T
E
L
K
O
M
NIKA
T
elec
o
mm
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
1
8
9
7
~
1
9
0
3
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Ke
m
e
n
r
is
te
k
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/
T
E
L
KOM
NI
KA
.
v
1
8
i4
.
1
4
0
6
9
1897
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Rice seed
i
m
a
g
e c
la
ss
ifica
tion ba
sed o
n HO
G
des
cri
ptor
w
ith
m
iss
ing
va
lu
es i
m
putatio
n
H
uy
Ng
uy
en
-
Q
uo
c
,
Vinh
T
r
uo
ng
H
o
a
ng
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Ho
Ch
i
M
in
h
Cit
y
Op
e
n
Un
iv
e
rsity
,
V
ietn
a
m
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
9
,
2019
R
ev
i
s
ed
Feb
1
6
,
2
0
2
0
A
cc
ep
ted
Ma
r
1
8
,
2
0
2
0
Rice
is
a
p
ri
m
a
r
y
so
u
rc
e
o
f
fo
o
d
c
o
n
su
m
e
d
b
y
a
l
m
o
st
h
a
l
f
o
f
w
o
rld
p
o
p
u
lati
o
n
.
Rice
q
u
a
li
ty
m
a
in
ly
d
e
p
e
n
d
s
o
n
th
e
p
u
rit
y
o
f
th
e
rice
se
e
d
.
In
o
rd
e
r
t
o
e
n
su
re
th
e
p
u
rit
y
o
f
rice
v
a
riet
y
,
th
e
re
c
o
g
n
it
io
n
p
r
o
c
e
ss
is
a
n
e
ss
e
n
ti
a
l
sta
g
e
.
In
th
is
p
a
p
e
r,
w
e
fi
rstl
y
p
ro
p
o
se
to
u
se
h
ist
o
g
ra
m
o
f
o
rien
ted
g
ra
d
ien
t
(HO
G
)
d
e
sc
rip
to
r
to
c
h
a
ra
c
teriz
e
rice
se
e
d
im
a
g
e
s.
S
in
c
e
th
e
siz
e
o
f
im
a
g
e
is
to
tally
ra
n
d
o
m
a
n
d
th
e
f
e
a
tu
re
s
e
x
trac
ted
b
y
HO
G
c
a
n
n
o
t
b
e
u
se
d
d
irec
tl
y
b
y
c
las
si
fi
e
r
d
u
e
to
th
e
d
iff
e
re
n
t
d
ime
n
sio
n
s.
W
e
a
p
p
ly
s
e
v
e
ra
l
im
p
u
tatio
n
m
e
th
o
d
s
t
o
fi
ll
t
h
e
m
issin
g
d
a
ta
f
o
r
HO
G
d
e
sc
rip
to
r.
T
h
e
e
x
p
e
ri
m
e
n
t
is
a
p
p
li
e
d
o
n
th
e
V
NRICE
b
e
n
c
h
m
a
rk
d
a
tas
e
t
to
e
v
a
lu
a
te
th
e
p
r
o
p
o
se
d
a
p
p
ro
a
c
h
.
K
ey
w
o
r
d
s
:
HOG
d
escr
ip
to
r
KNN
i
m
p
u
tatio
n
L
i
n
ea
r
in
ter
p
o
latio
n
Miss
i
n
g
v
al
u
e
i
m
p
u
tat
io
n
R
ice
s
ee
d
i
m
a
g
e
cla
s
s
i
fi
ca
tio
n
Z
er
o
i
m
p
u
tatio
n
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
:
Vin
h
T
r
u
o
n
g
Ho
an
g
,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scien
ce
,
Ho
C
h
i M
i
n
h
C
it
y
Op
en
U
n
i
v
er
s
it
y
,
9
7
Vo
Van
T
an
Stre
et,
W
ar
d
6
,
Dis
tr
ict
3
,
HC
M
C
it
y
,
Viet
n
a
m
.
E
m
ail
:
v
i
n
h
.
t
h
@
o
u
.
ed
u
.
v
n
1.
I
NT
RO
D
UCT
I
O
N
R
ice
cu
l
tiv
a
tio
n
i
s
th
e
m
ai
n
ag
r
icu
l
tu
r
e
i
n
m
a
n
y
co
u
n
tr
ies
.
I
n
o
r
d
er
to
p
r
o
d
u
ce
h
ig
h
q
u
alit
y
r
ice
s
ee
d
s
,
class
i
fi
ca
tio
n
is
t
h
e
m
o
s
t
i
m
p
o
r
ta
n
t
s
ta
g
e.
T
h
e
in
ten
t
io
n
o
f
cla
s
s
i
ficatio
n
s
ta
g
e
is
t
o
en
s
u
r
e
th
e
p
u
r
it
y
o
f
th
e
r
ice
s
ee
d
s
b
y
r
e
m
o
v
in
g
b
ad
o
n
es
o
r
r
ice
s
ee
d
s
f
r
o
m
an
o
th
er
v
ar
ieties.
T
h
is
p
r
o
ce
s
s
is
u
s
u
al
l
y
co
n
tr
o
lled
b
y
s
o
m
e
s
ta
n
d
ar
d
s
to
en
s
u
r
e
t
h
e
r
ice
s
ee
d
q
u
alit
y
an
d
p
u
r
it
y
b
e
f
o
r
e
s
ellin
g
to
th
e
f
ar
m
er
s
f
o
r
m
as
s
g
r
o
w
in
g
.
No
w
ad
a
y
s
,
in
V
ietn
a
m
,
t
h
e
c
lass
i
ficatio
n
s
tag
e
i
s
u
s
u
a
ll
y
d
o
n
e
b
y
e
y
es
o
f
s
k
ill
f
u
l
f
ar
m
er
b
ased
o
n
s
o
m
e
f
ea
t
u
r
es,
t
h
is
m
et
h
o
d
is
ti
m
e
co
n
s
u
m
i
n
g
a
n
d
m
a
y
g
i
v
e
lo
w
q
u
alit
y
s
ee
d
s
.
W
it
h
t
h
e
d
ev
elo
p
m
en
t
o
f
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
,
th
e
co
m
p
u
ter
v
is
io
n
h
as
b
ee
n
ap
p
lied
in
ag
r
icu
l
tu
r
e
b
y
v
ar
io
u
s
ap
p
licatio
n
s
o
f
p
atter
n
r
ec
o
g
n
itio
n
s
u
c
h
as
d
etec
tio
n
o
f
d
is
ea
s
es
in
h
u
m
a
n
an
d
p
lan
ts
,
m
a
n
u
f
ac
tu
r
i
n
g
a
u
to
m
at
ic
in
s
p
ec
tio
n
,
au
to
m
at
ic
c
h
ar
ac
ter
izatio
n
,
f
r
u
it,
v
e
g
etab
le
a
n
d
g
r
ai
n
q
u
alit
y
ass
es
s
m
en
t
[
1
-
3
]
.
T
h
e
an
al
y
s
i
s
an
d
t
h
e
d
etec
tio
n
o
f
r
ice
s
ee
d
s
i
s
ca
r
r
ied
b
y
a
n
a
u
to
m
at
ic
co
m
p
u
ter
-
aid
ed
v
i
s
io
n
s
y
s
te
m
.
T
h
e
s
tep
o
f
an
al
y
zi
n
g
a
n
d
r
ec
o
g
n
izi
n
g
i
m
a
g
es
r
eq
u
ir
es
d
e
fin
i
n
g
d
esc
r
ip
to
r
s
w
h
ic
h
r
ep
r
esen
t
d
i
f
f
er
en
t
clas
s
es
o
f
s
ee
d
tex
t
u
r
es
a
n
d
ca
n
d
is
cr
i
m
in
a
te
ag
ain
s
t t
h
e
m
.
Fu
r
t
h
er
m
o
r
e,
tex
t
u
r
e
an
al
y
s
is
is
an
in
te
n
s
iv
e
r
esear
ch
to
p
ic
o
v
er
th
e
y
ea
r
s
.
A
w
id
e
v
ar
iet
y
o
f
lo
ca
l
im
ag
e
d
es
c
r
i
p
t
o
r
s
h
av
e
b
e
e
n
p
r
o
p
o
s
e
d
a
n
d
t
h
is
s
ig
n
ifi
c
an
tly
co
n
t
r
i
b
u
t
e
d
th
e
p
r
o
g
r
es
s
in
im
ag
e
a
n
a
ly
s
i
s
an
d
o
t
h
e
r
m
a
ch
in
e
v
is
i
o
n
t
ask
s
.
A
c
c
o
r
d
in
g
t
o
a
r
e
c
en
t
s
u
r
v
ey
o
f
Hu
m
e
a
u
-
He
u
r
t
i
e
r
[
4
,
5
]
a
b
o
u
t
t
ex
tu
r
e
an
a
ly
s
is
,
t
ex
tu
r
e
a
t
t
r
i
b
u
t
es
c
an
b
e
d
iv
i
d
e
d
in
t
o
s
e
v
en
c
at
eg
o
r
i
es
d
efi
n
e
d
in
t
e
r
m
s
o
f
s
t
at
is
t
i
ca
l
,
s
t
r
u
c
tu
r
al
,
t
r
a
n
s
f
o
r
m
-
b
a
s
e
d
,
m
o
d
el
-
b
ased
,
g
r
ap
h
-
b
ased
,
le
ar
n
in
g
-
b
ased
,
an
d
en
tr
o
p
y
-
b
as
ed
.
Sev
er
al
tex
t
u
r
e
a
n
al
y
s
i
s
a
p
p
r
o
ac
h
es
b
ased
o
n
g
lo
b
al
f
ea
t
u
r
e,
i
n
cl
u
d
e
co
lo
r
Gab
o
r
fi
lter
i
n
g
[
6
]
,
Ma
r
k
o
v
r
a
n
d
o
m
fi
e
ld
m
o
d
el
[
7
]
.
So
m
e
o
f
t
h
e
e
f
f
ec
tiv
e
lo
ca
l
f
ea
t
u
r
e
m
et
h
o
d
s
ar
e
co
lo
r
s
ca
le
in
v
ar
ian
t
f
ea
t
u
r
e
tr
an
s
f
o
r
m
(
SIFT
)
[
8
]
,
co
lo
r
p
y
r
a
m
id
o
f
h
i
s
to
g
r
a
m
s
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
9
7
-
1
9
0
3
1898
o
r
ien
ted
g
r
ad
ien
t
s
(
P
HOG)
[
9
]
,
d
is
cr
i
m
i
n
ati
v
e
co
lo
r
d
escr
ip
to
r
s
(
DC
D)
[
1
0
]
,
th
r
ee
-
d
i
m
en
s
io
n
al
ad
ap
tiv
e
s
u
m
an
d
d
if
f
er
e
n
ce
h
i
s
to
g
r
a
m
s
(
3
D
-
A
S
DH)
[
1
1
]
,
co
lo
r
lo
ca
l
b
in
ar
y
p
atter
n
[
1
2
,
1
3
]
an
d
af
f
in
e
w
a
v
elet
[
14
]
.
Am
o
n
g
o
f
t
h
e
m
,
h
is
to
g
r
a
m
o
f
o
r
ien
ted
g
r
ad
ie
n
ts
(
HOG)
[
1
5
]
is
s
u
cc
es
s
f
u
ll
y
ap
p
lied
f
o
r
i
m
a
g
e
cla
s
s
i
fi
ca
tio
n
an
d
o
b
j
ec
t
d
etec
tio
n
.
Du
o
n
g
an
d
Ho
an
g
[
1
6
]
ap
p
l
y
to
e
x
tr
ac
t
r
ice
s
ee
d
i
m
a
g
es
b
ased
o
n
f
ea
t
u
r
es
co
d
ed
in
m
u
ltip
le
co
lo
r
s
p
ac
es
u
s
i
n
g
HOG
d
escr
ip
to
r
.
P
h
an
et
al.
[
1
7
]
ev
alu
ate
an
d
co
m
p
ar
e
d
i
f
f
er
en
t
lo
ca
l
i
m
a
g
e
d
escr
ip
to
r
s
(
GI
ST,
SIFT
,
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
e
s
)
an
d
clas
s
i
fi
er
(
r
an
d
o
m
f
o
r
est,
K
NN,
S
VM
)
f
o
r
r
ice
s
ee
d
v
ar
ieties
id
e
n
ti
fi
ca
tio
n
.
T
h
e
y
s
h
o
w
ed
th
at
th
e
r
a
n
d
o
m
f
o
r
est
g
iv
e
s
th
e
b
est
r
es
u
lt
s
f
o
r
d
is
cr
i
m
i
n
ati
n
g
r
ice
s
ee
d
i
m
a
g
es.
Mo
r
e
r
ec
en
tl
y
,
V
u
et
al.
[
1
8
]
p
r
o
p
o
s
e
to
u
s
e
m
o
r
p
h
o
lo
g
ical
an
d
g
eo
m
e
tr
ical
f
ea
t
u
r
es
to
class
if
y
t
h
r
ee
g
r
o
u
p
s
o
f
r
ice
s
ee
d
v
ar
ietie
s
.
In
th
e
p
ast,
m
a
n
y
w
o
r
k
s
p
r
o
p
o
s
e
to
f
u
s
e
f
ea
tu
r
e
s
ex
tr
ac
ted
f
r
o
m
lo
ca
l
i
m
a
g
e
d
escr
ip
to
r
s
in
o
r
d
er
to
en
h
a
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
.
Fo
r
ex
a
m
p
le,
L
u
r
s
t
w
u
t
a
n
d
P
o
r
n
p
an
o
m
c
h
ai
[
1
9
]
r
ec
en
tl
y
p
r
esen
t
a
m
et
h
o
d
to
ev
alu
a
te
r
ice
s
ee
d
g
er
m
in
atio
n
i
m
a
g
e
s
b
ased
o
n
n
e
u
r
al
n
et
w
o
r
k
s
.
T
h
e
y
ex
tr
ac
t
a
n
d
f
u
s
e
th
r
ee
f
ea
t
u
r
es
(
co
lo
r
,
m
o
r
p
h
o
lo
g
y
a
n
d
te
x
tu
r
e)
f
r
o
m
r
ice
s
ee
d
i
m
ag
e
s
i
n
o
r
d
er
to
ev
alu
ate
t
h
e
g
er
m
i
n
atio
n
.
Me
b
atsi
o
n
et
al.
[
20
]
co
m
b
i
n
e
f
o
u
r
ier
d
escr
ip
to
r
s
a
n
d
th
r
ee
g
eo
m
etr
ical
f
o
r
au
to
m
atic
cla
s
s
i
ficatio
n
o
f
n
o
n
-
t
o
u
ch
in
g
ce
r
e
a
l
g
r
ain
s
.
S
z
c
zy
p
is
k
i
e
t
al
[2
1
]
i
d
e
n
t
if
y
th
e
b
a
r
l
ey
v
a
r
i
e
t
i
es
b
a
s
e
d
o
n
im
ag
e
a
tt
r
i
b
u
t
es
e
x
t
r
a
c
t
e
d
f
r
o
m
s
h
a
p
e
,
c
o
l
o
r
a
n
d
t
e
x
t
u
r
e
o
f
in
d
iv
i
d
u
a
l
k
e
r
n
el
s
.
C
h
au
g
u
l
e
a
n
d
M
al
i
[
2
2
]
p
r
o
p
o
s
e
a
n
ew
f
e
at
u
r
e
e
x
t
r
ac
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
c
l
a
s
s
if
y
in
g
p
a
d
d
y
s
e
e
d
s
b
as
e
d
o
n
s
e
e
d
c
o
lo
r
,
s
h
a
p
e
,
a
n
d
t
ex
tu
r
e
f
r
o
m
h
o
r
i
z
o
n
ta
l
v
e
r
t
i
c
al
a
n
d
f
r
o
n
t
r
e
a
r
an
g
l
es
.
K
u
o
et
a
l
[2
3
]
r
e
c
o
g
n
i
z
e
r
i
ce
g
r
a
in
s
im
ag
e
b
y
u
s
in
g
th
e
s
p
a
r
s
e
-
r
e
p
r
e
s
en
ta
ti
o
n
-
b
as
e
d
clas
s
i
fi
ca
tio
n
o
n
t
h
e
3
0
v
ar
ieties
r
ice
r
ep
r
o
d
u
ce
d
in
a
lo
ca
l
g
r
ee
n
h
o
u
s
e
at
T
ai
w
an
L
i
et
al.
[
2
4
]
u
s
e
t
h
e
la
s
er
s
ca
n
n
in
g
s
y
s
te
m
to
ac
q
u
ir
e
th
e
t
h
r
ee
-
d
i
m
e
n
s
io
n
al
p
o
in
t
c
lo
u
d
o
f
a
r
ice
s
ee
d
.
T
h
e
len
g
th
,
w
id
t
h
,
t
h
ic
k
n
e
s
s
an
d
s
h
ap
e
o
f
r
ice
s
ee
d
ar
e
co
m
p
u
ted
b
ased
o
n
t
h
e
o
r
ien
ted
b
o
u
n
d
i
n
g
b
o
x
.
Ho
ai
et
al.
[
2
5
]
in
tr
o
d
u
ce
a
co
m
p
ar
at
iv
e
s
t
u
d
y
o
f
h
an
d
-
cr
af
ted
d
escr
ip
to
r
s
an
d
c
o
n
v
o
l
u
tio
n
al
n
eu
r
al
n
et
w
o
r
k
s
(
C
NN)
f
o
r
r
ice
s
ee
d
i
m
a
g
es c
l
ass
i
f
icatio
n
.
Ho
w
e
v
er
,
f
o
r
th
e
r
ea
l
-
w
o
r
ld
ap
p
licatio
n
,
w
e
r
ec
o
g
n
ize
t
h
a
t
HOG
f
ea
tu
r
e
v
ec
to
r
s
e
x
tr
ac
ted
f
r
o
m
i
m
a
g
es
w
it
h
r
an
d
o
m
s
izes
h
a
v
e
d
if
f
er
e
n
t
n
u
m
b
er
s
o
f
d
i
m
e
n
s
io
n
w
h
ic
h
i
s
i
m
p
o
s
s
ib
le
to
class
i
f
y
.
T
h
e
r
ea
s
o
n
i
s
b
ec
au
s
e
o
f
t
h
e
d
i
f
f
er
en
ce
o
f
th
e
i
m
a
g
e
s
ize.
C
u
r
r
en
t
s
o
lu
tio
n
f
o
r
th
is
p
r
o
b
lem
is
r
esize
all
t
h
e
i
m
a
g
e
s
et
to
o
n
e
g
en
er
al
s
ize,
b
u
t
t
h
i
s
m
et
h
o
d
m
a
y
ca
u
s
e
p
r
o
b
lem
s
lik
e
lo
w
r
eso
l
u
tio
n
,
i
n
f
o
r
m
atio
n
lo
s
s
,
etc.
An
o
th
er
ap
p
r
o
ac
h
ca
n
b
e
u
s
e
d
to
s
o
lv
e
t
h
is
p
r
o
b
le
m
i
s
m
i
s
s
i
n
g
v
al
u
e
i
m
p
u
tatio
n
[
2
6
]
.
T
h
is
p
r
o
ce
s
s
allo
w
s
to
r
ep
lace
th
e
m
is
s
i
n
g
v
a
lu
e
d
ata
w
i
th
s
u
b
s
tit
u
ted
v
al
u
es.
T
h
er
e
h
av
e
b
ee
n
m
an
y
ap
p
r
o
ac
h
es
d
e
v
elo
p
ed
f
o
r
class
i
f
y
in
g
t
h
e
i
n
co
m
p
lete
d
ata.
T
h
e
fi
r
s
t
o
n
e
i
s
to
r
e
m
o
v
e
th
e
m
i
s
s
i
n
g
v
al
u
e
p
atter
n
s
d
ir
ec
tl
y
.
Ho
w
ev
er
,
th
is
ap
p
r
o
ac
h
ca
n
o
n
l
y
b
e
r
ea
lized
w
h
e
n
th
e
m
i
s
s
i
n
g
d
ata
s
et
is
s
m
all.
I
n
th
e
last
f
e
w
y
e
ar
s
,
m
is
s
i
n
g
v
al
u
e
i
m
p
u
ta
tio
n
p
r
o
b
le
m
h
as
attr
ac
ted
m
o
r
e
atten
tio
n
b
y
m
a
n
y
r
e
s
ea
r
ch
er
s
.
T
h
e
in
v
es
tig
a
tio
n
s
co
v
er
a
w
id
e
r
a
n
g
e
o
f
tec
h
n
iq
u
es,
f
r
o
m
s
tatis
t
ic
al
i
m
p
u
tatio
n
tec
h
n
iq
u
e
s
a
n
d
m
ac
h
in
e
lear
n
in
g
-
b
ased
i
m
p
u
tat
io
n
m
et
h
o
d
s
th
e
s
tati
s
tical
i
m
p
u
tatio
n
m
eth
o
d
s
u
s
e
p
o
p
u
lar
s
tatis
t
ical
m
eth
o
d
s
s
u
ch
as
t
h
e
r
ep
lace
m
en
t
b
y
m
ea
n
o
f
th
e
av
ai
lab
le
d
ata
an
d
r
e
g
r
ess
io
n
m
o
d
el
s
o
f
m
is
s
in
g
v
alu
e
s
[
5
,
2
6
,
27
]
.
L
in
a
n
d
T
s
ai
[
2
8
]
r
ev
ie
w
an
d
an
al
y
ze
1
1
1
jo
u
r
n
al
p
ap
e
r
s
p
u
b
lis
h
ed
f
r
o
m
2
0
0
6
to
2
0
1
7
r
elate
d
to
s
o
lv
e
th
e
p
r
o
b
le
m
s
o
f
i
n
co
m
p
let
e
d
ataset
in
cl
u
d
in
g
th
e
c
h
o
ice
o
f
d
atasets
,
m
is
s
i
n
g
r
ates
a
n
d
m
is
s
i
n
g
n
es
s
m
ec
h
a
n
is
m
s
,
th
e
m
is
s
i
n
g
v
al
u
e
i
m
p
u
ta
tio
n
tec
h
n
iq
u
es a
n
d
ev
a
lu
atio
n
m
etr
ic
s
e
m
p
lo
y
ed
.
I
n
o
r
d
er
to
tack
le
t
h
e
li
m
it
o
f
HOG
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
r
an
d
o
m
s
ize
i
m
ag
e
s
,
w
e
p
r
o
p
o
s
e
to
ap
p
l
y
m
is
s
i
n
g
v
a
lu
e
s
i
m
p
u
tatio
n
m
e
th
o
d
to
g
a
in
t
h
e
s
a
m
e
d
i
m
e
n
s
i
o
n
al
f
ea
tu
r
e
v
ec
to
r
o
f
all
i
m
a
g
es
in
c
l
u
d
i
n
g
KN
N
i
m
p
u
ta
tio
n
,
ze
r
o
i
m
p
u
ta
tio
n
a
n
d
li
n
ea
r
in
ter
p
o
latio
n
.
T
h
e
f
o
llo
w
i
n
g
o
f
t
h
i
s
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
.
Sectio
n
2
in
tr
o
d
u
ce
s
r
esear
c
h
m
eth
o
d
s
w
h
ic
h
ar
e
HOG
d
escr
ip
to
r
an
d
m
i
s
s
i
n
g
v
al
u
es
i
m
p
u
tat
io
n
m
eth
o
d
s
.
Sectio
n
3
th
en
d
escr
ib
es
th
e
ex
p
er
i
m
en
ta
l
r
esu
lt
s
.
Fin
al
l
y
,
co
n
clu
s
io
n
a
n
d
f
u
t
u
r
e
w
o
r
k
s
ar
e
p
r
esen
ted
in
se
ctio
n
4
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
I
n
th
is
s
ec
tio
n
,
w
e
b
r
ie
fly
p
r
esen
t
th
e
h
i
s
to
g
r
a
m
s
o
f
o
r
ie
n
ted
g
r
ad
ie
n
t
w
h
ic
h
is
u
s
ed
to
ex
tr
ac
t
f
ea
t
u
r
es f
r
o
m
r
ice
s
ee
d
i
m
a
g
es
.
T
h
en
,
s
ev
er
al
m
i
s
s
i
n
g
v
al
u
e
i
m
p
u
tat
io
n
m
eth
o
d
s
ar
e
d
is
c
u
s
s
ed
.
2
.
1
.
H
is
t
o
g
ra
m
s
o
f
o
rient
ed
g
ra
dient
des
cr
ipto
r
His
to
g
r
a
m
s
o
f
o
r
ien
ted
g
r
ad
ien
t
(
HOG)
d
escr
ip
to
r
i
s
w
id
el
y
u
s
ed
i
n
o
b
j
ec
t
d
etec
tio
n
an
d
clas
s
i
fi
ca
t
io
n
,
e
s
p
ec
iall
y
f
o
r
p
er
s
o
n
d
etec
tio
n
.
I
t
is
fi
r
s
t
p
r
o
p
o
s
ed
b
y
Dala
l
a
n
d
T
r
ig
g
s
[
1
5
]
.
B
ef
o
r
e
co
m
p
u
ti
n
g
HO
G,
s
ev
er
al
p
r
o
ce
s
s
i
n
g
s
tep
s
ar
e
ad
o
p
te
d
in
o
r
d
er
to
r
ed
u
ce
n
o
is
e
an
d
in
cr
ea
s
e
th
e
p
er
f
o
r
m
a
n
ce
.
T
h
en
,
th
e
g
r
ad
ien
t
m
ag
n
it
u
d
e
(
,
)
an
d
a
n
g
le
o
f
g
r
ad
ien
t
(
,
)
v
ec
to
r
at
ea
ch
p
ix
el
ar
e
co
m
p
u
ted
in
an
8
×
8
p
ix
els
ce
ll,
t
h
i
s
s
tep
is
a
ls
o
ca
lled
g
r
ad
ien
t
co
m
p
u
tat
io
n
.
T
h
e
g
r
ad
ie
n
t
co
m
p
u
tatio
n
o
f
p
ix
el
co
o
r
d
in
ate
at
(
,
)
is
f
o
m
u
lated
as
f
o
llo
w
s
:
∆
=
|
(
−
1
,
)
−
(
+
1
,
)
|
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
R
ice
s
ee
d
ima
g
e
cla
s
s
ifi
ca
tio
n
b
a
s
ed
o
n
HOG
d
escr
ip
to
r
…
(
Hu
y
N
g
u
ye
n
-
Qu
o
c
)
1899
∆
=
|
(
,
−
1
)
−
(
,
+
1
)
|
(
2
)
(
,
)
=
√
∆
2
+
∆
2
(
3
)
(
,
)
=
(
∆
∆
)
(
4
)
w
h
e
r
e
,
g
r
ay
s
c
a
l
e
v
al
u
e
a
t
c
o
o
r
d
i
n
a
te
(
,
)
i
s
d
efi
n
e
d
a
s
(
,
)
,
∆
a
n
d
∆
a
r
e
h
o
r
i
z
o
n
t
al
a
n
d
v
e
r
ti
c
a
l
g
r
a
d
i
en
t
.
T
h
e
d
im
en
s
io
n
o
f
HOG
f
ea
t
u
r
e
v
ec
to
r
d
ep
en
d
s
o
n
th
e
ce
ll
s
ize
an
d
th
e
n
u
m
b
er
o
f
b
in
o
r
ien
tatio
n
u
s
ed
f
o
r
b
u
ild
in
g
th
e
i
n
ter
v
a
ls
o
f
th
e
an
g
les
o
f
t
h
e
g
r
ad
ien
t.
6
4
a
d
o
p
ted
g
r
ad
ien
t
f
ea
t
u
r
es
ar
e
d
iv
id
ed
in
to
9
-
b
in
h
is
to
g
r
a
m
w
h
ic
h
is
m
ai
n
l
y
u
s
ed
to
b
u
ild
t
h
e
in
ter
v
a
ls
o
f
t
h
e
an
g
le
s
o
f
th
e
g
r
ad
ie
n
t
f
r
o
m
0
to
1
8
0
d
eg
r
ee
s
f
o
r
u
n
s
i
g
n
ed
g
r
ad
ien
ts
(
o
r
f
r
o
m
0
to
3
6
0
d
eg
r
ee
s
in
ca
s
e
o
f
s
ig
n
e
d
g
r
ad
i
en
ts
)
.
So
,
th
er
e
w
ill
b
e
2
0
d
eg
r
ee
s
p
er
b
in
.
Fo
r
ea
c
h
g
r
ad
ien
t
f
ea
t
u
r
e,
its
m
a
g
n
it
u
d
e
w
ill
b
e
ad
d
ed
in
to
th
e
co
r
r
esp
o
n
d
in
g
an
g
le
in
th
e
h
is
to
g
r
a
m
.
Fi
n
all
y
,
h
is
to
g
r
a
m
f
r
o
m
a
ll
b
lo
ck
(
ea
ch
b
lo
ck
co
n
tai
n
s
2
×2
ce
lls
a
n
d
h
a
s
5
0
%
o
v
er
lap
)
ar
e
n
o
r
m
alize
d
a
n
d
co
m
b
i
n
ed
i
n
t
o
a
f
ea
t
u
r
e
v
ec
to
r
.
T
h
is
d
escr
i
p
to
r
h
as
b
ee
n
ap
p
lied
in
v
ar
io
u
s
ap
p
licatio
n
s
s
u
ch
as
f
ac
e
r
ec
o
g
n
itio
n
[
2
9
,
30
]
,
c
o
m
p
u
ter
-
aid
ed
d
iag
n
o
s
is
o
f
tu
b
er
cu
lo
s
i
s
[
3
1
]
,
m
ed
ical
i
m
ag
e
a
n
al
y
s
i
s
[
3
2
]
an
d
tr
af
f
ic
an
al
y
s
is
[
3
3
].
2
.
2
.
M
is
s
ing
v
a
lue i
m
pu
t
a
t
io
n
m
et
ho
ds
W
e
p
r
o
p
o
s
e
to
a
d
o
p
t th
r
ee
m
i
s
s
in
g
v
a
lu
e
i
m
p
u
tatio
n
m
et
h
o
d
s
w
h
ic
h
is
p
r
ese
n
ted
in
t
h
e
f
o
ll
o
w
i
n
g
.
KNN
i
m
p
u
tatio
n
(
KNNI
)
is
a
n
i
m
p
u
tatio
n
m
eth
o
d
b
ased
o
n
th
e
K
-
n
ea
r
est
n
ei
g
h
b
o
r
s
’
al
g
o
r
ith
m
b
y
u
s
i
n
g
th
e
co
r
r
elatio
n
s
tr
u
ct
u
r
e
o
f
th
e
d
ata.
T
h
e
m
i
s
s
i
n
g
v
al
u
e
is
i
m
p
u
ted
b
y
ta
k
e
th
e
w
ei
g
h
ted
m
ea
n
o
f
K
n
ea
r
est
v
alu
e
s
[
3
4,
35
]
.
T
h
is
m
et
h
o
d
is
m
o
s
tl
y
u
s
ed
th
a
n
m
ea
n
i
m
p
u
tat
io
n
a
n
d
o
th
er
m
et
h
o
d
s
b
ec
au
s
e
i
t
ca
n
h
an
d
le
b
o
th
ca
teg
o
r
ical
d
ata
an
d
co
n
ti
n
u
o
u
s
d
ata
w
it
h
m
u
ltip
le
m
is
s
i
n
g
v
al
u
es
a
n
d
h
ig
h
er
ac
c
u
r
ac
y
.
B
ased
o
n
B
r
an
d
en
an
d
Ver
b
o
v
en
,
w
e
ad
o
p
t K
=
1
0
.
L
i
n
ea
r
in
ter
p
o
latio
n
is
a
m
et
h
o
d
o
f
co
n
s
tr
u
cti
n
g
n
e
w
d
ata
p
o
in
t
b
ased
o
n
k
n
o
w
n
d
ata
p
o
in
ts
.
I
t
is
o
n
e
o
f
t
h
e
s
i
m
p
le
s
t
i
n
ter
p
o
latio
n
m
et
h
o
d
s
b
y
tak
in
g
t
w
o
k
n
o
wn
d
ata
p
o
in
ts
to
co
m
p
u
te
t
h
e
m
i
s
s
i
n
g
v
al
u
e.
T
h
e
lin
ea
r
in
ter
p
o
latio
n
at
th
e
p
o
in
t
(
,
)
ca
n
b
e
f
o
r
m
u
lated
as:
=
+
(
−
)
−
−
(
5
)
w
h
er
e,
(
,
)
an
d
C
(
,
)
ar
e
k
n
o
w
n
p
o
in
ts
.
is
u
s
u
al
l
y
b
et
w
ee
n
an
d
.
Z
er
o
i
m
p
u
tat
io
n
is
a
s
i
m
p
le
s
t
m
et
h
o
d
th
at
th
e
m
is
s
in
g
v
al
u
es
ar
e
s
u
b
s
tit
u
ted
b
y
ze
r
o
.
T
h
e
ai
m
s
o
f
t
h
i
s
m
et
h
o
d
ar
e
to
f
u
ll
y
ca
p
t
u
r
e
all
ax
es o
f
f
ea
t
u
r
e
v
ec
to
r
.
3.
RE
SU
L
T
S AN
D
AN
AL
Y
SI
S
3
.
1
.
Da
t
a
s
et
W
e
u
s
e
t
h
e
b
e
n
ch
m
a
r
k
r
i
ce
s
ee
d
(
V
N
R
I
C
E
)
d
a
t
as
e
t
w
h
i
ch
co
n
s
i
s
t
s
o
f
s
i
x
c
o
m
m
o
n
V
ie
tn
am
r
i
c
e
s
e
e
d
v
a
r
i
et
i
es
,
in
cl
u
d
i
n
g
B
C
-
1
5
,
Hu
o
n
g
T
h
o
m
-
1
,
N
e
p
-
8
7
,
Q
-
5
,
T
h
i
e
n
Uu
-
8
,
X
i
-
2
3
.
T
h
es
e
r
ice
s
e
e
d
s
a
r
e
s
am
p
l
e
d
f
r
o
m
a
r
i
ce
s
e
e
d
p
r
o
d
u
c
ti
o
n
co
m
p
an
y
w
h
e
r
e
t
h
e
r
i
ce
v
a
r
ie
ti
e
s
w
e
r
e
g
r
o
w
n
an
d
h
a
r
v
e
s
ted
f
o
l
l
o
w
in
g
c
e
r
t
ai
n
c
o
n
d
i
ti
o
n
s
f
o
r
s
t
an
d
a
r
d
r
i
c
e
s
ee
d
s
p
r
o
d
u
ct
i
o
n
.
A
ll
im
ag
es
a
r
e
a
c
q
u
i
r
e
d
b
y
a
C
M
OS
im
ag
e
s
e
n
s
o
r
c
o
l
o
r
c
am
e
r
a
.
F
ig
u
r
e
1
s
h
o
w
s
ex
am
p
l
e
im
ag
e
s
f
r
o
m
th
i
s
d
at
a
s
e
t
.
E
a
ch
c
o
lu
m
n
i
ll
u
s
t
r
at
e
s
e
a
ch
c
a
te
g
o
r
y
o
f
V
NR
I
C
E
d
a
t
as
e
t.
W
e
s
e
e
th
a
t
th
is
is
r
e
a
l
ly
a
ch
a
ll
e
n
g
e
ta
s
k
ev
en
f
o
r
h
u
m
an
s
in
ce
t
h
e
im
ag
e
s
l
o
o
k
s
im
il
a
r
.
T
h
e
k
-
n
e
a
r
es
t
n
e
ig
h
b
o
r
(
k
N
N
)
c
l
ass
ifi
e
r
as
s
o
ci
a
t
e
d
w
it
h
th
e
L
1
-
d
is
t
an
c
e
an
d
th
e
SV
M
c
la
s
s
ifi
e
r
a
r
e
c
o
n
s
i
d
e
r
e
d
i
n
o
r
d
e
r
t
o
cl
a
s
s
if
y
t
h
e
r
i
c
e
s
ee
d
im
ag
es
.
T
h
e
a
ch
i
ev
em
en
t
o
f
th
e
c
l
ass
ifi
c
a
t
i
o
n
i
s
m
ea
s
u
r
e
d
b
y
th
e
ac
cu
r
ac
y
r
at
e
w
h
i
ch
w
as
p
e
r
f
o
r
m
e
d
b
y
s
p
li
t
-
s
am
p
l
e
v
al
i
d
a
t
i
o
n
w
i
th
h
o
l
d
o
u
t
s
am
p
l
in
g
.
A
h
alf
o
f
th
e
d
at
a
w
er
e
u
s
e
d
as
th
e
in
p
u
t
o
f
th
e
cl
a
s
s
ifi
e
r
t
o
b
u
il
d
th
e
t
r
ai
n
in
g
m
o
d
e
l
w
h
i
l
e
th
e
r
es
t
w
e
r
e
u
s
e
d
t
o
t
es
t
i
t
.
T
a
b
l
e
1
p
r
e
s
en
t
t
h
e
ch
a
r
a
c
t
e
r
i
s
t
ic
o
f
V
NR
I
C
E
d
a
t
as
e
t
v
i
a
s
p
l
i
t
-
s
am
p
l
e
v
al
i
d
a
ti
o
n
m
eth
o
d
.
T
ab
le
1
.
C
h
ar
ac
ter
is
tic
o
f
VN
R
I
C
E
d
ataset
R
i
c
e
v
a
r
i
e
t
y
#
T
r
a
i
n
i
n
g
se
t
#
T
e
st
i
n
g
se
t
T
o
t
a
l
i
mag
e
s
BC
-
15
9
1
7
9
1
7
1
,
8
3
4
H
u
o
n
g
T
h
o
m
-
1
1
,
0
4
8
1
,
0
4
8
2
,
0
9
6
N
e
p
-
87
6
9
9
7
0
0
1
,
3
9
9
Q
-
5
9
6
2
9
6
2
1
,
9
2
4
T
h
i
e
n
U
u
-
8
5
1
3
5
1
3
1
,
0
2
6
Xi
-
23
1
,
1
1
3
1
,
1
1
3
2
,
2
2
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
9
7
-
1
9
0
3
1900
Fig
u
r
e
1
.
E
x
a
m
p
le
i
m
ag
e
s
f
r
o
m
s
i
x
r
ice
s
ee
d
v
ar
ietie
s
3
.
2
.
E
x
peri
m
ent
a
l
s
et
up
a
n
d
re
s
ults
M
o
s
t
c
l
as
s
ifi
e
r
s
r
e
q
u
i
r
e
th
e
s
am
e
d
im
en
s
i
o
n
o
f
in
p
u
t
t
r
a
in
in
g
d
at
a
w
h
il
e
th
e
HO
G
f
e
a
tu
r
e
v
e
c
t
o
r
s
a
r
e
m
a
in
ly
d
e
p
en
d
e
d
o
n
th
e
im
ag
e
s
i
z
e
.
T
h
e
V
NR
I
C
E
d
a
t
as
e
t
c
o
n
t
ai
n
s
m
an
y
im
ag
e
s
w
i
th
d
if
f
er
e
n
t
s
i
z
es
.
W
e
fi
r
s
t
r
e
s
i
z
e
al
l
th
e
im
ag
e
s
in
t
o
th
e
s
am
e
s
i
z
e
b
ef
o
r
e
ex
t
r
a
ct
in
g
th
e
H
O
G
f
e
at
u
r
e
s
.
T
h
e
m
in
im
u
m
an
d
m
ax
im
u
m
o
f
h
e
ig
h
t
(
)
a
n
d
w
i
d
th
(
)
o
f
r
ic
e
im
ag
es
f
r
o
m
VNR
I
C
E
a
r
e
=
169
,
=
46
,
=
380
,
=
103
.
T
h
e
class
i
fi
ca
tio
n
r
es
u
lts
ar
e
p
r
esen
ted
in
T
ab
le
2
b
y
t
w
o
cla
s
s
i
fi
er
s
.
T
h
e
s
ec
o
n
d
co
lu
m
n
r
ep
r
esen
ts
t
h
e
h
ei
g
h
t
an
d
w
id
t
h
o
f
i
m
ag
e
s
af
ter
p
r
o
ce
s
s
in
g
w
it
h
r
an
d
o
m
s
ize
s
.
T
h
e
th
ir
d
co
lu
m
n
s
h
o
w
s
t
h
e
d
i
m
en
s
io
n
o
f
HO
G
f
ea
t
u
r
es
o
b
tain
ed
co
r
r
esp
o
n
d
in
g
w
it
h
th
e
r
esized
i
m
a
g
e.
T
h
e
6
-
NN
clas
s
i
fi
er
is
co
n
s
id
er
e
d
s
in
ce
it
g
i
v
es
t
h
e
b
est p
er
f
o
r
m
a
n
ce
i
n
r
an
g
e
o
f
k
∈
{1
,
2
,
.
.
,
5
0
}.
T
ab
le
2
.
A
cc
u
r
ac
y
o
n
t
h
e
VN
R
I
C
E
d
ataset
w
it
h
r
an
d
o
m
s
el
ec
ted
i
m
ag
e
s
s
ize
N
o
.
I
mag
e
si
z
e
D
i
me
n
si
o
n
o
f
HOG
f
e
a
t
u
r
e
v
e
c
t
o
r
6
-
NN
(
%)
S
V
M
(
%)
1
4
6
×
4
6
5
7
6
7
2
.
7
3
7
4
.
7
2
2
5
0
×
1
0
0
1
,
9
8
0
7
7
.
1
4
6
5
.
1
0
3
4
6
×
1
6
9
2
,
8
8
0
7
6
.
2
9
6
9
.
6
3
4
1
0
3
×
1
0
3
4
,
3
5
6
7
8
.
4
3
7
4
.
9
9
5
4
6
×
3
8
0
6
,
6
2
4
7
4
.
8
5
7
7
.
7
0
6
1
0
0
×
1
5
0
6
,
7
3
2
7
8
.
5
4
8
0
.
5
2
7
7
7
×
2
2
9
7
,
7
7
6
7
7
.
9
1
8
1
.
8
8
8
7
9
×
2
2
8
7
,
7
7
6
7
7
.
4
9
8
1
.
9
6
9
1
0
3
×
1
6
9
7
,
9
2
0
8
0
.
0
8
8
2
.
0
8
10
1
0
1
×
3
0
0
1
4
,
2
5
6
7
7
.
2
5
8
5
.
1
9
11
1
6
9
×
1
6
9
1
4
,
4
0
0
7
9
.
6
2
8
3
.
5
8
12
1
0
3
×
3
8
0
1
8
,
2
1
6
7
5
.
7
4
8
6
.
2
3
13
1
2
0
×
4
0
0
2
4
,
6
9
6
7
5
.
5
1
8
6
.
9
5
14
3
8
0
×
3
8
0
7
6
,
1
7
6
7
8
.
3
0
8
5
.
8
9
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
7
7
.
1
3
7
9
.
7
4
W
e
o
b
s
er
v
e
th
at
th
e
b
est
ac
cu
r
ac
y
i
s
r
ea
ch
ed
w
h
e
n
w
e
r
esiz
e
i
m
ag
e
to
1
0
3
×1
6
9
f
o
r
6
-
NN
class
i
fi
er
an
d
1
2
0
×4
0
0
f
o
r
SVM
cla
s
s
i
fi
er
.
I
t
is
i
m
p
o
s
s
ib
le
to
d
ete
r
m
in
e
w
h
ic
h
s
ize
i
s
o
p
ti
m
a
l
to
tr
an
s
f
o
r
m
a
f
ter
1
4
tr
ials
.
A
d
d
itio
n
all
y
,
t
h
e
d
i
m
e
n
s
io
n
s
p
ac
e
o
f
H
OG
f
ea
t
u
r
es
i
n
cr
ea
s
e
s
w
h
e
n
t
h
e
i
m
a
g
e
s
ize
i
s
b
ig
g
er
.
I
n
o
r
d
er
to
a
p
p
ly
th
e
m
is
s
in
g
v
alu
e
i
m
p
u
ta
tio
n
,
w
e
ex
tr
ac
t
t
h
e
HOG
f
ea
t
u
r
es
f
ea
t
u
r
es
f
r
o
m
t
h
e
o
r
ig
i
n
al
i
m
a
g
e
w
it
h
r
an
d
o
m
s
izes.
T
h
e
d
i
m
e
n
s
io
n
o
f
s
h
o
r
test
an
d
lo
n
g
e
s
t
v
ec
to
r
is
3
,
8
8
8
an
d
1
2
,
6
3
6
r
esp
ec
tiv
el
y
.
T
h
e
t
h
r
ee
i
m
p
u
ta
tio
n
m
et
h
o
d
s
p
r
ese
n
ted
in
s
ec
tio
n
2
ar
e
th
e
n
ap
p
lied
to
fill
t
h
e
m
is
s
i
n
g
v
al
u
es.
I
t
is
w
o
r
t
h
to
n
o
te
t
h
at
th
e
i
m
p
u
tatio
n
s
ta
g
e
i
s
b
e
f
o
r
e
th
e
cr
o
s
s
v
alid
atio
n
,
s
o
t
h
ese
m
eth
o
d
s
ar
e
also
i
n
u
n
s
u
p
er
v
is
ed
lear
n
i
n
g
co
n
tex
t.
All
f
ea
t
u
r
e
v
ec
to
r
s
a
r
e
t
h
e
n
as
s
i
g
n
ed
all
m
is
s
in
g
v
alu
e
s
a
s
NaN
(
n
o
t
a
n
u
m
b
e
r
)
f
r
o
m
it
s
o
r
ig
in
a
l
len
g
th
to
1
2
,
6
3
6
.
Fo
r
ze
r
o
im
p
u
tatio
n
,
it
j
u
s
t
s
i
m
p
l
y
r
ep
lace
s
all
NaN
s
b
y
0
.
W
h
en
u
s
i
n
g
KNN
i
m
p
u
tatio
n
m
et
h
o
d
,
it
r
eq
u
ir
es
at
least
o
n
e
co
m
p
leted
f
ea
tu
r
e
v
ec
to
r
to
fill
t
h
e
m
is
s
i
n
g
v
a
l
u
es.
I
n
ca
s
e
o
f
lin
ea
r
in
ter
p
o
latio
n
m
et
h
o
d
,
at
least
t
w
o
v
ec
to
r
s
ar
e
r
eq
u
ir
ed
in
o
r
d
e
r
to
p
r
o
ce
ed
.
Fig
u
r
e
2
illu
s
tr
ates
t
h
e
ac
cu
r
ac
y
o
f
t
h
r
ee
i
m
p
u
ta
tio
n
m
et
h
o
d
s
o
n
VNRI
C
E
d
ataset
b
y
6
-
N
N
clas
s
i
fi
er
.
T
h
e
o
r
ig
in
al
d
i
m
en
s
io
n
is
b
a
s
ed
o
n
t
h
e
s
h
o
r
test
v
ec
to
r
w
it
h
3
,
8
8
8
f
ea
tu
r
es.
T
h
e
m
is
s
i
n
g
v
al
u
es
ar
e
fi
lled
b
y
1
0
0
f
ea
t
u
r
es
ea
c
h
ti
m
e.
Fro
m
t
h
i
s
ch
ar
t,
w
e
s
e
e
th
at
l
in
ea
r
i
n
ter
p
o
latio
n
clea
r
l
y
o
u
tp
er
f
o
r
m
s
th
a
n
t
w
o
o
th
er
m
et
h
o
d
s
.
S
u
r
p
r
is
in
g
l
y
,
t
h
e
ze
r
o
i
m
p
u
ta
tio
n
g
i
v
es
b
etter
r
esu
lts
t
h
a
n
1
0
-
NN
i
m
p
u
tat
io
n
m
eth
o
d
f
r
o
m
7
,
8
8
8
f
ea
tu
r
es.
F
u
r
t
h
er
m
o
r
e,
T
ab
le
s
3
an
d
4
d
etail
th
e
cla
s
s
i
ficatio
n
p
er
f
o
r
m
a
n
c
e
o
f
ea
c
h
m
et
h
o
d
o
n
th
r
ee
d
if
f
er
en
t
d
i
m
e
n
s
io
n
s
.
L
in
ea
r
i
n
ter
p
o
latio
n
m
et
h
o
d
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
R
ice
s
ee
d
ima
g
e
cla
s
s
ifi
ca
tio
n
b
a
s
ed
o
n
HOG
d
escr
ip
to
r
…
(
Hu
y
N
g
u
ye
n
-
Qu
o
c
)
1901
w
it
h
SVM
cla
s
s
i
fier
g
iv
e
s
t
h
e
b
est
ac
c
u
r
ac
y
w
it
h
9
9
.
9
4
%.
W
e
i
m
p
r
o
v
e
m
o
r
e
t
h
an
2
0
%
co
m
p
ar
ed
to
th
e
av
er
a
g
e
ac
cu
r
ac
y
w
it
h
r
an
d
o
m
r
esized
i
m
ag
e
i
n
T
ab
le
2
.
Fig
u
r
e
2
.
Fil
l
m
i
s
s
i
n
g
v
al
u
es
m
et
h
o
d
s
ex
p
er
i
m
e
n
t r
es
u
lt
s
ch
ar
t
T
ab
le
3
.
T
h
e
d
etailed
class
ifi
c
atio
n
p
er
f
o
r
m
a
n
ce
o
f
th
r
ee
m
i
s
s
i
n
g
v
al
u
e
i
m
p
u
ta
tio
n
m
et
h
o
d
s
o
n
th
r
ee
d
if
f
er
en
t d
i
m
en
s
io
n
s
N
u
mb
e
r
of
d
i
me
n
s
i
o
n
s
3
,
8
8
8
8
,
8
8
8
1
1
,
2
8
8
A
c
c
u
r
a
c
y
(
%)
10
-
N
N
i
mp
u
t
a
t
i
o
n
7
6
.
9
7
8
2
.
5
3
8
3
.
0
6
Z
e
r
o
i
mp
u
t
a
t
i
o
n
7
6
.
9
7
8
3
.
8
5
8
3
.
8
2
L
i
n
e
a
r
i
n
t
e
r
p
o
l
a
t
i
o
n
7
6
.
9
7
9
0
.
0
0
9
9
.
6
1
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
th
r
ee
i
m
p
u
tat
io
n
m
eth
o
d
o
n
r
an
d
o
m
s
elec
ted
d
i
m
e
n
s
io
n
I
mag
e
si
z
e
F
i
l
l
mi
ssi
n
g
v
a
l
u
e
s me
t
h
o
d
N
u
mb
e
r
o
f
d
i
me
n
s
i
o
n
s
A
c
c
u
r
a
c
y
(
%)
6
-
NN
S
V
M
O
r
i
g
i
n
a
l
i
mag
e
w
i
t
h
r
a
n
d
o
m
si
z
e
s
Z
e
r
o
i
mp
u
t
a
t
i
o
n
9
,
0
0
0
8
3
.
4
7
8
3
.
6
0
1
2
,
6
3
6
8
3
.
9
0
8
3
.
4
1
1
5
,
0
0
0
8
3
.
6
5
8
3
.
1
4
10
-
NN
i
mp
u
t
a
t
i
o
n
9
,
0
0
0
8
2
.
3
4
8
3
.
9
3
1
2
,
6
3
6
8
2
.
8
1
8
4
.
2
3
L
i
n
e
a
r
i
n
t
e
r
p
o
l
a
t
i
o
n
9
,
0
0
0
9
0
.
7
8
9
8
.
5
2
1
1
,
3
4
0
9
9
.
6
6
9
9
.
9
4
4.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
p
r
o
p
o
s
e
to
ap
p
ly
s
ev
er
al
m
i
s
s
i
n
g
v
al
u
e
i
m
p
u
tatio
n
m
et
h
o
d
s
to
tack
le
th
e
i
m
a
g
e
s
iz
e
o
f
HOG
d
escr
ip
to
r
.
B
y
u
s
i
n
g
th
r
ee
m
i
s
s
i
n
g
v
al
u
e
i
m
p
u
tatio
n
m
et
h
o
d
s
,
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
is
ef
fi
cie
n
t
b
y
clea
r
l
y
i
m
p
r
o
v
in
g
t
h
e
cla
s
s
i
fic
atio
n
p
er
f
o
r
m
a
n
ce
o
n
VNRI
C
E
i
m
a
g
e
d
ataset.
T
h
e
f
u
t
u
r
e
o
f
t
h
is
w
o
r
k
is
n
o
w
co
n
tin
u
ed
to
ap
p
ly
t
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
to
o
th
er
ty
p
e
s
o
f
tex
t
u
al
d
ata.
Sin
ce
t
h
e
fi
ll
ed
v
alu
e
m
ig
h
t
b
e
n
o
is
ed
a
n
d
ir
r
elev
a
n
t,
w
e
f
u
r
t
h
er
p
r
o
p
o
s
e
to
ap
p
ly
f
ea
tu
r
e
s
elec
tio
n
m
e
th
o
d
to
r
e
m
o
v
e
t
h
e
n
o
is
ed
f
ea
t
u
r
es
f
r
o
m
i
m
p
u
tat
io
n
m
eth
o
d
.
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
w
o
r
k
w
a
s
s
u
p
p
o
r
ted
b
y
Ho
C
h
i
Mi
n
h
C
it
y
Op
e
n
U
n
iv
er
s
it
y
u
n
d
er
Gr
an
t
No
E
.
2
0
1
9
.
0
6
.
1
.
T
h
e
au
th
o
r
s
al
s
o
w
o
u
ld
li
k
e
t
o
th
an
k
Dr
.
Ho
n
g
P
h
a
n
f
r
o
m
th
e
Vie
tn
a
m
Nat
io
n
al
U
n
i
v
e
r
s
it
y
o
f
Ag
r
icu
l
tu
r
e
f
o
r
p
r
o
v
id
in
g
t
h
e
R
ice
Seed
I
m
ag
e
d
ata
s
et.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6930
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
,
Vo
l.
18
,
No
.
4
,
A
u
g
u
s
t 2
0
2
0
:
1
8
9
7
-
1
9
0
3
1902
RE
F
E
R
E
NC
E
S
[1
]
J.
G
o
m
e
s
a
n
d
F.
L
e
ta
,
“
A
p
p
l
i
c
a
t
i
o
n
s
o
f
c
o
m
p
u
t
e
r
v
i
s
i
o
n
t
e
c
h
n
i
q
u
e
s
i
n
t
h
e
a
g
r
i
c
u
l
t
u
r
e
a
n
d
f
o
o
d
i
n
d
u
s
t
ry
:
A
r
e
v
i
e
w
,
”
E
u
r
o
p
e
a
n
F
o
o
d
R
e
s
e
a
r
c
h
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
3
5
,
p
p
.
9
8
9
–
1
0
0
0
,
2
0
1
4
.
[2
]
D.
I.
P
a
t
r
i
c
i
o
a
n
d
R.
R
ie
d
e
r
,
“
Co
m
p
u
t
e
r
v
is
i
o
n
a
n
d
a
r
t
ifi
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
p
re
c
i
s
i
o
n
a
g
r
i
c
u
l
t
u
r
e
fo
r
g
ra
i
n
c
r
o
p
s
:
A
sy
s
t
e
m
a
t
ic
r
e
v
i
e
w
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
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.
1
5
3
,
p
p
.
6
9
–
81
,
2
0
1
8
.
[3
]
A
.
C
.
T
y
a
g
i
,
“
T
o
w
a
r
d
s
a
s
e
c
o
n
d
g
re
e
n
r
e
v
o
l
u
t
i
o
n
,
”
I
r
r
i
g
a
t
i
o
n
a
n
d
D
r
a
i
n
a
g
e
,
v
o
l
.
6
5
,
n
o
.
4
,
p
p
.
3
8
8
–
3
8
9
,
2
0
1
6
.
[4
]
A
.
H
u
m
e
a
u
-
H
e
u
r
t
ie
r
,
“
T
e
x
t
u
r
e
f
e
a
tu
r
e
e
x
t
ra
c
t
i
o
n
m
e
t
h
o
d
s
:
A
s
u
rv
e
y
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
7
,
p
p
.
8
9
7
5
–
9
0
0
0
,
2
0
1
9
.
[5
]
C.
F
.
T
s
a
i
,
M
.
L
.
L
i
,
a
n
d
W
.
C
.
L
in
,
“
A
c
la
s
s
c
e
n
te
r
b
a
se
d
a
p
p
r
o
a
c
h
f
o
r
m
i
s
s
i
n
g
v
a
l
u
e
im
p
u
ta
t
i
o
n
,
”
K
n
o
w
l
e
d
g
e
-
B
a
s
e
d
S
y
s
t
e
ms
,
v
o
l
.
1
5
1
,
p
p
.
1
2
4
–
1
3
5
,
J
u
l
2
0
1
8
.
[6
]
A
.
S
i
n
h
a
,
S
.
Ba
n
e
r
j
i
,
a
n
d
C
.
L
i
u
,
“
N
o
v
e
l
c
o
l
o
r
G
a
b
o
r
-
L
B
P
-
P
H
O
G
(G
L
P
)
d
e
s
c
r
i
p
t
o
r
s
f
o
r
o
b
j
e
c
t
a
n
d
s
c
e
n
e
im
a
g
e
c
l
a
ss
ifi
c
a
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
E
i
g
h
t
h
I
n
d
i
a
n
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
s
i
o
n
,
G
r
a
p
h
i
c
s
a
n
d
I
m
a
g
e
P
r
o
c
e
s
s
i
n
g
,
n
o
.
5
8
,
p
p
.
1
-
8
,
2
0
1
2
.
[7
]
P
.
Va
c
h
a
,
M
.
H
a
i
n
d
l
,
a
n
d
T
.
S
u
k
,
“
C
o
l
o
u
r
a
n
d
r
o
t
a
t
i
o
n
i
n
v
a
r
i
a
n
t
t
e
x
t
u
r
a
l
f
e
a
t
u
r
e
s
b
a
s
e
d
o
n
M
a
r
k
o
v
ra
n
d
o
m
fi
e
l
d
s
,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
L
e
t
t
e
r
s
,
v
o
l
.
3
2
,
n
o
.
6
,
p
p
.
7
7
1
–
7
7
9
,
A
p
r
2
0
1
1
.
[8
]
A
.
B
o
s
c
h
,
A
.
Z
i
s
se
rm
a
n
,
a
n
d
X.
M
u
ñ
o
z
,
“
S
c
e
n
e
c
l
a
ss
ifi
c
a
t
i
o
n
v
i
a
p
L
S
A
,
”
E
u
r
o
p
e
a
n
c
o
n
f
e
r
e
n
c
e
o
n
c
o
m
p
u
t
e
r
v
is
i
o
n
,
S
p
r
i
n
g
e
r
,
p
p
.
5
1
7
–
5
3
0
,
2
0
0
6
.
[9
]
A
.
S
i
n
h
a
,
S
.
B
a
n
e
r
j
i
,
a
n
d
C
.
L
i
u
,
“
N
e
w
c
o
l
o
r
G
P
H
OG
d
e
s
c
r
i
p
t
o
r
s
f
o
r
o
b
j
e
c
t
a
n
d
s
c
e
n
e
im
a
g
e
c
la
s
s
ifi
c
a
t
i
o
n
,
”
M
a
c
h
i
n
e
V
i
s
i
o
n
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
5
,
n
o
.
2
,
p
p
.
3
6
1
–
3
7
5
,
F
e
b
2
0
1
4
.
[1
0
]
R
.
K
h
a
n
,
J
.
v
a
n
d
e
W
e
i
j
e
r
,
F
.
S
.
K
h
a
n
,
D
.
M
u
s
e
l
e
t
,
C
.
D
u
c
o
t
t
e
t
,
a
n
d
C
.
B
a
r
a
t
,
“
D
i
s
c
r
i
m
i
n
a
t
i
v
e
c
o
l
o
r
d
e
s
c
r
i
p
t
o
r
s
,
”
P
r
o
c
e
e
d
i
n
g
s
o
f
2
3
t
h
I
E
E
E
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
C
o
m
p
u
t
e
r
V
i
s
i
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
,
p
p
.
2
8
6
6
–
2873
,
2
0
1
3
.
[1
1
]
F
.
S
a
n
d
i
d
a
n
d
A
.
D
o
u
i
k
,
“
R
o
b
u
s
t
c
o
l
o
r
t
e
x
t
u
re
d
e
sc
r
i
p
t
o
r
f
o
r
m
a
te
r
i
a
l
re
c
o
g
n
i
t
i
o
n
,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
L
e
t
t
e
r
s
,
v
o
l
.
8
0
,
p
p
.
1
5
–
2
3
,
S
e
p
2
0
1
6
.
[1
2
]
T
.
M
a
e
n
p
a
a
,
M
.
P
i
e
t
i
k
a
i
n
e
n
,
a
n
d
J
.
Vi
e
r
t
o
l
a
,
“
S
e
p
a
r
a
t
i
n
g
c
o
lo
r
a
n
d
p
a
t
t
e
r
n
i
n
f
o
rm
a
t
i
o
n
f
o
r
c
o
l
o
r
t
e
x
t
u
r
e
d
i
s
c
r
im
i
n
a
t
i
o
n
,
”
O
b
j
e
c
t
re
c
o
g
n
i
t
i
o
n
s
u
p
p
o
r
t
e
d
b
y
u
s
e
r
i
n
t
e
r
a
c
t
i
o
n
f
o
r
s
e
rv
i
c
e
r
o
b
o
t
s
,
2
0
0
2
.
[1
3
]
T
.
M
a
e
n
p
a
a
a
n
d
M
.
P
i
e
t
i
k
¨
a
i
n
e
n
,
“
C
l
a
ss
ifi
c
a
t
i
o
n
w
i
t
h
c
o
l
o
r
a
n
d
t
e
x
tu
r
e
:
j
o
i
n
t
ly
o
r
s
e
p
a
r
a
te
ly
?
”
P
a
t
t
e
rn
R
e
c
o
g
n
i
t
i
o
n
,
v
o
l
.
3
7
,
n
o
.
8
,
p
p
.
1
6
2
9
–
1
6
4
0
,
A
u
g
2
0
0
4
.
[1
4
]
K
.
M
e
e
t
h
o
n
g
j
a
n
,
M
.
Dz
u
i
k
if
l
i
,
P
.
K
.
R
e
e
,
a
n
d
M
.
Y
.
Na
m
,
“
F
u
s
io
n
a
f
f
i
n
e
m
o
m
e
n
t
i
n
v
a
r
ia
n
t
s
a
n
d
w
a
v
e
l
e
t
p
a
c
k
e
t
f
e
a
t
u
r
e
s
s
e
le
c
t
i
o
n
f
o
r
f
a
c
e
v
e
r
if
ica
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
T
h
e
o
r
e
t
i
c
a
l
&
A
p
p
l
i
e
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
4
,
n
o
.
3
,
p
p
.
6
0
6
-
6
1
5
,
2
0
1
4
.
[1
5
]
N
.
D
a
la
l
a
n
d
B
.
T
r
ig
g
s
,
“
H
i
s
t
o
g
r
a
m
s
o
f
o
r
i
e
n
t
e
d
g
r
a
d
i
e
n
t
s
f
o
r
h
u
m
a
n
d
e
t
e
c
t
i
o
n
,
”
2
0
0
5
I
E
E
E
C
o
m
p
u
t
e
r
S
o
c
i
e
t
y
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
s
i
o
n
a
n
d
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
(
C
V
P
R
’
0
5
)
,
v
o
l
.
1
,
p
p
.
8
8
6
–
893
,
J
u
n
e
2
0
0
5
.
[1
6
]
H
.
D
u
o
n
g
a
n
d
V.
T
.
H
o
a
n
g
,
“
D
ime
n
s
i
o
n
a
l
i
ty
re
d
u
c
t
i
o
n
b
a
s
e
d
o
n
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
f
o
r
r
ic
e
v
a
r
ie
t
i
e
s
r
e
c
o
g
n
i
t
i
o
n
,
”
2
0
1
9
4
t
h
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
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
I
n
C
I
T
)
,
p
p
.
1
9
9
–
202
,
O
c
t
2
0
1
9
.
[1
7
]
P.
T
.
T
.
H
o
n
g
,
T.
T
.
T
.
H
a
i
,
L
.
T
.
L
a
n
,
V.
T
.
H
o
a
n
g
,
V.
H
a
i
,
a
n
d
T.
T
.
Ng
u
y
e
n
,
“
C
o
m
p
a
r
a
t
iv
e
s
t
u
d
y
o
n
v
i
s
i
o
n
b
a
s
e
d
r
i
c
e
s
e
e
d
v
a
r
i
e
t
ie
s
i
d
e
n
t
ifi
c
a
t
i
o
n
,
”
2
0
1
5
S
e
v
e
n
t
h
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
K
n
o
w
l
e
d
g
e
a
n
d
S
y
s
t
e
m
s
E
n
g
i
n
e
e
r
i
n
g
(
K
S
E
)
,
p
p
.
3
7
7
–
382
,
2
0
1
5
.
[1
8
]
H
.
Vu
,
V.
N
.
D
u
o
n
g
,
a
n
d
T
.
T
.
Ng
u
y
e
n
,
“
I
n
s
p
e
c
t
i
n
g
r
i
c
e
se
e
d
s
p
e
c
ie
s
p
u
r
i
ty
o
n
a
l
a
rg
e
d
a
t
a
s
e
t
u
s
i
n
g
g
e
o
m
e
t
r
i
c
a
l
a
n
d
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
,
”
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
N
i
n
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
I
n
f
o
r
m
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
-
S
o
I
C
T
2
0
1
8
,
p
p
.
3
2
1
–
328
,
2
0
1
8
.
[1
9
]
B
.
L
u
r
s
tw
u
t
a
n
d
C
.
P
o
r
n
p
a
n
o
m
c
h
a
i
,
“
Im
a
g
e
a
n
a
ly
s
is
b
a
s
e
d
o
n
c
o
l
o
r
,
s
h
a
p
e
a
n
d
t
e
x
t
u
r
e
f
o
r
r
i
c
e
se
e
d
(O
ry
z
a
sa
t
i
v
a
L
.
)
g
e
rm
i
n
a
t
i
o
n
e
v
a
l
u
a
t
i
o
n
,
”
A
g
r
i
c
u
l
t
u
r
e
a
n
d
N
a
t
u
r
a
l
R
e
s
o
u
r
c
e
s
,
v
o
l
.
5
1
,
n
o
.
5
,
p
p
.
3
8
3
–
3
8
9
,
O
c
t
2
0
1
7
.
[2
0
]
H
.
M
e
b
a
t
s
i
o
n
,
J
.
P
a
l
iw
a
l
,
a
n
d
D
.
Ja
y
a
s
,
“
A
u
t
o
m
a
t
ic
c
la
s
s
ifi
c
a
t
i
o
n
o
f
n
o
n
-
t
o
u
c
h
i
n
g
c
e
re
a
l
g
r
a
i
n
s i
n
d
i
g
i
ta
l
im
a
g
e
s
u
s
i
n
g
l
im
i
t
e
d
m
o
r
p
h
o
l
o
g
i
c
a
l
a
n
d
c
o
l
o
r
f
e
a
t
u
r
e
s
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
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
.
9
0
,
p
p
.
9
9
–
1
0
5
,
J
a
n
2
0
1
3
.
[2
1
]
P
.
M
.
S
z
c
z
y
p
i´
n
sk
i
,
A
.
K
l
e
p
a
c
z
k
o
,
a
n
d
P
.
Z
a
p
o
t
o
c
z
n
y
,
“
I
d
e
n
t
if
y
i
n
g
b
a
r
l
e
y
v
a
r
i
e
t
i
e
s
b
y
c
o
m
p
u
t
e
r
v
i
s
i
o
n
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
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.
1
1
0
,
p
p
.
1
–
8
,
J
a
n
.
2
0
1
5
.
[2
2
]
A
.
A
.
C
h
a
u
g
u
l
e
a
n
d
S
.
N
.
M
a
l
i
,
“
Id
e
n
t
i
fi
c
a
t
i
o
n
o
f
p
a
d
d
y
v
a
r
ie
t
i
e
s b
a
s
e
d
o
n
n
o
v
e
l
s
e
e
d
a
n
g
le
f
e
a
t
u
r
e
s
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
re
,
v
o
l
.
1
2
3
,
p
p
.
4
1
5
–
4
2
2
,
2
0
1
6
.
[2
3
]
T
.
Y
.
K
u
o
,
C
.
L
.
C
h
u
n
g
,
S
.
Y
.
C
h
e
n
,
H
.
A
.
L
i
n
,
a
n
d
Y
.
F
.
K
u
o
,
“
I
d
e
n
t
i
f
y
i
n
g
r
i
c
e
g
r
a
i
n
s
u
s
i
n
g
i
m
a
g
e
a
n
a
l
y
s
i
s
a
n
d
s
p
a
r
s
e
-
r
e
p
r
e
s
e
n
t
a
t
i
o
n
-
b
a
s
e
d
c
l
a
s
s
i
fi
c
a
t
i
o
n
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
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
.
1
2
7
,
p
p
.
7
1
6
–
7
2
5
,
S
e
p
2
0
1
6
.
[2
4
]
H
.
l
i
,
Y
.
Q
i
a
n
,
P
.
C
a
o
,
W
.
Y
i
n
,
F
.
D
a
i
,
F
.
H
u
,
a
n
d
Z
.
Y
a
n
,
“
C
a
lc
u
l
a
t
i
o
n
m
e
t
h
o
d
o
f
s
u
rf
a
c
e
s
h
a
p
e
f
e
a
tu
r
e
o
f
r
i
c
e
s
e
e
d
b
a
s
e
d
o
n
p
o
i
n
t
c
l
o
u
d
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
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.
1
4
2
,
p
p
.
4
1
6
–
4
2
3
,
N
o
v
.
2
0
1
7
.
[2
5
]
D
.
P
.
V.
H
o
a
i
,
T
.
S
u
r
i
n
w
a
r
a
n
g
k
o
o
n
,
V.
T
.
H
o
a
n
g
,
H
.
-
T
.
D
u
o
n
g
,
K
.
M
e
e
t
h
o
n
g
j
a
n
,
“
A
c
o
m
p
a
r
a
t
iv
e
s
t
u
d
y
o
f
r
ic
e
v
a
r
i
e
ty
c
l
a
ss
if
i
c
a
t
i
o
n
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
a
n
d
h
a
n
d
-
c
r
a
f
t
e
d
f
e
a
t
u
r
e
s
”
,
EC
T
I
T
r
a
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
e
r
An
d
I
n
f
o
r
m
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
4
,
n
o
.
1
,
2
0
2
0
.
[2
6
]
P.
J
.
G
a
r
c
ıa
L
a
e
n
c
i
n
a
,
J
.
L
.
S
a
n
c
h
o
G
ó
m
e
z
,
a
n
d
A
.
R
.
F
i
g
u
e
ir
a
s
Vi
d
a
l
,
“
P
a
t
t
e
r
n
c
l
a
s
s
ifi
c
a
t
i
o
n
w
i
t
h
m
is
s
i
n
g
d
a
t
a
:
a
r
e
v
iew
,
”
N
e
u
r
a
l
C
o
m
p
u
t
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
2
6
3
–
2
8
2
,
M
a
r
2
0
1
0
.
[2
7
]
A
.
M
.
S
e
fi
d
i
a
n
a
n
d
N
.
D
a
n
e
s
h
p
o
u
r
,
“
M
i
s
s
i
n
g
v
a
l
u
e
i
m
p
u
t
a
t
i
o
n
u
s
i
n
g
a
n
o
v
e
l
g
r
e
y
b
a
s
e
d
f
u
z
z
y
c
-
m
e
a
n
s
,
m
u
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
b
a
s
e
d
f
e
a
t
u
r
e
s
e
l
e
c
t
i
o
n
,
a
n
d
r
e
g
r
e
s
s
i
o
n
m
o
d
e
l
,
”
E
x
p
e
r
t
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
1
5
,
p
p
.
6
8
–
9
4
,
2
0
1
9
.
[2
8
]
W.
C
.
L
i
n
a
n
d
C
.
F
.
T
s
a
i
,
“
M
i
s
s
i
n
g
v
a
l
u
e
im
p
u
t
a
t
i
o
n
:
a
r
e
v
i
e
w
a
n
d
a
n
a
ly
s
i
s
o
f
t
h
e
l
i
t
e
ra
t
u
r
e
(
2
0
0
6
–
2
0
1
7
)
,
”
A
r
t
i
fi
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
v
i
e
w
,
v
o
l
.
5
3
,
n
o
.
2
,
p
p
.
1
4
8
7
–
1
5
0
9
,
F
e
b
2
0
1
9
.
[2
9
]
O
.
D
é
n
i
z
,
G
.
B
u
e
n
o
,
J
.
S
a
l
i
d
o
,
a
n
d
F
.
D
e
l
a
T
o
r
r
e
,
“
F
a
c
e
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
H
i
s
t
o
g
r
a
m
s
o
f
Or
i
e
n
t
e
d
G
ra
d
i
e
n
t
s
,
”
P
a
t
t
e
r
n
R
e
c
o
g
n
i
t
i
o
n
L
e
t
t
e
r
s
,
v
o
l
.
3
2
,
n
o
.
1
2
,
p
p
.
1
5
9
8
–
1
6
0
3
,
S
e
p
2
0
1
1
.
[3
0
]
H
.
T
.
M
.
N
h
a
t
a
n
d
V.
T
.
H
o
a
n
g
,
“
F
e
a
t
u
r
e
f
u
s
i
o
n
b
y
u
s
i
n
g
l
b
p
,
h
o
g
,
g
i
s
t
d
e
sc
r
i
p
t
o
r
s
a
n
d
c
a
n
o
n
i
c
a
l
c
o
r
re
l
a
t
i
o
n
a
n
a
ly
s
i
s
f
o
r
f
a
c
e
re
c
o
g
n
i
t
i
o
n
,
”
2
0
1
9
2
6
t
h
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
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
C
T
)
,
p
p
.
3
7
1
–
3
7
5
,
A
p
r
i
l
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
K
A
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l
C
o
n
tr
o
l
R
ice
s
ee
d
ima
g
e
cla
s
s
ifi
ca
tio
n
b
a
s
ed
o
n
HOG
d
escr
ip
to
r
…
(
Hu
y
N
g
u
ye
n
-
Qu
o
c
)
1903
[3
1
]
A
.
C
h
a
u
h
a
n
,
D
.
C
h
a
u
h
a
n
,
a
n
d
C
.
R
o
u
t
,
“
R
o
l
e
o
f
G
is
t
a
n
d
P
H
OG
F
e
a
t
u
r
e
s
i
n
C
o
m
p
u
t
e
r
-
A
i
d
e
d
D
i
a
g
n
o
s
i
s
o
f
T
u
b
e
r
c
u
l
o
s
i
s
w
i
t
h
o
u
t
S
e
g
m
e
n
t
a
t
i
o
n
,
”
P
l
o
S
O
N
E
,
v
o
l
.
9
,
n
o
.
11
,
2
0
1
4
.
[3
2
]
T
.
J
.
A
l
h
i
n
d
i
,
S
.
K
a
l
r
a
,
K
.
H
.
Ng
,
A
.
A
f
r
i
n
,
a
n
d
H
.
R
.
T
iz
h
o
o
s
h
,
“
C
o
m
p
a
r
i
n
g
L
B
P
,
H
OG
a
n
d
D
e
e
p
F
e
a
t
u
r
e
s
f
o
r
C
l
a
s
s
ifi
c
a
t
i
o
n
o
f
H
is
t
o
p
a
t
h
o
l
o
g
y
Im
a
g
e
s
,
”
2
0
1
8
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
r
e
n
c
e
o
n
N
e
u
r
a
l
Ne
t
w
o
r
k
s
(
I
J
C
N
N
)
,
R
i
o
d
e
J
a
n
e
i
r
o
:
I
E
E
E
,
p
p
.
1
–
7
,
J
u
l
2
0
1
8
.
[3
3
]
T
.
S
u
r
i
n
w
a
ra
n
g
k
o
o
n
,
S
.
N
i
t
s
u
w
a
t
,
a
n
d
J
.
E
l
v
i
n
,
“
A
t
r
a
f
f
ic
s
ig
n
d
e
t
e
c
t
i
o
n
a
n
d
r
e
c
o
g
n
i
t
i
o
n
sy
s
t
e
m
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
i
r
c
u
i
t
s
,
S
y
s
t
e
ms
a
n
d
S
i
g
n
a
l
P
r
o
c
e
s
s
i
n
g
,
v
o
l
.
7
,
n
o
.
1
,
p
p
.
5
8
–
6
5
,
2
0
1
3
.
[3
4
]
K
.
V.
B
r
a
n
d
e
n
a
n
d
S
.
Ve
r
b
o
v
e
n
,
“
R
o
b
u
s
t
d
a
ta
im
p
u
t
a
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
B
i
o
l
o
g
y
a
n
d
C
h
e
m
i
s
t
r
y
,
v
o
l
.
3
3
,
n
o
.
1
,
p
p
.
7
–
1
3
,
F
e
b
2
0
0
9
.
[3
5
]
L
.
A
.
H
u
n
t
,
“
M
i
s
s
i
n
g
Da
t
a
Im
p
u
t
a
t
i
o
n
a
n
d
I
t
s
Ef
f
e
c
t
o
n
t
h
e
A
c
c
u
r
a
c
y
o
f
C
la
s
s
ifi
c
a
t
i
o
n
,
”
,
i
n
:
F
.
P
a
l
u
m
b
o
,
A
.
M
o
n
t
a
n
a
r
i
,
a
n
d
M
.
Vi
c
h
i
,
“
S
t
u
d
i
e
s
i
n
C
l
a
ss
if
i
c
a
t
i
o
n
,
D
a
ta
A
n
a
ly
s
is
,
a
n
d
K
n
o
w
l
e
d
g
e
O
rg
a
n
i
z
a
t
i
o
n
,
”
D
a
t
a
S
c
i
e
n
c
e
,
C
h
a
m
:
S
p
r
i
n
g
e
r
I
n
te
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
p
p
.
3
–
14
,
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
H
u
y
Ng
u
y
e
n
-
Q
u
o
c
is
a
n
u
n
d
e
rg
ra
d
u
a
te
stu
d
e
n
t
f
ro
m
Ho
Ch
i
M
in
h
Cit
y
Op
e
n
Un
iv
e
rsity
,
V
ietn
a
m
.
His res
e
a
rc
h
in
tere
sts in
c
lu
d
e
p
a
tt
e
r
n
re
c
o
g
n
it
i
o
n
a
n
d
im
a
g
e
a
n
a
l
y
sis.
V
i
n
h
Tr
u
o
n
g
H
o
a
n
g
is
a
n
a
ss
i
sta
n
t
p
ro
f
e
ss
o
r
a
n
d
He
a
d
o
f
I
m
a
g
e
P
ro
c
e
ss
in
g
a
n
d
Co
m
p
u
ter
G
ra
p
h
ics
De
p
a
rt
m
e
n
t
a
t
th
e
H
o
C
h
i
M
in
h
Cit
y
Op
e
n
U
n
iv
e
rsity
,
V
ietn
a
m
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
im
a
g
e
a
n
a
l
y
sis a
n
d
f
e
a
tu
re
se
lec
ti
o
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.