I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
p
u
t
er
Science
Vo
l.
1
2
,
No
.
1
,
Octo
b
er
201
8
,
p
p
.
2
3
3
~
2
3
8
I
SS
N:
2502
-
4752
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ee
cs
.
v
1
2
.i
1
.
p
p
233
-
2
3
8
233
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e.
co
m/jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
ijeec
s
The E
m
beddi
ng
Perf
o
r
m
a
nce
of S
tegSVM
Mo
del in
I
m
a
g
e
Stega
no
g
ra
phy
H
a
niza
n Sha
k
er
H
us
s
a
i
n
1
,
R
o
s
hid
i D
i
n
2
,
M
o
hd
H
a
nif
Ali
3
,
No
r
B
a
lqi
s
4
1
,
3,
4
Ku
l
li
y
y
a
h
M
u
a
m
a
lat
d
a
n
S
a
in
s P
e
n
g
u
ru
sa
n
,
Un
iv
e
rsiti
Isla
m
An
tara
b
a
n
g
sa
S
u
lt
a
n
A
b
d
u
l
Ha
li
m
M
u
’a
d
z
a
m
S
h
a
h
,
0
9
3
0
0
,
Ke
d
a
h
,
M
a
lay
sia
2
S
c
h
o
o
l
o
f
Co
m
p
u
ti
n
g
(S
OC),
C
A
S
,
Un
iv
e
rsiti
Uta
ra
M
a
la
y
sia
0
6
0
1
0
S
i
n
to
k
,
Ke
d
a
h
,
M
a
lay
sia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
1
,
2
0
1
8
R
ev
i
s
ed
J
u
l 1
0
,
2
0
1
8
A
cc
ep
ted
Ju
l 2
5
,
2
0
1
8
T
h
is
p
a
p
e
r
f
o
c
u
se
s
o
n
o
n
e
o
f
th
e
a
re
a
s
o
f
in
f
o
rm
a
ti
o
n
h
id
in
g
w
h
ic
h
is
ima
g
e
ste
g
a
n
o
g
ra
p
h
y
.
It
p
ro
p
o
se
s
th
e
S
teg
S
V
M
m
o
d
e
l
a
s
a
n
e
m
b
e
d
d
in
g
tec
h
n
i
q
u
e
in
ste
g
a
n
o
g
ra
p
h
y
th
a
t
h
a
s
e
x
p
l
o
it
e
d
h
u
m
a
n
v
isu
a
l
sy
ste
m
th
ro
u
g
h
S
h
if
ted
L
S
B
th
a
t
sh
o
w
s
a
n
e
x
p
e
c
ted
p
e
rfo
rm
a
n
c
e
.
T
h
e
p
e
r
f
o
rm
a
n
c
e
o
f
th
is
tec
h
n
iq
u
e
e
v
a
lu
a
ti
o
n
is
b
a
se
d
o
n
im
p
e
rc
e
p
ti
b
i
li
ty
a
n
d
r
o
b
u
stn
e
ss
o
f
th
e
tec
h
n
i
q
u
e
c
o
m
p
a
re
d
to
th
e
o
th
e
r
p
re
v
io
u
s
m
o
d
e
ls
in
i
m
a
g
e
ste
g
a
n
o
g
ra
p
h
y
d
o
a
m
i
n
.
T
h
u
s,
th
e
re
su
lt
sh
o
w
s
th
a
t
th
e
p
ro
p
o
se
d
S
teg
S
V
M
m
o
d
e
l
is
p
ro
m
isin
g
.
F
o
r
f
u
rth
e
r
w
o
rk
,
it
is
su
g
g
e
ste
d
th
a
t
th
e
o
th
e
r
im
a
g
e
d
o
m
a
in
th
ro
u
g
h
o
th
e
r
in
telli
g
e
n
t
m
e
th
o
d
s s
h
o
u
ld
b
e
i
n
v
e
stig
a
ted
.
K
ey
w
o
r
d
s
:
I
m
ag
e
s
t
eg
an
o
g
r
a
p
h
y
L
e
as
t
s
ig
n
if
ic
an
t
b
i
t
D
i
s
c
r
e
t
e
c
o
s
in
e
t
r
an
s
f
o
r
m
Co
p
y
rig
h
t
©
2
0
1
8
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
:
R
o
s
h
id
i D
in
,
Ku
lli
y
y
ah
M
u
a
m
alat
d
an
Sa
in
s
P
en
g
u
r
u
s
a
n
,
Un
i
v
er
s
iti I
s
la
m
An
tar
ab
an
g
s
a
Su
lta
n
A
b
d
u
l H
ali
m
M
u
’
ad
za
m
S
h
ah
,
0
9
3
0
0
,
Ked
ah
,
Ma
lay
s
ia
.
E
m
ail:
r
o
s
h
id
i@
u
u
m
.
ed
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
co
n
ce
p
t
o
f
e
x
ch
a
n
g
in
g
h
id
d
en
in
f
o
r
m
at
io
n
ca
u
s
e
s
co
n
ce
r
n
s
i
n
t
h
e
f
ield
o
f
i
n
f
o
r
m
atio
n
s
ec
u
r
it
y
[
1
]
.
T
h
er
ef
o
r
e,
s
ev
er
al
m
et
h
o
d
s
h
a
v
e
b
ee
n
ap
p
lied
f
o
r
th
i
s
p
u
r
p
o
s
e
i
n
cl
u
d
in
g
cr
y
p
to
g
r
ap
h
y
,
s
teg
a
n
o
g
r
ap
h
y
,
an
d
w
a
ter
m
a
r
k
in
g
to
estab
lis
h
h
id
d
en
co
m
m
u
n
icatio
n
.
Secr
et
d
ata
ca
n
b
e
co
n
ce
aled
in
d
if
f
er
e
n
t
co
v
er
m
ed
ia
s
u
c
h
as
i
m
a
g
e,
v
id
eo
,
au
d
io
,
an
d
w
r
it
ten
te
x
t
[
2
]
.
Ho
w
e
v
er
,
a
m
o
n
g
all
th
e
s
e
m
eth
o
d
s
,
s
teg
a
n
o
g
r
ap
h
y
h
as
latel
y
ac
q
u
ir
ed
m
o
r
e
atten
tio
n
a
n
d
b
ec
o
m
in
g
i
n
cr
ea
s
i
n
g
l
y
i
m
p
o
r
t
an
t
i
n
t
h
e
f
ield
o
f
co
m
p
u
ter
s
ec
u
r
it
y
.
I
t
i
s
a
p
r
o
c
ess
t
h
at
in
v
o
l
v
es
h
id
in
g
m
es
s
a
g
es
i
n
o
th
er
m
es
s
ag
e
s
[
1
]
w
h
i
le
w
ater
m
ar
k
in
g
is
u
s
i
n
g
to
h
id
e
th
e
s
ec
r
et
m
es
s
ag
es
i
n
v
ar
io
u
s
m
ed
iu
m
[
2
]
.
T
h
e
k
e
y
d
if
f
er
e
n
ce
b
et
w
ee
n
s
teg
a
n
o
g
r
ap
h
y
an
d
w
ater
m
ar
k
i
n
g
is
t
h
at
th
e
g
o
a
l
o
f
s
teg
a
n
o
g
r
ap
h
y
is
m
o
r
e
to
co
v
er
t
co
m
m
u
n
icat
io
n
[
3
]
,
w
h
ich
i
s
w
h
y
,
th
e
f
u
n
d
a
m
en
ta
l
r
eq
u
ir
e
m
e
n
t
o
f
s
teg
an
o
g
r
ap
h
ic
al
g
o
r
ith
m
i
s
t
h
at
m
e
s
s
a
g
es
h
id
d
en
i
n
s
id
e
an
y
ca
r
r
ier
f
ile
s
h
o
u
ld
n
o
t
b
e
s
en
s
ib
le
to
h
u
m
a
n
b
ein
g
s
.
T
h
e
g
o
al
o
f
w
ater
m
ar
k
in
g
o
n
t
h
e
o
th
er
h
an
d
,
i
s
to
en
s
u
r
e
th
e
h
id
d
en
m
es
s
ag
e
al
w
a
y
s
r
e
m
ai
n
s
p
r
es
en
t
in
t
h
e
d
ig
ita
l
m
ed
ia
to
p
r
o
v
id
e
s
o
lid
p
r
o
o
f
o
f
o
w
n
er
s
h
ip
[
4
]
,
[
5
]
.
I
n
th
is
s
tu
d
y
,
t
h
e
f
o
c
u
s
is
g
e
n
er
all
y
o
n
s
teg
an
o
g
r
ap
h
y
a
n
d
s
p
ec
if
icall
y
o
n
i
m
a
g
e
s
te
g
a
n
o
g
r
ap
h
y
.
I
n
f
ac
t,
i
m
a
g
e
s
teg
a
n
o
g
r
ap
h
y
is
t
h
e
m
o
s
t
p
o
p
u
lar
an
d
w
id
el
y
ap
p
lied
tec
h
n
iq
u
e
to
d
a
y
[6
-
8]
.
Am
o
n
g
th
e
f
ac
to
r
s
th
at
led
to
th
is
s
itu
a
tio
n
is
b
ec
au
s
e
m
o
s
t
b
u
s
in
e
s
s
to
d
a
y
ar
e
u
s
in
g
d
ig
ital
i
m
a
g
es
as
th
e
m
ai
n
m
ed
i
u
m
to
d
is
s
e
m
i
n
ate
in
f
o
r
m
atio
n
to
b
e
m
o
r
e
attr
ac
tiv
e
s
u
ch
as
in
ad
v
er
ti
s
in
g
an
d
s
o
o
n
.
T
h
er
e
ar
e
t
w
o
p
o
p
u
l
ar
k
i
n
d
s
o
f
d
o
m
ai
n
i
m
a
g
es
t
h
at
ar
e
n
o
r
m
all
y
u
s
e
d
in
i
m
a
g
e
s
te
g
an
o
g
r
ap
h
y
,
n
a
m
el
y
s
p
atial
an
d
tr
an
s
f
o
r
m
d
o
m
ai
n
s
.
I
n
s
p
atial
d
o
m
ai
n
t
h
e
s
ec
r
et
-
m
e
s
s
a
g
e
is
d
ir
ec
tly
e
m
b
ed
d
ed
in
to
th
e
p
ix
els
o
f
t
h
e
co
v
er
-
i
m
ag
e,
f
o
r
ex
a
m
p
le,
b
y
L
SB
s
u
b
s
t
itu
t
io
n
.
Me
a
n
w
h
ile,
i
n
t
r
an
s
f
o
r
m
d
o
m
a
i
n
t
h
e
co
v
er
-
i
m
ag
e
is
f
ir
s
t
tr
an
s
f
o
r
m
ed
in
to
co
ef
f
ic
ien
t
s
s
u
c
h
a
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
233
–
2
3
8
234
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
(
D
C
T
)
,
d
is
cr
ete
f
o
u
r
ier
tr
an
s
f
o
r
m
(
DFT
)
an
d
d
is
cr
ete
w
a
v
el
et
tr
an
s
f
o
r
m
(
DW
T
)
d
o
m
ai
n
s
[6
]
,
[
8
]
.
Ho
w
e
v
er
,
th
e
m
o
s
t
p
o
p
u
lar
an
d
ex
te
n
s
i
v
el
y
u
s
ed
i
n
i
m
a
g
e
s
te
g
a
n
o
g
r
ap
h
y
is
DC
T
d
o
m
ai
n
[3
]
,
[
4
]
,
[
7]
.
T
h
is
is
b
ec
au
s
e
DC
T
d
o
m
ain
r
elati
v
el
y
co
n
s
u
m
e
s
less
p
o
w
er
an
d
h
as
s
h
o
w
n
to
b
e
u
n
co
r
r
elate
d
d
u
e
to
e
n
er
g
y
c
o
m
p
ac
tio
n
i
n
to
j
u
s
t
o
n
e
co
ef
f
icien
t
i.e
.
D
C
co
e
f
f
ic
ien
t
w
h
i
le
co
m
p
r
ess
i
n
g
t
h
e
co
ef
f
icie
n
t
s
v
al
u
es,
a
n
d
th
i
s
m
ak
es it p
o
s
s
ib
le
to
co
n
s
tr
u
ct
r
e
lativ
el
y
s
i
m
p
le
al
g
o
r
ith
m
s
[
7
]
.
Mo
s
t
o
f
i
m
a
g
es
t
y
p
e
s
h
a
v
e
b
ee
n
u
s
ed
as
t
h
e
co
v
er
-
i
m
a
g
e
in
th
ese
d
o
m
ai
n
s
li
k
e
B
it
m
ap
Fi
le
Fo
r
m
a
t
(
B
MP
)
,
J
o
in
t P
h
o
to
g
r
ap
h
ic
E
x
p
er
ts
Gr
o
u
p
(
J
P
E
G)
an
d
Gr
ap
h
ics I
n
ter
ch
a
n
g
e
Fo
r
m
at
(
GI
F)
i
m
ag
e
s
w
it
h
J
P
E
G
b
ein
g
t
h
e
m
o
s
t
co
m
m
o
n
i
m
a
g
e
f
o
r
m
at
f
o
r
I
n
ter
n
et
a
n
d
lo
ca
l
u
s
ag
e
s
in
ce
it
p
r
o
v
id
es
a
lar
g
e
co
m
p
r
ess
io
n
r
atio
an
d
m
a
in
tai
n
s
h
ig
h
i
m
a
g
e
q
u
alit
y
[
12
-
1
4
]
.
A
cc
o
r
d
in
g
to
C
h
ed
d
ad
[
7
]
,
im
a
g
e
s
te
g
a
n
o
g
r
a
p
h
y
i
s
t
h
e
f
ield
t
h
at
r
e
m
ain
s
u
n
te
s
ted
an
d
v
er
y
f
e
w
o
f
co
m
p
a
n
ies
a
n
d
ass
o
ci
atio
n
s
h
av
e
p
u
b
lis
h
ed
th
e
r
e
q
u
ir
e
m
e
n
ts
o
f
t
h
e
s
teg
a
n
o
g
r
ap
h
y
al
g
o
r
ith
m
e
v
a
lu
atio
n
.
T
h
is
i
s
b
ec
au
s
e
t
h
e
tar
g
et
o
f
th
e
s
te
g
a
n
o
g
r
ap
h
y
s
ch
e
m
e
e
v
al
u
atio
n
s
h
o
u
ld
b
e
clea
r
l
y
id
e
n
ti
f
ied
b
ased
o
n
it
p
u
r
p
o
s
es.
A
s
m
e
n
ti
o
n
ed
ea
r
lier
,
i
m
p
er
ce
p
tib
ilit
y
an
d
r
o
b
u
s
t
n
ess
ar
e
th
e
p
r
o
m
i
n
en
t
cr
iter
ia
s
i
n
ev
al
u
ati
n
g
t
h
e
s
teg
a
n
o
g
r
ap
h
ic
tec
h
n
iq
u
e.
T
h
er
ef
o
r
e,
th
is
p
ap
er
p
r
o
p
o
s
es
th
e
m
o
d
el
th
at
h
a
s
b
ee
n
d
ev
elo
p
ed
is
Steg
SVM
i
n
s
te
g
an
o
g
r
ap
h
y
.
I
t
ev
al
u
ates
t
h
is
m
o
d
el
in
c
o
m
p
ar
is
o
n
w
i
th
t
h
e
r
o
b
u
s
tn
es
s
an
d
i
m
p
er
ce
cp
tib
ilty
o
f
t
h
e
tech
n
iq
u
e
i
n
s
te
g
a
n
o
g
r
ap
h
y
.
2.
ST
E
G
SVM
M
O
DE
L
E
VALUA
T
I
O
N
Usu
al
l
y
,
P
ea
k
-
Si
g
n
a
l
-
to
-
No
is
e
-
R
at
io
(
P
SNR
)
is
u
tili
ze
d
to
v
er
if
y
th
e
p
er
ce
p
tu
al
tr
a
n
s
p
a
r
en
c
y
a
n
d
f
id
elit
y
o
f
i
m
a
g
e
s
te
g
a
n
o
g
r
ap
h
y
al
g
o
r
it
h
m
s
.
I
t
g
i
v
es
a
m
ea
s
u
r
e
o
f
t
h
e
s
tati
s
tical
d
i
f
f
er
en
c
es
b
et
w
ee
n
a
co
v
e
r
-
i
m
a
g
e
an
d
s
teg
o
-
i
m
ag
e.
P
SN
R
is
g
o
o
d
in
p
r
o
v
id
in
g
q
u
alita
tiv
e
r
an
k
o
r
d
er
s
co
r
es
as
lo
n
g
as
th
e
s
a
m
e
co
n
ten
t
an
d
th
e
s
a
m
e
alg
o
r
it
h
m
ar
e
u
s
ed
[
1
5
]
.
T
h
e
h
ig
h
er
th
e
P
SN
R
v
al
u
e,
th
e
m
o
r
e
e
f
f
ec
t
iv
e
t
h
e
tech
n
iq
u
e
i
s
.
As
s
u
c
h
,
t
h
e
tec
h
n
iq
u
e
ca
n
b
e
s
ai
d
ef
f
ec
t
iv
e
if
th
e
P
SN
R
v
al
u
e
is
m
o
r
e
t
h
a
n
4
0
d
B
.
C
h
ed
d
ad
et
al.
(
4
)
h
av
e
s
tated
th
at
i
f
th
e
P
SN
R
v
al
u
e
f
alls
b
elo
w
3
0
d
B
,
it
in
d
icate
s
th
at
th
e
q
u
alit
y
o
f
t
h
e
i
m
ag
e
i
s
f
air
l
y
lo
w
s
i
n
ce
th
e
d
is
to
r
tio
n
ca
u
s
ed
b
y
t
h
e
e
m
b
ed
d
in
g
i
s
n
o
ticea
b
le.
C
o
n
s
eq
u
en
tl
y
,
a
h
ig
h
q
u
a
lit
y
s
te
g
o
-
i
m
ag
e
s
h
o
u
ld
at
te
m
p
t
f
o
r
4
0
d
B
an
d
ab
o
v
e.
Fu
r
th
er
m
o
r
e,
a
g
r
ea
ter
P
SNR
v
al
u
e
m
ea
n
s
a
lo
w
er
d
eg
r
ee
o
f
i
m
a
g
e
d
is
to
r
tio
n
a
f
ter
th
e
s
ec
r
et
-
m
es
s
ag
e
is
e
m
b
ed
d
ed
.
I
n
d
eter
m
i
n
i
n
g
th
e
d
eg
r
ad
atio
n
w
ith
r
esp
ec
t
to
th
e
h
o
s
t
i
m
ag
e,
th
e
r
esear
ch
er
ap
p
lies
th
e
P
SN
R
m
e
tr
ic
(
P
ea
k
Si
g
n
al
-
to
No
is
e
R
a
tio
)
an
d
MSE
(
Me
an
Sq
u
ar
e
E
r
r
o
r
)
to
m
ea
s
u
r
e
t
h
e
d
is
to
r
tio
n
p
r
o
d
u
ce
d
af
ter
th
e
em
b
ed
d
i
n
g
p
r
o
ce
s
s
[
1
6
-
1
7
]
.
I
t i
s
d
ef
i
n
ed
as:
P
S
N
R
=
1
0
l
o
g
10
)
(
2
m
a
x
MS
E
C
M
S
E
=
2
1
1
)
(
1
Q
y
xy
xy
P
x
C
S
PQ
(
1
)
w
h
er
e
x
an
d
y
ar
e
th
e
i
m
a
g
e
c
o
o
r
d
in
ates,
P
an
d
Q
ar
e
th
e
d
im
en
s
io
n
s
o
f
t
h
e
i
m
a
g
e,
S
xy
is
t
h
e
g
en
er
ated
s
teg
o
-
i
m
a
g
e
a
n
d
C
x
y
is
th
e
co
v
er
i
m
ag
e
,
as
s
h
o
w
n
i
n
Fig
u
r
e
1
.
P
SNR
is
o
f
te
n
e
x
p
r
ess
ed
o
n
l
o
g
ar
ith
m
ic
s
ca
le
i
n
d
ec
ib
els (
d
B
)
[
4
]
.
Fig
u
r
e
1
.
I
m
a
g
eJ
ap
p
licatio
n
i
n
an
al
y
s
in
g
i
m
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Th
e
E
mb
ed
d
in
g
P
erfo
r
ma
n
ce
o
f S
teg
S
V
M
Mo
d
el
in
I
ma
g
e
…
(
Ha
n
iz
a
n
S
h
a
ke
r
Hu
s
s
a
in
)
235
T
h
er
e
ar
e
tw
o
k
i
n
d
s
o
f
m
etr
ic
s
th
at
ca
n
b
e
u
s
ed
in
o
r
d
er
to
ev
alu
ate
t
h
e
r
o
b
u
s
tn
e
s
s
o
f
s
ec
r
et
-
m
es
s
ag
e,
t
h
e
No
r
m
alize
d
C
r
o
s
s
-
C
o
r
r
elatio
n
(
NC
)
an
d
Si
m
ila
r
it
y
R
atio
(
S
R
)
.
B
o
th
o
f
th
ese
m
etr
ics ar
e
d
escr
ib
ed
in
th
e
n
e
x
t sect
io
n
s
,
r
esp
ec
tiv
el
y
.
T
h
e
r
o
b
u
s
tn
e
s
s
o
f
th
e
s
ec
r
et
-
m
ess
a
g
e
ca
n
b
e
ev
al
u
ated
u
s
in
g
th
e
No
r
m
alize
d
C
r
o
s
s
-
C
o
r
r
elatio
n
(
NC
)
b
et
w
ee
n
th
e
o
r
ig
in
al
s
ec
r
et
-
m
e
s
s
a
g
e
an
d
t
h
e
ex
tr
ac
ted
s
ec
r
et
-
m
es
s
ag
e.
T
h
e
NC
i
s
ev
alu
ated
b
y
v
ar
y
i
n
g
th
e
s
tr
e
n
g
t
h
o
f
ea
c
h
d
eg
r
ad
ati
o
n
p
r
o
ce
s
s
w
h
ic
h
is
d
ef
i
n
ed
as
:
NC
=
P
x
Q
y
P
x
Q
y
y
x
M
y
x
M
y
x
M
1
1
2
1
1
'
)]
,
(
[
)]
,
(
).
,
(
[
(
2
)
w
h
er
e,
M
=
s
ec
r
et
-
m
es
s
ag
e
; M
’
=
ex
tr
ac
ted
s
ec
r
et
-
m
ess
a
g
e
I
n
o
r
d
er
to
test
t
h
e
r
o
b
u
s
t
n
es
s
,
th
e
Si
m
ilar
it
y
R
atio
(
S
R
)
ca
n
b
e
ca
lc
u
lated
b
et
w
ee
n
o
r
ig
i
n
al
a
n
d
w
ater
m
ar
k
ed
i
m
ag
e
s
.
I
t c
an
b
e
ac
h
iev
ed
b
y
u
s
i
n
g
th
e
f
o
llo
w
i
n
g
eq
u
atio
n
:
SR
=
(
3
)
T
h
e
n
u
m
b
er
o
f
m
atch
i
n
g
p
ix
e
l
an
d
an
o
th
er
d
if
f
er
en
t
p
i
x
el
v
alu
es
ar
e
r
ep
r
esen
ted
b
y
S
an
d
D
r
esp
ec
tiv
el
y
.
I
f
th
e
v
al
u
e
o
f
SR
i
s
clo
s
ed
to
1
,
its
s
h
o
w
s
t
h
e
r
o
b
u
s
tn
e
s
s
o
f
w
a
ter
m
ar
k
i
s
b
etter
an
d
p
r
eser
v
ed
[
2
2
]
.
A
cc
o
r
d
in
g
to
T
s
ai
et
al.
[
2
3
]
NC
h
a
s
b
ee
n
co
m
m
o
n
l
y
u
s
e
d
as
a
m
e
tr
ic
to
ev
al
u
ate
th
e
d
eg
r
ee
o
f
s
i
m
ilar
it
y
b
et
w
ee
n
t
w
o
co
m
p
ar
ed
i
m
a
g
es
b
ec
a
u
s
e
o
f
th
e
s
e
t
w
o
ad
v
a
n
ta
g
es.
I
t
is
les
s
s
en
s
iti
v
e
to
lin
ea
r
ch
an
g
es
in
t
h
e
a
m
p
lit
u
d
e
o
f
ill
u
m
in
at
io
n
i
n
t
h
e
t
w
o
co
m
p
ar
e
d
i
m
ag
e
s
t
h
at
m
a
k
e
s
m
ea
s
u
r
e
m
en
t
m
o
r
e
ac
cu
r
at
e
ii)
I
t
is
co
n
f
i
n
ed
in
t
h
e
r
an
g
e
b
et
w
ee
n
-
1
an
d
1
th
a
t
t
h
e
s
ett
in
g
o
f
th
r
e
s
h
o
ld
v
al
u
e
i
s
m
u
c
h
ea
s
ier
b
ec
au
s
e
i
t
in
v
o
l
v
es
t
h
e
ca
lc
u
latio
n
o
f
a
s
m
aller
n
u
m
b
er
.
I
t
is
w
el
l
k
n
o
w
n
t
h
at
NC
ca
n
b
e
ef
f
icie
n
tl
y
i
m
p
le
m
en
t
ed
i
n
th
e
tr
an
s
f
o
r
m
d
o
m
ai
n
r
at
h
er
th
a
n
s
p
atial
d
o
m
ain
[
2
4
]
.
T
h
e
NC
v
alu
e
ca
n
b
e
ea
s
i
l
y
e
v
al
u
ated
b
y
u
s
i
n
g
N
C
ap
p
licatio
n
as sh
o
w
n
i
n
Fi
g
u
r
e
2
as f
o
llo
w
s
[
2
0
]
.
Fig
u
r
e
2
.
No
r
m
alize
d
C
r
o
s
s
-
C
o
r
r
elatio
n
T
h
er
ef
o
r
e,
P
SNR
an
d
NC
h
av
e
b
ee
n
s
elec
ted
to
b
e
u
s
ed
i
n
t
h
is
r
e
s
ea
r
ch
to
m
ea
s
u
r
e
t
h
e
i
m
p
er
ce
p
tib
ilit
y
o
f
co
v
er
-
i
m
a
g
e
a
n
d
th
e
r
o
b
u
s
t
n
es
s
o
f
s
e
cr
et
-
m
e
s
s
a
g
e
r
esp
ec
ti
v
el
y
.
Fo
r
th
e
P
SN
R
,
t
h
e
I
m
ag
eJ
ap
p
licatio
n
w
ill b
e
u
s
e
d
as a
to
o
l to
m
ea
s
u
r
e
th
e
co
v
er
-
i
m
a
g
e
[
2
1
]
.
I
ts
p
o
w
er
a
n
d
f
l
ex
ib
ilit
y
allo
w
it to
b
e
u
s
ed
as
a
r
esear
c
h
to
o
l
b
y
s
cie
n
ti
s
ts
in
v
ar
io
u
s
d
is
cip
lin
es
[
2
5
]
,
in
cl
u
d
in
g
i
m
a
g
e
i
n
f
o
r
m
atio
n
h
id
i
n
g
.
Me
an
w
h
ile,
t
h
e
N
C
T
o
o
l
h
as
b
ee
n
ch
o
s
e
n
to
b
e
u
s
ed
in
o
r
d
er
to
f
i
n
d
t
h
e
N
C
v
alu
e
s
b
et
wee
n
t
h
e
o
r
ig
i
n
al
an
d
th
e
ex
tr
ac
ted
s
ec
r
et
-
m
es
s
ag
e.
I
t h
as b
ee
n
u
s
ed
b
ec
au
s
e
o
f
t
h
e
av
ailab
ilit
y
an
d
also
as a
co
n
v
en
ie
n
t
s
a
m
p
le.
T
h
e
ev
al
u
atio
n
is
b
ased
o
n
th
e
v
al
u
e
b
et
w
ee
n
th
e
Ste
g
SVM
m
o
d
el
w
it
h
th
e
ex
is
ti
n
g
SVM
class
i
f
icatio
n
m
o
d
els
o
r
w
it
h
th
e
L
SB
s
u
b
s
tit
u
tio
n
s
tech
n
iq
u
es,
o
r
w
it
h
k
i
n
d
s
o
f
i
m
ag
e
p
r
o
ce
s
s
i
n
g
attac
k
s
.
A
s
m
en
tio
n
ed
ea
r
lier
,
im
p
er
ce
p
t
ib
ilit
y
an
d
r
o
b
u
s
t
n
ess
ar
e
th
e
t
w
o
m
o
s
t
i
m
p
o
r
ta
n
t
cr
iter
ia
[
2
4
,
2
5
,
1
6
]
in
ev
alu
a
tin
g
a
n
i
m
a
g
e
s
te
g
an
o
g
r
ap
h
y
.
T
h
e
i
m
p
er
ce
p
tib
ilit
y
an
d
r
o
b
u
s
t
n
es
s
o
f
Ste
g
S
V
M
is
b
ased
o
n
t
h
e
co
m
p
ar
is
o
n
b
et
w
ee
n
f
ir
s
t,
t
h
e
p
r
o
p
o
s
ed
an
d
ex
is
tin
g
m
o
d
e
l
an
d
s
ec
o
n
d
,
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
233
–
2
3
8
236
o
th
er
m
o
d
els
o
f
L
SB
s
u
b
s
t
it
u
tio
n
.
Fo
r
b
o
th
o
f
th
e
s
e
ex
p
e
r
i
m
en
ts
,
th
e
s
ec
r
et
-
m
es
s
ag
e
s
ize
h
as
b
ee
n
s
et
to
1
0
2
4
b
its
w
h
ile
t
h
e
p
en
alt
y
v
a
l
u
e
o
f
p
ar
a
m
eter
C
a
n
d
g
a
m
m
a
is
s
et
to
3
0
an
d
0
.
5
r
esp
ec
tiv
el
y
.
3.
RE
SUL
T
A
ND
DI
SCUS
SI
O
N
T
h
e
r
esu
lt
o
f
P
SNR
b
y
co
m
p
ar
in
g
t
w
o
t
y
p
es
o
f
L
SB
tech
n
iq
u
es:
Sh
i
f
ted
L
SB
an
d
D
ir
ec
t
L
SB
Su
b
s
ti
tu
t
io
n
is
s
h
o
w
n
i
n
T
ab
le
1
.
Sh
if
ted
L
SB
is
ap
p
lied
w
it
h
th
e
u
s
a
g
e
o
f
Ste
g
SV
M
w
h
ile
Dir
ec
t
L
SB
Su
b
s
ti
tu
t
io
n
tec
h
n
iq
u
e
is
r
ep
r
esen
ted
b
y
u
s
i
n
g
an
o
t
h
er
to
o
l th
at
is
S
teg
aM
a
g
e.
T
ab
le
1
.
P
SNR
o
f
d
if
f
er
en
t
L
S
B
s
u
b
s
tit
u
tio
n
Ty
p
e
s o
f
c
o
v
e
r
-
i
mag
e
s
P
S
N
R
S
h
i
f
t
e
d
L
S
B
(
S
t
e
g
S
V
M
)
D
i
r
e
c
t
L
S
B
S
u
b
s
t
i
t
u
t
i
o
n
(
S
t
e
g
a
M
a
g
e
)
L
e
n
a
4
9
.
8
6
3
2
.
7
6
B
a
b
o
o
n
4
9
.
3
3
3
1
.
4
5
U
i
t
m
4
8
.
8
9
2
9
.
0
1
C
l
o
c
k
4
7
.
6
8
2
8
.
9
1
A
cc
o
r
d
in
g
to
T
ab
le
1
,
it
clea
r
l
y
ill
u
s
tr
ates
t
h
e
u
s
a
g
e
o
f
S
h
if
ted
L
SB
tech
n
iq
u
e
r
es
u
lted
in
h
a
v
i
n
g
m
u
c
h
h
ig
h
er
P
SNR
f
o
r
all
t
y
p
es
o
f
co
v
er
-
i
m
a
g
e.
T
h
e
v
alu
e
f
o
r
all
P
SNR
f
o
r
Sh
i
f
ted
L
SB
tech
n
iq
u
e
r
ea
ch
ed
4
0
an
d
ab
o
v
e
co
m
p
ar
ed
to
an
o
th
er
tech
n
iq
u
e.
T
h
e
h
ig
h
e
s
t
P
SNR
is
4
9
.
8
6
th
r
o
u
g
h
L
e
n
a
co
v
er
-
i
m
ag
e
an
d
t
h
e
lo
w
es
t
is
4
7
.
6
8
f
o
r
C
lo
ck
co
v
er
-
i
m
a
g
e.
Me
an
w
h
ile,
f
o
r
Dir
ec
t
L
SB
Su
b
s
ti
tu
t
io
n
tech
n
iq
u
e,
th
e
h
i
g
h
est
P
SN
R
v
alu
e
i
s
o
n
l
y
at
3
2
.
7
6
.
an
d
th
e
lo
w
est
i
s
at
2
8
.
9
1
f
o
r
C
lo
ck
co
v
er
-
i
m
ag
e.
L
SB
S
h
i
f
ted
tech
n
iq
u
e
s
h
o
w
s
t
h
at,
it
is
n
o
t
o
n
l
y
s
u
cc
ee
d
ed
in
e
m
b
e
d
d
in
g
r
an
d
o
m
iz
in
g
i
m
p
le
m
e
n
t
atio
n
,
b
u
t
it
also
m
a
k
es
s
u
r
e
t
h
at
t
h
e
e
m
b
ed
d
in
g
lo
ca
tio
n
is
s
ec
u
r
ed
co
m
p
ar
ed
to
d
ir
ec
t
L
SB
s
u
b
s
tit
u
tio
n
.
As
f
o
r
r
o
b
u
s
tn
e
s
s
,
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
w
il
l
b
e
ev
alu
a
ted
b
ased
o
n
th
e
co
m
p
ar
is
o
n
o
f
th
e
v
al
u
e
o
f
n
o
r
m
al
ized
cr
o
s
s
-
co
r
r
elatio
n
(
NC
)
f
o
r
ex
tr
ac
ted
s
ec
r
et
-
m
es
s
ag
e
b
et
w
ee
n
f
ir
s
t,
th
e
p
r
o
p
o
s
ed
an
d
ex
is
ti
n
g
m
o
d
el
s
.
Seco
n
d
is
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
an
d
o
th
er
m
o
d
el
s
o
f
L
SB
s
u
b
s
tit
u
tio
n
.
T
h
ir
d
is
th
e
co
m
p
ar
is
o
n
b
et
wee
n
th
e
r
es
u
lt
s
o
f
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
at
tack
s
o
n
t
h
e
p
r
o
p
o
s
ed
an
d
ex
i
s
ti
n
g
m
o
d
el
s
.
A
s
f
o
r
t
h
ese
t
h
r
ee
e
x
p
er
im
en
ts
,
t
h
e
s
ize
f
o
r
th
e
s
ec
r
e
t
m
e
s
s
a
g
e
h
as
b
ee
n
j
u
s
tif
ied
to
1
0
2
4
b
its
w
h
i
le
th
e
v
alu
e
f
o
r
p
en
alt
y
p
ar
a
m
e
ter
C
an
d
g
a
m
m
a
i
s
3
0
an
d
0
.
5
r
e
s
p
ec
tiv
el
y
.
T
h
en
,
in
T
ab
le
2
th
e
s
h
i
f
ted
L
SB
tec
h
n
iq
u
e
r
ec
o
r
d
ed
h
ig
h
er
N
C
v
a
lu
e
as
r
ep
r
esen
tati
v
e
i
n
r
o
b
u
s
tn
es
s
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
an
d
o
th
er
m
o
d
el
o
f
L
SB
.
T
ab
le
2
.
NC
o
f
d
if
f
er
en
t
L
SB
s
u
b
s
t
itu
t
io
n
m
o
d
el
s
Ty
p
e
s o
f
c
o
v
e
r
-
i
mag
e
s
P
S
N
R
S
h
i
f
t
e
d
L
S
B
(
S
t
e
g
S
V
M
)
D
i
r
e
c
t
L
S
B
S
u
b
s
t
i
t
u
t
i
o
n
(
S
t
e
g
a
M
a
g
e
)
L
e
n
a
1
.
0
0
0
.
9
2
B
a
b
o
o
n
1
.
0
0
0
.
9
5
U
i
t
m
0
.
9
9
0
.
8
7
C
l
o
c
k
0
.
9
8
0
.
8
4
B
ased
o
n
T
ab
le
2
,
th
e
co
m
p
a
r
is
o
n
p
r
o
p
o
s
ed
m
o
d
el
w
ith
D
ir
ec
t
L
SB
Su
b
s
tit
u
tio
n
T
ec
h
n
i
q
u
e
w
it
h
t
h
e
v
al
u
e
r
an
g
e
f
r
o
m
0
.
9
8
to
1
.
0
.
Sim
u
l
tan
eo
u
l
y
,
Dir
ec
t
L
SB
S
u
b
s
tit
u
tio
n
T
ec
h
n
iq
u
e
r
ec
o
r
d
ed
NC
v
alu
e
th
at
i
s
m
u
c
h
lo
w
er
,
b
ein
g
t
h
e
h
i
g
h
e
s
t
v
al
u
e
is
0
.
9
5
an
d
th
e
lo
w
est
i
s
0
.
8
4
.
L
e
n
a
an
d
B
ab
o
o
n
C
o
v
er
-
i
m
a
g
e
r
ec
o
r
d
ed
h
ig
h
er
NC
v
alu
e
f
o
r
b
o
th
tec
h
n
iq
u
es
co
m
p
ar
ed
to
o
th
er
co
v
er
-
i
m
ag
e.
I
t
is
f
o
u
n
d
t
h
at
t
h
e
N
C
v
alu
e
is
m
u
c
h
h
ig
h
er
i
n
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
p
r
o
p
o
s
ed
m
o
d
el,
th
e
ex
i
s
ti
n
g
m
o
d
els
an
d
d
if
f
er
en
t
L
SB
s
u
b
s
tit
u
tio
n
m
eth
o
d
.
I
n
T
ab
le
3
,
af
ter
a
f
e
w
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
attac
k
s
,
th
e
e
x
tr
ac
ted
s
ec
r
et
-
m
e
s
s
a
g
e
is
v
al
u
ed
u
s
i
n
g
NC
.
T
ab
le
3
.
NC
o
f
d
if
f
er
en
t
k
i
n
d
s
o
f
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
at
tack
s
I
mag
e
P
r
o
c
e
ssi
n
g
A
t
t
a
c
k
s
C
o
mp
a
r
i
so
n
o
f
M
e
t
h
o
d
s
B
l
i
n
d
S
V
M
F
S
V
M
S
t
e
g
S
V
M
L
o
w
-
P
a
ss
F
i
l
t
e
r
i
n
g
0
.
9
5
0
.
9
7
0
.
9
8
S
a
l
t
&
P
e
p
p
e
r
N
o
i
se
0
.
7
2
0
.
9
7
0
.
9
8
JP
EG
A
t
t
a
c
k
0
.
9
5
0
.
9
6
0
.
9
6
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4752
Th
e
E
mb
ed
d
in
g
P
erfo
r
ma
n
ce
o
f S
teg
S
V
M
Mo
d
el
in
I
ma
g
e
…
(
Ha
n
iz
a
n
S
h
a
ke
r
Hu
s
s
a
in
)
237
B
ased
o
n
T
ab
le
3
,
Steg
SVM
m
o
d
el
s
h
o
w
ed
N
C
v
al
u
es
t
h
a
t
ar
e
h
i
g
h
f
o
r
all
t
y
p
es
o
f
i
m
ag
e
s
te
g
a
n
o
g
r
ap
h
y
attac
k
s
.
T
h
e
h
ig
h
es
t
NC
i
s
f
o
r
lo
w
-
p
ass
f
ilter
i
n
g
an
d
s
a
lt
-
p
ep
p
er
n
o
is
e,
w
h
ich
is
0
.
9
8
f
o
r
b
o
th
.
As
f
o
r
J
P
E
G
attac
k
,
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
r
ec
o
r
d
ed
NC
v
al
u
e
eq
u
al
s
to
0
.
9
6
.
Me
an
w
h
ile,
f
o
r
FS
V
M,
th
e
NC
v
al
u
e
i
s
b
et
w
ee
n
0
.
9
7
u
n
til 0
.
9
6
an
d
as f
o
r
B
lin
d
-
SV
M,
th
e
N
C
v
al
u
e
is
b
et
w
ee
n
0
.
7
2
-
0
.
9
5
.
T
h
e
N
C
v
al
u
e
is
a
f
f
ec
ted
af
ter
i
m
ag
e
p
r
o
ce
s
s
i
n
g
attac
k
s
as
it
r
ec
o
r
d
ed
m
u
c
h
h
i
g
h
er
v
alu
e
co
m
p
ar
ed
to
t
w
o
o
th
e
r
m
eth
o
d
s
,
n
a
m
el
y
B
lin
d
SVM
an
d
FS
VM
.
4
.
CO
NCLUS
I
O
N
T
h
is
p
ap
er
p
er
f
o
r
m
ed
th
e
ev
al
u
atio
n
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
Steg
SVM
m
o
d
el
co
m
p
ar
ed
to
th
e
o
th
er
m
o
d
el
t
h
r
o
u
g
h
i
m
p
er
ce
p
tib
ilit
y
an
d
r
o
b
u
s
t
n
e
s
s
o
f
th
e
tec
h
n
i
q
u
e.
Steg
SVM
m
o
d
el
w
er
e
ac
ce
p
tab
le
in
w
h
ich
i
t
s
h
o
w
s
a
h
i
g
h
er
q
u
alit
y
s
te
g
a
n
o
g
r
ap
h
y
,
th
u
s
en
h
a
n
cin
g
th
e
p
er
f
o
r
m
a
n
ce
o
f
ex
is
t
in
g
wo
r
k
s
.
I
n
ex
tr
ac
tin
g
p
r
o
ce
s
s
,
b
y
ex
p
lo
iti
n
g
t
h
e
S
VM
lear
n
in
g
ab
ilit
y
,
th
e
r
ig
h
t
s
ec
r
et
-
b
its
ca
n
b
e
r
ec
o
v
er
ed
.
B
ased
o
n
ea
ch
ex
p
er
i
m
e
n
t,
it
s
h
o
w
s
Steg
SV
M
m
o
d
el
h
as a
b
etter
p
er
f
o
r
m
an
c
e
t
h
an
t
h
e
p
r
ev
io
u
s
m
o
d
els
.
Fo
r
f
u
r
th
er
w
o
r
k
,
it
is
s
u
g
g
ested
t
h
at
t
h
e
o
th
er
i
m
a
g
e
d
o
m
ain
s
t
h
r
o
u
g
h
o
th
er
i
n
tel
lig
e
n
t
m
e
th
o
d
s
s
h
o
u
ld
b
e
in
v
e
s
tig
a
ted
.
ACK
NO
WL
E
D
G
E
M
E
NT
T
h
is
s
tu
d
y
w
o
u
ld
li
k
e
to
th
a
n
k
th
e
Mo
HE
Ma
la
y
s
ia
f
o
r
g
r
an
t
f
u
n
d
u
n
d
er
th
e
F
R
GS
w
it
h
S_
O
C
o
d
e
-
1
3
5
7
6
,
an
d
R
I
MC o
f
Un
i
v
er
s
i
ti Uta
r
a
Ma
la
y
s
ia,
Ked
ah
.
Ref
er
ence
s
[1
]
C.
C.
C
h
a
n
g
,
T
.
S
.
C
h
e
n
a
n
d
L
.
Z.
C
h
u
n
g
.
2
0
0
2
.
A
S
teg
a
n
o
g
ra
p
h
ic
M
e
th
o
d
B
a
se
d
U
p
o
n
J
PE
G
a
n
d
Qu
a
n
t
iza
ti
o
n
T
a
b
le M
o
d
if
ic
a
ti
o
n
.
I
n
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s
,
2
0
0
2
;
1
2
3
-
1
3
8
[2
]
A
.
Ch
e
d
d
a
d
,
J.
Co
n
d
e
ll
,
K.
Cu
rr
a
n
,
P
.
M
.
Ke
v
it
t.
Rev
iew:
Dig
it
a
l
Ima
g
e
S
te
g
a
n
o
g
ra
p
h
y
:
S
u
rv
e
y
a
n
d
An
a
lys
is
o
f
Cu
rr
e
n
t
M
e
th
o
d
s
.
Jo
u
rn
a
l
S
ig
n
a
l
P
r
o
c
e
ss
in
g
,
2
0
1
0
;
7
2
7
-
7
5
2
.
[3
]
Y.
G
.
F
u
,
R.
M
.
S
h
e
n
,
L
.
P
.
S
h
e
n
,
a
n
d
X
.
S
.
L
e
i.
2
0
0
5
.
Relia
b
le
In
fo
rm
a
t
i
o
n
Hid
i
n
g
Ba
se
d
o
n
S
u
p
p
o
rt
Vec
to
r
M
a
c
h
in
e
.
I
n
tern
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
In
f
o
rm
a
ti
c
a
.
2
0
0
5
;
3
3
3
-
3
4
6
.
[4
]
S.
S
h
e
n
,
H.
Z
h
a
n
g
,
D.
F
e
n
g
,
Z.
Ca
o
,
J.
Hu
a
n
g
.
S
u
rv
e
y
o
f
In
f
o
r
m
a
ti
o
n
S
e
c
u
rit
y
.
S
c
ien
c
e
in
Ch
in
a
S
e
rie
s
F:
In
fo
rm
a
t
io
n
S
c
ien
c
e
s
,
2
0
0
7
;
2
7
3
-
2
9
8
.
[5
]
H.
W
a
n
g
a
n
d
S
.
W
a
n
g
,
S
.
2
0
0
4
.
C
y
b
e
r
W
a
r
f
a
re
:
S
teg
a
n
o
g
ra
p
h
y
v
s.
S
teg
a
n
a
ly
si
s.
Co
mm
u
n
ic
a
ti
o
n
s
o
f
t
h
e
ACM
,
7
6
-
82
.
[6
]
L
.
Bin
,
H.
Ju
n
h
u
i,
H.
Jiw
u
Q.
S
.
Yu
n
.
A
S
u
rv
e
y
o
n
Im
a
g
e
S
teg
a
n
o
g
ra
p
h
y
a
n
d
S
teg
a
n
a
l
y
sis.
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
ti
o
n
Hid
in
g
a
n
d
M
u
lt
ime
d
i
a
S
ig
n
a
l
Pr
o
c
e
ss
in
g
,
2
0
1
1
;
1
4
2
-
1
7
2
.
[6
]
T
.
M
o
rk
e
l,
J.H.
El
o
f
f
a
n
d
M
.
S
.
Oliv
ier.
A
n
Ov
e
rv
ie
w
o
f
I
m
a
g
e
S
teg
a
n
o
g
ra
p
h
y
.
An
n
u
a
l
In
f
o
rm
a
ti
o
n
S
e
c
u
rity
S
o
u
th
Af
ric
a
Co
n
fer
e
n
c
e
.
S
a
n
d
to
n
,
S
o
u
t
h
A
f
ri
c
a
:
M
S
Oliv
ier.
2
0
0
5
[8
]
M
.
A
.
Yo
u
n
e
s
a
n
d
A
.
J
a
n
tan
.
A
Ne
w
S
teg
a
n
o
g
r
a
p
h
y
Ap
p
r
o
a
c
h
f
o
r
Ima
g
e
En
c
ry
p
ti
o
n
Exc
h
a
n
g
e
b
y
Us
in
g
th
e
L
e
a
st
S
ig
n
if
ica
n
t
B
it
I
n
se
rtio
n
.
In
ter
n
a
ti
o
n
a
l
Jo
u
rn
a
l
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
Ne
tw
o
rk
S
e
c
u
rit
y
.
2
0
0
8
;
2
4
7
-
2
5
4
.
[9
]
E.
Co
le..
Hid
in
g
in
Pl
a
in
S
i
g
h
t:
S
teg
a
n
o
g
r
a
p
h
y
a
n
d
t
h
e
Art
o
f
Co
v
e
rt
Co
mm
u
n
ica
ti
o
n
.
Ne
w
Y
o
rk
:
Jo
h
n
W
il
e
y
P
u
b
l
ish
i
n
g
In
c
.
2
0
0
3
[1
0
]
N.
S
a
th
ish
a
.
Emb
e
d
d
i
n
g
I
n
f
o
rm
a
ti
o
n
in
DCT
Co
e
ff
icie
n
ts
B
a
se
d
o
n
Ave
ra
g
e
Co
v
a
ri
a
n
c
e
.
I
n
tern
a
t
io
n
a
l
J
o
u
r
n
a
l
o
f
En
g
in
e
e
rin
g
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
.
2
0
1
1
;
3
1
8
4
-
3
1
9
4
.
[1
1
]
Z.
L
i,
K.
L
u
,
X
.
Zen
g
,
X.
P
a
n
.
2
0
1
0
.
A
Bl
i
n
d
S
teg
a
n
a
lytic
S
c
h
e
me
Ba
se
d
o
n
DCT
a
n
d
S
p
a
ti
a
l
Do
ma
in
f
o
r
J
PE
G
Ima
g
e
s.
Jo
u
rn
a
l
o
f
M
u
lt
im
e
d
ia
.
2
0
1
0
;
2
0
0
-
2
0
7
.
[1
2
]
J.
F
rid
r
ich
.
2
0
0
4
.
F
e
a
tu
re
d
-
Ba
s
e
d
S
teg
a
n
a
ly
sis
f
o
r
JP
EG
Im
a
g
e
s
a
n
d
Its
Im
p
li
c
a
ti
o
n
s
f
o
r
F
u
tu
re
De
sig
n
o
f
S
teg
a
n
o
g
ra
p
h
ic S
c
h
e
m
e
s.
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
In
f
o
rm
a
ti
o
n
Hid
in
g
.
2
0
0
4
;
6
7
-
8
1
.
[1
3
]
E.
M
a
rin
i
,
F
.
A
u
tru
ss
e
a
u
,
P
.
L
e
Ca
ll
e
t
a
n
d
P
.
Ca
m
p
isi,
P
.
2
0
0
7
.
Eva
lu
a
ti
o
n
o
f
S
t
a
n
d
a
r
d
W
a
ter
ma
rk
in
g
T
e
c
h
n
iq
u
e
s
.
El
e
c
tro
n
ic Im
a
g
in
g
,
S
e
c
u
rit
y
,
S
te
g
a
n
o
g
ra
p
h
y
,
a
n
d
W
a
ter
m
a
r
k
in
g
o
f
M
u
lt
im
e
d
ia Co
n
ten
ts
.
2
0
0
7
;
1
4
2
-
1
5
5
.
[1
4
]
N.
I.
W
u
a
n
d
M
.
S
.
Hw
a
n
g
.
Da
ta
Hid
in
g
:
Cu
rr
e
n
t
S
t
a
t
u
s a
n
d
Ke
y
Iss
u
e
s.
In
tern
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
Ne
tw
o
rk
S
e
c
u
rit
y
,
2
0
0
7
;
1
-
9.
[1
5
]
N.
Jia
n
g
.
A
No
v
e
l
A
n
a
l
y
sis M
e
th
o
d
o
f
In
f
o
rm
a
ti
o
n
Hid
i
n
g
.
In
ter
n
a
ti
o
n
a
l
C
o
n
g
re
ss
o
n
Ima
g
e
a
n
d
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
.
2
0
0
8
;
6
2
1
-
6
2
5
.
Ha
in
a
n
:
IEE
E
Co
m
p
u
ter S
o
c
iety
.
[1
6
]
A
.
A
.
G
u
tu
.
Pi
x
e
l
In
d
ica
to
r
T
e
c
h
n
iq
u
e
fo
r
RGB
Ima
g
e
S
teg
a
n
o
g
r
a
p
h
y
.
J
o
u
r
n
a
l
o
f
Em
e
r
g
in
g
Tec
h
n
o
l
o
g
ies
in
W
e
b
In
telli
g
e
n
c
e
,
2
0
1
0
;
5
6
-
6
4
.
[1
7
]
B.
Ka
ip
a
a
n
d
S
.
A
.
Ro
b
il
a
.
2
0
1
0
.
S
tatisti
c
a
l
S
teg
a
n
a
l
y
is
o
f
I
m
a
g
e
s
Us
in
g
Op
e
n
S
o
u
rc
e
S
o
f
tw
a
r
e
.
In
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Ap
p
li
c
a
ti
o
n
s a
n
d
T
e
c
h
n
o
l
o
g
y
.
2
0
1
0
;
1
-
5
.
I
EE
E
C
o
m
p
u
ter S
o
c
iety
.
[1
8
]
F.
M
e
n
g
,
H.
P
e
n
g
,
Z.
P
e
i,
J.
W
a
n
g
.
A
No
v
e
l
Bli
n
d
Im
a
g
e
W
a
ter
m
a
rk
in
g
S
c
h
e
m
e
B
a
se
d
o
n
S
u
p
p
o
rt
V
e
c
to
r
M
a
c
h
in
e
in
DCT
Do
m
a
in
.
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ta
ti
o
n
a
l
In
telli
g
e
n
c
e
a
n
d
S
e
c
u
rity
.
2
0
0
8
;
1
6
-
2
0
.
[1
9
]
C.
S
c
h
n
e
id
e
r,
W
.
Ra
sb
a
n
d
a
n
d
K.
El
ice
iri
.
2
0
1
2
.
NIH
Ima
g
e
to
Ima
g
e
J
:
2
5
y
e
a
rs
o
f
ima
g
e
a
n
a
lys
is
.
Na
tu
re
M
e
th
o
d
s
.
2
0
1
2
;
6
7
1
–
6
7
5
.
[2
0
]
C.
W
.
Hs
u
,
C.
C.
Ch
a
n
g
a
n
d
C.
J.
L
in
.
2
0
0
9
.
A
P
ra
c
ti
c
a
l
Gu
i
d
e
to
S
u
p
p
o
rt
Vec
to
r
Cla
ss
if
ica
ti
o
n
.
Bio
in
f
o
rm
a
ti
c
s
.
2
0
0
9
;
1
-
1
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4752
I
n
d
o
n
esia
n
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l
.
1
2
,
No
.
1
,
Octo
b
er
201
8
:
233
–
2
3
8
238
[2
1
]
H.
H.
T
sa
i,
H.
C.
Tse
n
g
a
n
d
Y.
S
.
L
a
i.
Ro
b
u
st
L
o
ss
les
s
Ima
g
e
W
a
t
e
rm
a
rk
in
g
Ba
se
d
o
n
A
-
T
rimm
e
d
M
e
a
n
Al
g
o
rith
m
a
n
d
S
u
p
p
o
rt
Vec
to
r M
a
c
h
i
n
e
.
T
h
e
Jo
u
r
n
a
l
o
f
S
y
ste
m
s an
d
S
o
f
tw
a
re
20
1
0
;
1
0
1
5
–
1
0
2
8
.
[2
2
]
J.
P
.
L
e
w
is.
1
9
9
8
.
i
d
io
m.
Re
tr
iev
e
d
No
v
e
m
b
e
r
1
6
,
2
0
1
2
,
f
ro
m
V
isi
o
n
I
n
terf
a
c
e
:
h
tt
p
:
//
ww
w
.
id
io
m
.
c
o
m
/~
z
il
la/P
a
p
e
rs/v
isio
n
In
terf
a
c
e
/
.
[2
3
]
R.
Di
n
,
A
.
S
a
m
su
d
in
.
In
t
e
leg
e
n
t
ste
g
a
n
a
lytic
sy
ste
m:
Ap
p
ica
ti
o
n
o
n
n
a
t
u
ra
l
l
a
n
u
g
a
e
e
n
v
iro
n
me
n
t.
W
S
EA
S
tran
sa
c
ti
o
n
o
n
S
y
ste
m
a
n
d
c
o
n
tro
l
.
2
0
0
9
;
4
(
8
):
3
7
9
-
3
8
8
.
[2
4
]
R.
Din
,
Z.
C
.
A
n
i,
A
.
S
a
m
su
d
in
.
A
F
o
rm
u
l
a
ti
o
n
o
f
c
o
n
d
it
io
n
a
l
sta
tes
o
n
ste
g
a
n
a
y
sis
a
p
p
ro
a
c
h
.
W
S
E
A
S
tran
sa
c
ti
o
n
o
n
m
a
th
e
m
a
ti
c
.
2
0
1
2
;
1
1
(
3
):
1
7
3
-
1
8
2
.
[2
5
]
R.
Din
,
A
.
S
a
m
su
d
in
,
T
.
Z.
T
.
M
u
d
a
,
A
.
Am
p
h
a
w
a
n
.
M
.
N.
O
m
a
r.
F
it
n
e
ss
v
a
lu
e
b
a
se
d
e
v
a
lu
a
ti
o
n
a
lg
o
ri
th
m
a
p
p
ro
a
c
h
f
o
r
tex
t
ste
g
a
n
a
l
y
sis
m
o
d
e
l.
In
ter
n
a
ti
o
n
a
l
jo
u
rn
a
l
o
f
ma
t
h
e
ma
ti
c
m
o
d
e
ls
a
n
d
me
th
o
d
s
in
a
p
p
l
ied
sc
ien
c
e
.
2
0
1
3
;
7
(
5
):
55
1
-
5
5
8
.
[2
6
]
Ha
n
iza
n
S
h
a
k
e
r
Hu
ss
a
in
,
Ro
sh
id
i
Din
,
R
u
sd
i
I
d
ru
s.
P
re
se
rv
e
I
m
p
e
rc
e
p
ti
b
il
it
y
a
n
d
Ro
b
u
st
n
e
ss
P
e
rf
o
rm
a
n
c
e
o
n
S
teg
a
n
o
g
ra
p
h
y
T
e
c
h
n
iq
u
e
b
a
se
d
o
n
S
teg
a
S
VM
-
S
h
if
ted
L
BS
M
o
d
e
l,
J
o
u
rn
a
l
o
f
Ph
y
sic
s:
Co
n
fer
e
n
c
e
S
e
rie
s
,
2
0
1
8
;
1
0
1
8
:
1
–
8.
Evaluation Warning : The document was created with Spire.PDF for Python.