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
.
799
~
805
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
9
.
i3
.
p
p
7
9
9
-
805
799
J
o
ur
na
l h
o
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
Ca
ss
a
v
a
Q
ua
lity Cla
ss
ificatio
n f
o
r
Ta
pio
ca
F
lo
ur In
g
redients
by
Using
ID3
Alg
o
rith
m
Yo
ha
ns
s
en
P
ra
t
a
m
a
1
,
H
a
di
Su
t
a
nto
Sa
ra
g
i
2
1
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
c
s an
d
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
De
l
In
st
it
u
te
o
f
T
e
c
h
n
o
lo
g
y
,
S
u
m
a
tera
Uta
ra
,
In
d
o
n
e
sia
2
F
a
c
u
lt
y
o
f
In
d
u
stria
l
E
n
g
in
e
e
rin
g
,
De
l
In
stit
u
te o
f
T
e
c
h
n
o
lo
g
y
,
Jl.
S
isin
g
a
m
a
n
g
a
ra
ja,
S
it
o
lu
a
m
a
,
T
o
b
a
S
a
m
o
sir,
S
u
m
a
tera
Uta
r
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
6
,
2
0
1
8
R
ev
i
s
ed
Feb
1
5
,
2
0
1
8
A
cc
ep
ted
Feb
2
3
,
2
0
1
8
Ca
ss
a
v
a
is
o
n
e
o
f
th
e
m
a
in
f
o
o
d
s
c
o
n
su
m
e
d
b
y
In
d
o
n
e
sia
n
p
e
o
p
le
a
n
d
m
a
in
in
g
re
d
ien
ts
to
m
a
k
e
tap
io
c
a
f
lo
u
r.
In
No
rt
h
S
u
m
a
tera
th
e
re
is
f
a
c
to
ry
th
a
t
p
ro
d
u
c
e
d
tap
i
o
c
a
f
lo
u
r
to
f
u
lf
il
l
c
o
n
su
m
e
r
d
e
m
a
n
d
.
T
o
b
e
a
b
le
to
m
e
e
t
th
e
n
e
e
d
s
o
f
c
o
n
s
u
m
e
rs
a
n
d
se
ize
m
a
rk
e
t
sh
a
re
,
th
e
p
r
o
d
u
c
t
m
u
st
h
a
v
e
a
g
o
o
d
q
u
a
li
ty
.
P
r
o
d
u
c
t
sp
e
c
if
ica
ti
o
n
s
a
re
a
re
f
e
re
n
c
e
f
o
r
p
ro
d
u
c
t
q
u
a
li
ty
a
n
d
m
e
a
su
re
d
w
it
h
7
p
a
ra
m
e
ter
s.
T
h
e
se
v
e
n
p
a
ra
m
e
ters
in
c
lu
d
e
w
h
it
e
n
e
ss
,
m
o
istu
re
c
o
n
ten
t,
sp
o
tn
e
ss
,
a
sh
c
o
n
ten
t,
t
h
in
n
e
ss
,
re
sid
u
a
l
sc
re
e
n
,
p
H
f
lo
u
r
,
w
h
ich
m
e
e
ts
th
e
In
d
o
n
e
sia
n
Na
ti
o
n
a
l
S
tan
d
a
rd
.
I
n
th
is
re
se
a
rc
h
we
u
se
t
w
o
p
a
ra
m
e
ters
(
w
h
it
e
n
e
ss
a
n
d
sp
o
tn
e
ss
)
to
d
e
term
in
e
th
e
q
u
a
li
ty
o
f
c
a
ss
a
v
a
a
n
d
h
e
lp
t
h
e
f
a
c
to
r
y
to
m
a
in
tain
th
e
i
r
p
ro
d
u
c
t
q
u
a
li
ty
.
In
h
e
re
w
e
u
s
e
b
lo
b
a
n
d
e
d
g
e
d
e
tec
ti
o
n
m
e
th
o
d
in
im
a
g
e
p
ro
c
e
ss
in
g
to
d
e
tec
t
sp
o
t
a
n
d
a
f
ter
th
a
t
c
las
si
f
ied
th
e
c
a
ss
a
v
a
b
y
u
sin
g
a
n
ID3
a
lg
o
rit
h
m
.
K
ey
w
o
r
d
s
:
A
l
g
o
rit
h
m
Ca
ss
a
v
a
ID3
Im
a
g
e
P
r
o
c
e
ss
in
g
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
:
Yo
h
an
s
s
e
n
P
r
ata
m
a
,
Facu
lt
y
o
f
I
n
d
u
s
tr
ial
E
n
g
in
ee
r
in
g
,
Del
I
n
s
tit
u
te
o
f
T
ec
h
n
o
lo
g
y
,
Jl.
S
isin
g
a
m
a
n
g
a
r
a
ja,
S
it
o
l
u
a
m
a
,
T
o
b
a
S
a
m
o
sir,
S
u
m
a
tera
Ut
a
ra
,
In
d
o
n
e
sia
,
T
e
l:
+
6
2
6
3
2
3
3
1
2
3
4
E
m
ail:
y
o
h
a
n
s
s
en
.
p
r
ata
m
a
@
d
el.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
P
r
o
d
u
ct
q
u
alit
y
i
s
a
m
ea
s
u
r
e
o
f
th
e
n
u
m
b
er
o
f
co
n
s
u
m
er
s
w
h
o
co
n
s
u
m
e
th
e
m
.
T
h
e
co
m
p
a
n
y
th
a
t
p
r
o
d
u
ce
d
ca
s
s
av
a
m
u
s
t
b
e
ab
le
to
co
m
p
ete
in
m
ar
k
e
t
s
h
ar
e.
T
o
attr
ac
t
th
e
co
n
s
u
m
er
s
,
th
e
co
m
p
a
n
y
m
u
s
t
i
m
p
r
o
v
e
t
h
e
q
u
alit
y
o
f
th
e
f
l
o
u
r
in
p
r
o
d
u
ctio
n
.
Sp
ec
i
f
icati
o
n
o
f
t
h
is
tap
io
ca
f
lo
u
r
w
h
ic
h
b
ec
o
m
e
i
n
d
icato
r
q
u
alit
y
o
f
tap
io
ca
f
lo
u
r
is
i
m
p
o
r
ta
n
t.
T
h
e
s
p
ec
if
icatio
n
o
f
tap
io
ca
f
lo
u
r
is
a
b
en
c
h
m
ar
k
o
f
f
lo
u
r
q
u
alit
y
m
ea
s
u
r
ed
b
y
s
ev
er
al
p
ar
a
m
e
te
r
s
.
E
ac
h
p
ar
am
e
ter
m
u
s
t c
o
m
p
l
y
w
it
h
th
e
SNI
.
T
o
b
e
ab
le
to
co
m
p
ete
i
n
m
ar
k
et
s
h
ar
e,
esp
ec
iall
y
i
n
No
r
th
Su
m
ater
a
r
eg
io
n
tap
io
ca
f
l
o
u
r
m
u
s
t
h
a
v
e
h
ig
h
q
u
al
it
y
.
T
ap
io
ca
f
lo
u
r
p
r
o
d
u
ce
d
b
y
th
e
co
m
p
an
y
is
d
is
tr
ib
u
ted
to
co
n
s
u
m
er
s
(
a
s
f
o
o
d
s
tu
f
f
)
an
d
to
in
d
u
s
tr
y
(
p
ap
er
m
ill
s
)
.
T
h
e
s
p
ec
if
icatio
n
o
f
t
h
e
b
en
c
h
m
ar
k
o
f
f
lo
u
r
q
u
alit
y
i
s
m
ea
s
u
r
ed
b
y
7
p
ar
a
m
eter
s
.
T
h
e
s
ev
e
n
p
ar
a
m
eter
s
ar
e
w
h
ite
n
e
s
s
,
m
o
is
t
u
r
e
co
n
te
n
t,
s
p
o
tn
es
s
,
ash
co
n
te
n
t,
t
h
in
n
es
s
,
r
esid
u
al
s
cr
ee
n
,
p
H
f
lo
u
r
.
T
ap
i
o
ca
f
lo
u
r
h
as
3
g
r
ad
es,
n
a
m
el
y
Gr
ad
e
A
,
Gr
ad
e
B
,
a
n
d
Gr
ad
e
C
.
Ho
w
e
v
er
,
th
e
co
m
p
an
y
o
n
l
y
p
r
o
d
u
ce
s
tap
io
ca
f
lo
u
r
w
it
h
Gr
ad
e
A
,
b
ec
au
s
e
ab
o
u
t
4
0
%
o
f
th
e
f
l
o
u
r
th
at
h
a
s
b
ee
n
p
r
o
d
u
ce
d
is
d
is
tr
ib
u
ted
to
th
e
in
d
u
s
tr
y
a
n
d
6
0
% is
d
is
tr
ib
u
te
d
to
co
n
s
u
m
er
s
(
u
s
ed
f
o
r
f
o
o
d
s
tu
f
f
)
.
Fo
r
th
e
p
u
r
p
o
s
e
to
h
elp
t
h
e
co
m
p
a
n
y
to
g
et
T
ap
io
ca
f
lo
u
r
t
h
at
h
as
Gr
ad
e
A
w
e
d
ec
id
e
to
p
er
f
o
r
m
a
n
i
m
a
g
e
p
r
o
ce
s
s
in
g
i
n
to
th
e
ca
s
s
av
a
i
m
a
g
e.
T
h
e
i
m
a
g
e
w
as
ta
k
en
b
y
u
s
i
n
g
a
ca
m
er
a
an
d
t
h
en
p
r
ep
r
o
ce
s
s
ed
b
y
s
o
m
e
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
al
g
o
r
ith
m
s
.
Af
ter
g
o
i
n
g
th
r
o
u
g
h
th
e
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e
th
e
n
t
h
e
i
m
a
g
e
w
er
e
p
r
o
ce
s
s
ed
b
y
b
lo
b
an
d
ed
g
e
d
etec
tio
n
m
eth
o
d
to
d
etec
t
s
p
o
t
an
d
d
eter
m
in
e
th
e
w
h
ite
n
es
s
.
Af
ter
t
h
e
s
p
o
t
an
d
w
h
ite
n
es
s
d
ata
a
lr
ea
d
y
co
llect
ed
th
e
n
w
e
u
s
e
t
h
e
I
D3
al
g
o
r
ith
m
to
d
eter
m
in
e
w
h
et
h
er
t
h
e
ca
s
s
a
v
a
i
s
Gr
ad
e
A
o
r
n
o
t.
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
:
7
9
9
–
8
0
5
800
Fig
u
r
e
1
.
I
n
p
u
t a
n
d
O
u
tp
u
t I
m
ag
e
Fig
u
r
e
1
s
h
o
w
t
h
e
i
m
ag
e
p
r
o
ce
s
s
i
n
g
p
r
o
ce
s
s
th
a
t
h
ap
p
en
e
d
in
th
e
p
r
ep
r
o
ce
s
s
ed
s
tag
e.
T
h
e
I
n
p
u
t
i
m
a
g
e
is
th
e
i
m
a
g
e
th
at
alr
ea
d
y
ca
p
t
u
r
ed
b
y
th
e
ca
m
er
a.
T
h
is
i
m
a
g
e
p
r
o
ce
s
s
ed
b
y
th
e
al
g
o
r
ith
m
to
p
r
o
d
u
ce
th
e
o
u
tp
u
t
i
m
a
g
e.
T
h
e
d
etail
ab
o
u
t
m
et
h
o
d
th
a
t
u
s
ed
in
t
h
is
r
e
s
ea
r
ch
w
i
ll
b
e
b
r
ief
e
x
p
lain
ed
in
th
e
n
e
x
t
s
ec
tio
n
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
w
ill
b
e
d
escr
ib
e
d
th
e
m
eth
o
d
s
th
at
u
s
ed
to
co
llect
an
d
p
r
o
ce
s
s
t
h
e
d
ata.
B
elo
w
i
s
t
h
e
m
et
h
o
d
th
at
u
s
ed
to
g
et
th
e
d
at
a
in
th
e
f
o
r
m
o
f
i
m
a
g
e.
Fig
u
r
e
2
.
Me
th
o
d
in
Sta
g
e
On
e
an
d
T
w
o
I
n
F
ig
u
r
e
2
w
e
ca
n
s
ee
th
e
f
ir
s
t
s
tep
th
at
n
ee
d
to
b
e
d
o
n
e
is
o
p
en
in
g
t
h
e
v
id
eo
s
tr
ea
m
a
n
d
tak
e
th
e
p
ictu
r
e
f
r
o
m
t
h
e
v
id
eo
.
T
h
e
tak
en
p
ict
u
r
e
w
ill
b
ec
o
m
e
a
n
i
n
p
u
t
i
m
a
g
e.
I
n
t
h
is
ap
p
licatio
n
d
ev
elo
p
m
e
n
t,
w
e
u
s
e
a
f
u
n
ctio
n
i
n
Op
en
C
V
a
n
d
C
v
B
lo
b
lib
r
ar
y
a
s
a
to
o
l.
T
h
e
f
u
n
ctio
n
th
at
u
s
ed
to
o
p
en
th
e
v
id
eo
is
o
p
en
f
u
n
ctio
n
an
d
to
ta
k
e
p
ictu
r
e
f
r
o
m
v
id
eo
w
e
u
s
e
q
u
er
y
f
r
a
m
e
f
u
n
ctio
n
.
B
o
th
f
u
n
c
tio
n
ar
e
m
e
m
b
er
f
r
o
m
Vid
eo
C
ap
tu
r
e
class
in
Op
e
n
C
V.
Af
ter
w
e
g
e
t
th
e
p
ictu
r
e
th
en
w
e
p
r
o
ce
s
s
th
e
i
m
a
g
e
b
y
u
s
in
g
th
e
ca
n
n
y
ed
g
e
d
etec
tio
n
alg
o
r
ith
m
.
W
e
u
s
e
ca
n
n
y
ed
g
e
d
etec
tio
n
i
n
h
er
e
b
ec
au
s
e
th
e
alg
o
r
it
h
m
is
co
n
s
id
er
ed
b
etter
th
an
s
o
b
el
an
d
p
r
e
w
itt
al
g
o
r
ith
m
[
1
]
.
A
f
ter
w
e
p
r
o
ce
s
s
ed
t
h
e
i
m
ag
e
w
it
h
ca
n
n
y
al
g
o
r
ith
m
t
h
e
n
th
e
i
m
a
g
e
o
u
tp
u
t
w
il
l b
e
a
b
i
n
ar
y
i
m
ag
e.
Fo
r
eg
r
o
u
n
d
(
ca
s
s
av
a)
is
r
ep
r
ese
n
ted
b
y
w
h
ite
co
lo
r
,
w
h
ile
b
ac
k
g
r
o
u
n
d
(
a
n
o
th
er
o
b
j
ec
t
in
s
tead
ca
s
s
av
a)
r
e
p
r
esen
ted
b
y
b
lack
co
lo
r
.
Un
til
n
o
w
w
e
a
lr
ea
d
y
p
ass
ed
2
s
tag
e,
b
eg
in
n
i
n
g
f
r
o
m
s
ta
g
e
to
g
et
t
h
e
i
n
p
u
t
i
m
a
g
e
f
r
o
m
v
id
eo
,
th
en
co
n
tin
u
ed
w
it
h
in
p
u
t
i
m
a
g
e
p
r
o
ce
s
s
in
g
w
i
th
ca
n
n
y
al
g
o
r
ith
m
[
1
]
.
W
ith
2
s
tag
es
ab
o
v
e
w
e
ca
n
alr
ea
d
y
d
is
tin
g
u
is
h
b
et
w
ee
n
t
h
e
ca
s
s
a
v
a
a
n
d
an
o
th
er
o
b
j
ec
t
th
at
ap
p
ea
r
s
o
n
th
e
f
r
a
m
e.
B
u
t
to
d
is
tin
g
u
is
h
b
et
w
ee
n
a
g
o
o
d
ca
s
s
av
a
an
d
a
b
ad
o
n
e
w
e
m
u
s
t
b
e
ab
le
to
d
etec
t
s
p
o
ts
o
n
ca
s
s
a
v
a.
T
h
e
ca
s
s
av
a
i
m
ag
e’
s
th
at
h
as
b
ee
n
d
etec
ted
as
f
o
r
eg
r
o
u
n
d
i
m
ag
e
w
ill
b
e
s
ep
ar
ated
af
ter
all.
S
o
n
o
w
w
e
ca
n
f
o
c
u
s
o
n
t
h
e
s
p
o
t
th
at
ex
is
t
in
th
e
ca
s
s
a
v
a.
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
C
a
s
s
a
va
Qu
a
lity Cl
a
s
s
if
ica
tio
n
fo
r
Ta
p
io
ca
F
l
o
u
r
I
n
g
r
ed
ien
ts
b
y
Usi
n
g
…
(
Yo
h
a
n
s
s
en
P
r
a
ta
ma
)
801
Fig
u
r
e
3
.
Me
th
o
d
in
Sta
g
e
T
h
r
ee
T
h
e
s
p
o
ts
th
a
t
e
x
is
t
i
n
t
h
e
ca
s
s
a
v
a
n
o
w
w
ill
b
ec
o
m
e
f
o
r
eg
r
o
u
n
d
o
b
j
ec
t
an
d
an
o
t
h
er
r
eg
i
o
n
i
n
t
h
e
cr
o
s
s
s
ec
tio
n
o
f
ca
s
s
a
v
a
w
ill
b
e
a
b
ac
k
g
r
o
u
n
d
.
T
h
e
s
p
o
ts
th
at
d
etec
ted
w
ill
b
e
r
ep
r
esen
ted
as
b
lo
b
f
ir
s
t,
th
e
n
af
ter
w
e
co
u
ld
d
etec
t
a
b
lo
b
,
w
e
co
u
ld
u
s
e
th
e
n
u
m
b
er
o
f
b
lo
b
in
f
o
r
m
a
tio
n
to
d
eter
m
i
n
e
q
u
alit
y
o
f
ca
s
s
av
a
.
T
h
e
in
p
u
t i
m
a
g
e
th
at
u
s
e
in
t
h
e
s
tag
e
3
is
a
g
r
a
y
s
ca
le
i
m
a
g
e
f
r
o
m
a
ca
s
s
av
a
cr
o
s
s
s
ec
tio
n
a
n
d
th
e
i
m
a
g
e
w
h
ich
is
alr
ea
d
y
m
a
s
k
ed
.
Ma
s
k
ed
p
er
f
o
r
m
i
n
h
er
e
to
r
ed
u
ce
th
e
n
o
is
e
an
d
w
e
u
s
ed
a
Ga
u
s
s
i
an
b
l
u
r
to
p
er
f
o
r
m
m
as
k
i
n
g
.
T
ab
le
1
.
P
r
o
d
u
ct
Sp
ec
if
icatio
n
No
P
a
r
a
me
t
e
r
S
p
e
c
i
f
i
c
a
t
i
o
n
1
W
h
i
t
e
n
e
ss
≥
9
1
.
0
%
2
T
h
i
n
n
e
ss
≥
9
9
.
5
0
%
3
S
p
o
t
s
≤ 5
4
mo
i
st
u
r
e
c
o
n
t
e
n
t
1
2
.
0
0
-
1
3
.
0
0
%
5
a
sh
c
o
n
t
e
n
t
0
.
0
2
-
0
.
0
6
%
6
R
e
si
d
u
a
l
scre
e
n
3
2
5
(
m
a
x
0
.
0
5
%),
7
p
H
f
l
o
u
r
5
.
6
-
6
.
5
I
f
w
e
s
ee
T
ab
le
1
,
w
e
f
o
u
n
d
t
h
at
th
e
s
p
ec
if
ica
tio
n
t
h
at
ac
co
r
d
in
g
to
co
n
s
u
m
er
ex
p
ec
tatio
n
s
i
s
if
t
h
e
n
u
m
b
er
o
f
s
p
o
ts
i
n
ca
s
s
a
v
a
i
s
s
m
aller
t
h
a
n
5
s
p
o
ts
.
Fro
m
h
er
e
w
e
co
u
ld
ch
ar
ac
ter
ized
t
h
e
ca
s
s
av
a
q
u
alit
y
b
ased
o
n
n
u
m
b
er
o
f
s
p
o
ts
t
h
at
ex
is
t.
C
las
s
if
icatio
n
w
a
s
m
ad
e
b
y
t
h
e
co
n
d
itio
n
in
t
h
e
T
ab
le
2
(
th
er
e
ar
e
3
k
in
d
co
n
d
itio
n
)
.
I
f
t
h
e
n
u
m
b
er
o
f
s
p
o
ts
s
m
aller
t
h
a
n
3
,
th
en
w
e
c
ateg
o
r
ize
ca
s
s
a
v
a
in
to
g
o
o
d
q
u
alit
y
an
d
o
th
er
t
h
a
n
th
at
t
h
e
ca
s
s
a
v
a
w
ill ca
te
g
o
r
iz
e
in
to
m
ed
i
u
m
o
r
b
ad
q
u
alit
y
.
T
ab
le
2
.
C
ass
av
a
C
lass
if
ica
tio
n
B
ased
o
n
Sp
o
ts
Q
u
a
l
i
t
y
/
G
r
a
d
e
N
u
mb
e
r
o
f
sp
o
t
s
G
o
o
d
(
G
r
a
d
e
A
)
S
p
o
t
s
<
3
M
e
d
i
u
m (G
r
a
d
e
B
)
3
≤
S
p
o
t
s ≤
5
B
a
d
(
G
r
a
d
e
C
)
S
p
o
t
s
>
5
B
esid
es
u
s
i
n
g
t
h
e
n
u
m
b
er
o
f
s
p
o
t
to
d
eter
m
i
n
e
t
h
e
ca
s
s
a
v
a
q
u
alit
y
,
w
e
u
s
e
w
h
ite
n
es
s
a
s
p
ar
am
eter
th
at
d
eter
m
i
n
e
t
h
e
q
u
alit
y
.
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
:
7
9
9
–
8
0
5
802
T
ab
le
3
.
C
ass
av
a
C
lass
if
ica
tio
n
B
ased
o
n
W
h
iten
e
s
s
Q
u
a
l
i
t
y
/
G
r
a
d
e
W
h
i
t
e
n
e
ss
G
o
o
d
(
A
)
≥
9
1
%
M
e
d
i
u
m (
B
)
8
9
%
B
a
d
(
C
)
≤
8
9
%
C
ass
a
v
a
Gr
ad
e
o
r
Qu
alit
y
th
a
t
p
r
o
d
u
ce
d
b
y
th
e
co
m
p
an
y
is
g
r
ad
e
A
ca
s
s
av
a.
So
w
e
u
s
e
an
i
m
a
g
e
p
r
o
ce
s
s
in
g
a
g
ai
n
to
d
eter
m
i
n
e
th
e
w
h
ite
n
es
s
o
f
ca
s
s
a
v
a.
T
o
g
et
th
e
w
h
ite
n
es
s
p
er
ce
n
tag
e,
w
e
co
m
p
ar
e
th
e
p
ix
el
v
al
u
e
o
f
an
i
n
p
u
t
i
m
ag
e
w
it
h
th
e
id
ea
l
v
al
u
e
f
o
r
th
e
w
h
ite
n
es
s
in
8
-
b
it
s
co
lo
r
s
y
s
t
e
m
(
2
5
5
,
2
5
5
,
2
5
5
)
.
T
h
en
w
e
av
er
a
g
i
n
g
s
p
ec
tr
al
d
i
s
tan
ce
f
r
o
m
ea
ch
p
i
x
el
v
al
u
e
i
f
t
h
e
d
i
f
f
er
e
n
ce
is
s
m
aller
t
h
a
n
9
%
th
e
n
w
e
co
u
ld
ca
teg
o
r
ize
th
e
ca
s
s
av
a
i
n
to
g
r
a
d
e
A
(
b
ased
o
n
T
ab
le
3
)
.
B
elo
w
i
s
th
e
s
p
ec
tr
al
d
is
tan
ce
f
o
r
m
u
la
th
a
t u
s
ed
:
i
is
a
b
an
d
(
d
im
en
s
io
n
)
an
d
d
i
is
v
al
u
e
o
f
p
ix
el
i
n
b
an
d
i,
o
th
er
w
is
e
e
i
is
v
a
lu
e
o
f
p
ix
e
l
e
in
b
an
d
i.
Fo
r
o
u
r
ca
s
e
d
h
as v
al
u
e
2
5
5
an
d
e
v
al
u
e
b
ased
o
n
th
e
p
ix
e
l i
n
ten
s
it
y
i
n
in
p
u
t i
m
ag
e.
T
h
e
in
p
u
t i
m
a
g
e
th
at
w
e
u
s
ed
to
g
et
t
h
is
w
h
ite
n
es
s
s
co
r
e
is
o
n
g
r
a
y
s
ca
le
co
lo
r
s
p
ac
e.
Un
til
n
o
w
w
e
alr
ea
d
y
h
a
v
e
2
p
ar
a
m
eter
s
to
m
a
k
e
cla
s
s
i
f
ic
atio
n
,
t
h
e
la
s
t
p
ar
a
m
eter
th
at
w
e
u
s
ed
is
m
o
is
t
u
r
e
co
n
te
n
t in
t
h
e
ca
s
s
av
a.
T
o
g
et
m
o
is
t
u
r
e
co
n
ten
t
w
e
u
s
e
m
o
is
t
u
r
e
m
eter
(
F
i
g
u
r
e
4
)
.
Fig
u
r
e
3
.
Mo
is
tu
r
e
Me
ter
Fo
r
m
o
is
t
u
r
e
w
e
o
n
l
y
h
av
e
2
d
is
cr
ete
p
ar
a
m
eter
v
a
lu
e
s
,
th
er
e
ar
e
g
o
o
d
an
d
b
ad
.
Go
o
d
if
th
e
m
o
is
t
u
r
e
co
n
ten
t
is
ar
o
u
n
d
1
2
-
1
3
%,
o
th
er
th
an
th
a
t
w
ill
b
e
class
if
ied
i
n
to
b
ad
ca
teg
o
r
y
.
Af
ter
w
e
g
e
t
3
p
a
r
am
e
ter
s
t
h
at
n
ee
d
ed
to
m
a
k
e
a
clas
s
i
f
icatio
n
(
n
u
m
b
er
o
f
s
p
o
ts
,
w
h
ite
n
es
s
,
an
d
m
o
is
t
u
r
e)
th
e
n
w
e
u
s
e
t
h
e
m
as i
n
p
u
t d
ata
f
o
r
lear
n
in
g
al
g
o
r
ith
m
.
B
elo
w
i
s
t
h
e
ex
a
m
p
le
o
f
co
llected
d
ata
(
T
ab
le
4
)
.
T
ab
le
4
.
Data
E
x
am
p
le
S
p
o
t
W
h
i
t
e
n
e
ss
M
o
i
st
u
r
e
Qu
a
l
i
t
y
M
e
d
i
u
m
G
o
o
d
G
o
o
d
G
o
o
d
B
a
d
M
e
d
i
u
m
B
a
d
B
a
d
M
e
d
i
u
m
G
o
o
d
B
a
d
G
o
o
d
M
e
d
i
u
m
B
a
d
G
o
o
d
B
a
d
G
o
o
d
M
e
d
i
u
m
B
a
d
B
a
d
T
h
e
d
ata
ab
o
v
e
is
alr
ea
d
y
p
as
t
th
e
p
r
ep
r
o
ce
s
s
in
g
s
ta
g
e
b
y
u
s
in
g
d
is
cr
etiza
tio
n
m
eth
o
d
(
to
d
is
cr
etize
th
e
d
ata
w
e
u
s
ed
th
e
r
u
le
f
r
o
m
T
ab
le
2
an
d
T
ab
le
3
)
.
I
n
th
is
r
esear
ch
w
e
u
s
ed
a
d
ec
i
s
io
n
tr
ee
lear
n
i
n
g
m
et
h
o
d
to
p
r
o
ce
s
s
th
e
d
ata
b
ec
au
s
e
t
h
e
p
r
o
b
le
m
t
h
at
w
o
u
ld
b
e
s
o
lv
ed
h
a
v
e
a
tar
g
et
f
u
n
ctio
n
wh
ich
h
a
s
a
d
is
cr
et
e
o
u
tp
u
t
a
n
d
t
h
er
e
ar
e
er
r
o
r
an
d
d
ata
lo
s
s
p
o
s
s
ib
il
it
y
f
r
o
m
t
h
e
tr
ai
n
i
n
g
d
ata.
T
h
e
d
ec
is
io
n
tr
ee
alg
o
r
it
h
m
t
h
at
u
s
ed
in
h
er
e
is
I
D3
alg
o
r
ith
m
.
I
D3
alg
o
r
ith
m
u
s
e
s
tat
is
tic
p
r
o
p
er
ties
th
at
r
ef
er
r
ed
as
in
f
o
r
m
atio
n
g
ain
a
n
d
th
is
in
f
o
r
m
atio
n
g
ai
n
w
ill b
e
u
s
ed
to
s
elec
t a
ca
n
d
id
ate
to
b
u
ild
th
e
tr
ee
[
2
]
.
T
o
g
et
th
e
in
f
o
r
m
a
tio
n
g
ai
n
ac
c
u
r
atel
y
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
C
a
s
s
a
va
Qu
a
lity Cl
a
s
s
if
ica
tio
n
fo
r
Ta
p
io
ca
F
l
o
u
r
I
n
g
r
ed
ien
ts
b
y
Usi
n
g
…
(
Yo
h
a
n
s
s
en
P
r
a
ta
ma
)
803
E
n
t
r
o
p
y
(
S
)
º
-
p
i
i
=
1
c
å
l
o
g
2
p
i
G
a
i
n
(
S
,
A
)
º
E
n
t
r
o
p
y
(
S
)
-
S
v
S
E
n
t
r
o
p
y
(
S
v
)
v
Î
V
a
l
u
e
s
(
A
)
å
w
e
n
ee
d
th
e
en
tr
o
p
y
f
ir
s
t.
E
n
tr
o
p
y
s
er
v
es
to
m
ea
s
u
r
e
th
e
a
m
o
u
n
t
o
f
i
n
f
o
r
m
atio
n
th
a
t
co
n
ta
in
ed
in
a
n
attr
ib
u
te.
B
elo
w
is
t
h
e
en
tr
o
p
y
f
o
r
m
u
lati
o
n
:
I
f
th
e
tar
g
et
attr
ib
u
te
h
as
d
if
f
er
en
t
v
al
u
e
as
m
u
ch
as
c
(
in
o
u
r
ca
s
e
th
e
tar
g
et
is
Qu
al
it
y
th
at
o
n
l
y
h
av
e
2
attr
ib
u
t:
Go
o
d
o
r
B
a
d
)
an
d
p
i
is
p
ar
t
o
f
S
th
at
b
elo
n
g
to
c.
A
f
ter
w
e
g
et
th
e
en
tr
o
p
y
w
e
co
u
ld
g
et
th
e
attr
ib
u
te
ef
f
ec
ti
v
en
e
s
s
v
alu
e
i
n
class
i
f
y
i
n
g
a
tr
ain
i
n
g
d
ata
o
r
w
e
u
s
u
all
y
ca
lled
it
as
in
f
o
r
m
atio
n
g
ai
n
[
2
]
.
T
h
e
in
f
o
r
m
atio
n
g
ai
n
,
Gain
(
S,
A
)
w
it
h
t
h
e
s
et
o
f
E
x
a
m
p
les S to
w
ar
d
s
attr
ib
u
te
A
ca
n
b
e
d
ef
i
n
ed
as f
o
llo
w
s
:
W
h
er
e
Valu
es
(
A
)
i
s
a
s
et
o
f
p
o
s
s
ib
le
v
al
u
es
in
at
tr
ib
u
te
A
,
a
n
d
Sv
is
a
s
u
b
s
et
o
f
S
w
h
er
e
a
ttrib
u
te
A
h
as a
v
a
lu
e
o
f
v
(
e.
g
.
S
v
=
{s
∈
S
|
A
(
s
)
=
v
})
.
W
h
er
ea
s
|
S
v
|
i
s
t
h
e
n
u
m
b
er
o
f
ele
m
en
ts
i
n
S
v
a
n
d
|
S
|
is
th
e
n
u
m
b
er
o
f
ele
m
e
n
ts
i
n
S.
T
h
e
f
ir
s
t
p
ar
t
o
f
th
e
g
ain
eq
u
ati
o
n
is
en
tr
o
p
y
o
f
S,
w
h
ile
th
e
s
ec
o
n
d
p
ar
t
is
th
e
ex
p
ec
ted
v
alu
e
o
f
en
tr
o
p
y
S a
f
ter
b
ein
g
p
ar
titi
o
n
ed
u
s
i
n
g
attr
ib
u
te
A
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
T
h
e
r
esu
lt t
h
at
w
e
g
et
f
r
o
m
t
h
e
s
tag
e
3
o
f
d
ata
ac
q
u
is
it
io
n
i
s
n
u
m
b
er
o
f
s
p
o
t.
Fir
s
t
w
e
tr
ied
to
ca
p
tu
r
e
th
e
i
m
ag
e
f
r
o
m
t
h
e
s
a
m
p
le
th
a
t h
as a
g
o
o
d
q
u
alit
y
an
d
t
h
en
w
e
w
i
ll g
et
t
h
e
r
es
u
lt a
s
s
h
o
wn
in
F
ig
u
r
e
5
.
Fig
u
r
e
5
.
Sp
o
t D
etec
tio
n
in
G
o
o
d
C
ass
av
a
T
h
er
e
is
n
o
b
lo
b
d
etec
ted
in
F
i
g
u
r
e
5
,
alt
h
o
u
g
h
th
er
e
w
a
s
a
s
m
all
b
lac
k
s
p
o
t th
a
t d
etec
ted
.
T
h
e
s
m
all
s
p
o
t
n
o
t
d
etec
ted
h
er
e
b
ec
au
s
e
w
e
alr
ea
d
y
d
eter
m
in
e
t
h
e
m
in
i
m
u
m
a
n
d
m
ax
i
m
u
m
ar
ea
o
f
b
lo
b
w
h
ic
h
ca
n
b
e
ca
teg
o
r
ized
as
s
p
o
t.
I
f
t
h
e
s
p
o
t
is
to
o
s
m
a
ll,
w
e
n
o
t
ca
te
g
o
r
iz
ed
it
as
a
s
p
o
t.
T
h
e
m
i
n
i
m
u
m
an
d
m
ax
i
m
u
m
s
ize
ar
ea
o
f
b
lo
b
is
d
ec
id
ed
b
y
ap
p
ly
in
g
a
lear
n
i
n
g
p
r
o
ce
s
s
.
A
f
ter
th
at
w
e
also
ca
p
tu
r
e
t
h
e
i
m
ag
e
f
r
o
m
t
h
e
b
ad
q
u
alit
y
s
a
m
p
le
(
F
i
g
u
r
e
6
)
.
Fig
u
r
e
6
.
Sp
o
t D
etec
tio
n
in
B
ad
C
ass
a
v
a
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
:
7
9
9
–
8
0
5
804
I
n
F
i
g
u
r
e
6
,
t
h
er
e
ar
e
3
b
lo
b
s
d
etec
ted
an
d
p
ass
t
h
e
m
i
n
i
m
u
m
ar
ea
s
ize
th
at
alr
ea
d
y
d
ec
id
ed
.
So
f
r
o
m
h
er
e
w
e
ca
n
co
n
cl
u
d
e
th
at
th
e
g
o
o
d
ca
s
s
av
a
h
as
ze
r
o
s
p
o
t
an
d
o
n
th
e
o
th
er
h
an
d
th
e
b
ad
ca
s
s
av
a
h
as
t
h
r
ee
n
u
m
b
er
s
o
f
s
p
o
ts
.
T
h
er
e
ar
e
t
h
r
ee
p
ar
a
m
eter
s
th
at
w
e
u
s
ed
to
d
eter
m
in
e
w
h
e
th
er
t
h
e
ca
s
s
av
a
is
b
ad
o
r
g
o
o
d
.
So
w
e
s
till
n
ee
d
th
e
i
n
f
o
r
m
ati
o
n
ab
o
u
t
w
h
ite
n
es
s
an
d
m
o
is
t
u
r
e.
I
n
b
ad
ca
s
s
av
a
w
e
f
i
n
d
th
at
th
e
w
h
ite
n
ess
i
s
b
elo
w
8
9
%
an
d
m
o
is
t
u
r
e
is
m
o
r
e
th
an
1
3
%,
s
o
a
f
ter
w
e
g
et
th
e
t
h
r
ee
p
ar
a
m
eter
s
i
n
f
o
r
m
ati
o
n
w
e
co
u
ld
d
ec
id
e
th
at
t
h
e
ca
s
s
a
v
a
q
u
alit
y
i
s
b
ad
.
I
n
T
ab
le
4
w
e
co
u
ld
s
ee
s
o
m
e
d
ata
s
a
m
p
le
t
h
at
w
e
’
v
e
al
r
ea
d
y
co
llec
ted
.
Fo
r
test
i
n
g
t
h
e
ac
cu
r
ac
y
is
u
s
ed
d
ataset
as
f
o
llo
w
s
:
T
ab
le
5
.
Data
s
et
D
a
t
a
se
t
s N
u
m
b
e
r
T
r
a
i
n
i
n
g
D
a
t
a
(
6
0
%)
T
e
st
D
a
t
a
(
4
0
%)
4
0
0
2
4
0
1
6
0
So
if
w
e
s
ee
T
ab
le
5
,
w
e
u
s
e
6
0
%
f
r
o
m
all
d
ata
s
a
m
p
le
as
tr
ain
i
n
g
d
ata
a
n
d
th
e
r
est
w
i
l
l
b
e
a
test
d
ata.
T
h
e
tr
ain
in
g
d
ata
w
i
ll
b
e
u
s
e
to
tr
ain
t
h
e
I
D3
alg
o
r
it
h
m
s
o
it
w
i
ll
h
av
e
it
’
s
o
w
n
cla
s
s
i
f
ier
i
n
tr
ee
f
o
r
m
.
T
h
e
r
u
le
i
n
t
h
e
c
lass
if
ier
(
tr
ee
)
w
i
ll
b
e
u
s
ed
to
clas
s
i
f
y
i
n
g
t
h
e
te
s
t
d
ata.
Af
ter
th
at
w
e
co
u
ld
g
et
t
h
e
ac
c
u
r
ac
y
f
r
o
m
th
e
ev
al
u
atio
n
r
es
u
lt
s
.
I
f
w
e
ch
a
n
g
e
t
h
e
n
u
m
b
er
o
r
p
er
ce
n
tag
e
o
f
tr
ain
i
n
g
d
ata
a
n
d
te
s
t
d
ata
th
e
n
w
e
w
i
ll
g
et
a
d
if
f
er
en
t tr
ee
.
T
h
e
F
ig
u
r
e
7
b
elo
w
is
a
n
ill
u
s
tr
at
io
n
o
f
t
h
e
ac
cu
r
ac
y
test
in
g
p
r
o
ce
s
s
th
a
t
p
er
f
o
r
m
ed
:
B
elo
w
is
t
h
e
d
ec
is
io
n
tr
ee
t
h
at
o
b
tain
ed
af
ter
w
e
p
r
o
ce
s
s
t
h
e
tr
ain
i
n
g
d
ata
(
F
i
g
u
r
e
8
)
:
Fig
u
r
e
7
.
A
cc
u
r
ac
y
tes
tin
g
p
r
o
ce
s
s
(
w
e
k
a.
w
ak
ai
to
.
ac
.
n
z)
Fig
ur
e 8. Dec
i
s
i
on
Tre
e
W
e
co
u
ld
s
ee
th
a
t
t
h
e
n
u
m
b
er
o
f
s
p
o
t
h
a
s
a
h
ig
h
es
t
i
n
f
o
r
m
a
tio
n
g
ai
n
v
al
u
e,
s
o
it
b
ec
a
m
e
a
tr
ee
r
o
o
t.
I
n
h
er
e
n
u
m
b
er
o
f
s
p
o
t
h
as
b
ig
g
er
ef
f
ec
t
i
n
d
ec
id
in
g
th
e
q
u
alit
y
o
f
ca
s
s
a
v
a
co
m
p
ar
ed
to
an
o
th
er
p
ar
a
m
eter
s
.
T
h
e
ac
cu
r
ac
y
th
a
t
w
e
g
e
t
f
r
o
m
t
h
e
d
ec
is
io
n
tr
ee
ab
o
v
e
cl
ass
i
f
ier
i
s
8
4
,
7
3
2
8
.
W
e
also
tr
y
to
co
m
p
ar
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
id
3
alg
o
r
it
h
m
w
it
h
8
o
th
er
al
g
o
r
ith
m
s
.
T
h
e
ac
cu
r
ac
y
o
f
t
h
e
8
al
g
o
r
ith
m
s
i
s
d
eter
m
i
n
ed
b
y
u
s
i
n
g
w
ek
a
a
n
d
b
elo
w
is
t
h
e
r
esu
lt
f
o
r
m
a
k
i
n
g
s
o
m
e
co
m
p
ar
is
o
n
:
T
ab
le
6
.
A
cc
u
r
ac
y
C
o
m
p
ar
is
o
n
N
o
.
A
l
g
o
r
i
t
h
m
N
a
me
A
c
c
u
r
a
c
y
(
%)
1.
B
a
y
e
sn
e
t
w
o
r
k
7
7
.
8
6
2
6
2.
Na
i
v
e
b
a
y
e
s
7
7
.
8
6
2
6
3.
R
a
n
d
o
mT
r
e
e
7
9
.
3
8
9
3
4.
ID
3
8
4
.
7
3
2
8
5.
K*
8
0
.
1
5
2
7
6.
R
a
n
d
o
mF
o
r
e
st
8
3
.
9
6
9
5
7.
K
N
e
a
r
e
st
N
e
i
g
h
b
o
u
r
8
4
.
7
3
2
8
8.
F
u
n
c
t
i
o
n
a
l
T
r
e
e
s
8
5
.
4
9
6
2
9.
J4
8
8
7
.
0
2
2
9
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
C
a
s
s
a
va
Qu
a
lity Cl
a
s
s
if
ica
tio
n
fo
r
Ta
p
io
ca
F
l
o
u
r
I
n
g
r
ed
ien
ts
b
y
Usi
n
g
…
(
Yo
h
a
n
s
s
en
P
r
a
ta
ma
)
805
Fro
m
T
ab
le
6
w
e
ca
n
s
ee
th
a
t
I
D3
alg
o
r
ith
m
is
n
o
t
th
e
b
est
alg
o
r
ith
m
b
u
t
it
s
ti
ll
h
a
v
e
a
g
o
o
d
p
er
f
o
r
m
a
n
ce
if
w
e
co
m
p
ar
e
w
it
h
an
o
t
h
er
alg
o
r
ith
m
.
4.
CO
NCLU
SI
O
N
Fro
m
o
u
r
r
esear
ch
,
w
e
ca
n
co
n
clu
d
e
t
h
at
to
d
eter
m
in
e
a
g
o
o
d
q
u
alit
y
ca
s
s
av
a
w
e
co
u
ld
u
s
e
i
m
a
g
e
p
r
o
ce
s
s
in
g
to
co
llect
th
e
d
ata
an
d
u
s
e
an
id
3
alg
o
r
it
h
m
to
p
r
o
ce
s
s
ed
th
e
d
ata
an
d
p
r
o
d
u
ce
s
o
m
e
d
ec
is
io
n
.
Fro
m
t
h
r
ee
p
ar
a
m
eter
s
t
h
at
u
s
ed
h
er
e,
th
er
e
ar
e
w
h
ite
n
e
s
s
,
m
o
i
s
t
u
r
e,
an
d
n
u
m
b
er
o
f
s
p
o
t
w
e
co
u
ld
g
et
8
4
.
7
3
2
8
%
ac
cu
r
ac
y
to
clas
s
i
f
y
t
h
e
ca
s
s
av
a
b
ased
o
n
it
q
u
alit
y
.
Fo
r
f
u
t
u
r
es
w
o
r
k
we
co
u
ld
ad
d
m
o
r
e
p
ar
am
eter
s
to
in
cr
ea
s
e
th
e
ac
c
u
r
ac
y
a
n
d
u
s
e
an
o
t
h
er
clas
s
i
f
i
er
alg
o
r
ith
m
s
u
c
h
as
n
e
u
r
al
n
e
t
w
o
r
k
w
h
ich
m
o
r
e
p
r
o
m
i
s
in
g
w
h
en
d
o
in
g
clas
s
i
f
i
ca
tio
n
.
RE
F
E
R
E
NC
E
S
[1
]
Ca
n
n
y
J
.
A
Co
m
p
u
tatio
n
a
l
A
p
p
r
o
a
c
h
to
E
d
g
e
De
tec
ti
o
n
.
J
o
u
rn
a
l
I
EE
-
PA
M
I
.
1
9
8
6
;
8
.
(
6
)
:
6
7
9
-
6
9
8
.
[2
]
M
it
c
h
e
ll
M
.
M
a
c
h
i
n
e
L
e
a
rn
in
g
.
E
d
i
ti
o
n
.
M
c
G
r
aw
-
Hill
.
1
9
9
7
:
55
-
60
.
[3
]
Ha
ij
ian
S
.
Be
st
-
F
irst
d
e
c
isio
n
tree
lea
rn
in
g
.
M
a
ste
r’s
T
h
e
sis.
Ha
m
il
to
n
:
P
o
stg
ra
d
u
a
te
Un
iv
e
rsity
o
f
W
a
ik
a
to
;
2
0
0
7
.
[4
]
Na
re
n
d
ra
V
a
n
d
Ha
re
e
sh
K
.
Qu
a
li
ty
In
sp
e
c
ti
o
n
a
n
d
G
ra
d
in
g
o
f
A
g
ricu
lt
u
ra
l
a
n
d
F
o
o
d
p
ro
c
d
u
c
ts
b
y
Co
m
p
u
ter
V
isio
n
-
A
Re
v
ie
w
.
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
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
)
.
2
(
1
).
[5
]
Ya
m
K
a
n
d
S
p
y
rid
o
n
E.
A
S
im
p
l
e
Dig
it
a
l
I
m
a
g
in
g
M
e
th
o
d
f
o
r
M
e
a
su
rin
g
a
n
d
A
n
a
ly
z
in
g
Co
lo
u
r
o
f
F
o
o
d
S
u
rf
a
c
e
s.
Jo
u
rn
a
l
o
f
F
o
o
d
E
n
g
in
e
e
rin
g
.
2
0
0
3
;
6
1
:
1
3
7
-
1
4
2
[6
]
Ko
d
a
g
a
li
A
a
n
d
Ba
laji
S
.
Co
m
p
u
t
e
r
V
isio
n
a
n
d
Im
a
g
e
A
n
a
l
y
sis
b
a
s
e
d
T
e
c
h
n
iq
u
e
s
f
o
r
A
u
to
m
a
ti
c
Ch
a
ra
c
teriz
a
ti
o
n
o
f
F
ru
it
s
-
a
Re
v
iew
.
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
Co
m
p
u
ter A
p
p
li
c
a
ti
o
n
s.
2
0
1
2
;
5
0
(
6
).
[7
]
L
p
e
z
-
G
a
r
c
a
F
,
A
n
d
re
u
-
Ga
rc
a
G
,
Blas
c
o
J,
A
lei
x
o
s
N,
a
n
d
V
a
li
e
n
t
e
M
.
A
u
to
m
a
ti
c
d
e
tec
ti
o
n
o
f
sk
in
d
e
f
e
c
t
s
in
c
it
ru
s
f
ru
it
s u
sin
g
a
m
u
lt
iv
a
riate
i
m
a
g
e
.
Co
m
p
u
ters
a
n
d
e
lec
tro
n
ics
in
A
g
ricu
lt
u
re
.
2
0
1
0
;
7
1
:1
8
9
-
1
9
7
.
[8
]
T
i
m
m
e
r
m
a
n
s
A
.
Co
m
p
u
ter
V
isi
o
n
S
y
ste
m
f
o
r
On
li
n
e
S
o
rti
n
g
o
f
P
o
t
P
lan
ts
Ba
se
d
o
n
L
e
a
rn
in
g
Tec
h
n
iq
u
e
s.
A
c
t
a
Ho
rti
c
u
lt
u
ra
e
.
1
9
9
8
;
4
2
1
:
9
1
-
98.
[9
]
S
a
rd
a
r
H.
Qu
a
li
ty
A
n
a
l
y
sis
in
g
ra
y
s
c
a
le
c
o
lo
r
u
sin
g
v
isu
a
l
a
p
p
e
a
ra
n
c
e
o
f
g
u
a
v
a
f
ru
it
.
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
En
g
in
e
e
rin
g
S
c
ien
c
e
s.
2
0
1
3
;
4
6
-
5
6
.
[1
0
]
Ro
c
h
a
A
,
Ha
u
a
g
g
e
D,
Wain
e
r
J,
G
o
ld
e
n
ste
in
S
.
A
u
to
m
a
ti
c
f
r
u
it
a
n
d
v
e
g
e
tab
le
c
las
sif
ic
a
ti
o
n
f
ro
m
i
m
a
g
e
s.
Co
m
p
u
ters
a
n
d
El
e
c
tro
n
ics
i
n
A
g
ricu
lt
u
re
.
2
0
1
0
;
7
0
:9
6
-
1
0
4
.
[1
1
]
Yo
u
se
f
A
.
Co
m
p
u
ter
v
isio
n
b
a
se
d
d
a
te
f
ru
it
g
ra
d
in
g
sy
ste
m
:
De
sig
n
a
n
d
im
p
le
m
e
n
tatio
n
.
J
o
f
Kin
g
S
a
u
d
Un
iv
e
rsit
y
.
Co
m
p
u
ter an
d
I
n
f
o
rm
a
ti
o
n
S
c
ien
c
e
s; 2
0
1
1
:
2
3
:
2
9
-
36.
[1
2
]
S
e
n
g
W
a
n
d
M
ir
isa
e
e
S
.
A
n
e
w
m
e
th
o
d
f
o
r
f
ru
it
s
re
c
o
g
n
it
io
n
sy
ste
m
.
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
a
n
d
In
f
o
rm
a
ti
c
s.
2
0
0
9
:
1
3
0
-
1
3
4
.
[1
3
]
Da
d
w
a
l
M
a
n
d
Ba
n
g
a
V
.
Esti
m
a
te
Rip
e
n
e
ss
Lev
e
l
o
f
f
ru
it
s
u
sin
g
RG
B
Co
lo
r
S
p
a
c
e
a
n
d
F
u
z
z
y
Lo
g
ic
T
e
c
h
n
iq
u
e
.
In
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
En
g
in
e
e
ri
n
g
a
n
d
A
d
v
a
n
c
e
d
T
e
c
h
n
o
lo
g
y
.
2
0
1
2
;
2
(1
)
:
2
2
5
-
2
2
9
.
[1
4
]
Be
n
h
u
ra
C
,
A
lb
e
rt
M
,
M
u
c
h
u
w
e
ti
M
,
G
o
m
b
iro
E.
A
ss
e
s
m
e
n
t
o
f
th
e
Co
lo
u
r
o
f
P
a
rin
a
ri
C
u
ra
t
e
ll
if
o
li
a
F
ru
it
u
si
n
g
a
n
im
a
g
e
p
ro
c
e
ss
in
g
c
o
m
p
u
ter
so
f
twa
re
p
a
c
k
a
g
e
.
In
tern
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ag
ricu
lt
u
ra
l
a
n
d
F
o
o
d
Re
se
a
rc
h
.
2
0
1
3
;
2
(4
):
41
-
48.
[1
5
]
Yu
d
o
n
g
Z
a
n
d
L
e
n
a
n
W
.
Clas
sif
ica
ti
o
n
o
f
f
ru
it
s
u
sin
g
c
o
m
p
u
ter
v
isio
n
a
n
d
m
u
lt
icla
ss
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
.
S
e
n
so
rs.
2
0
1
2
;
1
2
:
1
2
4
8
9
-
1
2
5
0
5
Evaluation Warning : The document was created with Spire.PDF for Python.