I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
,
p
p
.
3202
~
3
2
1
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
3
.
pp
3
2
0
2
-
3
2
1
1
3202
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Cla
ss
ificatio
n of
mo
rpho
lo
g
ica
lly
s
imila
r India
n rice
va
riety
using
ma
chine lea
rning
alg
o
rithms
H
a
rini Sha
da
k
s
ha
ra
pp
a
1
,
Sa
rit
ha
Cha
k
ra
s
a
li
2
,
K
rish
na
mu
rt
hy
G
o
ra
pp
a
Ning
a
pp
a
2
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
B
.
M
.
S
.
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
,
B
a
n
g
a
l
o
r
e
,
K
a
r
n
a
t
a
k
a
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
B
N
M
I
n
st
i
t
u
t
e
o
f
Te
c
h
n
o
l
o
g
y
,
B
a
n
g
a
l
o
r
e
,
K
a
r
n
a
t
a
k
a
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
9
,
2
0
2
4
R
ev
is
ed
Ma
r
1
2
,
2
0
2
5
Acc
ep
ted
Ma
r
2
0
,
2
0
2
5
In
d
ia,
a
m
o
n
g
th
e
a
g
ricu
lt
u
re
-
b
a
se
d
e
c
o
n
o
m
y
g
r
o
ws
wid
e
v
a
riety
o
f
rice
a
lo
n
g
wi
th
o
th
e
r
c
ro
p
s.
T
h
e
se
v
a
rieties
h
a
v
e
d
iffere
n
t
c
o
m
m
e
rc
ial
v
a
lu
e
s
a
s
th
e
y
a
re
d
iffere
n
t
in
th
e
ir
fe
a
tu
re
s.
It
b
e
c
o
m
e
s
e
x
trem
e
ly
c
h
a
ll
e
n
g
in
g
t
o
c
las
sify
rice
v
a
rieties
wh
ich
h
a
v
e
sim
il
a
r
fe
a
tu
re
s
b
u
t
a
re
d
iffere
n
t
in
t
h
e
ir
q
u
a
li
t
y
.
Th
is
stu
d
y
c
o
n
si
d
e
rs
fo
u
r
v
a
rieties
o
f
sim
il
a
r
lo
o
k
in
g
r
ice
wh
ic
h
c
o
n
fo
rm
t
o
b
e
S
o
n
a
-
M
a
su
r
i.
A t
o
t
a
l
o
f
4
1
8
0
ima
g
e
s
a
re
c
o
n
si
d
e
re
d
to
e
x
trac
t
5
6
fe
a
tu
re
s
in
c
l
u
d
in
g
tex
t
u
ra
l,
re
d
,
g
re
e
n
,
b
l
u
e
(RG
B)
a
n
d
h
u
e
,
s
a
tu
ra
ti
o
n
,
v
a
lu
e
(HSV)
c
o
l
o
r
a
n
d
wa
v
e
let
d
e
c
o
m
p
o
sit
io
n
.
M
a
c
h
i
n
e
lea
rn
i
n
g
(
M
L)
m
o
d
e
ls
li
k
e
su
p
p
o
rt
v
e
c
to
r
m
a
c
h
in
e
(
S
VM),
K
-
n
e
a
re
st
n
e
i
g
h
b
o
r
(KN
N),
d
e
c
isio
n
tree
(DT)
a
n
d
v
o
ti
n
g
c
l
a
ss
ifi
e
rs
a
re
d
e
v
e
lo
p
e
d
fo
r
fe
a
tu
re
d
a
tas
e
t
a
n
d
c
o
n
v
o
lu
ti
o
n
a
l
n
e
u
ra
l
n
e
two
rk
(CNN
)
m
o
d
e
l
fo
r
ima
g
e
d
a
t
a
se
t.
Th
e
re
su
lt
s
o
b
tai
n
e
d
fo
r
e
v
e
ry
m
o
d
e
l
a
re
o
b
tain
e
d
u
si
n
g
sta
ti
stica
l
m
e
th
o
d
s
a
n
d
th
e
re
su
lt
s
a
re
e
x
p
re
ss
e
d
in
a
tab
le
fo
r
a
c
c
u
ra
c
y
,
p
re
c
isio
n
,
r
e
c
a
ll
a
n
d
F1
-
sc
o
re
.
A
c
las
sific
a
ti
o
n
a
c
c
u
ra
c
y
o
f
7
2
.
4
8
%
is
o
b
tai
n
e
d
f
o
r
S
VM
u
si
n
g
p
o
l
y
n
o
m
ial
k
e
rn
e
l
tri
c
k
b
y
c
o
n
sid
e
rin
g
a
ll
5
6
fe
a
tu
re
s.
Th
e
c
u
sto
m
i
z
e
d
CNN
m
o
d
e
l
is
d
e
sig
n
e
d
with
t
h
re
e
c
o
n
v
o
lu
ti
o
n
lay
e
rs
h
a
s
re
su
l
ted
in
9
7
.
1
3
%
o
f
train
in
g
a
c
c
u
ra
c
y
a
n
d
8
7
.
5
%
o
f
v
a
li
d
a
ti
o
n
a
c
c
u
ra
c
y
.
Ba
se
d
o
n
th
e
re
su
lt
s
o
b
tai
n
e
d
,
it
is
witn
e
ss
e
d
th
a
t
t
h
e
M
L
m
o
d
e
ls
e
m
p
lo
y
e
d
i
n
th
is
stu
d
y
t
o
c
las
sify
rice
ty
p
e
s wit
h
sim
il
a
r
a
p
p
e
a
ra
n
c
e
s h
a
v
e
p
ra
c
ti
c
a
l
a
p
p
li
c
a
ti
o
n
s.
K
ey
w
o
r
d
s
:
Mo
r
p
h
o
l
o
g
ically
s
im
ilar
I
n
d
ian
r
ice
v
ar
iety
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Su
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
K
-
n
ea
r
est n
eig
h
b
o
r
Dec
is
io
n
tr
ee
GL
C
M,
R
G
B
an
d
HSV
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Har
in
i Sh
ad
ak
s
h
ar
ap
p
a
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Scien
ce
an
d
E
n
g
in
ee
r
i
n
g
,
B
.
M.
S
.
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
B
an
g
alo
r
e
-
5
6
0
0
1
9
,
Kar
n
atak
a,
I
n
d
ia
E
m
ail:
h
h
ar
in
is
8
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
d
ia
is
o
n
e
o
f
t
h
e
lar
g
est
r
ice
ex
p
o
r
ter
s
2
0
1
1
[
1
]
.
B
ein
g
th
e
m
ajo
r
cu
ltiv
ato
r
s
o
f
r
ice,
it
is
also
b
ein
g
a
s
tap
le
f
o
o
d
in
I
n
d
ia
a
n
d
in
m
o
s
t
o
f
th
e
o
th
er
co
u
n
tr
ies.
I
n
d
ia
g
r
o
ws
n
ea
r
ly
4
8
9
v
ar
ieti
es
o
f
r
ice
in
cl
u
d
in
g
n
ativ
e
as we
ll a
s
h
y
b
r
id
[
2
]
.
So
n
a
-
m
asu
r
i,
a
m
e
d
iu
m
-
s
len
d
er
r
ice
v
ar
iety
is
p
o
p
u
lar
in
th
e
s
o
u
th
er
n
r
e
g
io
n
o
f
I
n
d
ia,
is
also
o
n
e
o
f
th
e
m
o
s
t
v
alu
ab
le
co
m
m
er
cial
v
ar
ieties
o
f
r
ice,
alo
n
g
s
id
e
b
a
s
m
ati.
T
h
er
e
ar
e
d
if
f
er
en
t
r
ice
q
u
alities
av
ailab
le
in
th
e
m
ar
k
et
wh
ic
h
ar
e
s
im
ilar
to
s
o
n
a
-
m
asu
r
i
b
u
t
d
if
f
er
f
r
o
m
co
m
m
er
cial
v
alu
e.
Fra
u
d
u
len
t
tr
ad
er
s
q
u
o
te
h
ig
h
er
p
r
ices
f
o
r
l
o
w
q
u
ality
r
ice.
T
h
is
is
a
h
u
g
e
lo
s
s
f
o
r
b
o
t
h
co
n
s
u
m
er
s
an
d
th
e
f
o
o
d
i
n
d
u
s
tr
y
.
I
d
en
tify
in
g
th
e
r
ig
h
t
ty
p
e
o
f
r
ice
v
ar
iety
am
o
n
g
th
e
s
im
ilar
ty
p
e
is
a
ch
allen
g
e.
Fro
m
ag
es
th
is
q
u
ality
an
aly
s
i
s
i
s
p
er
f
o
r
m
e
d
b
y
th
e
h
u
m
a
n
in
s
p
ec
tio
n
m
eth
o
d
.
T
h
i
s
ap
p
r
o
a
ch
i
s
tr
u
ly
b
a
s
ed
o
n
th
e
k
n
o
wl
ed
g
e
o
f
t
h
e
ex
p
er
t
a
lo
n
g
w
it
h
b
ein
g
tim
e
co
n
s
u
m
in
g
an
d
lab
o
r
io
u
s
.
Hen
c
e
in
r
e
ce
n
t
s
tu
d
i
e
s
co
m
p
u
ter
v
i
s
io
n
an
d
m
a
ch
in
e
lea
r
n
in
g
(
ML
)
b
a
s
ed
a
u
to
m
at
ed
s
o
lu
tio
n
i
s
u
s
ed
f
o
r
t
h
e
r
ic
e
an
d
o
th
e
r
f
o
o
d
g
r
a
in
s
cla
s
s
if
i
ca
tio
n
[
3
]
.
T
h
e
d
e
ta
i
l
s
o
f
th
e
a
p
p
r
o
a
ch
e
s
f
o
l
lo
w
e
d
b
y
r
e
s
ea
r
ch
er
s
ar
e
en
co
m
p
as
s
ed
in
th
e
n
ex
t
s
e
ct
io
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
la
s
s
if
ica
tio
n
o
f m
o
r
p
h
o
lo
g
ic
a
lly
s
imila
r
I
n
d
ia
n
r
ice
va
r
iety
u
s
in
g
…
(
Ha
r
in
i S
h
a
d
a
ksh
a
r
a
p
p
a
)
3203
T
h
e
g
r
ea
test
o
f
th
e
r
esear
ch
wo
r
k
s
in
an
aly
s
is
o
f
r
ice
q
u
al
ity
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
an
d
m
ac
h
in
e
lear
n
in
g
.
T
h
ese
wo
r
k
s
ar
e
lim
i
ted
to
:
−
Mo
r
p
h
o
l
o
g
ically
d
is
s
im
ilar
v
a
r
iety
o
f
r
ice
−
L
im
ited
to
lo
n
g
s
len
d
er
r
ice
v
ar
iety
-
lik
e
B
asm
ati
−
No
n
-
I
n
d
ian
v
a
r
iety
o
f
r
ice
T
h
e
m
ajo
r
o
b
jectiv
e
o
f
th
is
r
esear
ch
wo
r
k
is
to
d
ev
elo
p
a
m
ac
h
in
e
v
is
io
n
s
y
s
tem
ca
p
ab
le
o
f
ac
c
u
r
ately
class
if
y
in
g
v
is
u
ally
s
im
ilar
v
ar
ieties
o
f
r
ice
b
ased
o
n
th
eir
ex
tr
ac
ted
tex
tu
r
al,
m
o
r
p
h
o
lo
g
ical,
an
d
co
lo
r
f
ea
tu
r
es
f
r
o
m
im
ag
es.
T
h
is
s
t
u
d
y
ad
d
r
ess
es
th
e
ch
allen
g
e
o
f
d
is
tin
g
u
is
h
in
g
b
etwe
en
r
ic
e
v
ar
ieties
th
at
lo
o
k
s
im
ilar
b
u
t
d
if
f
er
in
q
u
ality
a
n
d
c
o
m
m
er
cial
v
alu
e,
wh
ich
i
s
a
s
ig
n
if
ican
t
is
s
u
e
in
a
g
r
icu
l
tu
r
al
m
ar
k
etin
g
an
d
co
n
s
u
m
er
p
r
o
tectio
n
.
Su
cc
ess
f
u
l
ap
p
licatio
n
s
o
f
m
a
ch
in
e
v
is
io
n
in
th
e
f
ield
o
f
ag
r
icu
ltu
r
al
p
r
o
d
u
ct
in
s
p
ec
tio
n
h
av
e
b
ee
n
o
b
s
er
v
ed
,
alth
o
u
g
h
a
m
ajo
r
it
y
o
f
th
ese
e
f
f
o
r
ts
ar
e
s
till
i
n
th
e
r
esear
ch
an
d
d
e
v
elo
p
m
en
t
s
tag
e
[
4
]
.
T
h
e
ex
p
lo
r
atio
n
o
f
im
ag
e
p
r
o
ce
s
s
in
g
an
d
ML
in
th
e
d
o
m
ain
o
f
r
ice
q
u
ality
an
aly
s
is
h
as
b
ee
n
o
n
g
o
in
g
f
o
r
d
ec
a
d
es
an
d
h
as
g
a
r
n
er
ed
co
n
s
id
er
a
b
l
e
r
esear
ch
atten
tio
n
.
Har
in
i
et
a
l.
[
5
]
h
av
e
p
u
t
f
o
r
th
a
r
ev
iew
d
etailin
g
th
e
m
eth
o
d
s
em
p
lo
y
ed
in
f
o
o
d
g
r
ain
q
u
ality
an
aly
s
is
.
T
h
e
s
am
e
au
th
o
r
s
h
av
e
also
co
n
tr
ib
u
te
d
a
r
esear
ch
o
n
t
h
e
an
aly
s
is
o
f
r
ice
q
u
ality
i
n
ter
m
s
o
f
th
e
o
th
e
r
p
ar
a
m
eter
s
b
y
a
p
p
ly
in
g
ML
ap
p
r
o
ac
h
[
6
]
.
R
esear
ch
en
d
ea
v
o
r
s
h
av
e
g
r
o
wn
r
ap
id
ly
in
th
e
p
ast
d
ec
ad
e.
I
n
a
s
tu
d
y
co
n
d
u
cted
b
y
Ko
k
lu
et
a
l.
[
7
]
,
f
iv
e
d
is
tin
ct
v
ar
ieties
o
f
r
ice
c
u
ltiv
ated
in
T
u
r
k
ey
wer
e
i
n
v
e
s
tig
ated
.
T
h
e
s
tu
d
y
an
al
y
ze
s
f
iv
e
r
ice
v
ar
ieties
—
Ar
b
o
r
io
,
B
asm
ati,
I
p
s
ala,
J
asm
in
e,
an
d
Kar
ac
ad
a
g
—
u
s
in
g
m
o
r
p
h
o
l
o
g
ical,
co
lo
r
,
an
d
s
h
ap
e
f
ea
tu
r
es.
R
em
ar
k
ab
le
class
if
icatio
n
ac
cu
r
ac
ies
wer
e
ac
h
iev
ed
:
9
9
.
8
7
%
with
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
,
9
9
.
9
5
%
with
d
ee
p
n
e
u
r
al
n
etwo
r
k
(
DN
N)
,
an
d
a
p
er
f
ec
t
1
0
0
% with
c
o
n
v
o
lu
ti
o
n
al
n
e
u
r
al
n
etwo
r
k
(
C
NN)
.
Sin
g
h
et
a
l.
[
8
]
h
a
v
e
in
tr
o
d
u
c
ed
a
m
o
d
el
aim
ed
at
class
if
y
in
g
f
o
u
r
v
ar
ieties
o
f
r
ice
g
r
ain
t
h
r
o
u
g
h
th
e
in
teg
r
atio
n
o
f
im
ag
e
p
r
o
ce
s
s
in
g
an
d
ML
alg
o
r
ith
m
s
.
T
h
e
m
eth
o
d
o
l
o
g
y
ex
tr
ac
ts
co
l
o
r
,
t
ex
tu
r
e,
a
n
d
wav
elet
f
ea
tu
r
es,
u
s
in
g
s
u
p
p
o
r
t
v
ec
t
o
r
m
ac
h
in
e
(
SVM)
,
K
-
n
ea
r
est
n
eig
h
b
o
r
(
KNN)
,
n
aïv
e
B
ay
es
(
NB
)
,
an
d
b
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
etwo
r
k
(
B
PNN)
f
o
r
class
if
icatio
n
a
n
aly
s
is
.
B
PNN
ac
h
iev
es
th
e
h
ig
h
est
ac
cu
r
ac
y
o
f
9
6
% a
cr
o
s
s
all
f
ea
tu
r
e
s
ets,
th
o
u
g
h
t
h
e
s
tu
d
y
lac
k
s
d
etails o
n
r
ice
v
ar
ieties an
d
m
o
r
p
h
o
lo
g
ical
s
im
ilar
ities
.
A
wo
r
k
p
r
o
p
o
s
ed
b
y
Asi
f
et
a
l.
[
9
]
class
if
ies
s
ix
d
if
f
er
e
n
t
v
ar
iety
o
f
r
ice
an
d
also
aim
s
in
q
u
ality
an
aly
s
is
o
f
r
ice.
T
h
e
s
tu
d
y
u
s
ed
PC
A
an
d
C
an
n
y
ed
g
e
d
etec
tio
n
f
o
r
class
if
icatio
n
a
n
d
e
x
tr
ac
te
d
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
f
o
r
r
ice
q
u
ality
an
aly
s
is
,
ac
h
iev
in
g
9
2
.
3
%
a
n
d
8
9
.
5
%
ac
cu
r
ac
y
,
r
esp
ec
tiv
ely
.
Ho
wev
er
,
it d
o
es n
o
t d
is
cu
s
s
th
e
m
o
r
p
h
o
lo
g
ical
s
im
ilar
ity
o
f
th
e
r
ice
v
ar
ieties co
n
s
id
er
e
d
.
I
n
th
e
s
tu
d
y
c
o
n
d
u
cted
b
y
L
in
et
a
l.
[
1
0
]
,
a
d
ee
p
c
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
(
DC
NN)
was
u
s
ed
to
class
if
y
r
ice
k
er
n
el
im
ag
es,
o
u
tp
er
f
o
r
m
in
g
tr
a
d
itio
n
al
m
eth
o
d
s
lik
e
PHOG
-
KNN,
PHO
G
-
SVM,
GI
ST
-
KNN,
an
d
GI
ST
-
SVM.
T
h
e
DC
NN
ac
h
iev
ed
a
p
ea
k
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
9
.
4
%
with
a
b
atch
s
ize
o
f
1
5
an
d
2
0
ep
o
ch
s
.
C
in
ar
et
a
l.
[
1
1
]
h
av
e
em
er
g
e
d
with
a
co
m
p
u
ter
ized
v
is
io
n
-
b
ased
s
y
s
tem
was
d
ev
elo
p
ed
to
d
if
f
er
en
tiate
b
etwe
en
two
p
r
o
p
r
ietar
y
r
ice
s
p
ec
ies
u
s
in
g
3
,
8
1
0
r
ice
g
r
ain
im
ag
es
an
d
s
e
v
en
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es.
L
in
et
a
l.
em
p
lo
y
e
d
v
ar
io
u
s
ML
m
o
d
els,
ac
h
ie
v
in
g
class
if
icatio
n
ac
cu
r
ac
ies
o
f
L
R
-
9
3
.
0
2
%,
ML
P
-
9
2
.
8
6
%,
SVM
-
9
2
.
8
3
%,
DT
-
9
2
.
4
9
%,
R
F
-
9
2
.
3
9
%,
NB
-
9
1
.
7
1
%,
an
d
K
NN
-
8
8
.
5
8
%.
I
d
en
tify
in
g
an
d
class
if
y
in
g
v
i
s
u
ally
s
im
ilar
f
o
o
d
g
r
ain
s
is
ch
allen
g
in
g
,
b
u
t
a
u
to
m
ated
r
ec
o
g
n
itio
n
s
y
s
tem
s
h
elp
m
itig
ate
m
is
r
ec
o
g
n
itio
n
.
Gu
jjar
et
a
l.
[
1
2
]
p
r
o
p
o
s
ed
a
m
et
h
o
d
u
s
in
g
tex
tu
r
e,
m
o
r
p
h
o
lo
g
y
,
a
n
d
co
lo
r
-
b
ased
r
etr
iev
al
o
n
B
asm
ati
r
ice
im
ag
es,
em
p
lo
y
in
g
im
ag
e
war
p
in
g
,
d
is
cr
im
in
a
n
t
an
aly
s
is
,
an
d
a
b
ac
k
-
p
r
o
p
a
g
atio
n
n
e
u
r
al
n
et
wo
r
k
to
class
if
y
s
ix
r
ice
v
ar
ieties.
T
h
ey
d
ev
elo
p
ed
a
d
ig
ital
im
ag
e
an
aly
s
is
alg
o
r
ith
m
to
i
d
en
tify
s
ix
d
if
f
e
r
en
t
v
a
r
ieties
o
f
B
asm
ati
r
ice
s
ee
d
s
co
m
m
o
n
l
y
c
u
ltiv
ated
i
n
I
n
d
ia.
Dis
cr
im
in
ate
an
aly
s
is
was c
o
n
d
u
cted
u
s
in
g
n
in
e
f
ea
tu
r
es e
ac
h
f
o
r
c
o
lo
r
,
m
o
r
p
h
o
lo
g
ical,
an
d
tex
tu
r
e
asp
ec
ts
.
Ad
d
itio
n
ally
,
a
b
ac
k
-
p
r
o
p
a
g
atio
n
n
eu
r
al
n
etwo
r
k
-
b
ased
class
if
ier
was
im
p
lem
en
ted
f
o
r
th
e
i
d
en
tific
atio
n
o
f
u
n
k
n
o
wn
g
r
ain
ty
p
es
[
1
3
]
.
Ko
lk
u
r
e
et
a
l.
[
1
4
]
h
av
e
in
tr
o
d
u
ce
d
an
a
u
to
m
ated
ev
alu
atio
n
m
eth
o
d
was
i
n
tr
o
d
u
ce
d
f
o
r
r
ice
q
u
alit
y
ass
es
s
m
en
t
u
s
in
g
co
lo
r
an
d
g
eo
m
etr
ic
f
ea
tu
r
es.
A
n
eu
r
al
n
etwo
r
k
m
o
d
el,
tr
ai
n
ed
o
n
ap
p
ea
r
an
ce
f
ea
t
u
r
es,
ef
f
ec
tiv
ely
id
e
n
tifie
d
u
n
k
n
o
w
n
g
r
ai
n
s
an
d
d
em
o
n
s
tr
ated
p
r
o
m
is
in
g
r
esu
lts
in
q
u
ality
ev
a
lu
atio
n
.
Srim
u
ly
an
i
et
a
l.
[
1
5
]
a
n
aly
ze
d
n
in
e
I
n
d
o
n
esian
r
ice
v
a
r
ieties
u
s
in
g
i
m
ag
es
ca
p
tu
r
ed
with
a
C
an
o
n
D6
0
0
.
T
h
eir
s
tu
d
y
f
o
u
n
d
th
at
co
m
b
in
in
g
s
ix
g
eo
m
etr
ic
f
ea
tu
r
es
with
co
l
o
r
,
tex
tu
r
e,
a
n
d
s
h
a
p
e
im
p
r
o
v
ed
p
er
f
o
r
m
an
ce
,
ac
h
iev
i
n
g
1
0
0
%
ac
c
u
r
ac
y
with
th
e
b
ac
k
-
p
r
o
p
a
g
atio
n
alg
o
r
ith
m
a
n
d
a
5
.
2
%
in
cr
ea
s
e
with
lear
n
in
g
v
ec
to
r
q
u
an
tizatio
n
(
L
VQ)
.
T
h
e
p
r
im
ar
y
g
o
al
o
f
th
is
s
tu
d
y
is
to
cr
ea
te
a
m
ac
h
in
e
v
is
io
n
s
y
s
tem
ca
p
ab
le
o
f
class
if
y
in
g
v
is
u
ally
s
im
ilar
v
ar
ieties
o
f
r
ice
g
r
ai
n
b
ased
o
n
th
eir
ex
tr
ac
ted
t
ex
tu
r
al,
m
o
r
p
h
o
lo
g
ical,
an
d
co
lo
r
f
ea
tu
r
es
f
r
o
m
im
ag
es.
T
h
e
r
esear
ch
f
o
cu
s
es
o
n
d
ev
elo
p
in
g
a
n
alg
o
r
ith
m
d
esig
n
ed
to
ca
teg
o
r
iz
e
im
ag
es
o
f
f
o
u
r
s
im
ilar
-
lo
o
k
in
g
r
ice
v
ar
ieties
u
s
in
g
th
ese
ex
tr
ac
te
d
f
ea
t
u
r
es.
Sev
er
al
ML
m
o
d
els
a
r
e
ev
alu
ated
f
o
r
th
eir
ef
f
ec
tiv
en
ess
in
ac
h
iev
in
g
th
is
class
if
icatio
n
task
.
T
h
e
m
eth
o
d
o
lo
g
y
an
d
th
e
o
b
tai
n
ed
r
esu
lts
ar
e
f
u
r
t
h
er
elab
o
r
ated
in
t
h
e
s
u
b
s
eq
u
e
n
t sectio
n
s
o
f
th
is
p
ap
e
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
0
2
-
3
2
1
1
3204
2.
M
E
T
H
O
D
Sin
ce
th
er
e
is
a
n
ee
d
f
o
r
au
to
m
ated
s
o
lu
tio
n
s
,
ex
ten
s
iv
e
r
esear
ch
h
as
b
ee
n
co
n
d
u
cted
o
v
e
r
th
e
p
ast
d
ec
ad
e
o
n
th
e
q
u
ality
an
aly
s
is
o
f
f
o
o
d
g
r
ain
s
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
an
d
m
ac
h
in
e
lear
n
in
g
.
I
m
ag
e
p
r
o
ce
s
s
in
g
in
v
o
lv
es
s
ev
er
al
s
tep
s
lik
e
Pre
-
p
r
o
ce
s
s
in
g
,
s
eg
m
en
tatio
n
,
tr
an
s
f
o
r
m
atio
n
,
f
ea
t
u
r
e
ex
t
r
ac
tio
n
an
d
f
ea
tu
r
e
an
aly
s
is
[
3
]
.
T
h
e
p
r
o
ce
s
s
b
e
g
in
s
with
im
ag
e
co
llectio
n
u
s
in
g
a
s
tan
d
ar
d
s
etu
p
to
e
n
s
u
r
e
u
n
if
o
r
m
ity
an
d
m
in
im
ize
n
o
is
e,
f
o
llo
wed
b
y
p
r
ep
r
o
ce
s
s
in
g
to
r
em
o
v
e
ir
r
elev
an
t
in
f
o
r
m
atio
n
.
I
m
ag
e
s
eg
m
e
n
tatio
n
,
p
e
r
f
o
r
m
ed
in
th
e
s
p
atial
o
r
f
r
eq
u
en
cy
d
o
m
ain
,
id
en
tifie
s
m
ea
n
in
g
f
u
l
r
e
g
io
n
s
an
d
o
b
jects.
Seg
m
en
tatio
n
o
r
m
ath
em
atica
l
tr
an
s
f
o
r
m
atio
n
s
h
elp
e
x
tr
ac
t
ess
en
tial
f
ea
tu
r
es,
wh
ich
ar
e
f
u
r
th
er
r
e
f
in
ed
th
r
o
u
g
h
f
ilter
i
n
g
.
T
h
ese
f
ea
tu
r
es,
in
clu
d
in
g
g
e
o
m
etr
ic,
h
is
to
g
r
a
m
,
an
d
co
lo
r
p
r
o
p
er
ties
,
ar
e
th
en
an
aly
ze
d
f
o
r
class
if
icatio
n
.
T
h
is
s
tu
d
y
f
o
cu
s
es
o
n
a
p
ar
ticu
la
r
ty
p
e
o
f
r
ice
g
r
ain
s
.
T
h
e
in
itial
p
h
ase
in
v
o
l
v
ed
in
g
ath
er
i
n
g
s
am
p
les
o
f
th
e
r
ice
a
n
d
ca
p
tu
r
i
n
g
p
ictu
r
es to
estab
lis
h
d
ataset.
T
h
e
en
tire
p
r
o
ce
d
u
r
e
em
p
l
o
y
ed
f
o
r
th
is
in
v
esti
g
atio
n
is
o
u
tlin
ed
in
Fig
u
r
e
1
.
Fo
u
r
d
if
f
er
en
t
t
y
p
es
o
f
r
ice
s
h
o
wn
in
Fig
u
r
e
2
,
th
at
ar
e
av
ailab
le
in
t
h
e
m
ar
k
et
w
h
ich
h
a
v
e
m
o
r
p
h
o
lo
g
ical
s
im
ilar
ities
wer
e
g
ath
er
e
d
f
o
r
q
u
ality
a
n
aly
s
is
an
d
ass
ess
ed
at
M/s.
Sh
r
i
B
h
ag
y
alak
s
h
m
i
Ag
r
o
.
Fo
o
d
Pv
t.
L
td
.
T
h
ese
v
a
r
ieties,
co
m
p
ar
ab
le
to
So
n
a
-
Ma
s
u
r
i
an
d
ca
teg
o
r
ize
d
as
m
ed
i
u
m
-
s
ized
r
ice,
a
r
e
d
esig
n
ated
b
y
th
e
n
a
m
es:
i)
B
.
R
.
T
Daiwa
n
–
r
ef
er
r
ed
as
R
awh
(
Fig
u
r
e
2
(
a)
)
,
ii)
Gr
i
n
e
wo
r
ld
-
r
ef
er
r
e
d
as
R
awl
(
Fig
u
r
e
2
(
b
)
)
,
iii)
R
o
y
a
l
So
n
a
-
r
ef
er
r
e
d
as
Steam
h
(
Fig
u
r
e
2
(
c
)
)
,
a
n
d
i
v
)
Daiwa
n
So
n
a
-
r
ef
er
r
ed
as
Steam
l (
Fig
u
r
e
2
(
d
)
)
T
h
e
co
n
s
id
er
e
d
v
a
r
ieties
o
f
r
i
ce
s
am
p
les
h
av
e
two
r
aw
a
n
d
two
s
team
r
ice
ca
teg
o
r
ies.
T
h
e
m
ajo
r
ch
allen
g
e
in
th
is
class
if
icatio
n
m
o
d
el
is
th
e
s
im
ilar
f
ea
tu
r
es
am
o
n
g
th
ese
v
ar
ieties.
T
h
e
u
n
d
er
lin
g
ch
allen
g
e
o
f
th
is
wo
r
k
is
t
o
m
a
k
e
p
r
o
p
er
r
ice
v
ar
iety
class
if
icatio
n
.
T
h
is
in
f
lu
e
n
ce
s
th
e
c
o
m
m
er
cial
m
ar
k
et
o
f
th
e
g
r
ain
.
Fig
u
r
e
2
s
h
o
ws th
e
s
am
p
le
im
ag
es.
Fig
u
r
e
1
.
Me
th
o
d
f
o
llo
wed
f
o
r
class
if
icatio
n
o
f
s
im
ilar
lo
o
k
i
n
g
I
n
d
ian
r
ice
g
r
ain
s
(
a
)
(
b
)
(
c
)
(
d
)
Fig
u
r
e
2
.
Sam
p
le
im
a
g
es o
f
(
a
)
R
awh
)
,
(
b
)
R
awl,
(
c)
Steam
h
,
an
d
(
d
)
Steam
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
la
s
s
if
ica
tio
n
o
f m
o
r
p
h
o
lo
g
ic
a
lly
s
imila
r
I
n
d
ia
n
r
ice
va
r
iety
u
s
in
g
…
(
Ha
r
in
i S
h
a
d
a
ksh
a
r
a
p
p
a
)
3205
2
.
1
.
Da
t
a
s
et
cr
ea
t
io
n
A
to
tal
o
f
4
1
8
0
im
a
g
es
(
wh
ich
in
clu
d
e
1
0
4
5
im
ag
es
o
f
ea
ch
v
ar
iety
)
d
e
p
ictin
g
r
ice
k
er
n
els f
r
o
m
f
o
u
r
v
is
u
ally
an
alo
g
o
u
s
r
ice
v
ar
iet
ies
wer
e
ac
q
u
ir
ed
th
r
o
u
g
h
a
s
tan
d
ar
d
im
ag
e
ac
q
u
is
itio
n
m
o
d
el.
T
h
is
in
clu
d
es
E
ac
h
im
ag
e
th
at
was
ca
p
tu
r
e
d
u
s
in
g
a
m
o
b
ile
ca
m
e
r
a
f
ea
tu
r
in
g
5
0
MP
r
eso
lu
tio
n
,
2
.
5
X
z
o
o
m
,
a
n
d
f
lash
lig
h
t
in
a
s
tan
d
ar
d
ized
s
etu
p
.
T
h
e
ac
q
u
ir
e
d
im
ag
es
ar
e
ch
an
n
eled
f
o
r
in
itial
s
tep
s
wh
ich
in
clu
d
es
p
r
e
-
p
r
o
ce
s
s
ed
an
d
f
ea
tu
r
es
e
x
tr
ac
tio
n
.
A
to
tal
o
f
5
6
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
in
clu
d
i
n
g
tex
tu
r
al,
co
lo
r
a
n
d
wav
elet
f
ea
tu
r
es
ar
e
co
n
s
id
er
ed
.
T
h
e
f
ea
tu
r
es
ar
e
e
x
tr
ac
ted
u
s
in
g
g
r
ey
lev
el
c
o
-
o
cc
u
r
r
en
ce
m
atr
ix
(
GL
C
M)
,
r
ed
,
g
r
ee
n
,
b
l
u
e
(
R
GB
)
an
d
h
u
e,
s
atu
r
atio
n
,
v
alu
e
(
HSV)
co
l
o
r
s
p
ac
es.
T
h
e
f
ea
tu
r
es a
r
e
s
h
o
wn
in
T
ab
le
1
.
T
h
e
d
etails o
f
GL
C
M
f
ea
tu
r
es a
r
e
g
iv
en
in
T
a
b
le
2
.
T
ab
le
1
.
Featu
r
es
ex
tr
ac
te
d
f
r
o
m
th
e
r
ice
g
r
ain
im
ag
e
F
e
a
t
u
r
e
Ty
p
e
F
e
a
t
u
r
e
s
To
t
a
l
n
u
m
b
e
r
o
f
f
e
a
t
u
r
e
s
G
LC
M
W
i
d
t
h
,
C
o
n
t
r
a
st
,
D
i
ss
i
mi
l
a
r
i
t
y
H
e
i
g
h
t
,
A
sp
e
c
t
R
a
t
i
o
,
E
n
e
r
g
y
,
C
o
r
r
e
l
a
t
i
o
n
a
n
d
H
o
mo
g
e
n
e
i
t
y
.
8
R
G
B
a
n
d
H
S
V
C
o
l
o
r
S
k
e
w
n
e
ss,
S
t
a
n
d
a
r
d
d
e
v
i
a
t
i
o
n
,
K
u
r
t
o
s
i
s,
M
e
a
n
a
n
d
W
a
v
e
l
e
t
d
e
c
o
m
p
o
si
t
i
o
n
4
8
(
2
4
f
e
a
t
u
r
e
s
e
a
c
h
o
f
R
G
B
a
n
d
H
S
V
)
T
ab
le
2
.
Deta
ils
o
f
GL
C
M
f
ea
tu
r
es
[
1
6
]
S
l
.
N
o
.
F
e
a
t
u
r
e
Ex
p
l
a
n
a
t
i
o
n
1.
C
o
n
t
r
a
st
C
o
n
t
r
a
s
t
i
s
t
h
e
d
i
s
t
i
n
c
t
i
o
n
m
e
a
s
u
r
e
d
b
e
t
w
e
e
n
t
o
p
a
n
d
b
o
t
t
o
m
v
a
l
u
e
o
f
p
i
x
e
l
s
a
d
j
a
c
e
n
t
i
n
a
g
i
v
e
n
i
m
a
g
e
.
I
t
h
a
s
l
o
w
s
p
a
t
i
a
l
f
r
e
q
u
e
n
c
i
e
s
i
f
i
t
s
c
o
n
t
r
a
s
t
v
a
l
u
e
i
s
l
o
w
a
n
d
i
s
t
h
e
c
o
n
c
e
n
t
r
a
t
i
o
n
t
e
r
m
a
r
o
u
n
d
t
h
e
m
a
j
o
r
d
i
a
g
o
n
a
l
.
2.
D
i
ssi
m
i
l
a
r
i
t
y
D
i
s
s
i
m
i
l
a
r
i
t
y
m
e
a
s
u
r
e
s
t
h
e
l
o
c
a
l
v
a
r
i
a
t
i
o
n
s
l
i
n
e
a
r
l
y
i
n
a
g
i
v
e
n
i
m
a
g
e
.
3.
H
o
mo
g
e
n
e
i
t
y
I
t
l
o
o
k
s
a
t
b
i
g
g
e
r
v
a
l
u
e
s
w
h
e
n
t
h
e
r
e
i
s
a
l
e
s
s
e
r
d
i
f
f
e
r
e
n
c
e
b
e
t
w
e
e
n
t
h
e
p
a
i
r
o
f
g
r
e
y
t
o
n
e
e
l
e
m
e
n
t
s
.
H
o
m
o
g
e
n
e
i
t
y
i
s
s
e
n
s
i
t
i
v
e
t
o
n
e
a
r
l
y
d
i
a
g
o
n
a
l
e
l
e
m
e
n
t
s
.
W
h
e
n
t
h
e
p
i
x
e
l
s
i
n
i
m
a
g
e
s
a
r
e
i
d
e
n
t
i
c
a
l
,
t
h
e
m
e
a
s
u
r
e
o
f
h
o
m
o
g
e
n
e
i
t
y
w
i
l
l
b
e
h
i
g
h
e
s
t
.
T
h
i
s
i
s
t
h
e
o
p
p
o
s
i
t
e
o
f
c
o
n
t
r
a
s
t
.
4.
En
e
r
g
y
E
n
e
r
g
y
i
s
n
o
t
h
i
n
g
b
u
t
t
h
e
s
q
u
a
r
e
r
o
o
t
o
f
a
n
a
n
g
u
l
a
r
s
e
c
o
n
d
m
o
m
e
n
t
.
E
n
e
r
g
y
w
i
l
l
b
a
r
e
h
i
g
h
e
r
v
a
l
u
e
s
,
w
h
e
n
t
h
e
w
i
n
d
o
w
i
s
o
r
d
e
r
l
y
a
r
r
a
n
g
e
d
.
5.
C
o
r
r
e
l
a
t
i
o
n
C
o
r
r
e
l
a
t
i
o
n
g
i
v
e
s
l
i
n
e
a
r
d
e
p
e
n
d
e
n
c
i
e
s
a
m
o
n
g
t
h
e
g
r
a
y
t
o
n
e
o
f
t
h
e
i
m
a
g
e
.
T
h
e
ab
o
v
e
-
m
en
tio
n
ed
tex
t
u
r
e
f
ea
tu
r
es a
r
e
ca
lcu
lated
u
s
in
g
t
h
e
(
1
)
t
o
(
5
)
:
=
∑
∑
(
,
)
∗
(
−
)
2
−
1
=
0
−
1
=
0
(
1
)
=
∑
∑
(
,
)
∗
(
−
)
2
−
1
=
0
−
1
=
0
(
2
)
=
∑
∑
(
,
)
∗
|
−
|
−
1
=
0
−
1
=
0
(
3
)
=
∑
∑
(
,
)
2
−
1
=
0
−
1
=
0
(
4
)
=
∑
∑
(
,
)
(
−
µ
)
(
−
µ
)
2
−
1
=
0
−
1
=
0
(
5
)
I
n
th
e
ab
o
v
e
e
q
u
atio
n
s
:
n
-
th
e
n
u
m
b
er
o
f
g
r
ay
lev
els.
P(x
,
y
)
–
f
o
r
th
e
g
iv
e
n
p
o
s
itio
n
x
a
n
d
y
,
th
is
m
ea
s
u
r
es
th
e
g
r
ay
-
s
ca
le’
s
n
o
r
m
alize
d
with
th
e
s
u
m
eq
u
al
to
u
n
ity
.
µ
-
th
e
GL
C
M
m
ea
n
.
σ
2
-
th
e
v
ar
ian
ce
o
f
th
e
in
ten
s
ities
o
f
all
r
ef
er
en
ce
p
ix
els.
Alo
n
g
with
th
e
ab
o
v
e
lis
t
o
f
tex
tu
r
al
f
ea
tu
r
es,
4
8
co
lo
r
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
.
T
h
e
lis
t is sh
o
wn
in
T
ab
le
3
.
T
ab
le
3
.
L
is
t o
f
c
o
lo
r
f
ea
tu
r
es
C
o
l
o
r
S
p
a
c
e
F
e
a
t
u
r
e
R
G
B
M
e
a
n
_
R
G
B
_
R
M
e
a
n
_
R
G
B
_
G
M
e
a
n
_
R
G
B
_
B
S
t
d
_
R
G
B
_
R
S
t
d
_
R
G
B
_
G
S
t
d
_
R
G
B
_
B
S
k
e
w
_
R
G
B
_
R
S
k
e
w
_
R
G
B
_
G
S
k
e
w
_
R
G
B
_
B
K
u
r
t
o
si
s
_
R
G
B
_
R
K
u
r
t
o
si
s
_
R
G
B
_
G
K
u
r
t
o
si
s
_
R
G
B
_
B
H
A
A
R
_
R
LL
H
A
A
R
_
R
LH
H
A
A
R
_
R
H
L
H
A
A
R
_
R
H
H
H
A
A
R
_
G
LL
H
A
A
R
_
G
LH
H
A
A
R
_
GHL
H
A
A
R
_
GHH
H
A
A
R
_
B
LL
H
A
A
R
_
B
LH
H
A
A
R
_
B
H
L
H
A
A
R
_
B
H
H
H
S
V
M
e
a
n
_
H
S
V
_
H
M
e
a
n
_
H
S
V
_
S
M
e
a
n
_
H
S
V
_
V
S
t
d
_
H
S
V
_
H
S
t
d
_
H
S
V
_
S
S
t
d
_
H
S
V
_
V
S
k
e
w
_
H
S
V
_
R
S
k
e
w
_
H
S
V
_
G
S
k
e
w
_
H
S
V
_
B
K
u
r
t
o
si
s
_
H
S
V
_
R
K
u
r
t
o
si
s
_
H
S
V
_
G
K
u
r
t
o
si
s
_
H
S
V
_
B
H
A
A
R
_
R
LL
H
A
A
R
_
R
LH
H
A
A
R
_
R
H
L
H
A
A
R
_
R
H
H
H
A
A
R
_
G
LL
H
A
A
R
_
G
LH
H
A
A
R
_
GHL
H
A
A
R
_
GHH
H
A
A
R
_
B
LL
H
A
A
R
_
B
LH
H
A
A
R
_
B
H
L
H
A
A
R
_
B
H
H
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
0
2
-
3
2
1
1
3206
2
.
2
.
M
L
m
o
dels
On
ce
th
e
f
ea
tu
r
es
ar
e
ex
tr
ac
ted
,
th
e
ML
m
o
d
els
ar
e
tr
ain
ed
.
T
h
e
en
tire
d
ataset
in
clu
d
es
f
ea
tu
r
es
o
f
4
1
8
0
r
ice
k
er
n
els.
T
h
e
SVM,
KNN
an
d
d
ec
is
io
n
tr
ee
(
DT
)
a
r
e
u
s
ed
in
th
is
wo
r
k
.
T
h
is
d
ata
s
et
is
clas
s
if
ied
in
to
tr
ain
in
g
an
d
test
in
g
s
et
with
a
r
atio
o
f
8
0
:2
0
.
T
h
e
p
er
f
o
r
m
an
ce
s
o
f
ea
ch
o
f
th
ese
m
eth
o
d
s
ar
e
d
is
cu
s
s
ed
in
th
e
r
esu
lt sectio
n
o
f
th
e
p
ap
er
.
2
.
2
.
1
.
SVM
SVM
is
a
Su
p
er
v
is
ed
L
ea
r
n
in
g
alg
o
r
ith
m
u
s
ed
f
o
r
class
if
icatio
n
an
d
e
v
en
f
o
r
r
e
g
r
ess
io
n
p
r
o
b
lem
s
.
T
h
is
alg
o
r
ith
m
tr
ies
to
f
in
d
th
e
b
est
h
y
p
er
p
la
n
e
wh
ich
s
ep
ar
ates
th
e
two
class
es.
SVM
ca
n
h
a
n
d
le
n
o
n
-
lin
ea
r
d
ata
u
s
in
g
“Ke
r
n
el
tr
ic
k
”.
I
t
u
s
es th
r
ee
k
er
n
el
f
u
n
ctio
n
s
n
am
e
ly
: L
in
ea
r
,
Po
ly
n
o
m
ial,
an
d
R
ad
ial
b
asis
(
R
B
F).
2
.
2
.
2
.
DT
Dec
is
io
n
tr
ee
s
ca
n
p
er
f
o
r
m
b
o
th
class
if
icatio
n
an
d
r
eg
r
ess
io
n
task
s
.
A
d
ec
is
io
n
tr
ee
is
a
p
r
e
d
ictiv
e
m
o
d
el
th
at
m
ak
es
d
ec
is
io
n
s
b
ased
o
n
th
e
i
n
p
u
t
d
ata,
u
s
in
g
a
f
lo
wch
ar
t
-
lik
e
s
tr
u
ctu
r
e.
T
h
e
tr
ee
co
n
s
is
ts
o
f
b
r
an
ch
es,
a
r
o
o
t,
lea
v
es,
an
d
in
ter
n
al
n
o
d
es.
I
n
th
is
s
tr
u
ct
u
r
e,
ea
c
h
in
ter
n
al
n
o
d
e
test
s
an
attr
ib
u
te,
ev
er
y
b
r
an
ch
r
ep
r
esen
ts
an
attr
ib
u
te
v
alu
e,
a
n
d
ea
c
h
leaf
n
o
d
e
s
ig
n
if
ies
th
e
f
in
al
d
ec
is
io
n
o
r
p
r
ed
ictio
n
b
ased
o
n
th
e
p
r
o
v
id
e
d
d
ataset.
Attr
ib
u
te
s
elec
tio
n
at
in
ter
n
al
is
ca
r
r
ied
o
u
t
eith
e
r
b
y
ca
lcu
latin
g
I
n
f
o
r
m
atio
n
g
ain
(
I
G
)
o
r
Gin
i
in
d
ex
.
T
h
e
f
o
r
m
u
la
f
o
r
I
G
a
n
d
Gin
i
in
d
ex
is
g
iv
e
n
in
(
6
)
an
d
(
7
)
:
=
(
)
−
[
(
ℎ
)
∗
(
ℎ
)
(
6
)
=
1
−
∑
2
(7
)
E
n
tr
o
p
y
wh
ich
is
u
s
ed
in
I
G
ca
lcu
latio
n
is
th
e
am
o
u
n
t
o
f
u
n
ce
r
tain
ty
i
n
o
u
r
d
ataset
o
r
m
ea
s
u
r
e
o
f
d
is
o
r
d
er
.
T
h
e
ca
lcu
latio
n
o
f
E
n
tr
o
p
y
is
ca
r
r
ied
o
u
t u
s
in
g
th
e
f
o
r
m
u
la
(
8
)
:
E
(
S
)
=
−
p
(
+
)
l
og
p
(
+
)
−
p
(
−
)
l
og
p
(
−
)
(
8
)
h
er
e,
E
=
E
n
tr
o
p
y
,
S=
T
o
tal
n
u
m
b
er
o
f
s
am
p
les,
p
(
+
)
=
p
r
o
b
a
b
ilit
y
o
f
p
o
s
itiv
e
class
,
p
(
−
)
=
p
r
o
b
ab
ilit
y
o
f
n
eg
ativ
e
class
2
.
2
.
3
.
K
NN
T
h
is
alg
o
r
ith
m
c
o
n
s
id
er
s
th
e
s
im
ilar
ity
b
etwe
en
th
e
a
v
ailab
le
an
d
n
ew
d
ata.
I
t
t
h
en
ca
teg
o
r
izes
n
ew
d
ata
in
to
th
e
class
wh
ich
is
i
n
clo
s
e
p
r
o
x
im
ity
with
av
ailab
l
e
class
KNN
is
a
m
em
o
r
y
-
b
as
ed
alg
o
r
ith
m
as
is
s
to
r
es
th
e
av
ailab
le
d
ata
in
m
em
o
r
y
an
d
ass
ig
n
s
clas
s
to
n
ew
d
ata
b
ased
o
n
s
im
ilar
it
y
.
KNN
ca
lcu
lates
d
is
tan
ce
b
etwe
en
d
ata
p
o
in
ts
an
d
th
e
n
ew
d
ata
u
s
in
g
E
u
clid
ea
n
d
is
tan
ce
f
o
r
m
u
la
a
n
d
th
e
n
ew
d
ata
is
ca
teg
o
r
ized
to
t
h
e
n
ea
r
est
n
ei
g
h
b
o
r
.
T
h
e
f
o
r
m
u
la
f
o
r
ca
lcu
l
atin
g
E
u
clid
ea
n
d
is
tan
ce
is
p
r
o
v
id
ed
in
(
9
)
.
KNN
is
a
n
o
n
-
p
a
r
am
etr
ic
alg
o
r
ith
m
b
ec
au
s
e
it d
o
es n
o
t
m
ak
e
an
y
ass
u
m
p
tio
n
s
ab
o
u
t th
e
u
n
d
e
r
ly
in
g
d
ata.
=
√
(
2
−
1
)
2
+
(
2
−
1
)
2
(
9
)
wh
er
e
(
1
,
1
)
an
d
(
2
,
2
)
ar
e
th
e
co
-
o
r
d
in
ates o
f
th
e
two
d
ata
p
o
i
n
ts
.
2
.
2
.
4
.
E
ns
em
ble m
et
ho
d (
E
M
)
E
n
s
em
b
le
m
eth
o
d
s
r
ef
er
to
a
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
th
at
co
m
b
in
es
m
u
ltip
le
b
ase
m
o
d
el
s
to
cr
ea
t
e
an
o
p
tim
al
p
r
e
d
ictiv
e
m
o
d
el.
T
h
ese
en
s
em
b
les
ar
e
p
ar
tic
u
lar
ly
u
s
ef
u
l
in
class
if
icatio
n
task
s
,
as
th
ey
ca
n
ac
h
iev
e
h
i
g
h
ac
c
u
r
ac
ies
b
y
le
v
er
ag
in
g
th
e
d
iv
er
s
e
s
tr
en
g
th
s
o
f
in
d
iv
i
d
u
al
b
ase
m
o
d
els.
E
v
en
if
th
e
ac
cu
r
ac
y
o
f
ea
ch
b
ase
class
if
ier
i
s
r
elat
iv
ely
lo
w,
th
e
en
s
em
b
le
ca
n
ex
ce
l
if
d
if
f
er
en
t
b
ase
m
o
d
els
m
is
class
if
y
d
is
tin
ct
tr
ain
in
g
e
x
am
p
les.
I
n
th
is
wo
r
k
,
an
en
s
em
b
le
m
o
d
el
co
n
s
is
tin
g
o
f
SVM,
DT
an
d
KNN
i
s
u
s
ed
.
T
h
e
r
esu
lts
o
b
tain
ed
ar
e
d
is
cu
s
s
ed
in
th
e
r
esu
lt sectio
n
.
2
.
3
.
CNN
C
NN
i
s
a
m
o
d
el
th
at
m
ak
es
u
s
e
o
f
d
ee
p
lear
n
in
g
f
o
r
u
s
es
in
clu
d
in
g
n
atu
r
al
lan
g
u
ag
e,
s
p
ee
ch
r
ec
o
g
n
itio
n
,
p
ictu
r
e
p
r
o
ce
s
s
in
g
,
an
d
d
atasets
wh
er
e
lar
g
e
q
u
an
titi
es
o
f
d
ata
ex
is
t
[
1
7
]
.
E
n
d
-
to
-
e
n
d
class
if
icatio
n
ca
n
b
r
o
ad
ly
ap
p
ly
u
s
in
g
th
e
C
NN
m
o
d
el.
Data
as
th
e
in
p
u
t
f
o
r
th
e
C
NN
m
o
d
el
en
te
r
s
to
h
av
e
lay
er
s
af
ter
war
d
s
th
e
ex
tr
ac
tio
n
o
f
th
e
f
ea
tu
r
e
f
o
llo
wed
b
y
i
ts
clas
s
if
icatio
n
th
r
o
u
g
h
wh
ic
h
lear
n
in
g
h
a
p
p
en
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
la
s
s
if
ica
tio
n
o
f m
o
r
p
h
o
lo
g
ic
a
lly
s
imila
r
I
n
d
ia
n
r
ice
va
r
iety
u
s
in
g
…
(
Ha
r
in
i S
h
a
d
a
ksh
a
r
a
p
p
a
)
3207
to
ca
teg
o
r
ize
d
ata.
C
NN
is
a
d
ee
p
lear
n
in
g
m
o
d
el
wh
ich
h
a
s
f
iv
e
k
ey
lay
er
s
:
o
n
e
o
r
m
o
r
e
co
n
v
o
lu
tio
n
lay
er
,
p
o
o
lin
g
,
ac
tiv
atio
n
,
f
u
lly
c
o
n
n
ec
ted
an
d
th
e
class
if
icatio
n
lay
er
[
1
8
]
[
1
0
]
.
C
o
n
v
o
lu
tio
n
lay
e
r
s
u
s
e
v
ar
io
u
s
f
ilter
s
to
ex
tr
ac
t
f
ea
tu
r
e
s
f
r
o
m
d
if
f
er
e
n
t
r
eg
io
n
s
o
f
an
im
ag
e,
ad
ju
s
tin
g
s
tep
s
an
d
f
ilter
c
o
u
n
ts
to
en
h
an
ce
f
ea
t
u
r
e
e
x
tr
ac
tio
n
[
1
9
]
.
T
h
e
p
o
o
lin
g
lay
er
r
ed
u
ce
s
d
ata
co
m
p
lex
ity
f
r
o
m
th
e
co
n
v
o
lu
ti
o
n
lay
e
r
,
r
eq
u
ir
in
g
p
r
o
p
er
tu
n
i
n
g
f
o
r
o
p
tim
al
class
if
icatio
n
.
An
ac
tiv
atio
n
lay
er
ca
p
tu
r
es
n
o
n
-
lin
ea
r
r
elatio
n
s
h
i
p
s
b
etwe
en
i
n
p
u
t
an
d
o
u
tp
u
t
d
ata,
f
o
llo
wed
b
y
a
f
u
lly
co
n
n
e
cted
lay
er
[
2
0
]
.
I
n
m
u
lti
-
class
clas
s
if
icatio
n
,
th
e
So
f
tm
ax
ac
tiv
atio
n
f
u
n
ctio
n
is
co
m
m
o
n
ly
u
s
ed
f
o
r
f
i
n
al
p
r
e
d
ictio
n
s
[
2
1
]
.
I
n
th
is
s
tu
d
y
,
a
c
u
s
to
m
ized
C
NN
was
d
ev
elo
p
ed
an
d
u
s
ed
f
o
r
tr
ain
in
g
.
T
h
is
n
e
u
r
al
n
etw
o
r
k
m
o
d
el
co
n
s
is
ts
o
f
th
r
ee
co
n
v
o
lu
tio
n
al
lay
er
s
,
ea
c
h
o
n
e
h
as
a
m
ax
-
p
o
o
lin
g
lay
er
f
o
llo
win
g
th
em
.
I
m
ag
es
ar
e
s
ca
led
t
o
224
×
2
2
4
p
ix
els
b
e
f
o
r
e
b
ein
g
p
r
o
ce
s
s
ed
b
y
th
e
f
ir
s
t
lay
er
.
Af
t
er
th
e
t
h
ir
d
lay
er
,
a
Dr
o
p
o
u
t
la
y
er
is
ap
p
lied
,
a
n
d
th
e
o
u
tp
u
t
is
f
latten
ed
a
n
d
p
a
s
s
ed
th
r
o
u
g
h
a
So
f
tm
ax
ac
tiv
atio
n
f
u
n
ctio
n
with
f
o
u
r
n
eu
r
o
n
s
to
class
if
y
f
o
u
r
d
if
f
er
en
t ty
p
es o
f
r
ice.
T
h
e
C
NN
m
o
d
el
u
s
ed
in
t
h
is
s
tu
d
y
i
s
s
h
o
wn
in
Fig
u
r
e
3
.
Fig
u
r
e
3
.
A
c
u
s
to
m
ized
C
NN
ar
ch
itectu
r
e
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
s
ec
tio
n
p
r
esen
ts
r
esear
ch
f
in
d
in
g
s
wh
ile
also
p
r
o
v
id
in
g
a
th
o
r
o
u
g
h
d
is
cu
s
s
io
n
.
T
h
e
a
n
aly
s
is
o
f
p
er
f
o
r
m
an
ce
m
ea
s
u
r
es
b
ased
o
n
th
e
ex
tr
ac
te
d
f
ea
tu
r
es
is
d
i
s
cu
s
s
ed
in
th
is
s
ec
tio
n
[
2
2
]
.
S
VM
,
KNN,
DT
,
an
d
E
M
(
Vo
tin
g
class
if
ier
)
ar
e
in
d
iv
id
u
ally
tr
ain
ed
o
n
ea
ch
o
f
th
ese
f
ea
tu
r
e
s
ets.
A
co
m
p
ar
a
tiv
e
an
aly
s
is
i
s
th
en
p
er
f
o
r
m
ed
to
i
d
en
tify
th
e
o
p
ti
m
al
f
ea
tu
r
e
s
et
an
d
m
o
d
el
f
o
r
class
if
y
in
g
m
o
r
p
h
o
lo
g
ically
s
i
m
ilar
r
ice
v
ar
ieties.
Fo
r
th
e
SVM
with
an
R
B
F
k
er
n
el,
two
k
ey
h
y
p
er
p
ar
a
m
e
ter
s
,
'
C
'
an
d
'
g
am
m
a,
'
ar
e
cr
u
cial
in
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
.
T
h
e
m
o
d
el
is
test
ed
with
v
ar
io
u
s
g
am
m
a
v
alu
es to
d
eter
m
in
e
th
e
m
o
s
t su
itab
le
o
n
e.
Fig
u
r
e
4
p
r
esen
ts
th
e
r
esu
lts
o
b
tain
ed
f
o
r
ea
ch
m
o
d
el
ac
r
o
s
s
th
e
d
if
f
e
r
en
t
f
e
atu
r
e
s
ets
an
d
g
am
m
a
v
alu
es.
T
h
e
o
u
tc
o
m
es
d
er
iv
e
d
f
r
o
m
th
is
in
v
esti
g
atio
n
ar
e
o
r
g
an
ized
an
d
p
r
esen
ted
in
T
ab
le
4
wh
ich
in
clu
d
es
th
e
r
esu
lts
o
f
KNN,
DT
an
d
E
M
alo
n
g
with
SVM.
Acc
o
r
d
in
g
to
th
e
f
i
n
d
in
g
s
p
r
esen
te
d
in
T
a
b
le
4
,
n
o
tab
le
test
in
g
ac
cu
r
ac
y
is
attain
ed
with
co
lo
r
,
wav
elet,
an
d
tex
tu
r
al
f
ea
tu
r
es.
T
h
e
b
est p
er
f
o
r
m
a
n
ce
,
r
ea
ch
in
g
7
2
.
4
8
%,
is
o
b
s
er
v
ed
wh
en
u
tili
zin
g
Po
ly
n
o
m
ial
k
er
n
el
f
u
n
ctio
n
o
f
SVM
with
all
5
6
f
ea
tu
r
es.
Fig
u
r
e
4
.
Gr
a
p
h
s
h
o
win
g
th
e
a
cc
u
r
ac
y
o
f
SVM
R
B
F k
er
n
el
f
u
n
ctio
n
f
o
r
d
if
f
er
en
t
g
am
m
a
v
alu
e
0
10
20
30
40
50
60
70
80
0.05
0.2
0.5
0.8
1
Ac
curacy
G
amm
a
v
alu
e
G
L
CM
RG
B
HS
V
A
l
l
fe
atu
r
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
0
2
-
3
2
1
1
3208
T
ab
le
4
.
T
h
e
test
in
g
ac
cu
r
ac
ie
s
ac
h
iev
ed
b
y
SVM
(
with
lin
ea
r
,
p
o
ly
n
o
m
ial
an
d
R
B
F f
u
n
ctio
n
s
)
,
KNN,
an
d
DT
m
o
d
els o
n
v
ar
io
u
s
f
ea
t
u
r
e
s
ets ar
e
as f
o
llo
ws
F
e
a
t
u
r
e
S
e
t
Li
n
e
a
r
P
o
l
y
n
o
m
i
a
l
RBF
K
N
N
DT
EM
G
LC
M
5
6
.
3
3
%
5
8
.
8
5
%
5
8
.
9
%
(
g
a
mm
a
=
0
.
8
)
5
6
.
8
1
%
5
7
.
6
5
%
5
9
.
6
8
%
R
G
B
(
C
o
l
o
r
a
n
d
W
a
v
e
l
e
t
)
5
4
.
0
6
%
7
2
.
2
4
%
6
8
.
6
6
%
(
g
a
mm
a
=
0
.
8
)
4
2
.
9
4
%
4
8
.
3
2
%
5
5
.
2
6
%
H
S
V
(
C
o
l
o
r
a
n
d
W
a
v
e
l
e
t
)
5
6
.
9
3
%
6
9
.
1
3
%
6
7
.
2
2
%
(
g
a
mm
a
=
0
.
8
)
5
2
.
1
5
%
5
1
.
4
3
%
5
8
.
8
5
%
A
LL
6
8
.
1
8
%
7
2
.
4
8
%
6
8
.
9
9
%
5
8
.
4
9
%
6
5
.
4
3
%
6
5
.
7
8
%
3
.
1
.
T
ra
ini
ng
CNN
m
o
del
Ma
ch
in
e
lear
n
i
n
g
m
o
d
els
tr
ai
n
ed
o
v
er
th
e
e
x
tr
ac
ted
f
ea
tu
r
es
p
r
o
v
i
d
e
less
ac
cu
r
ac
y
b
ec
a
u
s
e
o
f
th
e
in
co
m
p
lete
f
ea
tu
r
e
s
et.
T
h
er
ef
o
r
e,
in
th
is
r
esear
ch
C
NN
m
o
d
el
is
u
tili
ze
d
wh
ich
ex
tr
ac
ts
h
ig
h
q
u
a
n
tity
f
ea
tu
r
e
s
et
f
r
o
m
t
h
e
s
et
o
f
im
a
g
es.
T
h
e
2
8
0
im
ag
es
ass
im
ilated
ar
e
s
p
lit
in
to
tr
ain
an
d
test
s
et
in
t
o
8
0
:2
0
r
atio
s
.
T
h
e
im
ag
es
ar
e
r
esized
to
th
e
s
ize
2
2
4
×
2
2
4
p
r
io
r
to
g
iv
in
g
it
a
s
in
p
u
t
to
th
e
C
NN
m
o
d
el.
A
C
NN
m
o
d
el
with
th
r
ee
co
n
v
o
l
u
tio
n
la
y
er
s
is
d
ev
elo
p
e
d
f
o
r
class
if
icatio
n
o
f
s
im
ilar
lo
o
k
in
g
r
ice
v
a
r
ieties.
T
h
e
in
itial
ex
p
er
im
en
ts
i
n
v
o
lv
e
d
u
s
in
g
3
2
f
ilter
s
o
f
s
ize
3
×
3
in
all
th
r
e
e
lay
er
s
wh
ic
h
a
r
e
later
tu
n
e
d
an
d
th
e
r
esu
lts
ar
e
r
ec
o
r
d
e
d
f
o
r
v
ar
y
in
g
e
p
o
ch
w
h
ich
is
tab
u
lated
in
T
a
b
le
5
.
T
ab
le
5
.
Per
f
o
r
m
an
ce
o
f
th
e
C
NN
m
o
d
el
th
e
tu
n
ed
n
u
m
b
er
o
f
f
ilter
s
in
th
r
ee
lay
e
r
s
ag
ain
s
t v
ar
y
in
g
ep
o
c
h
s
F
i
l
t
e
r
si
z
e
A
c
c
u
r
a
c
y
Ep
o
c
h
s
1
0
0
2
0
0
3
0
0
4
0
0
5
0
0
A
l
l
t
h
r
e
e
l
a
y
e
r
s w
i
t
h
3
2
f
i
l
t
e
r
s
,
e
a
c
h
(
3
x
3
)
.
Tr
a
i
n
i
n
g
4
5
%
7
2
.
9
%
8
9
%
9
1
.
9
5
%
9
4
.
2
5
%
V
a
l
i
d
a
t
i
o
n
5
0
%
6
7
.
5
%
8
0
%
8
2
.
5
%
8
7
.
5
%
3
2
f
i
l
t
e
r
s
-
La
y
e
r
o
n
e
a
n
d
t
w
o
6
4
f
i
l
t
e
r
s
e
a
c
h
(
3
×
3)
-
l
a
y
e
r
t
h
r
e
e
Tr
a
i
n
i
n
g
5
0
.
7
%
7
3
.
0
8
%
8
1
%
8
0
.
7
%
9
0
.
7
%
V
a
l
i
d
a
t
i
o
n
5
0
%
7
0
%
7
3
%
7
3
%
7
3
%
La
y
e
r
o
n
e
w
i
t
h
3
2
f
i
l
t
e
r
s
a
n
d
t
w
o
,
t
h
r
e
e
w
i
t
h
6
4
f
i
l
t
e
r
s
e
a
c
h
(
3
×
3
)
.
Tr
a
i
n
i
n
g
6
9
.
5
%
8
5
.
6
%
8
9
.
0
8
%
9
4
.
8
%
9
7
.
1
3
%
V
a
l
i
d
a
t
i
o
n
5
7
.
5
%
8
0
%
8
0
%
8
0
%
8
7
.
5
%
T
h
e
ac
cu
r
ac
y
d
u
r
i
n
g
tr
ain
in
g
an
d
v
alid
atio
n
p
h
ase
is
d
ep
ict
ed
in
Fig
u
r
e
5
al
o
n
g
with
th
e
lo
s
s
cu
r
v
e,
f
o
r
th
e
C
NN
m
o
d
el
h
av
in
g
3
2
f
ilter
s
in
lay
er
1
an
d
6
4
f
ilter
s
(
ea
ch
o
f
s
ize
3
×
3
)
in
lay
e
r
2
an
d
lay
er
3
.
I
t
ca
n
b
e
s
ee
n
f
r
o
m
t
h
e
g
r
a
p
h
t
h
at
l
o
s
s
d
ec
r
ea
s
es
with
th
e
in
cr
em
en
t
in
th
e
n
u
m
b
er
o
f
e
p
o
ch
s
a
n
d
,
s
im
u
ltan
eo
u
s
ly
,
th
e
ac
cu
r
ac
y
also
in
c
r
ea
s
es
with
th
e
in
cr
ea
s
e
in
ep
o
ch
s
.
T
a
b
le
6
d
ep
icts
th
e
to
tal
ac
cu
r
a
cy
,
r
ec
all,
an
d
F1
-
s
co
r
e
in
d
is
tin
g
u
is
h
in
g
m
o
r
p
h
o
lo
g
ically
an
alo
g
o
u
s
r
ice
v
a
r
ieties wh
en
a
C
NN
w
ith
3
2
f
ilter
s
in
lay
er
1
an
d
6
4
f
ilter
s
(
3
×3
)
in
la
y
er
2
an
d
la
y
er
3
is
ap
p
lied
.
Fig
u
r
e
5
.
T
h
e
T
r
ain
i
n
g
an
d
v
al
id
atio
n
lo
s
s
an
d
ac
cu
r
ac
y
cu
r
v
es o
f
th
e
C
NN
m
o
d
el
T
h
e
r
esu
lt a
ch
iev
ed
i
n
th
is
wo
r
k
is
co
m
p
ar
e
d
with
o
th
er
s
ig
n
if
ican
t w
o
r
k
in
th
e
s
am
e
f
ield
.
T
h
e
wo
r
k
ca
r
r
ied
o
u
t
b
y
Ko
k
l
u
et
a
l.
[
7
]
h
as
co
n
s
id
er
ed
f
iv
e
d
is
tin
ct
v
ar
iety
o
f
g
r
ain
s
g
r
o
w
n
in
T
u
r
k
ey
.
B
y
ap
p
ly
in
g
NN,
DNN
an
d
C
NN
th
ey
h
av
e
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
9
9
.
8
7
%,9
9
.
9
5
%
an
d
1
0
0
%
r
esp
e
ctiv
ely
.
Asi
f
et
a
l.
A
c
c
ur
ac
y
E
po
c
hs
E
po
c
hs
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
la
s
s
if
ica
tio
n
o
f m
o
r
p
h
o
lo
g
ic
a
lly
s
imila
r
I
n
d
ia
n
r
ice
va
r
iety
u
s
in
g
…
(
Ha
r
in
i S
h
a
d
a
ksh
a
r
a
p
p
a
)
3209
[
9
]
h
av
e
r
esear
ch
e
d
o
n
class
i
f
y
in
g
5
d
is
tin
ct
ty
p
es
o
f
r
ice
g
r
o
wn
i
n
Pak
is
tan
a
n
d
h
av
e
ap
p
lied
Prin
cip
a
l
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
an
d
C
an
n
y
ed
g
e
d
etec
tio
n
.
T
h
ey
h
av
e
g
o
t
an
ac
cu
r
ac
y
o
f
8
9
.
5
%.
Sin
g
h
et
a
l.
[
8
]
,
L
in
et
a
l.
[
1
0
]
an
d
A
h
m
ed
et
a
l.
[
2
3
]
h
a
v
e
wo
r
k
ed
o
n
d
is
tin
ct
v
ar
iety
o
f
r
ice
g
r
ain
s
f
r
o
m
th
eir
lo
ca
l
r
e
g
io
n
.
T
h
ey
h
av
e
ap
p
lied
ty
p
es
o
f
n
eu
r
al
n
etwo
r
k
m
o
d
els
an
d
h
av
e
o
b
tain
ed
9
9
.
4
%,
9
6
%
an
d
8
8
.
0
7
%
o
f
ac
cu
r
ac
y
.
L
iu
et
a
l.
[
2
4
]
a
n
d
Pra
n
s
h
u
S
ax
en
a
[
2
5
]
h
av
e
e
x
p
er
im
en
te
d
o
n
class
if
icatio
n
o
f
f
iv
e
v
a
r
ieties
o
f
d
is
tin
ct
r
ice
ty
p
es.
T
h
ey
h
a
v
e
ac
h
iev
e
d
o
v
er
9
9
.
8
5
%
o
f
ac
c
u
r
ac
y
b
y
a
p
p
ly
in
g
SVM
an
d
9
3
.
0
2
%
b
y
ap
p
ly
in
g
R
an
d
o
m
Fo
r
est C
las
s
if
ier
.
T
ab
le
6
.
C
NN
m
o
d
el'
s
p
r
ec
is
io
n
,
r
ec
all,
a
n
d
F1
-
s
co
r
e
m
ea
s
u
r
es a
r
e
p
r
o
v
id
ed
with
3
2
f
ilter
s
at
L
ay
er
1
an
d
6
4
f
ilter
s
at
b
o
th
L
ay
er
2
an
d
L
ay
er
3
at
ep
o
ch
=5
0
0
Ty
p
e
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
B
.
R
.
T
D
a
i
w
a
n
(
R
a
w
h
)
8
6
%
6
0
%
7
1
%
G
r
i
n
e
w
o
r
l
d
(
R
a
w
l
)
1
0
0
%
1
0
0
%
1
0
0
%
R
o
y
a
l
S
o
n
a
(
S
t
e
a
m
h
)
6
9
%
9
0
%
7
8
%
D
a
i
w
a
n
S
o
n
a
(
S
t
e
a
m
l
)
1
0
0
%
1
0
0
%
1
0
0
%
A
v
e
r
a
g
e
8
9
%
8
8
%
8
7
%
4.
CO
NCLU
SI
O
N
T
h
is
n
o
v
el
r
esear
ch
w
o
r
k
to
class
if
y
th
e
m
o
r
p
h
o
lo
g
icall
y
s
im
ilar
I
n
d
ian
r
ice
v
ar
iety
(
m
ed
iu
m
s
len
d
er
)
is
q
u
ite
a
ch
allen
g
in
g
task
.
T
h
e
o
b
jectiv
e
o
f
t
h
is
s
tu
d
y
is
to
ass
is
t
co
n
s
u
m
er
s
an
d
t
h
e
f
o
o
d
in
d
u
s
tr
y
in
ac
cu
r
ately
id
e
n
tify
in
g
th
e
a
p
p
r
o
p
r
iate
ty
p
e
o
f
r
ice.
Sam
p
les
o
f
f
o
u
r
m
ed
iu
m
-
s
ized
r
ice
t
y
p
es,
s
im
ilar
to
So
n
a
-
M
aso
o
r
i
r
ice,
wer
e
p
u
r
c
h
ased
f
r
o
m
th
e
co
m
m
er
cial
m
a
r
k
et
an
d
an
al
y
ze
d
at
Sh
r
i
B
h
ag
y
al
ak
s
h
m
i
Ag
r
o
Fo
o
d
Pv
t.
L
td
.
T
h
e
r
esu
lts
wer
e
co
m
p
ar
ed
with
th
e
ea
r
lier
wo
r
k
ca
r
r
ied
o
u
t b
y
v
ar
ies r
esear
ch
e
r
s
.
B
y
lo
o
k
in
g
at
ea
r
lier
w
o
r
k
o
n
r
ice
q
u
ality
a
n
aly
s
is
,
it
is
e
v
id
en
t
th
at
n
o
t
m
u
ch
w
o
r
k
is
d
o
n
e
o
n
a
m
o
r
p
h
o
lo
g
ically
s
im
ilar
v
a
r
iety
o
f
r
ice.
T
h
is
n
ew
wo
r
k
h
as
attain
ed
h
ig
h
est
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
7
.
1
3
%
an
d
test
in
g
ac
cu
r
ac
y
o
f
8
7
.
5
%
o
n
m
o
r
p
h
o
lo
g
ically
s
im
ilar
m
ed
i
u
m
s
len
d
er
I
n
d
ian
r
ice
class
if
i
ca
tio
n
.
T
h
e
s
tu
d
y
'
s
ap
p
r
o
ac
h
in
v
o
lv
ed
im
ag
e
ac
q
u
is
itio
n
,
p
r
e
-
p
r
o
ce
s
s
in
g
,
an
d
f
ea
tu
r
e
ex
tr
ac
tio
n
,
co
n
tr
ib
u
tin
g
to
th
e
o
u
tco
m
es
g
ath
er
ed
u
s
in
g
v
ar
io
u
s
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els.
Var
io
u
s
f
ea
tu
r
es,
in
clu
d
in
g
tex
t
u
r
al,
c
o
lo
r
,
an
d
wav
elet
d
ec
o
m
p
o
s
itio
n
in
b
o
th
R
GB
an
d
HSV
co
lo
r
s
p
ac
es,
wer
e
u
tili
ze
d
as
in
p
u
t
f
o
r
SVM,
KNN,
DT
an
d
E
M
(
v
o
tin
g
class
if
ier
)
alg
o
r
ith
m
s
.
Fu
r
th
er
m
o
r
e
,
th
e
im
ag
es
ac
q
u
i
r
ed
ar
e
r
escaled
t
o
a
p
ix
el
s
ize
o
f
2
2
4
x
2
2
4
an
d
is
g
iv
en
as
in
p
u
t
i
n
to
th
e
C
NN
m
o
d
el.
W
ith
th
e
en
tire
5
6
-
f
ea
t
u
r
e
s
et,
ac
cu
r
ac
y
o
f
7
2
.
4
8
%
is
o
b
tain
ed
.
T
h
e
C
NN
m
o
d
el
with
th
e
tu
n
ed
p
ar
am
et
er
s
h
as
ac
h
iev
ed
th
e
b
est
tr
ain
in
g
ac
cu
r
ac
y
o
f
9
7
%
an
d
v
ali
d
atio
n
ac
cu
r
ac
y
o
f
8
8
%.
T
h
e
o
u
tc
o
m
e
in
d
icate
s
th
at
tex
tu
r
al,
co
lo
r
,
a
n
d
wa
v
elet
f
ea
tu
r
es
ar
e
ess
en
tial
f
o
r
ac
h
ie
v
in
g
h
ig
h
ac
cu
r
ac
y
.
W
h
ile
SVM
p
er
f
o
r
m
s
b
est
am
o
n
g
ML
m
o
d
els,
C
NN
o
u
tp
er
f
o
r
m
s
t
h
em
b
y
a
u
to
m
atica
lly
ex
tr
ac
tin
g
m
o
r
e
f
ea
tu
r
es f
o
r
b
etter
class
if
icatio
n
.
ACK
NO
WL
E
DG
M
E
N
T
S
W
e
g
r
atef
u
lly
ac
k
n
o
wled
g
e
S
r
i
B
h
ag
y
alak
s
h
m
i
Ag
r
o
Fo
o
d
s
Pv
t.
L
td
.
,
B
an
g
alo
r
e,
I
n
d
ia,
f
o
r
th
e
u
s
e
o
f
lab
o
r
ato
r
y
e
q
u
ip
m
en
t
to
ca
r
r
y
o
u
t
th
e
wo
r
k
.
W
e
also
ap
p
r
ec
iate
B
NM
I
n
s
titu
te
o
f
T
e
ch
n
o
lo
g
y
f
o
r
g
i
v
in
g
p
er
m
is
s
io
n
to
ac
ce
s
s
th
e
VG
ST
-
f
u
n
d
e
d
lab
o
r
ato
r
y
f
ac
ilit
ies,
th
r
o
u
g
h
wh
ic
h
we
wer
e
a
b
le
to
p
e
r
f
o
r
m
o
u
r
ex
p
er
im
en
ts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
n
o
f
u
n
d
s
,
g
r
an
ts
,
o
r
o
th
e
r
s
u
p
p
o
r
t
wer
e
r
ec
eiv
ed
d
u
r
in
g
th
e
p
r
e
p
ar
atio
n
o
f
th
is
m
an
u
s
cr
ip
t.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Har
in
i Sh
ad
ak
s
h
ar
ap
p
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sar
ith
a
C
h
ak
r
asali
✓
✓
✓
✓
✓
✓
✓
✓
K
r
i
s
h
n
a
m
u
r
t
h
y
G
o
r
a
p
p
a
N
i
n
g
a
p
p
a
✓
✓
✓
✓
✓
✓
✓
✓
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
3
,
J
u
n
e
20
25
:
3
2
0
2
-
3
2
1
1
3210
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
e
au
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
av
e
n
o
co
n
f
lict
o
f
in
ter
est
(
f
in
an
cial,
p
e
r
s
o
n
al,
o
r
p
r
o
f
ess
io
n
al)
in
co
n
n
ec
tio
n
with
m
a
n
u
s
cr
ip
ts
.
No
n
-
f
in
an
cial
co
m
p
etin
g
i
n
ter
ests
in
clu
d
e
a
d
ec
lar
atio
n
o
f
p
o
liti
ca
l,
p
er
s
o
n
al,
r
elig
io
u
s
,
id
e
o
lo
g
ical,
ac
a
d
em
ic,
an
d
in
tellectu
al
co
m
p
etin
g
in
ter
ests
.
T
h
e
a
u
th
o
r
s
d
ec
lar
e
th
at
th
e
y
h
a
v
e
n
o
k
n
o
wn
c
o
m
p
etin
g
f
in
an
cial
in
ter
ests
o
r
p
er
s
o
n
al
r
elatio
n
s
h
i
p
s
th
at
co
u
ld
h
a
v
e
ap
p
ea
r
ed
t
o
in
f
lu
en
ce
th
e
wo
r
k
r
ep
o
r
ted
in
t
h
is
p
ap
er
.
I
f
th
er
e
ar
e
n
o
co
n
f
licts
o
f
in
ter
est,
p
lease
in
clu
d
e
th
e
f
o
llo
win
g
au
th
o
r
'
s
s
tatem
en
t:
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
aila
b
le
o
n
r
eq
u
est
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
,
HS.
T
h
e
d
ata,
wh
ich
c
o
n
tain
in
f
o
r
m
atio
n
th
at
c
o
u
ld
co
m
p
r
o
m
is
e
th
e
p
r
i
v
ac
y
o
f
r
e
s
ea
r
ch
p
ar
ticip
an
ts
ar
e
n
o
t p
u
b
licly
av
aila
b
le
d
u
e
to
ce
r
tain
r
estrictio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
“
I
C
A
R
-
I
n
d
i
a
n
i
n
st
i
t
u
t
e
o
f
r
i
c
e
r
e
s
e
a
r
c
h
,
”
I
C
A
R
-
I
n
d
i
a
n
I
n
st
i
t
u
t
e
o
f
R
i
c
e
Re
s
e
a
r
c
h
.
h
t
t
p
s
:
/
/
w
w
w
.
i
c
a
r
-
i
i
r
r
.
o
r
g
/
i
n
d
e
x
.
p
h
p
/
e
n
/
(
a
c
c
e
s
se
d
M
a
r
.
1
4
,
2
0
2
3
)
.
[
2
]
“
I
n
d
i
a
a
n
d
I
R
R
I
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Ri
c
e
Re
s
e
a
rc
h
I
n
st
i
t
u
t
e
.
h
t
t
p
s
:
/
/
w
w
w
.
i
r
r
i
.
o
r
g
/
w
h
e
r
e
-
we
-
w
o
r
k
/
c
o
u
n
t
r
i
e
s/
i
n
d
i
a
(
a
c
c
e
ss
e
d
M
a
r
.
1
4
,
2
0
2
5
)
.
[
3
]
S
.
E.
U
mb
a
u
g
h
,
C
o
m
p
u
t
e
r v
i
si
o
n
a
n
d
i
m
a
g
e
p
r
o
c
e
ssi
n
g
:
A
p
r
a
c
t
i
c
a
l
a
p
p
r
o
a
c
h
u
s
i
n
g
C
VI
P
t
o
o
l
s
.
P
r
e
n
t
i
c
e
H
a
l
l
,
1
9
9
7
.
[
4
]
G
.
Zh
a
n
g
,
D
.
S
.
J
a
y
a
s,
a
n
d
N
.
D
.
G
.
W
h
i
t
e
,
“
S
e
p
a
r
a
t
i
o
n
o
f
t
o
u
c
h
i
n
g
g
r
a
i
n
k
e
r
n
e
l
s
i
n
a
n
i
m
a
g
e
b
y
e
l
l
i
p
se
f
i
t
t
i
n
g
a
l
g
o
r
i
t
h
m
,
”
Bi
o
s
y
st
e
m
s E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
2
,
n
o
.
2
,
p
p
.
1
3
5
–
1
4
2
,
O
c
t
.
2
0
0
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
s
t
e
ms
e
n
g
.
2
0
0
5
.
0
6
.
0
1
0
.
[
5
]
S
.
H
a
r
i
n
i
,
S
.
C
h
a
k
r
a
sa
l
i
,
a
n
d
G
.
N
.
K
r
i
sh
n
a
m
u
r
t
h
y
,
“
A
s
u
r
v
e
y
o
n
f
o
o
d
g
r
a
i
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
R
e
se
a
rc
h
i
n
S
c
i
e
n
c
e
,
E
n
g
i
n
e
e
ri
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
6
,
p
p
.
6
6
2
7
–
6
6
3
3
,
2
0
1
8
.
[
6
]
S
.
H
a
r
i
n
i
,
S
.
C
h
a
k
r
a
sa
l
i
,
a
n
d
G
.
N
.
K
r
i
s
h
n
a
m
u
r
t
h
y
,
“
A
n
a
l
y
s
i
s
o
f
I
n
d
i
a
n
r
i
c
e
q
u
a
l
i
t
y
u
s
i
n
g
m
u
l
t
i
-
c
l
a
ss
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
,
”
2
0
2
3
,
p
p
.
7
9
1
–
8
0
2
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
19
-
7
3
4
6
-
8
_
6
8
.
[
7
]
M
.
K
o
k
l
u
,
I
.
C
i
n
a
r
,
a
n
d
Y
.
S
.
T
a
sp
i
n
a
r
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
v
a
r
i
e
t
i
e
s
w
i
t
h
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s,
”
C
o
m
p
u
t
e
r
s
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
Ag
r
i
c
u
l
t
u
re
,
v
o
l
.
1
8
7
,
A
u
g
.
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
1
.
1
0
6
2
8
5
.
[
8
]
K
.
R
.
S
i
n
g
h
a
n
d
S
.
C
h
a
u
d
h
u
r
y
,
“
Ef
f
i
c
i
e
n
t
t
e
c
h
n
i
q
u
e
f
o
r
r
i
c
e
g
r
a
i
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
b
a
c
k
-
p
r
o
p
a
g
a
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
a
n
d
w
a
v
e
l
e
t
d
e
c
o
m
p
o
si
t
i
o
n
,
”
I
ET C
o
m
p
u
t
e
r V
i
si
o
n
,
v
o
l
.
1
0
,
n
o
.
8
,
p
p
.
7
8
0
–
7
8
7
,
Ju
l
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
4
9
/
i
e
t
-
c
v
i
.
2
0
1
5
.
0
4
8
6
.
[
9
]
M
.
J.
A
s
i
f
,
T.
S
h
a
h
b
a
z
,
S
.
T
a
h
i
r
H
u
ssa
i
n
R
i
z
v
i
,
a
n
d
S
.
I
q
b
a
l
,
“
R
i
c
e
g
r
a
i
n
i
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
q
u
a
l
i
t
y
a
n
a
l
y
si
s
u
s
i
n
g
i
ma
g
e
p
r
o
c
e
ss
i
n
g
b
a
s
e
d
o
n
p
r
i
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
si
s,
”
i
n
2
0
1
8
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
R
e
c
e
n
t
A
d
v
a
n
c
e
s
i
n
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
(
RAE
E)
,
O
c
t
.
2
0
1
8
,
p
p
.
1
–
6
.
d
o
i
:
1
0
.
1
1
0
9
/
R
A
EE
.
2
0
1
8
.
8
7
0
6
8
9
1
.
[
1
0
]
P
.
Li
n
,
X
.
Li
,
Y
.
C
h
e
n
,
a
n
d
Y
.
H
e
,
“
A
d
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
a
r
c
h
i
t
e
c
t
u
r
e
f
o
r
b
o
o
st
i
n
g
i
ma
g
e
d
i
s
c
r
i
m
i
n
a
t
i
o
n
a
c
c
u
r
a
c
y
o
f
r
i
c
e
s
p
e
c
i
e
s,”
F
o
o
d
a
n
d
Bi
o
p
ro
c
e
ss
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
1
,
n
o
.
4
,
p
p
.
7
6
5
–
7
7
3
,
A
p
r
.
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
9
4
7
-
0
1
7
-
2
0
5
0
-
9.
[
1
1
]
M
.
K
o
k
l
u
a
n
d
I
.
C
i
n
a
r
,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
r
i
c
e
v
a
r
i
e
t
i
e
s
u
si
n
g
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
me
t
h
o
d
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
S
y
s
t
e
m
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s i
n
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
7
,
n
o
.
3
,
p
p
.
1
8
8
–
1
9
4
,
S
e
p
.
2
0
1
9
,
d
o
i
:
1
0
.
1
8
2
0
1
/
i
j
i
s
a
e
.
2
0
1
9
3
5
5
3
8
1
.
[
1
2
]
P
.
K
.
M
a
l
l
i
c
k
a
n
d
B
.
P
.
M
o
h
a
n
t
y
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
c
l
a
ssi
f
i
c
a
t
i
o
n
o
f
s
i
mi
l
a
r
l
o
o
k
i
n
g
f
o
o
d
g
r
a
i
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
O
f
Re
c
e
n
t
A
d
v
a
n
c
e
s i
n
En
g
i
n
e
e
ri
n
g
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
0
8
,
n
o
.
0
4
,
p
p
.
2
1
–
2
5
,
A
p
r
.
2
0
2
0
,
d
o
i
:
1
0
.
4
6
5
6
4
/
i
j
r
a
e
t
.
2
0
2
0
.
v
0
8
i
0
4
.
0
0
6
.
[
1
3
]
H
.
S
.
G
u
j
j
a
r
a
n
d
M
.
S
i
d
d
a
p
p
a
,
“
A
me
t
h
o
d
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
b
a
sm
a
t
i
r
i
c
e
g
r
a
i
n
o
f
i
n
d
i
a
a
n
d
i
t
s
q
u
a
l
i
t
y
u
s
i
n
g
p
a
t
t
e
r
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
r
i
n
g
R
e
se
a
rc
h
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s (I
J
E
RA)
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
2
6
8
–
2
7
3
,
2
0
1
3
.
[
1
4
]
V
.
S
.
K
o
l
k
u
r
e
a
n
d
B
.
N
.
S
h
a
i
k
h
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
a
n
d
q
u
a
l
i
t
y
t
e
st
i
n
g
o
f
r
i
c
e
g
r
a
i
n
s
u
s
i
n
g
i
ma
g
e
p
r
o
c
e
ss
i
n
g
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
R
e
c
e
n
t
T
re
n
d
s i
n
E
n
g
i
n
e
e
r
i
n
g
& R
e
se
a
rc
h
(
I
J
RTE
R)
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
1
3
0
–
1
3
5
,
2
0
1
7
.
[
1
5
]
W
.
S
r
i
m
u
l
y
a
n
i
a
n
d
A
.
M
u
s
d
h
o
l
i
f
a
h
,
“
I
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
r
i
c
e
v
a
r
i
e
t
y
u
si
n
g
g
e
o
m
e
t
r
i
c
f
e
a
t
u
r
e
s
a
n
d
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
J
C
C
S
(
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
i
n
g
a
n
d
C
y
b
e
r
n
e
t
i
c
s
S
y
st
e
m
s)
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
3
0
1
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
c
c
s
.
4
8
2
0
3
.
[
1
6
]
N
.
I
q
b
a
l
,
R
.
M
u
mt
a
z
,
U
.
S
h
a
f
i
,
a
n
d
S
.
M
.
H
.
Z
a
i
d
i
,
“
G
r
a
y
l
e
v
e
l
c
o
-
o
c
c
u
r
r
e
n
c
e
m
a
t
r
i
x
(
G
LC
M
)
t
e
x
t
u
r
e
b
a
se
d
c
r
o
p
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
si
n
g
l
o
w
a
l
t
i
t
u
d
e
r
e
m
o
t
e
se
n
si
n
g
p
l
a
t
f
o
r
ms,”
Pe
e
rJ
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
7
,
M
a
y
2
0
2
1
,
d
o
i
:
1
0
.
7
7
1
7
/
p
e
e
r
j
-
c
s.
5
3
6
.
[
1
7
]
E.
T.
C
h
a
mp
a
g
n
e
,
W
.
E.
M
a
r
sh
a
l
l
,
a
n
d
W
.
R
.
G
o
y
n
e
s,
“
Ef
f
e
c
t
o
f
d
e
g
r
e
e
o
f
mi
l
l
i
n
g
a
n
d
l
i
p
i
d
r
e
mo
v
a
l
o
n
st
a
r
c
h
g
e
l
a
t
i
n
i
z
a
t
i
o
n
i
n
t
h
e
b
r
o
w
n
r
i
c
e
k
e
r
n
e
l
,
”
C
e
re
a
l
C
h
e
m
i
st
ry
,
v
o
l
.
6
7
,
n
o
.
6
,
p
p
.
5
7
0
–
5
7
4
,
1
9
9
0
.
[
1
8
]
N
.
H
a
n
d
a
,
Y
.
K
a
u
s
h
i
k
,
N
.
S
h
a
r
ma
,
M
.
D
i
x
i
t
,
a
n
d
M
.
G
a
r
g
,
“
I
mag
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
,
”
2
0
2
1
,
p
p
.
5
1
0
–
5
1
7
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
981
-
16
-
3
6
6
0
-
8
_
4
8
.
[
1
9
]
Y
.
G
u
o
,
Y
.
Li
u
,
A
.
O
e
r
l
e
ma
n
s,
S
.
La
o
,
S
.
W
u
,
a
n
d
M
.
S
.
Le
w
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
v
i
su
a
l
u
n
d
e
r
s
t
a
n
d
i
n
g
:
A
r
e
v
i
e
w
,
”
N
e
u
ro
c
o
m
p
u
t
i
n
g
,
v
o
l
.
1
8
7
,
p
p
.
2
7
–
4
8
,
A
p
r
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
n
e
u
c
o
m.
2
0
1
5
.
0
9
.
1
1
6
.
[
2
0
]
D
.
S
c
h
e
r
e
r
,
A
.
M
ü
l
l
e
r
,
a
n
d
S
.
B
e
h
n
k
e
,
“
Ev
a
l
u
a
t
i
o
n
o
f
p
o
o
l
i
n
g
o
p
e
r
a
t
i
o
n
s
i
n
c
o
n
v
o
l
u
t
i
o
n
a
l
a
r
c
h
i
t
e
c
t
u
r
e
s
f
o
r
o
b
j
e
c
t
r
e
c
o
g
n
i
t
i
o
n
,
”
i
n
Art
i
f
i
c
i
a
l
N
e
u
r
a
l
N
e
t
w
o
r
k
s
–
I
C
AN
N
2
0
1
0
(
I
C
A
N
N
2
0
1
0
)
,
2
0
1
0
,
p
p
.
9
2
–
1
0
1
.
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
1
5
8
2
5
-
4
_
1
0
.
[
2
1
]
T.
N
.
S
a
i
n
a
t
h
,
A
.
M
o
h
a
me
d
,
B
.
K
i
n
g
sb
u
r
y
,
a
n
d
B
.
R
a
ma
b
h
a
d
r
a
n
,
“
D
e
e
p
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
L
V
C
S
R
,
”
i
n
2
0
1
3
I
EEE
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
Ac
o
u
st
i
c
s,
S
p
e
e
c
h
a
n
d
S
i
g
n
a
l
Pro
c
e
ssi
n
g
,
M
a
y
2
0
1
3
,
p
p
.
8
6
1
4
–
8
6
1
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
S
S
P
.
2
0
1
3
.
6
6
3
9
3
4
7
.
[
2
2
]
R
.
C
h
o
u
d
h
a
r
y
,
J.
P
a
l
i
w
a
l
,
a
n
d
D
.
S
.
Jay
a
s,
“
C
l
a
ssi
f
i
c
a
t
i
o
n
o
f
c
e
r
e
a
l
g
r
a
i
n
s
u
si
n
g
w
a
v
e
l
e
t
,
mo
r
p
h
o
l
o
g
i
c
a
l
,
c
o
l
o
u
r
,
a
n
d
t
e
x
t
u
r
a
l
f
e
a
t
u
r
e
s
o
f
n
o
n
-
t
o
u
c
h
i
n
g
k
e
r
n
e
l
i
mag
e
s,”
B
i
o
sys
t
e
m
s
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
9
9
,
n
o
.
3
,
p
p
.
3
3
0
–
3
3
7
,
M
a
r
.
2
0
0
8
,
d
o
i
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
C
la
s
s
if
ica
tio
n
o
f m
o
r
p
h
o
lo
g
ic
a
lly
s
imila
r
I
n
d
ia
n
r
ice
va
r
iety
u
s
in
g
…
(
Ha
r
in
i S
h
a
d
a
ksh
a
r
a
p
p
a
)
3211
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
s
t
e
ms
e
n
g
.
2
0
0
7
.
1
1
.
0
1
3
.
[
2
3
]
T.
A
h
m
e
d
,
C
.
R
.
R
a
h
ma
n
,
a
n
d
M
.
F
.
M
.
A
b
i
d
,
“
R
i
c
e
g
r
a
i
n
d
i
se
a
se
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
d
u
a
l
p
h
a
se
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
b
a
s
e
d
sy
s
t
e
m
a
i
me
d
a
t
sm
a
l
l
d
a
t
a
s
e
t
.
,
”
a
r
Xi
v
:
2
0
0
4
.
0
9
8
7
0
,
J
u
l
.
2
0
2
1
,
d
o
i
:
1
0
.
3
1
2
2
0
/
a
g
r
i
R
x
i
v
.
2
0
2
1
.
0
0
0
6
2
.
[
2
4
]
T.
L
i
u
e
t
a
l
.
,
“
A
sh
a
d
o
w
-
b
a
se
d
m
e
t
h
o
d
t
o
c
a
l
c
u
l
a
t
e
t
h
e
p
e
r
c
e
n
t
a
g
e
o
f
f
i
l
l
e
d
r
i
c
e
g
r
a
i
n
s
,
”
B
i
o
sys
t
e
m
s E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
5
0
,
p
p
.
7
9
–
8
8
,
O
c
t
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
sy
st
e
msen
g
.
2
0
1
6
.
0
7
.
0
1
1
.
[
2
5
]
P
.
S
a
x
e
n
a
,
K
.
P
r
i
y
a
,
S
.
G
o
e
l
,
P
.
K
.
A
g
g
a
r
w
a
l
,
A
.
S
i
n
h
a
,
a
n
d
P
.
A
i
n
,
“
R
i
c
e
v
a
r
i
e
t
i
e
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
ms,
”
J
o
u
rn
a
l
o
f
Ph
a
rm
a
c
e
u
t
i
c
a
l
N
e
g
a
t
i
v
e
R
e
su
l
t
s
,
v
o
l
.
1
3
,
n
o
.
S
p
e
c
i
a
l
i
ssu
e
0
7
,
2
0
2
2
,
d
o
i
:
1
0
.
4
7
7
5
0
/
p
n
r
.
2
0
2
2
.
1
3
.
S
0
7
.
4
7
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
a
r
in
i
S
h
a
d
a
k
sh
a
r
a
p
p
a
wo
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r,
in
in
fo
rm
a
ti
o
n
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
,
BM
S
CE.
S
h
e
o
b
tain
e
d
h
e
r
M
.
Tec
h
,
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
,
fro
m
S
c
h
o
o
l
o
f
En
g
in
e
e
rin
g
,
Ja
in
Un
i
v
e
rsity
,
Ba
n
g
a
lo
re
in
th
e
y
e
a
r
2
0
1
2
,
a
n
d
re
g
istere
d
fo
r
P
h
.
D
u
n
d
e
r
VT
U
in
De
c
e
m
b
e
r
2
0
1
7
.
He
r
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
ima
g
e
p
ro
c
e
ss
in
g
,
h
i
g
h
p
e
rf
o
rm
a
n
c
e
c
o
m
p
u
ti
n
g
a
n
d
m
a
c
h
i
n
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
h
h
a
rin
is8
@g
m
a
il
.
c
o
m
Dr
.
S
a
r
ith
a
Cha
k
r
a
sa
l
i
h
o
ld
s
a
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
M
a
d
u
ra
i
Ka
m
a
ra
j
Un
iv
e
rsity
,
fo
c
u
sin
g
o
n
m
e
d
ica
l
ima
g
e
se
c
u
rit
y
.
S
h
e
is
th
e
h
e
a
d
o
f
train
i
n
g
&
p
lac
e
m
e
n
t
a
n
d
a
p
ro
fe
ss
o
r
i
n
t
h
e
i
n
fo
rm
a
ti
o
n
sc
ien
c
e
&
e
n
g
in
e
e
rin
g
d
e
p
a
rtme
n
t
a
t
BNM
In
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
.
S
h
e
h
a
s r
e
c
e
iv
e
d
a
₹
2
0
lak
h
VG
S
T
g
ra
n
t
u
n
d
e
r
t
h
e
K
-
F
IS
T
L
1
sc
h
e
m
e
fo
r
a
p
ro
jec
t
o
n
G
P
G
P
U
c
o
m
p
u
ti
n
g
a
n
d
is
a
l
ife
m
e
m
b
e
r
o
f
IS
TE
a
n
d
C
S
I.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
rit
h
a
.
c
h
a
k
ra
sa
li
@g
m
a
il
.
c
o
m
Dr
.
K
r
ish
n
a
m
u
r
th
y
G
o
r
a
p
p
a
N
in
g
a
p
p
a
h
o
l
d
s
a
B.
E.
fr
o
m
Ku
v
e
m
p
u
Un
i
v
e
rsity
a
n
d
a
n
M
.
Tec
h
.
&
P
h
.
D
.
fro
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
Un
iv
e
rsit
y
.
He
h
a
s
se
rv
e
d
a
s
re
g
istrar
(e
v
a
lu
a
ti
o
n
)
a
t
VTU
a
n
d
a
s
p
ri
n
c
ip
a
l
a
n
d
is
c
u
rre
n
tl
y
t
h
e
d
e
p
u
t
y
d
irec
to
r
a
n
d
p
ro
fe
ss
o
r
o
f
CS
E
a
t
BNM
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
.
Wi
t
h
o
v
e
r
4
0
p
u
b
li
c
a
ti
o
n
s,
h
e
h
a
s
a
ls
o
re
p
re
se
n
ted
VTU
i
n
i
n
tern
a
ti
o
n
a
l
d
e
leg
a
ti
o
n
s,
v
isit
i
n
g
u
n
iv
e
rsiti
e
s
in
Eu
r
o
p
e
a
n
d
b
e
y
o
n
d
fo
r
a
c
a
d
e
m
ic co
ll
a
b
o
ra
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
n
m
it
p
rin
c
ip
a
l@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.