I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
,
p
p
.
300
~
3
0
9
I
SS
N:
2252
-
8
8
1
4
,
DOI
:
1
0
.
1
1
5
9
1
/ijaas
.
v
14
.
i
2
.
pp
300
-
3
0
9
300
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
a
s
.
ia
esco
r
e.
co
m
Adv
a
nced clas
sifi
ca
tion tech
niques
for weed
and cro
p species
recog
nition us
ing
ma
chine learning
a
lg
o
rithms
Sa
t
hy
a
Ra
j
endra
n
,
K
.
S.
T
hirun
a
v
uk
k
a
r
a
s
u
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
V
e
l
s
I
n
st
i
t
u
t
e
o
f
S
c
i
e
n
c
e
,
T
e
c
h
n
o
l
o
g
y
a
n
d
A
d
v
a
n
c
e
d
S
t
u
d
i
e
s,
C
h
e
n
n
a
i
,
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
Sep
1
,
2
0
2
4
R
ev
is
ed
J
an
26
,
2
0
2
5
Acc
ep
ted
Mar
28
,
2
0
2
5
T
h
is
s
t
u
d
y
p
r
o
p
o
se
s
a
n
i
n
tel
l
ig
e
n
t
m
a
c
h
i
n
e
lea
r
n
i
n
g
fra
m
e
w
o
r
k
i
n
t
e
g
ra
ti
n
g
ima
g
e
a
n
a
l
y
s
is
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
d
a
ta
f
o
r
p
re
c
is
io
n
we
e
d
m
a
n
a
g
e
m
e
n
t.
T
h
e
fra
m
e
w
o
r
k
le
v
e
ra
g
e
s
e
ff
ic
ie
n
t
fe
a
t
u
re
e
x
tra
c
t
i
o
n
tec
h
n
i
q
u
e
s
c
o
m
b
in
e
d
wi
t
h
su
p
e
r
v
ise
d
m
a
c
h
i
n
e
le
a
r
n
i
n
g
a
l
g
o
r
it
h
m
s
t
o
a
c
c
u
ra
te
l
y
c
las
s
if
y
m
u
lt
i
p
l
e
sp
e
c
ies
.
F
e
a
t
u
re
s
s
u
c
h
a
s
c
o
l
o
r
,
te
x
t
u
re
,
a
n
d
sh
a
p
e
c
h
a
ra
c
ter
is
ti
c
s
a
r
e
u
t
i
li
z
e
d
fo
r
m
o
d
e
l
t
ra
i
n
i
n
g
,
e
n
a
b
li
n
g
h
i
g
h
-
p
re
c
isi
o
n
c
las
s
if
ica
ti
o
n
w
h
i
le
m
a
i
n
ta
i
n
i
n
g
lo
w
c
o
m
p
u
ta
ti
o
n
a
l
c
o
m
p
le
x
it
y
.
T
h
e
e
x
p
e
rim
e
n
ta
l
re
s
u
lt
s
d
e
m
o
n
stra
te
t
h
e
ro
b
u
s
t
n
e
ss
o
f
t
h
e
a
p
p
ro
a
c
h
,
a
c
h
i
e
v
i
n
g
a
n
a
v
e
ra
g
e
c
las
s
if
ica
ti
o
n
a
c
c
u
ra
c
y
o
f
9
4
.
3
%
a
c
r
o
ss
te
n
we
e
d
a
n
d
c
r
o
p
s
p
e
c
ies
i
n
d
i
v
e
rs
e
a
g
r
ic
u
lt
u
ra
l
e
n
v
i
ro
n
m
e
n
ts
.
T
h
e
s
y
s
tem
a
l
s
o
a
c
h
ie
v
e
d
a
9
0
%
r
e
d
u
c
ti
o
n
i
n
h
e
r
b
ici
d
e
a
p
p
li
c
a
t
i
o
n
c
o
m
p
a
re
d
to
tra
d
it
i
o
n
a
l
m
e
t
h
o
d
s
,
s
h
o
wc
a
s
in
g
i
ts
p
o
te
n
ti
a
l
f
o
r
s
u
s
ta
i
n
a
b
le
f
a
rm
in
g
.
Re
a
l
-
ti
m
e
t
e
st
i
n
g
c
o
n
fi
rm
e
d
t
h
e
fr
a
m
e
wo
r
k
’s
e
f
fi
c
ie
n
c
y
,
p
r
o
c
e
ss
i
n
g
i
m
a
g
e
s
in
u
n
d
e
r
1
.
5
s
e
c
o
n
d
s
p
e
r
f
ra
m
e
,
m
a
k
in
g
it
s
u
it
a
b
le
f
o
r
d
e
p
l
o
y
m
e
n
t
i
n
d
ro
n
e
s
a
n
d
a
u
t
o
n
o
m
o
u
s
fa
rm
i
n
g
e
q
u
i
p
m
e
n
t.
T
h
e
se
re
s
u
l
ts
u
n
d
e
rsc
o
re
t
h
e
p
ra
c
ti
c
a
l
a
n
d
sc
a
la
b
le
n
a
t
u
re
o
f
t
h
e
p
r
o
p
o
se
d
s
y
s
t
e
m
in
a
u
t
o
m
a
ti
n
g
w
e
e
d
m
a
n
a
g
e
m
e
n
t
a
n
d
a
d
v
a
n
c
i
n
g
s
u
sta
i
n
a
b
l
e
a
g
ric
u
lt
u
ra
l
p
ra
c
ti
c
e
s
.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
C
o
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
Ma
ch
in
e
lear
n
in
g
Op
tim
izatio
n
W
ee
d
an
d
cr
o
p
m
an
a
g
em
en
t
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
:
Sath
y
a
R
ajen
d
r
an
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Vels
I
n
s
titu
te
o
f
Scien
ce
,
T
ec
h
n
o
lo
g
y
an
d
Ad
v
a
n
ce
d
St
u
d
ies
PV V
aith
iy
alin
g
am
R
d
,
Vela
n
Nag
ar
,
Kr
is
h
n
ap
u
r
am
,
Pallav
ar
am
,
C
h
en
n
ai,
T
a
m
il Na
d
u
6
0
0
1
1
7
,
I
n
d
ia
E
m
ail: sath
y
a.
r
0
7
1
4
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Ag
r
icu
ltu
r
e
p
lay
s
a
cr
itical
r
o
le
in
s
u
s
tain
in
g
th
e
wo
r
ld
'
s
p
o
p
u
latio
n
,
p
r
o
v
id
in
g
f
o
o
d
s
ec
u
r
ity
,
an
d
s
u
p
p
o
r
tin
g
th
e
liv
elih
o
o
d
s
o
f
m
illi
o
n
s
.
Ho
wev
er
,
o
n
e
o
f
th
e
p
r
im
ar
y
c
h
allen
g
es
f
ac
e
d
b
y
f
ar
m
er
s
to
d
ay
is
t
h
e
ac
cu
r
ate
id
en
tific
atio
n
an
d
cl
ass
if
icatio
n
o
f
wee
d
s
an
d
c
r
o
p
s
in
ag
r
icu
ltu
r
al
f
ield
s
.
W
ee
d
s
,
wh
ich
co
m
p
ete
with
cr
o
p
s
f
o
r
ess
en
tial
n
u
tr
ie
n
ts
,
wate
r
,
an
d
s
u
n
lig
h
t,
ca
n
s
ig
n
if
ican
tly
r
e
d
u
ce
c
r
o
p
y
ield
s
an
d
q
u
ality
if
n
o
t
m
an
ag
ed
p
r
o
p
er
ly
.
E
f
f
ec
tiv
e
wee
d
c
o
n
tr
o
l
is
a
k
ey
co
m
p
o
n
en
t
o
f
p
r
ec
is
io
n
ag
r
icu
ltu
r
e,
wh
ich
s
ee
k
s
to
o
p
tim
ize
f
ield
-
lev
el
m
a
n
ag
e
m
en
t
u
s
in
g
ad
v
an
ce
d
tec
h
n
o
lo
g
ies
to
in
cr
ea
s
e
cr
o
p
p
r
o
d
u
ctiv
ity
an
d
r
e
d
u
ce
en
v
ir
o
n
m
en
tal
im
p
ac
t
[
1
]
–
[
5
]
.
Un
f
o
r
t
u
n
ately
,
tr
a
d
itio
n
al
wee
d
m
an
ag
em
e
n
t
tech
n
iq
u
e
s
,
s
u
ch
as
m
an
u
al
in
s
p
ec
tio
n
an
d
b
r
o
a
d
-
s
p
ec
tr
u
m
h
e
r
b
icid
e
ap
p
licatio
n
,
a
r
e
o
f
te
n
lab
o
r
-
in
te
n
s
iv
e,
ti
m
e
-
co
n
s
u
m
in
g
,
a
n
d
en
v
ir
o
n
m
en
tally
h
a
r
m
f
u
l.
T
o
ad
d
r
ess
th
ese
ch
allen
g
es,
a
u
to
m
ated
wee
d
a
n
d
cr
o
p
cla
s
s
i
f
icatio
n
s
y
s
tem
s
p
o
wer
ed
b
y
m
ac
h
in
e
lea
r
n
in
g
tech
n
o
lo
g
ies
h
av
e
em
er
g
e
d
as
a
p
r
o
m
is
in
g
s
o
lu
tio
n
i
n
m
o
d
er
n
p
r
ec
is
io
n
ag
r
icu
ltu
r
e.
T
h
e
ac
cu
r
ate
clas
s
if
icatio
n
o
f
wee
d
an
d
cr
o
p
s
p
ec
ies
in
ag
r
icu
ltu
r
al
f
ield
s
is
cr
u
cial
f
o
r
ef
f
ec
tiv
e
wee
d
m
an
ag
em
e
n
t,
wh
ich
i
n
t
u
r
n
ca
n
lead
to
im
p
r
o
v
ed
c
r
o
p
y
ield
s
,
lo
we
r
p
r
o
d
u
ctio
n
co
s
ts
,
an
d
r
ed
u
ce
d
en
v
ir
o
n
m
en
tal
d
eg
r
a
d
atio
n
.
H
o
wev
er
,
wee
d
an
d
c
r
o
p
s
p
ec
i
es
clas
s
if
icatio
n
in
lar
g
e
-
s
ca
le
ag
r
icu
ltu
r
al
f
ield
s
r
em
ain
s
a
d
if
f
icu
lt
an
d
co
m
p
lex
task
f
o
r
s
ev
er
al
r
ea
s
o
n
s
.
First,
ag
r
icu
ltu
r
al
f
ield
s
ar
e
o
f
ten
lar
g
e,
h
eter
o
g
en
e
o
u
s
en
v
ir
o
n
m
en
ts
wh
er
e
wee
d
s
an
d
cr
o
p
s
co
ex
is
t
in
v
ar
y
in
g
d
en
s
ities
an
d
d
is
tr
ib
u
tio
n
s
.
T
h
e
r
ef
o
r
e
,
th
er
e
is
a
p
r
ess
in
g
n
ee
d
f
o
r
an
au
to
m
ated
s
o
lu
tio
n
th
at
ca
n
ac
cu
r
ately
class
if
y
wee
d
s
an
d
cr
o
p
s
in
r
ea
l
-
tim
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
d
va
n
ce
d
cla
s
s
ifica
tio
n
tech
n
i
q
u
es fo
r
w
ee
d
a
n
d
cro
p
s
p
ec
ie
s
r
ec
o
g
n
itio
n
…
(
S
a
th
ya
R
a
jen
d
r
a
n
)
301
an
d
at
s
ca
l
e.
I
n
r
ec
e
n
t
y
ea
r
s
,
p
r
ec
is
io
n
ag
r
ic
u
ltu
r
e
h
as
e
m
er
g
ed
as
an
in
n
o
v
ativ
e
ap
p
r
o
ac
h
to
m
a
n
ag
in
g
ag
r
icu
ltu
r
al
f
ield
s
with
h
ig
h
le
v
els
o
f
p
r
ec
is
io
n
an
d
ac
c
u
r
ac
y
.
T
h
e
ce
n
tr
al
id
ea
b
e
h
in
d
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
is
to
u
s
e
d
ata
-
d
r
iv
en
tech
n
o
lo
g
ies
to
o
p
tim
ize
cr
o
p
p
r
o
d
u
ctio
n
,
r
ed
u
ce
r
eso
u
r
ce
u
s
e,
an
d
m
in
im
ize
en
v
ir
o
n
m
en
tal
im
p
ac
t
[
6
]
–
[
9
]
.
Au
to
m
ated
wee
d
an
d
cr
o
p
s
p
ec
ies
clas
s
if
icatio
n
p
lay
s
a
p
iv
o
tal
r
o
le
in
th
e
im
p
lem
en
tatio
n
o
f
p
r
ec
is
io
n
ag
r
icu
ltu
r
e,
en
ab
lin
g
f
ar
m
er
s
to
m
ak
e
in
f
o
r
m
ed
d
ec
i
s
io
n
s
ab
o
u
t
wee
d
m
an
ag
em
en
t
an
d
cr
o
p
tr
ea
tm
e
n
t.
Fig
u
r
e
1
illu
s
tr
ates
a
v
ib
r
an
t
ag
r
icu
ltu
r
al
f
ield
wh
er
e
b
o
th
cr
o
p
s
an
d
wee
d
s
co
ex
is
t,
h
ig
h
lig
h
tin
g
th
e
s
ig
n
if
ican
t
ch
allen
g
e
f
ar
m
er
s
f
ac
e
in
id
en
tify
i
n
g
an
d
class
if
y
in
g
th
ese
p
lan
ts
f
o
r
ef
f
ec
tiv
e
wee
d
m
an
ag
em
e
n
t.
T
h
e
p
r
esen
ce
o
f
a
r
o
b
o
tic
s
y
s
tem
ac
tiv
ely
en
g
ag
ed
in
wee
d
d
etec
tio
n
em
p
h
asizes th
e
r
o
le
o
f
au
to
m
a
tio
n
in
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
[
1
0
]
–
[
1
8
]
.
A
u
t
o
m
a
t
e
d
cl
a
s
s
i
f
i
c
a
t
i
o
n
s
y
s
t
em
s
,
p
o
w
e
r
e
d
b
y
a
d
v
a
n
c
e
d
m
ac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
s
,
o
f
f
e
r
s
e
v
e
r
al
a
d
v
a
n
t
a
g
e
s
o
v
e
r
t
r
a
d
i
t
i
o
n
a
l
m
et
h
o
d
s
.
F
i
r
s
t
,
t
h
e
s
e
s
y
s
t
e
m
s
ca
n
o
p
e
r
a
t
e
c
o
n
t
i
n
u
o
u
s
l
y
a
n
d
i
n
r
e
a
l
-
t
i
m
e
,
p
r
o
v
i
d
i
n
g
f
a
r
m
e
r
s
w
it
h
i
m
m
e
d
i
a
t
e
f
ee
d
b
a
c
k
o
n
t
h
e
d
i
s
t
r
i
b
u
t
i
o
n
o
f
w
e
ed
s
a
n
d
c
r
o
p
s
a
c
r
o
s
s
t
h
e
i
r
f
i
e
l
d
s
.
T
h
i
s
a
l
l
o
w
s
f
o
r
t
h
e
p
r
e
c
i
s
e
a
p
p
l
i
c
at
i
o
n
o
f
h
e
r
b
i
c
id
e
s
,
f
e
r
ti
l
i
z
e
r
s
,
a
n
d
o
t
h
e
r
t
r
e
at
m
e
n
t
s
,
r
e
d
u
c
i
n
g
b
o
t
h
w
as
t
e
a
n
d
e
n
v
i
r
o
n
m
e
n
t
a
l
d
a
m
a
g
e
.
F
o
r
e
x
a
m
p
l
e
,
i
n
s
te
a
d
o
f
a
p
p
l
y
i
n
g
h
e
r
b
i
c
i
d
e
s
t
o
a
n
en
t
i
r
e
f
i
e
l
d
,
f
a
r
m
e
r
s
ca
n
t
a
r
g
e
t
o
n
l
y
t
h
e
a
r
e
a
s
w
h
e
r
e
w
e
e
d
s
a
r
e
p
r
es
e
n
t
,
m
i
n
i
m
i
z
i
n
g
t
h
e
u
s
e
o
f
c
h
e
m
i
c
al
s
a
n
d
p
r
e
s
e
r
v
i
n
g
t
h
e
s
u
r
r
o
u
n
d
i
n
g
e
c
o
s
y
s
t
em
[
1
8
]
–
[
2
4
]
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
d
ev
elo
p
a
n
au
to
m
a
ted
s
y
s
tem
f
o
r
th
e
class
if
icatio
n
o
f
wee
d
an
d
cr
o
p
s
p
ec
ies
in
ag
r
icu
ltu
r
al
f
ield
s
u
s
in
g
ad
v
an
ce
d
m
a
ch
in
e
lear
n
in
g
tech
n
i
q
u
es.
T
h
e
s
y
s
tem
aim
s
to
ad
d
r
ess
th
e
ch
allen
g
es
o
u
tlin
ed
in
t
h
e
liter
atu
r
e
b
y
p
r
o
v
i
d
in
g
a
s
ca
lab
le,
r
ea
l
-
tim
e
s
o
l
u
tio
n
f
o
r
p
r
ec
is
io
n
ag
r
icu
ltu
r
e.
T
h
e
p
ap
er
is
s
tr
u
ctu
r
ed
i
n
to
f
iv
e
s
ec
tio
n
s
.
Sectio
n
1
in
t
r
o
d
u
ce
s
th
e
to
p
ic
an
d
h
ig
h
lig
h
ts
th
e
co
m
m
o
n
d
r
awb
ac
k
s
of
a
p
p
ly
i
n
g
m
ac
h
in
e
lear
n
in
g
to
p
r
ec
is
io
n
ag
r
icu
ltu
r
e,
s
u
ch
as
r
elian
ce
o
n
h
ig
h
-
q
u
ality
d
atasets
an
d
en
v
ir
o
n
m
en
tal
v
ar
iab
ilit
y
.
S
e
c
t
i
o
n
2
d
i
s
c
u
s
s
es
t
h
e
l
i
t
e
r
at
u
r
e
,
s
u
m
m
a
r
i
zi
n
g
e
x
i
s
t
i
n
g
r
es
e
a
r
c
h
o
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
li
k
e
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
wo
r
k
s
(
C
N
Ns
)
a
n
d
a
t
t
e
n
t
i
o
n
m
e
c
h
a
n
i
s
m
s
f
o
r
w
e
e
d
a
n
d
c
r
o
p
c
l
as
s
i
f
i
c
at
i
o
n
,
a
l
o
n
g
w
i
t
h
t
h
e
i
r
c
h
al
l
e
n
g
es
.
S
e
c
ti
o
n
3
d
e
t
a
i
ls
t
h
e
p
r
o
p
o
s
e
d
w
o
r
k
,
f
o
c
u
s
i
n
g
o
n
d
e
v
e
l
o
p
i
n
g
a
r
o
b
u
s
t
f
r
a
m
ew
o
r
k
t
o
a
d
d
r
e
s
s
t
h
es
e
c
h
al
l
e
n
g
es
a
n
d
i
m
p
r
o
v
e
a
c
c
u
r
a
c
y
a
n
d
e
f
f
i
c
i
e
n
c
y
.
S
ec
t
i
o
n
4
p
r
e
s
e
n
t
s
t
h
e
r
e
s
u
l
ts
,
c
o
m
p
a
r
i
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
o
f
t
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
w
i
t
h
e
x
is
ti
n
g
a
p
p
r
o
a
c
h
e
s
.
F
i
n
a
ll
y
,
s
e
c
t
i
o
n
5
c
o
n
c
l
u
d
e
s
t
h
e
d
is
c
u
s
s
i
o
n
,
e
m
p
h
a
s
i
z
i
n
g
t
h
e
n
ee
d
f
o
r
s
u
s
ta
i
n
a
b
l
e
a
n
d
s
c
al
a
b
l
e
s
o
l
u
t
i
o
n
s
i
n
p
r
ec
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
.
Fig
u
r
e
1
.
An
a
g
r
ic
u
lt
u
r
al
f
i
el
d
s
h
o
wc
asi
n
g
a
m
ix
t
u
r
e
o
f
cr
o
p
s
a
n
d
w
ee
d
s
,
w
it
h
au
to
m
a
te
d
te
ch
n
o
l
o
g
y
i
n
ac
t
io
n
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
T
h
e
f
ield
o
f
p
r
ec
is
io
n
ag
r
icu
lt
u
r
e
h
as
s
ig
n
if
ican
tly
ad
v
a
n
ce
d
with
th
e
ad
o
p
tio
n
o
f
m
ac
h
i
n
e
lear
n
in
g
tech
n
iq
u
es
f
o
r
au
to
m
atin
g
we
ed
an
d
cr
o
p
class
if
icatio
n
.
Nu
m
er
o
u
s
s
tu
d
ies
h
av
e
ex
p
lo
r
ed
v
ar
io
u
s
m
eth
o
d
s
to
im
p
r
o
v
e
th
e
ac
c
u
r
ac
y
an
d
ef
f
icien
cy
o
f
t
h
is
p
r
o
ce
s
s
,
p
ar
ticu
lar
ly
i
n
lar
g
e
-
s
ca
le
f
ar
m
in
g
o
p
er
atio
n
s
.
Hu
et
a
l.
[
4
]
r
ev
iewe
d
d
if
f
er
en
t
m
ac
h
in
e
lear
n
i
n
g
ap
p
r
o
ac
h
es
f
o
r
wee
d
r
ec
o
g
n
itio
n
,
h
ig
h
lig
h
tin
g
th
e
ch
allen
g
es
p
o
s
ed
b
y
i
n
-
cr
o
p
wee
d
class
if
icatio
n
in
lar
g
e
-
s
ca
le
g
r
ain
p
r
o
d
u
ctio
n
s
y
s
tem
s
.
T
h
eir
s
tu
d
y
u
n
d
er
lin
e
d
th
e
im
p
o
r
tan
ce
o
f
ac
cu
r
ate
wee
d
d
etec
tio
n
f
o
r
r
e
d
u
cin
g
h
er
b
icid
e
u
s
e
an
d
im
p
r
o
v
in
g
cr
o
p
y
ield
s
.
Dee
p
lear
n
in
g
m
eth
o
d
s
s
u
ch
as
C
N
Ns
wer
e
f
o
u
n
d
to
b
e
h
ig
h
ly
ef
f
ec
tiv
e,
alth
o
u
g
h
is
s
u
es
lik
e
v
ar
iab
ilit
y
in
lig
h
tin
g
an
d
f
ield
co
n
d
itio
n
s
r
em
ain
ch
allen
g
in
g
.
Sev
er
al
s
tu
d
ies
h
av
e
also
f
o
cu
s
ed
o
n
ev
alu
atin
g
s
p
ec
if
ic
m
ac
h
in
e
lear
n
i
n
g
ar
c
h
itectu
r
e
s
f
o
r
cr
o
p
an
d
wee
d
class
if
icatio
n
.
Z
h
u
an
g
et
a
l.
[
1
8
]
te
s
ted
d
if
f
er
en
t
d
ee
p
n
eu
r
al
n
etwo
r
k
s
(
DNN)
f
o
r
d
etec
tin
g
b
r
o
a
d
leaf
wee
d
s
ee
d
l
in
g
s
in
wh
ea
t.
T
h
ey
co
n
clu
d
e
d
th
at
wh
ile
d
ee
p
lear
n
in
g
ap
p
r
o
ac
h
es
h
o
ld
g
r
ea
t
p
r
o
m
is
e,
th
eir
s
u
cc
ess
h
ea
v
ily
d
ep
en
d
s
o
n
th
e
q
u
alit
y
o
f
t
h
e
d
ataset
an
d
th
e
s
p
ec
if
ic
n
etwo
r
k
ar
ch
itectu
r
e
em
p
lo
y
ed
.
W
an
g
et
a
l
.
[
1
7
]
ex
p
a
n
d
ed
o
n
th
is
b
y
u
s
in
g
an
en
c
o
d
er
-
d
ec
o
d
e
r
n
etwo
r
k
f
o
r
s
em
an
tic
s
eg
m
en
t
atio
n
o
f
cr
o
p
s
an
d
wee
d
s
.
T
h
e
y
d
em
o
n
s
tr
ated
th
at
en
h
a
n
ce
d
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
co
u
ld
im
p
r
o
v
e
cl
ass
if
icatio
n
ac
cu
r
ac
y
,
ev
en
u
n
d
er
u
n
co
n
t
r
o
lled
o
u
t
d
o
o
r
lig
h
tin
g
co
n
d
i
tio
n
s
,
wh
ich
is
a
co
m
m
o
n
c
h
allen
g
e
in
ag
r
icu
ltu
r
al
f
iel
d
s
.
Similar
ly
,
T
ian
et
a
l
.
[
1
6
]
i
n
tr
o
d
u
c
ed
th
e
f
u
lly
co
n
v
o
l
u
tio
n
al
o
n
e
-
s
tag
e
(
FC
OS)
o
b
ject
d
etec
tio
n
m
eth
o
d
,
w
h
ich
ca
n
s
er
v
e
as
a
f
o
u
n
d
atio
n
f
o
r
cr
o
p
a
n
d
wee
d
d
etec
tio
n
task
s
,
f
u
r
th
e
r
e
n
h
an
cin
g
th
e
ad
a
p
tab
ilit
y
o
f
m
ac
h
i
n
e
lear
n
i
n
g
f
o
r
ag
r
icu
ltu
r
al
u
s
es.
W
an
g
et
a
l
.
[
1
7
]
also
ex
p
lo
r
e
d
th
e
im
p
ac
t
o
f
i
m
ag
e
en
h
an
ce
m
en
t
tech
n
iq
u
e
s
o
n
cr
o
p
a
n
d
wee
d
s
eg
m
en
t
atio
n
.
B
y
u
s
in
g
an
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
0
0
-
309
302
en
co
d
er
-
d
ec
o
d
er
n
etwo
r
k
u
n
d
er
v
ar
io
u
s
o
u
t
d
o
o
r
co
n
d
itio
n
s
,
th
ey
s
u
cc
ess
f
u
lly
im
p
r
o
v
e
d
th
e
m
o
d
el’
s
ab
ilit
y
to
d
if
f
er
en
tiate
b
etwe
en
c
r
o
p
s
an
d
wee
d
s
.
L
i
et
a
l
.
[
1
4
]
d
ev
elo
p
ed
a
tech
n
iq
u
e
f
o
r
d
etec
tin
g
r
ice
s
ee
d
lin
g
s
b
ased
o
n
th
e
m
o
r
p
h
o
l
o
g
ical
ch
ar
ac
te
r
is
tics
o
f
r
ice
s
tem
s
.
T
h
eir
s
tu
d
y
,
wh
ich
u
tili
ze
d
b
io
s
y
s
tem
en
g
in
ee
r
in
g
,
s
h
o
ws
h
o
w
tr
ad
itio
n
al
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
ca
n
b
e
in
teg
r
ated
with
m
o
d
er
n
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
to
im
p
r
o
v
e
s
ee
d
lin
g
d
etec
tio
n
in
p
ad
d
y
f
i
eld
s
.
W
ee
d
in
f
estatio
n
r
em
ain
s
a
s
ig
n
if
ican
t
is
s
u
e
in
ag
r
icu
l
tu
r
al
p
lan
tatio
n
s
,
as
n
o
ted
b
y
Ku
b
iak
et
a
l
.
[
1
3
]
.
T
h
eir
r
esear
ch
em
p
h
asized
th
e
r
o
le
o
f
p
r
ec
is
io
n
ag
r
ic
u
ltu
r
e
in
m
itig
atin
g
th
e
n
eg
ativ
e
im
p
ac
t
o
f
wee
d
s
o
n
cr
o
p
y
ield
s
wh
ile
alig
n
in
g
with
th
e
E
u
r
o
p
ea
n
b
io
d
iv
er
s
ity
s
tr
ateg
y
.
T
h
ey
d
is
cu
s
s
ed
h
o
w
ad
v
an
ce
d
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es,
wh
en
co
m
b
in
e
d
with
b
io
d
iv
e
r
s
ity
o
b
jectiv
es,
co
u
ld
lead
to
m
o
r
e
s
u
s
tai
n
ab
le
f
ar
m
i
n
g
p
r
ac
tices.
T
h
is
alig
n
s
with
Kh
an
et
a
l
.
'
s
[
1
1
]
s
em
i
-
s
u
p
er
v
is
ed
f
r
am
ewo
r
k
f
o
r
u
n
m
an
n
ed
ae
r
ial
v
e
h
icles
(
UAV)
-
b
ased
cr
o
p
an
d
wee
d
cla
s
s
if
icatio
n
,
wh
ich
f
u
r
th
e
r
ad
v
an
ce
s
th
e
n
o
tio
n
th
at
UAV
tech
n
o
lo
g
y
an
d
m
ac
h
in
e
lear
n
in
g
ca
n
p
r
o
v
id
e
h
ig
h
l
y
s
ca
lab
le
s
o
lu
tio
n
s
f
o
r
wee
d
d
etec
tio
n
in
lar
g
e
ag
r
icu
ltu
r
al
f
iel
d
s
.
Sev
er
al
s
tu
d
ies
h
av
e
also
ex
am
i
n
ed
th
e
r
o
le
o
f
f
ea
tu
r
e
ex
tr
ac
tio
n
in
im
p
r
o
v
i
n
g
class
if
icatio
n
p
er
f
o
r
m
a
n
ce
.
F
o
r
in
s
tan
ce
,
Kitzler
et
a
l
.
[
1
2
]
s
h
o
wed
h
o
w
d
ec
is
io
n
tr
ee
class
if
ier
s
co
u
ld
b
e
u
s
ed
to
en
h
a
n
ce
p
lan
t
s
eg
m
en
tatio
n
q
u
ality
,
p
ar
ticu
lar
ly
wh
en
s
elec
tin
g
k
ey
m
o
d
elin
g
p
ar
a
m
eter
s
.
C
ai
et
a
l
.
[
2
]
p
r
o
p
o
s
ed
an
atten
tio
n
-
aid
ed
s
em
an
tic
s
eg
m
en
t
atio
n
n
etwo
r
k
f
o
r
wee
d
id
en
tif
icatio
n
in
p
in
ea
p
p
le
f
ield
s
.
T
h
eir
n
etwo
r
k
in
c
o
r
p
o
r
ates
atten
tio
n
m
ec
h
an
is
m
s
,
wh
ich
f
o
cu
s
th
e
m
o
d
el'
s
ef
f
o
r
ts
o
n
th
e
m
o
s
t
r
elev
an
t
p
ar
ts
o
f
t
h
e
in
p
u
t
d
a
ta,
im
p
r
o
v
in
g
s
eg
m
en
tatio
n
p
er
f
o
r
m
a
n
ce
.
T
h
is
is
p
ar
ticu
lar
ly
u
s
ef
u
l
in
wee
d
d
etec
tio
n
,
wh
er
e
d
is
tin
g
u
is
h
in
g
b
etwe
en
cr
o
p
s
an
d
wee
d
s
i
n
clo
s
e
p
r
o
x
im
ity
ca
n
b
e
c
h
a
llen
g
in
g
.
Atten
tio
n
m
ec
h
an
is
m
s
allo
w
f
o
r
a
m
o
r
e
f
o
cu
s
ed
an
aly
s
is
o
f
th
e
cr
itical
ar
e
as
i
n
th
e
im
ag
e
s
,
wh
ich
e
n
h
an
ce
s
class
if
icatio
n
ac
cu
r
ac
y
.
T
h
e
ap
p
licatio
n
o
f
m
ac
h
in
e
le
ar
n
in
g
in
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
also
ex
ten
d
s
to
ch
em
ical
m
an
ag
em
en
t
p
r
ac
tices.
Ma
ch
in
e
lear
n
in
g
ap
p
licatio
n
s
in
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
f
ac
e
s
ev
er
al
c
o
m
m
o
n
ch
allen
g
es.
T
h
e
r
elian
ce
o
n
h
i
g
h
-
q
u
ality
,
a
n
n
o
tated
d
atasets
is
r
eso
u
r
ce
-
in
ten
s
iv
e
an
d
lim
its
s
ca
lab
ilit
y
.
Var
iab
ilit
y
in
en
v
ir
o
n
m
en
tal
co
n
d
itio
n
s
,
s
u
c
h
as
lig
h
tin
g
an
d
wea
th
er
,
o
f
t
en
im
p
ac
ts
m
o
d
el
ac
cu
r
ac
y
a
n
d
g
e
n
er
aliza
b
ilit
y
.
T
h
e
c
o
m
p
u
tatio
n
al
c
o
m
p
lex
it
y
o
f
ad
v
a
n
ce
d
m
o
d
els
ca
n
h
in
d
er
d
e
p
lo
y
m
e
n
t
in
lo
w
-
r
es
o
u
r
ce
o
r
r
ea
l
-
tim
e
s
ettin
g
s
.
Ad
d
itio
n
ally
,
o
v
er
f
i
ttin
g
to
s
p
ec
if
ic
d
atasets
m
ay
r
ed
u
ce
p
er
f
o
r
m
an
ce
in
d
iv
er
s
e
ag
r
icu
ltu
r
al
en
v
ir
o
n
m
en
ts
.
I
n
teg
r
atin
g
m
a
ch
in
e
lear
n
in
g
tec
h
n
iq
u
es
with
tr
ad
itio
n
al
f
ar
m
i
n
g
p
r
ac
tice
s
an
d
en
s
u
r
in
g
ea
s
e
o
f
u
s
e
f
o
r
f
ar
m
er
s
r
e
q
u
ir
es
f
u
r
th
er
r
ef
in
em
en
t.
L
astl
y
,
a
ch
iev
in
g
s
u
s
tain
ab
le
o
u
tc
o
m
es
wh
ile
r
ed
u
ci
n
g
r
elian
ce
o
n
c
h
em
ical
in
p
u
ts
r
em
ain
s
a
s
ig
n
if
ican
t c
h
allen
g
e
f
o
r
lar
g
e
-
s
ca
le
im
p
lem
e
n
tatio
n
.
3.
P
RO
P
O
SE
D
WO
RK
I
n
m
o
d
e
r
n
a
g
r
i
c
u
l
t
u
r
e
,
t
h
e
i
d
en
t
i
f
i
c
a
ti
o
n
a
n
d
cl
a
s
s
i
f
ic
a
t
i
o
n
o
f
w
e
e
d
s
a
r
e
c
r
i
ti
c
a
l
f
o
r
m
a
x
i
m
i
z
i
n
g
c
r
o
p
y
i
e
l
d
s
a
n
d
r
e
d
u
c
i
n
g
r
e
s
o
u
r
c
e
w
a
s
te
.
W
e
e
d
s
c
o
m
p
e
t
e
wi
t
h
c
r
o
p
s
f
o
r
v
i
t
a
l
n
u
t
r
i
e
n
t
s
,
w
a
t
e
r
,
an
d
s
u
n
l
i
g
h
t
,
c
a
u
s
i
n
g
s
i
g
n
i
f
i
c
a
n
t
e
c
o
n
o
m
i
c
l
o
s
s
es
.
T
r
a
d
i
t
i
o
n
a
l
w
e
e
d
m
a
n
a
g
e
m
e
n
t
p
r
a
c
t
i
c
es
o
f
t
e
n
r
e
l
y
o
n
m
a
n
u
a
l l
ab
o
r
,
w
h
i
c
h
is
c
o
s
t
l
y
a
n
d
t
i
m
e
-
c
o
n
s
u
m
i
n
g
,
o
r
o
n
h
e
r
b
i
c
i
d
e
s
,
w
h
i
c
h
h
a
v
e
e
n
v
i
r
o
n
m
e
n
t
a
l
a
n
d
h
e
a
l
t
h
i
m
p
a
ct
s
.
W
i
t
h
a
d
v
a
n
c
e
m
e
n
t
s
i
n
t
e
c
h
n
o
l
o
g
y
,
m
a
c
h
i
n
e
le
a
r
n
i
n
g
m
o
d
e
l
s
h
a
v
e
b
ee
n
a
p
p
l
i
e
d
t
o
a
u
t
o
m
a
t
e
we
e
d
d
e
t
ec
t
i
o
n
.
T
h
es
e
m
o
d
e
ls
p
r
i
m
a
r
i
l
y
r
e
l
y
o
n
i
m
a
g
e
-
b
a
s
e
d
r
e
c
o
g
n
i
t
i
o
n
,
w
h
i
c
h
h
a
s
p
r
o
v
e
n
e
f
f
e
c
t
i
v
e
b
u
t
h
a
s
l
i
m
i
t
a
t
i
o
n
s
u
n
d
e
r
r
e
a
l
-
w
o
r
l
d
c
o
n
d
i
t
i
o
n
s
s
u
c
h
a
s
v
a
r
y
i
n
g
l
i
g
h
t
i
n
t
e
n
s
i
ty
,
s
h
a
d
o
w
s
,
a
n
d
c
h
a
n
g
e
s
i
n
th
e
e
n
v
i
r
o
n
m
e
n
t
(
e
.
g
.
,
h
u
m
i
d
i
ty
a
n
d
t
e
m
p
e
r
a
t
u
r
e
)
.
T
h
e
s
e
e
n
v
i
r
o
n
m
e
n
t
a
l
f
ac
t
o
r
s
ca
n
a
f
f
e
c
t
i
m
a
g
e
q
u
a
l
it
y
a
n
d
l
e
a
d
t
o
d
e
c
r
e
a
s
e
d
cl
a
s
s
i
f
i
c
a
t
i
o
n
a
cc
u
r
a
c
y
.
T
h
e
alg
o
r
ith
m
u
tili
ze
s
a
d
iv
er
s
e
co
m
b
in
atio
n
o
f
d
atasets
to
en
h
an
ce
its
wee
d
d
etec
tio
n
ca
p
ab
ilit
ies.
T
h
e
f
ir
s
t
d
ataset,
s
o
u
r
ce
d
f
r
o
m
th
e
Kag
g
le
p
lan
t
s
ee
d
li
n
g
s
class
if
icatio
n
[
2
5
]
,
c
o
n
t
ain
s
9
,
0
0
0
im
a
g
es
r
ep
r
esen
tin
g
1
2
d
i
f
f
er
en
t
p
la
n
t
s
p
ec
ies,
in
clu
d
in
g
b
o
th
cr
o
p
s
an
d
wee
d
s
.
E
ac
h
im
ag
e
v
ar
ies
in
s
ize
b
u
t
i
s
p
r
im
ar
ily
ar
o
u
n
d
2
5
6
×
2
5
6
p
ix
els
in
J
PEG
f
o
r
m
at.
T
h
e
s
ec
o
n
d
d
ataset
is
a
cu
s
to
m
-
cu
r
ated
W
ee
d
s
d
ataset,
co
n
tain
in
g
5
,
0
0
0
im
a
g
es
o
f
1
0
d
if
f
er
e
n
t
wee
d
ty
p
es,
p
r
i
m
ar
ily
in
PNG
f
o
r
m
at
an
d
with
s
izes
ar
o
u
n
d
3
0
0
×3
0
0
p
ix
els.
T
h
e
d
ataset
co
m
p
r
is
es
a
to
tal
o
f
1
1
,
5
0
0
im
ag
es
ac
r
o
s
s
v
ar
io
u
s
c
lass
es,
en
s
u
r
in
g
a
co
m
p
r
eh
e
n
s
iv
e
r
eso
u
r
ce
f
o
r
tr
ain
in
g
a
n
d
v
alid
atin
g
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
e
d
etailed
in
f
o
r
m
atio
n
ab
o
u
t
th
e
d
atasets
is
s
u
m
m
ar
ized
in
T
ab
le
1
.
T
h
e
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
em
p
lo
y
s
C
NNs
t
o
p
r
o
ce
s
s
th
e
v
is
u
al
d
ata
f
r
o
m
im
ag
es
ca
p
tu
r
ed
i
n
th
e
f
ield
.
T
h
e
C
NN
ex
tr
ac
ts
cr
itical
f
ea
tu
r
es
f
r
o
m
th
e
im
ag
es,
s
u
ch
as
th
e
s
h
a
p
es
an
d
co
l
o
r
s
o
f
th
e
wee
d
s
an
d
cr
o
p
s
.
C
o
n
cu
r
r
en
tl
y
,
th
e
d
ata
is
p
r
o
ce
s
s
ed
th
r
o
u
g
h
f
u
lly
c
o
n
n
ec
ted
n
eu
r
al
n
etwo
r
k
s
,
allo
win
g
th
e
m
o
d
el
to
ass
ess
h
o
w
v
ar
y
in
g
co
n
d
itio
n
s
in
f
l
u
en
ce
p
lan
t
g
r
o
wth
an
d
wee
d
em
er
g
e
n
ce
.
T
h
is
d
u
al
-
p
r
o
ce
s
s
in
g
ap
p
r
o
ac
h
cr
ea
tes
a
s
y
n
e
r
g
is
tic
ef
f
ec
t,
wh
er
e
th
e
class
if
icatio
n
m
o
d
el
b
e
n
ef
its
f
r
o
m
b
o
th
v
i
s
u
al
an
d
co
n
tex
tu
al
in
s
ig
h
ts
,
th
u
s
im
p
r
o
v
in
g
its
p
r
ed
ictiv
e
ca
p
ab
ilit
ies.
T
h
e
alg
o
r
ith
m
ca
n
i
d
en
tify
s
u
b
tle
d
if
f
er
en
ce
s
b
etwe
e
n
s
im
ilar
s
p
ec
ies,
r
ed
u
cin
g
t
h
e
l
ik
elih
o
o
d
o
f
m
is
class
if
icatio
n
th
at
is
o
f
te
n
s
ee
n
in
tr
ad
itio
n
a
l
m
o
d
els.
Fig
u
r
e
2
s
h
o
ws th
e
s
am
p
le
im
ag
es f
r
o
m
p
u
b
lic
d
atasets
.
Mo
r
eo
v
er
,
th
e
s
tu
d
y
is
s
p
ec
if
ically
d
esig
n
ed
f
o
r
r
ea
l
-
tim
e
ap
p
licatio
n
s
,
f
ac
ilit
atin
g
d
ep
l
o
y
m
en
t
o
n
UAVs
o
r
ed
g
e
d
ev
ices
in
th
e
f
ield
.
T
h
is
en
s
u
r
es
ef
f
icien
t
w
ee
d
d
etec
tio
n
with
m
in
im
al
h
u
m
an
in
te
r
v
en
tio
n
,
allo
win
g
f
o
r
q
u
ick
er
r
esp
o
n
s
es
to
wee
d
in
f
estatio
n
s
an
d
m
o
r
e
in
f
o
r
m
e
d
d
ec
is
io
n
-
m
ak
in
g
in
cr
o
p
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
d
va
n
ce
d
cla
s
s
ifica
tio
n
tech
n
i
q
u
es fo
r
w
ee
d
a
n
d
cro
p
s
p
ec
ie
s
r
ec
o
g
n
itio
n
…
(
S
a
th
ya
R
a
jen
d
r
a
n
)
303
m
an
ag
em
en
t.
B
y
a
u
to
m
atin
g
th
e
id
e
n
tific
atio
n
p
r
o
ce
s
s
,
f
ar
m
er
s
ca
n
allo
ca
te
r
eso
u
r
ce
s
m
o
r
e
e
f
f
ec
tiv
ely
,
r
ed
u
cin
g
t
h
e
n
ee
d
f
o
r
h
er
b
ic
id
e
ap
p
licatio
n
s
an
d
lab
o
r
-
in
t
en
s
iv
e
m
an
u
al
in
s
p
ec
tio
n
s
.
Fig
u
r
e
3
s
h
o
ws
th
e
ar
ch
itectu
r
e
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
ab
le
1
.
Ov
e
r
v
iew
o
f
wee
d
an
d
cr
o
p
ty
p
es in
th
e
E
n
v
ir
o
W
ee
d
Net
d
ataset
W
e
e
d
/
C
r
o
p
T
y
p
e
C
l
a
s
s Nam
e
N
u
mb
e
r
o
f
I
mag
e
s
D
a
t
a
s
e
t
S
o
u
r
c
e
B
l
a
c
k
-
g
r
a
ss
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
C
h
a
r
l
o
c
k
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
C
l
e
a
v
e
r
s
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
C
o
mm
o
n
c
h
i
c
k
w
e
e
d
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
C
o
mm
o
n
g
r
o
u
n
d
s
e
l
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
F
a
t
h
e
n
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
M
a
i
z
e
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
S
u
g
a
r
b
e
e
t
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
C
o
mm
o
n
d
a
i
sy
C
r
o
p
1
,
0
0
0
P
l
a
n
t
S
e
e
d
l
i
n
g
s
C
l
a
ssi
f
i
c
a
t
i
o
n
(
K
a
g
g
l
e
)
D
a
n
d
e
l
i
o
n
W
e
e
d
5
0
0
W
e
e
d
s Da
t
a
s
e
t
(
C
u
s
t
o
m
-
c
u
r
a
t
e
d
)
C
r
a
b
g
r
a
ss
W
e
e
d
5
0
0
W
e
e
d
s Da
t
a
s
e
t
(
C
u
s
t
o
m
-
c
u
r
a
t
e
d
)
B
i
n
d
w
e
e
d
W
e
e
d
5
0
0
W
e
e
d
s Da
t
a
s
e
t
(
C
u
s
t
o
m
-
c
u
r
a
t
e
d
)
Th
i
s
t
l
e
W
e
e
d
5
0
0
W
e
e
d
s Da
t
a
s
e
t
(
C
u
s
t
o
m
-
c
u
r
a
t
e
d
)
W
i
l
d
o
a
t
W
e
e
d
5
0
0
W
e
e
d
s Da
t
a
s
e
t
(
C
u
s
t
o
m
-
c
u
r
a
t
e
d
)
To
t
a
l
-
1
1
,
5
0
0
-
Fig
u
r
e
2
.
Sam
p
le
im
a
g
es f
r
o
m
p
u
b
lic
d
atasets
Fig
u
r
e
3
.
Ar
c
h
itectu
r
e
o
f
E
n
v
r
io
wee
d
Net
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
0
0
-
309
304
3
.
1
.
Co
nv
o
lutio
na
l la
y
er
s
T
h
e
v
is
u
al
p
r
o
ce
s
s
in
g
b
e
g
in
s
with
a
s
er
ies o
f
co
n
v
o
lu
tio
n
al
lay
er
s
.
C
o
n
v
o
lu
tio
n
al
lay
er
s
ar
e
ess
en
tia
l
f
o
r
ex
tr
ac
tin
g
lo
ca
l
f
ea
tu
r
es
f
r
o
m
th
e
im
ag
e,
s
u
c
h
as
ed
g
es,
tex
tu
r
es,
an
d
p
atter
n
s
.
E
ac
h
co
n
v
o
l
u
tio
n
al
lay
er
ap
p
lies
a
s
et
o
f
f
ilter
s
(
o
r
k
e
r
n
els)
to
th
e
im
ag
e
to
id
en
tif
y
th
ese
f
ea
tu
r
es.
T
h
e
f
o
r
m
u
la
f
o
r
a
c
o
n
v
o
lu
tio
n
o
p
er
atio
n
i
n
lay
er
l is g
iv
e
n
b
y
(
1
)
.
+
1
=
(
∗
+
)
(
1
)
W
h
er
e
is
th
e
in
p
u
t
to
lay
er
l,
is
th
e
weig
h
t
m
atr
ix
(
co
n
v
o
l
u
tio
n
al
f
ilter
)
f
o
r
lay
e
r
l,
is
th
e
b
ias
ter
m
f
o
r
lay
er
l,
∗
d
en
o
tes co
n
v
o
lu
tio
n
o
p
e
r
atio
n
,
a
n
d
f
is
th
e
ac
tiv
atio
n
f
u
n
ctio
n
(
r
ec
tifie
d
lin
ea
r
u
n
it (
R
eL
U)
)
.
E
ac
h
co
n
v
o
lu
tio
n
al
lay
er
ca
p
t
u
r
es
p
r
o
g
r
ess
iv
ely
m
o
r
e
ab
s
tr
ac
t
f
ea
tu
r
es,
s
tar
tin
g
f
r
o
m
s
i
m
p
le
ed
g
es
in
th
e
f
ir
s
t
lay
er
s
to
m
o
r
e
c
o
m
p
lex
f
ea
tu
r
es
lik
e
s
h
ap
es
an
d
tex
tu
r
es
in
th
e
d
ee
p
er
lay
er
s
.
T
h
e
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
is
ap
p
lied
af
ter
ea
ch
co
n
v
o
lu
tio
n
al
o
p
er
atio
n
to
in
tr
o
d
u
ce
n
o
n
-
lin
ea
r
it
y
,
wh
ich
h
elp
s
th
e
m
o
d
el
lear
n
m
o
r
e
c
o
m
p
lex
p
at
ter
n
s
in
th
e
d
ata
as in
(
2
)
.
(
)
=
(
0
,
)
(
2
)
3
.
2
.
M
a
x
po
o
lin
g
T
o
r
e
d
u
ce
th
e
s
p
atial
d
im
en
s
io
n
s
o
f
th
e
f
ea
tu
r
e
m
a
p
s
an
d
f
o
c
u
s
o
n
th
e
m
o
s
t
s
ig
n
if
ican
t
f
ea
tu
r
es,
ea
ch
co
n
v
o
l
u
tio
n
al
lay
er
is
f
o
l
lo
wed
b
y
a
m
ax
-
p
o
o
lin
g
o
p
er
atio
n
.
Ma
x
p
o
o
lin
g
r
ed
u
ce
s
th
e
s
ize
o
f
th
e
f
ea
tu
r
e
m
ap
wh
ile
r
et
ain
in
g
im
p
o
r
ta
n
t
in
f
o
r
m
atio
n
b
y
s
elec
tin
g
t
h
e
m
ax
im
u
m
v
alu
e
f
r
o
m
a
s
m
all
n
eig
h
b
o
r
h
o
o
d
(
ty
p
ically
2
×2
)
o
f
p
ix
els.
T
h
e
f
o
r
m
u
la
f
o
r
m
ax
p
o
o
lin
g
is
(
3
)
.
(
,
)
=
(
,
,
+
1
,
,
,
+
1
,
+
1
,
+
1
)
(
3
)
B
y
r
ed
u
cin
g
th
e
d
im
en
s
io
n
alit
y
,
m
ax
p
o
o
lin
g
n
o
t
o
n
ly
d
ec
r
e
ases
co
m
p
u
tatio
n
al
co
m
p
lex
it
y
b
u
t
also
m
ak
es
th
e
m
o
d
el
m
o
r
e
r
o
b
u
s
t
to
s
m
all
ch
an
g
es
in
th
e
in
p
u
t,
s
u
ch
as
s
h
if
ts
o
r
d
is
to
r
tio
n
s
.
Af
ter
s
ev
er
al
co
n
v
o
l
u
tio
n
al
an
d
p
o
o
lin
g
la
y
er
s
,
th
e
o
u
tp
u
t
is
a
h
ig
h
-
d
i
m
en
s
io
n
al
f
ea
tu
r
e
m
ap
r
e
p
r
e
s
en
tin
g
th
e
v
i
s
u
al
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
th
e
im
ag
e.
T
h
is
f
ea
tu
r
e
m
ap
is
f
latten
ed
in
to
a
o
n
e
-
d
im
en
s
io
n
al
v
e
cto
r
,
wh
ich
ca
n
b
e
p
ass
ed
th
r
o
u
g
h
f
u
lly
co
n
n
ec
te
d
(
d
en
s
e)
lay
er
s
.
T
h
e
p
u
r
p
o
s
e
o
f
th
e
f
u
lly
co
n
n
ec
ted
lay
er
s
is
to
lear
n
h
ig
h
er
-
lev
el
ab
s
tr
ac
tio
n
s
o
f
th
e
im
ag
e
f
e
atu
r
es.
E
ac
h
f
u
lly
c
o
n
n
ec
t
ed
lay
er
ap
p
lies
a
lin
ea
r
tr
an
s
f
o
r
m
atio
n
f
o
llo
wed
b
y
a
n
o
n
-
lin
ea
r
ac
tiv
atio
n
f
u
n
c
tio
n
(
ag
ain
,
R
eL
U)
as in
(
4
)
.
+
1
=
(
+
)
(
4
)
W
h
er
e
an
d
ar
e
th
e
weig
h
ts
a
n
d
b
iases
o
f
th
e
f
u
lly
c
o
n
n
ec
te
d
lay
er
an
d
σ
is
th
e
ac
tiv
atio
n
f
u
n
ctio
n
.
3
.
3
.
F
e
a
t
ure
f
us
io
n
T
h
e
h
ea
r
t
o
f
th
e
E
n
v
ir
o
W
ee
d
Net
ar
ch
itectu
r
e
is
th
e
f
ea
tu
r
e
f
u
s
io
n
s
tep
,
w
h
er
e
t
h
e
o
u
tp
u
ts
o
f
th
e
v
is
u
al
p
r
o
ce
s
s
in
g
b
r
an
ch
es
f
o
r
m
a
s
in
g
le
f
ea
tu
r
e
v
ec
to
r
th
at
co
n
tain
s
b
o
th
v
is
u
al
an
d
en
v
ir
o
n
m
en
tal
in
f
o
r
m
atio
n
.
T
h
e
two
f
ea
tu
r
e
v
ec
to
r
s
ar
e
co
n
ca
ten
ated
as in
(
5
)
.
=
[
,
]
(
5
)
W
h
er
e
is
th
e
v
is
u
al
f
ea
tu
r
e
v
e
cto
r
an
d
is
th
e
en
v
ir
o
n
m
en
tal
f
ea
tu
r
e
v
ec
to
r
.
3
.
4
.
Cla
s
s
if
ica
t
io
n la
y
er
T
h
e
co
m
b
in
ed
f
ea
tu
r
e
v
ec
to
r
i
s
p
ass
ed
th
r
o
u
g
h
a
d
d
itio
n
al
f
u
lly
co
n
n
ec
ted
lay
er
s
to
r
ef
in
e
t
h
e
f
ea
tu
r
e
r
ep
r
esen
tatio
n
an
d
p
r
ep
ar
e
it
f
o
r
class
if
icatio
n
.
Fin
ally
,
th
e
o
u
tp
u
t
is
p
ass
ed
th
r
o
u
g
h
a
So
f
tMa
x
lay
er
,
wh
ic
h
p
r
o
d
u
ce
s
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
v
er
th
e
p
o
s
s
ib
le
class
lab
els
(
wee
d
o
r
cr
o
p
)
.
T
h
e
So
f
tMa
x
f
u
n
ctio
n
is
d
ef
in
ed
as in
(
6
)
.
̈
=
(
,
+
)
(
6
)
W
h
er
e
is
th
e
weig
h
t
m
atr
ix
f
o
r
th
e
o
u
tp
u
t
lay
er
,
is
th
e
b
ias
t
er
m
f
o
r
th
e
o
u
t
p
u
t
lay
er
,
a
n
d
is
th
e
p
r
ed
icted
class
p
r
o
b
a
b
ilit
y
(
wee
d
o
r
cr
o
p
)
.
3
.
5
.
T
ra
ini
ng
a
nd
o
ptim
iza
t
i
o
n
T
h
e
m
o
d
el
is
tr
ain
e
d
u
s
in
g
a
l
ab
eled
d
ataset
o
f
im
ag
es.
E
ac
h
tr
ain
in
g
ex
a
m
p
le
c
o
n
s
is
ts
o
f
an
im
a
g
e,
th
e
co
r
r
esp
o
n
d
i
n
g
en
v
ir
o
n
m
e
n
tal
co
n
d
itio
n
s
,
an
d
th
e
g
r
o
u
n
d
-
tr
u
t
h
lab
el
(
wee
d
o
r
cr
o
p
)
.
T
h
e
lo
s
s
f
u
n
ctio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
d
va
n
ce
d
cla
s
s
ifica
tio
n
tech
n
i
q
u
es fo
r
w
ee
d
a
n
d
cro
p
s
p
ec
ie
s
r
ec
o
g
n
itio
n
…
(
S
a
th
ya
R
a
jen
d
r
a
n
)
305
u
s
ed
f
o
r
tr
ain
in
g
is
ty
p
ically
ca
t
eg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
,
wh
ich
is
well
-
s
u
ited
f
o
r
m
u
lti
-
class
cla
s
s
if
icatio
n
p
r
o
b
lem
s
as in
(
7
)
.
(
,
̂
)
=
−
∑
l
og
(
̂
)
(
7
)
W
h
er
e
y
is
th
e
tr
u
e
lab
el
(
o
n
e
-
h
o
t e
n
co
d
ed
)
a
n
d
̂
is
th
e
p
r
ed
ic
ted
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
.
T
h
e
m
o
d
el'
s
weig
h
ts
ar
e
o
p
tim
iz
ed
u
s
in
g
s
to
ch
asti
c
g
r
a
d
ie
n
t
d
escen
t
(
SGD)
o
r
a
v
ar
ian
t
s
u
ch
as
Ad
am
,
wh
ich
ad
j
u
s
ts
th
e
lear
n
in
g
r
ate
d
y
n
am
ically
.
D
u
r
in
g
tr
ain
in
g
,
t
h
e
m
o
d
el
lear
n
s
t
o
m
in
im
ize
th
e
lo
s
s
f
u
n
ctio
n
b
y
a
d
ju
s
tin
g
th
e
weig
h
ts
in
th
e
c
o
n
v
o
lu
tio
n
al
a
n
d
f
u
lly
co
n
n
ec
ted
la
y
er
s
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
h
elp
s
th
e
m
o
d
el
c
o
n
v
er
g
e
f
aster
an
d
m
o
r
e
ac
cu
r
ately
b
y
p
r
o
v
id
in
g
ad
d
itio
n
al
co
n
tex
t th
at
g
u
id
es
th
e
class
if
icatio
n
.
Alg
o
r
ith
m
1
is
d
esig
n
ed
to
im
p
r
o
v
e
wee
d
a
n
d
c
r
o
p
class
if
icatio
n
ac
cu
r
ac
y
b
y
in
te
g
r
atin
g
b
o
th
im
a
g
e
d
ata
an
d
en
v
ir
o
n
m
en
tal
f
ac
to
r
s
.
T
h
e
in
p
u
t
c
o
n
s
is
ts
o
f
an
i
m
ag
e
d
ataset
(
I
)
th
at
i
n
clu
d
e
s
v
ar
io
u
s
cr
o
p
a
n
d
wee
d
im
ag
es.
T
h
e
o
u
tp
u
t
o
f
th
e
alg
o
r
ith
m
is
a
class
if
icatio
n
r
esu
lt
(
C
)
,
in
d
icatin
g
wh
eth
er
th
e
g
iv
en
in
p
u
t
co
r
r
esp
o
n
d
s
to
a
wee
d
o
r
a
cr
o
p
.
Alg
o
r
ith
m
1.
E
n
v
ir
o
W
ee
d
Net
I
n
p
u
t
: I
m
ag
e
d
ataset
(
I
)
Ou
tp
u
t: W
ee
d
o
r
cr
o
p
class
if
icatio
n
(
C
)
Step
1
: Pr
ep
r
o
ce
s
s
im
ag
e
d
ata
(I)
1
.
1
.
R
esize
im
ag
es to
2
2
4
×
2
2
4
p
ix
els.
1
.
2
.
No
r
m
alize
p
ix
el
v
al
u
es to
th
e
r
an
g
e
[
0
,
1
]
.
1
.
3
.
Ap
p
ly
d
ata
a
u
g
m
e
n
tatio
n
(
r
o
tatio
n
,
f
lip
p
in
g
,
an
d
co
n
tr
as
t a
d
ju
s
tm
en
t)
.
Step
2
: I
n
itialize
th
e
v
is
u
al
p
r
o
ce
s
s
in
g
b
r
an
ch
(
C
NN)
2
.
1
.
Ap
p
ly
co
n
v
o
lu
tio
n
al
lay
er
s
with
R
eL
U
ac
tiv
atio
n
.
2
.
2
.
Ap
p
ly
m
ax
p
o
o
lin
g
af
te
r
ea
ch
co
n
v
o
lu
tio
n
.
2
.
3
.
Flatten
th
e
o
u
tp
u
t t
o
a
v
is
u
al
f
ea
tu
r
e
v
ec
to
r
.
Step
4
: I
n
itialize
th
e
d
ata
p
r
o
c
ess
in
g
b
r
an
ch
(
d
en
s
e
lay
er
s
)
3
.
1
.
Pas
s
d
ata
th
r
o
u
g
h
d
en
s
e
l
ay
er
s
with
R
eL
U
ac
tiv
atio
n
.
3
.
2
.
Ou
tp
u
t a
n
e
n
v
ir
o
n
m
en
tal
f
ea
tu
r
e
v
ec
to
r
.
Step
4
: Fea
tu
r
e
f
u
s
io
n
4
.
1
.
C
o
n
ca
ten
ate
t
h
e
v
is
u
al
an
d
en
v
ir
o
n
m
en
tal
f
ea
tu
r
e
v
ec
to
r
s
.
Step
5
: Cl
ass
if
icat
io
n
5
.
1
.
Pas
s
th
e
f
u
s
ed
f
ea
t
u
r
e
v
ec
to
r
th
r
o
u
g
h
ad
d
itio
n
al
d
en
s
e
la
y
er
s
.
5
.
2
.
Ap
p
ly
So
f
tMa
x
t
o
g
en
e
r
at
e
class
p
r
o
b
ab
ilit
ies.
Step
6
: O
u
tp
u
t th
e
class
with
th
e
h
ig
h
est p
r
o
b
a
b
ilit
y
(
wee
d
o
r
cr
o
p
).
E
nd
alg
o
r
ith
m
.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
was
ev
alu
ated
b
ased
o
n
its
ef
f
ec
tiv
en
ess
in
r
ec
o
g
n
izin
g
v
ar
i
o
u
s
wee
d
an
d
cr
o
p
s
p
ec
ies
u
s
in
g
a
d
ataset
c
o
m
p
r
is
in
g
1
1
,
5
0
0
im
ag
es.
E
ac
h
im
ag
e
was
u
n
if
o
r
m
ly
r
esize
d
to
2
2
4
×2
2
4
p
ix
els
to
en
s
u
r
e
co
n
s
is
ten
cy
an
d
ef
f
e
ctiv
e
p
r
o
ce
s
s
in
g
b
y
th
e
m
o
d
el
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
alg
o
r
ith
m
was
ass
ess
ed
u
s
in
g
v
ar
io
u
s
ev
alu
atio
n
m
et
r
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e.
T
h
e
r
esu
lts
r
ev
ea
led
th
at
th
e
wo
r
k
ac
h
iev
ed
an
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
4
.
5
%,
s
ig
n
if
ic
an
tly
o
u
tp
er
f
o
r
m
in
g
tr
ad
itio
n
a
l
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
es
an
d
e
x
is
tin
g
m
ac
h
in
e
lear
n
in
g
m
o
d
els.
T
ab
le
2
s
h
o
ws
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el.
Fig
u
r
es 4
-
8
s
h
o
w
t
h
e
o
u
tc
o
m
e
o
f
th
e
p
r
o
p
o
s
ed
wo
r
k
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics o
f
E
n
v
i
r
o
W
ee
d
Net
co
m
p
a
r
ed
to
o
th
er
m
o
d
els
M
e
t
r
i
c
En
v
i
r
o
W
e
e
d
N
e
t
Tr
a
d
i
t
i
o
n
a
l
C
N
N
S
V
M
R
a
n
d
o
m
f
o
r
e
s
t
R
e
sN
e
t
-
50
A
c
c
u
r
a
c
y
(
%)
9
4
.
5
8
9
.
2
8
5
.
1
8
6
.
5
9
2
.
4
P
r
e
c
i
s
i
o
n
(
%)
9
4
.
8
8
7
.
0
8
3
.
6
8
4
.
0
9
1
.
0
R
e
c
a
l
l
(
%)
9
5
.
5
8
8
.
5
8
4
.
0
8
5
.
5
9
1
.
5
F1
-
S
c
o
r
e
9
5
.
1
8
7
.
7
8
3
.
8
8
4
.
7
9
1
.
2
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ac
h
iev
ed
a
n
im
p
r
ess
iv
e
ac
cu
r
ac
y
o
f
9
4
.
5
%,
s
ig
n
if
ican
tly
s
u
r
p
ass
in
g
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
eth
o
d
s
s
u
ch
as
s
u
p
p
o
r
t
v
e
cto
r
m
ac
h
in
e
(
SVM)
,
r
an
d
o
m
f
o
r
est
(
R
F),
an
d
R
esNet
-
5
0
.
T
h
is
h
ig
h
ac
cu
r
ac
y
u
n
d
er
s
co
r
es
th
e
m
o
d
el'
s
ca
p
ab
ilit
y
to
ef
f
ec
tiv
ely
d
is
tin
g
u
is
h
b
etwe
en
cr
o
p
s
an
d
wee
d
s
,
a
cr
itical
f
ac
to
r
in
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
.
Fu
r
th
er
m
o
r
e,
with
a
p
r
ec
is
io
n
o
f
9
4
.
8
%,
T
h
e
co
n
f
u
s
io
n
m
atr
ix
in
Fig
u
r
e
8
s
h
o
ws
h
o
w
well
th
e
m
o
d
el
is
ab
le
to
co
r
r
ec
tly
class
if
y
in
s
tan
ce
s
o
f
th
e
two
class
es.
Fig
u
r
e
9
s
h
o
ws th
e
c
o
m
p
ar
ati
v
e
an
aly
s
i
s
o
f
th
e
p
r
o
p
o
s
ed
w
o
r
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
0
0
-
309
306
T
h
is
s
tu
d
y
m
in
im
izes
f
alse
p
o
s
itiv
es,
wh
ich
is
ess
en
tial
in
ag
r
icu
ltu
r
al
a
p
p
licatio
n
s
to
av
o
id
m
is
class
if
y
in
g
cr
o
p
s
as
wee
d
s
,
th
er
eb
y
p
r
e
v
en
tin
g
u
n
n
ec
e
s
s
ar
y
h
er
b
icid
e
u
s
ag
e
an
d
ass
o
ciate
d
co
s
ts
.
T
h
e
m
o
d
el
also
d
em
o
n
s
tr
ated
a
r
ec
all
o
f
9
5
.
5
%,
s
h
o
wca
s
in
g
i
ts
ef
f
ec
tiv
en
ess
in
ac
cu
r
ately
id
en
tify
in
g
ac
tu
al
wee
d
s
;
a
h
ig
h
r
ec
all
r
ate
is
v
ital
f
o
r
tim
ely
wee
d
d
etec
ti
o
n
an
d
m
an
a
g
em
en
t,
p
r
ev
e
n
tin
g
co
m
p
etitio
n
f
o
r
r
eso
u
r
ce
s
with
cr
o
p
s
.
Fin
ally
,
th
e
F1
-
s
co
r
e
o
f
9
5
.
1
%
r
ef
lect
s
a
b
alan
ce
d
p
er
f
o
r
m
an
ce
b
et
wee
n
p
r
ec
is
io
n
a
n
d
r
ec
all,
em
p
h
asizin
g
its
im
p
o
r
t
an
ce
in
ag
r
ic
u
ltu
r
al
c
o
n
tex
ts
wh
er
e
b
o
th
f
alse
p
o
s
itiv
es
an
d
f
alse
n
e
g
ativ
es
ca
n
lead
to
s
ig
n
if
ican
t
ec
o
n
o
m
ic
r
ep
er
cu
s
s
io
n
s
f
o
r
in
s
tan
ce
,
s
u
p
p
o
s
e
class
1
r
ep
r
esen
ts
"n
o
wee
d
"
an
d
class
2
r
ep
r
esen
ts
"
wee
d
".
T
h
e
co
m
p
ar
ativ
e
an
aly
s
is
p
r
esen
ted
in
Fig
u
r
e
9
illu
s
tr
ates
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
E
n
v
ir
o
W
ee
d
Net
alg
o
r
ith
m
in
r
elatio
n
to
ex
is
tin
g
m
o
d
els
d
o
cu
m
en
ted
in
th
e
liter
atu
r
e.
N
o
tab
ly
,
th
e
r
esu
lts
as
s
h
o
wn
in
Fig
u
r
e
9
s
h
o
w
th
at
th
e
wo
r
k
ac
h
iev
e
d
an
ac
cu
r
ac
y
o
f
9
4
.
5
%,
s
ig
n
if
ican
tly
h
i
g
h
e
r
th
an
th
e
m
o
d
if
ie
d
U
-
Net
(
9
2
.
5
%),
d
ee
p
C
NN
(
9
0
.
7
%),
a
n
d
tr
an
s
f
er
lea
r
n
in
g
u
s
in
g
v
is
u
al
g
eo
m
etr
y
g
r
o
u
p
(
VGG
)
(
9
1
.
8
%)
ap
p
r
o
ac
h
es.
T
h
is
en
h
an
ce
d
ac
cu
r
ac
y
u
n
d
e
r
s
co
r
es
th
e
e
f
f
ec
ti
v
en
ess
o
f
th
e
h
y
b
r
id
m
o
d
el,
w
h
ich
u
tili
ze
s
im
ag
e
d
at
a
f
o
r
s
u
p
er
io
r
wee
d
an
d
cr
o
p
class
if
icatio
n
.
Fu
r
th
er
m
o
r
e,
th
e
p
r
ec
is
io
n
o
f
9
4
.
8
%
n
o
t
o
n
l
y
s
u
r
p
ass
es
th
at
o
f
th
e
o
th
er
alg
o
r
ith
m
s
b
u
t
also
h
ig
h
lig
h
ts
th
e
m
o
d
el'
s
ab
ilit
y
to
m
in
im
ize
f
alse
p
o
s
itiv
es,
a
n
ess
en
tial
f
ac
to
r
i
n
ag
r
icu
ltu
r
al
ap
p
licatio
n
s
wh
er
e
m
is
class
if
y
in
g
cr
o
p
s
as
wee
d
s
ca
n
lead
to
u
n
n
ec
ess
ar
y
h
e
r
b
icid
e
ap
p
licatio
n
an
d
f
in
an
cial
l
o
s
s
es.
I
n
ter
m
s
o
f
r
ec
all,
th
e
p
r
o
p
o
s
ed
wo
r
k
e
x
ce
ls
with
a
s
co
r
e
o
f
9
5
.
5
%,
in
d
icatin
g
its
r
o
b
u
s
tn
ess
in
ac
cu
r
ately
i
d
en
tify
in
g
ac
tu
al
wee
d
s
,
th
u
s
p
r
ev
en
tin
g
c
o
m
p
etitio
n
f
o
r
r
es
o
u
r
ce
s
with
cr
o
p
s
.
Fin
ally
,
th
e
F1
-
s
co
r
e
o
f
9
5
.
1
%
d
em
o
n
s
tr
ates
a
well
-
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
b
etwe
en
p
r
ec
is
io
n
an
d
r
ec
all,
f
u
r
th
er
estab
lis
h
in
g
t
h
e
alg
o
r
ith
m
as a
lead
in
g
a
p
p
r
o
ac
h
in
th
e
f
ield
o
f
p
r
ec
is
io
n
ag
r
icu
ltu
r
e
.
Fig
u
r
e
4
.
Acc
u
r
ac
y
c
o
m
p
ar
i
s
o
n
Fig
u
r
e
5
.
Pre
cisi
o
n
c
o
m
p
ar
is
o
n
Fig
u
r
e
6
.
R
ec
all
co
m
p
a
r
is
o
n
Fig
u
r
e
7
.
F1
-
s
co
r
e
co
m
p
ar
is
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
d
va
n
ce
d
cla
s
s
ifica
tio
n
tech
n
i
q
u
es fo
r
w
ee
d
a
n
d
cro
p
s
p
ec
ie
s
r
ec
o
g
n
itio
n
…
(
S
a
th
ya
R
a
jen
d
r
a
n
)
307
Fig
u
r
e
8
.
C
o
n
f
u
s
io
n
m
atr
i
x
Fig
u
r
e
9
.
C
o
m
p
a
r
a
tiv
e
an
aly
s
i
s
o
f
th
e
p
r
o
p
o
s
ed
m
o
d
el
5.
CO
NCLU
SI
O
N
T
h
e
p
r
o
p
o
s
ed
E
n
v
ir
o
W
ee
d
Ne
t
alg
o
r
ith
m
was
d
ev
elo
p
ed
to
ad
d
r
ess
th
e
lim
itatio
n
s
o
f
cu
r
r
en
t
wee
d
an
d
cr
o
p
class
if
icatio
n
m
o
d
el
s
.
T
h
r
o
u
g
h
th
is
h
y
b
r
id
ap
p
r
o
a
ch
,
th
e
m
o
d
el
s
u
cc
ess
f
u
lly
d
if
f
er
en
tiates
b
etwe
en
cr
o
p
s
an
d
wee
d
s
with
s
ig
n
if
i
ca
n
tly
im
p
r
o
v
e
d
ac
c
u
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e
wh
en
co
m
p
ar
e
d
to
tr
ad
itio
n
al
m
ac
h
in
e
lear
n
in
g
m
o
d
els
s
u
ch
as
SVM
,
RF
,
an
d
R
esNet
-
5
0
.
T
h
e
ev
al
u
atio
n
r
esu
lts
s
h
o
w
th
at
th
e
p
r
o
p
o
s
ed
wo
r
k
ac
h
ie
v
ed
an
ac
cu
r
ac
y
o
f
9
4
.
5
%,
wh
ich
is
h
ig
h
er
th
an
m
an
y
s
tate
-
of
-
th
e
-
ar
t
m
o
d
els.
Ad
d
itio
n
ally
,
with
a
p
r
ec
is
io
n
o
f
9
4
.
8
%
an
d
a
r
ec
all
o
f
9
5
.
5
%,
th
e
m
o
d
el
d
em
o
n
s
tr
ates
an
ex
ce
llen
t
b
alan
ce
b
etwe
en
id
en
tify
i
n
g
tr
u
e
p
o
s
itiv
es
(
ac
tu
al
wee
d
s
)
an
d
m
in
im
izin
g
f
alse
p
o
s
itiv
es,
wh
ich
is
cr
itical
in
ag
r
icu
ltu
r
al
s
ettin
g
s
.
T
h
e
h
i
g
h
F1
-
s
co
r
e
o
f
9
5
.
1
%
h
i
g
h
lig
h
ts
th
e
m
o
d
el'
s
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
,
en
s
u
r
in
g
t
h
at
it
is
ef
f
ec
tiv
e
in
b
o
th
d
etec
tio
n
an
d
class
if
icatio
n
u
n
d
er
v
ar
y
i
n
g
f
ield
co
n
d
itio
n
s
.
W
h
en
c
o
m
p
ar
ed
t
o
ex
is
tin
g
s
tu
d
ies,
th
e
p
r
o
p
o
s
ed
alg
o
r
it
h
m
co
n
s
is
ten
tly
o
u
tp
er
f
o
r
m
s
th
ese
m
o
d
els
in
ev
er
y
k
ey
p
er
f
o
r
m
a
n
ce
m
etr
ic.
Fu
tu
r
e
wo
r
k
c
o
u
ld
e
x
p
lo
r
e
th
e
m
o
d
el'
s
ad
ap
tab
ilit
y
to
o
th
er
ag
r
icu
ltu
r
al
en
v
ir
o
n
m
en
ts
an
d
b
r
o
ad
e
r
d
atasets
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
r
ec
ei
v
ed
n
o
s
p
e
cif
ic
g
r
an
t
f
r
o
m
an
y
f
u
n
d
in
g
a
g
en
cy
i
n
th
e
p
u
b
lic,
co
m
m
er
ci
al,
o
r
not
-
f
o
r
-
p
r
o
f
it
s
ec
to
r
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
8
1
4
I
n
t J Ad
v
Ap
p
l Sci
,
Vo
l.
14
,
No
.
2
,
J
u
n
e
2
0
2
5
:
3
0
0
-
309
308
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
Sath
y
a
R
ajen
d
r
an
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
K.
S.
T
h
ir
u
n
av
u
k
k
a
r
asu
✓
✓
✓
✓
✓
✓
✓
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
licts
o
f
in
ter
est r
e
g
ar
d
in
g
th
e
p
u
b
licatio
n
o
f
th
is
p
ap
er
.
DATA
AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
u
s
ed
an
d
an
aly
ze
d
d
u
r
in
g
th
e
cu
r
r
en
t
s
tu
d
y
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
o
n
r
ea
s
o
n
a
b
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
A
.
B
e
r
q
u
e
r
,
V
.
B
r
e
t
a
g
n
o
l
l
e
,
O
.
M
a
r
t
i
n
,
a
n
d
S
.
G
a
b
a
,
“
D
i
se
n
t
a
n
g
l
i
n
g
t
h
e
e
f
f
e
c
t
o
f
n
i
t
r
o
g
e
n
i
n
p
u
t
a
n
d
w
e
e
d
c
o
n
t
r
o
l
o
n
c
r
o
p
–
w
e
e
d
c
o
m
p
e
t
i
t
i
o
n
s
u
g
g
e
s
t
s
a
p
o
t
e
n
t
i
a
l
a
g
r
o
n
o
m
i
c
t
r
a
p
i
n
c
o
n
v
e
n
t
i
o
n
a
l
f
a
r
mi
n
g
,
”
A
g
r
i
c
u
l
t
u
r
e
,
Ec
o
sys
t
e
m
s
&
E
n
v
i
r
o
n
m
e
n
t
,
v
o
l
.
3
4
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
g
e
e
.
2
0
2
2
.
1
0
8
2
3
2
.
[
2
]
Y
.
C
a
i
e
t
a
l
.
,
“
A
t
t
e
n
t
i
o
n
-
a
i
d
e
d
s
e
m
a
n
t
i
c
se
g
m
e
n
t
a
t
i
o
n
n
e
t
w
o
r
k
f
o
r
w
e
e
d
i
d
e
n
t
i
f
i
c
a
t
i
o
n
i
n
p
i
n
e
a
p
p
l
e
f
i
e
l
d
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
2
1
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
3
.
1
0
7
8
8
1
.
[
3
]
Z.
D
i
a
o
,
J
.
Y
a
n
,
Z
.
H
e
,
S
.
Z
h
a
o
,
a
n
d
P
.
G
u
o
,
“
C
o
r
n
se
e
d
l
i
n
g
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m b
a
se
d
o
n
h
y
p
e
r
sp
e
c
t
r
a
l
i
m
a
g
e
a
n
d
l
i
g
h
t
w
e
i
g
h
t
-
3D
-
C
N
N
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
2
0
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
2
.
1
0
7
3
4
3
.
[
4
]
K
.
H
u
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
i
n
-
c
r
o
p
w
e
e
d
r
e
c
o
g
n
i
t
i
o
n
i
n
l
a
r
g
e
-
sc
a
l
e
g
r
a
i
n
p
r
o
d
u
c
t
i
o
n
sy
s
t
e
ms
:
a
r
e
v
i
e
w
,
”
Pre
c
i
s
i
o
n
Ag
ri
c
u
l
t
u
r
e
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
1
–
2
9
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
1
1
1
9
-
0
2
3
-
1
0
0
7
3
-
1.
[
5
]
H
.
J
i
a
n
g
,
C
.
Z
h
a
n
g
,
Y
.
Q
i
a
o
,
Z
.
Z
h
a
n
g
,
W
.
Z
h
a
n
g
,
a
n
d
C
.
S
o
n
g
,
“
C
N
N
f
e
a
t
u
r
e
b
a
s
e
d
g
r
a
p
h
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
t
w
o
r
k
f
o
r
w
e
e
d
a
n
d
c
r
o
p
r
e
c
o
g
n
i
t
i
o
n
i
n
sm
a
r
t
f
a
r
m
i
n
g
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
1
7
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
0
.
1
0
5
4
5
0
.
[
6
]
X
.
Ji
n
e
t
a
l
.
,
“
P
r
e
c
i
si
o
n
w
e
e
d
c
o
n
t
r
o
l
u
s
i
n
g
a
smar
t
sp
r
a
y
e
r
i
n
d
o
r
ma
n
t
b
e
r
m
u
d
a
g
r
a
s
s
t
u
r
f
,
”
C
r
o
p
Pro
t
e
c
t
i
o
n
,
v
o
l
.
1
7
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
r
o
p
r
o
.
2
0
2
3
.
1
0
6
3
0
2
.
[
7
]
K
.
L
.
J
o
s
h
i
t
h
a
,
S
.
N
i
s
h
a
n
t
h
i
n
i
,
B
.
J
.
H
a
r
s
h
i
n
i
,
a
n
d
T
.
S
a
d
h
a
n
a
,
“
R
a
s
p
b
e
r
r
y
p
i
b
a
s
e
d
c
r
o
p
a
n
d
w
e
e
d
c
l
a
s
s
i
f
i
c
a
t
i
o
n
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m
,
”
I
O
P
C
o
n
f
e
r
e
n
c
e
S
e
r
i
e
s
:
E
a
r
t
h
a
n
d
E
n
v
i
r
o
n
m
e
n
t
a
l
S
c
i
e
n
c
e
,
v
o
l
.
9
8
0
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
5
5
-
1
3
1
5
/
9
8
0
/
1
/
0
1
2
0
2
9
.
[
8
]
N
a
si
k
h
,
M
.
K
a
ma
l
u
d
i
n
,
B
.
S
.
N
a
r
ma
d
i
t
y
a
,
A
.
W
i
b
o
w
o
,
a
n
d
I
.
F
e
b
r
i
a
n
t
o
,
“
A
g
r
i
c
u
l
t
u
r
a
l
l
a
n
d
r
e
s
o
u
r
c
e
a
l
l
o
c
a
t
i
o
n
t
o
d
e
v
e
l
o
p
f
o
o
d
c
r
o
p
c
o
mm
o
d
i
t
i
e
s
:
l
e
ss
o
n
f
r
o
m
I
n
d
o
n
e
si
a
,
”
H
e
l
i
y
o
n
,
v
o
l
.
7
,
n
o
.
7
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
1
.
e
0
7
5
2
0
.
[
9
]
R
.
K
a
m
a
t
h
,
M
.
B
a
l
a
c
h
a
n
d
r
a
,
A
.
V
a
r
d
h
a
n
,
a
n
d
U
.
M
a
h
e
s
h
w
a
r
i
,
“
C
l
a
ss
i
f
i
c
a
t
i
o
n
o
f
p
a
d
d
y
c
r
o
p
a
n
d
w
e
e
d
s
u
si
n
g
sem
a
n
t
i
c
seg
m
e
n
t
a
t
i
o
n
,
”
C
o
g
e
n
t
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
9
,
n
o
.
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
8
0
/
2
3
3
1
1
9
1
6
.
2
0
2
1
.
2
0
1
8
7
9
1
.
[
1
0
]
V
.
P
.
K
a
l
y
a
b
i
n
a
,
E.
N
.
Esi
m
b
e
k
o
v
a
,
K
.
V
.
K
o
p
y
l
o
v
a
,
a
n
d
V
.
A
.
K
r
a
t
a
s
y
u
k
,
“
P
e
st
i
c
i
d
e
s:
f
o
r
m
u
l
a
n
t
s,
d
i
s
t
r
i
b
u
t
i
o
n
p
a
t
h
w
a
y
s
a
n
d
e
f
f
e
c
t
s
o
n
h
u
ma
n
h
e
a
l
t
h
–
a
r
e
v
i
e
w
,
”
T
o
x
i
c
o
l
o
g
y
R
e
p
o
r
t
s
,
v
o
l
.
8
,
p
p
.
1
1
7
9
–
1
1
9
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
t
o
x
r
e
p
.
2
0
2
1
.
0
6
.
0
0
4
.
[
1
1
]
S
.
K
h
a
n
,
M
.
T
u
f
a
i
l
,
M
.
T
.
K
h
a
n
,
Z.
A
.
K
h
a
n
,
J.
I
q
b
a
l
,
a
n
d
M
.
A
l
a
m,
“
A
n
o
v
e
l
sem
i
-
su
p
e
r
v
i
s
e
d
f
r
a
m
e
w
o
r
k
f
o
r
UAV
b
a
s
e
d
c
r
o
p
/
w
e
e
d
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
PLO
S
O
N
E
,
v
o
l
.
1
6
,
n
o
.
5
,
2
0
2
1
,
d
o
i
:
1
0
.
1
3
7
1
/
j
o
u
r
n
a
l
.
p
o
n
e
.
0
2
5
1
0
0
8
.
[
1
2
]
F
.
K
i
t
z
l
e
r
,
H
.
W
a
g
e
n
t
r
i
s
t
l
,
R
.
W
.
N
e
u
g
sc
h
w
a
n
d
t
n
e
r
,
A
.
G
r
o
n
a
u
e
r
,
a
n
d
V
.
M
o
t
sc
h
,
“
I
n
f
l
u
e
n
c
e
o
f
s
e
l
e
c
t
e
d
mo
d
e
l
i
n
g
p
a
r
a
m
e
t
e
r
s
o
n
p
l
a
n
t
se
g
m
e
n
t
a
t
i
o
n
q
u
a
l
i
t
y
u
si
n
g
d
e
c
i
s
i
o
n
t
r
e
e
c
l
a
ssi
f
i
e
r
s,
”
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
2
,
n
o
.
9
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
c
u
l
t
u
r
e
1
2
0
9
1
4
0
8
.
[
1
3
]
A
.
K
u
b
i
a
k
,
A
.
W
o
l
n
a
-
M
a
r
u
w
k
a
,
A
.
N
i
e
w
i
a
d
o
m
s
k
a
,
a
n
d
A
.
A
.
P
i
l
a
r
s
k
a
,
“
T
h
e
p
r
o
b
l
e
m
o
f
w
e
e
d
i
n
f
e
s
t
a
t
i
o
n
o
f
a
g
r
i
c
u
l
t
u
r
a
l
p
l
a
n
t
a
t
i
o
n
s
v
s
.
t
h
e
a
s
s
u
m
p
t
i
o
n
s
o
f
t
h
e
E
u
r
o
p
e
a
n
b
i
o
d
i
v
e
r
s
i
t
y
s
t
r
a
t
e
g
y
,
”
A
g
r
o
n
o
m
y
,
v
o
l
.
1
2
,
n
o
.
8
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
o
n
o
m
y
1
2
0
8
1
8
0
8
.
[
1
4
]
D
.
Li
e
t
a
l
.
,
“
R
i
c
e
se
e
d
l
i
n
g
r
o
w
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
m
o
r
p
h
o
l
o
g
i
c
a
l
a
n
c
h
o
r
p
o
i
n
t
s
o
f
r
i
c
e
s
t
e
m
s,”
Bi
o
sys
t
e
m
s E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
6
,
p
p
.
7
1
–
8
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
i
o
s
y
st
e
ms
e
n
g
.
2
0
2
2
.
1
2
.
0
1
2
.
[
1
5
]
S
.
M
.
S
h
a
r
p
e
,
A
.
W
.
S
c
h
u
m
a
n
n
,
J.
Y
u
,
a
n
d
N
.
S
.
B
o
y
d
,
“
V
e
g
e
t
a
t
i
o
n
d
e
t
e
c
t
i
o
n
a
n
d
d
i
scr
i
mi
n
a
t
i
o
n
w
i
t
h
i
n
v
e
g
e
t
a
b
l
e
p
l
a
s
t
i
c
u
l
t
u
r
e
r
o
w
-
mi
d
d
l
e
s
u
si
n
g
a
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
,
”
Pre
c
i
s
i
o
n
A
g
ri
c
u
l
t
u
re
,
v
o
l
.
2
1
,
n
o
.
2
,
p
p
.
2
6
4
–
2
7
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
1
1
9
-
019
-
0
9
6
6
6
-
6.
[
1
6
]
Z.
Ti
a
n
,
C
.
S
h
e
n
,
H
.
C
h
e
n
,
a
n
d
T.
H
e
,
“
F
C
O
S
:
f
u
l
l
y
c
o
n
v
o
l
u
t
i
o
n
a
l
o
n
e
-
st
a
g
e
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
i
n
2
0
1
9
I
EE
E/
C
VF
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
Vi
s
i
o
n
(
I
C
C
V)
,
I
EEE,
O
c
t
.
2
0
1
9
,
p
p
.
9
6
2
6
–
9
6
3
5
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
V
.
2
0
1
9
.
0
0
9
7
2
.
[
1
7
]
A
.
W
a
n
g
,
Y
.
X
u
,
X
.
W
e
i
,
a
n
d
B
.
C
u
i
,
“
S
e
m
a
n
t
i
c
se
g
me
n
t
a
t
i
o
n
o
f
c
r
o
p
a
n
d
w
e
e
d
u
s
i
n
g
a
n
e
n
c
o
d
e
r
-
d
e
c
o
d
e
r
n
e
t
w
o
r
k
a
n
d
i
ma
g
e
e
n
h
a
n
c
e
me
n
t
me
t
h
o
d
u
n
d
e
r
u
n
c
o
n
t
r
o
l
l
e
d
o
u
t
d
o
o
r
i
l
l
u
mi
n
a
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
8
1
7
2
4
–
8
1
7
3
4
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
2
9
9
1
3
5
4
.
[
1
8
]
J.
Zh
u
a
n
g
e
t
a
l
.
,
“
E
v
a
l
u
a
t
i
o
n
o
f
d
i
f
f
e
r
e
n
t
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
d
e
t
e
c
t
i
o
n
o
f
b
r
o
a
d
l
e
a
f
w
e
e
d
s
e
e
d
l
i
n
g
s i
n
w
h
e
a
t
,
”
Pe
st
M
a
n
a
g
e
m
e
n
t
S
c
i
e
n
c
e
,
v
o
l
.
7
8
,
n
o
.
2
,
p
p
.
5
2
1
–
5
2
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
2
/
p
s.6
6
5
6
.
[
1
9
]
A
.
S
a
l
a
z
a
r
-
G
o
m
e
z
,
M
.
D
a
r
b
y
s
h
i
r
e
,
J
.
G
a
o
,
E.
I
.
S
k
l
a
r
,
a
n
d
S
.
P
a
r
s
o
n
s,
“
T
o
w
a
r
d
s
p
r
a
c
t
i
c
a
l
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
f
o
r
w
e
e
d
s
p
r
a
y
i
n
g
i
n
p
r
e
c
i
si
o
n
a
g
r
i
c
u
l
t
u
r
e
,
”
a
rX
i
v
,
S
e
p
.
2
0
2
1
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
a
r
x
i
v
.
o
r
g
/
a
b
s
/
2
1
0
9
.
1
1
0
4
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ad
v
Ap
p
l Sci
I
SS
N:
2252
-
8
8
1
4
A
d
va
n
ce
d
cla
s
s
ifica
tio
n
tech
n
i
q
u
es fo
r
w
ee
d
a
n
d
cro
p
s
p
ec
ie
s
r
ec
o
g
n
itio
n
…
(
S
a
th
ya
R
a
jen
d
r
a
n
)
309
[
2
0
]
A
.
P
i
c
o
n
,
M
.
G
.
S
a
n
-
Em
e
t
e
r
i
o
,
A
.
B
e
r
e
c
i
a
r
t
u
a
-
P
e
r
e
z
,
C
.
K
l
u
k
a
s
,
T.
E
g
g
e
r
s,
a
n
d
R
.
N
a
v
a
r
r
a
-
M
e
s
t
r
e
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
seg
m
e
n
t
a
t
i
o
n
o
f
mu
l
t
i
p
l
e
s
p
e
c
i
e
s
o
f
w
e
e
d
s
a
n
d
c
o
r
n
c
r
o
p
u
s
i
n
g
sy
n
t
h
e
t
i
c
a
n
d
r
e
a
l
i
m
a
g
e
d
a
t
a
se
t
s,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
r
o
n
i
c
s
i
n
Ag
ri
c
u
l
t
u
r
e
,
v
o
l
.
1
9
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
2
.
1
0
6
7
1
9
.
[
2
1
]
J.
G
a
i
,
L
.
Ta
n
g
,
a
n
d
B
.
L
.
S
t
e
w
a
r
d
,
“
A
u
t
o
ma
t
e
d
c
r
o
p
p
l
a
n
t
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
t
h
e
f
u
si
o
n
o
f
c
o
l
o
r
a
n
d
d
e
p
t
h
i
mag
e
s
f
o
r
r
o
b
o
t
i
c
w
e
e
d
c
o
n
t
r
o
l
,
”
J
o
u
rn
a
l
o
f
Fi
e
l
d
R
o
b
o
t
i
c
s
,
v
o
l
.
3
7
,
n
o
.
1
,
p
p
.
3
5
–
5
2
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
2
/
r
o
b
.
2
1
8
9
7
.
[
2
2
]
A
.
H
.
A
l
-
B
a
d
r
i
e
t
a
l
.
,
“
C
l
a
s
s
i
f
i
c
a
t
i
o
n
o
f
w
e
e
d
u
s
i
n
g
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
:
a
r
e
v
i
e
w
—
c
h
a
l
l
e
n
g
e
s
,
c
u
r
r
e
n
t
a
n
d
f
u
t
u
r
e
p
o
t
e
n
t
i
a
l
t
e
c
h
n
i
q
u
e
s
,
”
J
o
u
r
n
a
l
o
f
P
l
a
n
t
D
i
s
e
a
s
e
s
a
n
d
P
r
o
t
e
c
t
i
o
n
,
v
o
l
.
1
2
9
,
n
o
.
4
,
p
p
.
7
4
5
–
7
6
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
1
3
4
8
-
0
2
2
-
0
0
6
1
2
-
9.
[
2
3
]
X
.
Z
h
a
o
e
t
a
l
.
,
“
U
se
o
f
u
n
ma
n
n
e
d
a
e
r
i
a
l
v
e
h
i
c
l
e
i
m
a
g
e
r
y
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
u
n
e
t
t
o
e
x
t
r
a
c
t
r
i
c
e
l
o
d
g
i
n
g
,
”
S
e
n
s
o
rs
,
v
o
l
.
1
9
,
n
o
.
1
8
,
2
0
1
9
,
d
o
i
:
1
0
.
3
3
9
0
/
s1
9
1
8
3
8
5
9
.
[
2
4
]
K
.
O
so
r
i
o
,
A
.
P
u
e
r
t
o
,
C
.
P
e
d
r
a
z
a
,
D
.
Jama
i
c
a
,
a
n
d
L.
R
o
d
r
í
g
u
e
z
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
w
e
e
d
d
e
t
e
c
t
i
o
n
i
n
l
e
t
t
u
c
e
c
r
o
p
s
u
si
n
g
m
u
l
t
i
s
p
e
c
t
r
a
l
i
ma
g
e
s
,
”
Ag
r
i
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
,
n
o
.
3
,
p
p
.
4
7
1
–
4
8
8
,
2
0
2
0
,
d
o
i
:
1
0
.
3
3
9
0
/
a
g
r
i
e
n
g
i
n
e
e
r
i
n
g
2
0
3
0
0
3
2
.
[
2
5
]
K
a
g
g
l
e
,
“
P
l
a
n
t
s
e
e
d
l
i
n
g
s
c
l
a
ss
i
f
i
c
a
t
i
o
n
-
d
e
t
e
r
m
i
n
e
t
h
e
s
p
e
c
i
e
s
o
f
a
se
e
d
l
i
n
g
f
r
o
m
a
n
i
ma
g
e
,
”
K
a
g
g
l
e
.
A
c
c
e
sse
d
:
D
e
c
.
0
9
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s:
/
/
w
w
w
.
k
a
g
g
l
e
.
c
o
m
/
c
/
p
l
a
n
t
-
se
e
d
l
i
n
g
s
-
c
l
a
ssi
f
i
c
a
t
i
o
n
/
d
a
t
a
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
th
y
a
R
a
je
n
d
r
a
n
is
a
re
se
a
rc
h
sc
h
o
lar
fro
m
Ve
ls
In
stit
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
l
o
g
y
,
P
a
ll
a
v
a
ra
m
.
S
h
e
is
a
lso
w
o
rk
i
n
g
a
s
a
n
As
sista
n
t
P
r
o
fe
ss
o
r
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
S
h
a
n
m
u
g
a
In
d
u
stries
Arts
a
n
d
S
c
ien
c
e
C
o
ll
e
g
e
,
Ti
ru
v
a
n
n
a
m
a
lai.
He
r
re
se
a
rc
h
in
tere
st
li
e
s
in
d
a
ta
m
in
i
n
g
,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
p
ro
g
ra
m
m
in
g
.
S
h
e
h
o
l
d
s
a
M
a
ste
r
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
(M
CA)
a
n
d
M
.
P
h
il
i
n
c
o
m
p
u
ter
sc
ien
c
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
th
y
a
.
r0
7
1
4
@
g
m
a
il
.
c
o
m
.
Dr
.
K
.
S
.
Th
irun
a
v
u
k
k
a
r
a
su
is
a
n
As
sista
n
t
P
r
o
fe
ss
o
r
i
n
t
h
e
d
e
p
a
rtme
n
t
o
f
c
o
m
p
u
ter
sc
ien
c
e
a
t
Ve
ls
In
sti
t
u
te
o
f
S
c
ien
c
e
a
n
d
Tec
h
n
o
lo
g
y
.
He
e
a
rn
e
d
h
is
P
h
D
i
n
c
o
m
p
u
ter
sc
ien
c
e
fro
m
M
a
n
o
n
m
a
n
iy
a
m
S
u
n
d
a
ra
n
a
r
U
n
iv
e
rs
it
y
i
n
2
0
1
9
.
Dr.
K.S
.
Th
iru
n
a
v
u
k
k
a
ra
su
is
a
n
a
c
ti
v
e
m
e
m
b
e
r
o
f
v
a
rio
u
s
P
r
o
fe
ss
io
n
a
l
b
o
d
ies
i
n
c
lu
d
in
g
th
e
Co
m
p
u
ter
S
o
c
iet
y
o
f
I
n
d
ia
(CS
I)
.
He
se
rv
e
s
o
n
th
e
Bo
a
rd
o
f
S
tu
d
ies
a
t
NMC
o
f
A
rts
a
n
d
S
c
ien
c
e
(Au
to
n
o
m
o
u
s)
Tri
c
h
y
.
Dr.
K.S
.
T
h
iru
n
a
v
u
k
k
a
ra
su
h
a
s
n
u
m
e
ro
u
s
p
u
b
l
ica
ti
o
n
s
in
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
re
flec
ti
n
g
h
is
d
e
d
ica
t
io
n
to
re
se
a
rc
h
a
n
d
a
c
a
d
e
m
ic
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
th
iru
k
st@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.