I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
201
6
,
p
p
.
279
7
~
2
8
0
4
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
6i
6
.
1
1
0
5
3
2797
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
The Co
ntour
Ex
t
ra
ction o
f
C
up in
Fundus I
m
a
g
es fo
r
G
la
uco
m
a
Detecti
o
n
Anin
d
it
a
Septia
rini
,
H
a
m
da
ni
,
Dy
na
M
a
risa
K
ha
irina
F
a
c
u
lt
y
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
M
u
law
a
rm
a
n
Un
iv
e
rsit
y
,
S
a
m
a
rin
d
a
,
In
d
o
n
e
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
2
8
,
2
0
1
6
R
ev
i
s
ed
A
u
g
2
6
,
2
0
1
6
A
cc
ep
ted
Sep
20
,
2
0
1
6
G
lau
c
o
m
a
is
th
e
se
c
o
n
d
lea
d
in
g
c
a
u
se
o
f
b
li
n
d
n
e
ss
in
th
e
w
o
rld
;
th
e
re
f
o
re
th
e
d
e
tec
ti
o
n
o
f
g
lau
c
o
m
a
is
re
q
u
ired
.
T
h
e
d
e
tec
ti
o
n
o
f
g
lau
c
o
m
a
is
u
se
d
t
o
d
isti
n
g
u
is
h
w
h
e
th
e
r
a
p
a
ti
e
n
t'
s
e
y
e
is
n
o
rm
a
l
o
r
g
lau
c
o
m
a
.
A
n
e
x
p
e
rt
o
b
se
rv
e
d
th
e
stru
c
t
u
re
o
f
th
e
re
ti
n
a
u
sin
g
f
u
n
d
u
s
im
a
g
e
to
d
e
tec
t
g
lau
c
o
m
a
.
In
th
is
re
se
a
rc
h
,
w
e
p
ro
p
o
se
f
e
a
tu
re
e
x
trac
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
c
u
p
a
re
a
c
o
n
to
u
r
u
si
n
g
f
u
n
d
u
s
im
a
g
e
s
to
d
e
tec
t
g
lau
c
o
m
a
.
Ou
r
p
ro
p
o
se
d
m
e
th
o
d
h
a
s
b
e
e
n
e
v
a
lu
a
ted
o
n
4
4
f
u
n
d
u
s
i
m
a
g
e
s
c
o
n
sistin
g
o
f
2
3
n
o
rm
a
l
a
n
d
2
1
g
lau
c
o
m
a
.
T
h
e
d
a
ta
is
d
iv
id
e
d
in
to
tw
o
p
a
rts:
f
irstl
y
,
u
se
d
to
th
e
lea
rn
in
g
p
h
a
se
a
n
d
se
c
o
n
d
ly
,
u
se
d
t
o
t
h
e
t
e
stin
g
p
h
a
se
.
In
o
r
d
e
r
to
id
e
n
ti
fy
th
e
f
u
n
d
u
s
im
a
g
e
s
in
c
lu
d
in
g
t
h
e
c
las
s
o
f
n
o
rm
a
l
o
r
g
lau
c
o
m
a
,
w
e
a
p
p
li
e
d
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
s
(
S
VM)
m
e
th
o
d
.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
o
u
r
m
e
th
o
d
a
c
h
iev
e
s
th
e
a
c
c
u
ra
c
y
o
f
9
4
.
4
4
%
.
K
ey
w
o
r
d
:
C
o
n
to
u
r
f
ea
t
u
r
es
C
u
p
F
u
n
d
u
s
i
m
a
g
e
Glau
co
m
a
M
o
r
p
h
o
lo
g
y
Co
p
y
rig
h
t
©
2
0
1
6
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
An
i
n
d
ita
Sep
tiar
in
i,
Facu
lt
y
o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Un
i
v
er
s
ita
s
Mu
la
w
ar
m
a
n
,
Sa
m
ar
i
n
d
a
-
7
5
1
2
3
,
I
n
d
o
n
esia.
E
m
ail: a
n
i
n
d
ita@
u
n
m
u
l.a
c.
id
1.
I
NT
RO
D
UCT
I
O
N
Glau
co
m
a
i
s
an
e
y
e
d
is
ea
s
e
t
h
at
ca
n
ca
u
s
e
v
is
io
n
p
r
o
b
lem
s
.
T
h
is
d
is
ea
s
e
is
th
e
s
ec
o
n
d
ca
u
s
e
o
f
b
lin
d
n
es
s
i
n
th
e
w
o
r
ld
[
1
]
,
th
er
ef
o
r
e
th
e
d
etec
tio
n
o
f
g
la
u
co
m
a
is
r
eq
u
ir
ed
.
T
h
e
d
etec
tio
n
o
f
g
la
u
co
m
a
b
y
a
n
ex
p
er
t
ca
r
r
ied
o
u
t
b
y
o
b
s
er
v
i
n
g
th
e
s
tr
u
ctu
r
e
o
f
t
h
e
r
etin
a
u
s
in
g
a
f
u
n
d
u
s
i
m
a
g
e,
to
d
eter
m
in
e
th
e
e
y
e
s
o
f
th
e
p
atien
t
ar
e
n
o
r
m
al
an
d
g
la
u
c
o
m
a
.
C
u
r
r
en
t
l
y
,
r
esear
ch
o
n
au
to
m
at
ic
g
la
u
co
m
a
d
etec
tio
n
tech
n
iq
u
e
s
h
av
e
b
ee
n
d
ev
elo
p
ed
.
Mo
s
t
o
f
th
e
r
esear
ch
u
s
i
n
g
f
u
n
d
u
s
i
m
a
g
es
as
in
p
u
t
d
ata
a
n
d
s
e
v
er
al
f
ea
t
u
r
e
ex
tr
ac
tio
n
m
et
h
o
d
s
h
a
v
e
b
ee
n
ap
p
lied
.
Sev
er
al
p
r
ev
io
u
s
r
e
s
ea
r
ch
es
r
elate
d
to
au
to
m
ati
c
g
la
u
co
m
a
d
etec
tio
n
g
en
er
ated
b
y
ap
p
ly
in
g
n
o
n
-
m
o
r
p
h
o
lo
g
ical
f
ea
t
u
r
e
e
x
tr
ac
t
io
n
m
eth
o
d
(
i
m
ag
e
-
b
ased
f
ea
tu
r
es).
T
h
e
f
ea
tu
r
e
r
e
f
er
r
ed
to
co
lo
r
,
s
h
ap
e
o
r
tex
t
u
r
e
o
n
th
e
o
p
tic
n
er
v
e
h
ea
d
(
ONH)
,
r
etin
al
n
er
v
e
f
ib
er
la
y
er
(
R
NF
L
)
o
r
b
lo
o
d
v
e
s
s
el
a
s
p
ar
t
o
f
t
h
e
st
r
u
ct
u
r
e
o
f
th
e
r
eti
n
a
[
2
]
.
T
h
e
s
e
p
ar
ts
u
n
d
er
g
o
ch
an
g
es
i
n
p
atien
t
s
w
it
h
g
la
u
co
m
a
[
3
]
.
ONH
(
also
ca
lled
d
is
c)
is
th
e
p
ar
t
ar
ea
w
it
h
r
o
u
n
d
s
h
a
p
e.
In
s
id
e
o
f
th
e
d
is
c,
th
er
e
is
a
s
m
aller
ar
ea
w
ith
r
o
u
n
d
s
h
a
p
e
ca
lled
a
cu
p
an
d
a
n
eu
r
o
r
eti
n
al
r
i
m
w
h
ich
is
a
n
ar
ea
t
h
at
lie
s
b
et
w
ee
n
th
e
d
is
c
an
d
t
h
e
c
u
p
.
R
N
F
L
is
th
e
ar
ea
o
u
ts
id
e
o
f
t
h
e
d
is
k
w
h
er
e
th
e
s
tr
u
ct
u
r
e
o
f
t
h
ick
n
e
s
s
o
f
t
h
e
R
NF
L
is
th
e
o
n
e
w
h
ic
h
d
i
s
ti
n
g
u
is
h
e
s
w
h
et
h
er
a
p
atien
t
's
e
y
e
is
n
o
r
m
al
o
r
g
la
u
co
m
a.
T
h
e
illu
s
tr
atio
n
o
f
ONH
a
n
d
R
NF
L
s
tr
u
ctu
r
e
ar
e
s
h
o
w
n
i
n
Fi
g
u
r
e
1
.
I
n
th
e
f
ea
t
u
r
es
e
x
tr
ac
tio
n
o
f
t
h
e
ONH
ap
p
lied
th
e
p
r
o
ce
s
s
o
f
b
lo
o
d
v
ess
el
i
n
p
ain
ti
n
g
as
th
e
p
r
ev
io
u
s
p
h
ase
in
o
r
d
er
to
r
em
o
v
e
o
r
b
lu
r
r
in
g
t
h
e
b
lo
o
d
v
ess
el
t
h
at
p
r
esen
ce
s
as
n
o
is
e.
T
h
is
p
r
o
ce
s
s
is
r
eq
u
ir
ed
th
e
d
etec
tio
n
to
d
eter
m
in
e
t
h
e
p
r
esen
ce
o
f
t
h
e
b
lo
o
d
v
ess
el.
Sev
er
al
m
e
th
o
d
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
f
o
r
th
e
d
etec
tio
n
o
f
t
h
e
b
lo
o
d
v
ess
el
.
T
h
r
esh
o
ld
in
g
w
it
h
th
e
lo
w
p
ix
el
v
a
lu
e
s
in
th
e
i
m
a
g
e
f
o
l
lo
w
ed
b
y
m
e
d
ia
n
f
ilter
i
n
g
o
f
t
h
e
s
ize
4
1
x
41
[
4
]
,
u
s
in
g
th
r
e
s
h
o
ld
p
r
o
b
in
g
[
5
]
a
n
d
n
o
r
m
alize
d
m
at
h
e
m
atica
l
m
o
r
p
h
o
lo
g
y
(
u
s
ed
to
en
h
a
n
ce
t
h
e
v
e
s
s
el
s
)
f
o
llo
w
ed
b
y
n
e
u
r
o
f
u
zz
y
clas
s
i
f
ier
[
6
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Th
e
C
o
n
to
u
r
E
xtra
ctio
n
o
f Cu
p
in
F
u
n
d
u
s
I
ma
g
es fo
r
Gla
u
c
o
ma
Dete
ctio
n
(
A
n
in
d
ita
S
ep
ti
a
r
in
i
)
2798
Su
b
s
eq
u
e
n
tl
y
,
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
f
th
e
ON
H
b
ased
o
n
s
h
ap
e
p
r
o
p
o
s
ed
b
y
u
s
in
g
m
o
m
en
t
m
e
th
o
d
in
th
e
i
m
ag
e
o
f
C
o
n
f
o
ca
l
Sc
an
n
i
n
g
L
a
s
er
T
o
m
o
g
r
ap
h
y
(
C
S
L
T
)
[
7
]
,
Self
-
Or
g
a
n
izi
n
g
Ma
p
(
SOM)
[
8
]
an
d
Var
iatio
n
al
E
x
p
ec
tatio
n
Ma
x
i
m
izatio
n
(
VE
M)
o
n
th
e
i
m
ag
e
o
f
Heid
elb
er
g
R
eti
n
a
T
o
m
o
g
r
ap
h
(
HR
T
)
[
9
]
.
Sev
er
al
f
ea
t
u
r
e
e
x
tr
ac
tio
n
m
eth
o
d
s
o
f
t
h
e
te
x
t
u
r
e
ap
p
r
o
ac
h
ed
b
y
u
s
in
g
Hi
g
h
er
Or
d
er
Sp
ec
tr
a
(
HOS)
m
et
h
o
d
[
1
0
]
,
th
e
co
m
b
i
n
atio
n
o
f
HOS
an
d
Dis
cr
ete
W
av
el
et
T
r
an
s
f
o
r
m
(
DW
T
)
[
1
1
-
12]
,
w
av
ele
t
s
u
b
-
b
an
d
s
(
w
a
v
elet
s
u
b
b
an
d
s
Dau
b
ec
h
ies
(
Db
4
)
,
S
y
m
lets
(
s
y
m
4
)
an
d
f
ilter
B
io
r
th
o
g
o
n
a
l
(
b
i0
3
.
7
,
b
i0
4
.
2
&
b
i0
4
.
7
)
)
[
1
3
]
.
Fra
ctal
Di
m
en
s
i
o
n
[
1
4
]
,
Gr
ay
L
e
v
el
C
o
-
o
cc
u
r
r
en
ce
Ma
tr
i
x
(
G
L
C
M)
[
1
5
]
.
I
n
2
0
0
7
B
o
ck
et
al.
h
as
b
ee
n
i
m
p
le
m
e
n
ted
f
ea
t
u
r
e
ex
tr
ac
tio
n
b
y
co
m
b
i
n
in
g
t
h
e
s
h
ap
e,
tex
t
u
r
e
an
d
co
lo
r
f
ea
tu
r
es
u
s
i
n
g
i
n
te
n
s
it
y
v
alu
e
o
f
p
i
x
el,
Gab
o
r
Fil
ter
,
c
o
ef
f
icie
n
t,
Fo
u
r
ier
T
r
an
s
f
o
r
m
(
FF
T
)
an
d
m
o
d
el
h
is
to
g
r
a
m
m
eth
o
d
[
1
6
]
,
th
en
in
2
0
1
0
h
e
m
o
d
if
ied
h
is
r
esear
ch
b
y
d
i
f
f
er
e
n
t
m
eth
o
d
: i
n
ten
s
it
y
o
f
lin
e
p
ix
e
l,
FF
T
an
d
B
-
s
p
lin
e
[
1
7
]
.
(
b
)
(
a
)
(
b
)
Fig
u
r
e
1
.
St
r
u
ct
u
r
e
o
f
(
a)
ONH
an
d
(
b
)
R
NFL
I
n
o
r
d
er
to
ex
tr
ac
t
t
h
e
f
ea
t
u
r
e
o
f
t
h
e
R
NF
L
,
t
h
e
p
r
ev
io
u
s
r
esear
ch
es
ap
p
lied
Gau
s
s
ia
n
Ma
r
k
o
v
r
an
d
o
m
f
ield
s
an
d
lo
ca
l
b
in
ar
y
p
atter
n
m
et
h
o
d
[
1
8
]
,
f
r
ac
tal
d
i
m
e
n
s
io
n
[
1
9
-
20]
.
Ko
lar
an
d
J
an
(
2
0
0
8
)
u
s
ed
s
i
m
p
le
b
o
x
co
u
n
ti
n
g
,
m
ax
i
m
u
m
li
k
eli
h
o
o
d
esti
m
ato
r
s
an
d
s
p
ec
tr
al
-
b
ase
d
m
e
th
o
d
[
1
9
]
,
w
h
ile
Ki
m
et
al.
(
2
0
1
3
)
u
s
ed
b
o
x
-
co
u
n
ti
n
g
an
d
m
u
lti
f
r
ac
tio
n
al
B
r
o
w
n
ian
m
o
t
io
n
[
2
0
]
.
T
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
to
w
ar
d
s
b
lo
o
d
v
ess
el
h
as
d
o
n
e
u
s
i
n
g
v
ess
e
l
ce
n
tr
al
ax
i
s
d
etec
tio
n
,
m
a
k
in
g
t
h
e
au
to
m
atic
m
o
d
u
l
e
r
eg
is
tr
atio
n
u
s
i
n
g
r
etin
a
i
m
ag
e
s
b
y
s
elf
-
o
r
g
an
iz
in
g
m
ap
s
(
SO
Ms)
to
l
o
o
k
f
o
r
s
o
m
e
attr
ib
u
te
s
s
u
c
h
as
co
n
n
ec
ti
n
g
p
o
in
t,
th
e
f
o
r
m
o
f
t
h
e
v
es
s
el
[
2
1
]
.
T
h
e
r
esu
lt o
f
f
ea
t
u
r
e
ex
tr
ac
tio
n
p
r
o
d
u
ce
d
d
ata
w
it
h
lar
g
e
d
i
m
en
s
io
n
,
t
h
er
ef
o
r
e
to
o
v
er
co
m
e
th
e
ca
s
e
,
d
i
m
en
s
io
n
r
ed
u
ctio
n
is
r
eq
u
i
r
ed
b
y
P
r
in
cip
al
C
o
m
p
o
n
e
n
t
A
n
al
y
s
is
(
P
C
A
)
[
1
2
]
,
[
1
6
-
17]
o
r
Seq
u
en
tial
Fo
r
w
ar
d
Flo
ati
n
g
Selectio
n
(
S
FF
S)
to
ex
ec
u
te
f
ea
t
u
r
e
s
elec
t
i
o
n
[
1
5
]
.
Fu
r
th
er
m
o
r
e,
t
h
er
e
ar
e
s
ev
er
al
m
et
h
o
d
s
u
s
ed
to
t
h
e
cla
s
s
i
f
icat
io
n
p
h
ase
s
u
c
h
as
:
S
u
p
p
o
r
t
Vec
to
r
Ma
ch
in
e
s
(
SVM)
[
7
]
,
[
1
1
]
,
[
1
6
-
17]
,
Naïv
e
B
a
y
e
s
ian
[
1
0
]
,
s
tatis
tic
al
an
al
y
s
i
s
[
1
4
]
,
Mu
ltil
a
ye
r
P
ercep
tr
o
n
(
ML
P
)
[
7
]
,
[
2
1
]
,
P
r
o
b
a
b
ilis
tic
N
eu
r
a
l
N
etw
o
r
k
(
P
NN)
[
1
2
]
,
Lea
r
n
i
n
g
V
ec
to
r
Qu
a
n
tiz
a
tio
n
(
L
VQ)
[
8
]
an
d
th
e
co
m
b
i
n
atio
n
o
f
M
L
P
w
ith
b
ac
k
p
r
o
p
ag
atio
n
[
1
3
]
.
I
n
th
i
s
r
esear
c
h
,
w
e
p
r
o
p
o
s
e
th
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
o
f
t
h
e
O
NH
b
ased
o
n
t
h
e
cu
p
ar
ea
co
n
to
u
r
b
y
s
i
m
p
l
e
m
et
h
o
d
s
o
f
t
h
r
esh
o
ld
i
n
g
an
d
m
o
r
p
h
o
lo
g
y
f
o
r
g
la
u
c
o
m
a
d
etec
tio
n
u
s
in
g
f
u
n
d
u
s
i
m
ag
e
s
.
T
h
e
u
s
e
o
f
f
u
n
d
u
s
i
m
ag
e
s
d
u
e
to
s
ev
er
al
r
ea
s
o
n
s
s
u
c
h
as
t
h
e
f
u
n
d
u
s
ca
m
er
a
w
id
el
y
f
o
u
n
d
in
h
ea
lt
h
ca
r
e
ce
n
ter
,
ch
ea
p
er
,
an
d
it
ca
n
b
e
u
s
ed
to
o
b
s
er
v
e
an
o
th
er
d
i
s
ea
s
e:
d
iab
e
tic
r
eti
n
o
p
ath
y
an
d
h
y
p
er
te
n
s
i
v
e
r
eti
n
o
p
ath
y
.
T
h
e
r
est
s
ec
tio
n
in
t
h
is
p
ap
er
w
e
ex
p
lai
n
th
e
r
esear
ch
m
e
th
o
d
in
Secti
o
n
2
.
T
h
e
r
esu
lt
an
d
d
is
cu
s
s
io
n
ar
e
p
r
esen
ted
in
Sectio
n
3
.
Fin
al
l
y
,
Sect
io
n
4
co
n
clu
d
es t
h
e
p
ap
er
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
Ou
r
m
et
h
o
d
d
iv
id
ed
in
t
o
t
w
o
m
ai
n
p
h
a
s
e:
t
h
e
p
h
ase
o
f
lear
n
in
g
an
d
test
i
n
g
as
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
2
.
T
h
e
in
itial
in
p
u
t
o
f
ea
ch
p
h
a
s
e
is
th
e
ONH
i
m
a
g
e.
I
t
s
i
m
ilar
to
th
e
s
et
u
p
o
f
t
h
e
w
o
r
k
in
[
2
2
-
23]
.
I
n
t
h
e
lear
n
in
g
p
h
ase,
d
ata
class
(
n
o
r
m
al/
g
lau
co
m
a)
is
r
eq
u
ir
ed
as
th
e
in
p
u
t
to
g
i
v
e
a
lab
el
ag
ain
s
t
t
h
e
ONH
i
m
a
g
e
to
d
eter
m
in
e
w
h
eth
er
th
e
i
m
a
g
e
i
s
n
o
r
m
al
o
r
g
lau
co
m
a.
T
h
e
m
ai
n
p
h
a
s
es
o
f
t
h
i
s
r
esear
ch
co
n
ta
in
s
e
v
er
al
p
r
o
ce
s
s
es,
n
a
m
el
y
p
r
e
-
p
r
o
ce
s
s
in
g
,
ex
tr
ac
tin
g
f
ea
t
u
r
es
o
f
t
h
e
cu
p
ar
ea
an
d
co
n
to
u
r
d
escr
i
p
to
r
.
T
h
e
p
h
ase
o
f
lear
n
in
g
a
n
d
test
i
n
g
ar
e
ter
m
in
ated
b
y
t
h
e
p
r
o
ce
s
s
s
av
i
n
g
th
e
co
n
to
u
r
f
ea
t
u
r
es a
n
d
class
i
f
ica
tio
n
r
esp
ec
tiv
el
y
.
2
.
1
.
P
re
-
P
ro
ce
s
s
ing
T
h
e
f
ir
s
t
s
tep
o
f
t
h
is
p
r
o
ce
s
s
w
a
s
co
n
v
er
ti
n
g
t
h
e
ON
H
i
m
a
g
e
(
Fi
g
u
r
e
1
(
a)
)
as
t
h
e
i
n
itia
l
in
p
u
t
i
n
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
9
7
–
2
8
0
4
2799
g
r
ee
n
co
lo
r
b
ec
au
s
e
t
h
e
ar
ea
o
f
th
e
c
u
p
an
d
th
e
ar
ea
o
f
n
o
n
-
c
u
p
is
m
o
r
e
clea
r
l
y
d
is
ti
n
g
u
is
h
ab
le
i
n
th
is
co
lo
r
[
2
3
-
24]
.
Su
b
s
eq
u
en
tl
y
,
w
e
a
p
p
lied
th
e
p
r
o
ce
s
s
o
f
b
lo
o
d
v
ess
el
i
n
p
ain
ti
n
g
b
y
th
e
m
o
r
p
h
o
lo
g
y
clo
s
in
g
o
p
er
atio
n
f
o
llo
w
ed
b
y
co
n
v
er
t
in
g
t
h
i
s
r
esu
lt in
to
g
r
a
y
s
ca
le
i
m
ag
e.
O
N
H
i
m
a
g
e
s
,
C
l
a
s
s
O
N
H
i
m
a
g
e
s
C
l
a
s
s
i
f
i
c
a
t
i
o
n
S
a
v
i
n
g
t
h
e
c
o
n
t
o
u
r
f
e
a
t
u
r
e
s
N
o
r
m
a
l
/
G
l
a
u
c
o
m
a
T
e
s
t
i
n
g
p
h
a
s
e
L
e
a
r
n
i
n
g
p
h
a
s
e
P
r
e
-
p
r
o
c
e
s
s
i
n
g
C
o
n
v
e
r
t
i
n
g
R
G
B
t
o
g
r
e
e
n
c
o
l
o
r
B
l
o
o
d
v
e
s
s
e
l
s
i
n
p
a
i
n
t
i
n
g
E
x
t
r
a
c
t
i
n
g
f
e
a
t
u
r
e
s
o
f
t
h
e
c
u
p
a
r
e
a
C
o
n
v
e
r
t
i
n
g
t
o
g
r
a
y
s
c
a
l
e
i
m
a
g
e
T
h
r
e
s
h
o
l
d
i
n
g
D
i
l
a
t
i
o
n
E
r
o
s
i
o
n
C
o
n
t
o
u
r
d
e
s
c
r
i
p
t
o
r
E
d
g
e
d
e
t
e
c
t
i
o
n
D
i
l
a
t
i
o
n
N
o
r
m
a
l
i
z
a
t
i
o
n
F
o
r
m
i
n
g
t
h
e
f
e
a
t
u
r
e
m
a
t
r
i
x
Fig
u
r
e
2
.
B
lo
ck
Di
ag
r
a
m
o
f
o
u
r
P
r
o
p
o
s
ed
M
eth
o
d
f
o
r
Glau
co
m
a
Dete
ctio
n
2
.
2
.
E
x
t
ra
ct
ing
F
ea
t
ures
o
f
t
he
Cup Ar
ea
T
h
e
g
r
a
y
s
ca
le
i
m
a
g
e
in
Fi
g
u
r
e
3
(
a)
as
th
e
in
p
u
t
o
f
th
is
p
r
o
ce
s
s
s
h
o
w
ed
th
at
t
h
e
ar
ea
o
f
t
h
e
cu
p
h
a
s
th
e
h
i
g
h
er
i
n
te
n
s
i
t
y
v
al
u
es
(
I
)
th
a
n
t
h
e
s
u
r
r
o
u
n
d
in
g
ar
ea
.
I
n
o
r
d
er
to
d
is
tin
g
u
i
s
h
th
e
ar
ea
o
f
th
e
cu
p
w
i
th
th
e
s
u
r
r
o
u
n
d
in
g
,
w
e
ap
p
lied
th
r
esh
o
ld
in
g
w
it
h
t
h
e
i
n
itia
l
th
r
es
h
o
ld
v
al
u
e
(
T
)
is
th
e
m
ea
n
v
a
lu
e
o
f
I
(
s
ee
Fig
u
r
e
3
(
b
)
as
th
e
r
esu
lt
)
.
I
f
th
e
r
esu
lt
s
o
f
p
ix
els
t
h
r
es
h
o
ld
in
g
r
ea
ch
th
e
ed
g
e
o
f
th
e
i
m
ag
e,
th
e
n
u
p
d
ate
th
e
T
v
alu
e
b
y
in
cr
ea
s
in
g
t
h
e
T
v
alu
e
u
n
t
il
n
o
n
e
o
f
th
e
p
ix
e
ls
th
r
es
h
o
ld
in
g
r
ea
ch
e
s
th
e
ed
g
e
o
f
th
e
i
m
a
g
e
a
s
s
h
o
w
in
Fi
g
u
r
e
3
(
c
)
.
Fu
r
th
er
m
o
r
e,
th
e
o
p
er
atio
n
o
f
er
o
s
io
n
a
n
d
d
ilatio
n
ar
e
ap
p
lied
to
r
em
o
v
e
th
e
p
ix
els
t
h
at
p
r
ed
icted
as th
e
ar
ea
o
f
n
o
n
-
c
u
p
(
Fig
u
r
e
3
(
d
)
as
th
e
r
esu
lt).
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
3
.
T
h
e
R
es
u
lt o
f
E
x
tr
ac
tin
g
Fe
at
u
r
es
(
a
)
Gr
a
y
s
ca
le
I
m
ag
e,
(
b
)
First T
h
r
esh
o
ld
in
g
,
(
c
)
Fin
al
T
h
r
esh
o
ld
in
g
an
d
(
d
)
Mo
r
p
h
o
lo
g
y
Op
e
r
atio
n
2
.
3
.
Co
nt
o
ur
Descript
o
r
T
h
e
ai
m
o
f
th
e
co
n
to
u
r
d
escr
i
p
to
r
is
to
o
b
tain
th
e
f
ea
t
u
r
e
m
atr
ix
b
ased
o
n
t
h
e
co
n
to
u
r
o
f
t
h
e
cu
p
.
T
h
e
f
ir
s
t
s
tep
o
f
th
is
p
r
o
ce
s
s
is
d
et
ec
tio
n
th
e
ed
g
e
o
f
t
h
e
cu
p
u
s
i
n
g
So
b
el
m
et
h
o
d
,
w
h
er
e
th
e
r
esu
lt
s
ar
e
s
h
o
w
n
i
n
Fig
u
r
e
4
(
a)
.
Seco
n
d
,
in
o
r
d
er
to
co
m
b
i
n
ed
th
e
u
n
co
n
n
ec
ted
p
ix
els
in
Fi
g
u
r
e
4
(
a)
w
e
ap
p
lied
d
ilatio
n
o
p
er
atio
n
(
s
ee
Fi
g
u
r
e
4
(
b
)
)
.
Sin
ce
t
h
e
s
i
ze
o
f
Fig
u
r
e
4
(
b
)
ca
n
b
e
d
if
f
er
en
t,
t
h
e
n
o
r
m
aliz
in
g
p
r
o
ce
s
s
is
r
eq
u
ir
ed
to
f
o
r
m
ed
s
u
b
-
i
m
a
g
e
w
i
th
s
ize
4
8
0
x
4
8
0
s
ize
an
d
p
lace
d
th
e
co
n
to
u
r
o
f
th
e
c
u
p
in
t
h
e
m
id
d
le
o
f
t
h
e
i
m
a
g
e
as
s
h
o
w
n
in
Fig
u
r
e
4
(
c)
.
T
h
is
i
m
ag
e
u
s
ed
as
a
r
ef
er
en
ce
to
o
b
tain
t
h
e
2
D
f
ea
tu
r
e
m
atr
i
x
,
b
y
r
esizi
n
g
Fi
g
u
r
e
3
(
c)
in
to
240x
2
4
0
p
ix
els.
T
h
e
v
alu
e
o
f
t
h
e
f
ea
t
u
r
e
m
a
tr
ix
co
n
s
is
ts
0
o
r
1
b
ased
o
n
th
e
cu
p
co
n
to
u
r
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Th
e
C
o
n
to
u
r
E
xtra
ctio
n
o
f Cu
p
in
F
u
n
d
u
s
I
ma
g
es fo
r
Gla
u
c
o
ma
Dete
ctio
n
(
A
n
in
d
ita
S
ep
ti
a
r
in
i
)
2800
Fu
r
t
h
er
m
o
r
e,
i
n
o
r
d
er
to
s
i
m
p
lify
t
h
e
s
u
b
s
eq
u
en
tial
p
r
o
ce
s
s
,
w
e
r
ed
u
ce
d
t
h
e
s
ize
o
f
t
h
e
f
ea
t
u
r
e
m
atr
i
x
b
y
ad
d
in
g
th
e
co
n
ten
t
o
f
f
ea
t
u
r
e
m
a
tr
ix
b
ased
o
n
t
h
e
s
q
u
ar
e
k
er
n
e
l
(
s
ize
3
0
x
3
0
)
to
a
s
ize
8
x
8
.
Fig
u
r
e
5
s
h
o
w
s
t
h
e
ill
u
s
tr
at
io
n
o
f
t
h
e
Nx
N
f
ea
tu
r
e
m
atr
ix
a
n
d
th
e
r
esu
lt
o
f
r
esized
f
ea
t
u
r
e
m
atr
i
x
b
a
s
ed
o
n
th
e
k
er
n
el
w
it
h
s
ize
4
x
4
.
(
a)
(
b
)
(
c)
Fig
u
r
e
4
.
T
h
e
I
m
ag
e
R
es
u
lt o
f
(
a)
So
b
el
Me
th
o
d
,
(
b
)
Dilatio
n
Op
er
at
io
n
d
an
(
c)
No
r
m
alize
d
I
m
a
g
e
Fig
u
r
e
5
.
T
h
e
I
llu
s
t
r
atio
n
o
f
R
ed
u
ctio
n
P
r
o
ce
s
s
f
r
o
m
t
h
e
Fea
tu
r
e
Ma
tr
i
x
2
.
4
.
Cla
s
s
if
ica
t
io
n
T
h
e
f
i
n
al
s
tep
o
f
th
e
test
in
g
p
h
ase,
w
e
us
ed
t
h
e
f
ea
t
u
r
e
m
atr
ix
(
s
ize
8
x
8
)
as
t
h
e
i
n
p
u
t
an
d
ap
p
lied
th
e
class
i
f
icatio
n
p
r
o
ce
s
s
to
d
eter
m
i
n
e
t
h
e
ON
H
i
m
ag
e
w
as
cla
s
s
i
f
ied
as
n
o
r
m
a
l
o
r
g
la
u
co
m
a
class
.
I
n
o
r
d
er
t
o
o
b
tain
a
g
o
o
d
class
if
icatio
n
r
esu
lt,
d
eter
m
i
n
atio
n
o
f
th
e
h
y
p
er
p
lan
e
p
lay
s
an
i
m
p
o
r
tan
t
r
o
le.
I
n
th
is
r
esear
ch
,
to
p
r
o
d
u
ce
th
e
s
u
itab
le
h
y
p
er
p
lan
e
w
e
ap
p
lied
SVM
m
et
h
o
d
.
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
N
I
n
th
i
s
r
esear
ch
,
a
d
ataset
o
f
t
h
e
f
u
n
d
u
s
i
m
a
g
e
s
co
llected
f
r
o
m
Dr
.
Y
A
P
E
y
e
Ho
s
p
ital
i
n
Yo
g
y
a
k
ar
ta
th
at
co
m
p
o
s
ed
o
f
4
4
ONH
i
m
ag
es
(
2
3
n
o
r
m
al
a
n
d
2
1
g
lau
c
o
m
a)
o
b
tain
ed
f
r
o
m
4
4
f
u
ll
f
u
n
d
u
s
i
m
a
g
e
s
.
T
h
e
d
ataset
co
n
s
is
t
o
f
th
e
f
u
n
d
u
s
i
m
ag
e
s
o
f
O
NH
w
i
th
d
if
f
er
en
t
s
ize
s
in
ce
th
e
e
y
e
o
f
p
atien
ts
h
av
e
t
h
e
ON
H
w
it
h
v
ar
y
i
n
g
s
ized
.
T
h
e
f
u
n
d
u
s
i
m
ag
es
ca
p
t
u
r
ed
b
y
f
u
n
d
u
s
ca
m
er
a
C
ar
l
Z
eis
s
AG
w
it
h
3
0
o
f
ield
-
of
-
v
ie
w
(
F
OV)
an
d
d
ig
ital
ca
m
er
a
Ni
k
o
n
N1
5
0
o
f
s
ize
2
2
4
0
x
1
4
8
8
p
ix
el.
A
to
tal
o
f
2
7
i
m
a
g
es
(
1
3
n
o
r
m
al
an
d
1
3
g
lau
co
m
a)
an
d
1
8
i
m
a
g
es
(
1
0
n
o
r
m
al
a
n
d
8
g
lau
co
m
a)
u
s
ed
a
s
ex
p
er
i
m
en
tal
d
ata
i
n
t
h
e
p
h
ase
o
f
l
ea
r
n
in
g
a
n
d
test
i
n
g
r
esp
ec
tiv
el
y
.
Fo
r
ea
c
h
i
m
a
g
e
w
as
lab
eled
as
c
lass
o
f
n
o
r
m
al
o
r
g
la
u
co
m
a
b
y
a
g
la
u
co
m
a
e
x
p
er
t.
T
h
e
e
x
a
m
p
le
s
o
f
t
h
e
ONH
i
m
ag
e
s
w
it
h
d
i
f
f
er
e
n
t size
(
i
n
p
ix
el
s
)
an
d
class
lab
el
as s
h
o
w
n
in
Fi
g
u
r
e
6
.
W
e
u
s
ed
th
e
v
al
u
e
o
f
p
r
ec
is
i
o
n
,
r
ec
all,
Fs
co
r
e
an
d
ac
cu
r
a
c
y
to
m
ea
s
u
r
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
v
a
lu
e
o
f
p
r
ec
is
io
n
,
r
ec
all
a
n
d
Fs
co
r
e
l
ies
b
et
w
ee
n
0
an
d
1
,
w
h
ile
t
h
e
v
al
u
e
o
f
ac
cu
r
ac
y
lies
b
et
w
ee
n
1
a
n
d
1
0
0
.
I
n
o
r
d
er
to
in
d
icate
s
an
ac
cu
r
ate
m
eth
o
d
th
e
y
s
h
o
u
ld
h
av
e
h
ig
h
v
alu
es.
T
h
e
v
al
u
e
o
f
p
r
ec
is
io
n
,
r
ec
all,
Fs
co
r
e
an
d
ac
cu
r
ac
y
ar
e
d
ef
i
n
ed
as f
o
llo
w
s
:
(
1
)
(
2
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
9
7
–
2
8
0
4
2801
(
3
)
(
4
)
w
h
er
e
T
r
u
e
Po
s
itiv
e
(
T
P)
:
is
th
e
n
u
m
b
er
o
f
class
n
o
r
m
al
cla
s
s
i
f
ied
as c
lass
n
o
r
m
al
T
r
u
e
Neg
ativ
e
(
T
N)
:
is
th
e
n
u
m
b
er
o
f
cla
s
s
g
la
u
co
m
a
cla
s
s
i
f
ied
as c
lass
g
lau
co
m
a
Fals
e
P
o
s
itiv
e
(
FP
)
:
is
t
h
e
n
u
m
b
er
o
f
cla
s
s
g
la
u
co
m
a
cla
s
s
i
f
ied
as c
lass
n
o
r
m
al
Fals
e
Ne
g
ati
v
e
(
FN)
:
is
t
h
e
n
u
m
b
er
o
f
cla
s
s
n
o
r
m
al
cla
s
s
i
f
ie
d
as c
lass
g
la
u
co
m
a
Size
: 3
9
4
X
3
9
3
C
las
s
: G
lau
co
m
a
Size
: 2
3
2
X
2
3
7
C
las
s
: G
lau
co
m
a
Size
: 3
9
2
X
4
1
6
C
las
s
: G
lau
co
m
a
Size
3
7
5
X
4
2
3
C
las
s
: N
o
r
m
al
Size
3
1
1
X
3
4
5
C
las
s
: N
o
r
m
al
Fig
u
r
e
6
.
T
h
e
ONH
I
m
a
g
es
w
i
th
Di
f
f
er
en
t Size
(
i
n
p
ix
el
s
)
an
d
C
lass
L
ab
el
(
a)
(
b
)
(
c)
Fig
u
r
e
7
.
Featu
r
es
Ma
tr
i
x
Fo
r
m
atio
n
Step
,
C
o
llu
m
n
(
a)
Or
ig
in
al
I
m
a
g
e
,
(
b
)
C
u
p
A
r
ea
C
o
n
t
o
u
r
an
d
(
c
)
Featu
r
es M
atr
ix
o
f
C
u
p
A
r
ea
C
o
n
to
u
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Th
e
C
o
n
to
u
r
E
xtra
ctio
n
o
f Cu
p
in
F
u
n
d
u
s
I
ma
g
es fo
r
Gla
u
c
o
ma
Dete
ctio
n
(
A
n
in
d
ita
S
ep
ti
a
r
in
i
)
2802
I
n
o
r
d
er
to
d
eter
m
i
n
e
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
m
et
h
o
d
,
w
e
c
o
m
p
ar
ed
th
e
cla
s
s
i
f
icat
io
n
r
es
u
lts
o
f
th
e
ONH
i
m
a
g
es
o
f
o
u
r
m
e
th
o
d
b
y
f
o
r
m
i
n
g
t
h
e
f
ea
t
u
r
e
m
atr
i
x
ag
ai
n
s
t
t
h
e
class
if
ica
tio
n
r
esu
lt
s
o
f
th
e
e
x
p
er
t
b
ased
o
n
o
b
s
er
v
atio
n
o
f
th
e
O
NH
i
m
a
g
e
.
Sev
er
al
p
r
o
ce
s
s
es
w
er
e
ap
p
lied
to
th
e
ONH
i
m
a
g
e
(
Fig
u
r
e
7
(
a)
)
as
th
e
in
it
ial
in
p
u
t
to
p
r
o
d
u
ce
th
e
co
n
to
u
r
o
f
th
e
cu
p
ar
ea
(
Fig
u
r
e
7
(
b
)
)
u
p
to
f
o
r
m
th
e
f
ea
tu
r
e
m
atr
i
x
as
illu
s
tr
ated
in
Fi
g
u
r
e
7
(
c)
.
W
e
ev
alu
ated
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
u
s
i
n
g
f
o
u
r
k
i
n
d
s
o
f
clas
s
if
ica
tio
n
m
eth
o
d
s
n
a
m
el
y
M
L
P
,
Naiv
e
B
ay
e
s
,
k
-
NN
a
n
d
SVM
to
f
in
d
o
u
t
th
e
o
p
ti
m
al
cla
s
s
i
f
icat
io
n
m
e
th
o
d
.
T
ab
le
1
c
o
m
p
ar
es
all
th
e
cla
s
s
i
f
icatio
n
m
et
h
o
d
s
in
ter
m
s
o
f
a
v
er
ag
e
p
r
ec
is
io
n
,
r
ec
all,
Fs
co
r
e
an
d
ac
cu
r
ac
y
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
m
et
h
o
d
is
s
u
m
m
ar
ized
i
n
T
ab
le
1
.
T
h
e
tab
le
s
h
o
w
s
th
at
o
u
r
m
eth
o
d
ac
h
iev
e
s
th
e
h
ig
h
v
al
u
e
o
f
p
r
ec
is
io
n
,
r
ec
all
an
d
Fs
co
r
e
o
f
0
.
9
5
,
0
.
9
4
an
d
0
.
9
4
r
esp
ec
tiv
el
y
,
w
h
i
le
th
e
ac
cu
r
ac
y
o
f
9
4
.
4
4
%
u
s
in
g
SVM
m
et
h
o
d
as
class
i
f
ier
.
T
h
er
e
ar
e
a
f
ew
i
n
s
ig
h
ts
f
r
o
m
o
u
r
ex
p
er
i
m
e
n
t
r
es
u
lt
r
elate
d
to
g
lau
co
m
a
d
etec
tio
n
i
n
ter
m
o
f
th
e
ex
tr
ac
tio
n
f
ea
t
u
r
es.
I
n
t
h
is
r
esear
ch
,
th
e
co
m
b
i
n
ed
o
f
th
e
co
n
to
u
r
ex
tr
ac
tio
n
o
f
th
e
c
u
p
an
d
SV
M
m
et
h
o
d
as
class
if
ier
p
r
o
d
u
ce
co
m
p
etit
iv
e
r
es
u
lt.
I
t
is
b
ased
o
n
th
e
co
m
p
ar
is
o
n
o
f
t
h
e
r
esu
lt
s
w
it
h
s
e
v
er
al
p
r
ev
io
u
s
r
ea
s
er
ce
s
w
h
ic
h
u
s
e
d
if
f
er
e
n
t f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
as s
h
o
w
n
in
T
ab
le
2
.
T
ab
le
1
.
T
h
e
C
o
m
p
ar
is
o
n
P
er
f
o
r
m
a
n
ce
o
f
C
las
s
if
icatio
n
Me
t
h
o
d
C
l
a
ssi
f
i
e
r
C
l
a
ss
P
r
e
c
i
si
o
n
R
e
c
a
l
l
F
sco
r
e
A
c
c
u
r
a
c
y
(
%)
M
L
P
G
l
a
u
c
o
ma
0
.
6
4
0
.
8
7
0
.
7
4
7
2
.
2
2
N
o
r
mal
0
.
8
6
0
.
6
0
0
.
7
1
A
v
e
r
a
g
e
0
.
7
6
0
.
7
2
0
.
7
2
N
a
ï
v
e
B
a
y
e
s
G
l
a
u
c
o
ma
0
.
6
7
1
.
0
0
0
.
8
0
7
7
.
7
8
N
o
r
mal
1
.
0
0
0
.
6
0
0
.
7
5
A
v
e
r
a
g
e
0
.
8
5
0
.
7
8
0
.
7
7
k
-
NN
G
l
a
u
c
o
ma
0
.
8
0
1
.
0
0
0
.
8
9
8
8
.
8
9
N
o
r
mal
1
.
0
0
0
.
8
0
0
.
8
9
A
v
e
r
a
g
e
0
.
9
1
0
.
8
9
0
.
8
9
S
V
M
G
l
a
u
c
o
ma
1
.
0
0
0
.
8
7
0
.
9
3
9
4
.
4
4
N
o
r
mal
0
.
9
1
1
.
0
0
0
.
9
5
A
v
e
r
a
g
e
0
.
9
5
0
.
9
4
0
.
9
4
T
ab
le
2
.
T
h
e
C
o
m
p
ar
is
o
n
o
f
R
esu
lt
s
w
it
h
o
th
er
R
e
s
ea
r
ch
s
R
e
se
a
r
c
h
D
a
t
a
se
t
F
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
C
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
M
a
t
so
p
o
u
l
o
s e
t
a
l
.
(
2
0
0
8
)
1
2
7
i
mag
e
s (5
6
g
l
a
u
c
o
ma
a
n
d
7
1
n
o
r
mal
)
B
l
o
o
d
v
e
ssel
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
s
e
l
f
o
rg
a
n
i
z
i
n
g
m
a
p
s
(
S
O
M
s)
M
u
l
t
i
l
a
y
e
r
e
d
A
N
N
8
7
.
5
%
M
a
t
su
d
a
e
t
a
l
.
(
2
0
0
9
)
1
3
3
i
mag
e
s
(
9
1
n
o
r
mal
a
n
d
4
2
g
l
a
u
c
o
ma)
V
e
c
t
o
r
f
e
a
t
u
r
e
s e
x
t
r
a
c
t
i
o
n
u
si
n
g
S
O
M
L
V
Q
7
1
,
2
%
B
o
c
k
e
t
a
l
.
(
2
0
1
0
)
5
7
5
i
mag
e
s (2
3
9
g
l
a
u
c
o
ma
a
n
d
3
3
6
n
o
r
mal
)
R
a
w
i
n
t
e
n
si
t
i
e
s,
f
o
u
r
i
e
r
a
n
a
l
y
si
s
a
n
d
B
-
sp
l
i
n
e
i
n
t
e
r
p
o
l
a
t
i
o
n
S
V
M
8
8
%
A
n
n
u
a
n
d
J
u
st
i
n
(
2
0
1
3
)
2
0
i
m
a
g
e
s (1
0
n
o
r
mal
a
n
d
1
0
g
l
a
u
c
o
ma)
M
e
t
o
d
e
D
i
scre
t
e
W
a
v
e
l
e
t
T
r
a
n
sf
o
r
m
(
D
W
T
)
P
N
N
9
0
%
N
o
r
o
n
h
a
e
t
a
l
.
(
2
0
1
4
)
2
7
2
i
mag
e
s (1
0
0
n
o
r
mal
,
1
7
2
g
l
a
u
c
o
ma)
H
i
g
h
e
r
O
r
d
e
r
S
p
e
c
t
r
a
(
H
O
S
)
c
u
m
u
l
a
n
t
s
N
a
ï
v
e
B
a
y
e
si
a
n
9
2
,
6
5
%
O
u
r
me
t
h
o
d
4
4
i
m
a
g
e
s (2
3
n
o
r
mal
a
n
d
2
1
g
l
a
u
c
o
ma)
C
o
n
t
o
u
r
f
e
a
t
u
r
e
b
a
se
d
o
n
t
h
e
c
u
p
u
si
n
g
t
h
r
e
sh
o
l
d
i
n
g
a
n
d
mo
r
p
h
o
l
o
g
y
S
V
M
9
4
.
4
4
%
B
ased
o
n
tab
le
2
,
g
lau
co
m
a
d
etec
tio
n
p
r
o
d
u
ce
d
b
y
s
ev
e
r
al
ap
p
r
o
ac
h
es
,
s
u
ch
as
B
lo
o
d
v
ess
el
ex
tr
ac
tio
n
u
s
i
n
g
S
OM
s
[
2
1
]
,
Vec
to
r
f
ea
tu
r
es
ex
tr
ac
tio
n
u
s
in
g
SOM
[
8
]
,
R
aw
i
n
te
n
s
it
ies,
f
o
u
r
ier
an
al
y
s
is
an
d
B
-
s
p
lin
e
i
n
ter
p
o
latio
n
[
1
7
]
,
DW
T
m
et
h
o
d
[
1
2
]
an
d
HOS
c
u
m
u
lan
t
s
[
1
0
]
.
W
e
co
m
p
ar
e
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
p
r
o
p
o
s
ed
m
e
th
o
d
b
ased
o
n
t
h
e
ac
cu
r
ac
y
ac
h
ie
v
e
m
e
n
t.
T
h
e
a
cc
u
r
ac
y
ac
h
ie
v
ed
b
y
[
2
1
]
is
8
7
.
5
%,
[
8
]
is
7
1
.
2
%,
[
1
7
]
is
8
8
%,
[
1
2
]
is
9
0
% a
n
d
[
1
0
]
is
9
2
.
6
5
%.
4.
CO
NCLU
SI
O
N
I
n
t
h
is
r
e
s
ea
r
ch
,
w
e
p
r
o
p
o
s
e
g
lau
co
m
a
d
etec
tio
n
m
et
h
o
d
b
ased
o
n
t
h
e
co
n
to
u
r
e
x
tr
ac
tio
n
o
f
t
h
e
cu
p
in
f
u
n
d
u
s
i
m
ag
e
s
.
T
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
ev
alu
ated
ag
ai
n
s
t
4
4
i
m
ag
e
s
co
n
s
i
s
ti
n
g
o
f
2
3
n
o
r
m
al
a
n
d
2
1
g
lau
co
m
a.
I
t
ac
h
ie
v
es
th
e
v
al
u
e
o
f
t
h
e
ac
c
u
r
ac
y
o
f
9
4
.
4
4
%
u
s
in
g
SVM
m
et
h
o
d
as
t
h
e
cla
s
s
if
ier
.
I
t
p
r
o
v
es
th
a
t
th
e
co
n
to
u
r
o
f
t
h
e
c
u
p
is
a
r
eliab
le
f
ea
tu
r
e
t
h
at
ca
n
b
e
u
s
ed
in
th
e
g
la
u
co
m
a
d
etec
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
6
,
No
.
6
,
Dec
em
b
er
2
0
1
6
:
2
7
9
7
–
2
8
0
4
2803
ACK
NO
WL
E
D
G
E
M
E
NT
S
T
h
is
r
esear
ch
w
a
s
s
u
p
p
o
r
ted
b
y
Dr
.
Y
A
P
E
y
e
Ho
s
p
ital
Yo
g
y
a
k
ar
ta
I
n
d
o
n
e
s
ia
f
o
r
p
r
o
v
id
in
g
t
h
e
ex
p
er
i
m
e
n
tal
d
ata
to
u
s
ed
i
n
t
h
is
r
esear
c
h
.
RE
F
E
R
E
NC
E
S
[1
]
H.A
.
Qu
ig
le
y
,
“
Nu
m
b
e
r
o
f
P
e
o
p
l
e
w
it
h
G
lau
c
o
m
a
W
o
rld
w
id
e
”
,
Br
.
J
.
Op
h
th
a
lmo
l
.
,
v
o
l.
8
0
,
n
o
.
5
,
p
p
.
3
8
9
–
9
3
,
M
a
y
1
9
9
6
.
[2
]
A
.
S
e
p
ti
a
rin
i
a
n
d
A
.
Ha
rjo
k
o
,
“
Au
to
m
a
ti
c
G
lau
c
o
m
a
De
t
e
c
ti
o
n
Ba
se
d
o
n
T
h
e
Ty
p
e
o
f
F
e
a
tu
re
s
Us
e
d
:
A
Re
v
ie
w
”
,
J
.
T
h
e
o
r.
Ap
p
l.
I
n
f.
T
e
c
h
n
o
l.
,
v
o
l.
7
2
,
n
o
.
3
,
p
p
.
3
6
6
–
3
7
5
,
2
0
1
5
.
[3
]
G
.
K.
Krie
g
lstein
a
n
d
R.
N.
W
e
in
r
e
b
,
Gla
u
c
o
ma
(
Esse
n
ti
a
ls
i
n
Op
h
th
a
lm
o
lo
g
y
)
.
S
p
rin
g
e
r
-
V
e
rlag
Be
rli
n
He
id
e
lb
e
rg
,
2
0
0
9
.
[4
]
H.
T
jan
d
ra
sa
,
A
.
W
ij
a
y
a
n
ti
,
a
n
d
N.
S
u
c
iati,
“
Op
ti
c
Ne
rv
e
He
a
d
S
e
g
m
e
n
tatio
n
Us
in
g
Ho
u
g
h
T
ra
n
sfo
rm
a
n
d
A
c
ti
v
e
Co
n
t
o
u
rs
”
,
T
EL
KOM
NIKA
,
v
o
l.
1
0
,
n
o
.
3
,
p
p
.
5
3
1
–
5
3
6
,
2
0
1
2
.
[5
]
M
.
Us
m
a
n
Ak
ra
m
,
I.
Ja
m
a
l,
a
n
d
A
.
T
a
riq
,
“
Blo
o
d
V
e
ss
e
l
E
n
h
a
n
c
e
m
e
n
t
a
n
d
S
e
g
m
e
n
tatio
n
F
o
r
S
c
re
e
n
in
g
o
f
Dia
b
e
ti
c
Re
ti
n
o
p
a
th
y
”
,
T
e
lko
mn
ika
,
v
o
l.
1
0
,
n
o
.
2
,
p
p
.
3
2
7
–
3
3
4
,
2
0
1
2
.
[6
]
R.
A
k
h
a
v
a
n
a
n
d
K.
F
a
e
z
,
“
Tw
o
No
v
e
l
Re
ti
n
a
l
Blo
o
d
V
e
ss
e
l
S
e
g
m
e
n
tatio
n
A
lg
o
rit
h
m
s
”
,
In
t.
J
.
El
e
c
tr.
Co
mp
u
t.
En
g
.
,
v
o
l.
4
,
n
o
.
3
,
p
p
.
3
9
8
–
4
1
0
,
2
0
1
4
.
[7
]
J.
Yu
,
S
.
S
ib
te,
R.
A
b
id
i,
P
.
H.
A
rtes
,
a
n
d
A
.
M
c
in
ty
re
,
“
A
u
to
m
a
ted
Op
ti
c
Ne
rv
e
A
n
a
l
y
sis
f
o
r
Dia
g
n
o
stic
S
u
p
p
o
rt
in
G
lau
c
o
m
a
”
,
in
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
8
t
h
IE
EE
S
y
m
p
o
siu
m
o
n
Co
m
p
u
ter
-
Ba
se
d
M
e
d
ica
l
S
y
ste
ms
,
2
0
0
5
.
[8
]
N.
M
a
tsu
d
a
,
J.
L
a
a
k
so
n
e
n
,
F
.
T
a
ji
m
a
,
a
n
d
H.
S
a
to
,
“
Clas
sif
ic
a
ti
o
n
o
f
F
u
n
d
u
s
Im
a
g
e
s
f
o
r
Dia
g
n
o
sin
g
G
l
a
u
c
o
m
a
b
y
S
e
lf
-
Org
a
n
izin
g
M
a
p
a
n
d
L
e
a
rn
in
g
V
e
c
to
r”
,
in
In
ter
n
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Ne
u
ra
l
In
fo
rm
a
ti
o
n
Pr
o
c
e
ss
in
g
,
2
0
0
9
,
p
p
.
7
0
3
–
7
1
0
.
[9
]
A
.
Be
lg
h
it
h
,
M
.
Ba
las
u
b
ra
m
a
n
ian
,
C.
B
o
w
d
,
R.
N.
W
e
in
re
b
,
a
n
d
L
.
M
.
Zan
g
w
il
l,
“
A
Un
if
ied
F
ra
m
e
w
o
rk
f
o
r
G
lau
c
o
m
a
P
ro
g
re
ss
io
n
De
tec
ti
o
n
u
sin
g
He
id
e
lb
e
rg
Re
ti
n
a
T
o
m
o
g
ra
p
h
Im
a
g
e
s
”
,
C
o
mp
u
t.
M
e
d
.
I
ma
g
in
g
Gr
a
p
h
.
,
v
o
l.
3
8
,
n
o
.
5
,
p
p
.
4
1
1
–
4
2
0
,
2
0
1
4
.
[1
0
]
K.P
.
No
r
o
n
h
a
,
U.R.
A
c
h
a
r
y
a
,
K
.
P
.
Na
y
a
k
,
R.
Jo
y
,
a
n
d
S
.
V
Bh
a
n
d
a
ry
,
“
A
u
to
m
a
t
e
d
Clas
sif
ic
a
ti
o
n
o
f
G
lau
c
o
m
a
S
tag
e
s u
sin
g
Hig
h
e
r
Ord
e
r
Cu
m
u
lan
t
F
e
a
tu
re
s”
,
Bi
o
me
d
.
S
ig
n
a
l
Pr
o
c
e
ss
.
Co
n
tro
l
,
v
o
l
.
1
0
,
p
p
.
1
7
4
–
1
8
3
,
2
0
1
4
.
[1
1
]
M
.
R.
K.
M
o
o
k
iah
,
U.R.
A
c
h
a
r
y
a
,
C.
M
.
L
i
m
,
A
.
P
e
tzn
ick
,
a
n
d
J.S
.
S
u
ri,
“
Da
ta
M
in
in
g
T
e
c
h
n
iq
u
e
f
o
r
A
u
to
m
a
ted
Dia
g
n
o
sis
o
f
G
l
a
u
c
o
m
a
u
sin
g
Hi
g
h
e
r
Ord
e
r
S
p
e
c
tra
a
n
d
W
a
v
e
let
En
e
rg
y
F
e
a
tu
re
s”
,
Kn
o
wled
g
e
-
B
a
se
d
S
y
st.
,
v
o
l.
3
3
,
p
p
.
7
3
–
8
2
,
2
0
1
2
.
[1
2
]
N.
A
n
n
u
a
n
d
J.
Ju
stin
,
“
Clas
sif
ica
ti
o
n
o
f
G
lau
c
o
m
a
I
m
a
g
e
s
u
sin
g
W
a
v
e
le
t
b
a
s
e
d
En
e
rg
y
F
e
a
tu
re
s
a
n
d
P
CA
”
,
In
t.
J
.
S
c
i.
E
n
g
.
Res
.
,
v
o
l.
4
,
n
o
.
5
,
p
p
.
1
3
6
9
–
1
3
7
4
,
2
0
1
3
.
[1
3
]
R.
G
a
y
a
th
ri,
P
.
V
Ra
o
,
a
n
d
S
.
A
r
u
n
a
,
“
A
u
to
m
a
ted
G
lau
c
o
m
a
De
te
c
ti
o
n
S
y
ste
m
b
a
se
d
o
n
W
a
v
e
let
En
e
rg
y
f
e
a
tu
re
s
a
n
d
A
NN
”
,
in
In
ter
n
a
ti
o
n
a
i
Co
n
fer
e
n
c
e
o
n
Ad
v
a
n
c
e
s
in
Co
mp
u
ti
n
g
,
Co
mm
u
n
ica
ti
o
n
s
a
n
d
In
f
o
rm
a
ti
c
s
,
2
0
1
4
,
p
p
.
2
8
0
8
–
2
8
1
2
.
[1
4
]
D.
L
a
m
a
n
i,
Ra
m
e
g
o
w
d
a
,
a
n
d
T
.
M
a
n
ju
n
a
th
,
“
F
ra
c
tal
Dim
e
n
sio
n
a
s
Dia
g
n
o
stic P
a
ra
m
e
t
e
r
to
De
tec
t
G
lau
c
o
m
a
”
,
In
t
.
J
.
In
n
o
v
.
E
n
g
.
T
e
c
h
n
o
l.
,
v
o
l.
2
,
n
o
.
1
,
p
p
.
6
3
–
6
9
,
2
0
1
3
.
[1
5
]
S
.
Ka
rth
ik
e
y
a
n
a
n
d
N.
Re
n
g
a
ra
ja
n
,
“
P
e
rf
o
rm
a
n
c
e
A
n
a
l
y
sis
o
f
G
r
a
y
Lev
e
l
Co
-
Oc
c
u
rre
n
c
e
M
a
tri
x
Tex
tu
re
F
e
a
tu
re
s
f
o
r
G
l
a
u
c
o
m
a
Dia
g
n
o
sis”
,
Am.
J
.
Ap
p
l
.
S
c
i.
,
v
o
l.
1
1
,
n
o
.
2
,
p
p
.
2
4
8
–
2
5
7
,
2
0
1
4
.
[1
6
]
R.
Bo
c
k
,
J.
M
e
ier,
G
.
M
ich
e
lso
n
,
L.
G.
N
y
u
l,
a
n
d
J.
Ho
rn
e
g
g
e
r,
“
C
las
sify
in
g
G
lau
c
o
m
a
w
it
h
I
m
a
g
e
-
Ba
se
d
F
e
a
tu
re
s
f
ro
m
F
u
n
d
u
s
P
h
o
t
o
g
ra
p
h
s”
,
S
p
rin
g
e
r
-
Ver
la
g
,
p
p
.
3
5
5
–
3
6
4
,
2
0
0
7
.
[1
7
]
R.
Bo
c
k
,
J.
M
e
ier,
L
.
G
.
N
y
ú
l,
J
.
Ho
rn
e
g
g
e
r,
a
n
d
G
.
M
ich
e
lso
n
,
“
G
lau
c
o
m
a
ris
k
in
d
e
x
:
A
u
to
m
a
ted
G
l
a
u
c
o
m
a
De
te
c
ti
o
n
f
ro
m
Co
lo
r
F
u
n
d
u
s Ii
m
a
g
e
s
”
,
M
e
d
.
Ima
g
e
A
n
a
l
.
,
v
o
l.
1
4
,
n
o
.
3
,
p
p
.
4
7
1
–
4
8
1
,
2
0
1
0
.
[1
8
]
J.
Od
strc
il
ik
,
R.
Ko
lar,
R.
T
o
rn
o
w
,
J.
Ja
n
,
A
.
Bu
d
a
i,
M
.
M
a
y
e
r,
M
.
V
o
d
a
k
o
v
a
,
R.
L
a
e
m
m
e
r,
M
.
L
a
m
o
s,
Z.
Ku
n
a
,
J.
G
a
z
a
re
k
,
T
.
Ku
b
e
n
a
,
P
.
Ce
r
n
o
se
k
,
a
n
d
M
.
R
o
n
z
h
i
n
a
,
“
T
h
ick
n
e
ss
re
late
d
tex
tu
ra
l
p
ro
p
e
rt
ies
o
f
re
ti
n
a
l
n
e
rv
e
f
ib
e
r
la
y
e
r
in
c
o
lo
r
f
u
n
d
u
s
im
a
g
e
s”
,
Co
mp
u
t.
M
e
d
.
Ima
g
in
g
Gr
a
p
h
.
,
v
o
l.
3
8
,
n
o
.
6
,
p
p
.
5
0
8
–
5
1
6
,
2
0
1
4
.
[1
9
]
R.
Ko
lar
a
n
d
J.
Ja
n
,
“
De
tec
ti
o
n
o
f
G
lau
c
o
m
a
to
u
s
Ey
e
v
ia
Co
lo
r
F
u
n
d
u
s
Im
a
g
e
s
Us
in
g
F
ra
c
ta
l
Dim
e
n
sio
n
s”
,
RA
DIO
ENGINEE
R
ING
,
v
o
l.
1
7
,
n
o
.
3
,
p
p
.
1
0
9
–
1
1
4
,
2
0
0
8
.
[2
0
]
P
.
Y.
Kim
,
K.M
.
If
tek
h
a
ru
d
d
in
,
P
.
G
.
Da
v
e
y
,
M
.
T
o
th
,
A
.
G
a
r
a
s,
G
.
Ho
ll
o
,
a
n
d
E
.
A
.
Esso
c
k
,
“
No
v
e
l
F
ra
c
tal
F
e
a
tu
re
-
Ba
se
d
M
u
lt
icla
ss
G
lau
c
o
m
a
De
t
e
c
ti
o
n
a
n
d
P
ro
g
re
ss
io
n
P
re
d
icti
o
n
”
,
IEE
E
J
.
B
io
me
d
.
He
a
l.
INF
ORM
AT
ICS
,
v
o
l.
1
7
,
n
o
.
2
,
p
p
.
2
6
9
–
2
7
6
,
2
0
1
3
.
[2
1
]
G
.
K.
M
a
tso
p
o
u
l
o
s,
P
.
A
.
A
sv
e
s
tas
,
K.K.
De
li
b
a
sis,
N.A
.
M
o
u
ra
v
li
a
n
sk
y
,
a
n
d
T
.
G
.
Ze
y
e
n
,
“
De
tec
ti
o
n
o
f
G
lau
c
o
m
a
to
u
s
Ch
a
n
g
e
Ba
se
d
o
n
V
e
ss
e
l
S
h
a
p
e
A
n
a
ly
sis”
,
Co
mp
u
t.
M
e
d
.
Ima
g
in
g
Gr
a
p
h
.
,
v
o
l.
3
2
,
p
p
.
1
8
3
–
1
9
2
,
2
0
0
8
.
[2
2
]
N.
T
a
n
,
Y.
X
u
,
W
.
B.
G
o
h
,
a
n
d
J.
L
iu
,
“
Ro
b
u
st
M
u
lt
i
-
S
c
a
le
S
u
p
e
rp
ix
e
l
Clas
si
f
ic
a
ti
o
n
F
o
r
Op
ti
c
Cu
p
L
o
c
a
li
z
a
ti
o
n
”
,
Co
mp
u
t
.
M
e
d
.
Im
a
g
i
n
g
Gr
a
p
h
.
,
v
o
l.
4
0
,
p
p
.
1
8
2
–
1
9
3
,
M
a
r.
2
0
1
5
.
[2
3
]
H.
A
h
m
a
d
,
A
.
Ya
m
in
,
A
.
S
h
a
k
e
e
l,
S
.
O.
G
il
lan
i,
a
n
d
U.
A
n
sa
ri,
“
De
tec
ti
o
n
o
f
G
lau
c
o
m
a
Us
in
g
Re
ti
n
a
l
F
u
n
d
u
s
Im
a
g
e
s”
,
p
p
.
3
2
1
–
3
2
4
,
2
0
1
4
.
[2
4
]
J.
Na
y
a
k
a
n
d
R.
A
.
U,
“
A
u
to
m
a
t
e
d
Dia
g
n
o
sis
o
f
G
lau
c
o
m
a
Us
in
g
D
ig
it
a
l
F
u
n
d
u
s
Im
a
g
e
s”
,
J
.
M
e
d
.
S
y
st.
,
v
o
l.
3
3
,
p
p
.
337
–
3
4
6
,
2
0
0
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
Th
e
C
o
n
to
u
r
E
xtra
ctio
n
o
f Cu
p
in
F
u
n
d
u
s
I
ma
g
es fo
r
Gla
u
c
o
ma
Dete
ctio
n
(
A
n
in
d
ita
S
ep
ti
a
r
in
i
)
2804
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
An
in
d
ita
S
e
p
tia
r
i
n
i
w
a
s
b
o
rn
i
n
Ng
a
n
ju
k
,
Eas
t
Ja
v
a
,
I
n
d
o
n
e
sia
in
S
e
p
tem
b
e
r
1
st
19
82
.
S
h
e
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r
d
e
g
re
e
in
In
f
o
rm
a
ti
c
En
g
in
e
e
rin
g
o
f
Un
iv
e
rsitas
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
in
2
0
0
5
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
in
c
e
d
e
g
re
e
a
t
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
in
2
0
0
9
.
Cu
rre
n
tl
y
,
s
h
e
is
a
tt
e
n
d
in
g
d
o
c
to
ra
l
p
ro
g
ra
m
in
De
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
,
Un
iv
e
rsitas
Ga
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
.
S
h
e
is
w
o
rk
in
g
a
s
a
le
c
tu
re
in
th
e
d
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
Un
iv
e
rsitas
M
u
la
w
a
r
m
a
n
,
S
a
m
a
rin
d
a
,
In
d
o
n
e
sia
sin
c
e
2
0
0
9
.
He
r
re
se
a
rc
h
in
tere
st are
ima
g
e
p
ro
c
e
ss
in
g
,
p
a
tt
e
rn
re
c
o
g
n
it
i
o
n
a
n
d
n
e
u
ra
l
n
e
tw
o
rk
.
H
a
m
d
a
n
i
wa
s
b
o
rn
in
M
u
a
ra
Be
n
g
k
a
l
,
Eas
t
Ka
li
m
a
n
tan
,
I
n
d
o
n
e
sia
in
Ju
n
e
6
th
19
79
.
H
e
re
c
e
iv
e
d
h
is
Ba
c
h
e
lo
r
d
e
g
re
e
in
In
f
o
rm
a
ti
c
En
g
in
e
e
rin
g
of
Un
iv
e
rsitas
A
h
m
a
d
Da
h
lan
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
in
2
0
0
2
.
He
re
c
e
iv
e
d
h
e
r
M
a
ste
r
o
f
Co
m
p
u
ter
S
c
in
c
e
d
e
g
re
e
a
t
Un
iv
e
rsitas
G
a
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
in
2
0
0
9
.
Cu
rre
n
tl
y
,
h
e
is
a
tt
e
n
d
in
g
d
o
c
t
o
ra
l
p
ro
g
ra
m
in
D
e
p
a
rt
m
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Un
iv
e
rsitas
Ga
d
jah
M
a
d
a
,
Yo
g
y
a
k
a
rta,
In
d
o
n
e
sia
.
H
e
is
w
o
rk
in
g
a
s
a
l
e
c
tu
re
in
th
e
d
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
Un
iv
e
rsitas
M
u
la
w
a
r
m
a
n
,
S
a
m
a
rin
d
a
,
In
d
o
n
e
sia
sin
c
e
2
0
0
5
.
His
re
se
a
r
c
h
in
tere
st
a
re
G
r
o
u
p
De
c
isio
n
S
u
p
p
o
rt
,
Da
ta
S
e
c
u
rit
y
a
n
d
In
f
o
rm
a
ti
o
n
S
y
ste
m
.
Dy
n
a
M
a
r
isa
K
h
a
irin
a
w
a
s
b
o
rn
in
S
a
m
a
rin
d
a
,
Eas
t
Ka
li
m
a
n
tan
,
I
n
d
o
n
e
sia
in
M
a
re
t
5
th
19
84
.
S
h
e
re
c
e
iv
e
d
h
e
r
Ba
c
h
e
lo
r
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
of
Un
iv
e
rsitas
M
u
law
a
r
m
a
n
,
In
d
o
n
e
sia
in
2
0
0
7
.
S
h
e
re
c
e
iv
e
d
h
e
r
M
a
ste
r
o
f
In
f
o
r
m
a
ti
o
n
S
y
ste
m
d
e
g
re
e
a
t
Un
iv
e
rsitas
Dip
o
n
e
g
o
ro
,
S
e
m
a
ra
n
g
,
In
d
o
n
e
sia
in
2
0
1
2
.
S
h
e
is
w
o
rk
in
g
a
s
a
le
c
tu
re
in
th
e
d
e
p
a
rtm
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
Un
iv
e
rsitas
M
u
law
a
r
m
a
n
,
S
a
m
a
rin
d
a
,
In
d
o
n
e
sia
sin
c
e
2
0
0
8
.
He
r
re
se
a
rc
h
in
tere
st
a
re
in
f
o
rm
a
ti
o
n
s
y
ste
m
a
n
d
d
e
c
isio
n
su
p
p
o
r
t
sy
ste
m
.
S
h
e
is
m
e
e
m
b
e
r
o
f
I
AA
II
(Ik
a
t
a
n
A
h
li
In
f
o
rm
a
ti
k
a
In
d
o
n
e
sia
)
a
n
d
A
P
T
IKO
M
(A
ss
o
c
iatio
n
o
f
Co
m
p
u
ti
n
g
a
n
d
I
n
f
o
rm
a
ti
c
s
In
stit
u
ti
o
n
In
d
o
n
e
sia
)
Evaluation Warning : The document was created with Spire.PDF for Python.