I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
,
p
p
.
806
~
811
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i3
.
p
p
8
0
6
-
811
806
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
A
n
A
u
to
ma
tic C
of
fe
e Pla
n
t Dise
ases Ide
nt
i
ficat
i
on
Usi
ng
H
y
b
rid
A
p
pr
oac
hes o
f Im
a
ge Pr
ocessi
ng
a
nd
Decisio
n T
ree
Abrha
m
Deba
s
u M
eng
is
t
u
,
Sef
f
i G
ebey
ehu M
eng
is
t
u
,
Da
g
na
chew
M
elesew
B
ah
ir
Dar
I
n
s
tit
u
te
o
f
T
ec
h
n
o
l
o
g
y
,
Fac
u
lt
y
o
f
C
o
m
p
u
ti
n
g
,
B
ah
ir
Dar
Un
i
v
er
s
it
y
,
E
th
io
p
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
3
,
2
0
1
8
R
ev
i
s
ed
Feb
1
5
,
2
0
1
8
A
cc
ep
ted
Feb
2
2
,
2
0
1
8
Co
f
fe
e
L
e
a
f
Ru
st
(CL
R),
Co
ff
e
e
Be
rr
y
Dis
e
a
se
(CB
D)
a
n
d
Co
f
fe
e
W
il
t
Dise
a
se
(CWD)
a
r
e
th
e
th
re
e
m
a
in
d
ise
a
se
s
th
a
t
a
tt
a
c
k
c
o
ffe
e
p
lan
ts.
T
h
is
p
a
p
e
r
p
re
se
n
ts
t
h
e
id
e
n
t
if
ica
ti
o
n
o
f
th
e
se
ty
p
e
s
d
ise
a
s
e
s
u
sin
g
h
y
b
rid
a
p
p
ro
a
c
h
e
s o
f
im
a
g
e
p
ro
c
e
ss
in
g
a
n
d
d
e
c
isio
n
tree
.
T
h
e
im
a
g
e
s
a
re
t
a
k
e
n
f
ro
m
S
o
u
t
h
e
rn
Et
h
i
o
p
ia,
Jim
m
a
a
n
d
Ze
g
ie.
In
th
is
p
a
p
e
r
b
a
c
k
p
ro
p
a
g
a
ti
o
n
a
rti
f
icia
l
n
e
u
ra
l
n
e
tw
o
rk
(BP
NN
)
a
n
d
d
e
c
isio
n
tree
h
a
d
b
e
e
n
u
se
d
a
s
tec
h
n
i
q
u
e
s;
a
to
tal
o
f
9
1
0
0
im
a
g
e
s
w
e
re
c
o
ll
e
c
ted
.
F
ro
m
th
e
se
,
7
0
%
a
re
u
se
d
fo
r
train
in
g
a
n
d
t
h
e
re
m
a
in
in
g
3
0
%
a
re
u
se
d
f
o
r
tes
ti
n
g
.
I
n
g
e
n
e
ra
l,
9
4
.
5
%
a
c
c
u
ra
c
y
a
c
h
iev
e
d
w
h
e
n
d
e
c
isio
n
tree
a
n
d
B
P
NN
w
it
h
tan
h
a
c
ti
v
a
ti
o
n
f
u
n
c
ti
o
n
a
re
c
o
m
b
in
e
d
.
K
ey
w
o
r
d
s
:
B
P
NN
C
L
R
C
B
D
C
W
D
Dec
is
io
n
tr
ee
Co
p
y
rig
h
t
©
2
0
1
8
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
b
r
h
a
m
Deb
as
u
Me
n
g
i
s
t
u
,
B
ah
ir
Dar
I
n
s
tit
u
te
o
f
T
ec
h
n
o
l
o
g
y
,
Facu
lt
y
o
f
C
o
m
p
u
tin
g
,
B
ah
ir
Dar
Un
iv
er
s
it
y
,
E
t
h
io
p
i
a
.
E
m
ail:
ab
r
h
a
m
d
@
b
d
u
.
ed
u
.
et
1.
I
NT
RO
D
UCT
I
O
N
C
o
f
f
ee
p
lan
t
i
s
a
p
lan
t
w
h
ich
is
g
r
o
w
n
i
n
all
o
v
er
th
e
w
o
r
ld
p
ar
ticu
lar
l
y
in
E
t
h
io
p
ia.
I
n
E
th
io
p
ia
ag
r
icu
l
tu
r
al
s
ec
to
r
p
la
y
s
a
ce
n
tr
al
r
o
le
i
n
t
h
e
ec
o
n
o
m
ic
a
n
d
s
o
cial
li
f
e
o
f
t
h
e
n
atio
n
.
A
r
o
u
n
d
8
0
to
8
5
%
o
f
p
eo
p
le
in
E
th
io
p
ia
ar
e
d
ep
en
d
en
t
i
n
a
g
r
ic
u
lt
u
r
e;
a
m
o
n
g
8
0
t
o
8
5
%
ab
o
u
t
4
0
%
o
f
th
e
s
ec
t
o
r
co
n
tr
ib
u
tes
f
r
o
m
cu
lti
v
atio
n
o
f
co
f
f
ee
[
1
]
.
T
h
e
co
f
f
ee
s
w
h
ic
h
ar
e
f
o
u
n
d
in
E
t
h
io
p
ia
ar
e
A
r
ab
ica
t
y
p
e,
I
n
E
t
h
io
p
ia
co
f
f
ee
g
r
o
w
s
in
e
v
er
y
r
e
g
io
n
o
f
t
h
e
co
u
n
tr
y
b
u
t
m
aj
o
r
ity
ar
e
p
r
o
d
u
ce
d
in
th
e
Or
o
m
ia
R
e
g
io
n
(
6
3
.
7
%)
an
d
in
th
e
So
u
t
h
er
n
Natio
n
s
,
Nat
io
n
alit
ies
(
3
4
.
4
%),
w
it
h
les
s
er
a
m
o
u
n
t
s
i
n
t
h
e
Ga
m
b
ela
R
e
g
io
n
an
d
ar
o
u
n
d
th
e
cit
y
o
f
Dir
e
Da
w
a
[
3
]
.
Gen
er
all
y
i
n
E
t
h
i
o
p
ia
m
u
c
h
o
f
t
h
e
co
f
f
ee
ar
e
p
r
o
d
u
ce
d
in
altitu
d
e
s
b
et
w
e
en
1
,
0
0
0
an
d
2
,
0
0
0
m
eter
s
.
T
h
e
s
p
ec
ies
co
f
f
ee
is
en
d
e
m
ic
to
Af
r
ica
a
n
d
a
n
u
m
b
er
o
f
class
es
ar
e
d
escr
ib
ed
in
W
est,
C
en
tr
al
an
d
E
ast
Af
r
ica
[
2
]
.
B
ec
au
s
e
o
f
co
f
f
ee
d
is
ea
s
e
co
n
s
tr
ai
n
ts
an
d
g
lo
b
al
w
ar
m
in
g
f
ac
to
r
s
o
n
l
y
t
w
o
t
y
p
es
o
f
co
f
f
ee
p
lan
t
ar
e
n
o
w
ad
a
y
s
co
m
m
er
ci
all
y
g
r
o
w
n
w
o
r
ld
w
id
e,
th
e
s
e
a
r
e
C
o
f
f
ee
ca
n
ep
h
o
r
a
(
R
o
b
u
s
ta
)
w
h
ich
ar
e
g
r
o
wn
in
lo
w
la
n
d
s
a
n
d
C
o
f
f
ee
ar
ab
i
ca
(
A
r
ab
ica)
th
at
ar
e
p
r
o
d
u
ce
d
in
h
i
g
h
la
n
d
s
o
f
Af
r
ica.
T
h
e
s
p
ec
ies
o
f
co
f
f
ee
ar
ab
ica
ty
p
e
o
r
ig
in
a
ted
f
r
o
m
E
th
io
p
ia
esp
ec
iall
y
in
t
h
e
p
r
o
v
in
ce
o
f
Ka
f
f
a.
Du
r
i
n
g
1
5
th
ce
n
t
u
r
y
Ye
m
en
tr
ad
er
s
d
is
tr
ib
u
ted
co
f
f
ee
A
r
ab
ica
t
y
p
e
i
n
all
o
v
er
th
e
w
o
r
ld
.
T
o
d
ay
,
t
h
er
e
is
a
f
e
w
r
ai
n
f
o
r
es
ts
i
n
t
h
e
s
o
u
th
w
e
s
t
an
d
s
o
u
th
ea
s
t
E
t
h
io
p
ia
t
h
at
p
r
o
d
u
ce
s
a
co
f
f
ee
p
lan
t
in
a
lar
g
e
v
ar
iet
y
o
f
s
h
ad
e
tr
ee
s
[
3
]
.
C
o
f
f
ee
P
lan
t
d
is
ea
s
e
is
a
d
is
ea
s
e
th
a
t
af
f
ec
ts
co
f
f
e
e
p
lan
ts
o
n
t
h
e
leav
e
s
,
s
te
m
s
an
d
r
o
o
ts
p
ar
ts
n
o
w
ad
a
y
s
co
f
f
ee
p
lan
t
d
is
ea
s
e
s
b
ec
o
m
e
s
cr
itical
p
r
o
b
le
m
a
n
d
ca
n
ca
u
s
e
s
i
g
n
i
f
ican
t
r
ed
u
c
tio
n
i
n
b
o
t
h
q
u
al
it
y
a
n
d
q
u
a
n
tit
y
o
f
a
g
r
icu
ltu
r
al
co
f
f
ee
p
r
o
d
u
cts.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
u
to
ma
tic
C
o
ffee
P
la
n
t D
i
s
ea
s
es I
d
en
tifi
ca
tio
n
Usi
n
g
Hyb
r
id
.
.
.
(
A
b
r
a
h
a
m
Deb
a
s
u
Men
g
is
tu
)
807
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
P
.
R
ev
ath
i
&
M.
He
m
alat
h
a
[
4
]
,
in
th
is
r
esear
c
h
p
ap
er
th
e
au
th
o
r
s
f
o
cu
s
o
n
co
tto
n
i
m
ag
e
th
at
id
en
ti
f
ies
t
h
e
in
f
ec
ted
p
ar
ts
f
r
o
m
a
g
i
v
en
co
tto
n
i
m
a
g
es.
B
esid
es
P
.
R
ev
ath
i
a
n
d
M.
He
m
alat
h
a,
th
e
id
en
ti
f
icatio
n
h
as
t
w
o
p
h
a
s
es.
T
h
e
f
ir
s
t
p
h
ase
i
n
t
h
e
r
esear
ch
is
u
s
i
n
g
ed
g
e
d
etec
tio
n
t
h
is
h
elp
th
e
a
u
t
h
o
r
s
to
d
etec
t
th
e
b
o
r
d
er
o
f
th
e
i
m
a
g
e
af
ter
co
m
p
leti
n
g
ed
g
e
d
etec
ti
o
n
an
al
y
s
i
s
p
h
ase
i
s
co
n
d
u
c
te
d
.
T
h
e
s
ec
o
n
d
p
h
ase
is
t
h
e
clas
s
i
f
icatio
n
o
f
d
is
ea
s
es
u
s
in
g
t
h
e
p
r
o
p
o
s
ed
Ho
m
o
g
en
eo
u
s
P
ix
e
l
C
o
u
n
t
in
g
T
ec
h
n
iq
u
e
f
o
r
C
o
tto
n
Dis
ea
s
e
s
Dete
ctio
n
(
HP
C
C
DD
)
A
l
g
o
r
ith
m
.
Dh
ee
b
A
l
B
as
h
is
h
e
t
al
[
5
]
,
in
th
eir
w
o
r
k
t
h
e
au
t
h
o
r
s
h
av
e
p
r
o
p
o
s
ed
a
f
r
am
e
w
o
r
k
f
o
r
d
etec
tio
n
an
d
class
i
f
icatio
n
o
f
p
lan
t
lea
f
d
is
ea
s
es
th
e
y
also
u
s
ed
K
m
ea
n
s
tech
n
iq
u
es
f
o
r
s
e
g
m
e
n
tat
io
n
.
Fo
r
ex
tr
ac
tin
g
t
h
e
v
alu
e
s
o
f
h
u
e,
i
n
te
n
s
it
y
a
n
d
s
atu
r
atio
n
f
o
r
m
a
g
i
v
e
n
R
GB
in
p
u
t
i
m
a
g
e
s
th
e
a
u
t
h
o
r
s
ar
e
c
o
n
v
er
ted
R
GB
i
n
to
HI
S c
o
lo
r
s
p
ac
e
th
is
h
elp
s
to
c
alcu
late
t
h
e
co
lo
r
o
f
a
g
iv
e
n
i
m
ag
e
s
.
P
r
ak
ash
M.
Ma
i
n
k
ar
&
S
h
r
ee
k
an
t
G
h
o
r
p
ad
e
[
6
]
,
in
th
is
r
ese
ar
ch
,
th
e
a
u
th
o
r
s
p
r
o
v
id
e
s
o
f
t
w
ar
e
b
ased
o
n
i
m
ag
i
n
g
tec
h
n
iq
u
e
s
to
a
u
t
o
m
a
ticall
y
d
etec
t
a
n
d
c
la
s
s
i
f
y
p
lan
t
lea
f
d
is
ea
s
e
s
.
Si
m
ilar
l
y
th
e
a
u
t
h
o
r
s
i
n
cl
u
d
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es s
tar
tin
g
f
r
o
m
i
m
a
g
e
ac
q
u
i
s
itio
n
to
class
if
icatio
n
.
P
r
em
alat
h
a.
V
etal
[
7
]
,
in
t
h
i
s
p
ap
er
,
th
e
au
th
o
r
s
h
a
v
e
u
s
ed
s
p
atial
FC
M
&
P
NN
(
F
u
zz
y
C
-
Me
an
s
a
n
d
P
r
o
b
ab
ilis
tic
n
eu
r
al
n
et
w
o
r
k
)
o
n
co
tto
n
p
lan
t
to
id
en
ti
f
y
th
e
d
is
ea
s
e
in
co
tto
n
p
la
n
t.
T
h
e
au
th
o
r
s
h
av
e
u
s
ed
i
m
a
g
e
ac
q
u
is
itio
n
d
e
v
ices
to
ac
q
u
ir
e
i
m
ag
e
s
a
n
d
t
h
e
i
m
a
g
e
s
ar
e
t
h
e
n
s
u
b
j
ec
ted
to
p
r
e
-
p
r
o
ce
s
s
in
g
a
n
d
n
o
is
e
f
ilter
i
n
g
m
ec
h
a
n
is
m
s
f
o
r
a
g
iv
en
i
m
ag
e
s
t
h
e
a
u
t
h
o
r
s
h
av
e
also
u
s
e
s
p
atial
F
C
M
c
lu
s
ter
in
g
m
eth
o
d
s
f
o
r
s
eg
m
e
n
ti
n
g
t
h
e
g
iv
e
n
i
m
ag
e.
Nik
ita
R
is
h
i
&
J
ag
b
ir
Si
n
g
h
Gill
[
8
]
,
th
e
au
t
h
o
r
s
h
a
v
e
u
s
ed
w
h
ea
t
an
d
g
r
ap
e
d
is
ea
s
es
b
ased
o
n
d
if
f
er
e
n
t
tec
h
n
iq
u
es
t
h
e
s
e
tec
h
n
iq
u
es
i
n
cl
u
d
e
Ots
u
m
et
h
o
d
,
i
m
a
g
e
co
m
p
r
ess
io
n
,
i
m
ag
e
c
r
o
p
p
in
g
a
n
d
i
m
ag
e
n
o
is
e
r
e
m
o
v
al
f
o
r
clas
s
if
icatio
n
th
e
y
u
s
ed
n
e
u
r
al
n
et
w
o
r
k
s
i
n
clu
d
i
n
g
b
ac
k
p
r
o
p
ag
atio
n
(
B
P
)
n
et
w
o
r
k
s
,
r
ad
ial
b
asis
f
u
n
ctio
n
(
R
B
F)
n
e
u
r
al
n
et
w
o
r
k
s
;
g
en
er
alize
d
r
e
g
r
ess
io
n
n
e
t
w
o
r
k
s
(
GR
N
Ns)
a
n
d
p
r
o
b
a
b
ilis
tic
n
eu
r
al
n
et
w
o
r
k
s
(
P
NNs)
to
d
iag
n
o
s
e
w
h
ea
t a
n
d
g
r
ap
e
d
is
ea
s
es.
I
n
r
esear
ch
[
9
]
,
th
e
au
th
o
r
s
’
p
r
esen
ts
a
n
ass
es
s
m
en
t
o
n
m
et
h
o
d
s
th
at
in
d
icate
s
th
e
u
s
e
d
ig
ital
i
m
ag
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
e
s
o
n
ag
r
i
cu
lt
u
r
e
to
d
etec
t
q
u
an
tify
an
d
class
i
f
y
p
la
n
t
d
is
ea
s
e
s
f
r
o
m
d
i
g
ital
i
m
ag
e
s
in
t
h
e
v
is
ib
le
s
p
ec
tr
u
m
.
Haig
u
an
g
W
an
g
,
etal
[
1
0
]
,
i
n
th
eir
w
o
r
k
p
lan
t
d
is
ea
s
e
id
en
ti
f
icatio
n
b
ased
o
n
i
m
ag
e
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
th
e
au
th
o
r
s
e
x
tr
ac
te
d
th
r
ee
g
r
o
u
p
s
o
f
f
ea
t
u
r
es
i.e
.
co
lo
r
,
s
h
ap
e
an
d
tex
tu
r
e
f
ea
t
u
r
es
an
d
t
h
e
y
u
s
ed
p
r
in
cip
al
co
m
p
o
n
en
t
a
n
al
y
s
i
s
(
P
C
A
)
f
o
r
r
ed
u
cin
g
t
h
e
d
i
m
e
n
s
io
n
s
o
f
f
ea
t
u
r
e
s
p
ac
e
an
d
th
en
n
e
u
r
al
n
et
w
o
r
k
s
in
cl
u
d
in
g
b
ac
k
p
r
o
p
ag
atio
n
(
B
P
)
n
et
w
o
r
k
w
er
e
u
s
ed
as
th
e
class
i
f
ier
s
to
id
en
ti
f
y
w
h
ea
t
d
is
ea
s
es
an
d
g
r
ap
e
d
is
ea
s
es,
r
esp
ec
ti
v
el
y
.
I
n
r
esear
ch
[
1
1
]
,
th
e
au
t
h
o
r
u
s
ed
t
h
e
tech
n
iq
u
e
s
o
f
m
ac
h
i
n
e
v
i
s
io
n
t
h
at
ar
e
ap
p
lied
to
ap
p
lied
to
ag
r
icu
l
tu
r
al
s
cie
n
ce
an
d
i
t h
a
s
g
r
ea
t p
er
s
p
ec
tiv
e
e
s
p
ec
iall
y
i
n
th
e
p
la
n
t p
r
o
tectio
n
f
ield
,
w
h
i
ch
u
lti
m
atel
y
lead
s
to
cr
o
p
s
m
an
a
g
e
m
e
n
t.
S.
P
h
ad
ik
ar
,
etal
[
1
2
]
in
th
is
r
esear
ch
p
ap
er
th
e
au
th
o
r
s
u
s
ed
SVM
an
d
B
a
y
es
o
n
r
ice
d
is
ea
s
es
d
etec
tio
n
.
I
n
th
e
w
o
r
k
o
f
th
e
a
u
th
o
r
s
,
an
a
u
to
m
a
ted
s
y
s
te
m
h
as
b
ee
n
d
ev
elo
p
ed
to
class
if
y
t
h
e
leaf
b
r
o
w
n
s
p
o
t
an
d
th
e
lea
f
b
last
d
is
ea
s
e
s
o
f
r
i
ce
p
lan
t b
ased
o
n
th
e
m
o
r
p
h
o
l
o
g
ical
ch
a
n
g
e
s
o
f
t
h
e
p
lan
t
s
.
Hab
ta
m
u
Mi
n
asie
[
1
3
]
,
in
t
h
is
r
esear
ch
p
ap
er
t
h
e
au
th
o
r
s
h
o
w
n
t
h
at
t
h
e
ap
p
licatio
n
o
f
i
m
a
g
e
p
r
o
ce
s
s
in
g
o
n
id
en
tific
atio
n
s
o
f
E
th
io
p
ia
n
co
f
f
ee
b
ea
n
s
b
ased
o
n
th
e
ir
g
r
o
w
in
g
ar
ea
i
n
v
ie
w
o
f
t
h
i
s
t
h
e
au
th
o
r
s
c
lass
if
y
d
i
f
f
er
e
n
t
v
ar
ieties
o
f
E
th
io
p
ia
n
co
f
f
ee
b
a
s
ed
o
n
th
e
ir
g
r
o
w
i
n
g
r
e
g
io
n
s
th
at
ar
e
f
o
u
n
d
in
E
th
io
p
ia
(
B
a
le,
Har
ar
,
J
im
m
a,
L
i
m
u
,
Sid
a
m
o
an
d
W
eleg
a)
wh
ich
ar
e
p
o
p
u
lar
an
d
w
id
el
y
p
l
an
ted
in
E
t
h
io
p
ia.
A
b
r
h
a
m
Deb
a
s
u
e
tal
[
1
4
]
,
in
th
eir
w
o
r
k
e
n
ti
tled
as
“
E
t
h
io
p
ian
C
o
f
f
ee
P
lan
t
Dis
ea
s
es
R
e
co
g
n
itio
n
B
ased
o
n
I
m
ag
in
g
a
n
d
m
ac
h
i
n
e
lear
n
i
n
g
”
t
h
e
au
th
o
r
s
h
av
e
s
h
o
w
n
t
h
at
t
h
e
ap
p
licatio
n
o
f
i
m
ag
e
p
r
o
ce
s
s
in
g
an
d
m
ac
h
in
e
lear
n
i
n
g
to
id
en
ti
f
y
co
f
f
ee
lea
f
d
is
ea
s
es
b
e
s
id
es,
th
e
au
t
h
o
r
s
h
a
v
e
u
s
ed
th
e
co
m
b
in
ed
ap
p
r
o
ac
h
es o
f
SOM
an
d
R
B
F
f
o
r
th
e
id
en
ti
f
icat
io
n
o
f
E
t
h
io
p
ian
co
f
f
ee
p
la
n
t d
is
ea
s
e
s
.
I
n
r
esear
ch
[
1
5
]
,
th
e
a
u
t
h
o
r
s
s
h
o
w
ed
th
a
t
Ob
j
ec
t
Dete
ctio
n
u
s
i
n
g
Haa
r
C
a
s
ca
d
e
C
lasi
f
i
er
w
id
el
y
ap
p
lied
in
s
ev
er
al
d
ev
ice
s
an
d
a
p
p
licatio
n
s
as a
m
ed
i
u
m
o
f
i
n
ter
ac
tio
n
b
et
w
ee
n
h
u
m
a
n
an
d
co
m
p
u
ter
.
I
n
r
esear
ch
[
1
6
]
,
th
e
au
th
o
r
f
o
cu
s
es
o
n
w
o
o
d
ch
ar
ac
ter
izatio
n
th
at
in
c
lu
d
es
:
h
ar
d
n
es
s
,
s
tr
en
g
t
h
,
clea
v
ag
e
r
e
s
is
ta
n
ce
,
etc.
Am
o
n
g
t
h
ese
p
r
o
p
er
ties
th
er
e
th
at
ca
n
b
e
m
ea
s
u
r
ed
o
r
esti
m
ated
b
y
v
is
u
al
o
b
s
er
v
atio
n
o
n
cr
o
s
s
-
s
ec
tio
n
al
ar
ea
s
o
f
w
o
o
d
.
E
d
g
e
d
etec
tio
n
is
ap
p
lied
to
th
e
w
o
o
d
test
i
m
ag
e
s
w
it
h
t
h
e
ai
m
to
im
p
r
o
v
i
n
g
th
e
ch
ar
ac
ter
is
t
ic
s
o
f
w
o
o
d
f
ib
er
s
s
o
as
to
m
ak
e
it
ea
s
ier
to
d
is
tin
g
u
i
s
h
t
h
eir
q
u
alit
y
.
T
h
e
au
th
o
r
s
u
s
ed
Naï
v
e
B
a
y
es c
las
s
i
f
ie
r
f
o
r
class
if
icatio
n
.
I
n
r
esear
ch
[
1
7
]
,
th
e
r
esear
c
h
er
s
s
h
o
w
ed
th
a
t
t
h
e
r
ice
v
ar
iet
y
an
d
t
h
e
q
u
a
lit
y
o
f
r
ic
e
lead
to
o
r
ig
in
ali
t
y
ce
r
ti
f
icatio
n
o
f
r
ice
b
y
ex
is
ti
n
g
in
s
tit
u
tio
n
s
.
T
h
e
au
th
o
r
s
d
ev
elo
p
ed
a
s
y
s
te
m
u
s
ed
as
a
to
o
l
to
id
en
ti
f
y
r
ice
v
ar
ieties.
I
d
en
t
if
icatio
n
p
r
o
ce
s
s
w
as
p
er
f
o
r
m
ed
b
y
an
al
y
zi
n
g
r
ice
i
m
a
g
es
u
s
i
n
g
i
m
a
g
e
p
r
o
ce
s
s
in
g
.
T
h
e
an
al
y
ze
d
f
e
atu
r
es
f
o
r
id
en
tific
atio
n
co
n
s
is
ted
o
f
s
i
x
co
lo
r
f
ea
tu
r
es,
f
o
u
r
m
o
r
p
h
o
lo
g
ica
l
f
ea
t
u
r
es,
an
d
t
w
o
te
x
t
u
r
e
f
ea
t
u
r
es.
C
las
s
i
f
ier
u
s
ed
L
V
Q
n
e
u
r
al
n
et
w
o
r
k
al
g
o
r
it
h
m
.
I
d
en
t
if
i
ca
tio
n
r
es
u
lts
u
s
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
8
0
6
–
8
1
1
808
a
co
m
b
in
atio
n
o
f
al
l f
ea
t
u
r
es
g
av
e
av
er
a
g
e
ac
cu
r
ac
y
o
f
7
0
,
3
%
w
it
h
t
h
e
h
i
g
h
est c
lass
if
ica
ti
o
n
ac
cu
r
ac
y
lev
el
o
f
9
6
,
6
% f
o
r
Me
n
tik
W
an
g
i a
n
d
t
h
e
lo
w
e
s
t c
las
s
i
f
icatio
n
ac
cu
r
a
c
y
o
f
3
0
%
f
o
r
C
ilo
s
ar
i.
I
n
r
esear
ch
[
1
8
]
,
in
t
h
eir
w
o
r
k
en
titl
ed
as
“
C
o
tto
n
P
ests
a
n
d
Dis
ea
s
es
Dete
c
tio
n
B
ased
o
n
I
m
a
g
e
P
r
o
ce
s
s
in
g
”
th
e
au
to
r
s
h
a
v
e
s
h
o
w
n
th
at
t
h
r
ee
d
if
f
er
en
t
co
lo
r
m
o
d
els
f
o
r
ex
tr
ac
ti
n
g
t
h
e
d
a
m
ag
ed
i
m
a
g
e
f
r
o
m
co
tto
n
leaf
i
m
a
g
es
w
er
e
i
m
p
le
m
en
ted
,
n
a
m
el
y
R
GB
co
lo
r
m
o
d
el,
HSI
co
lo
r
m
o
d
el,
an
d
Y
C
b
C
r
co
lo
r
m
o
d
el.
T
h
e
r
atio
o
f
d
a
m
a
g
e
(
γ
)
w
a
s
c
h
o
s
en
as
f
ea
t
u
r
e
to
m
ea
s
u
r
e
t
h
e
d
eg
r
ee
o
f
d
a
m
ag
e
w
h
ich
ca
u
s
ed
b
y
d
is
ea
s
es
o
r
p
ests
.
T
h
is
p
ap
er
also
s
h
o
w
s
th
e
co
m
p
ar
is
o
n
o
f
th
e
r
es
u
lt
s
o
b
tain
ed
b
y
t
h
e
i
m
p
le
m
e
n
ti
n
g
in
d
i
f
f
er
e
n
t
co
lo
r
m
o
d
el
s
,
th
e
co
m
p
ar
is
o
n
o
f
r
esu
lt
s
s
h
o
w
s
g
o
o
d
ac
cu
r
ac
y
i
n
b
o
th
co
lo
r
m
o
d
els
an
d
YC
b
C
r
co
lo
r
s
p
ac
e
is
co
n
s
id
er
ed
as th
e
b
est co
lo
r
m
o
d
el
f
o
r
ex
tr
ac
tin
g
th
e
d
a
m
a
g
e
d
im
a
g
e
s.
3.
RE
S
E
ARCH
M
E
T
H
O
DS
T
o
co
llect
th
e
d
ata
s
et
o
f
co
f
f
ee
p
lan
t
d
is
ea
s
e
s
i
m
a
g
e
ca
n
o
n
E
OS
6
0
0
d
ca
m
er
a
ar
e
u
s
ed
.
W
h
en
i
m
a
g
es
w
er
e
ta
k
e
n
,
th
e
ca
m
e
r
a
w
as
f
i
x
ed
o
n
a
s
tan
d
w
h
ic
h
r
ed
u
ce
s
t
h
e
m
o
v
e
m
e
n
t
o
f
h
an
d
an
d
ca
p
tu
r
i
n
g
u
n
i
f
o
r
m
i
m
a
g
e
s
o
f
co
f
f
ee
p
la
n
t.
T
o
o
b
tain
u
n
i
f
o
r
m
li
g
h
tn
i
n
g
o
r
b
alan
ce
d
ill
u
m
i
n
atio
n
1
0
0
W
lam
p
is
u
s
ed
.
Hav
i
n
g
s
u
c
h
t
y
p
es
o
f
d
ata
s
et
,
it
w
a
s
v
er
y
h
elp
f
u
l
to
id
en
ti
f
y
th
e
d
i
s
ea
s
es
t
y
p
e.
A
to
tal
o
f
9
1
0
0
im
a
g
es
ar
e
co
n
s
id
er
ed
f
o
r
t
h
is
s
t
u
d
y
.
On
ce
th
e
d
ata
s
et
co
llected
,
v
ar
io
u
s
p
r
o
ce
s
s
i
n
g
s
tep
s
ar
e
p
er
f
o
r
m
ed
to
ac
h
iev
e
th
e
g
o
al
o
f
th
e
s
tu
d
y
th
r
o
u
g
h
M
AT
L
A
B
,
2
0
1
3
.
T
h
e
k
n
o
w
led
g
e
b
ase
i
s
a
ce
n
tr
al
p
ar
t
co
m
p
o
n
e
n
t
o
f
t
h
e
e
x
p
er
t
s
y
s
te
m
f
o
r
w
h
ic
h
i
n
f
o
r
m
atio
n
w
as
o
b
tain
ed
f
r
o
m
a
n
e
x
p
er
t.
Dev
elo
p
in
g
a
k
n
o
w
led
g
e
b
ase
w
it
h
t
h
e
h
elp
o
f
a
n
e
x
p
er
t
as
a
tr
u
s
ted
s
o
u
r
ce
o
f
in
f
o
r
m
atio
n
is
th
e
m
o
s
t i
m
p
o
r
t
an
t t
h
i
n
g
in
th
e
ex
p
er
t s
y
s
te
m
s
o
th
at
th
e
r
e
s
u
l
t
w
ill
b
e
co
r
r
ec
t a
n
d
v
alid
.
I
n
t
h
i
s
ca
s
e,
d
ir
ec
t in
ter
v
ie
w
s
w
it
h
s
o
m
e
ex
p
er
t o
f
t
h
e
co
f
f
ee
p
lan
t a
r
e
co
n
d
u
cted
.
4.
CO
F
F
E
E
P
L
ANT D
I
S
E
AS
E
S IDE
NT
I
F
I
CA
T
I
O
N
D
E
S
I
G
N
T
h
e
co
f
f
ee
p
lan
t
id
e
n
ti
f
icatio
n
s
y
s
te
m
co
n
tai
n
s
t
w
o
b
asic
p
a
r
ts
th
e
f
ir
s
t
p
ar
t
is
b
u
ild
in
g
a
k
n
o
w
led
g
e
b
ase
s
y
s
te
m
a
n
d
th
e
s
ec
o
n
d
p
ar
t
is
i
m
ag
e
p
r
o
ce
s
s
i
n
g
p
ar
t.
I
n
d
ev
elo
p
in
g
a
k
n
o
w
led
g
e
b
ase
s
y
s
te
m
ex
tr
ac
tin
g
th
e
k
n
o
w
led
g
e
o
f
an
ex
p
er
t
a
n
d
d
ev
elo
p
a
r
u
le
u
s
i
n
g
d
ec
is
i
o
n
tr
ee
m
eth
o
d
s
in
th
i
s
ca
s
e,
f
o
r
ev
er
y
s
y
m
p
to
m
o
f
co
f
f
ee
p
lan
t
d
is
ea
s
es
w
e
s
h
o
u
ld
co
n
ti
n
u
e
to
ap
p
l
y
th
e
r
u
le
u
n
ti
l
n
o
r
u
le
s
t
h
at
ca
n
b
e
ap
p
lied
o
r
o
b
j
ec
tiv
e
h
as
b
ee
n
ac
h
ie
v
ed
.
I
n
ca
s
e
o
f
im
a
g
e
p
r
o
ce
s
s
in
g
,
th
e
f
ir
s
t
s
t
ag
e
is
co
f
f
ee
p
lan
t
d
is
ea
s
es
ar
e
g
iv
e
n
as
in
p
u
t
to
th
e
s
y
s
te
m
.
T
h
e
s
ec
o
n
d
s
tep
s
f
o
r
co
f
f
ee
p
la
n
t
d
is
ea
s
e
s
r
ec
o
g
n
itio
n
is
th
a
t
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
i
m
a
g
e
,
p
r
e
-
p
r
o
ce
s
s
in
g
i
m
a
g
e
co
m
m
o
n
l
y
u
s
ed
r
e
m
o
v
i
n
g
lo
w
f
r
eq
u
en
c
y
b
ac
k
g
r
o
u
n
d
n
o
is
e,
n
o
r
m
alize
th
e
in
ten
s
it
y
o
f
th
e
in
d
iv
id
u
al
p
ar
ticles
o
n
a
g
iv
e
n
i
m
a
g
e,
r
e
m
o
v
in
g
r
ef
lectio
n
an
d
m
as
k
i
n
g
p
o
r
tio
n
o
f
i
m
a
g
e
th
ese
is
b
ec
au
s
e
o
f
n
o
is
es
ca
u
s
e
in
ac
c
u
r
ac
y
i
n
i
d
en
tific
at
io
n
o
f
co
f
f
ee
p
lan
t
d
is
ea
s
es.
Me
d
ia
n
f
i
lter
in
g
i
s
u
s
ed
f
o
r
r
ed
u
cin
g
n
o
is
es
o
n
co
f
f
ee
p
lan
t
i
m
a
g
es
.
I
m
a
g
e
s
eg
m
e
n
tatio
n
is
th
e
m
aj
o
r
tech
n
iq
u
es
b
eh
in
d
u
n
d
er
s
tan
d
in
g
o
f
co
f
f
ee
p
lan
t
d
is
ea
s
es
id
e
n
ti
f
icatio
n
.
T
h
er
e
ar
e
d
if
f
er
en
t
tech
n
iq
u
es
o
f
i
m
ag
e
s
e
g
m
en
ta
tio
n
,
b
u
t
t
h
er
e
is
n
o
o
n
e
s
i
n
g
le
tech
n
iq
u
e
th
a
t
is
ap
p
r
o
p
r
iate
to
all
im
a
g
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
.
T
h
er
ef
o
r
e
in
th
is
r
esear
ch
K
-
m
ea
n
s
s
eg
m
e
n
tatio
n
tech
n
iq
u
e
s
ar
e
u
s
ed
.
I
n
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
tag
e,
t
h
e
f
ea
t
u
r
es
o
f
co
f
f
ee
p
lan
t
d
is
ea
s
e
s
ar
e
ex
tr
ac
ted
to
f
ee
d
in
to
th
e
clas
s
if
ier
s
.
T
h
e
p
u
r
p
o
s
e
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
is
to
r
ed
u
ce
th
e
o
r
ig
in
al
d
ata
s
et
b
y
m
ea
s
u
r
in
g
p
r
o
p
er
ties
,
o
r
f
ea
tu
r
es,
th
at
d
is
t
in
g
u
is
h
b
et
w
ee
n
th
e
th
r
ee
t
y
p
es
o
f
co
f
f
ee
p
la
n
t
d
is
ea
s
e
s
.
I
n
o
u
r
ca
s
e
w
e
h
a
v
e
th
r
ee
g
r
o
u
p
s
o
f
f
ea
tu
r
e
s
th
e
s
e
ar
e
GL
C
M,
St
atis
tical
a
n
d
C
o
lo
r
f
ea
tu
r
e
s
.
I
n
E
th
io
p
ia
n
co
f
f
ee
p
lan
t
d
is
ea
s
es
th
e
y
h
a
v
e
d
i
f
f
e
r
en
t
co
lo
r
v
ar
iatio
n
o
f
ea
c
h
t
y
p
e
an
d
co
lo
r
a
n
al
y
s
i
s
co
m
p
u
ted
b
y
ta
k
i
n
g
HS
V
v
alu
e
s
.
(
)
(
)
,
(
)
-
*
,
(
)
(
)
-
,
(
)
(
)
(
)
-
+
T
h
e
f
in
al
s
tep
o
f
co
f
f
ee
p
la
n
t
lea
f
d
is
ea
s
e
s
r
ec
o
g
n
itio
n
is
th
e
cla
s
s
i
f
ica
tio
n
s
tag
e.
A
class
i
f
ier
class
i
f
ies
th
e
g
iv
e
n
d
ataset
s
i
n
to
th
eir
co
r
r
esp
o
n
d
in
g
clas
s
.
I
n
o
r
d
er
to
tr
ain
t
h
e
clas
s
i
f
ier
s
,
a
s
et
o
f
tr
ain
in
g
o
f
co
f
f
ee
p
la
n
t
d
is
ea
s
es
i
m
a
g
e
was
r
eq
u
ir
e
d
,
an
d
th
e
c
lass
lab
el
w
h
er
e
it
b
elo
n
g
s
to
,
9
1
0
0
co
f
f
ee
p
lan
t
d
i
s
ea
s
e
s
i
m
a
g
e
w
er
e
tak
e
n
f
r
o
m
r
e
g
i
o
n
s
o
f
E
t
h
io
p
ia
w
h
er
e
m
o
r
e
co
f
f
ee
s
ar
e
p
r
o
d
u
ce
d
th
at
is
So
u
th
er
n
Natio
n
s
,
Natio
n
alitie
s
,
J
i
m
m
a
an
d
Z
eg
i
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
u
to
ma
tic
C
o
ffee
P
la
n
t D
i
s
ea
s
es I
d
en
tifi
ca
tio
n
Usi
n
g
Hyb
r
id
.
.
.
(
A
b
r
a
h
a
m
Deb
a
s
u
Men
g
is
tu
)
809
Fig
u
r
e1
.
C
o
f
f
ee
P
lan
t D
is
ea
s
e
I
d
en
tif
icat
io
n
Mo
d
el
E
x
p
lain
i
n
g
r
esear
ch
c
h
r
o
n
o
lo
g
ical,
in
c
lu
d
i
n
g
r
esear
c
h
d
esi
g
n
,
r
esear
c
h
p
r
o
ce
d
u
r
e
(
in
th
e
f
o
r
m
o
f
alg
o
r
ith
m
s
,
P
s
eu
d
o
co
d
e
o
r
o
t
h
er
)
,
h
o
w
to
test
a
n
d
d
ata
ac
q
u
is
i
tio
n
[
1
]
,
[
3
]
.
T
h
e
d
escr
ip
tio
n
o
f
th
e
co
u
r
s
e
o
f
r
esear
ch
s
h
o
u
ld
b
e
s
u
p
p
o
r
ted
r
ef
er
en
ce
s
,
s
o
th
e
ex
p
la
n
atio
n
ca
n
b
e
ac
ce
p
ted
s
cien
ti
f
icall
y
[
2
]
,
[
4
]
.
5.
RE
SU
L
T
S
W
e
h
av
e
d
es
ig
n
ed
ex
p
er
i
m
e
n
tal
s
ce
n
ar
io
s
to
test
th
e
id
en
ti
f
icatio
n
p
er
f
o
r
m
a
n
ce
b
y
tak
i
n
g
th
e
ex
tr
ac
ted
f
ea
t
u
r
es
o
f
th
e
d
i
s
ea
s
ed
i
m
a
g
e.
W
e
h
a
v
e
1
7
f
ea
tu
r
es
w
h
ic
h
ar
e
ex
tr
ac
ted
f
r
o
m
a
g
iv
e
n
co
f
f
ee
p
la
n
t
i
m
a
g
e
t
h
ese
ar
e
f
i
v
e
G
L
C
M,
s
i
x
s
ta
tis
t
ical
a
n
d
s
i
x
co
lo
r
f
ea
t
u
r
es.
T
h
e
p
er
f
o
r
m
a
n
ce
s
o
f
r
ec
o
g
n
itio
n
w
er
e
test
ed
b
y
B
P
NN
(
B
ac
k
P
r
o
p
ag
atio
n
Ne
u
r
al
Net
w
o
r
k
)
.
I
n
o
r
d
e
r
to
tr
ain
th
e
class
i
f
ier
s
,
a
s
et
o
f
tr
ain
in
g
d
is
ea
s
ed
co
f
f
ee
i
m
a
g
e
w
a
s
g
i
v
en
to
t
h
e
m
o
d
el
i
n
ad
d
itio
n
t
o
th
e
cla
s
s
lab
el
o
f
E
t
h
io
p
ian
co
f
f
ee
p
lan
t
i
m
ag
e.
Fro
m
t
h
e
to
tal
o
f
9
1
0
0
d
ata
s
ets,
6
3
7
0
w
er
e
u
s
ed
f
o
r
m
o
d
el
tr
ain
i
n
g
a
n
d
2
7
3
0
w
er
e
u
s
ed
f
o
r
p
er
f
o
r
m
an
c
e
test
i
n
g
.
I
n
t
h
is
r
esear
ch
,
t
h
er
e
ar
e
th
r
ee
o
u
tp
u
t
cla
s
s
es,
b
ec
a
u
s
e
th
e
co
f
f
ee
p
la
n
t
d
is
ea
s
es
t
y
p
e
w
er
e
t
h
r
ee
.
T
h
e
r
ep
r
esen
tin
g
f
ea
t
u
r
es
o
f
tr
ai
n
in
g
w
er
e
n
o
r
m
alize
d
w
it
h
m
ea
n
0
an
d
v
ar
ian
ce
1
th
is
h
elp
s
th
e
m
o
d
el
to
co
n
v
er
g
e.
T
h
e
n
eu
r
al
n
et
w
o
r
k
n
ee
d
s
1
7
in
p
u
ts
o
f
t
h
e
co
m
b
in
ed
f
ea
t
u
r
e
v
ec
to
r
s
o
f
G
L
C
M,
C
O
L
O
R
a
n
d
ST
A
T
I
S
T
I
C
AL
an
d
3
n
eu
r
o
n
s
in
its
o
u
tp
u
t
la
y
er
to
class
if
y
t
h
e
t
y
p
e.
T
h
e
h
id
d
en
la
y
er
h
as
1
7
n
eu
r
o
n
s
th
i
s
n
u
m
b
er
w
as
p
ick
ed
b
y
tr
ial
a
n
d
er
r
o
r
m
et
h
o
d
s
,
if
t
h
e
n
et
wo
r
k
h
as
tr
o
u
b
le
o
f
lear
n
in
g
ca
p
ab
ilit
ies,
an
d
th
e
n
n
eu
r
o
n
s
ca
n
b
e
ad
d
ed
to
th
is
la
y
er
.
T
h
er
e
is
a
s
ig
n
i
f
ica
n
t
ch
an
g
e
w
h
en
w
e
i
n
cr
ea
s
e
t
h
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
s
n
e
u
r
o
n
s
u
n
til
1
7
b
u
t
th
er
e
is
n
o
ch
an
g
e
w
h
e
n
th
e
n
u
m
b
er
o
f
h
id
d
en
la
y
er
n
e
u
r
o
n
s
in
cr
ea
s
es
ab
o
v
e
1
7
.
E
ac
h
v
al
u
e
f
r
o
m
t
h
e
in
p
u
t
la
y
er
is
d
u
p
licated
a
n
d
s
en
t
to
all
o
f
th
e
h
id
d
en
n
o
d
es.
T
h
e
r
esu
lt
i
n
d
icate
d
th
at
t
h
er
e
w
as
9
4
.
5
%
u
s
i
n
g
B
P
NN
w
it
h
ta
n
h
s
ig
m
o
id
ac
ti
v
atio
n
f
u
n
ctio
n
.
A
f
ter
co
n
d
u
cti
n
g
t
h
e
ab
o
v
e
ex
p
er
i
m
en
ts
9
4
.
5
%
s
u
cc
es
s
ac
h
ie
v
ed
w
h
e
n
b
ac
k
p
r
o
p
ag
atio
n
ar
ti
f
icial
n
eu
r
al
n
et
w
o
r
k
w
it
h
ta
n
h
ac
ti
v
atio
n
f
u
n
ctio
n
ar
e
co
m
b
i
n
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
9
,
No
.
3
,
Ma
r
ch
2
0
1
8
:
8
0
6
–
8
1
1
810
Fig
u
r
e
2
.
C
o
n
f
u
s
io
n
m
atr
ix
6.
CO
NCLU
SI
O
N
T
h
e
aim
o
f
th
e
r
esear
ch
p
a
p
er
is
to
d
ev
elo
p
a
h
y
b
r
id
s
y
s
te
m
u
s
i
n
g
d
ec
is
io
n
tr
ee
an
d
i
m
ag
e
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
I
n
ad
d
it
io
n
,
t
h
is
r
esear
ch
h
a
s
b
ee
n
f
o
c
u
s
ed
o
n
co
f
f
ee
p
la
n
t
d
i
s
ea
s
e
s
i
d
en
tific
atio
n
s
i
n
ce
it
m
atch
e
s
w
it
h
th
e
o
r
ig
i
n
al
p
u
r
p
o
s
e
o
f
th
e
r
esear
ch
.
I
n
th
is
p
ap
er
,
B
P
NN
w
i
th
t
h
e
co
m
b
in
ed
f
ea
t
u
r
es
o
f
GL
C
M,
C
O
L
OR
,
ST
A
T
I
ST
I
C
AL
an
d
k
n
o
w
led
g
e
b
ase
s
y
s
te
m
(
KB
)
in
co
f
f
ee
d
i
s
ea
s
e
s
id
en
ti
f
icatio
n
ar
e
test
ed
an
d
th
e
ac
c
u
r
ac
y
o
f
t
h
e
s
y
s
te
m
ar
e
p
r
ese
n
ted
,
an
d
t
h
e
r
esu
lts
o
f
B
P
NN
w
it
h
ta
n
h
ac
tiv
atio
n
f
u
n
cti
on
ap
p
r
o
ac
h
es
w
er
e
d
is
cu
s
s
ed
an
d
en
co
u
r
ag
i
n
g
r
es
u
lt
s
w
er
e
o
b
tain
ed
.
RE
F
E
R
E
NC
E
S
[
1
]
A
le
m
a
y
e
h
u
As
f
a
w
Am
a
m
o
,
“
Co
ff
e
e
P
ro
d
u
c
ti
o
n
a
n
d
M
a
rk
e
ti
n
g
in
Et
h
i
o
p
ia”
,
Eu
ro
p
e
a
n
J
o
u
rn
a
l
o
f
Bu
sin
e
ss
a
n
d
M
a
n
a
g
e
me
n
t,
V
o
l
.
6
,
No
.
3
7
,
2
0
1
4
.
[
2
]
Ba
rt
M
in
ten
,
S
e
n
e
sh
a
w
Ta
m
ru
,
Tad
e
ss
e
Ku
m
a
,
a
n
d
Ya
w
N
y
a
rk
o
,
“
S
tru
c
tu
re
a
n
d
Per
fo
rm
a
n
c
e
o
f
E
th
io
p
ia
’s
C
o
ff
e
e
Exp
o
rt
S
e
c
to
r”
,
E
th
i
o
p
ia
S
trate
g
y
S
u
p
p
o
rt
P
r
o
g
ra
m
,
2
0
1
2
.
[
3
]
A
b
rh
a
m
De
a
b
su
,
Da
g
n
a
c
h
e
w
M
e
les
e
w
a
n
d
S
e
ff
i
G
e
b
e
y
e
h
u
,
“
Im
a
g
e
A
n
a
l
y
sis
f
o
r
Et
h
io
p
ia
n
c
o
f
f
e
e
p
lan
t
d
ise
a
se
s
id
e
n
ti
f
ica
ti
o
n
,
CS
C
-
j
o
u
r
n
a
l,
V
o
l.
9
,
No
.
4
(
2
0
1
6
)
.
[
4
]
P
.
Re
v
a
th
i
M
.
He
m
a
l
a
th
a
,
“
Ho
m
o
g
e
n
o
u
s
S
e
g
m
e
n
tatio
n
b
a
s
e
d
Ed
g
e
De
te
c
ti
o
n
T
e
c
h
n
iq
u
e
s
f
o
r
P
ro
f
icie
n
t
Id
e
n
ti
f
ica
ti
o
n
o
f
th
e
Co
tt
o
n
L
e
a
f
S
p
o
t
Dise
a
se
s”
,
a
,
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
Ap
p
l
ica
ti
o
n
s,
Vo
lu
m
e
4
7
–
No
.
2
,
Ju
n
e
2
0
1
2
.
[
5
]
Dh
e
e
b
A
l
B
a
sh
ish
,
M
a
li
k
Bra
ik
,
a
n
d
S
u
li
e
m
a
n
Ba
n
i
A
h
m
a
d
,
”
A
Fra
me
wo
rk
fo
r De
tec
ti
o
n
a
n
d
Cla
ss
if
ica
ti
o
n
o
f
Pl
a
n
t
L
e
a
f
a
n
d
S
tem
Dise
a
se
s”
,
2
0
1
0
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
S
ig
n
a
l
a
n
d
Im
a
g
e
P
ro
c
e
ss
in
g
.
[
6
]
P
ra
k
a
sh
M
.
M
a
in
k
a
r,
S
h
re
e
k
a
n
t
G
h
o
rp
a
d
e
,
M
a
y
u
r
A
d
a
w
a
d
k
a
r,
Co
ff
e
e
d
ise
a
se
s
Dise
a
se
De
tec
ti
o
n
a
n
d
Clas
sif
ic
a
ti
o
n
Us
in
g
Im
a
g
e
P
ro
c
e
ss
in
g
T
e
c
h
n
iq
u
e
s,
V
o
l
u
m
e
2
,
Iss
u
e
4
,
2
0
1
5
.
[
7
]
P
re
m
a
lath
a
.
V
,
V
a
larm
a
th
y
.
S
,
S
u
m
it
h
ra
.
M
.
G
,
“
Dise
a
s
e
Id
e
n
ti
f
ica
ti
o
n
in
C
o
tt
o
n
P
lan
ts
Us
in
g
S
p
a
ti
a
l
F
CM
&
P
NN
Clas
sif
ier
”
,
IJ
IRCCE
,
Vo
l.
3
,
Iss
u
e
4
,
A
p
ril
2
0
1
5
.
[
8
]
Nik
it
a
Rish
i
,
Ja
g
b
ir
S
i
n
g
h
G
il
l,
”
A
n
Ov
e
r
v
ie
w
o
n
De
tec
ti
o
n
a
n
d
Clas
sif
ica
ti
o
n
o
f
P
lan
t
Dis
e
a
se
s
in
Im
a
g
e
P
r
o
c
e
ss
in
g
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
ien
ti
f
ic
En
g
i
n
e
e
rin
g
a
n
d
R
e
se
a
rc
h
(
IJ
S
ER
)
V
o
l
u
m
e
3
Iss
u
e
5
,
M
a
y
2
0
1
5
.
[
9
]
Ja
y
m
e
G
a
rc
ia
A
rn
a
l
Ba
rb
e
d
o
,
Di
g
it
a
l
ima
g
e
p
ro
c
e
ss
in
g
te
c
h
n
iq
u
e
s
f
o
r
d
e
tec
ti
n
g
,
q
u
a
n
ti
f
y
in
g
a
n
d
c
las
si
fy
in
g
p
lan
t
d
ise
a
se
s,
S
p
rin
g
e
r
P
lu
s,
De
c
e
m
b
e
r
2
0
1
3
.
[
1
0
]
Ha
ig
u
a
n
g
W
a
n
g
,
G
u
a
n
li
n
L
i,
Zh
a
n
h
o
n
g
M
a
,
X
iao
l
o
n
g
L
i,
I
m
a
g
e
Re
c
o
g
n
it
io
n
o
f
P
lan
t
Dis
e
a
se
s
Ba
s
e
d
o
n
Ba
c
k
p
ro
p
a
g
a
ti
o
n
Ne
tw
o
rk
s :
IEE
E
,
2
0
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
A
n
A
u
to
ma
tic
C
o
ffee
P
la
n
t D
i
s
ea
s
es I
d
en
tifi
ca
tio
n
Usi
n
g
Hyb
r
id
.
.
.
(
A
b
r
a
h
a
m
Deb
a
s
u
Men
g
is
tu
)
811
[
1
1
]
A
n
u
p
V
i
b
h
u
te,
A
p
p
li
c
a
ti
o
n
s
o
f
Im
a
g
e
P
ro
c
e
ss
in
g
in
A
g
ricu
lt
u
re
:
A
S
u
rv
e
y
,
In
ter
n
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
C
o
mp
u
ter
Ap
p
li
c
a
ti
o
n
s
(
0
9
7
5
–
8
8
8
7
)
Vo
lu
m
e
5
2
–
N
o
.
2
,
A
u
g
u
st 2
0
1
2
.
[
1
2
]
A
n
tan
u
P
h
a
d
ik
a
r
a
n
d
Ja
y
a
S
il
,
“
Ri
c
e
d
ise
a
se
id
e
n
ti
fi
c
a
ti
o
n
u
si
n
g
p
a
tt
e
rn
re
c
o
g
n
it
io
n
tec
h
n
iq
u
e
s"
,
P
ro
c
e
e
d
i
n
g
s
o
f
1
1
t
h
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
ter
a
n
d
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
(ICCIT
2
0
0
8
)
,
2
5
-
2
7
De
c
e
m
b
e
r,
2
0
0
8
,
K
h
u
l
n
a
.
[
1
3
]
Ha
b
tam
u
M
in
a
sie
“
Ima
g
e
a
n
a
lys
i
s
fo
r E
t
h
io
p
ia
n
c
o
ff
e
e
c
la
ss
if
ica
ti
o
n
”
,
2
0
0
8
,
A
d
d
is
A
b
a
b
a
Un
iv
e
rsity
[
1
4
]
A
b
rh
a
m
De
a
b
su
,
Da
g
n
a
c
h
e
w
M
e
les
e
w
a
n
d
S
e
f
f
i
G
e
b
e
y
e
h
u
,
“
Et
h
io
p
ia
n
Co
f
f
e
e
P
lan
t
Dise
a
se
s
Re
c
o
g
n
it
io
n
Ba
se
d
o
n
Im
a
g
in
g
a
n
d
M
a
c
h
in
e
L
e
a
rn
in
g
T
e
c
h
n
iq
u
e
s,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Da
t
a
b
a
se
T
h
e
o
ry
a
n
d
A
p
p
li
c
a
ti
o
n
,
Vo
l.
9
,
No
.
4
(
2
0
1
6
)
,
p
p
.
7
9
-
88.
[
1
5
]
F
it
ri
Uta
m
in
in
g
ru
m
,
Re
n
a
ld
i
P
ri
m
a
s
w
a
r
a
P
ra
e
ty
a
,
Yu
it
a
A
ru
m
S
a
ri,
”
I
m
a
g
e
P
ro
c
e
ss
in
g
f
o
r
Ra
p
id
l
y
E
y
e
De
te
c
ti
o
n
b
a
se
d
o
n
Ro
b
u
st Ha
a
r
S
l
id
i
n
g
W
in
d
o
w
”
,
IAE
S
,
V
o
l
7
,
No
2
.
[
1
6
]
A
c
h
m
a
d
F
a
h
ru
ro
z
i1
,
S
a
rif
u
d
d
i
n
M
a
d
e
n
d
a
1
,
Ern
a
stu
t
i1
,
Dja
ti
Ke
ra
m
i,
“
W
o
o
d
Clas
sif
ic
a
ti
o
n
Ba
se
d
o
n
Ed
g
e
De
tec
ti
o
n
s an
d
T
e
x
tu
re
F
e
a
tu
re
s
S
e
lec
ti
o
n
”
,
IAE
S
,
Vo
l.
6
,
N
o
.
5
,
Oc
to
b
e
r
2
0
1
6
,
p
p
.
2
1
6
7
~
2
1
7
5
.
[
1
7
]
L
il
ik
S
u
m
a
r
y
a
n
ti
,
A
in
a
M
u
sd
h
o
li
f
a
h
,
S
ri
Ha
rtati,
“
Dig
it
a
l
Im
a
g
e
Ba
se
d
Id
e
n
ti
f
ica
ti
o
n
o
f
Rice
V
a
ri
e
t
y
Us
in
g
Im
a
g
e
P
r
o
c
e
ss
in
g
a
n
d
Ne
u
ra
l
Ne
tw
o
rk
”
,
T
EL
KOM
NIKA
In
d
o
n
e
sia
n
J
o
u
r
n
a
l
o
f
E
lec
trica
l
E
n
g
i
n
e
e
rin
g
Vo
l
1
6
N
o
1
,
2
0
1
5
.
[
1
8
]
Qin
g
h
a
i
He
,
Be
n
x
u
e
M
a
,
Du
a
n
y
a
n
g
Qu
,
Q
ian
g
Zh
a
n
g
,
X
in
m
in
Ho
u
,
Jin
g
Zh
a
o
,
“
Co
tt
o
n
P
e
sts
a
n
d
Dise
a
s
e
s
De
tec
ti
o
n
Ba
se
d
o
n
Im
a
g
e
P
ro
c
e
ss
in
g
”
,
T
EL
KOM
NIKA
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
E
n
g
i
n
e
e
rin
g
Vo
l
1
1
No
6
,
2
0
13
.
Evaluation Warning : The document was created with Spire.PDF for Python.