I
ndo
ne
s
i
a
n J
o
ur
na
l
o
f
E
l
e
c
t
r
i
c
a
l
E
ng
i
ne
e
r
i
ng
a
nd C
o
m
p
u
t
e
r
Sc
i
e
nc
e
V
o
l.
11
,
N
o.
2
,
A
ug
us
t
201
8
,
pp.
54
9
~
55
7
I
SSN
:
2502
-
4752
,
D
O
I
:
10.
11
591/
i
j
eecs
.
v
11.
i
2
.p
p
549
-
5
57
549
Jou
r
n
al
h
om
e
p
age
:
h
ttp
:
//ia
e
s
c
or
e
.
c
om
/
j
our
nal
s
/
i
nde
x
.
php/
i
j
e
e
c
s
E
v
a
lua
t
io
n o
f
Co
lo
r M
o
dels
f
o
r P
a
l
m
O
il
F
res
h
F
r
uit
B
unch
Ripenes
s
Cla
s
s
if
i
c
a
t
io
n
N
ur
ba
i
t
y
Sa
br
i
1
,
Z
a
i
da
h I
br
a
hi
m
2
,
D
i
n
o
I
sa
3
1
F
acu
l
t
y
o
f
C
o
m
p
u
t
er
an
d
M
at
h
e
m
at
i
cal
S
ci
en
ces
,
U
n
iv
e
r
s
iti T
e
k
n
o
lo
g
i M
A
R
A
,
C
a
m
pus
M
e
l
a
k
a
,
7730
0
M
e
l
a
k
a
2
F
acu
l
t
y
o
f
C
o
m
p
u
t
er
an
d
M
at
h
e
m
at
i
cal
S
ci
en
ces
,
U
n
i
v
er
s
i
t
i
T
e
k
n
o
l
o
g
i
M
A
R
A
,
C
a
m
pus
S
ha
h A
l
a
m
,
4045
0 S
e
l
a
ng
or
3
F
a
c
u
lty
o
f
En
g
in
e
e
r
in
g
,
U
n
iv
e
r
s
ity
o
f
N
o
ttin
g
h
a
m
M
a
la
y
s
ia
C
a
m
p
u
s
,
J
a
la
n
B
r
og
a
,
43
50
0
S
e
m
e
n
y
i
h,
S
e
l
a
ng
or
A
rt
i
cl
e I
n
f
o
AB
S
T
RAC
T
A
r
tic
le
h
is
to
r
y
:
R
ecei
v
ed
Fe
b
12
,
201
8
Re
v
i
se
d
A
pr
17
,
201
8
A
ccep
t
ed
Ap
r
21
,
2
018
T
hi
s
pa
pe
r
i
nv
e
s
t
i
g
a
t
e
s
t
he
a
pp
l
i
c
a
t
i
on
of
e
i
g
ht
c
ol
or
m
ode
l
s
f
or
a
ut
om
a
t
i
c
p
a
lm
o
il F
r
e
s
h
F
r
u
it B
u
n
c
h
(
F
F
B
)
r
ip
e
n
e
s
s
c
la
s
s
i
f
ic
a
tio
n
w
ith
m
u
lti
-
cl
as
s
S
up
por
t
V
e
c
t
or
M
a
c
hi
ne
(
S
V
M
)
.
R
i
pe
ne
s
s
c
l
a
s
s
i
f
i
c
a
t
i
on i
s
i
m
por
t
a
nt
dur
i
ng
ha
r
v
e
s
t
i
ng
t
o e
ns
ur
e
t
ha
t
t
he
y
ar
e
h
ar
v
es
t
ed
d
u
r
i
n
g
t
h
e co
r
r
ect
r
i
p
e s
t
ag
e
f
o
r
opt
i
m
um
oi
l
pr
od
uc
t
i
o
n.
S
in
c
e
c
o
lo
r
is
a
s
ig
n
if
ic
a
n
t in
d
i
c
a
to
r
f
o
r
a
g
r
ic
u
ltu
r
is
ts
to
d
e
te
r
m
in
e
th
e
r
ip
e
n
e
s
s
o
f
F
F
B
,
it is
c
r
itic
a
l to
d
e
te
r
m
in
e
th
e
r
i
g
ht
c
ol
or
m
ode
l
.
E
i
g
ht
c
ol
or
m
ode
l
s
ha
v
e
be
e
n i
nv
e
s
t
i
g
a
t
e
d
n
a
m
el
y
,
H
S
V
,
I1
I2
I
3
,
L
A
B,
X
Y
Z
,
Y
Cb
Cr,
Y
IQ
,
Y
U
V
a
n
d
RG
B.
Co
l
o
r m
o
m
e
n
t
s
w
e
r
e
ex
t
r
act
ed
f
r
o
m
ea
ch
o
f
t
h
es
e co
l
o
r
m
o
d
el
s
f
o
r
t
h
e cl
as
s
i
f
i
cat
i
o
n
o
f
f
o
u
r
s
t
ag
e
s
of
F
F
B
r
i
pe
ne
s
s
t
ha
t
a
r
e
unr
i
pe
,
unde
r
-
r
i
pe
,
r
i
pe
a
nd ov
e
r
-
r
i
p
e.
A
d
at
ab
as
e o
f
f
i
ve
hun
dr
e
d
i
m
a
ge
s
of
pa
l
m
oi
l
F
F
B
ha
s
be
e
n c
ons
t
r
uc
t
e
d a
n
d e
x
pe
r
i
m
e
nt
s
s
how
e
d t
ha
t
Y
C
bC
r
a
nd Y
U
V
out
pe
r
f
or
m
t
he
ot
he
r
c
ol
or
m
ode
l
s
.
Ke
y
wo
rd
s
:
F
r
e
s
h
F
r
ui
t
B
u
nc
h (
F
F
B
)
C
ol
or
m
ode
l
s
C
ol
or
m
o
m
e
n
t
SV
M
C
opy
r
i
g
ht
©
201
8
I
ns
t
i
t
ut
e
o
f
A
d
v
anc
e
d E
ngi
ne
e
r
i
ng
an
d
Sc
i
e
nc
e
.
All
ri
g
h
t
s re
se
rv
e
d
.
Co
rre
sp
o
n
d
i
n
g
Au
t
h
o
r
:
N
u
r
b
ai
t
y
S
ab
r
i
,
F
acu
l
t
y
o
f
C
o
m
p
u
t
er
an
d
M
at
h
e
m
a
t
i
cal
S
ci
e
n
ces
,
U
ni
ve
r
s
i
t
i
T
e
kno
l
o
gi
M
A
R
A
,
C
a
m
p
us
M
e
l
a
ka
,
7
7
3
0
0
M
e
l
a
ka
.
E
m
a
il:
n
u
r
b
ai
t
y
_
s
ab
r
i
@
m
el
a
k
a.
u
i
t
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
q
u
a
lit
y
o
f
p
a
l
m
o
il F
r
e
s
h
F
r
u
it
B
un
c
h
(
F
F
B
)
i
s
i
m
por
t
a
n
t
du
e
t
o h
i
gh
m
a
r
k
e
t
de
m
a
n
ds
on
pa
l
m
o
i
l
p
r
o
d
uc
t
s
s
uc
h a
s
c
o
n
s
u
m
p
t
i
o
n,
c
o
s
m
e
t
i
c
i
nd
us
t
r
y a
nd
m
a
n
y
m
o
r
e
.
O
ne
o
f
t
he
m
a
i
n c
ha
l
l
e
n
ge
s
i
n
f
r
ui
t
i
nd
u
s
t
r
y
i
s
t
o
i
d
e
nt
i
f
y t
he
r
i
g
h
t
f
r
ui
t
f
o
r
ha
r
ve
s
t
i
n
g.
I
n o
r
d
e
r
t
o
p
r
e
s
e
r
ve
a
nd
m
a
i
nt
a
i
n t
h
e
q
u
a
lit
y
o
f
p
a
l
m
o
il
p
r
o
d
u
c
t,
it is
c
r
u
c
ia
l
to
h
a
r
v
e
s
t p
a
l
m
o
il
F
F
B
a
t
th
e
r
ig
h
t
s
ta
g
e
.
T
h
e
p
r
o
f
it o
f
p
a
l
m
o
il
in
d
u
s
tr
y
r
e
lie
s
o
n
t
h
e
p
o
s
t
ha
r
ve
s
t
i
n
g
l
e
ve
l
[1
]
.
T
he
r
e
f
o
r
e
,
b
y
ha
r
ve
s
t
i
ng
p
a
l
m
o
i
l
F
F
B
a
t
t
he
r
i
g
ht
p
ha
s
e
o
f
m
a
t
ur
i
t
y
,
it
e
n
s
ur
e
s
id
e
a
l q
u
a
li
t
y
a
n
d opt
i
m
i
z
e
d t
h
e
a
m
o
un
t
of
oi
l
pr
odu
c
t
i
on
.
I
n
M
a
l
a
y
s
i
a
,
E
l
a
i
e
s
G
un
e
e
ns
i
s
i
s
t
h
e
c
o
m
m
o
n
s
p
eci
es
o
f
p
al
m
o
i
l
t
h
at
i
s
a
v
ai
l
ab
l
e an
d
m
o
s
t
l
y
p
l
an
t
ed
.
T
h
e r
i
p
en
es
s
o
f
t
h
i
s
s
p
eci
e
s
i
s
d
et
er
m
i
n
ed
b
y
M
al
a
y
s
i
a
n
P
al
m
O
i
l
B
o
ar
d
[
2]
.
T
ab
l
e 1
s
h
o
w
s
s
o
me
s
a
mp
l
e
i
m
a
g
e
s
o
f t
h
e
f
o
ur
l
e
ve
l
s
o
f
r
i
p
e
ne
s
s
s
t
a
ge
s
fo
r
p
a
l
m
o
i
l
FFB
.
B
y
l
o
o
k
i
n
g
at
T
ab
l
e 1
,
w
e
can
s
ee
t
h
at
t
h
es
e
d
i
f
f
er
en
t
l
e
v
el
s
o
f
r
i
p
e
n
es
s
can
b
e eas
i
l
y
d
e
te
r
m
in
e
d
th
r
o
u
g
h
c
o
lo
r
b
u
t th
e
s
e
c
o
lo
r
i
m
a
g
e
s
a
r
e
in
f
l
u
e
n
c
e
d
b
y
ill
u
m
in
a
t
io
n
.
T
h
u
s
,
it
is
v
e
r
y
c
h
a
lle
n
g
in
g
to
id
e
n
tif
y
t
h
e
r
ig
h
t c
o
lo
r
s
in
c
e
d
if
f
e
r
e
n
t o
u
td
o
o
r
lig
h
t
in
g
c
o
n
d
itio
n
c
a
n
a
f
f
e
c
t t
h
e
c
o
lo
r
o
f
th
e
i
m
a
g
e
s
.
R
e
c
e
n
t
l
y
,
v
a
r
io
u
s
s
tu
d
ie
s
in
c
o
m
p
u
te
r
v
i
s
io
n
f
o
r
f
r
u
it r
ip
e
n
e
s
s
c
la
s
s
if
ic
a
tio
n
s
u
c
h
a
s
w
a
te
r
m
e
lo
n
,
b
an
an
as
,
a
n
d
t
o
m
at
o
es
h
av
e b
een
ex
p
l
o
r
ed
[
3
]
.
M
o
s
t
o
f
t
h
e
s
e s
t
u
d
i
es
u
s
e
co
l
o
r
as
t
h
e
p
ar
a
m
et
er
t
o
d
et
er
m
i
n
e
th
e
r
ip
e
n
e
s
s
s
ta
g
e
th
a
t i
n
v
o
lv
e
s
th
e
e
x
tr
a
c
tio
n
o
f
u
s
e
f
u
l in
f
o
r
m
a
tio
n
c
o
n
c
e
r
n
i
n
g
t
h
e
s
p
e
c
tr
a
l p
r
o
p
e
r
tie
s
o
f
th
e
f
r
u
i
t
s
u
r
f
ace.
T
h
er
e a
r
e s
ev
er
al
co
l
o
r
m
o
d
el
s
t
h
at
can
b
e i
n
v
es
t
i
g
at
ed
i
n
o
r
d
er
t
o
cr
eat
e
a
r
el
i
ab
l
e ap
p
r
o
ach
t
o
cl
as
s
i
f
y
t
h
e
f
r
u
i
t
s
i
n
t
o
d
i
f
f
er
e
n
t
cl
as
s
es
o
f
r
i
p
en
es
s
[
3
]
.
T
h
er
ef
o
r
e,
s
el
ect
i
n
g
an
ap
p
r
o
p
r
i
at
e an
d
accu
r
at
e co
l
o
r
m
ode
l
i
s
c
r
u
c
i
a
l
f
or
de
s
i
g
ni
ng
a
n
d
m
ode
l
l
i
n
g a
ut
o
m
a
t
e
d
m
a
c
hi
n
e
v
i
s
i
on s
y
s
t
e
m
f
or
pa
l
m
oi
l
F
F
B
r
i
pe
n
e
s
s
c
la
s
s
i
f
ic
a
tio
n
[
4
]
.
T
h
e
m
os
t
c
o
m
m
on c
ol
or
m
ode
l
i
s
R
G
B
w
h
e
r
e
a
ny
c
ol
or
i
s
de
s
c
r
i
be
d b
y
i
t
s
i
n
t
e
n
s
i
t
i
e
s
of
R
e
d (
R
)
,
G
r
een
(
G
)
a
n
d
B
l
u
e (
B
)
.
R
G
B
v
al
u
es
ar
e s
u
i
t
ab
l
e t
o
b
e
u
s
ed
f
o
r
co
n
s
t
an
t
l
i
g
h
t
i
n
g
e
n
v
i
r
o
n
m
en
t
s
i
n
ce
t
h
e
y
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
25
02
-
4752
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
,
V
o
l.
11
, N
o
.
2
,
A
ug
us
t
2018
:
5
49
–
557
550
a
f
f
e
c
t
e
d
b
y
c
ha
ngi
n
g l
i
g
ht
i
nt
e
ns
i
t
i
e
s
[
5]
.
R
G
B
i
s
a
t
y
pi
c
a
l
c
ol
or
m
ode
l
u
s
e
d i
n
m
a
ny
f
r
ui
t
g
r
a
di
n
g r
e
s
e
a
r
c
h
s
u
c
h
as
p
each
es
[
6
]
,
m
an
g
o
s
t
e
en
[
7
]
,
t
o
m
at
o
[
8
]
an
d
av
o
cad
o
es
[
9
]
,
[
1
0
]
.
R
G
B
co
l
o
r
m
o
d
el
h
as
b
een
ap
p
l
i
ed
i
n
pa
l
m
oi
l
F
F
B
g
r
a
di
ng
i
n
[
11]
-
[
13]
bu
t
R
G
B
i
s
e
a
s
i
l
y
i
nf
l
u
e
n
c
e
d by
i
l
l
um
i
n
a
tio
n
.
A
n
o
th
e
r
c
o
lo
r
m
o
d
e
l t
h
a
t
is
c
o
m
m
o
n
l
y
u
s
e
d
to
c
la
s
s
i
f
y
f
r
u
it r
ip
e
n
e
s
s
is
th
e
d
e
s
c
r
ip
tiv
e
p
a
r
a
m
e
te
r
s
H
u
e,
S
at
u
r
at
i
o
n
a
n
d
V
al
u
e (
H
S
V
)
w
h
er
e H
u
e
d
es
cr
i
b
es
t
h
e co
l
o
r
;
S
at
u
r
at
i
o
n
r
ep
r
es
e
n
t
s
t
h
e p
u
r
i
t
y
o
f
t
h
at
c
o
lo
r
w
h
ile
V
a
l
u
e
i
s
its
b
r
ig
h
tn
e
s
s
.
H
S
V
is
le
s
s
a
f
f
e
c
t
e
d
by
i
l
l
um
i
n
a
t
i
o
n
c
h
a
n
g
e
s
c
o
m
pa
r
e
d
t
o R
G
B
[
14]
.
H
S
V
i
s
u
s
ed
i
n
[
8
]
t
o
d
et
er
m
i
n
e t
h
e r
i
p
en
es
s
o
f
t
o
m
at
o
b
y
e
x
t
r
act
i
n
g
t
h
e H
u
e
v
al
u
e
f
r
o
m
F
F
B
i
m
a
g
e.
I
n
p
al
m
o
i
l
r
es
ear
ch
,
t
h
i
s
co
l
o
r
m
o
d
el
i
n
cr
eas
es
t
h
e
p
al
m
o
i
l
r
i
p
en
es
s
cl
as
s
i
f
i
cat
i
o
n
acc
u
r
ac
y
b
y
2
0
%
co
m
p
ar
ed
t
o
R
G
B
c
ol
or
m
ode
l
[
2]
.
T
ab
l
e 1
.
T
h
e r
i
p
en
es
s
s
t
ag
e o
f
p
al
m
o
i
l
F
F
B
b
y
M
a
la
y
s
ia
n
P
a
l
m
O
il B
o
a
r
d
[
2
]
Im
a
g
e
S
t
a
g
e
C
o
l
o
r c
h
a
ra
c
t
e
ri
s
t
i
c
U
n
r
i
p
e
P
u
r
p
l
i
s
h
b
l
a
c
k
U
n
d
e
r
-
ri
p
e
R
ed
d
i
s
h
b
l
ac
k
R
ip
e
R
ed
O
v
e
rri
p
e
R
e
d
di
s
h or
a
n
g
e
I
n
te
r
n
a
tio
n
a
l C
o
m
m
is
s
io
n
o
n
I
llu
m
in
a
tio
n
(
C
o
m
m
is
s
io
n
i
n
te
r
n
a
tio
n
a
le
d
e
l’
é
c
la
ir
a
g
e
)
(C
IE
)
L
a
b
c
ol
or
m
ode
l
i
s
a
s
s
oc
i
a
t
e
d
w
i
t
h
di
s
pl
a
y
s
y
s
t
e
m
s
u
c
h
a
s
t
e
l
e
vi
s
i
on
or
c
ol
or
m
on
i
t
or
t
o a
da
p
t
w
i
t
h
h
um
a
n
c
ol
or
r
es
p
o
n
s
e ch
ar
act
er
i
s
t
i
cs
[
1
5
]
.
T
h
i
s
co
l
o
r
m
o
d
el
h
as
b
e
en
ap
p
l
i
ed
r
i
p
en
es
s
g
r
ad
i
n
g
o
f
ap
p
l
e an
d
t
o
m
a
t
o
[
16]
,
[
1
7]
.
I
n
pa
l
m
oi
l
g
r
a
di
n
g
,
t
h
i
s
c
ol
or
m
ode
l
ha
s
be
e
n
u
s
e
d
by
[
2]
,
[
1
1]
,
[1
8
]
,
[
1
9
]
b
u
t
a
t th
e
s
eg
m
e
n
t
at
i
o
n
s
t
ag
e
w
h
er
e t
h
i
s
s
t
ag
e r
e
m
o
v
es
t
h
e n
o
i
s
es
f
r
o
m
t
h
e F
F
B
p
al
m
o
i
l
i
m
a
g
e.
T
h
i
s
co
l
o
r
m
o
d
el
pr
odu
ces
a g
o
o
d
s
eg
m
e
n
t
at
i
o
n
r
es
u
l
t
w
h
er
e i
t
m
a
n
a
g
es
t
o
r
em
o
v
e t
h
e u
n
w
a
n
t
ed
ar
eas
i
n
t
h
e i
m
ag
e.
Y
Cb
Cr
c
ol
or
m
ode
l
c
o
m
m
o
n
l
y
u
s
e
i
n
ope
r
a
t
i
on
i
n
di
g
i
t
a
l
vi
de
o a
n
d i
m
a
g
e
c
o
m
pr
e
s
s
i
o
n
[
21]
.
H
i
g
h
accu
r
ac
y
h
a
s
b
een
ach
i
ev
ed
i
n
cl
a
s
s
i
f
i
cat
i
o
n
o
f
r
i
p
en
e
s
s
s
t
ag
e
f
o
r
w
a
t
e
r
m
e
l
o
n
[
19]
a
n
d or
a
ng
e
[
22]
bu
t
m
o
d
er
at
e
f
o
r
t
o
m
at
o
[
2
0
]
r
i
p
e
n
es
s
cl
as
s
i
f
i
cat
i
o
n
f
o
r
a l
eas
t
n
o
i
s
e b
ack
g
r
o
u
n
d
en
v
i
r
o
n
m
en
t
.
I
n
o
r
an
g
e r
i
p
en
es
s
r
e
c
o
g
n
itio
n
,
lo
w
e
s
t e
r
r
o
r
r
e
c
o
g
n
itio
n
w
it
h
t
h
e
m
o
s
t r
o
b
u
s
t a
lg
o
r
it
h
m
f
o
r
o
r
a
n
g
e
r
e
c
o
g
n
itio
n
h
a
s
b
e
e
n
re
c
o
rd
e
d
[2
2
].
T
h
e
I
1I
2I
3 c
ol
or
m
ode
l
u
s
e
d i
n
a
ppl
e
de
t
e
c
t
i
on
w
h
e
r
e
i
t
s
u
c
c
e
s
s
f
u
l
l
y
di
s
t
i
ng
u
i
s
h o
bj
e
c
t
f
or
m
ba
c
k
g
r
oun
d [
23]
.
I
n
o
r
a
n
g
e
r
e
c
og
n
i
t
i
o
n
,
t
h
i
s
c
ol
or
m
ode
l
s
h
o
w
s
a
h
i
gh
r
e
c
og
ni
t
i
on
e
r
r
or
c
om
pa
r
e
d t
o ot
h
e
r
c
ol
or
m
ode
l
[
22]
.
T
h
i
s
c
ol
or
m
ode
l
h
a
s
a
l
s
o be
e
n
us
e
d
t
o
r
eco
g
n
i
ze d
at
es
.
H
o
w
ev
er
,
i
t
p
r
o
d
u
ce a m
o
d
er
at
e
r
e
s
ul
t
o
f
c
hr
o
m
i
na
c
e
c
o
m
p
o
ne
nt
va
l
ue
[2
4
].
T
h
e
Y
I
Q
c
ol
or
m
ode
l
i
s
o
f
t
e
n
u
s
e
d i
n
s
e
gm
e
nt
a
t
i
on
ope
r
a
t
i
on
[
25]
,
[
2
6
]
w
h
er
e Y
s
t
o
r
es
t
h
e v
al
u
e o
f
lu
m
in
a
n
c
e
,
I
s
to
r
e
s
th
e
v
a
lu
e
o
f
h
u
e
w
h
ile
Q
i
s
f
o
r
s
a
t
u
r
a
tio
n
.
B
es
i
d
es
s
e
g
m
e
n
t
at
i
o
n
,
i
t
h
a
s
al
s
o
b
een
u
s
ed
f
o
r
c
la
s
s
i
f
ic
a
tio
n
p
u
r
p
o
s
e
s
u
c
h
a
s
ir
is
a
u
t
h
e
n
tic
a
tio
n
[
2
7
]
,
[
2
8
]
.
A
co
m
p
ar
at
i
v
e s
t
u
d
y
b
et
w
een
H
S
V
a
n
d
Y
I
Q
c
ol
or
m
ode
l
s
f
or
or
a
n
g
e
f
r
u
i
t
g
r
a
di
ng
h
a
s
s
h
o
w
n
t
h
a
t
Y
I
Q
c
ol
or
m
ode
l
i
s
be
t
t
e
r
t
h
a
n
H
S
V
[
28]
.
B
e
s
i
de
s
th
a
t,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
I
SSN
:
2502
-
4752
E
v
al
uat
i
on of
C
ol
or
M
ode
l
s
f
or
P
al
m
O
i
l
F
r
e
s
h F
r
ui
t
B
unc
h R
i
pe
ne
s
s
…
(
N
ur
bai
t
y
Sabr
i
)
551
Y
I
Q
c
o
l
o
r
m
o
d
e
l
ha
s
a
l
s
o
s
ho
w
n
hi
g
h a
c
c
ur
a
c
y p
e
r
f
o
r
m
a
nc
e
d
ur
i
ng
ni
g
ht
e
n
vi
r
o
n
m
e
nt
f
o
r
l
i
t
c
hi
r
e
c
o
gni
t
i
o
n [
2
9
]
.
X
Y
Z
m
o
d
el
i
s
b
as
ed
o
n
h
u
m
an
t
r
i
g
o
n
o
m
et
r
i
c r
et
i
n
a an
d
i
t
h
as
b
een
ap
p
l
i
ed
o
n
a
g
r
i
cu
l
t
u
r
e p
r
o
d
u
ct
cl
as
s
i
f
i
cat
i
o
n
s
u
ch
a
s
i
n
ap
p
l
e g
r
ad
i
n
g
s
ys
t
e
m
[
3
0
]
a
n
d
s
o
r
tin
g
a
c
itr
u
s
f
r
u
it [
3
1
]
.
H
o
w
e
v
e
r
,
th
is
r
e
s
u
lt v
a
r
ie
s
d
u
e t
o
t
h
e ap
p
l
i
cat
i
o
n
o
f
d
i
f
f
er
en
t
cl
as
s
i
f
i
er
s
.
I
t
h
a
s
al
s
o
b
een
u
s
ed
t
o
r
ed
u
ce t
h
e i
m
a
g
e
s
i
ze o
r
p
r
o
ces
s
i
n
g
t
i
m
e
of
R
G
B
c
ol
or
m
ode
l
f
or
g
r
a
di
ng
a
n
i
m
a
g
e
of
a
g
r
i
c
u
l
t
u
r
a
l
pr
odu
c
t
i
n
do
or
a
n
d ou
t
do
or
e
n
v
i
r
o
nm
e
n
t
[
32]
.
Y
U
V
co
l
o
r
m
o
d
el
d
ef
i
n
es
a c
o
l
o
r
s
p
ace i
n
t
er
m
s
o
f
o
n
e l
u
m
a (
Y
)
an
d
t
w
o
c
h
r
o
m
i
n
an
ce
(
U
V
)
an
d
i
t
h
a
s
l
e
s
s
c
o
m
pu
t
a
t
i
on
a
l
t
i
m
e
c
om
pa
r
e
d t
o ot
h
e
r
R
G
B
c
ol
or
m
ode
l
[
33]
.
T
h
e
c
ol
or
m
ode
l
i
s
c
l
os
e
r
t
o h
um
a
n
p
er
cep
t
i
o
n
r
at
h
er
t
h
an
t
h
e
c
o
nve
nt
i
o
na
l
R
G
B
[
3
4
]
.
I
t
ha
s
b
e
e
n u
s
e
d
i
n a
gr
i
c
ul
t
ur
e
p
r
o
d
uc
t
w
h
e
r
e
us
i
n
g
a
s
i
n
gl
e
va
l
ue
i
n Y
U
V
i
s
go
o
d
e
no
u
gh t
o
a
c
hi
e
ve
hi
gh c
l
a
s
s
i
f
i
c
a
t
i
o
n a
c
c
ur
a
c
y
s
uc
h a
s
i
n o
r
a
nge
s
a
nd
t
o
m
a
t
o
r
e
c
o
gni
t
i
o
n [
2
2
]
,
[
35]
.
S
i
n
c
e
v
a
r
i
ous
r
e
s
u
l
t
s
h
a
v
e
be
e
n
pr
odu
c
e
d by
di
f
f
e
r
e
nt
c
o
l
o
r
m
o
d
e
l
s
,
a
n
i
n
ve
s
t
i
ga
t
i
o
n a
m
o
ng t
he
s
e
r
e
por
t
e
d
e
i
g
h
t
(
8)
c
ol
or
m
ode
l
s
i
s
i
nv
e
s
t
i
g
a
t
e
d i
n
t
h
i
s
pa
pe
r
.
T
h
e
c
ol
or
m
ode
l
s
a
r
e
H
S
V
,
I
1I
2I
3
,
L
A
B
,
X
Y
Z
,
Y
C
b
R
c
,
Y
I
Q
,
Y
U
V
a
n
d
R
G
B
.
T
h
e
y
w
ill
b
e
u
t
iliz
e
d
to
c
la
s
s
if
y
th
e
p
a
l
m
o
il
F
B
B
r
ip
e
n
e
s
s
.
R
e
s
e
a
r
c
h
e
s
ha
ve
be
e
n
c
on
du
c
t
e
d t
o c
l
a
s
s
i
f
y
v
a
r
i
ou
s
s
t
a
g
e
s
of
r
i
pe
n
e
s
s
f
or
pa
l
m
oi
l
F
B
B
.
A
c
c
or
di
ng
t
o [
2]
m
o
s
t
of
t
h
e
pa
l
m
oi
l
g
r
a
di
ng
f
oc
u
s
e
s
o
n
t
w
o,
t
h
r
e
e
or
f
ou
r
s
t
a
g
e
s
w
hi
c
h
i
s
un
r
i
pe
,
r
e
ddi
s
h
bl
a
c
k
a
s
un
de
r
r
i
pe
,
r
e
d
a
s
r
i
pe
,
a
n
d
r
ed
d
i
s
h
o
r
an
g
e as
o
v
er
r
i
p
e.
R
e
s
ea
rc
h
b
y
[1
8
]
,
[
3
6]
,
[
37]
f
oc
u
s
on
t
w
o s
t
a
g
e
s
w
hi
c
h
a
r
e
r
i
pe
a
n
d u
n
r
i
pe
of
F
F
B
a
nd
a
c
hi
e
ve
d
hi
gh a
c
c
ur
a
c
y
r
e
s
ul
t
s
.
[
3
]
,
[
13
]
,
[
38]
,
[
3
9
]
r
eco
g
n
i
ze t
h
r
ee s
t
a
g
es
o
f
F
F
B
r
i
p
en
es
s
w
h
i
c
h
i
s
u
n
r
i
pe
,
r
i
pe
a
n
d ov
e
r
r
i
pe
w
hi
l
e
[
2]
,
[
4
0
]
w
o
r
k o
n f
o
ur
s
t
a
ge
s
w
hi
c
h i
s
u
n
r
i
pe
,
un
de
r
r
i
pe
,
r
i
pe
a
n
d ov
e
r
r
i
pe
.
A
r
ti
f
ic
ia
l
N
e
u
r
a
l
N
e
t
w
o
r
k
(
A
N
N
)
h
a
s
b
e
e
n
u
tiliz
e
d
to
c
la
s
s
i
f
y
p
a
l
m
o
il
F
F
B
i
n
to
f
o
u
r
r
ip
e
n
e
s
s
s
t
ag
e
s
[
2
]
.
H
o
w
e
v
er
,
A
N
N
t
a
k
es
a
l
o
n
g
p
r
o
ces
s
i
n
g
t
i
m
e d
u
e t
o
o
v
er
-
f
itti
n
g
is
s
u
e
.
R
e
s
e
a
r
c
h
o
n
c
o
lo
r
m
o
d
e
l
e
va
l
ua
t
i
o
n ha
ve
b
e
e
n
d
o
n
e f
o
r
m
ed
i
cal
p
l
an
t
i
d
en
t
i
f
i
er
u
s
i
n
g
t
ex
t
u
r
e f
eat
u
r
es
w
i
t
h
d
i
f
f
er
en
t
cl
as
s
i
f
i
er
s
n
a
m
el
y
S
t
o
ch
as
t
i
c G
r
ad
i
en
t
D
e
s
cen
t
(
S
G
D
)
,
k
-
n
ear
es
t
n
ei
g
h
b
o
u
r
(
k
N
N
)
,
S
u
p
p
o
r
t
v
ect
o
r
m
ac
h
i
n
e (
S
V
M
)
,
L
i
n
ear
D
i
s
c
r
i
m
i
na
nt
A
na
l
ys
i
s
(
L
D
A
)
a
nd
Q
ua
d
r
a
t
i
c
D
i
s
c
r
i
m
i
na
nt
A
na
l
ys
i
s
(
Q
D
A
)
c
l
a
s
si
f
i
e
r
s
[
41]
.
S
V
M
pr
odu
c
e
s
t
h
e b
es
t
i
d
en
t
i
f
i
cat
i
o
n
r
es
u
l
t
co
m
p
ar
ed
t
o
t
h
e o
t
h
er
cl
as
s
i
f
i
er
s
.
T
h
u
s
,
t
h
i
s
r
es
ear
ch
i
n
v
es
t
i
g
at
e
s
t
h
e
p
er
f
o
r
m
a
n
ce o
f
t
h
e
ei
g
h
t
c
o
l
o
r
m
o
d
el
s
m
en
t
i
o
n
ed
ear
l
i
er
f
o
r
f
o
u
r
s
t
ag
e
s
o
f
p
al
m
o
i
l
F
F
B
r
i
p
en
es
s
c
la
s
s
i
f
ic
a
tio
n
w
it
h
S
u
p
p
o
r
t
V
e
ct
o
r
Mach
i
n
e (
S
V
M
)
.
T
h
is
p
a
p
e
r
is
o
r
g
a
n
iz
e
d
a
s
f
o
llo
w
s
:
s
ta
r
tin
g
w
i
th
in
tr
o
d
u
c
ti
o
n
to
p
a
l
m
o
il
F
F
B
a
n
d
d
e
s
c
r
ip
tio
n
o
f
each
co
l
o
r
s
p
ace u
s
ed
i
n
t
h
i
s
r
es
ear
ch
.
T
h
e n
e
x
t
s
ec
t
i
o
n
d
i
s
cu
s
s
es
t
h
e
v
ar
i
o
u
s
co
l
o
r
m
o
d
e
l
s
ev
al
u
at
ed
i
n
t
h
i
s
r
es
ear
ch
f
o
l
l
o
w
e
d
b
y
d
i
s
c
us
s
i
o
ns
o
n r
e
s
ul
t
s
a
na
l
ys
i
s
.
T
he
l
a
s
t
s
e
c
t
i
o
n c
o
nc
l
ud
e
s
t
hi
s
p
a
p
e
r
w
i
t
h
f
ut
ur
e
w
o
r
k.
2.
R
ES
EA
R
C
H
M
ETH
O
D
2.
1.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o X
Y
Z
T
h
e v
al
u
e
s
o
f
X
Y
Z
ar
e co
m
p
u
t
ed
u
s
i
n
g
l
i
n
ear
t
r
an
s
f
o
r
m
at
i
o
n
f
r
o
m
R
G
B
co
l
o
r
co
o
r
d
i
n
at
es
as
s
h
o
w
n
in
E
q
u
a
tio
n
(1
).
(
1)
2.
2.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o L
A
B
L
ab
i
s
k
n
o
w
n
as
d
ev
i
ce
-
i
n
d
ep
en
d
an
t
co
l
o
r
m
o
d
el
w
h
er
e
L
r
ep
r
es
en
t
s
t
h
e i
m
a
g
e l
i
g
h
t
n
e
s
s
,
*
a
r
ep
r
es
en
t
s
r
ed
an
d
g
r
een
,
t
h
e
b
l
u
e/
y
el
l
o
w
co
o
r
d
i
n
at
es
o
f
co
l
o
r
-
op
p
o
ne
nt
ar
e
r
ep
r
es
en
t
ed
w
i
t
h
*
b
[
35]
T
hi
s
c
ol
or
m
o
d
e
l is
a
c
qu
i
r
e
d f
r
om
X
Y
Z
a
n
d
w
e
l
l
k
n
o
w
n
c
ol
or
m
ode
l
a
c
c
o
r
di
n
g
t
o h
um
a
n
c
ol
or
pe
r
c
e
pt
i
on
s
y
s
t
e
m
d
u
e t
o
co
m
p
r
e
h
en
s
i
v
e r
an
g
e o
f
co
l
o
r
s
a
n
d
l
i
n
ear
r
ep
r
es
en
t
at
i
o
n
[
35]
.
E
qu
a
t
i
on
s
(
2)
t
o (
4)
s
ho
w
t
h
e
c
a
l
c
u
l
a
t
i
on
o
f
L
A
B
co
l
o
r
s
p
ace.
(2
)
(3
)
(4
)
2
.
3
.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o Y
U
V
Y
U
V
i
s
k
no
w
n a
s
l
u
m
i
na
nc
e
-
ch
r
o
m
i
n
an
ce s
p
ace
w
h
er
e i
t
r
ep
r
es
en
t
s
o
n
e co
m
p
o
n
e
n
t
o
f
l
u
m
i
n
a
n
ce
an
d
t
w
o
co
m
p
o
n
en
t
s
o
f
c
h
r
o
m
i
n
an
ce.
T
h
e l
u
m
i
n
a
n
ce co
m
p
o
n
en
t
i
s
r
ep
r
es
e
n
t
ed
b
y
Y
p
r
o
d
u
ced
f
r
o
m
X
Y
Z
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
25
02
-
4752
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
,
V
o
l.
11
, N
o
.
2
,
A
ug
us
t
2018
:
5
49
–
557
552
c
ol
or
m
ode
l
w
hi
l
e
l
um
i
n
a
n
c
e
of
U
a
n
d V
a
r
e
pr
odu
c
e
d f
r
o
m
t
h
e
c
o
m
bi
n
a
t
i
on
o
f
t
h
e
Y
c
o
m
pon
e
n
t
.
E
qu
a
t
i
on
(
5)
s
h
o
w
s
t
h
e
c
onv
e
r
s
i
on
of
R
G
B
t
o Y
U
V
c
ol
or
m
ode
l
.
(5
)
2
.4
.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o H
S
V
H
S
V
t
h
a
t
i
s
de
r
i
v
e
d f
r
o
m
R
G
B
c
ol
or
m
ode
l
pr
e
s
e
nt
e
d by
H
u
e
,
S
a
tu
r
a
tio
n
a
n
d
V
a
lu
e
is
a
qu
a
n
t
i
f
i
c
a
t
i
on
of
hum
a
n
c
ol
or
v
i
s
i
o
n
.
I
t
i
s
w
i
de
l
y
us
e
d a
n
d m
or
e
s
u
i
t
a
bl
e
c
ol
or
s
pa
c
e
f
or
h
um
a
n
e
y
e
s
.
H
S
L
i
s
t
h
e al
t
er
n
at
i
v
e co
l
o
r
m
o
d
el
f
o
r
H
S
V
w
h
er
e i
t
i
s
r
ep
r
es
en
t
ed
b
y
H
-
H
ue
,
S
-
s
a
t
ur
a
t
i
o
n a
nd
L
-
l
i
gh
t
ne
s
s
.
H
ue
(
H
)
i
s
pr
odu
c
e
d
b
y
t
h
e b
as
e co
l
o
r
o
r
s
h
ad
es
i
n
t
h
e
f
o
r
m
o
f
d
eg
r
ee o
r
n
u
m
b
er
.
S
at
u
r
at
i
o
n
(
S
)
i
s
t
h
e r
at
i
o
o
f
w
h
i
t
e
c
o
l
o
r
o
r
b
r
i
ght
ne
s
s
o
f
a
ni
m
a
g
e
.
T
he
va
l
ue
(
V
)
r
e
p
r
e
s
e
nt
s
t
he
l
i
ght
ne
s
s
o
f
t
he
c
o
l
o
r
w
he
r
e
0
i
s
b
l
a
c
k a
nd
t
he
lig
h
tn
e
s
s
i
n
c
r
e
a
s
e
s
i
f
it i
s
m
o
v
e
a
w
a
y
f
r
o
m
b
la
c
k
[
42]
,
[
2
6
]
.
E
q
u
a
tio
n
s
(
6
)
to
(
9
)
illu
s
tr
a
te
th
e
tr
a
n
s
f
o
r
m
a
tio
n
f
r
o
m
R
G
B
t
o H
S
V
c
ol
or
s
pa
c
e
s
:
=
1
2
(
2
−
−
)
(
−
)
2
−
(
−
)
(
−
)
(6
)
=
(
,
,
)
+
(
,
,
)
2
(7
)
=
(
,
,
)
−
(
,
,
)
(
,
,
)
+
mi
n
(
,
,
)
<
0
.
5
(8
)
=
(
,
,
)
−
(
,
,
)
2
−
(
,
,
)
+
mi
n
(
,
,
)
≥
0
.
5
(9
)
2
.5
.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o I
1I
2I
3
T
he
I
nt
e
ns
i
t
y
-
r
e
d
,
I
nt
e
ns
i
t
y
-
g
r
een
,
I
n
t
en
s
i
t
y
-
bl
u
e
(
I
1I
2I
3)
c
ol
or
m
ode
l
w
a
s
obt
a
i
n
e
d t
hr
ou
g
h
t
h
e
de
c
or
r
e
l
a
t
i
on
of
t
h
e
R
G
B
c
ol
or
c
om
pon
e
n
t
s
us
i
n
g
t
h
e
K
–
L
t
r
a
n
s
f
or
m
b
y
[
43]
a
s
i
n
E
qu
a
t
i
on
(
10)
.
T
h
i
s
c
ol
or
m
o
d
e
l
is
p
r
o
d
u
c
e
d
f
r
o
m
R
G
B
m
a
n
ip
u
la
tio
n
.
I
t i
s
u
s
e
d
to
h
i
g
h
l
ig
h
t t
h
e
i
m
a
g
e
th
a
t c
o
n
ta
i
n
s
li
g
h
t e
f
f
e
c
ts
s
p
eci
f
i
cal
l
y
f
o
r
g
litte
r
y
o
b
j
e
c
t [
4
4
]
.
(
10)
2
.6
.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o Y
I
Q
T
h
e Y
I
Q
co
l
o
r
m
o
d
el
w
h
er
e
Y
r
e
p
r
e
s
e
nt
s
a
l
u
m
a
(
b
r
i
ght
ne
s
s
o
f
a
n i
m
a
ge
us
e
d
i
n b
l
a
c
k a
nd
w
hi
t
e
te
le
v
i
s
io
n
)
i
n
f
o
r
m
a
tio
n
,
I
st
a
n
d
s
f
o
r
“
i
n
-
p
ha
s
e
”
a
nd
t
he
Q
r
ep
r
es
en
t
s
“
q
u
ad
r
at
u
r
e” i
s
g
en
er
at
ed
f
r
o
m
c
lo
c
k
w
is
e
r
o
ta
tio
n
o
f
U
a
n
d
V
f
r
o
m
Y
U
V
c
ol
or
m
ode
l
[
45]
.
Y
I
Q
c
ol
or
m
ode
l
i
s
g
e
n
e
r
a
l
l
y
us
e
d i
n
N
a
t
i
on
a
l
T
e
le
v
is
io
n
S
y
s
te
m
C
o
m
m
itt
e
(
N
S
T
C
)
te
le
v
is
io
n
s
ta
n
d
a
r
d
[
2
6
]
.
T
h
is
c
o
lo
r
m
o
d
e
l i
s
in
te
n
d
e
d
to
ta
k
e
a
d
va
nt
a
ge
o
f
h
um
a
n
c
ol
or
-
r
e
s
p
o
ns
e
s
ho
w
n
i
n
E
qu
a
t
i
on
(
11)
.
(
11)
2
.7
.
T
r
an
s
f
or
m
at
i
on
f
r
o
m
R
G
B
t
o
YCb
Cr
T
h
e Y
C
b
C
r
co
l
o
r
m
o
d
el
co
n
s
i
s
t
s
o
f
t
h
e Y
t
h
e l
u
m
i
n
an
ce co
m
p
o
n
en
t
,
an
d
d
es
cr
i
p
t
i
o
n
o
f
c
h
r
o
m
i
n
an
ce
c
om
pon
e
n
t
r
e
pr
e
s
e
n
t
e
d b
y
C
b a
n
d C
r
c
h
a
n
n
e
l
s
.
T
h
i
s
c
ol
or
m
ode
l
u
s
e
d
in
s
k
i
n
c
o
lo
r
d
e
te
c
tio
n
d
u
e
to
d
iv
is
io
n
o
f
l
u
m
i
na
nc
e
f
r
o
m
c
hr
o
m
i
na
n
c
e
[
4
6
]
a
s
s
ho
w
n i
n E
q
ua
t
i
o
ns
(
1
2
)
t
o (
14
)
.
Y
=
0.
2
99R
+
0.
58
7G
+
0.
11
4B
(1
2
)
Cb
=
(B
–
Y
)
*
0.
56
4 +
1
28
(
13)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
I
SSN
:
2502
-
4752
E
v
al
uat
i
on of
C
ol
or
M
ode
l
s
f
or
P
al
m
O
i
l
F
r
e
s
h F
r
ui
t
B
unc
h R
i
pe
ne
s
s
…
(
N
ur
bai
t
y
Sabr
i
)
553
Cr =
(R
–
Y
)
*
0.
713
+
12
8
(
14)
a)
F
ea
t
u
re E
x
t
ra
ct
i
o
n
T
h
er
e ar
e m
an
y
t
ec
h
n
i
q
u
es
u
s
ed
i
n
co
l
o
r
f
eat
u
r
es
a
n
d
a
m
o
n
g
t
h
e p
o
p
u
l
ar
f
ea
t
u
r
es
ar
e co
l
o
r
m
o
m
en
t
[
12]
,
[
3
6]
,
[
32]
a
n
d c
ol
or
h
i
s
t
og
r
a
m
[2
]
,
[
2
2]
.
A
hi
g
h n
u
m
b
e
r
o
f
a
c
c
ur
a
c
y
ha
s
b
e
e
n a
c
hi
e
ve
d
us
i
ng c
o
l
o
r
m
o
m
e
n
t o
n
p
a
l
m
o
il F
F
B
r
e
c
o
g
n
itio
n
[3
6
].
T
h
e
re
f
o
re
,
t
h
i
s
r
es
ear
ch
i
m
p
l
e
m
e
n
t
s
co
l
o
r
m
o
m
e
n
t
f
o
r
co
l
o
r
m
o
d
e
l
a
na
l
ys
i
s
.
C
o
lo
r
m
o
m
e
n
t
f
e
a
tu
r
e
i
s
p
o
p
u
la
r
f
o
r
c
o
lo
r
d
e
te
c
tio
n
a
p
p
lic
a
tio
n
d
u
e
to
it
s
a
b
ilit
y
to
d
e
a
l
w
it
h
l
i
gh
t
i
n
g
a
n
d i
l
l
um
i
n
a
t
i
on
c
o
ndi
t
i
on
s
pe
c
i
f
i
c
a
l
l
y
f
or
pa
l
m
oi
l
g
r
a
di
ng
u
s
i
ng
R
G
B
c
ol
or
i
m
a
g
e
[
47]
.
T
h
e
m
ean
,
s
t
a
nd
a
r
d
d
e
vi
a
t
i
o
n a
nd
s
ke
w
n
e
s
s
f
o
r
e
a
c
h c
o
l
o
r
c
ha
nne
l
i
s
c
a
l
c
ul
a
t
e
d
i
s
s
ho
w
n
i
n E
q
ua
t
i
o
ns
(
1
1
)
unt
i
l
(
1
4
)
.
M
O
M
E
N
T
1
: E
q
u
a
tio
n
(
1
5
)
f
i
n
d
s
t
h
e a
v
er
ag
e
co
l
o
r
v
al
u
e o
f
a
n
i
m
ag
e
w
h
er
e N
r
ep
r
es
en
t
s
t
h
e s
i
ze o
f
an
i
m
a
g
e i
n
p
i
x
el
s
w
h
i
l
e t
h
e P
i
j
r
ep
r
es
en
t
s
t
he
p
i
xe
l
i
nt
e
ns
i
t
y
a
c
c
o
r
d
i
ng t
o
c
o
l
o
r
c
ha
n
ne
l
s
u
c
h a
s
H
/
S
/
V
,
Y
/
I
/
Q
a
nd
Y
/
U
/
V
i
n r
o
w
s
a
nd
c
o
l
u
m
ns
.
(1
5
)
M
O
M
E
N
T
2
: E
q
u
a
tio
n
(
1
6
)
,
,
i
s
al
s
o
k
n
o
w
n
as
t
h
e s
q
u
ar
e r
o
o
t
o
f
t
h
e v
ar
i
an
ce o
f
t
h
e co
l
o
r
d
is
tr
ib
u
tio
n
o
r
S
t
an
d
ar
d
D
ev
i
at
i
o
n
w
h
er
e t
h
e
cu
r
r
en
t
p
i
x
el
i
s
d
ed
u
ct
ed
f
r
o
m
t
h
e
m
ean
c
om
put
e
d i
n
E
qu
a
t
i
on
(
1
6
)
.
T
hi
s
v
al
u
e i
s
t
h
en
s
q
u
ar
e r
o
o
t
t
o
p
r
o
d
u
ce a s
t
an
d
ar
d
d
ev
i
at
i
o
n
,
.
(1
6
)
M
O
M
E
N
T
3
: E
q
u
a
tio
n
(
1
7
)
,
,
fo
r
S
k
e
w
n
e
s
s
i
s
a
m
ea
s
u
r
e o
f
t
h
e d
e
g
r
ee o
f
as
y
m
m
et
r
y
i
n
t
h
e d
i
s
t
r
i
b
u
t
i
o
n
.
T
h
e cu
r
r
en
t
p
i
x
el
i
s
d
ed
u
ct
ed
f
r
o
m
t
h
e
m
ean
v
al
u
e,
,
a
n
d s
qu
a
r
e
r
oot
of
t
h
r
e
e
t
o pr
odu
c
e
t
h
e
s
k
e
w
ne
s
s
,
,
v
al
u
e
f
r
o
m
eac
h
co
l
o
r
ch
an
n
el
.
(1
7
)
b)
Suppo
r
t
V
e
c
t
o
r
M
a
c
hi
ne
(
SV
M
)
S
V
M
is
u
s
e
d
to
d
is
c
r
i
m
i
n
a
te
m
u
ltip
le
o
b
j
e
c
ts
f
r
o
m
e
a
c
h
o
th
e
r
b
y
g
r
o
u
p
i
n
g
th
e
a
ttr
ib
u
te
o
f
e
a
c
h
acco
r
d
i
n
g
o
b
j
ect
w
i
t
h
h
o
m
o
g
en
eo
u
s
c
h
ar
act
er
i
s
t
i
c.
I
t
w
o
r
k
s
b
y
s
ep
ar
at
i
n
g
cl
a
s
s
es
i
n
t
o
p
o
s
i
t
i
v
e an
d
n
e
g
at
i
v
e
cl
as
s
es
b
y
s
ear
ch
i
n
g
f
o
r
t
h
e
m
ax
i
m
u
m
m
ar
g
i
n
ar
o
u
n
d
h
y
p
er
p
l
an
e [
8
]
.
T
h
i
s
r
es
ear
c
h
f
o
cu
s
es
o
n
S
V
M
cl
as
s
i
f
i
cat
i
o
n
t
o
cl
as
s
i
f
y
b
et
w
e
en
f
o
u
r
s
t
ag
e
s
o
f
F
F
B
u
s
i
n
g
p
o
l
y
n
o
m
i
al
k
er
n
el
f
u
n
ct
i
o
n
.
T
h
e
f
l
o
w
o
f
p
r
o
ces
s
o
f
th
is
r
e
s
e
a
r
c
h
is
s
h
o
w
n
i
n
F
i
g
u
r
e
2
.
I
t s
ta
r
ts
w
it
h
i
m
a
g
e
a
c
q
u
is
itio
n
,
p
r
e
-
pr
oc
e
s
s
i
ng
,
c
o
l
o
r
f
eat
u
r
e ex
t
r
act
i
o
n
an
d
cl
as
s
i
f
i
cat
i
o
n
at
t
h
e e
n
d
t
h
i
s
p
r
o
ces
s
.
T
h
e r
es
u
l
t
i
s
t
h
e
cl
as
s
i
f
i
cat
i
o
n
o
f
t
h
e F
F
B
r
i
p
en
es
s
g
r
ad
i
n
g
s
t
a
g
e
th
a
t is
o
v
e
r
-
r
i
pe
,
r
i
pe
,
u
n
r
i
pe
or
u
n
de
r
-
r
ip
e
.
F
i
g
ur
e
2
.
T
he
c
o
l
or
m
o
d
el
o
f
p
al
m
o
i
l
F
F
B
r
i
p
en
es
s
cl
as
s
i
f
i
cat
i
o
n
p
r
o
ces
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
25
02
-
4752
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
,
V
o
l.
11
, N
o
.
2
,
A
ug
us
t
2018
:
5
49
–
557
554
c)
D
at
a c
ol
l
e
c
t
i
on
A
b
o
u
t
5
0
0
p
al
m
o
i
l
F
B
B
co
l
o
r
i
m
ag
e
s
w
er
e cap
t
u
r
ed
b
y
a p
al
m
o
i
l
ex
p
er
t
f
r
o
m
a
n
es
t
at
e l
o
cat
ed
at
B
at
u
P
ah
at
,
J
o
h
o
r
D
ar
u
l
T
ak
zi
m
,
M
al
a
y
s
i
a,
t
h
at
co
n
s
i
s
t
s
o
f
8
7
i
m
ag
e
s
o
f
o
v
er
-
r
i
p
e
FFB
,
1
26 i
m
a
g
e
s
of
r
i
pe
F
F
B
,
109 i
m
a
g
e
s
of
un
de
r
-
r
i
p
e F
F
B
an
d
1
4
7
i
m
a
g
es
o
f
u
n
r
i
p
e F
F
B
.
T
h
es
e i
m
a
g
es
ar
e
m
an
u
al
l
y
cr
o
p
p
ed
t
o
o
b
t
ai
n
t
h
e
r
eg
i
o
n
o
f
i
n
t
er
es
t
o
r
t
h
e F
F
B
ar
ea an
d
el
i
m
i
n
at
e
t
h
e
n
o
n
-
F
F
B
ar
eas
s
u
ch
as
t
r
ees
,
l
eav
e
s
a
n
d
o
t
h
er
o
b
j
ect
s
.
T
h
es
e co
l
o
r
i
m
a
g
es
a
r
e
t
h
e
n
t
r
a
ns
f
or
m
e
d i
n
t
o 8 t
y
p
e
s
of
c
ol
or
m
ode
l
s
w
hi
c
h
a
r
e
H
S
V
,
I
1I
2I
3,
L
A
B
,
XYZ
,
YC
b
C
r
,
YI
Q,
YUV
a
n
d
R
GB
u
s
i
n
g
t
h
e
eq
u
at
i
o
n
s
e
x
p
l
ai
n
ed
ear
l
i
er
.
T
a
b
le
2
illu
s
tr
a
te
s
s
o
m
e
s
a
m
p
le
i
m
a
g
es
as
a r
es
u
l
t
o
f
t
h
e 8
co
l
o
r
m
o
d
el
s
.
T
ab
l
e 2
.
F
o
u
r
p
a
lm
o
il F
F
B
r
i
p
e
n
e
s
s
s
ta
g
e
s
w
ith
e
ig
h
t
c
ol
or
m
ode
l
s
S
t
a
g
es
M
o
d
el
s
O
v
er
-
ri
p
e
R
ip
e
U
n
r
i
p
e
U
n
d
e
r
-
ri
p
e
R
GB
L
AB
I
1
I
2
I
3
HS
V
XYZ
Y
Cb
Cr
Y
I
Q
YUV
3.
RE
S
U
L
T
S
AND D
I
S
CU
S
S
I
O
N
T
hi
s
e
xp
e
r
i
m
e
nt
i
s
c
o
nd
uc
t
e
d
us
i
n
g M
A
T
L
A
B
R
2
0
1
6
a
f
o
r
f
e
a
t
ur
e
e
xt
r
a
c
t
i
o
n a
nd
W
e
ka
f
o
r
t
he
a
n
a
l
y
s
i
s
t
ool
.
T
h
e
da
t
a
i
s
r
a
n
dom
l
y
di
vi
de
d
t
o
80%
t
r
a
i
n
i
n
g
a
n
d 20%
t
e
s
t
i
n
g
.
T
a
bl
e
3
s
h
o
w
s
t
h
e
r
i
pe
n
e
s
s
cl
as
s
i
f
i
cat
i
o
n
r
at
e f
o
r
each
co
l
o
r
m
o
d
el
b
as
ed
o
n
co
l
o
r
m
o
m
e
n
t
f
ea
t
u
r
es
w
h
er
e
i
t
i
s
co
m
p
u
t
ed
u
s
i
n
g
E
qu
a
t
i
on
14.
(
14)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
I
SSN
:
2502
-
4752
E
v
al
uat
i
on of
C
ol
or
M
ode
l
s
f
or
P
al
m
O
i
l
F
r
e
s
h F
r
ui
t
B
unc
h R
i
pe
ne
s
s
…
(
N
ur
bai
t
y
Sabr
i
)
555
T
a
b
le
3
.
R
e
s
u
lt o
f
p
a
l
m
o
il r
ip
e
n
e
s
s
c
la
s
s
if
ic
a
tio
n
r
a
t
e
f
or
t
he
8 c
ol
or
m
ode
l
s
C
o
l
o
r
M
o
d
e
l
R
i
p
en
es
s
C
l
a
s
s
i
f
i
ca
t
i
o
n
r
a
t
e (
%
)
HS
V
8
7
.
2
I1
I
2
I3
8
5
.
1
L
AB
9
7
.
2
XYZ
8
7
.
2
YCb
Cr
9
8
.
9
Y
I
Q
8
5
.
6
YUV
9
8
.
9
R
GB
6
8
.
6
B
y
o
b
s
er
v
i
n
g
t
h
e r
es
u
l
t
s
i
n
T
a
b
l
e 3
,
i
t
cl
ea
r
l
y
s
h
o
w
s
t
h
at
Y
C
b
C
r
an
d
Y
U
V
p
r
o
d
u
ce s
i
m
i
l
ar
r
i
p
en
es
s
cl
as
s
i
f
i
cat
i
o
n
r
at
e t
h
at
i
s
h
i
g
h
er
t
h
an
t
h
e o
t
h
er
co
l
o
r
m
o
d
el
s
.
I
t
can
b
e co
n
cl
u
d
ed
t
h
at
b
o
t
h
co
l
o
r
m
o
d
el
s
i
s
m
o
r
e
r
o
b
u
s
t
to
ill
u
m
i
n
a
tio
n
c
om
pa
r
e
d t
o ot
h
e
r
c
ol
or
m
od
e
l
s
.
B
e
s
i
de
s
t
h
a
t
,
i
t
a
l
s
o
s
h
o
w
s
t
h
a
t
t
h
e
s
e
c
ol
or
m
o
d
el
s
ar
e l
e
s
s
af
f
ect
ed
w
i
t
h
g
l
o
s
s
i
n
e
s
s
a
n
d
s
i
l
h
o
u
et
t
e
s
u
r
f
ace o
f
a
n
i
m
a
g
e co
m
p
ar
ed
t
o
o
t
h
er
co
l
o
r
m
o
d
el
s
.
B
o
t
h
o
f
t
h
es
e co
l
o
r
m
o
d
el
s
h
av
e t
h
e s
a
m
e i
n
co
r
r
ect
cl
as
s
i
f
i
ca
t
i
o
n
o
f
t
h
e o
v
er
r
i
p
e i
m
a
g
es
t
h
at
h
a
v
e b
een
i
n
co
r
r
ect
l
y
cl
a
s
s
i
f
i
ed
as
u
n
d
er
r
i
p
e.
T
h
i
s
m
a
y
b
e d
u
e t
o
t
h
e d
i
f
f
er
en
t
n
u
m
b
er
o
f
t
r
ai
n
i
n
g
d
at
a f
o
r
each
s
t
a
g
e o
f
r
i
p
e
n
e
s
s.
R
G
B
c
o
lo
r
m
o
d
e
l
w
it
h
o
u
t tr
a
n
s
f
o
r
m
a
tio
n
s
h
o
w
s
a
s
li
g
h
tl
y
lo
w
r
e
s
u
lt
c
o
m
p
a
r
e
d
to
th
e
o
t
h
e
r
c
o
lo
r
m
ode
l
s
.
T
h
i
s
i
s
du
e
t
o
h
i
gh c
or
r
e
l
a
t
i
on
be
t
w
e
e
n r
i
pe
,
un
r
i
pe
,
ov
e
r
-
r
i
p
e
a
nd
und
e
r
-
r
i
p
e p
al
m
o
i
l
F
F
B
i
m
ag
e
s
.
B
e
s
id
e
s
th
a
t,
t
h
is
e
x
p
e
r
i
m
e
n
t
a
ls
o
s
h
o
w
s
th
a
t t
h
e
c
o
lo
r
m
o
d
e
ls
w
it
h
d
is
c
r
i
m
in
a
t
in
g
p
o
w
e
r
s
u
c
h
a
s
H
S
V
,
L
A
B
an
d
R
G
B
ar
e n
o
t
as
s
o
ci
at
ed
w
i
t
h
t
h
e r
i
p
en
e
s
s
c
la
s
s
if
ic
a
tio
n
r
a
te
.
4.
CO
NCL
US
I
O
N
T
h
i
s
pa
pe
r
f
oc
u
s
e
s
on
t
h
e
e
f
f
e
c
t
of
a
ppl
y
i
ng
di
f
f
e
r
e
n
t
c
ol
or
m
ode
l
f
or
pa
l
m
oi
l
F
F
B
r
i
pe
n
e
s
s
cl
as
s
i
f
i
cat
i
o
n
.
E
i
g
h
t
co
l
o
r
m
o
d
el
s
h
av
e b
ee
n
co
m
p
ar
ed
i
n
t
h
i
s
r
es
ear
c
h
w
h
i
c
h
i
s
H
S
V
,
I
1
I
2
I
3
,
L
A
B
,
X
Y
Z
,
Y
Cb
Cr
,
Y
I
Q
,
Y
U
V
an
d
R
G
B
.
F
o
u
r
l
ev
el
s
o
f
p
al
m
o
i
l
r
i
p
en
es
s
h
as
b
een
a
n
al
y
zed
w
h
i
ch
i
s
r
i
p
e,
u
n
r
i
p
e,
o
v
er
-
r
i
pe
a
n
d un
de
r
-
r
i
p
e.
E
ac
h
co
l
o
r
m
o
d
el
h
a
s
i
t
s
o
w
n
c
h
ar
act
e
r
i
s
t
i
c a
n
d
d
et
er
m
i
n
at
i
o
n
p
o
w
e
r
.
Y
C
b
C
r
a
n
d
Y
U
V
co
l
o
r
m
o
d
el
s
p
r
o
d
u
ce t
h
e
h
i
g
h
e
s
t
r
i
p
en
e
s
s
cl
as
s
i
f
i
cat
io
n
f
o
r
p
a
l
m
o
il F
F
B
.
D
e
v
e
l
opm
e
n
t
o
f
m
obi
l
e
a
p
p
lic
a
tio
n
f
o
r
r
ip
e
n
e
s
s
c
la
s
s
i
f
ic
a
tio
n
w
ill b
e
a
p
p
lie
d
in
th
e
f
u
tu
r
e
.
B
e
s
id
e
s
th
a
t,
m
o
r
e
d
a
ta
w
ill b
e
c
o
lle
c
te
d
an
d
m
o
r
e co
m
p
ar
at
i
v
e
s
t
u
d
y
o
n
f
eat
u
r
es
e
x
t
r
act
ed
f
r
o
m
t
h
es
e co
l
o
r
m
o
d
el
s
a
n
d
cl
as
s
i
f
i
er
s
w
i
l
l
al
s
o
be
c
o
nd
uc
t
e
d
i
n t
he
f
ut
ur
e
.
ACK
NO
W
L
E
D
G
E
M
E
NT
T
hi
s
r
e
s
e
a
r
c
h i
s
f
i
na
nc
i
a
l
l
y
s
up
p
o
r
t
e
d
b
y
I
ns
t
i
t
ut
P
e
n
gur
us
a
n P
e
n
y
e
l
i
d
i
ka
n d
a
n I
no
va
s
i
(
I
R
M
I
)
,
U
ni
ve
r
s
i
t
i
T
e
kno
l
o
gi
M
A
R
A
w
i
t
h p
r
o
j
e
c
t
c
o
d
e
6
00
-
I
R
M
I
/
D
A
N
A
5/
3/
A
R
A
S
(
0186/
201
6)
.
R
EF
ER
EN
C
ES
[
1]
K
a
m
a
l
, M
. M
.,
M
as
azh
ar
,
A
.
N
.
I
.
,
&
R
ah
m
an
,
F
.
A
.
(
2
0
1
8
)
.
C
l
as
s
i
f
i
cat
i
o
n
o
f
L
ea
f
D
i
s
e
as
e
f
r
o
m
I
m
ag
e
P
r
o
ces
s
i
n
g
T
e
c
hni
que
.
I
n
do
ne
s
i
a
n J
o
ur
na
l
of
E
l
e
c
t
r
i
c
al
E
n
gi
ne
e
r
i
ng
an
d C
om
put
e
r
Sc
i
e
nc
e
,
10
(1
)
.
[
2]
F
ad
i
l
ah
,
N
.
,
M
o
h
am
ad
-
S
a
l
e
h
, J
.,
A
b
d
u
l
H
a
l
i
m
, Z
., I
b
r
a
h
i
m
, H
., &
S
y
e
d
A
l
i
,
S
.
(
2
0
1
2
)
.
I
n
te
llig
e
n
t C
o
l
o
r
V
is
io
n
S
y
s
t
e
m
f
o
r
R
ip
e
n
e
s
s
C
la
s
s
if
ic
a
tio
n
o
f
O
il
P
a
lm
F
r
e
s
h
F
r
u
it B
u
n
c
h
.
S
e
n
so
rs
,
1
41
79
-
14
19
5
[
3]
C
h
o
o
n
g
, T
. S
., A
b
b
a
s
, S
., S
h
a
r
i
f
f
, A
. R
., H
a
l
i
m
, R
., I
s
m
a
i
l
, M
. H
.
S
., Y
u
n
u
s
, R
., &
A
h
m
a
d
u
n
, F
. R
.
(
2
0
0
6
)
. D
i
g
i
t
a
l
i
m
a
g
e p
r
o
ces
s
i
n
g
o
f
p
a
l
m
o
il f
r
u
its
.
I
nt
e
r
n
at
i
o
nal
J
our
nal
of
F
o
od
E
ngi
ne
e
r
i
ng
,
2
(2
)
.
[
4]
D
.J
. L
e
e
, J
.K
A
r
c
h
i
b
a
l
d
, a
n
d
G
.M
. X
i
o
n
g
, “
R
api
d C
ol
or
G
r
a
di
n
g f
or
F
r
ui
t
Q
u
al
i
t
y
E
v
a
l
u
at
i
o
n U
s
i
ng D
i
r
e
c
t
C
ol
or
M
appi
ng
,
”
I
E
E
E
T
r
a
ns
a
c
t
i
ons
on
A
ut
om
a
t
i
on S
c
i
e
nc
e
a
n
d E
ng
i
ne
e
r
i
ng
,
v
ol
.
8/
2
,
p.
29
2
-
30
2,
A
pr
i
l
2
011
.
[
5]
R
.
H
u
d
zar
i
,
W
.
W
.
I
s
h
ak
an
d
M
.
N
o
r
m
an
]
,
P
ar
am
et
er
a
ccep
t
a
n
ce o
f
s
o
f
t
w
ar
e d
ev
el
o
p
m
en
t
f
o
r
o
i
l
p
al
m
f
r
u
i
t
m
a
tu
r
ity
p
r
e
d
ic
tio
n
,
J
.
So
f
t
w
.
E
ng.
,
v
ol
.
4,
20
10
,
p
p.
24
4
–
25
6.
[
6]
S
l
a
ug
ht
e
r
,
D
.
C
.
,
C
r
i
s
os
t
o,
C
.
H
.
,
&
T
i
w
a
r
i
,
G
.
(
2013)
.
N
o
nde
s
t
r
u
c
tiv
e
d
e
te
r
m
in
a
tio
n
o
f
f
le
s
h
c
o
lo
r
in
c
lin
g
s
to
n
e
p
each
es
.
J
our
n
al
of
F
oo
d E
ngi
ne
e
r
i
ng,
11
6(
4)
,
9
20e
9
25
.
)
[
7]
P
a
l
a
p
o
l
, Y
., K
e
t
s
a
, S
., S
t
e
v
e
n
s
o
n
, D
., C
o
o
n
e
y
, J
. M
., A
l
l
a
n
,
A
. C
.
, &
F
e
r
g
u
s
o
n
, I
. B
. (
2
0
0
9
)
. C
o
l
o
u
r
d
e
v
e
l
o
p
m
e
n
t
an
d
q
u
al
i
t
y
o
f
m
an
g
o
s
t
een
(
g
ar
ci
n
i
am
a
ng
os
t
a
na
L
.
)
f
r
ui
t
dur
i
ng
r
i
pe
ni
ng
a
n
d a
f
t
e
r
ha
r
v
e
s
t
.
P
os
t
h
ar
v
e
s
t
B
i
ol
o
gy
a
nd
T
e
c
hnol
ogy
,
5
1(
3)
,
3
49e
3
53
.
)
[
8]
E
l
-
B
en
d
ar
y
,
N
.
,
E
l
H
ar
i
r
i
,
E
.
,
E
l
l
a H
as
s
an
i
en
,
A
.
,
&
B
ad
r
,
A
.
(
2
0
1
5
)
.
U
s
i
n
g
m
ach
i
n
e l
ear
n
i
n
g
t
ech
n
i
q
u
es
f
o
r
ev
al
u
at
i
n
g
t
o
m
at
o
r
i
p
en
es
s
.
E
xp
er
t
S
ys
t
em
s
w
ith
A
p
p
lic
a
ti
o
n
s
,
V
ol
u
m
e
42,
I
s
s
ue
4,
18
92
-
19
05.
[
9]
Z
ha
ng
,
D
o
ng
,
e
t
a
l
.
"
D
a
t
e
m
a
t
ur
i
t
y
a
nd qua
l
i
t
y
e
v
a
l
ua
t
i
on us
i
ng
c
ol
or
di
s
t
r
i
b
ut
i
o
n a
n
a
l
y
s
i
s
a
nd ba
c
k
p
r
o
je
c
tio
n
.
"
J
our
nal
of
F
o
od
E
n
gi
ne
e
r
i
ng
13
1
(
2
01
4)
:
16
1
-
16
9.
[
1
0]
G
u
e
r
r
e
r
o
, E
. R
., &
B
e
n
a
v
i
d
e
s
, G
.
M
. (
2
0
1
4
,
J
u
ne
)
.
A
ut
om
a
t
e
d s
y
s
t
e
m
f
or
c
l
a
s
s
i
f
y
i
ng
H
a
s
s
a
v
oc
a
dos
ba
s
e
d on i
m
a
g
e
pr
oc
e
s
s
i
ng
t
e
c
hni
que
s
.
I
n
C
om
m
u
ni
c
at
i
ons
an
d
C
om
put
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SSN
:
25
02
-
4752
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
,
V
o
l.
11
, N
o
.
2
,
A
ug
us
t
2018
:
5
49
–
557
556
[
1
1]
J
a
f
f
a
r
,
A
.
,
J
a
a
f
a
r
,
R
.
,
J
a
m
i
l
,
N
.
,
L
ow
,
C
.
Y
.
,
&
A
bd
ul
l
a
h,
B
.
(
20
09)
.
P
h
ot
og
r
a
m
m
e
t
r
i
c
g
r
a
di
ng
of
oi
l
pa
l
m
f
r
e
s
h f
r
ui
t
bunc
he
s
.
I
n
t.
J.
M
ech
.
M
ech
a
t
r
o
n
.
E
n
g
,
9
, 1
8
-
24.
[
1
2]
W
B
udi
ha
r
t
o,
A
S
a
nt
os
o,
D
P
ur
w
a
nt
o,
A
J
a
z
i
di
e
.
M
ul
t
i
pl
e
m
ov
i
ng
obs
t
a
c
l
e
s
a
v
oi
da
nc
e
of
s
e
r
v
i
c
e
r
obot
us
i
ng
s
t
e
r
e
o
v
is
io
n
.
T
E
L
K
O
M
N
I
K
A
(
T
e
l
e
c
om
m
uni
c
at
i
o
n,
C
om
put
i
n
g,
E
l
e
c
t
r
o
n
i
c
s
and
C
o
nt
r
ol
)
.
2
01
1;
9(
3)
:
4
33
-
444
.
[
1
3]
Ja
m
i
l
,
N.
,
M
oha
m
e
d,
A
.
,
&
A
bdul
l
a
h,
S
.
(
20
09
)
.
A
ut
om
at
e
d G
r
a
di
ng of
P
a
l
m
O
i
l
F
r
e
s
h F
r
ui
t
B
unc
he
s
(
F
F
B
)
us
i
ng
N
eu
r
o
-
F
u
z
z
y T
ech
n
i
q
u
e.
I
n
t
e
r
na
t
i
ona
l
C
onf
e
r
e
nc
e
of
S
of
t
C
om
put
i
ng
a
nd
P
a
t
t
e
r
n R
e
c
og
ni
t
i
on
.
[
1
4]
W
.
I
.
W
.
I
s
ha
k
a
nd M
.
H
.
R
a
z
a
l
i
,
H
ue
opt
i
c
a
l
pr
ope
r
t
i
e
s
t
o
m
ode
l
o
i
l
pa
l
m
f
r
e
s
h
f
r
ui
t
bunc
he
s
m
a
t
ur
i
t
y
i
nde
x
,
W
or
l
d
M
u
lti
-
C
onf
e
r
e
nc
e
on S
y
s
t
e
m
i
c
s
,
C
y
be
r
ne
t
i
c
s
a
nd
P
a
t
t
e
r
n
R
e
c
og
ni
t
i
on,
2
01
0.
[
1
5]
W
a
ng
,
Y
.
,
L
i
,
W
.
,
P
a
ng
,
S
.
,
&
K
a
n,
J
.
(
2
01
3)
.
S
e
g
m
e
nt
a
t
i
on m
e
t
hod of
L
i
ngw
u l
ong
j
uj
ube
s
ba
s
e
d o
n L
*
a
*
b
*
c
ol
or
s
p
ace.
I
ndo
ne
s
i
a
n J
o
ur
na
l
of
E
l
e
c
t
r
i
c
al
E
n
gi
ne
e
r
i
ng
an
d C
om
put
e
r
Sc
i
e
nc
e
,
11
(
9
)
,
53
44
-
53
51
.
[
1
6]
H
u
an
g
,
L
.
,
&
H
e,
D
.
(
2
0
1
2
)
.
R
i
p
e f
u
j
i
ap
p
l
e
d
et
ect
i
o
n
m
o
d
el
an
al
y
s
i
s
i
n
n
at
u
r
al
t
r
ee can
o
p
y
.
I
nd
on
e
s
i
an
J
o
ur
n
al
of
E
l
ect
r
i
ca
l
E
n
g
i
n
eer
i
n
g
a
n
d
C
o
m
p
u
t
er
S
ci
en
ce
,
10
(
7
)
,
17
71
-
17
78
.
[
1
7]
S
y
a
hr
i
r
,
W
.
,
S
ur
y
a
nt
i
,
A
.
,
&
C
onns
y
nn,
C
.
(
20
09)
.
C
ol
or
gr
ad
i
ng i
n T
om
at
o M
a
t
ur
i
t
y
E
s
t
i
m
a
t
or
us
i
n
g i
m
a
ge
pr
oc
e
s
s
i
ng t
e
c
hn
i
q
ue
.
C
om
put
e
r
S
c
i
e
nc
e
a
nd I
nf
or
m
a
t
i
on T
e
c
hnol
ogy
,
200
9.
I
C
C
S
I
T
200
9.
2
nd I
E
E
E
I
nt
e
r
na
t
i
ona
l
C
o
n
f
er
en
ce o
n
.
[
1
8]
R
o
s
el
een
a,
J
.
,
N
u
r
s
u
r
i
at
i
,
J
.
,
A
hm
e
d,
J
.
,
&
L
ow
,
C
.
(
20
11)
.
A
s
s
e
s
s
m
e
nt
of
pa
l
m
oi
l
f
r
e
s
h f
r
ui
t
bu
nc
he
s
us
i
ng
p
h
o
t
o
g
r
am
m
et
r
i
c g
r
ad
i
n
g
s
y
s
t
e
m
.
I
nt
e
r
na
t
i
o
nal
F
o
od
R
e
s
e
ar
c
h J
ou
r
nal
,
9
99
-
10
05
.
[
1
9]
S
h
ah
R
i
zam
,
M
.
S
.
B
.
,
F
ar
ah
Y
as
m
i
n
,
A
.
R
.
,
A
h
m
ad
I
h
s
an
,
M
.
Y
.
,
&
S
h
azan
a,
K
.
(
2
0
0
9
)
.
N
o
n
-
de
s
t
r
uc
tiv
e
w
at
er
m
el
o
n
r
i
p
en
es
s
d
et
er
m
i
n
at
i
o
n
u
s
i
n
g
i
m
ag
e p
r
o
ces
s
i
n
g
an
d
ar
t
i
f
i
ci
al
n
eu
r
al
n
et
w
o
r
k
(
A
N
N
)
.
I
n
t
e
r
na
t
i
on
al
J
our
n
al
o
f
E
l
e
c
t
r
i
c
al
an
d C
om
pu
t
e
r
E
ngi
ne
e
r
i
ng
,
4
(6
)
.
[
2
0]
M
oha
m
a
di
,
H
.
M
.
,
A
l
i
m
a
r
da
ni
,
R
.
,
&
O
m
i
d,
M
.
(
2
01
1)
.
D
e
t
e
c
t
i
on
of
r
e
d r
i
pe
t
om
a
t
oe
s
on s
t
e
m
us
i
ng
I
m
a
ge
P
r
oc
e
s
s
i
ng
T
e
c
hni
que
s
.
Jo
u
r
n
a
l
o
f
A
m
er
i
ca
n
S
ci
en
ce
.
[
2
1]
C
ha
ud
ha
r
y
,
P
.
,
C
ha
u
dha
r
i
,
A
.
K
.
,
C
he
e
r
a
n,
D
.
,
&
G
oda
r
a
,
S
.
(
2
01
2)
.
C
o
l
or
T
r
a
ns
f
or
m
B
a
s
e
d A
ppr
oa
c
h f
or
D
i
s
e
a
s
e
S
pot
D
e
t
e
c
t
i
on on
P
l
a
nt
L
e
a
f
.
I
nt
e
r
nat
i
o
nal
J
our
nal
of
C
om
p
ut
e
r
S
c
i
e
nc
e
and
T
e
l
e
c
om
m
uni
c
at
i
o
ns
.
[
2
2]
H
er
n
án
d
ez
-
H
er
n
án
d
ez,
J
.
,
H
er
n
án
d
ez
-
H
er
n
án
d
ez,
M
.
,
F
el
i
ci
an
o
-
M
o
r
al
es
,
S
.
,
Á
l
v
ar
ez
-
H
i
l
ar
i
o
,
V
.
,
&
H
er
r
er
a
-
M
i
r
a
nda
,
I
.
(
20
17)
.
S
e
a
r
c
h f
or
O
pt
i
m
u
m
C
ol
or
S
pa
c
e
f
or
t
he
R
e
c
og
ni
t
i
on of
O
r
a
ng
e
s
i
n
A
g
r
i
c
ul
t
ur
a
l
F
i
e
l
ds
.
Spr
i
n
ge
r
I
nt
e
r
n
at
i
on
al
P
ubl
i
s
hi
ng
,
2
96
–
30
7.
[
2
3]
J
i
d
o
n
g
, L
., W
e
i
, J
., F
e
n
g
y
i
, C
., D
e
a
n
, Z
., &
B
o
,
X
. (
2
0
1
2
)
.
R
e
s
e
ar
c
h o
n t
he
R
e
c
ogn
i
t
i
o
n M
e
t
ho
d f
or
O
bs
c
ur
e
d A
p
pl
e
i
n N
a
t
ur
a
l
E
nv
i
r
onm
e
nt
.
P
r
oc
e
e
di
ng
s
of
t
he
31s
t
C
hi
ne
s
e
C
ont
r
ol
C
onf
e
r
e
nc
e
.
[
2
4]
X
i
a
o
, A
., L
i
, W
., H
u
a
n
g
, X
., W
a
n
g
, L
., C
h
a
i
, X
., &
L
i
,
C
.
(
2013)
.
T
he
R
e
s
e
a
r
c
h O
f
D
e
t
e
c
t
i
ona
l
M
e
t
hod O
n C
hi
ne
s
e
D
a
t
e
s
J
i
a
ng
t
ou B
a
s
e
d O
n C
hr
om
i
na
nc
e
C
om
pone
nt
A
nd I
m
a
ge
M
or
p
hol
og
y
.
J
our
nal
O
f
T
he
or
e
t
i
c
al
A
n
d A
p
pl
i
e
d
I
nf
or
m
at
i
o
n T
e
c
h
nol
ogy
.
[
2
5]
P
, G
., &
V
, R
. (
2
0
1
4
)
.
Y
I
Q
C
ol
o
r
Spac
e
bas
e
d
Sat
e
l
l
i
t
e
I
m
age
Se
gm
e
n
t
at
i
o
n us
i
n
g M
odi
f
i
e
d F
C
M
C
l
us
t
e
r
i
ng a
nd
H
i
s
t
ogr
am
E
q
ual
i
z
at
i
o
n.
I
n
t
er
n
at
i
o
n
al
C
o
n
f
er
en
ce o
n
A
d
v
an
ce i
n
E
l
ect
r
i
cal
E
n
g
i
n
eer
i
n
g
,
1
-
5.
[
2
6]
w
i
c
hl
,
K
.
,
S
huk
l
a
,
R
.
,
&
S
ha
h,
A
.
K
.
(
20
17)
.
C
ol
or
I
m
a
g
e
S
e
gm
e
nt
a
t
i
on
us
i
ng
F
C
M
C
l
us
t
e
r
i
ng
T
e
c
hni
que
i
n R
G
B
,
L
*
a
*
b
, H
S
V
, Y
I
Q
C
o
l
o
r
s
p
aces
.
E
ur
ope
an J
our
n
al
of
A
dv
a
nc
e
s
i
n
E
ng
i
ne
e
r
i
ng
a
nd
T
e
c
hn
ol
o
gy
,
1
94
-
2
00.
[
2
7]
N
a
r
ot
e
,
A
.
S
.
,
&
W
a
g
h
m
a
r
e
,
L
.
M
.
(
2
01
7)
.
C
ol
or
I
r
i
s
A
ut
he
nt
i
c
a
t
i
on
us
i
ng
C
o
l
or
M
o
de
l
s
.
I
nt
e
r
n
at
i
on
al
J
o
ur
n
al
o
f
C
om
put
e
r
A
pp
l
i
c
at
i
ons
.
[
2
8]
S
uha
s
i
n
i
,
A
.
,
&
T
he
ndr
a
l
,
R
.
(
2
01
7)
.
A
u
to
m
a
te
d
s
k
in
d
e
f
e
c
t id
e
n
tif
ic
a
tio
n
s
y
s
te
m
.
C
u
r
r
en
t
S
ci
en
ce
.
[
2
9]
X
i
o
n
g
,
J
., L
i
n
, R
.
, L
i
u
,
Z
.
, H
e
, Z
., T
a
n
g
, L
., Y
a
n
g
, Z
., e
t
a
l
.
(
2
0
1
7
)
.
T
h
e
r
e
c
o
g
n
i
t
i
o
n
o
f
l
i
t
c
h
i
c
l
u
s
t
e
r
s
a
n
d
t
h
e
c
a
l
c
ul
a
t
i
on
of
pi
c
k
i
ng
poi
nt
i
n a
n
oc
t
ur
na
l
na
t
ur
a
l
e
nv
i
r
onm
e
nt
.
b
i
o
sy
st
e
ms
e
ngi
ne
e
r
i
ng
, 4
4
-
5
7.
[
3
0]
T
o
y
l
a
n ,
H
.
,
&
K
us
c
u ,
H
.
(
2014)
.
A
R
e
a
l
-
T
i
m
e
A
ppl
e
G
r
a
di
ng
S
y
s
t
e
m
U
s
i
ng
M
ul
t
i
c
ol
or
S
pa
c
e
.
T
h
e
S
c
ie
n
tific
W
or
l
d J
our
nal
.
[
31]
B
la
s
c
o
,
J
.
,
A
le
ix
o
s
,
N
.
,
G
ó
m
e
z
,
J
.
,
&
M
o
ltó
,
E
.
(
2
0
0
7
)
.
C
itr
u
s
s
o
r
tin
g
b
y
id
e
n
tif
ic
a
ti
o
n
o
f
th
e
m
o
s
t
co
m
m
o
n
d
ef
ect
s
u
s
in
g
m
u
l
tis
p
e
c
tr
a
l c
o
m
p
u
te
r
v
i
s
io
n
.
J
our
nal
of
F
ood
E
ngi
ne
e
r
i
ng
,
83
(
3)
,
384
-
393.
)
[
3
2]
A
l
f
at
n
i
,
M
.
S
.
,
M
o
h
am
ed
S
h
ar
i
f
f
,
A
.
,
A
b
d
u
l
l
ah
,
M
.
,
B
e
n
S
aeed
,
O
.
,
&
M
.
C
ees
a
y
,
O
.
(
2
0
1
1
)
.
R
ecen
t
M
et
h
o
d
s
an
d
T
e
c
hni
que
s
of
E
x
t
e
r
na
l
G
r
a
di
ng
S
y
s
t
e
m
s
f
or
A
g
r
i
c
ul
t
ur
a
l
C
r
op
s
Q
u
a
lity
I
n
s
p
e
c
tio
n
-
R
ev
i
ew
.
I
nt
e
r
nat
i
on
al
J
o
ur
n
al
of
F
oo
d E
ngi
ne
e
r
i
ng
.
[
3
3]
V
y
a
s
,
A
.
M
.
,
T
a
l
a
t
i
,
B
.
,
&
N
a
i
k
,
S
.
(
20
13)
.
C
o
l
o
ur
F
e
a
t
ur
e
E
x
t
r
a
c
t
i
on T
e
c
hni
que
s
of
F
r
ui
t
s
:
A
S
ur
ve
y
.
I
nt
e
r
nat
i
o
nal
J
our
n
al
o
f
C
om
put
e
r
A
ppl
i
c
at
i
on
s
.
[
3
4]
L
u
s
z
c
z
k
i
e
w
i
c
z
-
P
i
a
t
e
k
,
M
.
(
20
14)
.
W
hi
c
h c
ol
or
s
pa
c
e
s
houl
d be
c
hos
e
n f
or
r
ob
us
t
c
ol
or
i
m
a
g
e
r
e
t
r
i
e
v
a
l
ba
s
e
d on
m
i
x
t
ur
e
m
ode
l
i
ng
.
I
m
age
P
r
oc
e
s
s
i
ng
an
d C
om
m
uni
c
at
i
o
ns
C
h
al
l
e
n
ge
s
,
55
-
64
.
[
3
5]
C
he
n,
X
.
,
&
Y
a
ng
,
S
.
X
.
(
20
13)
.
A
pr
a
c
t
i
c
a
l
s
ol
ut
i
o
n f
or
r
i
pe
t
om
a
t
o r
e
c
og
ni
t
i
o
n a
nd l
oc
a
l
i
s
a
t
i
on
.
J
our
na
l
o
f
R
e
al
-
T
i
m
e I
m
a
g
e P
r
o
ces
s
i
n
g
, 3
5
-
51.
[
3
6]
S
a
br
i
,
N
.
,
I
br
a
hi
m
,
Z
.
,
S
y
a
hl
a
n,
S
.
,
J
a
m
i
l
,
N
.
,
&
M
a
ng
s
hor
,
N
.
N
.
A
.
(
2017)
.
P
a
l
m
oi
l
f
r
e
s
h
f
r
ui
t
bunc
h r
i
pe
ne
s
s
g
r
a
d
in
g
id
e
n
tif
ic
a
tio
n
u
s
in
g
c
o
lo
r
f
e
a
tu
r
e
s
.
J
our
n
al
of
F
un
dam
e
nt
al
and
A
p
pl
i
e
d
Sc
i
e
nc
e
s
,
9
(
4
S
),
56
3
-
579
.
[
3
7]
A
,
H
.
,
N
,
S
.
,
&
M
.
A
,
R
.
(
2
01
7)
.
A
ppl
i
c
a
t
i
on
of
I
nt
e
g
r
a
t
e
d A
H
P
a
nd T
O
P
S
I
S
T
e
c
hni
que
s
f
or
D
e
t
e
r
m
i
ni
ng
t
he
B
e
s
t
F
re
s
h
F
ru
i
t
Bu
n
c
h
e
s
(F
F
B)
.
J
o
ur
n
al
o
f
T
e
l
e
c
om
m
u
ni
c
at
i
on
E
l
e
c
t
r
on
i
c
an
d C
om
put
e
r
E
ngi
ne
e
r
i
ng
.
[
3
8]
M
o
h
am
m
ed
B
en
S
aeed
,
O
.
,
S
an
k
ar
an
,
S
.
,
M
o
h
am
ed
S
h
a
r
i
f
f
,
A
., M
o
h
d
S
h
a
f
r
i
, H
., E
h
s
a
n
i
, R
., A
l
f
a
t
n
i
, M
.
S
., e
t
a
l
.
(
20
12)
.
C
l
a
s
s
i
f
i
c
a
t
i
on of
oi
l
pa
l
m
f
r
e
s
h
f
r
ui
t
bunc
he
s
ba
s
e
d on t
he
i
r
m
a
t
ur
i
t
y
us
i
ng
por
t
a
bl
e
f
our
-
b
a
n
d
se
n
so
r
sy
st
e
m
.
C
om
put
e
r
s
an
d
E
l
e
c
t
r
o
ni
c
s
i
n A
g
r
i
c
ul
t
ur
e
, 5
5
–
6
0.
[
3
9]
H
u
d
zar
i
,
R
.
,
W
an
I
s
h
ak
,
W
.
,
&
N
o
o
r
m
an
,
M
.
(
2
0
1
0
)
.
P
ar
am
et
er
accep
t
an
ce o
f
s
o
f
t
w
ar
e d
ev
el
o
p
m
en
t
f
o
r
o
i
l
p
al
m
f
r
u
it m
a
tu
r
ity
p
r
e
d
ic
tio
n
.
J
our
nal
of
S
of
t
w
ar
e
E
n
gi
ne
e
r
i
n
g
,
2
44
-
25
6.
[
4
0]
J
una
i
da
h
,
M
.
J
.
,
N
or
i
z
z
a
h,
A
.
R
.
,
Z
a
l
i
ha
,
O
.
,
&
M
oha
m
a
d,
S
.
(
2
015
)
.
O
pt
i
m
i
s
a
t
i
on of
s
t
e
r
i
l
i
s
a
t
i
o
n pr
o
ces
s
f
o
r
o
i
l
pa
l
m
f
r
e
s
h f
r
ui
t
bunc
h
a
t
di
f
f
e
r
e
nt
r
i
pe
ne
s
s
.
I
n
t
e
r
nat
i
on
al
F
o
od R
e
s
e
ar
c
h J
our
n
al
,
22
(1
).
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nd
o
ne
s
i
a
n J
E
l
e
c
E
ng
&
C
o
m
p
S
c
i
I
SSN
:
2502
-
4752
E
v
al
uat
i
on of
C
ol
or
M
ode
l
s
f
or
P
al
m
O
i
l
F
r
e
s
h F
r
ui
t
B
unc
h R
i
pe
ne
s
s
…
(
N
ur
bai
t
y
Sabr
i
)
557
[
4
1]
A
r
un,
C
.
,
&
D
ur
a
i
r
a
j
,
D
.
(
2017)
.
I
de
nt
i
f
y
i
ng
M
e
di
c
i
na
l
P
l
a
nt
L
e
a
v
e
s
U
s
i
ng
T
e
x
t
ur
e
s
A
nd O
pt
i
m
a
l
C
ol
our
S
pa
c
e
s
C
ha
nne
l
.
J
our
nal
of
C
om
p
ut
e
r
Sc
i
e
nc
e
an
d I
nf
or
m
at
i
on
,
19
-
28
.
[
4
2]
S
hi
pm
a
n,
J
.
W
.
(
2012,
10 1
6)
.
I
nt
r
od
uc
t
i
on t
o c
ol
or
t
he
or
y
.
R
e
t
r
i
e
v
e
d 12 21,
20
17,
f
r
om
N
e
w
M
e
x
i
c
o
T
e
c
h:
ht
t
p:
/
/
i
nf
oh
os
t
.
nm
t
.
e
du/
t
c
c
/
he
l
p/
p
ubs
/
c
ol
or
t
he
or
y
/
w
e
b/
hs
v
.
ht
m
l
[
4
3]
O
ht
a
,
Y
.
I
.
,
K
a
na
de
,
T
.
,
&
S
a
k
a
i
,
T
.
(
198
0)
.
C
ol
or
i
nf
or
m
a
t
i
on f
or
r
e
g
i
on s
e
gm
e
nt
a
t
i
on.
C
om
pu
t
e
r
gr
aph
i
c
s
an
d
i
m
age
pr
oc
e
s
s
i
ng
,
13
(
3)
,
22
2
-
24
1.
[
4
4]
B
i
m
bo,
A
.
D
.
(
2016)
.
R
e
s
our
c
e
s
:
M
I
C
C
M
e
di
a I
nt
e
gr
at
i
on
an
d C
o
m
m
uni
c
at
i
on C
e
nt
e
r
.
R
e
t
r
i
e
v
e
d 12 22
,
2
01
7,
f
r
om
M
I
C
C
M
e
di
a
I
nt
e
g
r
a
t
i
on a
nd C
o
m
m
uni
c
a
t
i
on C
e
nt
e
r
:
h
ttp
s
:/
/w
w
w
.
m
ic
c
.
u
n
if
i.
it/r
e
s
o
u
r
c
e
s
/
[
4
5]
P
la
ta
n
io
t
is
,
K
.
N
.
,
&
V
e
ne
t
s
a
nop
oul
os
,
A
.
N
.
(
2013)
.
C
ol
or
i
m
a
ge
pr
oc
e
s
s
i
ng an
d ap
pl
i
c
at
i
o
ns
.
S
p
r
i
n
g
er
S
ci
en
ce &
B
u
s
i
n
es
s
M
ed
i
a.
[
4
6]
Z
ah
er
H
am
i
d
A
l
-
T
ai
r
i
,
R
ah
m
i
t
a
W
i
r
zaR
ah
m
at
,
M
.
I
q
b
al
S
ar
i
p
an
an
d
P
u
t
er
i
S
u
h
ai
zaS
u
l
ai
m
an
,
“S
k
i
n
s
eg
m
en
t
at
i
o
n
us
i
ng
Y
U
V
a
nd R
G
B
c
ol
or
s
pa
c
e
s
”
i
n J
our
nal
of
I
nf
or
m
at
i
on
P
r
oc
e
s
s
i
ng Sy
s
t
e
m
s
(
J
IP
S
),
(
20
14)
,
p
p.
283
~
2
99
[
4
7]
A
M
unt
a
s
a
,
I
A
S
i
r
a
j
udi
n,
M
H
P
ur
n
om
o.
A
ppe
a
r
a
nc
e
g
l
oba
l
a
nd
l
oc
a
l
s
t
r
uc
t
ur
e
f
us
i
o
n f
or
f
a
c
e
i
m
a
g
e
r
e
c
og
ni
t
i
on.
T
E
L
K
O
M
N
I
K
A
(
T
e
l
e
c
om
m
uni
c
at
i
on,
C
om
p
ut
i
ng
,
Ele
c
tr
o
n
ic
s
a
n
d
C
o
n
tr
o
l)
.
2
01
1;
9 (
1)
:
1
25
-
1
32
.
Evaluation Warning : The document was created with Spire.PDF for Python.