p
la
n
t
d
i
s
ea
s
es
ar
e
ass
ess
ed
b
y
ca
lcu
lati
n
g
t
h
e
q
u
o
tien
t
o
f
d
is
ea
s
e
s
p
o
t
a
n
d
lea
f
ar
ea
s
.
J
a
y
m
e
Gar
cia
a
n
d
A
r
n
a
l
B
ar
b
ed
o
[
9
]
d
ev
elo
p
ed
m
o
d
el
f
o
r
s
eg
m
e
n
tatio
n
m
e
th
o
d
s
i
n
w
h
ic
h
t
h
r
esh
o
ld
i
n
g
b
a
s
ed
o
n
R
OI
i
n
C
MY
K
-
XY
Z
co
lo
r
s
p
ac
e
to
an
al
y
s
i
s
w
h
ite
f
lie
s
s
y
m
p
to
m
s
d
is
ea
s
e
o
n
s
o
y
b
ea
n
lea
v
es
w
as
s
h
o
w
n
o
n
it.T
h
e
o
b
j
ec
tiv
es
o
f
t
h
is
wo
r
k
is
to
d
e
v
elo
p
an
i
m
a
g
e
a
n
al
y
s
is
tech
n
iq
u
e
f
o
r
esti
m
ati
n
g
th
e
s
e
v
er
it
y
lev
el
[
1
1
]
o
f
s
o
y
b
ea
n
d
is
ea
s
e
b
ased
o
n
d
is
ea
s
ed
ar
ea
a
s
w
ell
a
s
to
co
m
p
ar
e
th
e
r
esu
lts
w
it
h
m
an
u
al
s
co
r
in
g
u
s
in
g
k
e
n
tu
ck
y
[
1
0
]
d
iag
r
a
m
k
e
y
.
2.
CL
AS
SI
F
I
CAT
I
O
N
P
RIN
C
I
P
L
E
T
h
e
s
ev
er
it
y
e
x
ten
t
o
f
th
e
p
la
n
t
leav
e
s
d
is
ea
s
e
s
is
co
m
m
o
n
l
y
m
ea
s
u
r
ed
b
y
th
e
r
atio
o
f
d
is
ea
s
e
ar
ea
an
d
leaf
ar
ea
r
atio
.
A
d
o
p
tin
g
i
m
ag
e
p
r
o
ce
s
s
i
n
g
m
e
th
o
d
to
m
ea
s
u
r
e
ca
n
b
e
ex
p
r
es
s
ed
as th
e
f
o
llo
w
in
g
f
o
r
m
u
la.
[
3
]
∑
(
)
∑
(
)
∑
(
)
∑
(
)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
(
1
)
A
d
——
Dis
ea
s
e
R
e
g
io
n
A
r
ea
;
A
l
——
L
ea
f
R
e
g
io
n
A
r
ea
;
P
——
Un
i
t P
ix
el
E
x
p
r
ess
ed
Ar
ea
;
R
d
——
Dis
ea
s
e
R
e
g
io
n
;
R
l
——
L
ea
f
R
e
g
io
n
.
Un
it
p
i
x
el
i
n
th
e
s
a
m
e
d
ig
it
al
i
m
a
g
e
r
ep
r
esen
te
t
h
e
s
a
m
e
s
ize,
s
o
r
atio
DS
ca
n
b
e
o
b
tain
ed
b
y
s
eg
m
e
n
ti
n
g
.
D
is
ea
s
ed
r
e
g
io
n
f
r
o
m
leaf
R
e
g
io
n
a
n
d
C
alc
u
lati
n
g
p
i
x
el
n
u
m
b
er
∑
(
)
o
f
d
is
ea
s
ed
r
eg
io
n
an
d
∑
(
)
o
f
lea
f
r
eg
io
n
in
th
e
cl
u
s
tu
r
e
i
m
ag
e.
T
h
en
ac
co
r
d
in
g
to
d
is
ea
s
e
clas
s
i
f
icatio
n
s
ta
n
d
ar
d
co
n
s
u
lt
tab
le
th
e
f
i
n
al
s
e
v
er
it
y
lev
e
l c
an
b
e
ac
h
iev
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Gra
d
in
g
o
f S
o
yb
ea
n
Lea
f D
is
ea
s
e
B
a
s
ed
o
n
S
eg
men
ted
I
ma
g
e
Usi
n
g
K
-
mea
n
s
(
S
a
ch
in
B
a
l
kris
h
n
a
J
.
)
15
3.
SE
V
E
RI
T
Y
AS
SE
SS
M
E
NT
S B
Y
AREA DI
AG
RAM
K
E
Y
Ass
es
s
i
n
g
t
h
e
s
e
v
er
it
y
o
f
s
o
y
b
ea
n
f
o
liar
d
is
ea
s
es
b
y
u
s
i
n
g
a
n
ar
ea
d
iag
r
a
m
k
e
y
[
4
]
[
1
0
]
w
as
ca
teg
o
r
ized
p
er
ce
n
tag
e
s
o
f
in
f
lectio
n
o
f
te
n
le
v
els
as
s
h
o
w
i
n
Fi
g
u
r
e.
1
.
E
ac
h
lea
f
i
m
a
g
e
s
a
m
p
les
w
as
v
i
s
u
all
y
ass
es
s
ed
i
n
d
ep
en
d
en
tl
y
&
th
e
n
w
i
th
i
m
a
g
e
an
al
y
s
is
m
et
h
o
d
s
u
p
o
n
to
th
e
d
is
cr
etio
n
o
f
t
h
e
i
n
d
iv
id
u
al
r
ater
s
[
1
1
]
w
er
e
tak
e
n
i
n
to
ac
co
u
n
t
f
o
r
m
et
h
o
d
v
alid
itatio
n
.
Fig
u
r
e
1
.
Diag
r
a
m
k
e
y
f
o
r
ass
ess
m
en
t o
f
Fo
liear
d
is
ea
s
e
s
o
f
So
y
b
ea
n
(
B
ased
o
n
A
f
i
g
u
r
e
in
KE
NT
UC
KY
I
n
teg
r
ated
C
r
o
p
Ma
n
u
al
f
o
r
S
o
y
b
ea
n
s
I
MP
-
3
.
2
0
0
9
.
P
G.
3
)
4.
SE
V
E
RI
T
Y
AS
SE
SS
M
E
NT
B
Y
I
M
AG
E
ANALY
SI
S
4
.
1
.
I
M
AG
E
SE
G
M
E
NT
A
T
I
O
N
Seg
m
en
ta
tio
n
i
s
th
e
cla
s
s
if
ica
tio
n
s
o
f
a
n
i
m
a
g
e
in
to
m
ea
n
in
g
f
u
l
d
ata
f
o
r
ea
s
y
a
n
al
y
s
i
s
o
f
t
h
e
i
m
ag
e
.
T
h
e
ex
is
t
in
g
m
et
h
o
d
s
f
o
r
s
e
g
m
en
tatio
n
ar
e
t
h
r
esh
o
ld
i
n
g
,
r
eg
io
n
g
r
o
w
i
n
g
an
d
c
lu
s
ter
in
g
.
T
h
r
esh
o
ld
in
g
is
t
h
e
s
i
m
p
le
s
t
m
et
h
o
d
o
f
i
m
ag
e
p
r
o
ce
s
s
in
g
.
Fro
m
an
R
GB
i
m
ag
e
co
n
v
er
ted
to
th
e
co
r
r
esp
o
n
d
in
g
g
r
a
y
lev
e
l
in
te
n
s
it
y
i
m
a
g
e
[
1
7
]
,
i
m
a
g
e
ca
n
b
e
p
ar
titi
o
n
ed
b
y
b
in
ar
y
v
al
u
es,
1
a
n
d
0
.
T
h
e
r
eg
io
n
ab
o
v
e
th
e
th
r
es
h
o
ld
m
a
y
b
e
ass
ig
n
ed
1
an
d
t
h
at
o
f
b
el
o
w
t
h
e
t
h
r
es
h
o
ld
m
a
y
b
e
ass
ig
n
ed
ze
r
o
.
T
h
is
h
is
t
o
g
r
a
m
a
p
p
r
o
ac
h
ca
n
n
o
t
b
e
r
ela
y
ed
u
p
o
n
f
o
r
ef
f
ec
ti
v
e
c
l
ass
i
f
icatio
n
o
f
t
h
e
i
m
a
g
e
i
n
f
o
r
m
atio
n
as
th
e
b
in
ar
y
ap
p
r
o
ac
h
o
f
cla
s
s
i
f
icatio
n
li
m
it
s
t
h
e
r
ep
r
esen
tatio
n
o
f
i
m
ag
e
s
e
g
m
en
t
s
an
d
f
u
r
th
er
r
ed
u
ce
s
p
r
o
p
er
d
etec
tio
n
[
1
4
]
[
1
6
]
[
1
8
]
o
f
th
e
r
eq
u
ir
ed
ar
ea
.
C
o
n
s
id
er
in
g
t
h
is
li
m
ai
t
atio
n
k
-
m
ea
n
s
cl
u
s
ter
i
n
g
m
et
h
o
d
f
o
r
leaf
i
m
ag
e
s
eg
m
e
n
ta
tio
n
is
u
s
ed
i
n
th
i
s
p
ap
er
.
4
.
2
.
P
RO
P
O
SE
D
CL
U
ST
UR
I
NG
M
E
T
H
O
D
:
Seg
m
en
tatio
n
ap
p
r
o
ac
h
es
b
ased
o
n
clu
s
ter
in
g
h
as
m
an
y
a
d
v
an
ta
g
es
o
v
er
o
th
er
ap
p
r
o
a
ch
es
as
it
p
r
o
v
id
es
an
ef
f
icie
n
t
cla
s
s
i
f
i
ca
tio
n
o
f
i
m
a
g
e
i
n
f
o
r
m
atio
n
an
d
ca
n
b
e
i
m
p
le
m
e
n
ted
i
n
m
a
n
y
f
ield
s
o
f
h
u
m
a
n
i
n
ter
est
s
u
c
h
a
s
a
v
iat
io
n
,
m
ilit
ar
y
an
d
m
ed
ical
f
ield
s
.
T
h
e
i
m
p
le
m
en
ta
tio
n
o
f
s
eg
m
e
n
tatio
n
o
n
ag
r
icu
l
tu
r
e
h
as
ar
o
u
s
ed
t
h
e
i
n
t
er
est
o
f
m
a
n
y
s
c
h
o
lar
s
f
o
r
it
p
av
es
a
n
ea
s
y
to
i
m
p
le
m
e
n
t
an
d
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
d
etec
tin
g
v
ar
io
u
s
p
at
h
o
g
en
s
a
n
d
it
i
s
h
ar
m
les
s
d
u
e
t
o
lo
w
co
n
s
u
m
p
tio
n
o
f
ar
ti
f
i
cial
p
esti
cid
es
a
n
d
h
er
b
icid
es
K
-
m
ea
n
s
cl
u
s
ter
i
n
g
is
u
s
ed
to
p
ar
titi
o
n
th
e
lea
f
i
m
a
g
e
i
n
to
f
o
u
r
cl
u
s
ter
s
in
w
h
ich
o
n
e
o
r
m
o
r
e
clu
s
ter
s
co
n
tai
n
th
e
d
is
ea
s
e
i
n
ca
s
e
w
h
en
t
h
e
leaf
i
s
in
f
ec
te
d
b
y
m
o
r
e
th
a
n
o
n
e
d
is
ea
s
e.
K
m
ea
n
s
clu
s
ter
in
g
alg
o
r
ith
m
w
as
d
e
v
elo
p
ed
b
y
J
.
Ma
cQu
ee
n
(
1
9
6
7
)
an
d
th
e
n
b
y
J
.
A
.
Har
ti
g
an
a
n
d
M.
A
.
W
o
n
g
[
1
4
]
.
T
h
e
k
-
m
ea
n
s
cl
u
s
ter
in
g
a
lg
o
r
it
h
m
s
t
r
ies
to
cla
s
s
i
f
y
o
b
j
ec
ts
(
p
ix
el
s
i
n
o
u
r
ca
s
e)
b
ased
o
n
a
s
et
o
f
f
ea
t
u
r
es
in
to
K
n
u
m
b
er
o
f
clas
s
es.
T
h
e
cla
s
s
i
f
icatio
n
is
d
o
n
e
b
y
m
in
i
m
iz
i
n
g
th
e
s
u
m
o
f
s
q
u
ar
e
s
o
f
d
is
tan
ce
s
b
et
w
ee
n
th
e
o
b
j
ec
ts
an
d
th
e
co
r
r
esp
o
n
d
in
g
clu
s
ter
o
r
class
ce
n
tr
o
id
.
I
n
o
u
r
ex
p
er
i
m
e
n
ts
,
t
h
e
K
-
m
ea
n
s
clu
s
ter
i
n
g
is
s
et
to
u
s
e
s
q
u
ar
ed
E
u
clid
ea
n
d
is
ta
n
c
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
3
–
21
16
4
.
2
.
1
.
Descript
io
n o
f
Alg
o
rit
h
m
T
h
e
alg
o
r
ith
m
i
s
v
er
y
s
i
m
ilar
to
Fo
r
g
y
’
s
alg
o
r
it
h
m
[
1
9
]
.
B
esid
es
th
e
d
ata,
i
n
p
u
t
to
t
h
e
alg
o
r
ith
m
co
n
s
is
ts
o
f
k
,
t
h
e
n
u
m
b
er
o
f
c
lu
s
ter
s
to
b
e
d
ev
elo
p
ed
.
Fo
r
g
y
’
s
al
g
o
r
ith
m
i
s
iter
ati
v
e,
b
u
t
k
-
m
ea
n
s
a
lg
o
r
it
h
m
m
ak
e
s
o
n
l
y
t
w
o
p
ass
e
s
th
r
o
u
g
h
th
e
d
ata
s
et.
1
.
B
eg
in
w
ith
k
cl
u
s
ter
ce
n
tr
es,
ea
ch
co
n
s
is
ti
n
g
o
f
o
n
e
o
f
t
h
e
f
ir
s
t
k
s
a
m
p
le
s
.
Fo
r
ea
ch
o
f
th
e
r
e
m
ai
n
i
n
g
n
-
k
s
a
m
p
les,
f
in
d
th
e
ce
n
tr
o
id
n
e
ar
est
it.
P
u
t
t
h
e
s
a
m
p
le
in
t
h
e
clu
s
ter
id
en
ti
f
ied
w
it
h
th
i
s
n
ea
r
est
ce
n
tr
o
id
.
Af
ter
ea
ch
s
a
m
p
le
i
s
ass
i
g
n
ed
,
r
ec
o
m
p
u
te
th
e
ce
n
tr
o
id
o
f
th
e
alter
ed
clu
s
ter
.
2
.
Go
th
r
o
u
g
h
th
e
d
ata
a
s
ec
o
n
d
ti
m
e.
Fo
r
ea
ch
s
a
m
p
le,
f
in
d
th
e
ce
n
tr
o
id
n
ea
r
est
it.
P
u
t
th
e
s
a
m
p
le
i
n
th
e
clu
s
ter
id
en
t
if
ied
w
it
h
t
h
is
n
ea
r
est
ce
n
tr
o
id
.
(
Du
r
in
g
t
h
i
s
s
t
ep
,
d
o
n
o
t
r
ec
o
m
p
u
te
an
y
ce
n
tr
o
id
)
A
d
d
itio
n
o
f
ce
r
tai
n
f
ea
t
u
r
es
i
n
th
e
e
x
i
s
tin
g
k
m
ea
n
s
al
g
o
r
ith
m
i
m
p
r
o
v
es
t
h
e
d
etec
tio
n
o
f
t
h
e
in
t
er
ested
r
eg
io
n
ef
f
ec
tiv
e
l
y
w
it
h
m
i
n
i
m
u
m
c
h
an
ce
o
f
f
a
u
lt
y
cl
u
s
ter
in
g
.
T
h
e
f
ir
s
t
s
tep
i
n
k
-
m
ea
n
s
cl
u
s
ter
i
n
g
is
t
h
e
in
itial
is
atio
n
o
f
clu
s
ter
ce
n
tr
e
s
.
C
o
m
m
o
n
m
et
h
o
d
s
f
o
r
i
n
iti
alis
atio
n
in
c
lu
d
e
r
a
n
d
o
m
l
y
c
h
o
s
en
s
tar
t
s
o
r
u
s
i
n
g
h
i
er
ar
ch
ical
clu
s
ter
in
g
t
o
o
b
tain
k
in
itia
l c
en
tr
es [
1
9
]
-
[
2
0
]
.
T
h
e
in
itialis
a
tio
n
s
tep
s
ca
n
b
e
ex
p
lain
ed
as
f
o
llo
w
s
.
1
.
C
o
n
v
er
t n
×p
i
m
a
g
e
m
atr
i
x
X
to
n
×
(
p
-
1
)
m
atr
i
x
Z
,
w
h
e
r
e
ea
ch
r
o
w
Z
i o
f
Z
is
t
h
e
p
o
lar
r
ep
r
esen
tatio
n
o
f
th
e
co
r
r
esp
o
n
d
in
g
r
o
w
(
X
i
S
p
)
o
f
X.
2
.
Fo
r
ea
ch
co
lu
m
n
Z
,
f
i
n
d
t
h
e
p
air
o
f
n
ei
g
h
b
o
u
r
i
n
g
p
o
in
ts
w
it
h
t
h
e
lar
g
es
t a
n
g
u
lar
d
is
ta
n
ce
b
et
w
ee
n
t
h
e
m
an
d
r
o
tate
Z
s
u
c
h
t
h
at
t
h
es
e
n
eig
h
b
o
u
r
s
h
av
e
t
h
e
lar
g
e
s
t l
in
ea
r
d
is
tan
ce
b
et
w
ee
n
t
h
e
m
.
3
.
On
e
d
im
e
n
s
io
n
al
m
atr
ix
f
o
r
k
-
m
ea
n
s
is
i
n
itialized
w
it
h
g
r
ea
test
v
alu
e
i
n
te
g
er
o
b
tain
ed
f
r
o
m
(
K
(
p
-
2)
1/
(
p
-
2)
eq
u
i
-
s
p
ac
ed
q
u
an
titi
e
s
.
4
.
2
.
1
.
Appl
y
ing
m
a
s
k
ing
t
o
K
-
m
ea
ns
a
lg
o
rit
h
m
.
Fo
r
a
g
iv
en
k
an
d
in
i
tial
cl
u
s
t
er
ce
n
tr
es
{
k
;
k
=1
…
k
},
t
h
e
g
en
er
al
s
tr
ateg
y
is
to
p
o
s
itio
n
t
h
e
d
atase
ts
in
to
k
c
lu
s
ter
s
,
t
h
en
to
iter
ate
th
e
cl
u
s
ter
m
ea
n
d
ir
ec
tio
n
s
u
n
til
co
n
v
er
g
e
n
ce
[
2
0
]
.
T
h
e
ex
a
ct
alg
o
r
ith
m
ca
n
b
e
ex
p
lain
ed
as
f
o
llo
w
s
.
1
.
Giv
en
―k
‖
i
n
itiali
s
i
n
g
cl
u
s
ter
m
ea
n
d
ir
ec
tio
n
s
1
,
2
,
…
k
,
f
i
n
d
th
e
t
w
o
clo
s
est
m
ea
n
d
ir
ec
tio
n
s
f
o
r
ev
er
y
Ob
s
er
v
atio
n
Xi; i=
1
,
2
…n
.
2
.
C
lass
if
y
t
h
e
g
r
o
u
p
s
b
y
C
1
i a
n
d
C
2
i r
esp
ec
tiv
el
y
.
A
s
s
i
g
n
th
e
u
p
d
ate
eq
u
atio
n
V
k
-
=
(
n
k
-
1)
2
–
nk
2
|
|
Xk
|
|
2
-
1
an
d
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
(
1
)
V
k
+
=
(
n
k
+
1
)
2
–
nk
2
|
|
X
k
|
|
2
-
1
(
2
)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
(
2
)
A
ll c
l
u
s
ter
s
ar
e
i
n
th
e
li
v
e
i
m
ag
e
s
et
at
t
h
is
s
tag
e.
3
.
T
h
e
liv
e
s
et
is
u
p
d
ated
to
f
i
n
d
o
p
ti
m
u
m
co
n
v
er
g
e
n
ce
4
.
Op
tim
u
m
tr
a
n
s
f
er
s
ta
g
e:
F
o
r
ea
ch
Xi,
i=
1
,
2
…n
,
w
e
ca
lc
u
late
t
h
e
m
a
x
i
m
u
m
r
ed
u
ct
io
n
i
n
th
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
.
B
y
r
ep
lacin
g
t
h
e
liv
e
f
u
n
ctio
n
!
i
w
it
h
a
n
o
th
er
c
lass
,
m
a
x
i
m
u
m
r
ed
u
ctio
n
ca
n
b
e
o
b
tain
ed
as
I
f
W
i >
0
,
th
en
th
e
o
n
l
y
q
u
a
n
ti
t
y
to
b
e
u
p
d
ated
is
C
2
i =
Ki
.
5
.
Qu
ick
tr
an
s
f
er
s
ta
g
e
in
c
l
u
d
es s
w
ap
p
in
g
a
n
d
th
e
o
b
j
ec
ti
v
e
f
u
n
ctio
n
a
n
d
th
e
c
h
an
g
e
i
n
th
e
o
b
j
ec
tiv
e
f
u
n
ctio
n
ca
n
b
e
ca
lcu
late
d
as
I
t is p
r
o
v
id
in
g
a
q
u
ic
k
w
a
y
o
f
o
b
tain
in
g
f
in
al
v
al
u
e.
T
h
e
ex
ac
t
ex
tr
ac
tio
n
o
f
t
h
e
less
io
n
ar
ea
s
o
f
t
h
e
s
o
y
b
ea
n
leaf
ca
n
b
e
d
etec
ted
b
y
m
a
s
k
i
n
g
th
e
clu
s
ter
ed
s
a
m
p
le
co
n
ta
in
i
n
g
t
h
e
p
lan
t
r
e
g
io
n
a
n
d
t
h
en
s
u
b
t
r
ac
tin
g
it
f
r
o
m
t
h
e
ac
q
u
ir
ed
i
m
ag
e.
T
h
e
m
o
d
i
f
ied
alg
o
r
ith
m
d
ev
e
lo
p
ed
u
s
i
n
g
k
-
m
ea
n
s
cl
u
s
ter
i
n
g
ca
n
b
e
d
is
c
u
s
s
ed
w
it
h
t
h
e
ex
p
er
i
m
en
tal
r
esu
lt
s
o
b
tain
ed
f
r
o
m
a,
B
ac
ter
ial
B
lig
h
t,
Sep
to
r
ia
B
r
o
w
n
Sp
o
t,
an
d
B
ea
n
p
o
d
Mo
ttle in
f
ec
ted
d
is
ea
s
ed
leaf
r
esep
ec
tiv
el
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Gra
d
in
g
o
f S
o
yb
ea
n
Lea
f D
is
ea
s
e
B
a
s
ed
o
n
S
eg
men
ted
I
ma
g
e
Usi
n
g
K
-
mea
n
s
(
S
a
ch
in
B
a
l
kris
h
n
a
J
.
)
17
5.
E
XP
E
R
I
M
E
NT
A
L
P
RO
CI
DURE
5
.
1
.
I
m
a
g
e
Acquis
it
io
n
T
h
is
s
t
u
d
y
tak
e
s
B
ac
ter
ial
L
ea
f
B
li
g
h
t,
Sep
to
r
ia
B
r
o
w
n
s
p
o
t,
B
ea
n
P
o
d
Mo
ttle
Vir
u
s
i
n
f
ec
ted
s
o
y
b
ea
n
lea
f
i
m
a
g
es
o
f
s
o
y
b
ea
n
as
ex
a
m
p
le
f
o
r
illu
s
tr
ati
n
g
t
h
e
p
lan
t
d
is
ea
s
e
e
x
ten
t
g
r
ad
in
g
m
eth
o
d
[
1
4
]
.
I
n
f
ec
ted
lea
v
es
ar
e
p
lace
d
f
lat
o
n
a
w
h
ite
b
ac
k
g
r
o
u
n
d
.
T
h
e
o
p
tical
ax
is
o
f
d
ig
ital
ca
m
er
a
is
p
er
p
en
d
icu
lar
to
th
e
lea
f
p
lan
e
to
s
h
o
o
t
i
m
a
g
es,
w
h
ic
h
ar
e
d
ep
o
s
ited
in
th
e
co
m
p
u
ter
f
o
r
f
u
t
u
r
e
u
s
e.
F
ig
u
r
e
2
(
a
-
c)
s
h
o
w
s
ac
q
u
ir
ed
i
m
ag
e
o
f
s
o
y
b
ea
n
lea
f
d
is
ese
s
.
(
a)
(
b
)
©
Fig
u
r
e
2
.
A
cq
u
ir
ed
I
m
a
g
e
o
f
s
o
y
b
ea
n
(
a)
B
ac
ter
ial
L
ea
f
B
lig
h
t.
(
b
)
Sep
to
r
ia
B
r
o
w
n
s
p
o
t.
(
c)
B
ea
n
p
o
d
m
o
ttle.
5
.
2
.
Seg
m
e
nta
t
io
n
T
o
E
x
t
ra
ct
Di
s
ea
s
ed
O
bje
ct
s
I
n
T
he
Cl
us
t
er
Af
ter
ac
q
u
ir
i
n
g
t
h
e
i
m
ag
e,
clu
s
ter
i
n
g
is
d
o
n
e
to
s
ep
ar
ate
th
e
b
ac
k
g
r
o
u
n
d
an
d
t
h
e
f
o
r
eg
r
o
u
n
d
i
m
a
g
e.
T
h
is
is
d
o
n
e
b
y
u
p
d
ati
n
g
th
e
li
v
e
s
et
w
ith
cl
u
s
ter
g
r
o
u
p
s
o
f
lo
w
er
in
ten
s
itie
s
as
a
g
r
o
u
p
.
I
n
th
is
s
tep
it
is
ch
ec
k
ed
w
h
et
h
er
th
e
C
n
i
g
r
o
u
p
s
atis
f
ies
W
i
>
n
.
T
h
e
f
o
r
eg
r
o
u
n
d
i
m
a
g
e
i
s
t
h
u
s
m
ap
p
ed
w
it
h
a
ze
r
o
le
v
el
in
te
n
s
it
y
to
p
er
f
o
r
m
f
u
r
t
h
er
l
o
g
ical
o
p
er
atio
n
s
o
n
t
h
e
clu
s
ter
g
r
o
u
p
.
Fig
u
r
e
3
(
d
-
f
)
s
h
o
w
s
Se
g
m
e
n
tatio
n
to
ex
tr
ac
t th
e
r
e
g
io
n
o
f
i
n
ter
est (
R
OI
)
.
(
d
)
(
e)
(
f
)
Fig
u
r
e
3.
Seg
m
en
ta
tio
n
to
ex
tr
ac
t th
e
r
eg
io
n
o
f
in
ter
est (
R
OI
)
f
o
r
B
ac
ter
ial
L
ea
f
B
lig
h
t (
d
)
,
Sep
to
r
ia
B
r
o
w
n
s
p
o
t
(
e)
,
an
d
B
ea
n
leaf
p
o
d
m
o
ttle (
f
)
.
5
.
3.
Clus
t
er
ing
B
a
s
ed
O
n In
t
ens
it
y
M
a
pp
ing
T
h
e
ac
q
u
ir
ed
im
a
g
e
is
t
h
e
n
s
e
p
ar
ated
to
clu
s
ter
g
r
o
u
p
s
b
ase
d
o
n
k
-
m
ea
n
s
cl
u
s
ter
i
n
g
.
T
h
en
g
r
a
y
le
v
el
m
ap
p
in
g
i
s
p
er
f
o
r
m
ed
to
s
ep
ar
ate
th
e
i
m
ag
e
to
i
n
te
n
s
it
y
f
i
eld
s
w
h
ich
h
e
lp
s
i
n
s
ep
ar
atio
n
o
f
t
h
e
lea
f
i
m
ag
e
f
r
o
m
t
h
e
o
b
tain
ed
i
m
a
g
e.
T
h
e
leaf
i
m
a
g
e
ar
ea
to
b
e
h
i
g
h
l
ig
h
ted
is
lab
elled
in
w
i
th
th
e
c
lu
s
ter
in
d
ex
a
s
s
h
o
w
n
in
f
ig
u
r
e
4
(
g
-
i)
f
o
r
B
ac
ter
ial
L
ea
f
B
lig
h
t.
(
g
)
Sep
to
r
ia
B
r
o
w
n
s
p
o
t.
(
h
)
an
d
B
ea
n
p
o
d
m
o
tt
le
(
i)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
3
–
21
18
(
g
)
(
h
)
(
i)
Fig
u
r
e
4.
Sep
ar
atio
n
o
f
i
m
a
g
e
in
to
g
r
a
y
lev
el
cl
u
s
ter
s
to
o
b
tain
u
s
e
f
u
l le
a
f
ar
ea
f
o
r
B
ac
ter
ial
L
ea
f
B
lig
h
t.
(
g
)
Sep
to
r
ia
B
r
o
w
n
s
p
o
t.
(
h
)
an
d
B
ea
n
p
o
d
m
o
ttle (
i)
.
5
.
4.
H
i
g
hli
g
hting
T
he
L
ea
f
A
re
a
T
h
e
p
ix
el
g
r
o
u
p
s
b
elo
n
g
in
g
t
o
th
e
i
n
te
n
s
it
y
m
ar
k
ed
ar
ea
a
lo
n
e
ar
e
ex
tr
ac
ted
a
n
d
is
s
h
o
w
n
i
n
t
h
e
i
m
a
g
e
b
elo
w
to
o
b
tain
t
h
e
h
i
g
h
l
ig
h
ted
lea
f
ar
ea
alo
n
e
f
r
o
m
t
h
e
ac
q
u
ir
ed
i
m
a
g
e.
T
h
e
ex
tr
ac
ted
leaf
i
m
a
g
e
is
f
u
r
t
h
er
co
r
r
ec
ted
b
y
m
as
k
in
g
w
it
h
a
n
i
m
a
g
e
m
atr
i
x
o
f
s
i
m
il
ar
in
te
n
s
it
y
p
i
x
els.
I
t
p
r
o
v
id
es
a
b
etter
clar
it
y
f
o
r
th
e
o
b
tain
ed
i
m
ag
e
a
n
d
aid
s
th
e
s
ep
ar
atio
n
o
f
i
m
a
g
e
u
s
i
n
g
d
is
ti
n
g
u
i
s
h
ab
le
f
ea
t
u
r
es
o
f
th
e
lea
f
i
m
a
g
e.
An
ex
a
m
p
le
o
f
t
h
e
o
u
tp
u
t
o
f
K
Me
an
s
c
lu
s
ter
in
g
f
o
r
a
lea
f
i
n
f
ec
ted
w
it
h
B
ac
ter
ial
L
ea
f
B
lig
h
t
(
k)
,
Sep
to
r
ia
B
r
o
w
n
s
p
o
t
(
l)
,
an
d
B
ea
n
leaf
p
o
d
m
o
ttle(
m
)
d
is
ea
s
e
is
s
h
o
wn
in
f
i
g
u
r
e
5
(
k
-
m
)
.
(
k
)
(
l)
(
m
)
Fig
u
r
e
5
.
E
x
tr
ac
tin
g
t
h
e
leaf
ar
ea
f
o
r
B
ac
ter
ial
L
ea
f
B
lig
h
t (
k
)
,
Sep
to
r
ia
B
r
o
w
n
s
p
o
t
(
l)
,
an
d
B
ea
n
leaf
p
o
d
m
o
ttle (
m
)
(
r
ef
er
e
n
ce
i
m
a
g
e
)
5
.
5.
Su
btr
a
ct
ing
T
he
Clus
t
er
ed
L
ea
f
I
m
a
g
e
F
ro
m
T
he
B
a
s
e
I
m
a
g
e.
(
n
)
(
o
)
(
p
)
Fig
u
r
e
6
.
T
h
e
Fin
al
C
l
u
s
ter
ed
A
r
ea
C
o
n
tai
n
in
g
T
h
e
I
n
f
ec
ted
A
r
ea
Fo
r
B
ac
ter
ial
L
ea
f
B
lig
h
t
(d
)
,
Sep
to
r
ia
B
r
o
w
n
Sp
o
t
(
e)
,
a
n
d
B
ea
n
L
ea
f
P
o
d
Mo
ttle.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Gra
d
in
g
o
f S
o
yb
ea
n
Lea
f D
is
ea
s
e
B
a
s
ed
o
n
S
eg
men
ted
I
ma
g
e
Usi
n
g
K
-
mea
n
s
(
S
a
ch
in
B
a
l
kris
h
n
a
J
.
)
19
T
h
e
f
in
al
cl
u
s
ter
i
n
g
i
s
d
o
n
e
b
y
s
u
b
tr
ac
tin
g
th
e
r
e
f
er
en
ce
i
m
ag
e
f
r
o
m
t
h
e
b
ase
i
m
a
g
e
f
o
r
m
ed
f
r
o
m
co
n
v
o
lu
tin
g
th
e
cl
u
s
ter
o
b
tain
ed
f
r
o
m
f
ig
4
w
it
h
th
e
ac
q
u
ir
e
d
im
a
g
e.
T
h
e
ad
v
an
tag
e
o
f
th
i
s
alg
o
r
ith
m
is
th
a
t
it
g
iv
e
s
h
i
g
h
p
r
ec
is
io
n
w
i
th
lo
w
o
p
er
atin
g
ti
m
e.
T
h
e
f
in
al
clu
s
ter
ed
im
a
g
e
s
h
o
w
in
g
th
e
B
a
cter
ial
L
ea
f
B
lig
h
t
(
n
)
,
Sep
to
r
ia
B
r
o
w
n
s
p
o
t
(
o
)
,
a
n
d
B
ea
n
leaf
p
o
d
m
o
ttle (
p
)
in
f
ig
u
r
e
6
(
n
-
p
)
.
T
h
e
o
v
er
all
f
lo
w
o
f
th
e
p
r
o
g
r
a
m
ca
n
b
e
s
u
m
m
ar
ized
w
it
h
t
h
e
f
o
llo
w
in
g
s
tep
s
.
Step
1
: A
cq
u
ir
i
n
g
th
e
i
m
a
g
e.
Step
2
:
Sto
r
in
g
t
h
e
R
OI
as th
e
b
ase
i
m
a
g
e
to
b
e
clu
s
ter
ed
f
o
r
f
u
r
t
h
er
o
p
er
atio
n
s
.
Step
3
: Cl
u
s
ter
to
ex
tr
ac
t u
s
ef
u
l le
af
ar
ea
f
r
o
m
t
h
e
R
OI
Step
4
:
Sto
r
in
g
th
e
lea
f
i
m
a
g
e
o
b
tain
ed
af
ter
ap
p
ly
i
n
g
t
h
e
clu
s
ter
f
ie
ld
an
d
u
s
i
n
g
it
a
s
r
ef
er
en
ce
i
m
a
g
e.
Step
5
: Su
b
tr
ac
tin
g
t
h
e
r
ef
er
en
ce
i
m
ag
e
f
r
o
m
t
h
e
b
ase
i
m
ag
e.
6.
RE
SU
L
T
a
n
d CO
NCL
USI
O
N
A
s
u
itab
le
g
r
a
y
le
v
el
cl
u
s
ter
s
u
s
ed
to
o
b
tain
u
s
ef
u
l
lea
f
ar
ea
.
Fro
m
th
e
f
i
g
u
r
e
it
ca
n
b
e
s
ee
n
th
at
t
h
e
leaf
r
eg
io
n
ca
n
b
e
w
ell
d
etec
t
ed
an
d
af
ter
s
u
b
tr
ac
ti
n
g
th
e
c
lu
s
ter
ed
lea
f
i
m
a
g
e
f
r
o
m
t
h
e
b
ase
i
m
a
g
e
d
is
ea
s
e
r
eg
io
n
ca
n
b
e
w
ell
d
etec
ted
.
I
t
ca
n
b
e
s
ee
n
f
r
o
m
th
e
f
i
g
u
r
e
t
h
at
alth
o
u
g
h
s
o
m
e
v
ei
n
s
ca
n
b
e
d
etec
ted
,
th
e
y
ca
n
b
e
d
ea
lt a
s
n
o
is
e
s
i
n
ce
t
h
e
y
ar
e
s
ca
tter
ed
an
d
t
h
eir
u
n
it a
r
ea
is
s
m
all
co
m
p
ar
ed
to
th
e
les
io
n
ca
s
e.
T
o
s
elec
t th
e
ap
p
r
o
p
r
i
ate
cir
cu
lar
s
tr
u
ctu
r
e
ele
m
e
n
ts
to
u
n
s
ea
l
to
o
b
tain
th
e
f
i
n
al
cl
u
s
ter
ed
ar
ea
co
n
tai
n
i
n
g
th
e
i
n
f
ec
ted
ar
e
a
i
m
a
g
e
o
f
lesi
o
n
.
Af
ter
f
i
n
al
cl
u
s
t
u
r
i
n
g
t
h
e
n
u
m
b
er
o
f
p
ix
el
s
∑
(
)
in
th
e
d
esea
s
e
r
eg
io
n
is
3
3
4
3
0
an
d
th
e
n
u
m
b
er
o
f
p
ix
els
∑
(
)
in
th
e
leaf
r
eg
io
n
is
144704
f
o
r
(
B
ac
ter
ial
L
ea
f
B
lig
h
t)
.
T
h
u
s
it
ca
n
b
e
ca
lcu
lated
th
at
th
e
r
atio
DS
o
f
th
e
d
is
ea
s
ed
an
d
lea
f
ar
ea
i
s
0
.
2
3
1
an
d
i
ts
s
e
v
er
it
y
is
2
3
.
1
0
%
.
an
d
d
is
ea
s
e
s
ca
le
ra
t
ing
i
s
5
A
cc
o
r
d
in
g
to
t
h
e
g
r
ad
e
tab
le,
as
t
h
e
f
o
llo
w
i
n
g
tab
le
1
,
o
f
t
h
e
s
o
y
b
ea
n
lea
f
d
i
s
ea
s
e
p
r
o
v
i
d
ed
b
y
t
h
e
li
ter
atu
r
e
[
4
]
[
5
]
[
6
]
,
th
e
d
is
e
s
ed
s
e
v
er
it
y
is
lie
s
b
et
w
ee
n
1
0
.
1
–
2
5
%
a
nd
he
nce
dis
ea
s
e
s
ca
le
ra
t
in
g
(
G
ra
de)
is
5
a
f
te
r
p
r
o
g
r
am
m
i
n
g
to
ch
ec
k
u
p
th
e
tab
le.
Su
b
s
eq
u
e
n
tl
y
,
te
n
i
m
a
g
es
–
o
f
ar
ea
d
iag
r
a
m
k
e
y
f
o
r
as
s
e
s
s
m
e
n
t
o
f
b
ac
ter
ial
lea
f
b
lig
h
t,
Sep
to
r
ia
b
r
o
w
n
leaf
s
p
o
t
an
d
B
ae
an
lef
p
o
d
m
o
ttle
m
o
s
aic
v
ir
u
s
w
er
e
test
ed
an
d
ca
lcu
la
ted
DS
v
al
u
e
b
y
i
m
a
g
e
an
al
y
s
is
.
An
al
y
s
is
o
f
t
h
e
ar
ea
d
iag
r
a
m
k
e
y
w
as a
n
al
y
ze
d
b
y
i
m
a
g
es p
r
o
ce
s
s
i
n
g
n
u
m
b
er
o
f
p
ix
el
lie
s
in
d
is
esed
ar
ea
a
n
d
leaf
r
eg
io
n
ar
ea
b
u
t
p
er
ce
n
tag
e
o
f
i
n
f
ec
t
co
n
s
id
er
ab
ly
ap
p
r
o
x
ia
m
te
esp
ec
iall
y
le
v
els
o
f
1
–
7
(
T
ab
le
1
)
.
T
h
e
im
a
g
e
a
n
al
y
s
es
w
er
e
u
s
ed
f
u
r
t
h
er
clas
s
if
icatio
n
o
f
t
h
e
s
ev
er
it
y
lev
el
s
.
T
ab
le
1
.
So
y
b
ea
n
L
ea
f
D
is
ea
s
e
Sev
er
it
y
Scale
R
at
in
g
[
4
]
D
i
se
a
se
S
c
a
l
e
Ra
t
i
n
g
D
i
se
a
se
S
e
v
e
r
i
t
y
D
e
scri
p
t
i
o
n
0
--
N
o
l
e
si
o
n
s/
sp
o
t
s
1
1%
l
e
a
f
a
r
e
a
c
o
v
e
r
e
d
w
i
t
h
l
e
si
o
n
s/
s
p
o
t
s
3
1
.
1
-
1
0
%
l
e
a
f
a
r
e
a
c
o
v
e
r
e
d
w
i
t
h
l
e
si
o
n
s/
s
p
o
t
s,
n
o
sp
o
t
s o
n
st
e
m
5
1
0
.
1
–
2
5
%
l
e
a
f
a
r
e
a
c
o
v
e
r
e
d
w
i
t
h
l
e
si
o
n
s/
s
p
o
t
s,
n
o
d
e
f
o
l
i
a
t
i
o
n
;
l
i
t
t
l
e
d
a
m
a
g
e
7
2
5
.
1
–
5
0
%
l
e
a
f
a
r
e
a
c
o
v
e
r
e
d
w
i
t
h
l
e
si
o
n
s/
sp
o
t
s;
so
me
l
e
a
v
e
s
d
r
o
p
;
d
e
a
t
h
o
f
f
e
w
p
l
a
n
t
s;
d
a
m
a
g
e
c
o
n
sp
i
c
u
o
u
s
9
5
0
%
o
f
A
b
o
v
e
M
o
r
e
t
h
a
n
5
0
%
a
r
e
a
c
o
v
e
r
e
d
,
l
e
si
o
n
s/
sp
o
t
s
v
e
r
y
c
o
mm
o
n
o
n
a
l
l
p
a
r
t
s
,
d
e
f
o
l
i
a
t
i
o
n
c
o
mm
o
n
;
d
e
a
t
h
o
f
p
l
a
n
t
s
c
o
mm
o
n
;
d
a
mag
e
mo
r
e
t
h
a
n
5
0
%.
6
.
1
.
Sev
er
it
y
E
s
t
i
m
a
t
io
n
Dis
ea
s
e
s
e
v
er
it
y
is
t
h
e
lesi
o
n
ar
ea
o
f
th
e
leav
es
s
h
o
w
i
n
g
s
y
m
p
to
m
s
o
f
s
p
o
t
d
is
ea
s
e
an
d
it
is
m
o
s
t
o
f
ten
e
x
p
r
ess
ed
as
a
p
er
ce
n
ta
g
e
[
6
]
.
T
h
e
d
is
ea
s
e
s
ev
er
it
y
o
f
t
h
e
s
o
y
b
ea
n
lea
v
es
i
s
m
ea
s
u
r
ed
b
y
co
m
p
ar
i
n
g
t
h
e
n
u
m
b
er
o
f
i
n
f
ec
ted
p
ix
el
lesi
o
n
ar
ea
w
i
th
t
h
e
to
tal
p
ix
el
s
o
f
leaf
ar
ea
f
r
o
m
t
h
e
s
eg
m
e
n
ted
i
m
a
g
e
[
7
]
[
1
2
]
[
1
3
]
.
T
h
e
lesi
o
n
p
er
ce
n
tag
e
o
f
lea
f
i
s
co
m
p
u
ted
u
s
i
n
g
eq
u
atio
n
(
5
)
.
∑
(
)
∑
(
)
∑
(
)
∑
(
)
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
(
5
)
Hen
ce
;
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
5
,
No
.
1
,
Ma
r
ch
2
0
1
6
:
1
3
–
21
20
W
h
er
e,
DS
is
lesi
o
n
o
f
d
is
ea
s
e
s
ev
er
it
y
is
to
tal
p
ix
el
in
d
is
ea
s
ed
ar
ea
o
f
s
eg
m
e
n
ted
lesi
o
n
,
an
d
is
to
tal
p
ix
el
o
f
lea
f
ar
ea
.
Fig
u
r
e
7
(
q
-
s
)
s
h
o
w
s
esti
m
ated
s
o
y
b
e
n
d
is
ea
s
e
s
e
v
er
ities
w
i
th
its
s
ca
le
r
atin
g
f
o
r
B
ac
ter
ial
L
ea
f
B
li
g
h
t
(
DS
=
2
3
.
1
0
%
&
G
ra
de=
5
)
.
(
g
)
Sep
t
o
r
ia
B
r
o
w
n
s
p
o
t
(
D
S=
2
6
.
2
0
%
&
G
ra
de=
7
)
.
(
h
)
an
d
B
ea
n
leaf
p
o
d
m
o
ttle
(
DS
=
4
4
.
1
6
%
& G
ra
de=
7)
(
i)
.
(
q
)
(r)
(
s
)
Fig
u
r
e7
.
E
s
tia
m
ted
d
is
ea
s
ed
s
ev
er
it
y
a
n
d
its
s
ca
le
r
atin
g
f
o
r
:
B
ac
ter
ial
L
ea
f
B
lig
h
t (
q
)
,
Sep
to
r
ia
B
r
o
w
n
Sp
o
t
(
r
)
an
d
B
ea
n
leaf
p
o
d
m
o
ttle(
s
)
.
CO
NCLU
SI
O
N
A
d
i
g
ital
i
m
ag
e
a
n
al
y
s
i
s
tech
n
iq
u
e
p
r
o
p
o
s
ed
in
th
is
w
o
r
k
is
d
ev
elo
p
ed
to
m
ea
s
u
r
e
p
er
ce
n
tag
e
o
f
s
ev
er
it
y
f
o
r
,
b
ac
ter
ial
lea
f
b
li
g
h
t
Sep
ter
o
ial
b
r
o
w
n
leaf
s
p
o
t,
an
d
b
ea
n
leaf
p
o
d
m
o
ttle
,
s
o
y
b
ea
n
d
is
ea
s
e
s
r
esep
ec
tiv
el
y
.
I
n
t
h
e
s
ev
er
i
t
y
est
i
m
a
tio
n
,
w
id
er
le
s
io
n
r
esu
lt
s
i
n
h
i
g
h
er
s
ev
er
it
y
e
s
t
i
m
atio
n
.
T
h
e
n
e
w
tech
n
iq
u
e
h
a
s
r
esu
l
ted
h
i
g
h
ac
cu
r
ac
y
in
id
e
n
ti
f
y
i
n
g
s
o
y
b
ea
n
lea
f
d
is
ea
s
e
s
co
r
in
g
g
r
ad
e
w
it
h
s
e
v
er
it
y
esti
m
atio
n
s
f
o
r
b
ac
ter
ial
lea
f
b
lig
h
t
(
DS
=
2
3
.
1
0
%
&
G
ra
de
=
5
)
,
Sep
ter
o
ial
b
r
o
w
n
lea
f
s
p
o
t
(
DS=
2
6
.
2
0
%
&
G
ra
d
e=
7
)
an
d
b
ea
n
leaf
p
o
d
m
o
ttle
(
D
S=
4
4
.
1
6
%
&
G
ra
d
e=
7
)
.
Ma
n
u
al
tec
h
n
iq
u
e
r
e
f
f
e
r
ed
to
m
ea
s
u
r
e
t
h
e
p
er
ce
n
tag
e
o
f
d
is
ea
s
e
s
e
v
er
it
y
o
f
ar
ea
d
iag
r
a
m
k
e
y
f
o
u
n
d
t
h
at
v
al
u
es
ap
p
r
o
x
ia
m
ate
co
r
r
es
p
o
n
d
s
to
esti
m
ated
class
i
f
ied
cr
iter
ia
v
al
u
e.
C
o
m
p
ar
ativ
e
ass
e
s
s
m
e
n
t
r
es
u
lts
s
h
o
w
ed
a
g
o
o
d
ag
r
ee
m
e
n
t
b
et
wee
n
th
e
n
u
m
b
er
s
o
f
p
er
ce
n
tag
e
s
ca
le
g
r
ad
in
g
o
b
tain
ed
b
y
m
an
u
al
s
co
r
i
n
g
a
n
d
b
y
i
m
a
g
e
an
al
y
s
is
.
C
o
m
p
a
r
ed
to
th
r
esh
o
ld
in
g
tech
n
iq
u
e
c
lu
s
ter
in
g
k
m
ea
n
s
p
r
o
v
es
s
i
m
p
le
an
d
ef
f
ec
ti
v
e
in
d
eter
m
i
n
i
n
g
t
h
e
i
n
f
ec
ted
ar
ea
w
ith
r
ed
u
ce
d
r
eq
u
ir
e
m
en
t
o
f
m
a
n
u
al
cl
u
s
ter
s
elec
tio
n
.
T
h
e
u
s
a
g
e
o
f
p
r
o
p
o
s
ed
i
m
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
f
o
r
p
lan
t
d
is
ea
s
e
d
eg
r
ee
g
r
ad
in
g
w
ill
h
elp
to
eli
m
i
n
ate
s
th
e
s
u
b
j
ec
tiv
it
y
o
f
tr
ad
itio
n
al
class
i
f
icat
io
n
m
e
th
o
d
s
an
d
h
u
m
an
-
in
d
u
ce
d
er
r
o
r
s
.
Hen
ce
t
h
is
ap
p
r
o
ac
h
w
ill
b
e
e
f
f
icien
t
f
o
r
es
ti
m
atio
n
o
f
d
is
ea
s
e
s
e
v
er
it
y
a
n
d
ca
u
s
e
to
p
r
o
v
id
e
ac
cu
r
ate
d
ata
f
o
r
d
is
ea
s
e
p
e
s
ticid
e
co
n
tr
o
l
ap
p
licatio
n
.
An
alg
o
r
it
h
m
f
o
r
u
p
d
atin
g
th
e
clu
s
ter
s
th
r
o
u
g
h
iter
atio
n
co
u
ld
f
u
r
t
h
er
i
m
p
r
o
v
e
th
e
o
b
tain
ed
r
esu
lt
s
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
W
e
ac
k
n
o
w
led
g
e
s
u
p
p
o
r
t o
f
t
h
is
w
o
r
k
b
y
Dr
.
C
.
T
.
Ku
m
b
h
a
r
,
Ass
i
s
tan
t
P
r
o
f
ess
o
r
o
f
P
lan
t
P
ath
o
lo
g
y
,
Z
o
n
al
A
g
r
ic
u
lt
u
r
al
R
esear
c
h
Statio
n
o
f
,
S
u
b
-
m
o
n
ta
n
e
Z
o
n
e,
Ko
l
h
ap
u
r
u
n
d
er
Ma
h
at
m
a
P
h
u
le
Kr
i
s
h
i
Vid
y
ap
ee
th
r
ah
u
r
i,
Ma
h
ar
a
s
h
t
r
a
I
n
d
ia.
RE
F
E
R
E
NC
E
S
[1
]
Da
e
Gw
a
n
Kim
,
T
h
o
m
a
s
F
.
Bu
rk
s,
Jia
n
w
e
i
Qin
,
Du
k
e
M
.
B
u
lan
o
n
,
―
Clas
sif
ica
ti
o
n
o
f
g
ra
p
e
f
ru
it
p
e
e
l
d
ise
a
se
s
u
sin
g
c
o
l
o
r
tex
tu
re
f
e
a
tu
re
a
n
a
ly
sis‖
,
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
n
A
g
ric
u
lt
u
re
a
n
d
B
io
l
o
g
ic
a
l
E
n
g
i
n
e
e
rin
g
,
V
o
l
:2
,
No
:3
,
S
e
p
tem
b
e
r
2
0
0
9
.
[2
]
Al
-
Ba
sh
ish
,
D.,
M
.
Bra
ik
a
n
d
S
.
Ba
n
i
-
A
h
m
a
d
,
2
0
1
1
.
―
De
tec
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
lea
f
d
ise
a
se
s
u
sin
g
K
-
m
e
a
n
s
-
b
a
se
d
se
g
m
e
n
tatio
n
a
n
d
n
e
u
r
a
l
n
e
tw
o
rk
s
b
a
se
d
c
las
sif
ic
a
ti
o
n
‖
.
In
f
o
rm
.
T
e
c
h
n
o
l.
J.,
1
0
:
2
6
7
-
2
7
5
.
DO
I:1
0
.
3
9
2
3
/i
tj
.
2
0
1
1
.
2
6
7
.
2
7
5
,
Ja
n
u
a
ry
,
2
0
1
1
.
[3
]
W
.
CIiv
e
Ja
m
e
s,
A
n
il
lu
stra
ted
s
e
ries
o
f
a
ss
e
s
s
m
e
n
t
k
e
y
s
f
o
r
p
lan
t
d
ise
a
se
s,
th
e
ir
p
re
p
a
ra
ti
o
n
a
n
d
u
sa
g
e
'
v
o
l.
5
1
,
n
o
.
2
,
c
a
n
.
p
la
n
t
d
is.
su
rv
.
j
u
n
e
,
7
9
7
7
.
p
p
3
9
-
6
5
.
[4
]
P
a
u
l
V
i
n
c
e
ll
i
a
n
d
Do
n
a
ld
E.
He
r
sh
m
a
n
,
―
A
ss
e
ss
in
g
F
o
li
a
r
Dise
a
se
s
o
f
Co
rn
,
S
o
y
b
e
a
n
s,
a
n
d
W
h
e
a
t
‖
,
P
rin
c
i
p
les
a
n
d
P
ra
c
ti
c
e
s
P
P
F
S
-
M
IS
C
-
0
6
,
2
0
1
1
.
[5
]
S
h
e
n
W
e
izh
e
n
g
a
n
d
W
u
Ya
c
h
u
n
,
―
Gr
a
d
in
g
M
e
th
o
d
o
f
L
e
a
f
S
p
o
t
Dise
a
se
Ba
se
d
o
n
Ima
g
e
Pro
c
e
ss
in
g
,‖
2
0
0
8
IEE
E
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Co
m
p
u
ter S
c
ien
c
e
a
n
d
S
o
f
tw
a
re
En
g
in
e
e
rin
g
.
p
p
.
4
9
1
-
4
9
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Gra
d
in
g
o
f S
o
yb
ea
n
Lea
f D
is
ea
s
e
B
a
s
ed
o
n
S
eg
men
ted
I
ma
g
e
Usi
n
g
K
-
mea
n
s
(
S
a
ch
in
B
a
l
kris
h
n
a
J
.
)
21
[6
]
Dr.S
a
n
jay
B.
P
a
ti
l,
Dr
.
S
.
K.B
h
o
d
h
e
,
―
lea
f
d
ise
a
se
s
e
v
e
rit
y
M
e
a
s
u
re
m
e
n
t
u
sin
g
ima
g
e
P
ro
c
e
ss
in
g
.
‖
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
a
n
d
T
e
c
h
n
o
l
o
g
y
V
o
l.
3
(5
),
2
0
1
1
,
p
p
2
9
7
-
3
0
1
.
[7
]
Ev
y
K
a
m
il
a
h
Ra
tn
a
sa
ri
a
n
d
o
th
e
r
s,
―
su
g
a
rc
a
n
e
lea
f
d
ise
a
se
d
e
tec
ti
o
n
a
n
d
se
v
e
rity
e
stima
ti
o
n
b
a
se
d
o
n
se
g
me
n
ted
sp
o
t
im
a
g
e
”
.
I
EE
E
2
0
1
4
I
n
tern
a
t
io
n
a
l
C
o
n
f
e
re
n
c
e
o
n
In
f
o
rm
a
ti
o
n
,
Co
m
m
u
n
ica
ti
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
y
ste
m
,
p
p
93
-
98.
[8
]
Kitt
ip
o
n
g
P
o
w
b
u
n
t
h
o
rn
&
o
th
e
rs
,
―
Asse
ss
m
e
n
t
o
f
Bro
wn
L
e
a
f
S
p
o
t
Dise
a
se
in
c
a
ss
a
v
a
u
sin
g
Ima
g
e
An
a
lys
is
.
‖
T
h
e
In
tern
a
ti
o
n
a
l
c
o
n
f
e
re
n
c
e
o
f
th
e
T
h
a
i
S
o
c
iety
o
f
A
g
ricu
lt
u
ra
l
En
g
in
e
e
rin
g
2
0
1
2
,
Ch
ian
g
m
a
i,
T
h
a
il
a
n
d
.
[9
]
Ja
y
m
e
G
a
rc
ia
A
rn
a
l
Ba
rb
e
d
o
,
―
Au
to
m
a
ti
c
a
ll
y
M
e
a
su
rin
g
Earl
y
a
n
d
L
a
te
L
e
a
f
S
p
o
t
L
e
sio
n
s in
P
e
a
n
u
t
P
lan
ts
Us
in
g
Dig
it
a
l
Im
a
g
e
P
ro
c
e
ss
in
g
.
[1
0
]
Do
u
g
las
W
.
Jo
h
n
s
o
n
,
L
e
e
H.
T
o
w
n
se
n
d
,
―
k
e
n
tu
c
k
y
in
teg
ra
ted
c
ro
p
m
a
n
a
g
e
m
e
n
t
m
a
n
u
a
l
f
o
r
f
ield
c
ro
p
s
so
y
b
e
a
n
‖
IPM
-
3
.
2
0
0
9
.
[1
1
]
S
riv
a
sta
v
a
,
S
.
K.
a
n
d
G
u
p
ta,
G
.
K.
(2
0
1
0
)
P
ro
c
e
e
d
i
n
g
s
a
n
d
tec
h
n
ica
l
p
ro
g
ra
m
m
e
2
0
0
9
-
1
0
.
Dire
c
to
ra
t
e
o
f
S
o
y
b
e
a
n
Re
se
a
rc
h
,
In
d
o
re
.
p
p
1
-
79
[1
2
]
T
e
jal
D
e
sh
p
a
n
d
e
a
n
d
K.S
.
Ra
g
h
u
v
a
n
sh
i,
―
G
r
a
d
in
g
&
Id
e
n
ti
f
ica
ti
o
n
o
f
Dise
a
s
e
in
P
o
m
e
g
ra
n
a
te
L
e
a
f
a
n
d
F
ru
it
,
‖
(
IJ
CS
IT
)
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
S
c
ien
c
e
a
n
d
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
,
V
o
l
.
5
(3
)
,
2
0
1
4
,
4
6
3
8
-
4
6
4
5
[1
3
]
S
a
n
jee
v
S
S
a
n
n
a
k
k
i,
Vijay
S
Ra
jp
u
ro
h
it
,
V
B
Na
rg
u
n
d
,
e
t.
a
l(2
0
1
1
),
―
L
e
a
f
Dise
a
se
G
r
a
d
in
g
b
y
M
a
c
h
in
e
V
isio
n
a
n
d
F
u
z
z
y
L
o
g
i
c
‖
,
In
t.
J
.
Co
m
p
.
T
e
c
h
.
Ap
p
l
.
,
V
o
l
2
(
5
),
1
7
0
9
-
1
7
1
6
[1
4
]
Am
in
a
Bh
a
ik
a
,
―
Esti
m
a
ti
o
n
o
f
Ye
ll
o
w
Ru
st
in
W
h
e
a
t
Cro
p
Us
in
g
K
-
M
e
a
n
s
S
e
g
m
e
n
tatio
n
,
‖
IJ
S
R
,
VO
L
.
2
.
Iss
u
e
1
2
,
2
0
1
3
.
[1
5
]
M
u
ra
li
Krish
n
a
n
&
Dr.
M
.
G
.
S
u
m
it
ra
,
―
A
No
v
e
l
a
lg
o
rith
m
f
o
r
De
tec
ti
n
g
Ba
c
ter
ia
l
L
e
a
f
S
c
o
rc
h
(
BL
S
)
o
f
S
h
a
d
e
T
re
e
s
Us
in
g
Ima
g
e
Pr
o
c
e
ss
in
g
,
‖
2
0
1
3
IE
EE
1
1
t
h
M
a
lay
sia
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
m
u
n
ica
ti
o
n
s
p
p
.
4
7
4
-
478
[1
6
]
G
.
A
n
th
o
n
y
s
a
n
d
N.
W
ic
k
ra
m
a
ra
c
h
c
h
,
―
An
Ima
g
e
Rec
o
g
n
i
ti
o
n
S
y
ste
m
fo
r
Cro
p
Dise
a
se
Id
e
n
ti
fi
c
a
ti
o
n
o
f
Pa
d
d
y
fi
e
ld
s
i
n
S
ri
L
a
n
k
a
‖
IEE
E
F
o
u
rt
h
In
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
In
d
u
strial
a
n
d
In
f
o
rm
a
ti
o
n
S
y
ste
m
s,
ICIIS
2
0
0
9
,
2
8
-
3
I
De
c
e
m
b
e
r2
0
0
9
,
S
ri
L
a
n
k
a
.
P
P
4
0
3
-
4
0
7
.
[1
7
]
S
.
A
n
a
n
th
i
a
n
d
S
.
V
is
h
n
u
V
a
rth
in
i,
―
De
tec
ti
o
n
a
n
d
c
las
sif
ica
ti
o
n
o
f
p
lan
t
lea
f
d
ise
a
se
s
‖
IJ
RE
S
,
V
o
l
.
2
,
Iss
u
e
.
2
,
IS
S
N:
2
2
4
9
-
3
9
0
5
,
p
p
.
7
6
3
-
7
7
3
.
[1
8
]
A
ja
y
A
.
G
u
rjar
a
n
d
V
iraj
A
.
G
u
l
h
a
n
e
―
Dise
a
s
e
De
t
e
c
ti
o
n
On
Co
tt
o
n
L
e
a
v
e
s
b
y
Ei
g
e
n
f
e
a
tu
re
Re
g
u
lariz
a
ti
o
n
a
n
d
Ex
trac
ti
o
n
T
e
c
h
n
iq
u
e
‖
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
tro
n
ics
,
Co
mm
u
n
ica
ti
o
n
&
S
o
ft
Co
mp
u
ti
n
g
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
(
IJ
ECS
CS
E),
V
o
l
.
1
,
Iss
u
e
.
1
[
1
9
]
P
a
tt
e
rn
Re
c
o
g
n
i
ti
o
n
a
n
d
i
m
a
g
e
a
n
a
l
y
sis.,
Earl
G
o
se
,
Rich
a
rd
Jo
h
n
so
n
b
a
u
g
h
,
S
tev
e
Jo
st ,
P
re
n
t
ice
-
Ha
ll
,
In
d
ia.
P
g
.
2
1
0
-
2
1
9
.
[2
0
]
C
o
n
str
a
in
e
d
K
-
me
a
n
s Cl
u
ste
rin
g
wit
h
B
a
c
k
g
ro
u
n
d
Kn
o
wled
g
e
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
Ei
g
h
tee
n
t
h
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
M
a
c
h
i
n
e
L
e
a
rn
in
g
,
2
0
0
1
,
p
.
5
7
7
-
5
8
4
.
Kiri
W
a
g
sta
,
S
e
th
Ro
g
e
rs ro
g
e
rs@
rtn
a
.
d
a
im
lerc
h
r
y
sle
r.
c
o
m
S
tef
a
n
S
c
h
r
o
e
d
.
B
I
B
L
I
O
G
R
AP
H
Y
O
F
AUT
H
O
RS
M
r.
S
a
c
h
in
.
B.
Ja
d
h
a
v
h
a
s
p
u
rsu
in
g
P
h
.
D
f
ro
m
V
T
U
Blg
a
u
m
a
n
d
a
w
a
rd
e
d
M
.
E
in
El
e
c
tro
n
ics
a
n
d
B
.
E
.
i
n
El
e
c
tro
n
ics
&
T
e
lec
o
m
m
u
n
ica
ti
o
n
f
ro
m
S
h
iv
a
ji
u
n
iv
e
rsity
k
o
lh
a
p
u
r.
C
u
rre
n
tl
y
h
e
is
w
o
rk
in
g
a
s
a
n
A
s
sista
n
t
P
r
o
f
e
ss
o
r
in
De
p
a
rtm
e
n
t
o
f
El
e
c
tr
o
n
ics
&
T
e
lec
o
m
m
u
n
ica
ti
o
n
En
g
in
e
e
rin
g
a
t
B
h
a
ra
ti
v
id
y
a
p
e
e
t
h
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
Ko
lh
a
p
u
r.
He
h
a
s
k
e
e
n
in
tere
st
i
n
t
h
e
f
ield
o
f
I
m
a
g
e
p
ro
c
e
ss
in
g
.
P
r
o
f
.
Dr.
S
a
n
jay
Ba
p
u
so
P
a
ti
l
h
a
s
Aw
a
rd
e
d
P
h
.
D
i
n
su
b
jec
t
o
f
El
e
c
tro
n
ics
&
T
e
le
c
o
m
m
u
n
ica
ti
o
n
,
G
ra
d
u
a
ti
o
n
a
n
d
P
o
st
g
ra
d
u
a
ti
o
n
i
n
El
e
c
tro
n
i
c
s
En
g
in
e
e
rin
g
.
His
f
i
e
ld
o
f
stu
d
y
is
Dig
it
a
l
I
m
a
g
e
P
ro
c
e
ss
in
g
.
His
k
e
e
n
in
tere
st
in
a
p
p
li
c
a
ti
o
n
o
f
i
m
a
g
e
p
ro
c
e
ss
in
g
f
o
r
―
P
re
c
isio
n
F
a
rm
in
g
‖
.
H
e
h
a
d
w
o
rk
e
d
a
s
P
ro
f
e
ss
o
r,
A
ss
ist
a
n
t
p
ro
f
e
ss
o
r
a
n
d
L
e
c
tu
re
r
u
n
d
e
r
P
u
n
e
a
s
we
ll
a
s
S
h
iv
a
ji
Un
iv
e
rc
it
y
K
o
lh
a
p
u
r.
His
to
tal
e
d
u
c
a
ti
o
n
a
s
w
e
ll
a
s
in
d
u
strial
e
x
p
e
ian
c
e
is
a
b
o
u
t
m
o
re
th
a
n
2
4
y
e
a
rs.
Cu
rre
n
tl
y
w
o
rk
in
g
a
s
P
rin
c
i
p
a
l
a
t
M
BT
Ca
m
p
u
s,
Isla
m
p
u
r
.
He
h
a
s
w
rit
ten
se
v
e
ra
l
tec
h
n
ica
l
p
a
p
e
rs
in
re
p
u
ted
i
n
tern
a
t
io
n
a
l
Jo
u
rn
a
l
a
n
d
Co
n
f
e
re
n
c
e
s.
H
e
is
li
f
e
m
e
m
b
e
r
o
f
IS
T
E.
Evaluation Warning : The document was created with Spire.PDF for Python.