I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
38
,
No
.
3
,
J
u
n
e
2
0
2
5
,
p
p
.
1
851
~
1
8
6
1
I
SS
N:
2
5
0
2
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
38
.i
3
.
p
p
1
8
5
1
-
1
8
6
1
1851
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Dev
elo
pment of
c
ha
ra
cter
e
x
trac
ti
o
n t
echniq
ues to
detec
t
chicken gen
der b
a
sed o
n egg
sha
pe
Adil Set
ia
wa
n
1
,
Y
uh
a
n
d
r
i
2
,
M
u
h
a
m
m
a
d
T
a
j
u
d
d
i
n
3
1
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
a
s Pu
t
r
a
I
n
d
o
n
e
si
a
Y
P
TK
P
a
d
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
D
o
c
t
o
r
,
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
F
a
c
u
l
t
y
,
U
n
i
v
e
r
si
t
a
s P
u
t
r
a
I
n
d
o
n
e
si
a
Y
P
T
K
,
P
a
d
a
n
g
,
I
n
d
o
n
e
s
i
a
3
D
e
p
a
r
t
e
m
e
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
F
a
c
u
l
t
y
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
B
u
mi
g
o
r
a
U
n
i
v
e
r
s
i
t
y
,
N
T
B
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
14
,
2
0
2
4
R
ev
is
ed
Dec
2
,
2
0
2
4
Acc
ep
ted
Feb
27
,
2
0
2
5
Th
is
re
se
a
rc
h
in
v
e
sti
g
a
tes
th
e
d
i
ffe
re
n
ti
a
ti
o
n
o
f
c
h
ic
k
e
n
se
x
b
a
se
d
o
n
e
g
g
sh
a
p
e
ima
g
e
s
b
y
d
e
v
e
lo
p
i
n
g
a
n
in
n
o
v
a
ti
v
e
e
c
c
e
n
tri
c
it
y
sh
a
p
e
fe
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
.
Th
e
g
o
a
l
is
to
d
e
term
in
e
th
e
se
x
o
f
c
h
ick
e
n
s
b
e
fo
re
h
a
tch
in
g
,
b
y
id
e
n
t
ify
i
n
g
t
h
e
se
x
o
f
t
h
e
e
g
g
p
ri
o
r
to
i
n
c
u
b
a
ti
o
n
.
Im
a
g
e
s
o
f
e
g
g
s
a
re
c
a
p
t
u
re
d
u
sin
g
a
sm
a
r
tp
h
o
n
e
c
a
m
e
ra
,
c
re
a
ti
n
g
a
d
a
tas
e
t
o
f
1
5
0
ima
g
e
s
e
a
c
h
o
f
m
a
le
a
n
d
fe
m
a
le
e
g
g
s,
wit
h
e
x
p
e
rt
a
ss
istan
c
e
.
Th
e
re
se
a
rc
h
a
ims
to
a
c
c
u
ra
tely
id
e
n
ti
f
y
m
a
le
a
n
d
fe
m
a
le
e
g
g
s,
a
id
in
g
b
re
e
d
e
rs
in
so
rti
n
g
th
e
m
.
Th
e
re
se
a
rc
h
in
tro
d
u
c
e
s
a
u
n
i
q
u
e
m
e
th
o
d
to
e
x
p
a
n
d
th
e
e
c
c
e
n
tri
c
it
y
v
a
lu
e
ra
n
g
e
,
e
n
h
a
n
c
in
g
t
h
e
p
re
c
i
sio
n
o
f
e
g
g
s
h
a
p
e
a
n
a
ly
sis.
Ch
a
ra
c
teristic
e
x
trac
ti
o
n
re
su
l
ts
in
c
lu
d
e
:
a
re
a
=
1
2
9
0
1
9
4
,
e
c
c
e
n
tri
c
it
y
=
6
.
5
6
,
c
o
n
tras
t
=
0
.
0
3
,
c
o
rre
lati
o
n
=
0
.
9
9
,
e
n
e
rg
y
=
0
.
4
4
,
a
n
d
h
o
m
o
g
e
n
e
it
y
=
0
.
9
8
,
wi
th
a
p
re
v
io
u
s
v
a
lu
e
o
f
0
.
7
2
.
F
o
r
F
e
a
tu
re
S
e
lec
ti
o
n
,
th
e
v
a
l
u
e
s
o
b
ta
in
e
d
a
re
:
e
c
c
e
n
t
ricity
=
0
.
9
0
1
1
8
8
0
4
9
,
Are
a
=
0
.
7
3
,
En
e
rg
y
=
0
.
0
3
,
Co
n
tras
t
=
0
.
0
1
,
Ho
m
o
g
e
n
e
it
y
=
0
.
0
1
,
a
n
d
Co
rre
latio
n
=
0
.
0
1
.
Th
e
se
fi
n
d
in
g
s
d
e
m
o
n
stra
te
sig
n
ifi
c
a
n
t
im
p
ro
v
e
m
e
n
ts
in
d
iff
e
re
n
ti
a
ti
n
g
c
h
ic
k
e
n
se
x
fro
m
e
g
g
ima
g
e
s,
sh
o
wc
a
sin
g
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
n
e
wl
y
d
e
v
e
lo
p
e
d
e
c
c
e
n
tri
c
it
y
sh
a
p
e
fe
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
.
K
ey
w
o
r
d
s
:
E
cc
en
tr
icity
E
g
g
s
Featu
r
e
ex
tr
ac
tio
n
Featu
r
e
s
elec
tio
n
Sh
ap
e
f
ea
tu
r
es
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
:
Ad
il Setiawa
n
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
Un
iv
er
s
it
as Pu
tr
a
I
n
d
o
n
esia Y
PTK
Pad
an
g
Pad
an
g
,
W
est Su
m
ater
a,
2
5
2
2
1
,
I
n
d
o
n
esia
E
m
ail: a
d
io
1
6
5
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
R
esear
ch
to
d
etec
t
th
e
s
ex
o
f
ch
ick
en
s
s
till
in
th
e
eg
g
u
s
in
g
d
ig
ital
im
ag
e
ex
tr
ac
tio
n
m
eth
o
d
s
,
esp
ec
ially
th
r
o
u
g
h
ec
ce
n
tr
icit
y
p
ar
a
m
eter
s
,
h
as
s
ig
n
if
ican
t
i
m
p
o
r
tan
ce
in
th
e
p
o
u
ltr
y
in
d
u
s
tr
y
.
E
ar
ly
d
etec
tio
n
o
f
ch
ick
e
n
s
ex
allo
ws
f
ar
m
er
s
to
o
p
tim
ize
th
e
r
e
ar
in
g
p
r
o
ce
s
s
b
y
s
ep
ar
atin
g
eg
g
s
th
at
will
p
r
o
d
u
ce
m
ales
f
r
o
m
f
em
ales
ea
r
ly
o
n
.
T
h
is
is
v
er
y
im
p
o
r
ta
n
t
b
ec
au
s
e
m
ales
ar
e
o
f
ten
less
ec
o
n
o
m
ical
to
r
aise
th
an
f
em
ales
th
at
ca
n
lay
eg
g
s
.
Dig
ital im
ag
e
ex
tr
ac
tio
n
m
eth
o
d
s
o
n
c
h
ick
en
eg
g
s
allo
w
n
o
n
-
in
v
asiv
e
an
d
ac
cu
r
ate
an
aly
s
is
to
d
eter
m
in
e
th
e
s
ex
o
f
em
b
r
y
o
s
.
E
cc
en
tr
icity
,
wh
ic
h
m
ea
s
u
r
es
th
e
im
p
er
f
ec
tio
n
s
o
f
t
h
e
s
h
ap
e
o
f
o
b
jects
in
th
e
im
ag
e,
ca
n
b
e
u
s
ed
as
a
p
ar
am
eter
to
d
etec
t
s
m
all
b
u
t
s
ig
n
if
ican
t
d
if
f
er
e
n
ce
s
b
etwe
en
eg
g
s
co
n
tai
n
in
g
m
ale
an
d
f
em
ale
em
b
r
y
o
s
.
T
h
e
u
s
e
o
f
ec
ce
n
tr
icity
i
n
th
is
im
ag
e
an
aly
s
is
o
f
f
er
s
a
m
o
r
e
ef
f
icien
t
an
d
r
ap
i
d
ap
p
r
o
ac
h
co
m
p
a
r
ed
to
co
n
v
en
tio
n
al
m
eth
o
d
s
s
u
ch
as v
en
t sex
in
g
o
r
DNA
an
aly
s
is
,
wh
ich
ar
e
m
o
r
e
ex
p
e
n
s
iv
e
an
d
tim
e
-
c
o
n
s
u
m
in
g
.
T
h
e
b
en
ef
its
o
f
th
is
r
esear
ch
in
cl
u
d
e
in
c
r
ea
s
ed
o
p
e
r
atio
n
al
e
f
f
icien
cy
,
r
ed
u
ce
d
p
r
o
d
u
ctio
n
co
s
ts
,
an
d
im
p
r
o
v
ed
an
im
al
welf
ar
e.
B
y
elim
in
atin
g
th
e
n
ee
d
to
h
atch
a
n
d
r
aise
u
n
ec
o
n
o
m
ical
m
ales,
r
eso
u
r
ce
s
ca
n
b
e
allo
c
ated
m
o
r
e
ap
p
r
o
p
r
iately
to
s
u
p
p
o
r
t
th
e
g
r
o
wth
o
f
p
r
o
d
u
ctiv
e
f
em
ales.
Ov
er
all,
th
e
d
ev
elo
p
m
en
t
o
f
a
d
ig
ital
im
ag
e
ex
tr
ac
tio
n
m
eth
o
d
f
o
r
d
etec
tin
g
th
e
s
ex
o
f
c
h
ick
en
s
in
eg
g
s
b
ased
o
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
5
1
-
1
8
6
1
1852
ec
ce
n
tr
icity
o
f
f
e
r
s
an
in
n
o
v
ati
v
e
an
d
s
u
s
tain
ab
le
tech
n
o
lo
g
i
ca
l
s
o
lu
tio
n
to
ch
allen
g
es
in
t
h
e
p
o
u
ltry
in
d
u
s
tr
y
,
with
th
e
p
o
ten
tial to
in
c
r
ea
s
e
ef
f
icien
cy
,
r
e
d
u
ce
c
o
s
ts
,
an
d
im
p
r
o
v
e
a
n
im
al
welf
ar
e.
T
h
e
aim
o
f
th
is
r
esear
ch
was
to
au
to
m
atica
lly
p
r
e
d
ict
th
e
s
ex
o
f
f
er
tili
ze
d
d
u
ck
eg
g
s
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
.
Featu
r
e
e
x
tr
ac
tio
n
u
tili
ze
d
eg
g
ec
ce
n
tr
icity
,
a
n
d
th
e
class
if
ier
em
p
l
o
y
ed
a
s
eg
r
eg
ato
r
s
en
s
o
r
,
ac
h
iev
in
g
a
n
ac
cu
r
ac
y
o
f
7
5
.
2
2
%
[
1
]
.
I
n
Dio
ce
s
an
'
s
r
esear
ch
,
th
e
f
o
cu
s
was
o
n
d
eter
m
in
i
n
g
th
e
p
e
r
f
o
r
m
an
ce
o
f
a
class
if
icatio
n
m
o
d
el
f
o
r
J
ap
an
ese
q
u
ail
eg
g
s
.
Seg
m
en
ta
tio
n
was
p
er
f
o
r
m
ed
u
s
in
g
c
an
n
y
ed
g
e
d
etec
tio
n
,
f
ea
tu
r
e
ex
tr
ac
tio
n
e
m
p
lo
y
ed
eg
g
m
o
r
p
h
o
l
o
g
y
,
a
n
d
th
e
cl
ass
if
ier
was
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
(
SVM)
,
r
esu
ltin
g
in
an
ac
cu
r
ac
y
o
f
8
2
.
8
8
%
[
2
]
.
W
ar
an
u
s
ast'
s
r
esear
ch
aim
ed
to
d
etec
t
th
e
s
ex
o
f
ch
ick
en
eg
g
s
b
ased
o
n
s
ize
class
if
icatio
n
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
.
Seg
m
en
tatio
n
wa
s
d
o
n
e
u
s
in
g
ed
g
e
d
e
t
e
c
t
i
o
n
,
f
e
a
t
u
r
e
e
x
t
r
a
c
ti
o
n
wi
t
h
G
r
a
b
C
u
t
,
a
n
d
c
l
ass
i
f
i
c
at
i
o
n
u
s
i
n
g
S
VM
,
a
c
h
i
e
v
i
n
g
a
n
a
c
cu
r
a
c
y
o
f
8
0
.
4
%
[
3
]
.
D
i
a
n
t
o
r
o
'
s
r
es
e
a
r
c
h
f
o
c
u
s
e
d
o
n
d
e
v
e
l
o
p
i
n
g
a
n
e
g
g
f
e
r
t
i
l
i
t
y
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
f
o
r
i
m
a
g
e
s
o
f
f
r
e
e
-
r
a
n
g
e
c
h
i
c
k
e
n
e
g
g
s
u
s
i
n
g
t
h
e
n
a
i
v
e
b
a
y
es
cl
a
s
s
i
f
i
e
r
al
g
o
r
i
t
h
m
.
T
h
e
b
e
s
t
a
c
c
u
r
a
c
y
f
r
o
m
t
r
a
i
n
i
n
g
d
a
t
a
t
r
ia
l
s
w
as
8
0
%
[
4
]
.
Z
h
ao
'
s
r
esear
ch
aim
ed
to
d
etec
t
f
ir
s
t
-
o
r
d
er
f
ea
tu
r
e
e
x
tr
ac
tio
n
an
d
p
r
i
n
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
to
id
en
tify
ty
p
es
o
f
f
r
e
e
-
r
an
g
e
a
n
d
Ar
a
b
ic
ch
ick
e
n
e
g
g
s
,
ac
h
iev
in
g
an
ac
cu
r
ac
y
o
f
9
5
%
with
PC
A
[
5
]
.
Pan
'
s
r
esear
ch
tar
g
eted
th
e
ea
r
ly
d
eter
m
in
atio
n
o
f
th
e
s
ex
o
f
ch
ick
en
em
b
r
y
o
s
d
u
r
i
n
g
in
cu
b
atio
n
u
s
in
g
h
y
p
er
s
p
ec
tr
al
im
ag
es.
Pre
d
ict
io
n
s
with
an
ar
tific
ial
n
eu
r
al
n
etwo
r
k
(
ANN)
m
o
d
el
s
h
o
wed
an
i
n
cr
ea
s
e
in
ac
cu
r
ac
y
f
r
o
m
8
0
.
0
0
%
to
8
2
.
8
6
%,
in
d
icatin
g
th
at
r
em
o
v
in
g
in
ter
f
e
r
en
ce
in
f
o
r
m
atio
n
im
p
r
o
v
es
m
o
d
el
ac
cu
r
ac
y
[
6
]
.
Saif
u
llah
'
s
r
ese
ar
ch
s
o
u
g
h
t
to
i
d
en
tify
th
e
f
e
r
tili
ty
o
f
ch
ick
en
eg
g
s
u
s
in
g
FOS
an
d
B
P
-
n
eu
r
al
n
etwo
r
k
s
in
im
ag
e
p
r
o
ce
s
s
in
g
[
7
]
.
T
h
e
r
esu
lts
in
d
icate
d
th
at
FOS
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
B
P
-
n
eu
r
al
n
etwo
r
k
s
co
u
ld
ef
f
ec
tiv
ely
d
etec
t
e
m
b
r
y
o
n
ic
ch
ic
k
en
e
g
g
s
,
alth
o
u
g
h
s
o
m
e
eg
g
im
ag
es
ex
h
ib
ited
s
im
ilar
p
atter
n
s
in
FOS
[
8
]
.
B
u
d
iar
to
's
r
esear
ch
aim
s
to
d
etec
t
eg
g
f
er
tili
ty
u
s
in
g
im
ag
e
p
r
o
ce
s
s
in
g
an
d
f
u
zz
y
lo
g
ic.
T
h
e
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
ed
s
en
s
itiv
it
y
,
s
p
ec
if
icity
,
an
d
av
er
ag
e
ac
cu
r
a
cy
r
esu
lts
o
f
9
4
.
6
%,
9
4
.
0
7
%,
an
d
9
4
.
6
8
%,
r
esp
ec
tiv
ely
[
9
]
.
I
n
S
aif
u
llah
'
s
r
esear
ch
,
th
e
g
o
al
w
as
to
s
eg
m
en
t
im
ag
es
o
f
em
b
r
y
o
n
ated
e
g
g
s
u
s
in
g
th
e
K
-
m
ea
n
s
alg
o
r
ith
m
.
E
x
p
er
im
en
tal
r
esu
lts
in
d
icate
d
th
at
th
e
p
r
o
ce
s
s
r
u
n
s
ef
f
ec
ti
v
ely
,
with
a
m
ea
n
s
tr
u
ctu
r
al
s
im
ilar
ity
in
d
ex
(
MSSI
M)
v
alu
e
o
f
0
.
9
9
9
5
,
s
u
g
g
e
s
tin
g
th
at
th
e
p
r
o
ce
s
s
ed
im
ag
e
r
etain
s
m
o
s
t
o
f
th
e
o
r
ig
in
al
im
ag
e
in
f
o
r
m
atio
n
.
A
d
d
itio
n
ally
,
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
p
r
o
v
id
e
d
a
clea
r
d
ep
ictio
n
o
f
th
e
em
b
r
y
o
with
in
th
e
eg
g
,
d
em
o
n
s
tr
atin
g
th
e
ef
f
icac
y
o
f
K
-
m
ea
n
s
s
eg
m
en
tatio
n
f
o
r
d
etec
tin
g
em
b
r
y
o
s
[
1
0
]
.
Ma
h
d
i'
s
r
esear
ch
,
titl
ed
“
Ma
ch
i
n
e
v
is
i
o
n
s
y
s
tem
f
o
r
d
etec
tin
g
f
e
r
tile
eg
g
s
in
th
e
in
c
u
b
atio
n
in
d
u
s
tr
y
,
”
aim
ed
to
e
n
s
u
r
e
th
at
eg
g
s
p
lace
d
in
in
cu
b
ato
r
s
ar
e
f
er
tile.
A
f
er
tili
ty
d
ete
ctio
n
m
ac
h
in
e
s
y
s
tem
was
d
ev
elo
p
ed
an
d
ev
alu
ate
d
,
em
p
lo
y
in
g
m
ec
h
atr
o
n
ic
m
ac
h
in
es
to
o
b
tain
ac
cu
r
ate
d
ig
ital
im
ag
es
o
f
eg
g
s
with
o
u
t
ca
u
s
in
g
d
am
ag
e.
C
o
m
p
ar
is
o
n
s
with
ex
is
tin
g
m
eth
o
d
s
s
h
o
wed
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
tem
ac
h
iev
ed
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
,
p
r
o
v
in
g
h
ig
h
ly
r
eliab
le
f
o
r
a
p
p
licatio
n
in
th
e
in
cu
b
atio
n
in
d
u
s
tr
y
[
1
1
]
.
J
ee
r
ap
a'
s
r
esear
ch
,
titl
ed
“
E
g
g
weig
h
t
p
r
e
d
ictio
n
a
n
d
eg
g
s
i
ze
class
if
icatio
n
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,
”
aim
e
d
to
m
ea
s
u
r
e
eg
g
weig
h
t
an
d
a
s
s
es
s
s
ize
f
o
r
g
r
ad
in
g
p
u
r
p
o
s
es.
T
h
e
s
tu
d
y
u
s
ed
im
ag
e
p
r
o
ce
s
s
in
g
an
d
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es
to
p
r
e
d
i
ct
ch
ick
en
eg
g
weig
h
t
an
d
cla
s
s
if
y
eg
g
s
ize
f
r
o
m
a
s
in
g
le
eg
g
im
ag
e.
A
b
r
o
wn
c
h
ick
en
eg
g
was
p
h
o
t
o
g
r
ap
h
ed
,
an
d
th
ir
tee
n
g
eo
m
etr
ic
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
f
r
o
m
th
e
s
eg
m
en
ted
eg
g
im
ag
e.
W
eig
h
t
p
r
ed
ictio
n
u
s
in
g
lin
ea
r
r
eg
r
ess
io
n
y
ield
ed
a
co
r
r
el
atio
n
co
ef
f
icie
n
t
o
f
0
.
9
9
1
5
,
an
d
s
ize
class
if
icatio
n
u
s
in
g
a
SVM
ac
h
iev
ed
an
ac
cu
r
ac
y
o
f
8
7
.
5
8
%
[
1
2
]
.
M
o
r
p
h
o
lo
g
ical
f
ea
tu
r
e
ex
tr
ac
tio
n
is
a
m
eth
o
d
f
o
r
d
er
i
v
in
g
an
d
p
r
o
ce
s
s
in
g
s
cien
tific
in
f
o
r
m
atio
n
f
r
o
m
im
ag
e
d
ata
r
elate
d
to
th
e
s
h
a
p
e
o
f
o
b
s
er
v
e
d
f
ea
tu
r
es
[
1
3
]
-
[
1
5
]
.
T
h
is
m
eth
o
d
is
u
s
ed
f
o
r
p
att
er
n
r
ec
o
g
n
itio
n
to
o
b
tai
n
cr
itical
in
f
o
r
m
atio
n
f
o
r
ac
cu
r
ac
y
class
if
icatio
n
t
ec
h
n
iq
u
es
[
1
7
]
-
[
1
9
]
,
s
er
v
in
g
as
ess
en
tial
in
p
u
t
f
o
r
class
if
icatio
n
,
p
r
ed
ictio
n
,
an
d
d
ata
an
aly
s
is
.
E
d
g
e
d
etec
tio
n
is
v
it
al
in
an
aly
zin
g
v
ar
io
u
s
im
ag
es,
in
clu
d
in
g
th
o
s
e
in
m
e
d
ical
f
i
eld
s
[
2
0
]
.
Dete
r
m
in
in
g
eg
g
s
ex
b
ef
o
r
e
h
atch
in
g
is
co
m
m
o
n
ly
p
er
f
o
r
m
ed
to
s
o
r
t
e
g
g
s
p
r
i
o
r
to
in
cu
b
atio
n
.
T
h
is
s
tu
d
y
u
s
es
s
m
ar
tp
h
o
n
e
ca
m
er
as
f
o
r
im
ag
e
ac
q
u
is
itio
n
,
c
ap
t
u
r
in
g
eg
g
im
ag
es
at
a
d
is
tan
ce
o
f
1
3
cm
to
en
s
u
r
e
clar
ity
an
d
u
n
if
o
r
m
s
h
ap
e.
T
h
e
r
esear
ch
aim
s
to
ac
cu
r
a
tely
id
en
tify
m
ale
an
d
f
e
m
ale
eg
g
s
,
f
ac
ilit
atin
g
b
r
ee
d
er
s
'
s
o
r
tin
g
p
r
o
ce
s
s
es.
T
h
e
n
o
v
elty
lies
in
th
e
d
ev
elo
p
m
en
t
o
f
an
e
cc
en
tr
icity
s
h
ap
e
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
,
wh
ich
c
o
m
p
ar
es
th
e
d
is
tan
ce
b
etwe
en
th
e
m
in
o
r
el
lip
s
e
f
o
cu
s
(
b
)
an
d
t
h
e
m
ajo
r
ellip
s
e
f
o
cu
s
(
a)
o
f
an
o
b
ject'
s
ar
ea
/s
h
ap
e.
T
y
p
ical
ly
,
th
e
r
esu
ltin
g
v
alu
e
r
an
g
es
f
r
o
m
0
to
1
,
b
u
t
t
h
is
s
tu
d
y
ex
p
a
n
d
s
th
e
s
ca
le
to
0
-
9
f
o
r
a
b
r
o
a
d
er
in
ter
v
al.
A
n
elo
n
g
ated
ar
ea
y
ield
s
an
E
v
alu
e
n
ea
r
0
,
wh
ile
a
cir
cu
lar
/s
p
h
e
r
ical
ar
ea
y
ield
s
an
E
v
alu
e
n
ea
r
9
,
aid
i
n
g
i
n
m
ea
s
u
r
in
g
e
g
g
o
v
ality
.
Ad
d
itio
n
ally
,
th
e
d
is
c
m
eth
o
d
m
ea
s
u
r
es
eg
g
v
o
lu
m
e,
with
lar
g
er
v
o
lu
m
es
in
d
icatin
g
m
al
e
eg
g
s
an
d
s
m
aller
v
o
lu
m
es
i
n
d
icatin
g
f
e
m
ale
eg
g
s
.
T
h
e
f
i
n
d
in
g
s
in
th
is
s
tu
d
y
ar
e
th
at
t
h
e
m
eth
o
d
we
p
r
o
p
o
s
ed
s
u
cc
ess
f
u
lly
d
etec
ted
th
e
g
en
d
er
o
f
c
h
ick
en
eg
g
s
,
n
a
m
ely
eg
g
s
o
f
m
ale
ch
ick
en
o
r
eg
g
s
o
f
f
em
ale
c
h
ick
en
b
ased
o
n
ch
ick
en
eg
g
i
m
ag
es
b
y
d
ev
elo
p
in
g
a
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
.
T
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
f
o
r
m
u
la
d
ev
elo
p
e
d
in
th
is
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
is
th
e
e
cc
en
tr
icity
v
alu
e.
T
h
e
v
alu
e
we
d
ev
el
o
p
ed
is
n
am
e
d
th
e
e
cc
en
tr
icity
p
lu
s
f
o
r
m
u
la.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dev
elo
p
men
t o
f c
h
a
r
a
cter e
xtra
ctio
n
tech
n
iq
u
es to
d
etec
t c
h
icke
n
g
en
d
er b
a
s
ed
o
n
…
(
A
d
i
l S
etia
w
a
n
)
1853
2.
M
E
T
H
O
D
T
h
e
m
o
d
e
l
d
e
v
e
l
o
p
e
d
i
n
t
h
i
s
r
e
s
e
a
r
c
h
i
s
t
h
e
d
e
v
e
l
o
p
m
e
n
t
o
f
a
m
o
d
e
l
f
o
r
t
h
e
e
x
t
r
a
c
t
i
o
n
o
f
s
h
a
p
e
f
e
a
t
u
r
e
s
c
o
m
b
i
n
e
d
w
i
t
h
S
V
M
i
n
d
e
t
e
c
t
i
n
g
s
e
x
i
n
p
o
u
l
t
r
y
e
g
g
s
.
T
h
e
r
e
s
u
l
t
i
s
a
n
a
r
c
h
i
t
e
c
t
u
r
a
l
m
o
d
e
l
,
a
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
f
o
r
s
h
a
p
e
f
e
a
t
u
r
e
s
t
o
d
e
t
e
c
t
s
e
x
i
n
e
g
g
s
.
F
i
g
u
r
e
1
s
h
o
w
s
t
h
e
r
e
s
e
a
r
c
h
f
r
a
m
e
w
o
r
k
o
f
t
h
i
s
s
t
u
d
y
.
Fig
u
r
e
1
.
R
esear
ch
f
r
am
ewo
r
k
2
.
1
.
P
re
-
pro
ce
s
s
ing
I
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
is
th
e
in
itial
s
tep
in
p
r
o
ce
s
s
in
g
an
eg
g
im
ag
e,
in
v
o
lv
in
g
th
e
co
n
v
e
r
s
io
n
o
f
an
R
GB
im
ag
e
to
a
g
r
ay
s
ca
le
im
ag
e
to
s
im
p
lify
s
u
b
s
eq
u
e
n
t
p
r
o
ce
s
s
es.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
aim
s
to
en
h
an
c
e
th
e
im
ag
e
q
u
ality
,
m
ak
in
g
it
ea
s
ier
to
p
r
o
ce
s
s
an
d
an
aly
ze
in
th
e
s
u
b
s
eq
u
en
t
s
tep
s
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
es
in
clu
d
e
cr
o
p
p
in
g
an
d
f
ilter
in
g
p
r
o
ce
s
s
es.
B
ef
o
r
e
in
itiatin
g
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e,
th
e
in
p
u
t
im
ag
e
is
ac
q
u
ir
ed
f
r
o
m
t
h
e
s
o
u
r
ce
.
a)
I
n
p
u
t
i
m
a
g
e
:
I
n
p
u
t
im
ag
es
s
h
o
u
ld
b
e
s
elec
ted
ca
r
ef
u
lly
with
atten
tio
n
to
f
o
r
m
at,
co
lo
r
,
q
u
a
lity
an
d
s
o
u
r
ce
.
T
h
e
im
ag
e
is
r
ea
d
u
s
in
g
th
e
i
m
r
ea
d
f
u
n
ctio
n
a
n
d
s
to
r
ed
in
t
h
e
p
r
e_
a
v
ar
iab
le.
Pr
o
ce
s
s
in
g
th
e
i
n
p
u
t
im
ag
e
in
clu
d
es
ca
lcu
latin
g
im
ag
e
d
im
en
s
io
n
s
an
d
s
to
r
in
g
t
h
em
in
th
e
s
ize
v
ar
iab
le,
o
b
tain
in
g
im
ag
e
s
ize
in
f
o
r
m
atio
n
in
th
e
“
wid
th
x
h
eig
h
t
”
f
o
r
m
at
an
d
s
to
r
in
g
it
in
th
e
tex
t_
s
ize
v
ar
iab
le,
as
well
as
id
en
tify
in
g
th
e
im
ag
e
f
o
r
m
at,
s
u
ch
as
*
.
j
p
g
.
All
th
is
in
f
o
r
m
atio
n
will
b
e
d
is
p
lay
ed
in
th
e
MA
T
L
AB
GUI
,
an
d
th
e
in
p
u
t im
ag
e
will b
e
d
is
p
lay
ed
.
b)
I
m
ag
e
c
r
o
p
p
in
g
:
T
h
e
cr
o
p
p
in
g
p
r
o
ce
s
s
in
v
o
lv
es
cu
ttin
g
p
ar
ts
o
f
th
e
im
ag
e
to
s
im
p
lify
th
e
s
ize
an
d
f
o
cu
s
o
n
th
e
o
b
ject
o
f
in
ter
est.
T
h
e
p
u
r
p
o
s
e
o
f
c
r
o
p
p
in
g
is
to
r
e
m
o
v
e
u
n
n
ec
ess
ar
y
n
o
is
e
o
u
ts
id
e
th
e
r
esear
ch
o
b
ject
b
y
tr
im
m
in
g
ea
ch
s
id
e
o
f
t
h
e
im
ag
e
.
T
h
is
r
esu
lts
in
an
ar
ea
o
f
in
ter
est,
allo
win
g
th
e
r
em
o
v
al
o
f
u
n
n
ee
d
e
d
r
eg
i
o
n
s
o
u
ts
id
e
th
e
o
b
ject’
s
r
eg
io
n
o
f
i
n
ter
est
(
R
OI
)
[
2
1
]
,
[
2
2
]
.
c)
R
GB
im
ag
e
to
g
r
ay
s
ca
le
:
T
h
e
in
itial
p
r
o
ce
s
s
in
v
o
lv
es
co
n
v
er
tin
g
th
e
r
ed
g
r
ee
n
b
lu
e
(
R
GB
)
im
ag
e
to
a
g
r
ay
s
ca
le
im
ag
e
to
s
im
p
lify
th
e
r
ec
o
g
n
itio
n
o
f
th
e
eg
g
im
ag
e
[
2
3
]
.
At
th
is
s
tag
e,
p
r
ep
r
o
ce
s
s
in
g
is
p
er
f
o
r
m
ed
b
y
co
n
v
er
tin
g
th
e
R
GB
im
ag
e
to
g
r
ay
s
ca
le.
I
n
t
h
e
R
GB
to
g
r
ay
s
ca
le
s
tag
e
,
th
e
in
p
u
t
im
ag
e
is
tr
an
s
f
o
r
m
ed
in
to
g
r
ay
s
ca
le
f
o
r
m
.
C
o
n
v
er
tin
g
th
e
i
n
p
u
t
im
a
g
e
to
g
r
a
y
s
ca
le
is
a
co
m
m
o
n
s
tep
in
d
ig
ital
im
ag
e
p
r
o
ce
s
s
in
g
,
w
h
ich
co
n
v
er
ts
a
co
lo
r
im
ag
e
i
n
to
a
g
r
ay
s
ca
le
im
ag
e.
2
.
2
.
Seg
m
ent
a
t
i
o
n
I
m
a
g
e
s
e
g
m
e
n
t
at
i
o
n
is
t
h
e
i
n
tr
i
c
a
t
e
p
r
o
c
es
s
o
f
d
i
s
a
s
s
e
m
b
l
i
n
g
o
r
c
a
t
e
g
o
r
i
z
i
n
g
a
n
i
m
a
g
e
b
as
e
d
o
n
t
h
e
i
n
t
r
i
n
s
ic
c
h
a
r
a
c
t
e
r
is
ti
c
s
o
f
i
ts
p
ix
e
l
s
[
2
4
]
.
T
h
i
s
s
e
g
m
e
n
ta
t
i
o
n
c
an
m
a
n
i
f
e
s
t
a
s
t
h
e
is
o
l
at
i
o
n
o
f
t
h
e
f
o
r
e
g
r
o
u
n
d
f
r
o
m
t
h
e
b
a
c
k
g
r
o
u
n
d
o
r
t
h
e
a
m
a
l
g
a
m
a
t
i
o
n
o
f
p
i
x
e
l
r
e
g
i
o
n
s
b
as
ed
o
n
s
i
m
i
la
r
i
t
ie
s
i
n
c
o
l
o
r
o
r
s
h
a
p
e
.
T
h
e
p
r
i
m
a
r
y
o
b
j
e
c
t
i
v
e
o
f
s
e
g
m
e
n
t
a
t
i
o
n
is
t
o
s
t
r
e
a
m
li
n
e
i
m
a
g
e
a
n
al
y
s
is
b
y
co
n
c
e
n
t
r
a
t
i
n
g
o
n
s
p
e
c
i
f
i
c
a
r
e
as
o
r
o
b
j
e
c
t
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
5
1
-
1
8
6
1
1854
a)
YC
b
C
r
co
lo
r
s
p
ac
e
tr
an
s
f
o
r
m
atio
n
.
T
h
e
YC
b
C
r
co
lo
r
s
p
ac
e
tr
an
s
f
o
r
m
atio
n
in
v
o
lv
es
s
ep
ar
atin
g
R
GB
co
lo
r
s
in
to
lu
m
in
a
n
ce
an
d
c
h
r
o
m
in
an
ce
co
m
p
o
n
e
n
ts
[
2
5
]
.
T
h
e
R
GB
co
lo
r
s
p
ac
e
in
t
h
e
o
r
ig
in
al
im
ag
e
co
n
tain
s
lig
h
tin
g
e
f
f
ec
ts
th
at
alter
co
lo
r
ch
a
r
ac
ter
is
tics
,
n
ec
ess
itatin
g
co
n
v
er
s
io
n
in
to
a
ch
r
o
m
atic
co
l
o
r
s
p
ac
e
to
m
itig
ate
th
ese
ef
f
ec
ts
,
u
s
in
g
th
e
YC
b
C
r
co
lo
r
m
o
d
el.
I
n
th
is
m
o
d
el,
Y
r
ep
r
es
en
ts
lu
m
in
an
c
e
(
b
r
ig
h
t
n
ess
lev
el)
,
C
b
r
ep
r
esen
ts
ch
r
o
m
in
a
n
ce
b
l
u
e
(
b
l
u
en
e
s
s
lev
el)
,
an
d
C
r
r
ep
r
esen
ts
c
h
r
o
m
in
a
n
ce
r
e
d
(
r
ed
n
ess
lev
el)
.
b)
Fil
lin
g
h
o
les.
Fil
lin
g
Ho
les
is
an
im
ag
e
s
eg
m
en
tatio
n
m
eth
o
d
th
at
d
is
tin
g
u
is
h
es
o
b
jects
f
r
o
m
th
e
b
ac
k
g
r
o
u
n
d
in
an
im
ag
e
b
ased
o
n
v
ar
iatio
n
s
in
b
r
i
g
h
tn
ess
o
r
d
ar
k
n
ess
[
2
6
]
,
[
2
7
]
.
Dar
k
er
im
ag
e
r
eg
io
n
s
ar
e
r
en
d
er
e
d
ev
en
d
ar
k
er
(
p
u
r
e
b
l
ac
k
with
an
in
ten
s
ity
v
alu
e
o
f
0
)
,
wh
ile
lig
h
ter
r
eg
io
n
s
ar
e
r
e
n
d
er
ed
b
r
ig
h
ter
(
p
u
r
e
wh
ite
with
a
n
in
ten
s
ity
v
alu
e
o
f
1
)
.
C
o
n
s
eq
u
en
tly
,
th
e
o
u
tp
u
t
o
f
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
u
s
in
g
th
e
th
r
esh
o
ld
in
g
m
eth
o
d
is
a
b
i
n
a
r
y
im
ag
e
with
p
ix
el
in
ten
s
ity
v
alu
es
o
f
eith
e
r
0
o
r
1
.
O
n
ce
th
e
im
ag
e
h
as
b
ee
n
s
eg
m
e
n
ted
,
o
r
th
e
o
b
ject
h
as
b
ee
n
s
u
cc
ess
f
u
lly
s
ep
ar
at
ed
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
,
th
e
r
esu
ltan
t
b
in
ar
y
im
ag
e
ca
n
b
e
u
tili
ze
d
as a
m
ask
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
in
g
,
en
s
u
r
in
g
th
e
o
r
ig
i
n
al
im
ag
e
is
d
is
p
lay
ed
with
o
u
t its
b
ac
k
g
r
o
u
n
d
.
c)
E
d
g
e
d
et
ec
t
io
n
.
T
h
e
ed
g
e
d
etec
tio
n
s
tag
e
is
a
cr
u
cial
s
tep
in
th
e
im
ag
e
p
r
o
ce
s
s
in
g
p
i
p
elin
e,
aim
ed
at
id
en
tify
in
g
an
d
em
p
h
asizin
g
th
e
ed
g
es
with
in
a
n
im
a
g
e
[
2
8
]
.
T
h
is
p
r
o
ce
s
s
u
tili
ze
s
s
p
ec
ial
ized
alg
o
r
ith
m
s
to
d
is
tin
g
u
is
h
b
etwe
en
r
eg
io
n
s
with
s
ig
n
if
ican
t
in
ten
s
ity
ch
an
g
es
an
d
th
o
s
e
with
o
u
t.
B
y
ac
ce
n
tu
atin
g
th
e
ed
g
es
o
f
o
b
jects
in
an
im
ag
e,
ed
g
e
d
etec
tio
n
e
n
h
an
ce
s
th
e
clar
ity
an
d
s
tr
u
ctu
r
al
d
etail
o
f
th
e
im
ag
e.
T
h
e
u
ltima
te
o
b
jectiv
e
o
f
th
is
s
tag
e
is
to
im
p
r
o
v
e
th
e
s
h
ar
p
n
ess
an
d
d
etail
o
f
im
ag
es
th
at
m
ay
h
a
v
e
ex
p
er
ien
ce
d
b
lu
r
r
i
n
g
o
r
d
etai
l
lo
s
s
d
u
e
to
er
r
o
r
s
o
r
a
r
tifa
cts
in
tr
o
d
u
ce
d
d
u
r
in
g
th
e
im
ag
e
ac
q
u
is
itio
n
p
r
o
ce
s
s
.
d)
Pre
witt
ed
g
e
d
etec
tio
n
.
Pre
wit
t
ed
g
e
d
etec
tio
n
is
a
c
r
itical
s
tag
e
in
th
e
im
a
g
e
p
r
o
ce
s
s
in
g
wo
r
k
f
lo
w,
aim
e
d
at
r
ed
u
cin
g
o
r
elim
in
atin
g
n
o
is
e
b
ef
o
r
e
ex
ec
u
tin
g
th
e
ed
g
e
d
etec
tio
n
s
tep
[
2
9
]
.
T
h
is
s
tep
is
ess
en
t
ial
to
en
s
u
r
e
ac
cu
r
ate
an
d
s
h
ar
p
e
r
e
d
g
e
d
etec
tio
n
r
esu
lts
.
T
o
ev
al
u
ate
th
e
ed
g
e
d
etec
tio
n
p
er
f
o
r
m
an
ce
u
s
in
g
th
e
Pre
witt
m
eth
o
d
,
a
tr
ial
will
b
e
co
n
d
u
cted
b
y
d
ev
el
o
p
in
g
a
p
r
o
g
r
am
u
s
in
g
MA
T
L
AB
s
o
f
twar
e.
T
h
e
p
r
o
g
r
a
m
will
im
p
lem
en
t
ed
g
e
d
etec
tio
n
u
s
in
g
th
e
Pre
witt
m
eth
o
d
,
al
o
n
g
with
o
th
e
r
r
elev
an
t
e
d
g
e
d
etec
tio
n
tech
n
iq
u
es.
e)
B
in
ar
y
tr
an
s
f
o
r
m
atio
n
.
B
in
ar
y
tr
an
s
f
o
r
m
atio
n
is
a
p
iv
o
tal
s
tag
e
in
im
ag
e
p
r
o
ce
s
s
in
g
,
aim
in
g
to
p
r
o
d
u
ce
a
n
im
ag
e
r
ep
r
esen
tatio
n
with
b
la
ck
an
d
wh
ite
g
r
ad
atio
n
s
,
wh
er
e
ea
ch
p
ix
el
is
ass
ig
n
ed
a
b
in
ar
y
v
alu
e:
0
f
o
r
b
lack
an
d
1
f
o
r
w
h
ite
[
3
0
]
.
T
h
is
p
r
o
ce
s
s
ty
p
ically
in
v
o
lv
es
ass
ig
n
in
g
a
v
alu
e
o
f
1
to
p
ix
els
th
at
ar
e
p
ar
t
o
f
th
e
o
b
ject
o
f
in
ter
est,
wh
ile
p
ix
els
in
th
e
b
ac
k
g
r
o
u
n
d
ar
e
a
s
s
ig
n
ed
a
v
alu
e
o
f
0
.
C
o
n
s
eq
u
en
tly
,
a
b
in
ar
y
im
ag
e
is
g
e
n
er
ated
w
ith
p
i
x
els
co
lo
r
ed
wh
ite
o
r
b
lack
ac
co
r
d
in
g
to
t
h
eir
ass
ig
n
ed
lab
el.
I
n
th
r
esh
o
ld
in
g
,
s
elec
tin
g
th
e
ap
p
r
o
p
r
iate
th
r
e
s
h
o
ld
v
alu
e
is
a
cr
u
cial
p
ar
a
m
eter
th
at
in
f
lu
en
ce
s
th
e
f
in
al
b
in
ar
y
im
ag
e
r
esu
lt.
2
.3
.
New
f
e
a
t
ure
ex
t
r
a
ct
io
n
m
et
ho
d
Featu
r
e
ex
tr
ac
tio
n
is
a
p
r
o
ce
s
s
o
f
tak
in
g
f
ea
tu
r
es
w
h
er
e
th
e
o
b
tain
ed
v
alu
es
will
later
b
e
an
aly
ze
d
f
o
r
f
u
r
th
er
p
r
o
ce
s
s
es
[
3
1
]
,
[
3
2
]
.
T
h
e
n
o
v
elty
o
f
th
is
r
esear
ch
lies
in
th
e
s
tag
e
o
f
d
e
v
elo
p
in
g
an
ex
tr
ac
tio
n
an
d
f
ea
tu
r
e
s
elec
tio
n
alg
o
r
ith
m
c
alled
ec
ce
n
tr
i
city
f
ea
tu
r
e
d
ev
elo
p
m
en
t.
T
h
is
s
tag
e
is
a
r
es
ea
r
ch
co
n
tr
ib
u
tio
n
,
wh
er
e
ec
ce
n
t
r
icity
is
d
e
v
elo
p
ed
b
ased
o
n
th
e
r
atio
b
etwe
e
n
th
e
d
is
tan
ce
o
f
th
e
m
in
o
r
el
lip
s
e
f
o
ci
b
a
n
d
th
e
m
ajo
r
ellip
s
e
f
o
ci
a
o
f
a
r
e
g
io
n
/s
h
ap
e
o
n
th
e
o
b
ject,
wh
ich
ca
n
b
e
s
ee
n
in
t
h
e
b
asi
c
f
o
r
m
u
la
b
elo
w.
=
√
1
−
2
2
*
9
(
1
)
T
h
e
v
alu
e
o
f
E
r
a
n
g
es f
r
o
m
0
t
o
1
.
A
r
eg
io
n
ap
p
r
o
ac
h
in
g
a
s
tr
aig
h
t lin
e
(
elo
n
g
ate
d
)
will h
av
e
E
clo
s
e
to
1
,
wh
e
r
ea
s
a
cir
cu
lar
r
eg
io
n
will
h
av
e
E
clo
s
e
to
0
.
Her
e,
a
is
th
e
m
ajo
r
ellip
s
e
f
o
ci
an
d
b
is
th
e
m
in
o
r
ellip
s
e
f
o
ci.
T
h
is
ec
ce
n
tr
icity
r
an
g
es
f
r
o
m
0
to
1
,
s
o
it
r
eq
u
i
r
es
f
u
r
th
er
d
e
v
elo
p
m
en
t
to
ac
h
iev
e
a
wid
er
r
esu
lt
v
alu
e,
m
a
k
in
g
th
e
i
n
ter
v
al
b
r
o
ad
er
.
A
r
eg
io
n
ap
p
r
o
ac
h
in
g
a
s
tr
aig
h
t
lin
e
(
elo
n
g
ated
)
will
h
av
e
E
a
p
p
r
o
ac
h
in
g
a
lar
g
er
v
alu
e,
wh
ile
a
cir
cu
lar
r
eg
io
n
will
h
av
e
E
ap
p
r
o
ac
h
in
g
a
s
m
aller
v
alu
e
.
T
h
is
is
n
ee
d
ed
to
m
ea
s
u
r
e
th
e
elo
n
g
atio
n
o
f
an
eg
g
.
T
h
e
n
o
v
elty
o
f
e
cc
en
tr
icity
Plu
s
ca
n
b
e
d
escr
ib
ed
as f
o
llo
ws:
Step
1
: E
cc
en
tr
icity
an
d
m
u
lti
p
licatio
n
b
y
9
.
Ass
u
m
e:
E
is
th
e
o
r
ig
in
al
ec
ce
n
tr
icity
v
alu
e.
W
e
m
u
ltip
ly
th
is
ec
ce
n
tr
icity
v
alu
e
b
y
9
,
r
esu
ltin
g
in
Step
2
: A
p
p
licatio
n
o
f
c
o
n
d
itio
n
s
.
Nex
t,
we
ap
p
ly
t
h
e
f
o
llo
win
g
co
n
d
itio
n
s
to
th
e
r
esu
lt E
1
:
−
If
1
<
6
.
2721
,
th
en
s
u
b
tr
ac
t 3
.
1
3
9
f
r
o
m
th
e
r
esu
lt.
−
If
1
<
6
.
2721
,
th
en
2
=
1
−
3
.
139
.
=
√
−
*
9
=
√
−
*
9
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dev
elo
p
men
t o
f c
h
a
r
a
cter e
xtra
ctio
n
tech
n
iq
u
es to
d
etec
t c
h
icke
n
g
en
d
er b
a
s
ed
o
n
…
(
A
d
i
l S
etia
w
a
n
)
1855
−
If
1
>
6
.
2721
,
th
en
ad
d
3
.
1
3
9
to
t
h
e
r
esu
l
t.
−
If
1
>
6
.
2721
,
th
en
2
=
1
+
3
.
139
.
Step
3
: Fo
r
m
u
latin
g
t
h
e
eq
u
ati
o
n
b
ased
o
n
co
n
d
itio
n
s
.
W
e
th
en
f
o
r
m
u
late
th
e
eq
u
atio
n
E
2
b
ased
o
n
th
ese
co
n
d
itio
n
s
:
1.
Fo
r
E
1
=
9
E
,
J
ik
a
E
1
<
6
,
2
7
2
1
:
E
2
=
9
E
-
3
,
1
3
9
E
2
=
π
2.
Un
tu
k
E
1
=9
E
,
J
ik
a
E
1
>
6
,
2
7
2
1
:
E
2
=
9
E
+
3
.
1
3
9
E
2
=
π
Step
4
: D
eter
m
in
in
g
th
e
b
o
u
n
d
ar
ies o
f
B
atas
E
k
etik
a
1
b
er
u
b
ah
d
ar
i
k
u
r
an
g
d
ar
i
6
,
2
7
2
1
/2
π
m
en
j
ad
i
leb
ih
b
esar
d
ar
i
atau
s
am
a
d
en
g
an
6
,
2
7
2
1
ad
ala
h
:
E
=
6
,
2
7
2
1
/2
π
Ma
k
a,
=
(
6
,
2
7
2
1
1
)
=
2
π
T
h
e
b
o
u
n
d
a
r
y
o
f
E
wh
en
E
1
c
h
an
g
es f
r
o
m
less
th
an
6
.
2
7
2
1
/2
to
g
r
ea
ter
th
a
n
o
r
eq
u
al
t
o
6
.
2
7
2
1
is
:
E
=
6
,
2
7
2
1
/2
π
T
h
u
s
,
=
(
6
,
2
7
2
1
1
)
=
2
π
Step
5
: Fin
al
eq
u
atio
n
with
c
o
n
d
itio
n
s
.
C
o
m
b
in
e
b
o
th
co
n
d
itio
n
s
in
to
o
n
e
eq
u
atio
n
to
p
r
o
d
u
ce
th
e
f
i
n
al
f
o
r
m
u
la:
|
2
|
=
{
9
−
π
,
<
2
π
9
+
π
,
>
2
π
As
well
as
f
ea
tu
r
e
ex
tr
ac
tio
n
o
n
a
r
ea
f
e
atu
r
es
as
well
as
co
n
tr
ast,
en
er
g
y
,
h
o
m
o
g
e
n
eity
a
n
d
e
n
tr
o
p
y
.
T
h
e
s
h
ap
e
f
ea
tu
r
es
u
s
ed
ar
e
ec
ce
n
tr
icity
an
d
a
r
ea
.
W
h
er
e
th
e
o
b
ject
u
s
ed
ca
n
b
e
e
x
tr
ac
ted
in
to
6
ch
ar
ac
ter
is
tics
.
T
h
e
alg
o
r
ith
m
f
o
r
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
tag
es
u
s
ed
i
n
th
is
r
esear
ch
ca
n
b
e
s
ee
n
in
alg
o
r
ith
m
1
.
Alg
o
r
ith
m
1
.
New
f
ea
tu
r
e
e
x
tr
ac
tio
n
m
eth
o
d
1.
Read the edge detection image
2.
Convert image to double.
3.
Ca
rr
y
ou
t
th
e
Feature
Ext
raction
process
by
determining
the
Area,
Eccentricity,
Contras,
Correlation, Energy and Homogeneity values.
4.
Eccentricity Modified = arrayfun(@(E) ...
(9 * E
-
3.139) * (9 * E < 6.2721) + ...
(9 * E + 3.139) * (9 * E >= 6.2721), ... Eccentricity)
;
5.
Obtain the average value results from Feature Extraction.
6.
Determine the classification target
The values
will be saved in svm.mat
2
.
4
.
F
e
a
t
ure
s
elec
t
io
n
Featu
r
e
s
elec
tio
n
is
a
cr
u
cial
s
tag
e
in
p
r
ep
r
o
ce
s
s
in
g
f
o
r
d
et
ec
tio
n
,
aim
in
g
to
s
elec
t
th
e
m
o
s
t
r
elev
an
t
s
u
b
s
et
o
f
f
ea
tu
r
es
f
r
o
m
th
e
av
ailab
le
s
et.
T
h
is
r
esear
ch
em
p
lo
y
s
th
e
Gain
t
Sco
r
e
tech
n
iq
u
e,
wh
ich
co
m
b
i
n
es
attr
ib
u
te
r
an
k
in
g
with
th
e
ass
ess
m
en
t
o
f
ea
ch
f
ea
tu
r
e'
s
s
ig
n
if
ican
ce
b
ased
o
n
d
ata
ch
ar
ac
ter
is
tics
.
T
h
e
Gain
t
Sco
r
e
p
r
io
r
itizes
th
e
m
o
s
t
im
p
o
r
tan
t
o
r
r
elev
an
t
f
ea
t
u
r
es
f
o
r
th
e
d
ata
b
ein
g
p
r
o
ce
s
s
ed
.
I
n
p
r
ac
tice,
th
e
Gain
t
Sco
r
e
g
en
er
ates
a
r
an
k
in
g
o
f
f
ea
tu
r
es
b
ased
o
n
th
eir
s
ig
n
if
ican
ce
.
Usi
n
g
s
ix
p
r
e
d
eter
m
in
ed
f
ea
tu
r
es,
th
e
tech
n
iq
u
e
is
ex
p
ec
ted
to
p
r
o
d
u
ce
a
d
o
m
in
a
n
t
s
u
b
s
et,
with
h
ig
h
er
Gain
t
Sco
r
e
v
alu
es
in
d
icat
in
g
h
ig
h
er
p
r
io
r
ity
in
th
e
s
elec
tio
n
p
r
o
ce
s
s
.
=
−
(
2
)
2.
5
.
Cla
s
s
if
ica
t
io
n
I
n
th
e
im
ag
e
class
if
icatio
n
s
t
ag
e,
th
e
SVM
m
eth
o
d
is
em
p
lo
y
ed
to
class
if
y
eg
g
im
ag
e
s
in
to
two
ca
teg
o
r
ies:
m
ale
eg
g
s
an
d
f
e
m
ale
eg
g
s
[
3
3
]
,
[
3
4
]
.
T
h
e
im
ag
es
s
u
b
jecte
d
to
th
is
clas
s
if
i
ca
tio
n
s
tag
e
ar
e
n
ew
an
d
h
a
v
e
n
o
t
b
ee
n
p
r
ev
io
u
s
ly
p
r
o
ce
s
s
ed
.
T
h
e
im
a
g
e
g
r
o
u
p
i
n
g
p
r
o
ce
s
s
is
co
n
d
u
cted
in
two
m
ain
s
tep
s:
a)
T
r
ain
in
g
:
Data
o
b
tain
ed
f
r
o
m
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
tag
e
is
s
to
r
ed
in
a
s
p
ec
ialized
d
atab
a
s
e
co
n
tain
in
g
th
e
im
ag
e
ch
ar
ac
ter
is
tics
.
T
h
is
d
ata
is
th
en
u
s
ed
to
tr
ain
th
e
SVM
m
o
d
el.
T
h
e
tr
ain
in
g
p
r
o
ce
s
s
u
tili
ze
s
th
e
SVM
m
eth
o
d
,
wh
er
e
th
e
p
r
o
ce
s
s
ed
an
d
s
to
r
ed
d
ata
s
er
v
es
as
s
am
p
les
to
tr
ain
th
e
class
if
icat
io
n
m
o
d
el.
C
o
n
s
eq
u
en
tly
,
th
e
SVM
m
o
d
el
lear
n
s
to
d
if
f
er
e
n
tiate
th
e
ch
ar
ac
ter
is
tics
o
f
m
ale
an
d
f
em
ale
eg
g
im
ag
es b
ased
o
n
t
h
e
p
r
o
v
id
ed
tr
ain
in
g
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
5
1
-
1
8
6
1
1856
b)
T
esti
n
g
:
At
th
e
test
in
g
s
tag
e,
th
e
im
ag
es
in
th
e
test
in
g
f
o
ld
er
ar
e
u
s
ed
as
in
p
u
t
f
o
r
th
e
SVM
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
is
class
if
icatio
n
p
r
o
ce
s
s
aim
s
to
ev
alu
ate
th
e
ac
cu
r
ac
y
o
f
t
h
e
p
r
e
v
io
u
s
ly
tr
ain
e
d
SVM
m
o
d
el.
T
h
e
r
esu
lt o
f
th
is
class
if
icat
io
n
p
r
o
ce
s
s
is
th
e
g
r
o
u
p
in
g
o
f
im
ag
es in
to
two
ca
teg
o
r
ies:
m
ale
eg
g
s
an
d
f
em
ale
e
g
g
s
.
T
h
is
test
in
g
s
tag
e
ass
ess
e
s
th
e
SVM
m
o
d
el'
s
ab
ilit
y
to
class
if
y
n
e
w
im
ag
es
th
at
h
av
e
n
o
t b
ee
n
p
r
o
ce
s
s
ed
b
e
f
o
r
e.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
we
will
d
is
cu
s
s
in
d
etail
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
ea
c
h
p
r
o
ce
d
u
r
al
s
tag
e
co
n
d
u
cted
i
n
th
is
r
esear
ch
an
d
p
r
o
v
id
e
a
c
o
m
p
r
eh
e
n
s
iv
e
d
is
cu
s
s
io
n
o
f
t
h
e
p
r
e
v
io
u
s
ly
d
escr
ib
ed
r
esu
lt
s
.
T
h
e
o
u
tco
m
es
o
f
th
is
r
esear
ch
in
clu
d
e
a
v
ar
iet
y
o
f
im
a
g
es
p
r
o
d
u
ce
d
t
h
r
o
u
g
h
d
if
f
er
e
n
t
p
h
ases
o
f
t
h
e
r
ese
ar
ch
p
r
o
ce
s
s
.
T
h
ese
im
ag
es
en
co
m
p
ass
th
e
in
iti
al
in
p
u
t
im
ag
es
u
s
ed
in
t
h
e
r
esear
ch
,
im
a
g
es
o
b
tain
e
d
af
ter
th
e
in
itial
p
r
ep
r
o
ce
s
s
in
g
,
im
ag
es
th
at
h
av
e
u
n
d
er
g
o
n
e
th
e
m
ain
p
r
o
ce
s
s
in
g
s
tag
es,
an
d
th
e
f
in
al
im
ag
es
th
at
r
ef
lect
th
e
o
u
tp
u
t
o
f
th
e
e
n
tire
an
aly
s
is
an
d
p
r
o
ce
s
s
in
g
p
r
o
ce
d
u
r
e
.
3
.
1
.
P
re
-
pro
ce
s
s
ing
re
s
ult
3
.
1
.
1
.
I
m
a
g
e
inp
ut
re
s
ult
T
h
e
f
ir
s
t p
r
ep
r
o
ce
s
s
in
g
s
tag
e
i
n
th
is
r
esear
c
h
is
im
a
g
e
i
n
p
u
t.
T
h
e
in
p
u
t
im
a
g
e
is
a
n
R
GB
-
co
lo
r
ed
e
g
g
im
ag
e
in
J
PG
f
o
r
m
at,
en
ter
ed
i
n
to
th
e
d
ata
p
r
o
ce
s
s
in
g
s
y
s
tem
to
b
e
p
r
o
ce
s
s
ed
in
th
e
s
u
b
s
eq
u
en
t
s
tag
e.
T
h
e
in
p
u
t
im
ag
es
m
ee
t
th
e
s
tan
d
ar
d
s
f
o
r
d
ata
p
r
o
ce
s
s
in
g
,
in
clu
d
i
n
g
g
o
o
d
lig
h
tin
g
an
d
ac
c
u
r
ate
d
ata
co
llectio
n
.
A
to
tal
o
f
3
0
0
ch
ick
en
eg
g
im
a
g
es
will
b
e
u
s
ed
as
r
esear
c
h
o
b
jects.
As
a
s
am
p
le,
8
im
ag
es
ar
e
d
is
p
lay
ed
,
as
s
h
o
wn
in
T
ab
le
1
.
3
.
1
.
2
.
RG
B
im
a
g
e
t
o
g
ra
y
s
ca
le
im
a
g
e
re
s
ult
T
h
e
s
tep
s
to
co
n
v
er
t
a
co
lo
r
im
ag
e
to
a
g
r
ay
s
ca
le
im
ag
e
b
eg
in
with
ex
am
in
in
g
th
e
in
p
u
t
im
ag
e
to
d
eter
m
in
e
th
e
n
u
m
b
er
o
f
c
o
lo
r
ch
a
n
n
els.
I
f
th
e
im
ag
e
h
as
th
r
ee
co
l
o
r
c
h
an
n
els
(
R
GB
)
,
th
e
n
ex
t
s
tep
is
to
co
n
v
er
t
th
e
im
ag
e
to
g
r
ay
s
ca
le
u
s
in
g
th
e
`
r
g
b
2
g
r
ay
`
f
u
n
ct
io
n
.
T
h
e
co
n
v
e
r
s
io
n
r
esu
lt
s
ar
e
th
en
s
av
ed
f
o
r
f
u
r
th
er
u
s
e.
I
f
th
e
co
lo
r
c
h
an
n
el
s
ize
is
n
o
t
eq
u
al
to
3
,
it
in
d
icate
s
th
at
th
e
im
ag
e
is
n
o
t
in
R
GB
f
o
r
m
at,
s
o
th
e
im
ag
e
is
d
ir
ec
tly
co
p
ied
t
o
th
e
p
r
e_
b
im
ag
e
with
o
u
t
ch
a
n
g
es.
Af
ter
co
n
v
er
s
io
n
,
th
e
g
r
ay
s
ca
le
im
ag
e
is
d
is
p
lay
ed
in
th
e
s
p
ec
if
ie
d
ax
es
.
T
h
e
r
esu
lts
o
f
th
e
R
GB
to
g
r
ay
s
ca
le
co
n
v
er
s
io
n
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
T
ab
le
1
.
E
g
g
in
p
u
t im
ag
e
Eg
g
1
Eg
g
2
Eg
g
3
Eg
g
4
Eg
g
5
Eg
g
6
Eg
g
7
Eg
g
8
T
ab
le
2
.
R
GB
to
g
r
ay
s
ca
le,
Y
C
b
C
r
co
lo
r
s
p
ac
e
tr
an
s
f
o
r
m
atio
n
an
d
f
illi
n
g
h
o
les r
esu
lt
N
o
I
n
p
u
t
I
mag
e
R
G
B
I
mag
e
t
o
G
r
a
y
s
c
a
l
e
Y
C
b
C
r
C
o
l
o
r
S
p
a
c
e
F
i
l
l
i
n
g
H
o
l
e
s
N
o
I
n
p
u
t
I
mag
e
R
G
B
I
mag
e
t
o
G
r
a
y
s
c
a
l
e
Y
C
b
C
r
C
o
l
o
r
S
p
a
c
e
F
i
l
l
i
n
g
H
o
l
e
s
1
5
2
6
3
7
4
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dev
elo
p
men
t o
f c
h
a
r
a
cter e
xtra
ctio
n
tech
n
iq
u
es to
d
etec
t c
h
icke
n
g
en
d
er b
a
s
ed
o
n
…
(
A
d
i
l S
etia
w
a
n
)
1857
3
.
2
.
Seg
m
ent
a
t
i
o
n
re
s
ult
3
.
2
.
1
.
YCbCr
co
lo
r
s
pa
ce
t
ra
ns
f
o
rm
a
t
io
n r
esu
lt
T
h
e
YC
b
C
r
co
lo
r
s
p
ac
e
tr
an
s
f
o
r
m
atio
n
is
a
p
r
o
ce
s
s
wh
e
r
e
c
o
lo
r
s
in
R
GB
f
o
r
m
at
ar
e
s
ep
ar
ated
in
to
lu
m
in
an
ce
(
b
r
ig
h
tn
ess
)
an
d
c
h
r
o
m
in
a
n
ce
(
co
lo
r
)
in
f
o
r
m
ati
o
n
.
C
o
lo
r
s
in
th
e
R
GB
co
lo
r
s
p
ac
e
o
f
th
e
o
r
ig
i
n
al
im
ag
e
o
f
ten
r
etain
lig
h
tin
g
ef
f
ec
ts
th
at
ca
n
alter
co
lo
r
ch
ar
ac
ter
is
tics
.
T
o
m
itig
ate
th
i
s
i
s
s
u
e,
it
is
n
ec
es
s
ar
y
to
co
n
v
er
t
th
e
im
ag
e
in
to
a
ch
r
o
m
atic
co
lo
r
s
p
ac
e,
wh
ich
b
etter
r
ed
u
ce
s
th
e
in
f
lu
en
ce
o
f
li
g
h
tin
g
ef
f
ec
ts
.
T
h
e
YC
b
C
r
co
lo
r
m
o
d
el
is
co
m
m
o
n
ly
u
s
ed
f
o
r
t
h
is
p
u
r
p
o
s
e
b
ec
au
s
e
it
s
ep
ar
ates
th
e
co
lo
r
co
m
p
o
n
en
t
(
ch
r
o
m
i
n
an
ce
)
f
r
o
m
th
e
b
r
ig
h
t
n
ess
co
m
p
o
n
e
n
t
(
lu
m
i
n
an
ce
)
,
f
ac
ilit
atin
g
f
u
r
th
e
r
im
ag
e
p
r
o
c
ess
in
g
.
T
h
e
r
esu
lts
o
f
th
e
YC
b
C
r
co
lo
r
s
p
ac
e
t
r
an
s
f
o
r
m
atio
n
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
3
.
2
.
2
.
F
illi
ng
ho
les re
s
ult
T
h
e
s
tep
s
to
c
o
n
v
e
r
t
a
YC
b
C
r
im
ag
e
t
o
a
Ho
les
im
ag
e
b
eg
i
n
with
v
er
if
y
in
g
th
at
th
e
i
n
p
u
t
im
ag
e
h
as
th
r
ee
co
lo
r
c
h
an
n
els
(
R
GB
)
.
T
h
is
is
cr
u
cial
b
ec
au
s
e
p
r
o
p
er
co
n
v
er
s
io
n
o
f
a
YC
b
C
r
im
ag
e
to
a
Ho
les
im
ag
e
r
eq
u
ir
es
an
im
a
g
e
with
in
tac
t
R
GB
co
lo
r
ch
an
n
els.
On
ce
th
e
im
ag
e
m
ee
ts
th
ese
cr
ite
r
ia,
th
e
co
n
v
er
s
io
n
p
r
o
ce
s
s
is
ex
ec
u
ted
b
y
co
n
s
id
er
in
g
th
e
c
h
an
g
es
in
ea
ch
co
l
o
r
ch
an
n
el.
T
h
is
en
s
u
r
es
th
at
th
e
co
n
v
er
s
io
n
f
r
o
m
th
e
YC
b
C
r
im
ag
e
to
th
e
H
o
les
im
ag
e
is
p
er
f
o
r
m
e
d
ac
cu
r
ately
an
d
ef
f
icien
tly
,
r
esu
ltin
g
in
an
im
a
g
e
r
ep
r
esen
tatio
n
s
u
itab
le
f
o
r
s
u
b
s
eq
u
en
t a
n
aly
s
is
an
d
p
r
o
ce
s
s
in
g
.
T
h
e
r
esu
lts
o
f
th
e
Fil
lin
g
Ho
les p
r
o
ce
s
s
ca
n
b
e
s
ee
n
in
T
ab
le
2
.
3
.
3
.
E
dg
e
det
ec
t
io
n r
esu
lt
3
.
3
.
1
.
P
re
wit
t
edg
e
det
ec
t
i
o
n r
esu
lt
T
h
e
Pre
witt
m
eth
o
d
is
a
tech
n
iq
u
e
u
s
ed
in
th
e
im
ag
e
ed
g
e
d
etec
tio
n
s
tag
e,
aim
ed
at
r
ed
u
cin
g
n
o
is
e
in
ter
f
er
en
ce
b
ef
o
r
e
p
er
f
o
r
m
i
n
g
ed
g
e
d
etec
tio
n
ca
lc
u
latio
n
s
.
I
n
th
is
co
n
tex
t,
th
e
Pre
witt
m
eth
o
d
id
e
n
tifie
s
th
e
ed
g
es
o
f
o
b
jects
in
im
ag
es
b
y
u
tili
zin
g
th
e
Pre
witt
o
p
er
ato
r
.
T
o
test
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
Pre
witt
m
eth
o
d
in
d
etec
tin
g
ed
g
es,
a
p
r
o
g
r
a
m
was
cr
ea
ted
u
s
in
g
MA
T
L
AB
s
o
f
t
war
e.
T
h
is
s
tag
e
is
cr
u
cial
f
o
r
v
er
if
y
in
g
th
e
ed
g
e
d
etec
tio
n
r
esu
lts
p
r
o
d
u
ce
d
b
y
th
e
Pre
witt
m
et
h
o
d
,
allo
win
g
its
q
u
ality
to
b
e
m
ea
s
u
r
ed
an
d
ev
alu
ate
d
f
o
r
ac
cu
r
ac
y
.
T
h
e
r
esu
lts
o
f
th
e
Pre
witt e
d
g
e
d
etec
tio
n
ca
n
b
e
s
e
en
in
T
ab
le
3
.
3
.
3
.
2
.
B
ina
ry
t
ra
ns
f
o
rma
t
io
n
re
s
ult
T
h
is
s
tag
e
in
v
o
lv
es
p
r
o
d
u
cin
g
a
g
r
ad
atio
n
o
f
b
lack
(
b
it
0
)
an
d
wh
ite
(
b
it
1
)
.
T
y
p
ically
,
th
e
o
b
ject
p
ix
el
is
ass
ig
n
ed
a
v
alu
e
o
f
1
,
wh
ile
th
e
b
ac
k
g
r
o
u
n
d
p
i
x
el
is
as
s
ig
n
ed
a
v
alu
e
o
f
0
.
C
o
n
s
eq
u
en
tly
,
a
b
in
ar
y
im
ag
e
is
f
o
r
m
ed
b
y
co
lo
r
in
g
ea
ch
p
ix
el
as
wh
ite
o
r
b
lack
,
d
ep
en
d
i
n
g
o
n
its
lab
el.
T
h
e
k
ey
p
ar
am
eter
in
th
e
th
r
esh
o
ld
in
g
p
r
o
ce
s
s
is
th
e
s
el
ec
tio
n
o
f
th
e
th
r
esh
o
ld
v
alu
e.
T
h
er
e
ar
e
s
ev
er
al
m
eth
o
d
s
av
a
ilab
le
f
o
r
ch
o
o
s
in
g
an
ap
p
r
o
p
r
iate
th
r
esh
o
ld
v
alu
e
.
T
h
e
r
esu
lts
o
f
th
e
b
in
ar
y
tr
an
s
f
o
r
m
atio
n
ca
n
b
e
s
ee
n
i
n
T
ab
le
3
.
T
ab
le
3
.
Pre
witt
ed
g
e
d
etec
tio
n
an
d
b
in
ar
y
tr
an
s
f
o
r
m
atio
n
r
e
s
u
lt
No
F
i
l
l
i
n
g
H
o
l
e
s
P
r
e
w
i
t
t
E
d
g
e
D
e
t
e
c
t
i
o
n
B
i
n
a
r
y
Tr
a
n
sf
o
r
-
mat
i
o
n
No
F
i
l
l
i
n
g
H
o
l
e
s
P
r
e
w
i
t
t
E
d
g
e
D
e
t
e
c
t
i
o
n
B
i
n
a
r
y
Tr
a
n
sf
o
r
-
mat
i
o
n
1
5
2
6
3
7
4
8
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
5
1
-
1
8
6
1
1858
3
.
4
.
F
e
a
t
ure
ex
t
r
a
ct
io
n r
esu
lt
3
.
4
.
1
.
O
ld
f
ea
t
ure
ex
t
ra
ct
i
o
n m
et
ho
d r
esu
lt
Featu
r
e
ex
tr
ac
tio
n
is
a
p
r
o
ce
s
s
th
at
ex
tr
ac
ts
im
p
o
r
tan
t
in
f
o
r
m
atio
n
o
r
c
h
ar
ac
ter
is
tics
f
r
o
m
d
ata,
with
th
e
o
b
tain
ed
v
alu
es
b
ein
g
a
n
a
ly
ze
d
f
u
r
t
h
er
in
s
u
b
s
eq
u
en
t
r
e
s
ea
r
ch
o
r
ap
p
licatio
n
s
.
I
n
th
is
r
esear
ch
,
th
er
e
is
a
n
o
v
el
asp
ec
t h
ig
h
lig
h
ted
at
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
tag
e,
f
o
c
u
s
in
g
o
n
t
h
e
d
ev
el
o
p
m
en
t
o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
an
d
s
elec
tio
n
alg
o
r
ith
m
s
k
n
o
wn
as
ec
ce
n
tr
icity
f
ea
tu
r
e
d
e
v
elo
p
m
en
t.
T
h
e
p
ar
am
eter
s
u
s
ed
to
tr
ac
k
f
ea
tu
r
es
in
th
e
im
ag
e
in
clu
d
e
ec
ce
n
t
r
icity
r
a
tio
,
ar
ea
,
co
n
tr
ast,
en
e
r
g
y
,
h
o
m
o
g
e
n
eity
,
an
d
e
n
tr
o
p
y
.
T
h
e
s
h
ap
e
f
ea
tu
r
es
o
f
p
ar
ticu
lar
c
o
n
ce
r
n
in
th
is
r
es
ea
r
ch
ar
e
ec
ce
n
tr
icity
an
d
ar
e
a,
wh
ich
ar
e
cr
u
cial
i
n
d
icato
r
s
in
d
escr
ib
in
g
t
h
e
ch
ar
ac
ter
is
tics
o
f
a
n
o
b
ject
in
an
im
ag
e.
B
y
an
al
y
zin
g
th
ese
f
ea
tu
r
es,
o
b
jects
in
th
e
im
a
g
e
ca
n
b
e
ex
tr
ac
ted
an
d
r
e
p
r
esen
ted
m
o
r
e
co
m
p
r
e
h
en
s
iv
ely
u
s
in
g
s
ix
d
if
f
er
e
n
t
c
h
ar
ac
ter
is
tics
,
f
ac
ilit
atin
g
f
u
r
t
h
er
an
al
y
s
is
o
f
th
ese
o
b
jects.
T
h
e
r
esu
lts
o
f
th
e
o
ld
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
r
esu
lt c
an
b
e
s
ee
n
in
T
a
b
le
4
.
3
.
4
.
2
.
New
f
ea
t
ure
ex
t
ra
ct
io
n
m
et
ho
d r
esu
lt
Featu
r
e
s
elec
tio
n
is
a
cr
itical
s
tep
in
th
e
p
r
e
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
f
o
r
d
etec
tio
n
,
wh
er
e
th
is
r
esear
ch
ad
o
p
ts
th
e
attr
ib
u
te
f
r
eq
u
e
n
t
s
elec
tio
n
(
ASF)
tech
n
iq
u
e
to
o
p
tim
ize
th
e
p
r
o
ce
s
s
.
ASF
i
s
u
s
ed
to
p
r
io
r
itize
attr
ib
u
tes
an
d
ass
ess
th
eir
im
p
o
r
tan
ce
b
ased
o
n
th
e
s
p
ec
if
ic
n
ee
d
s
o
f
th
e
d
ata
b
ein
g
p
r
o
ce
s
s
ed
.
I
n
th
is
s
tag
e,
af
ter
ap
p
ly
in
g
th
e
ASF
tech
n
i
q
u
e
t
o
th
e
s
ix
s
elec
ted
f
ea
tu
r
e
s
,
th
e
g
o
al
is
t
o
o
b
tain
th
e
m
o
s
t
d
o
m
in
an
t
f
ea
tu
r
e
s
u
b
s
et.
T
h
is
is
ac
h
iev
e
d
b
y
p
r
o
d
u
cin
g
a
s
eq
u
en
ce
o
f
f
ea
t
u
r
e
ASF
v
alu
es
f
r
o
m
h
ig
h
est
to
lo
west,
m
ak
in
g
it
ea
s
ier
to
s
elec
t
th
e
f
ea
tu
r
es
to
b
e
u
s
ed
b
ased
o
n
t
h
e
s
p
ec
if
ic
n
ee
d
s
o
f
th
e
d
ata
an
al
y
s
is
b
ein
g
ca
r
r
ie
d
o
u
t.
T
h
e
r
esu
lts
o
f
th
e
n
ew
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
r
esu
lt c
an
b
e
s
ee
n
in
T
ab
le
4
.
3
.
5
.
Cla
s
s
if
ica
t
io
n
re
s
ult
Af
ter
th
e
p
r
ev
io
u
s
s
tag
e
is
co
m
p
leted
,
th
e
n
ex
t
s
tep
is
to
d
eter
m
in
e
th
e
eg
g
s
am
p
le
s
ize
b
ased
o
n
p
r
ev
io
u
s
r
esu
lts
.
I
n
th
is
co
n
tex
t,
th
e
SVM
class
if
icatio
n
m
eth
o
d
is
ap
p
lied
to
p
r
o
ce
s
s
th
e
eg
g
s
ize
m
ea
s
u
r
em
en
ts
,
u
s
in
g
s
ix
f
ea
tu
r
es
g
en
er
ated
f
r
o
m
th
e
m
o
s
t
r
elev
an
t
g
e
o
m
etr
ic
p
r
o
p
e
r
ties
o
f
th
e
ellip
s
e.
T
h
ese
f
ea
tu
r
es
in
clu
d
e
v
a
r
io
u
s
p
ar
a
m
eter
s
ca
lcu
lated
f
r
o
m
th
e
g
eo
m
etr
ic
ch
ar
ac
ter
is
tics
o
f
th
e
ellip
s
e,
wh
ich
ar
e
th
en
u
s
ed
in
t
h
e
class
if
icatio
n
p
r
o
ce
s
s
to
ac
cu
r
ately
d
eter
m
in
e
eg
g
s
ize.
I
n
T
ab
le
4
,
th
e
r
esu
lts
o
f
th
e
m
ale
eg
g
im
ag
e
test
d
ata
ca
n
b
e
s
h
o
wn
.
Y
o
u
ca
n
s
ee
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
r
esu
lts
in
th
e
im
ag
e
as
f
o
llo
ws:
ar
ea
=
1
2
9
0
1
9
4
,
e
cc
en
tr
icity
=
6
.
5
6
,
co
n
tr
ast
=
0
.
0
3
,
co
r
r
elatio
n
=
0
.
9
9
,
en
er
g
y
=
0
.
4
4
,
h
o
m
o
g
e
n
eity
=
0
.
9
8
T
h
e
p
r
o
ce
s
s
t
h
at
o
cc
u
r
s
at
t
h
e
class
if
icatio
n
s
tag
e
is
th
at
th
e
test
im
ag
e
s
to
r
ed
in
th
e
test
in
g
f
o
ld
er
is
s
elec
ted
ac
co
r
d
in
g
to
th
e
im
ag
e
y
o
u
wan
t
to
test
.
I
f
th
e
eg
g
im
a
g
e
is
s
elec
ted
th
en
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
f
o
r
th
e
test
d
ata
w
ill
wo
r
k
.
T
h
e
r
esu
lts
o
f
th
e
s
el
ec
ted
test
d
ata
ca
n
g
r
o
u
p
th
e
im
ag
es
ac
co
r
d
in
g
t
o
th
e
s
p
ec
if
ied
r
esu
lts
as
in
th
e
im
ag
e
ab
o
v
e.
T
h
e
r
esu
lts
id
en
tifie
d
m
ale
eg
g
s
T
ab
le
4
.
C
lass
if
icatio
n
r
esu
lts
o
f
test
d
ata
f
o
r
m
ale
eg
g
ty
p
es
.
T
ab
le
4
.
Old
f
ea
tu
r
e,
n
ew
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
eth
o
d
No
an
d
class
if
icatio
n
r
esu
lt
No
A
r
e
a
Ec
c
e
n
t
r
i
c
i
t
y
C
o
n
t
r
a
st
C
o
r
r
e
l
a
t
i
o
n
En
e
r
g
y
H
o
mo
g
e
n
e
i
t
y
C
l
a
s
si
f
i
c
a
t
i
o
n
O
l
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
met
h
o
d
1
1
2
9
0
1
9
4
6
,
5
0
,
0
3
0
,
9
9
0
,
4
5
0
,
9
8
M
a
l
e
2
1
2
9
8
5
0
1
6
,
7
0
,
0
2
0
,
9
9
0
,
4
6
0
,
9
8
M
a
l
e
3
1
3
0
2
8
0
2
6
,
7
0
,
0
2
0
,
9
9
0
,
4
5
0
,
9
9
M
a
l
e
4
1
3
2
5
5
0
9
6
,
8
0
,
0
3
0
,
9
9
0
,
4
5
0
,
9
9
M
a
l
e
5
1
3
2
4
0
7
2
6
,
8
0
,
0
3
0
,
9
9
0
,
4
5
0
,
9
9
F
e
mal
e
6
1
3
2
0
3
8
0
6
,
8
0
,
0
3
0
,
9
9
0
,
4
5
0
,
9
8
F
e
mal
e
7
1
2
9
7
0
0
5
6
,
8
0
,
0
2
0
,
9
9
0
,
4
5
0
,
9
9
F
e
mal
e
8
1
3
4
0
0
5
6
6
,
8
0
,
0
3
0
,
9
9
0
,
4
4
0
,
9
8
F
e
mal
e
N
e
w
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
1
5
9
,
1
9
5
,
9
9
2
,
7
9
1
0
0
5
,
7
5
4
8
3
,
0
M
a
l
e
2
7
7
,
6
9
8
,
0
4
3
,
0
6
-
4
0
,
3
1
7
,
0
2
4
,
4
M
a
l
e
3
7
9
,
6
9
8
,
6
-
3
1
,
5
8
-
1
9
,
8
3
1
0
,
0
6
6
1
,
7
M
a
l
e
4
1
0
0
9
9
,
8
5
9
,
9
5
5
9
,
3
3
1
0
,
1
4
-
5
,
9
M
a
l
e
5
9
8
,
5
9
9
,
5
6
8
,
3
4
9
0
,
0
9
7
,
7
6
-
1
1
8
,
5
F
e
mal
e
6
9
1
,
9
9
9
,
7
1
0
0
4
9
,
8
6
9
,
1
7
-
2
7
4
,
3
F
e
mal
e
7
4
3
,
3
9
9
,
9
-
5
2
,
6
-
3
8
,
8
6
5
,
7
4
1
0
0
F
e
mal
e
8
1
2
5
,
5
9
5
,
9
6
2
,
0
9
9
4
1
,
8
5
9
,
5
6
-
1
9
7
,
8
F
e
mal
e
4.
CO
NCLU
SI
O
N
Ob
tain
in
g
r
elev
an
t
d
ata
f
o
r
d
i
f
f
er
en
t
ty
p
es
o
f
c
h
ick
e
n
s
p
r
es
en
ts
s
ig
n
if
ican
t
ch
allen
g
es
d
u
e
to
lim
ited
im
ag
er
y
.
T
o
ad
d
r
ess
th
is
,
r
esear
ch
er
s
d
ev
elo
p
ed
an
in
n
o
v
ati
v
e
e
cc
en
tr
icity
p
ar
am
ete
r
tech
n
iq
u
e
f
o
r
d
etec
tin
g
g
en
d
er
in
ch
ic
k
en
eg
g
s
.
T
h
is
s
tu
d
y
in
tr
o
d
u
ce
d
m
o
d
els f
o
r
f
e
atu
r
e
ex
tr
ac
tio
n
an
d
s
elec
tio
n
u
s
in
g
th
e
ex
tr
ac
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
Dev
elo
p
men
t o
f c
h
a
r
a
cter e
xtra
ctio
n
tech
n
iq
u
es to
d
etec
t c
h
icke
n
g
en
d
er b
a
s
ed
o
n
…
(
A
d
i
l S
etia
w
a
n
)
1859
an
d
s
elec
tio
n
-
to
tal
o
f
f
ea
tu
r
es
(ES
-
T
F)
m
eth
o
d
.
T
h
e
E
S
-
T
F
m
eth
o
d
tr
ac
k
s
f
ea
tu
r
e
r
atio
s
o
f
e
cc
en
tr
icity
,
Ar
ea
,
E
n
er
g
y
,
C
o
n
tr
ast,
Ho
m
o
g
e
n
eity
,
an
d
C
o
r
r
elatio
n
t
o
id
en
tif
y
k
ey
ch
a
r
ac
ter
is
tics
.
T
h
e
d
ataset
in
clu
d
ed
3
0
0
im
ag
es,
eq
u
ally
d
iv
id
e
d
in
to
1
5
0
m
ale
an
d
1
5
0
f
em
ale
eg
g
im
ag
es,
an
d
was
f
u
r
th
er
ex
p
a
n
d
ed
to
in
co
r
p
o
r
ate
1
5
0
tr
ai
n
in
g
d
ata
p
o
in
ts
with
3
0
0
m
ale
an
d
f
em
ale
e
g
g
o
b
je
ct
d
ata
an
d
8
0
test
d
ata
p
o
in
ts
with
3
0
0
m
ale
a
n
d
f
em
ale
im
ag
e
d
ata.
T
h
e
s
tu
d
y
f
o
cu
s
ed
o
n
f
ea
tu
r
e
s
elec
tio
n
b
y
m
ea
s
u
r
i
n
g
t
h
e
d
is
tan
ce
b
et
wee
n
th
e
v
alu
es
o
f
m
ale
an
d
f
em
ale
eg
g
im
ag
e
ex
tr
ac
ts
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
d
if
f
er
en
ce
s
b
etwe
en
m
ale
an
d
f
em
ale
eg
g
im
ag
es,
with
th
e
f
o
llo
win
g
f
ea
tu
r
e
v
alu
es:
e
cc
en
tr
icity
=
9
8
.
9
5
,
a
r
ea
=
8
4
.
4
8
,
e
n
er
g
y
=
4
3
.
2
5
,
c
o
n
tr
ast
=
3
0
.
6
4
,
h
o
m
o
g
e
n
eity
=
7
.
3
1
,
an
d
c
o
r
r
elatio
n
=
0
.
0
1
.
T
h
ese
v
alu
es
h
i
g
h
lig
h
t
t
h
e
ef
f
ec
tiv
en
ess
o
f
th
e
f
ea
tu
r
e
ex
t
r
ac
tio
n
a
n
d
s
elec
ti
o
n
p
r
o
ce
s
s
.
T
h
is
s
tu
d
y
s
h
o
w
ca
s
es
th
e
n
o
v
elty
o
f
th
e
d
ev
elo
p
ed
e
cc
e
n
tr
icity
p
ar
am
eter
tech
n
i
q
u
e
an
d
th
e
E
S
-
T
F
m
eth
o
d
in
ef
f
e
ctiv
e
ly
d
if
f
er
en
tiatin
g
g
en
d
er
in
ch
ick
en
eg
g
s
.
T
h
e
s
ig
n
if
ican
t
v
alu
es
o
b
tain
ed
f
o
r
ea
ch
f
ea
tu
r
e
u
n
d
e
r
s
co
r
e
th
e
r
o
b
u
s
tn
ess
o
f
th
e
a
p
p
r
o
ac
h
,
o
f
f
er
in
g
a
r
eliab
le
f
o
u
n
d
atio
n
f
o
r
f
u
r
th
er
r
esear
c
h
an
d
a
p
p
licatio
n
in
p
o
u
ltry
s
c
ien
ce
an
d
in
d
u
s
tr
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esear
ch
was
n
o
t
s
u
p
p
o
r
t
ed
b
y
an
y
g
r
an
ts
f
r
o
m
f
u
n
d
in
g
b
o
d
ies
in
th
e
p
u
b
lic,
p
r
iv
ate,
o
r
n
o
t
-
f
o
r
-
p
r
o
f
it secto
r
s
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Ad
il Setiawa
n
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Yu
h
an
d
r
i
✓
✓
✓
✓
✓
✓
✓
✓
Mu
h
am
m
ad
T
aju
d
d
i
n
✓
✓
✓
✓
✓
✓
✓
✓
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
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
E
T
H
I
CAL AP
P
RO
V
AL
T
h
e
r
esear
ch
r
elate
d
to
an
i
m
a
l
u
s
e
h
as
b
ee
n
co
m
p
lied
with
all
th
e
r
elev
an
t
n
atio
n
al
r
eg
u
l
atio
n
s
an
d
in
s
titu
tio
n
al
p
o
licies f
o
r
th
e
ca
r
e
an
d
u
s
e
o
f
an
im
als.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
t
h
at
s
u
p
p
o
r
t
t
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
a
r
e
av
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
a
u
th
o
r
,
[
AS
]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
I
.
S
e
ma
a
n
d
A
.
G
ü
l
s
e
n
,
“
A
n
i
n
v
e
s
t
i
g
a
t
i
o
n
o
n
t
h
e
d
e
t
e
r
mi
n
a
t
i
o
n
o
f
f
a
c
t
o
r
s
i
n
f
l
u
e
n
c
i
n
g
c
h
i
c
k
se
x
p
r
e
d
i
c
t
i
o
n
i
n
h
a
t
c
h
i
n
g
e
g
g
s
,
”
Af
ri
c
a
n
J
o
u
r
n
a
l
o
f
A
g
ri
c
u
l
t
u
r
a
l
Re
s
e
a
rch
,
v
o
l
.
9
,
n
o
.
6
,
p
p
.
6
0
3
–
6
0
6
,
F
e
b
.
2
0
1
9
,
d
o
i
:
1
0
.
5
8
9
7
/
a
j
a
r
2
0
1
3
.
8
2
3
0
.
[
2
]
K
.
B
h
a
r
o
d
i
y
a
a
n
d
A
.
M
.
G
o
n
s
a
i
,
“
A
n
i
mp
r
o
v
e
d
e
d
g
e
d
e
t
e
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
X
-
R
a
y
i
m
a
g
e
s
b
a
se
d
o
n
t
h
e
st
a
t
i
s
t
i
c
a
l
r
a
n
g
e
,
”
H
e
l
i
y
o
n
,
v
o
l
.
5
,
n
o
.
1
0
,
p
.
e
0
2
7
4
3
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
1
9
.
e
0
2
7
4
3
.
[
3
]
M
.
A
.
A
n
sar
i
,
D
.
K
u
r
c
h
a
n
i
y
a
,
a
n
d
M
.
D
i
x
i
t
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
s
i
s
o
f
i
m
a
g
e
e
d
g
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
O
p
t
i
c
s
a
n
d
L
a
ser
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
9
8
,
p
p
.
1
5
7
-
1
6
8
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
l
e
o
.
2
0
1
7
.
0
9
.
2
0
2
.
[
4
]
K
.
S
h
a
h
,
V
.
K
e
d
i
a
,
R
.
R
a
u
t
,
S
.
A
n
sa
r
i
,
a
n
d
A
.
S
h
r
o
f
f
,
“
Ev
a
l
u
a
t
i
o
n
a
n
d
c
o
mp
a
r
a
t
i
v
e
s
t
u
d
y
o
f
e
d
g
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
I
O
S
R
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
2
,
n
o
.
5
,
p
p
.
6
–
1
5
,
O
c
t
.
2
0
2
0
,
d
o
i
:
1
0
.
9
7
9
0
/
0
6
6
1
-
2
2
0
5
0
3
0
6
1
5
.
[
5
]
D
h
r
u
v
,
N
.
M
i
t
t
a
l
,
a
n
d
M
.
M
o
d
i
,
“
C
o
mp
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
e
d
g
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
m
e
d
i
c
a
l
i
m
a
g
e
s
o
f
d
i
f
f
e
r
e
n
t
b
o
d
y
p
a
r
t
s,
”
i
n
Da
t
a
S
c
i
e
n
c
e
a
n
d
An
a
l
y
t
i
c
s
,
S
p
r
i
n
g
e
r
S
i
n
g
a
p
o
r
e
,
2
0
1
8
,
p
p
.
1
6
4
–
1
7
6
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
10
-
8
5
2
7
-
7
_
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
38
,
No
.
3
,
J
u
n
e
20
25
:
1
8
5
1
-
1
8
6
1
1860
[
6
]
I
.
N
.
M
o
h
a
p
a
t
r
a
,
“
I
mag
e
e
d
g
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
T
ra
n
s
a
c
t
i
o
n
s
o
n
I
m
a
g
e
Pr
o
c
e
ssi
n
g
a
n
d
C
o
m
p
u
t
e
r
Vi
s
i
o
n
,
v
o
l
.
5
,
n
o
.
1
5
,
p
p
.
15
–
1
9
,
D
e
c
.
2
0
1
9
,
d
o
i
:
1
0
.
1
9
1
0
1
/
t
i
p
c
v
.
2
0
1
9
.
5
1
5
0
0
8
.
[
7
]
I
.
V
a
n
k
o
v
a
e
t
a
l
.
,
“
M
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
u
s
e
f
u
l
i
n
t
h
e
d
i
f
f
e
r
e
n
t
i
a
l
d
i
a
g
n
o
si
s
b
e
t
w
e
e
n
u
n
d
i
f
f
e
r
e
n
t
i
a
t
e
d
c
a
r
c
i
n
o
m
a
a
n
d
g
a
s
t
r
o
i
n
t
e
s
t
i
n
a
l
s
t
r
o
m
a
l
t
u
m
o
r
,
”
An
n
a
l
s
o
f
D
i
a
g
n
o
st
i
c
Pa
t
h
o
l
o
g
y
,
v
o
l
.
4
6
,
p
.
1
5
1
5
2
7
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
n
n
d
i
a
g
p
a
t
h
.
2
0
2
0
.
1
5
1
5
2
7
.
[
8
]
B
a
i
,
“
M
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
f
o
r
d
e
t
a
i
l
-
ma
i
n
t
a
i
n
e
d
i
ma
g
e
e
n
h
a
n
c
e
me
n
t
b
y
u
si
n
g
t
w
o
t
y
p
e
s
o
f
a
l
t
e
r
n
a
t
i
n
g
f
i
l
t
e
r
s
a
n
d
t
h
r
e
s
h
o
l
d
c
o
n
s
t
r
a
i
n
e
d
s
t
r
a
t
e
g
y
,
”
O
p
t
i
k
-
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
f
o
r
L
i
g
h
t
a
n
d
El
e
c
t
r
o
n
O
p
t
i
c
s
,
v
o
l
.
1
2
6
,
n
o
.
2
4
,
p
p
.
5
0
3
8
–
5
0
4
3
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
l
e
o
.
2
0
1
5
.
0
9
.
2
0
2
.
[
9
]
S
.
C
h
i
d
a
m
b
a
r
a
n
a
t
h
a
n
,
A
.
R
a
d
h
i
k
a
,
V
.
V
.
P
r
i
y
a
,
S
.
K
.
M
o
h
a
n
,
a
n
d
M
.
G
.
G
i
r
e
e
sh
a
n
,
“
O
p
t
i
ma
l
S
V
M
b
a
se
d
b
r
a
i
n
t
u
mo
r
M
R
I
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
i
n
c
l
o
u
d
I
n
t
e
r
n
e
t
o
f
M
e
d
i
c
a
l
T
h
i
n
g
s,
”
i
n
C
o
g
n
i
t
i
v
e
I
n
t
e
r
n
e
t
o
f
M
e
d
i
c
a
l
T
h
i
n
g
s
f
o
r
S
m
a
rt
H
e
a
l
t
h
c
a
re
,
S
p
r
i
n
g
e
r
,
C
h
a
m,
2
0
2
1
,
p
p
.
8
7
–
1
0
3
,
d
o
i
:
1
0
.
2
2
1
4
6
/
i
j
i
t
e
e
.
6
2
6
6
3
.
[
1
0
]
I
.
V
.
M
u
t
n
e
j
a
,
“
M
e
t
h
o
d
s
o
f
i
m
a
g
e
e
d
g
e
d
e
t
e
c
t
i
o
n
:
A
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
E
l
e
c
t
r
o
n
i
c
S
y
st
e
m
s
,
v
o
l
.
4
,
n
o
.
2
,
2
0
1
5
,
d
o
i
:
1
0
.
4
1
7
2
/
2
3
3
2
-
0
7
9
6
.
1
0
0
0
1
5
0
.
[
1
1
]
J.
L
.
D
i
o
ses,
R
.
P
.
M
e
d
i
n
a
,
A
.
C
.
F
a
j
a
r
d
o
,
a
n
d
A
.
A
.
H
e
r
n
a
n
d
e
z
,
“
P
e
r
f
o
r
man
c
e
o
f
c
l
a
ss
i
f
i
c
a
t
i
o
n
m
o
d
e
l
s
i
n
Ja
p
a
n
e
s
e
q
u
a
i
l
e
g
g
sex
i
n
g
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
1
I
EEE
1
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
l
l
o
q
u
i
u
m
o
n
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
&
I
t
s
A
p
p
l
i
c
a
t
i
o
n
s
(
C
S
PA)
,
M
a
r
.
2
0
2
1
,
p
p
.
2
9
–
3
4
,
d
o
i
:
1
0
.
1
1
0
9
/
C
S
P
A
5
2
1
4
1
.
2
0
2
1
.
9
3
7
7
2
7
5
.
[
1
2
]
N
.
A
.
F
a
d
c
h
a
r
a
n
d
J
.
C
.
D
.
C
r
u
z
,
“
P
r
e
d
i
c
t
i
o
n
m
o
d
e
l
f
o
r
c
h
i
c
k
e
n
e
g
g
f
e
r
t
i
l
i
t
y
u
si
n
g
a
r
t
i
f
i
c
i
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
2
0
I
EEE
7
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
d
u
s
t
ri
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
(
I
C
I
EA)
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
,
2
0
2
0
,
p
p
.
9
1
6
–
9
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
EA
4
9
7
7
4
.
2
0
2
0
.
9
1
0
1
9
6
6
.
[
1
3
]
M
.
H
a
s
h
e
m
z
a
d
e
h
a
n
d
N
.
F
a
r
a
j
z
a
d
e
h
,
“
A
m
a
c
h
i
n
e
v
i
si
o
n
s
y
s
t
e
m
f
o
r
d
e
t
e
c
t
i
n
g
f
e
r
t
i
l
e
e
g
g
s
i
n
t
h
e
i
n
c
u
b
a
t
i
o
n
i
n
d
u
st
r
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
y
s
t
e
m
s
,
v
o
l
.
9
,
n
o
.
5
,
p
p
.
8
5
0
–
8
6
2
,
S
e
p
.
2
0
1
6
,
d
o
i
:
1
0
.
1
0
8
0
/
1
8
7
5
6
8
9
1
.
2
0
1
6
.
1
2
3
7
1
8
5
.
[
1
4
]
K
.
O
.
I
d
a
h
o
r
,
L
.
A
.
F
.
A
k
i
n
o
l
a
,
a
n
d
S
.
S
.
C
h
i
a
“
P
r
e
d
e
t
e
r
m
i
n
a
t
i
o
n
o
f
q
u
a
i
l
c
h
i
c
k
s
e
x
u
si
n
g
e
g
g
i
n
d
i
c
e
s
i
n
n
o
r
t
h
c
e
n
t
r
a
l
N
i
g
e
r
i
a
,
”
J
o
u
rn
a
l
o
f
An
i
m
a
l
Pr
o
d
u
c
t
i
o
n
Ad
v
a
n
c
e
s
,
v
o
l
.
5
,
n
o
.
1
,
p
.
5
9
9
,
2
0
1
5
,
d
o
i
:
1
0
.
5
4
5
5
/
j
a
p
a
.
2
0
1
4
1
2
2
3
0
7
4
3
1
1
.
[
1
5
]
I
.
I
n
d
r
a
,
T.
H
a
sa
n
u
d
d
i
n
,
R
.
S
a
t
r
a
,
a
n
d
N
.
R
.
W
i
b
o
w
o
,
“
E
g
g
s
d
e
t
e
c
t
i
o
n
u
s
i
n
g
O
t
s
u
t
h
r
e
s
h
o
l
d
i
n
g
me
t
h
o
d
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
8
2
n
d
Ea
s
t
I
n
d
o
n
e
s
i
a
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
EI
C
o
n
C
I
T
)
,
M
a
k
a
ss
a
r
,
I
n
d
o
n
e
s
i
a
,
2
0
1
8
,
p
p
.
1
0
–
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
EI
C
o
n
C
I
T.
2
0
1
8
.
8
8
7
8
5
1
7
.
[
1
6
]
J.
Th
i
p
a
k
o
r
n
,
R
.
W
a
r
a
n
u
s
a
st
,
a
n
d
P
.
R
i
y
a
m
o
n
g
k
o
l
,
“
E
g
g
w
e
i
g
h
t
p
r
e
d
i
c
t
i
o
n
a
n
d
e
g
g
si
z
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
i
ma
g
e
p
r
o
c
e
ss
i
n
g
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
7
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
r
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
/
El
e
c
t
r
o
n
i
c
s
,
C
o
m
p
u
t
e
r,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
E
C
T
I
-
C
O
N
)
,
Ju
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
e
c
t
i
c
o
n
.
2
0
1
7
.
8
0
9
6
2
7
8
.
[
1
7
]
J.
Th
i
p
a
k
o
r
n
,
R
.
W
a
r
a
n
u
s
a
st
,
a
n
d
P
.
R
i
y
a
m
o
n
g
k
o
l
,
“
E
g
g
w
e
i
g
h
t
p
r
e
d
i
c
t
i
o
n
a
n
d
e
g
g
si
z
e
c
l
a
ssi
f
i
c
a
t
i
o
n
u
si
n
g
i
ma
g
e
p
r
o
c
e
ss
i
n
g
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
,
”
p
res
e
n
t
e
d
a
t
t
h
e
2
0
1
7
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
/
El
e
c
t
ro
n
i
c
s,
C
o
m
p
u
t
e
r,
T
e
l
e
c
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
E
C
T
I
-
C
O
N
)
,
Ju
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
e
c
t
i
c
o
n
.
2
0
1
7
.
8
0
9
6
2
7
8
.
[
1
8
]
K
.
B
r
e
si
l
l
a
e
t
a
l
.
,
“
S
i
n
g
l
e
-
sh
o
t
c
o
n
v
o
l
u
t
i
o
n
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
r
e
a
l
-
t
i
m
e
f
r
u
i
t
d
e
t
e
c
t
i
o
n
w
i
t
h
i
n
t
h
e
t
r
e
e
,
”
F
ro
n
t
i
e
rs
i
n
P
l
a
n
t
S
c
i
e
n
c
e
,
v
o
l
.
1
0
,
M
a
y
2
0
1
9
,
d
o
i
:
1
0
.
3
3
8
9
/
f
p
l
s
.
2
0
1
9
.
0
0
6
1
1
.
[
1
9
]
K
a
u
r
a
n
d
D
.
S
i
n
g
h
,
“
G
e
o
met
r
i
c
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
o
f
s
e
l
e
c
t
e
d
r
i
c
e
g
r
a
i
n
s u
s
i
n
g
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
t
e
c
h
n
i
q
u
e
s,”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
C
h
e
m
i
c
a
l
An
a
l
y
si
s
(
I
J
C
A)
,
v
o
l
.
1
2
4
,
n
o
.
8
,
p
p
.
4
1
–
4
6
,
A
u
g
.
2
0
1
5
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
1
5
9
0
5
5
7
6
.
[
2
0
]
G
.
K
u
m
a
r
a
n
d
P
.
K
.
B
h
a
t
i
a
,
P
.
K
.
“
A
d
e
t
a
i
l
e
d
r
e
v
i
e
w
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
i
n
i
ma
g
e
p
r
o
c
e
ss
i
n
g
sy
s
t
e
ms
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
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
i
e
s
,
A
C
C
T
,
5
–
1
2
.
2
0
1
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
T.
2
0
1
4
.
7
4
.
[
2
1
]
M
.
K
u
mar,
S
.
G
u
p
t
a
,
X
.
-
Z.
G
a
o
,
a
n
d
A
.
S
i
n
g
h
,
“
P
l
a
n
t
sp
e
c
i
e
s
r
e
c
o
g
n
i
t
i
o
n
u
s
i
n
g
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
a
n
d
a
d
a
p
t
i
v
e
b
o
o
s
t
i
n
g
met
h
o
d
o
l
o
g
y
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
6
3
9
1
2
–
1
6
3
9
1
8
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
5
2
1
7
6
.
[
2
2
]
M
.
A
.
T.
V
a
l
d
e
z
,
P
.
A
.
S
.
T
.
W
a
t
t
,
a
n
d
G
.
P
.
M
a
p
p
a
t
a
o
,
“
A
u
t
o
ma
t
e
d
f
e
r
t
i
l
i
z
e
d
d
u
c
k
e
g
g
so
r
t
i
n
g
s
y
st
e
m
u
s
i
n
g
i
m
a
g
e
p
r
o
c
e
ss
i
n
g
,
”
Ad
v
a
n
c
e
d
S
c
i
e
n
c
e
L
e
t
t
e
rs
,
v
o
l
.
2
3
,
n
o
.
6
,
p
p
.
5
1
9
1
–
5
1
9
4
,
J
u
n
.
2
0
1
7
,
d
o
i
:
1
0
.
1
1
6
6
/
a
sl
.
2
0
1
7
.
7
3
3
9
.
[
2
3
]
M
.
H
a
s
h
e
m
z
a
d
e
h
,
“
A
v
i
si
o
n
m
a
c
h
i
n
e
f
o
r
d
e
t
e
c
t
i
n
g
f
e
r
t
i
l
e
e
g
g
s
a
n
d
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
n
e
u
r
a
l
n
e
t
w
o
r
k
s a
n
d
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
s
i
n
t
h
i
s
ma
c
h
i
n
e
,
”
J
o
u
rn
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
D
e
c
i
s
i
o
n
S
u
p
p
o
rt
S
y
st
e
m
s
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
9
7
–
1
1
2
,
D
e
c
.
2
0
1
7
,
d
o
i
:
1
0
.
2
9
2
5
2
/
j
s
d
p
.
1
4
.
3
.
9
7
.
[
2
4
]
M
.
K
r
a
u
t
w
a
l
d
-
J
u
n
g
h
a
n
n
s
e
t
a
l
.
,
“
C
u
r
r
e
n
t
a
p
p
r
o
a
c
h
e
s t
o
a
v
o
i
d
t
h
e
c
u
l
l
i
n
g
o
f
d
a
y
-
o
l
d
m
a
l
e
c
h
i
c
k
s i
n
t
h
e
l
a
y
e
r
i
n
d
u
st
r
y
,
w
i
t
h
sp
e
c
i
a
l
r
e
f
e
r
e
n
c
e
t
o
s
p
e
c
t
r
o
s
c
o
p
i
c
met
h
o
d
s
,
”
Po
u
l
t
ry
S
c
i
e
n
c
e
,
v
o
l
.
9
7
,
n
o
.
3
,
p
p
.
7
4
9
–
7
5
7
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
8
2
/
p
s
/
p
e
x
3
8
9
.
[
2
5
]
M
.
S
.
N
i
x
o
n
a
n
d
A
.
S
.
A
g
u
a
d
o
,
“
L
o
w
-
l
e
v
e
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
(
i
n
c
l
u
d
i
n
g
e
d
g
e
d
e
t
e
c
t
i
o
n
)
,
”
i
n
Fe
a
t
u
re
E
x
t
r
a
c
t
i
o
n
a
n
d
I
m
a
g
e
Pro
c
e
ssi
n
g
f
o
r
C
o
m
p
u
t
e
r V
i
s
i
o
n
,
El
s
e
v
i
e
r
,
2
0
2
0
,
p
p
.
1
4
1
–
2
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
p
l
p
h
.
2
0
1
6
.
0
3
.
0
0
9
.
[
2
6
]
M
.
S
a
n
,
M
.
M
.
A
u
n
g
,
a
n
d
P
.
P
.
K
h
a
i
n
g
,
“
F
r
u
i
t
r
e
c
o
g
n
i
t
i
o
n
u
si
n
g
c
o
l
o
r
a
n
d
m
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
f
u
s
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
m
a
g
e
,
G
ra
p
h
i
c
s
a
n
d
S
i
g
n
a
l
Pr
o
c
e
s
si
n
g
,
v
o
l
.
1
1
,
n
o
.
1
0
,
p
p
.
8
–
1
5
,
O
c
t
.
2
0
1
9
,
d
o
i
:
1
0
.
5
8
1
5
/
i
j
i
g
s
p
.
2
0
1
9
.
1
0
.
0
2
.
[
2
7
]
M
.
Ta
m
a
y
o
-
O
r
d
ó
ñ
e
z
e
t
a
l
.
,
“
M
o
r
p
h
o
l
o
g
i
c
a
l
f
e
a
t
u
r
e
s
o
f
d
i
f
f
e
r
e
n
t
p
o
l
y
p
l
o
i
d
s
f
o
r
a
d
a
p
t
a
t
i
o
n
a
n
d
m
o
l
e
c
u
l
a
r
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
o
f
C
C
-
N
B
S
-
LR
R
a
n
d
L
EA
g
e
n
e
f
a
mi
l
i
e
s
i
n
A
g
a
v
e
L.
,
”
J
o
u
r
n
a
l
o
f
P
l
a
n
t
Ph
y
si
o
l
o
g
y
,
v
o
l
.
1
9
5
,
p
p
.
8
0
–
9
4
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
p
l
p
h
.
2
0
1
6
.
0
3
.
0
0
9
.
[
2
8
]
M
.
A
.
A
n
sar
i
,
D
.
K
u
r
c
h
a
n
i
y
a
,
a
n
d
M
.
D
i
x
i
t
,
“
A
c
o
m
p
r
e
h
e
n
si
v
e
a
n
a
l
y
si
s
o
f
i
m
a
g
e
e
d
g
e
d
e
t
e
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
M
u
l
t
i
m
e
d
i
a
a
n
d
U
b
i
q
u
i
t
o
u
s E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
2
,
n
o
.
1
1
,
p
p
.
1
–
1
2
,
N
o
v
.
2
0
1
7
,
d
o
i
:
1
0
.
1
4
2
5
7
/
i
j
m
u
e
.
2
0
1
7
.
1
2
.
1
1
.
0
1
.
[
2
9
]
B
.
N
a
r
i
n
,
S
.
B
u
n
t
a
n
,
N
.
C
h
u
m
u
a
n
g
,
a
n
d
M
.
K
e
t
c
h
a
m
,
“
P
e
r
f
o
r
ma
n
c
e
a
n
a
l
y
s
i
s
o
f
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
i
ma
g
e
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
8
1
8
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
C
o
m
m
u
n
i
c
a
t
i
o
n
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
(
I
S
C
I
T
)
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
,
S
e
p
.
2
0
1
8
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
I
T.
2
0
1
8
.
8
5
8
7
9
8
0
.
[
3
0
]
O
.
N
u
r
h
a
y
a
t
i
,
“
I
mag
e
p
r
o
c
e
ss
i
n
g
f
o
r
i
d
e
n
t
i
f
i
c
a
t
i
o
n
o
f
Le
g
h
o
r
n
a
n
d
O
me
g
a
-
3
c
h
i
c
k
e
n
e
g
g
s
u
si
n
g
K
-
mea
n
c
l
u
s
t
e
r
i
n
g
a
n
d
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,
”
J
o
u
rn
a
l
o
f
S
m
a
rt
I
n
f
o
rm
a
t
i
c
s
a
n
d
N
e
t
w
o
r
k
e
d
B
u
si
n
e
ss
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
8
4
–
9
3
,
J
u
n
.
2
0
2
0
,
d
o
i
:
1
0
.
2
1
4
5
6
/
v
o
l
1
0
i
ss
1
p
p
8
4
-
9
3
.
[
3
1
]
J.
X
u
,
“
I
mag
e
d
a
t
a
v
i
s
u
a
l
i
z
a
t
i
o
n
a
n
d
c
o
mm
u
n
i
c
a
t
i
o
n
s
y
st
e
m
b
a
se
d
o
n
s
e
n
s
o
r
n
e
t
w
o
r
k
s
i
m
u
l
a
t
i
o
n
a
n
d
v
i
s
u
a
l
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
,
”
Me
a
su
r
e
m
e
n
t
a
n
d
S
e
n
so
rs
,
v
o
l
.
3
3
,
p
.
1
0
1
2
2
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
m
e
a
s
e
n
.
2
0
2
4
.
1
0
1
2
2
3
.
[
3
2
]
W
.
Y
o
u
,
K
.
J.
T.
N
o
o
n
a
n
,
a
n
d
G
.
W
.
C
o
a
t
e
s,
“
A
n
a
l
y
s
i
s
o
f
t
h
e
o
f
f
-
f
o
c
a
l
so
u
r
c
e
i
n
t
r
a
n
sm
i
ssi
o
n
g
e
o
m
e
t
r
y
X
-
r
a
y
s
y
st
e
ms,
”
Pr
o
g
res
s
i
n
Po
l
y
m
e
r
S
c
i
e
n
c
e
,
p
.
1
0
1
1
7
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
5
3
5
8
.
[
3
3
]
H
.
H
e
n
d
r
i
e
t
a
l
.
,
“
A
h
y
b
r
i
d
d
a
t
a
mi
n
i
n
g
f
o
r
p
r
e
d
i
c
t
i
n
g
sc
h
o
l
a
r
sh
i
p
r
e
c
i
p
i
e
n
t
s
t
u
d
e
n
t
s
b
y
c
o
m
b
i
n
i
n
g
K
-
M
e
a
n
s
a
n
d
C
4
.
5
m
e
t
h
o
d
s,
”
I
n
d
o
n
e
si
a
n
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
3
3
,
n
o
.
3
,
p
.
1
7
2
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s.
v
3
3
.
i
3
.
p
p
1
7
2
6
-
1
7
3
5
.
[
3
4
]
H
.
H
e
n
d
r
i
,
M
a
sr
i
a
d
i
,
a
n
d
M
a
r
d
i
s
o
n
,
“
A
n
o
v
e
l
a
l
g
o
r
i
t
h
m
f
o
r
m
o
n
i
t
o
r
i
n
g
f
i
e
l
d
d
a
t
a
c
o
l
l
e
c
t
i
o
n
o
f
f
i
c
e
r
s
o
f
I
n
d
o
n
e
si
a
’
s
C
e
n
t
r
a
l
S
t
a
t
i
st
i
c
s
A
g
e
n
c
y
(
B
P
S
)
u
s
i
n
g
w
e
b
-
b
a
s
e
d
d
i
g
i
t
a
l
t
e
c
h
n
o
l
o
g
y
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
n
A
d
v
a
n
c
e
d
S
c
i
e
n
c
e
,
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
3
,
n
o
.
3
,
p
.
1
1
5
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
8
5
1
7
/
i
j
a
se
i
t
.
1
3
.
3
.
1
8
3
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.