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.
9
,
No
.
5
,
Octo
b
e
r
2
0
1
9
,
p
p
.
3
4
7
4
~
3
4
7
9
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
9
i
5
.
p
p
3
4
7
4
-
3479
3474
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
/
I
JE
C
E
An ef
ficien
t
co
m
p
utatio
na
l appro
a
ch t
o
bala
nce
the
t
ra
de
-
o
ff
betw
een i
m
a
g
e f
o
rensics
and p
erce
ptual i
m
a
g
e quali
ty
Sh
a
s
hi
dh
a
r
T
M
1
,
K
B
Ra
m
e
s
h
2
1
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
a
n
d
E
n
g
in
e
e
rin
g
,
A
M
C
En
g
in
e
e
rin
g
Co
ll
e
g
e
,
In
d
ia
2
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
I
n
stru
m
e
n
tatio
n
E
n
g
in
e
e
rin
g
,
R
VCE,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
7
,
2
0
1
9
R
ev
i
s
ed
A
p
r
9
,
2
0
1
9
A
cc
ep
ted
A
p
r
1
7
,
2
0
1
9
T
h
e
in
c
re
a
sin
g
tren
d
s
o
f
im
a
g
e
p
ro
c
e
ss
in
g
a
p
p
li
c
a
ti
o
n
s
p
lay
a
v
e
r
y
c
ru
c
ial
ro
le
in
th
e
m
o
d
e
rn
-
d
a
y
in
f
o
rm
a
ti
o
n
p
r
o
p
a
g
a
ti
o
n
w
it
h
th
e
e
a
se
o
f
c
o
st
e
ffe
c
ti
v
e
n
e
ss
.
A
s
i
m
a
g
e
tran
s
m
issio
n
o
r
b
ro
a
d
c
a
sti
n
g
is
t
h
e
sim
p
les
t
f
o
rm
c
o
m
m
u
n
ica
ti
o
n
w
h
ich
d
e
term
in
e
s
e
a
s
y
,
f
a
ste
st
a
n
d
e
ff
e
c
ti
v
e
w
a
y
o
f
n
e
tw
o
r
k
re
so
u
rc
e
u
ti
li
z
a
ti
o
n
,
t
h
e
re
b
y
sin
c
e
p
a
st
o
n
e
d
e
c
a
d
e
it
h
a
s
g
a
in
e
d
sig
n
if
ica
n
t
a
tt
e
n
ti
o
n
a
m
o
n
g
v
a
rio
u
s
re
se
a
r
c
h
c
o
m
m
u
n
it
ies
.
A
s
m
o
st
o
f
th
e
im
a
g
e
a
tt
rib
u
tes
o
f
ten
c
o
n
tain
s
v
isu
a
l
e
n
ti
ti
e
s
c
o
rre
sp
o
n
d
in
g
t
o
a
n
y
in
d
iv
id
u
a
l,
h
e
n
c
e
,
e
x
p
lo
ra
ti
o
n
a
n
d
f
o
rg
in
g
o
f
su
c
h
a
tt
rib
u
tes
w
it
h
m
a
li
c
io
u
s
in
ten
ti
o
n
o
f
ten
lea
d
s
to
so
c
ial
a
n
d
p
e
rso
n
a
l
li
f
e
v
io
latio
n
a
n
d
a
lso
c
a
u
se
s
in
tellec
tu
a
l
p
ro
p
e
rty
ri
g
h
t
v
io
latio
n
w
h
e
n
so
c
ial
m
e
d
ia,
m
a
tri
m
o
n
ial
a
n
d
b
u
si
n
e
ss
a
p
p
li
c
a
ti
o
n
s a
re
c
o
n
c
e
rn
e
d
.
A
lt
h
o
u
g
h
a
n
e
x
ten
siv
e
re
se
a
r
c
h
e
ff
o
rt
e
n
d
e
a
v
o
re
d
p
e
rtain
in
g
t
o
im
a
g
e
f
o
re
n
sic
s
in
th
e
p
a
st,
b
u
t
e
x
isti
n
g
tec
h
n
i
q
u
e
s
lac
k
e
ffe
c
ti
v
e
n
e
ss
to
w
a
rd
s
m
a
in
tain
in
g
e
q
u
il
i
b
ri
u
m
in
b
e
tw
e
e
n
b
o
th
im
a
g
e
f
o
re
n
sic
s
a
n
d
im
a
g
e
q
u
a
li
t
y
a
ss
e
ss
m
e
n
t
p
e
rf
o
r
m
a
n
c
e
s
f
ro
m
c
o
m
p
u
tatio
n
a
l
v
ie
w
p
o
in
t.
A
d
d
re
ss
in
g
th
is
li
m
it
a
ti
o
n
a
ss
o
c
iate
d
w
it
h
th
e
e
x
isti
n
g
s
y
ste
m
,
th
is
p
r
o
p
o
se
d
stu
d
y
h
a
s
c
o
m
e
u
p
w
it
h
a
n
o
v
e
l
so
lu
ti
o
n
w
h
ich
a
c
h
iev
e
s
h
ig
h
e
r
d
e
g
re
e
o
f
i
m
a
g
e
f
o
re
n
sic
s
w
it
h
o
u
t
c
o
m
p
ro
m
isin
g
th
e
v
isu
a
l
p
e
rc
e
p
ti
o
n
o
f
a
n
im
a
g
e
.
T
h
e
stu
d
y
f
o
r
m
u
late
s
a
n
in
te
ll
ig
e
n
t
e
m
p
iri
c
a
l
f
ra
m
e
wo
rk
w
h
ich
d
e
term
in
e
s
c
o
st
-
e
ff
e
c
ti
v
e
a
u
th
e
n
ti
c
a
ti
o
n
o
f
a
n
im
a
g
e
o
b
jec
t
f
ro
m
b
o
th
c
o
m
p
lex
it
y
a
n
d
q
u
a
li
ty
v
ie
w
p
o
in
t.
F
in
a
ll
y
,
th
e
stu
d
y
a
lso
p
re
se
n
ted
a
n
u
m
e
rica
l
si
m
u
latio
n
o
u
tco
m
e
to
e
n
su
re
t
h
e
p
e
rf
o
rm
a
n
c
e
e
ff
icie
n
c
y
o
f
th
e
s
y
ste
m
.
K
ey
w
o
r
d
s
:
Dig
ital
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
I
m
ag
e
I
m
ag
e
f
o
r
en
s
ic
s
I
m
ag
e
p
er
ce
p
tu
al
q
u
al
it
y
Un
s
u
p
er
v
is
ed
l
ea
r
n
in
g
Co
p
y
rig
h
t
©
2
0
1
9
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
:
Sh
as
h
id
h
ar
T
M,
R
esear
ch
Sch
o
lar
,
Dep
ar
t
m
e
n
t
o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
ic
atio
n
&
E
n
g
in
ee
r
i
n
g
,
A
M
C
E
n
g
i
n
ee
r
in
g
C
o
lle
g
e,
B
en
g
al
u
r
u
,
I
n
d
ia
.
E
m
ail: s
h
a
s
h
id
h
ar
t
m
2
0
1
4
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
is
er
a
o
f
v
ar
io
u
s
s
o
cial
m
ed
ia
ap
p
licatio
n
s
s
u
ch
a
s
Fa
ce
b
o
o
k
,
T
w
itter
etc.
alo
n
g
w
i
th
d
i
f
f
er
e
n
t
clo
u
d
b
ased
m
atr
i
m
o
n
ia
l
an
d
b
u
s
in
es
s
ap
p
licatio
n
s
,
t
h
er
e
is
an
in
cr
ea
s
i
n
g
d
e
m
a
n
d
f
o
r
i
m
ag
e
attr
ib
u
te
ex
ch
a
n
g
e.
I
t
b
asicall
y
r
esu
l
ts
in
a
h
i
g
h
er
d
eg
r
ee
o
f
v
u
ln
er
a
b
ilit
y
w
h
er
e
i
m
ag
e
ca
n
b
e
m
a
licio
u
s
l
y
ta
m
p
er
ed
u
s
i
n
g
an
ed
itin
g
to
o
l
[
1
-
3]
.
T
h
ese
t
y
p
e
s
o
f
to
o
ls
ar
e
m
o
s
t
l
y
u
s
e
to
m
a
n
ip
u
late
th
e
i
m
ag
e
co
n
ten
t
in
a
w
a
y
w
h
er
e
v
i
s
u
al
i
n
ter
p
r
etatio
n
o
f
s
u
b
j
ec
ts
p
er
tain
i
n
g
to
th
at
p
a
r
ticu
lar
i
m
ag
e
b
e
co
m
e
c
h
alle
n
g
i
n
g
f
o
r
a
v
ie
w
er
.
I
t
ca
n
b
e
s
ee
n
t
h
at
t
h
is
ar
ea
o
f
r
esear
ch
i
s
m
o
r
e
th
a
n
o
n
e
d
ec
ad
e
o
ld
,
w
h
er
e
d
ig
ita
l
i
m
a
g
e
co
n
te
n
t
p
r
i
v
ac
y
p
r
eser
v
atio
n
p
r
o
b
le
m
s
ar
e
at
t
o
p
m
o
s
t
co
n
ce
r
n
f
r
o
m
au
t
h
e
n
t
icatio
n
v
ie
w
p
o
in
t
[
4
,
5
]
.
A
lt
h
o
u
g
h
a
lar
g
e
s
et
o
f
ar
ch
iv
e
s
e
m
p
h
as
ized
to
w
ar
d
s
id
en
ti
f
icatio
n
o
f
i
m
a
g
e
f
o
r
g
er
y
o
r
ta
m
p
er
i
n
g
d
etec
tio
n
w
it
h
d
if
f
er
e
n
t
f
o
r
m
s
o
f
r
esear
ch
b
u
t
m
aj
o
r
it
y
o
f
th
e
m
d
o
n
o
t
i
m
p
o
s
e
an
y
f
u
ll
-
p
r
o
o
f
s
o
lu
tio
n
s
th
a
t
r
ep
o
r
ted
as
b
en
ch
m
ar
k
till
d
ate.
Mo
r
eo
v
er
,
ap
p
ly
i
n
g
i
m
a
g
e
f
o
r
en
s
ics
to
r
ev
ea
l
t
h
e
u
n
d
er
l
y
i
n
g
f
ac
t
o
f
te
n
lead
s
o
f
co
llate
r
al
lo
s
s
o
f
i
m
a
g
e
in
f
o
r
m
atio
n
w
h
ic
h
is
s
till
a
g
a
p
n
ee
d
to
b
e
a
d
d
r
ess
.
T
h
er
eb
y
,
in
th
i
s
liter
at
u
r
e
a
co
m
p
u
tati
o
n
al
m
ec
h
an
is
m
is
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
efficien
t c
o
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
b
a
la
n
ce
th
e
tr
a
d
e
-
o
f
f b
etw
ee
n
ima
g
e
fo
r
en
s
ics
.
..
(
S
h
a
s
h
id
h
a
r
T M)
3475
co
n
ce
p
tu
alize
d
an
d
d
ev
elo
p
ed
f
o
r
v
is
u
al
d
escr
ip
to
r
s
to
ex
tr
ac
t
R
OI
f
ea
tu
r
e
s
f
r
o
m
t
h
e
m
aj
o
r
b
lo
ck
o
b
j
ec
t,
p
r
o
b
a
b
ly
ta
k
i
n
g
o
u
t ROI
li
k
e
v
is
io
n
,
o
r
o
th
er
i
m
p
o
r
tan
t c
o
n
s
tr
u
ct
s
in
a
h
u
m
a
n
f
ac
e
w
h
i
c
h
p
lay
s
i
m
p
o
r
ta
n
t r
o
le
to
h
elp
f
o
r
en
s
ic
p
r
o
ce
s
s
a
s
t
h
ese
ar
e
th
e
ar
ea
s
w
h
ic
h
ar
e
f
o
r
g
ed
[
6
-
8
]
.
T
h
e
d
i
m
en
s
io
n
alit
y
o
f
t
h
e
i
m
ag
e
o
b
j
ec
ts
is
u
s
u
a
ll
y
v
er
y
h
i
g
h
t
h
at
r
eq
u
ir
es
s
p
litt
i
n
g
o
f
t
h
e
s
a
m
p
les.
T
h
e
o
b
j
ec
tiv
e
f
u
n
cti
o
n
is
to
m
ax
i
m
ize
th
e
class
if
ica
tio
n
ac
cu
r
ac
y
;
th
er
ef
o
r
e,
th
e
o
p
tim
ali
t
y
is
iter
a
ted
b
etw
ee
n
th
e
b
alan
ce
o
f
t
h
e
r
atio
o
f
tr
ain
in
g
v
er
s
u
s
test
i
n
g
d
ataset
to
h
an
d
le
tr
ad
e
-
o
f
f
o
f
ac
cu
r
ac
y
a
n
d
tr
ain
in
g
.
T
h
e
class
i
f
y
i
n
g
ca
p
ac
it
y
is
b
u
il
t
o
n
th
e
a
m
o
u
n
t a
n
d
f
ea
t
u
r
e
s
et,
tr
ai
n
i
n
g
o
f
t
h
e
a
m
o
u
n
t
a
n
d
f
ea
t
u
r
e
s
e
t tr
ain
in
g
o
f
t
h
e
tr
ain
i
n
g
s
a
m
p
l
e
s
et,
w
h
er
e
a
s
th
e
m
o
d
el
v
al
id
atio
n
f
o
r
its
ac
c
u
r
ac
y
is
d
o
n
e
o
n
th
e
test
d
ata.
T
h
e
co
n
v
e
n
tio
n
al
s
tati
s
tical
ap
p
r
o
ac
h
as
co
n
s
ta
n
t
to
th
e
m
ac
h
i
n
e
lear
n
i
n
g
ap
p
r
o
ac
h
is
d
ev
elo
p
ed
w
it
h
o
u
t
t
h
e
s
e
p
ar
atio
n
an
d
s
p
litt
in
g
p
r
o
ce
s
s
o
f
th
e
in
to
tr
ain
in
g
an
d
test
i
n
g
[
9
,
1
0
]
.
T
h
e
p
r
im
e
f
o
cu
s
laid
h
er
e
is
to
ac
h
ie
v
e
m
a
x
i
m
u
m
p
o
s
s
ib
le
ac
cu
r
ac
y
i
n
i
m
a
g
e
f
o
r
en
s
ic
s
o
p
er
atio
n
w
h
ile
co
m
p
r
o
m
i
s
in
g
th
e
q
u
ali
t
y
o
f
i
m
a
g
e
d
ata.
T
h
e
s
tu
d
y
al
s
o
in
co
r
p
o
r
ates
a
co
m
p
u
tatio
n
all
y
e
f
f
icie
n
t
i
m
a
g
e
f
o
r
en
s
ic
m
ec
h
an
i
s
m
a
s
s
i
s
ted
b
y
u
n
-
s
u
p
er
v
is
ed
lear
n
i
n
g
ap
p
r
o
ac
h
w
h
ic
h
d
eter
m
in
e
s
ac
cu
r
a
c
y
o
f
i
m
a
g
e
o
b
j
ec
t
class
i
f
icatio
n
a
n
d
d
etec
tio
n
.
T
h
e
co
n
s
ec
u
tiv
e
s
e
g
m
en
ts
o
f
th
i
s
p
ap
er
ar
e
o
r
g
a
n
ized
as
Sectio
n
1
.
2
w
h
ic
h
b
asicall
y
h
ig
h
li
g
h
ts
t
h
e
ex
iti
n
g
s
tate
-
of
-
t
h
e
-
a
r
t
ap
p
r
o
ac
h
es
w
h
ic
h
h
as
al
s
o
ad
d
r
ess
ed
th
e
s
i
m
ilar
p
r
o
b
lem
an
d
also
b
ased
o
n
t
h
e
i
n
v
e
s
ti
g
ati
o
n
it
id
en
tifie
s
a
n
d
ill
u
s
tr
ate
s
th
e
p
r
o
b
le
m
i
n
Sect
io
n
1
.
3
.
Sectio
n
2
b
asicall
y
h
ig
h
li
g
h
ts
t
h
e
e
m
p
ir
ical
d
esig
n
an
d
m
o
d
eli
n
g
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
llo
w
ed
b
y
e
lab
o
r
ated
d
is
cu
s
s
io
n
o
f
n
u
m
er
ical
o
u
tco
m
e
o
b
tain
ed
in
Sectio
n
3
.
Fin
al
l
y
,
Secti
o
n
4
co
n
clu
d
es
th
e
co
n
tr
ib
u
to
r
y
asp
ec
t
s
o
f
th
e
p
r
o
p
o
s
ed
r
esear
ch
w
o
r
k
.
T
h
is
s
ec
tio
n
b
asical
l
y
e
x
tr
ac
ts
th
e
u
n
d
er
l
y
i
n
g
f
ac
t
s
f
r
o
m
m
o
s
tl
y
ci
ted
co
n
v
e
n
tio
n
a
l
liter
atu
r
es
w
h
er
e
th
e
p
r
i
m
e
e
m
p
h
asize
h
as
b
ee
n
in
cl
in
ed
to
w
ar
d
s
i
m
a
g
e
f
o
r
en
s
ic
s
.
T
h
e
s
tu
d
y
o
f
Fa
n
et
a
l.
[
1
1
]
p
r
esen
ted
an
o
p
tim
izatio
n
-
o
r
ien
ted
ap
p
r
o
ac
h
w
h
ic
h
ap
p
lies
ap
p
r
o
x
im
a
tio
n
to
en
h
a
n
ce
a
m
ed
ia
n
f
il
ter
ed
im
a
g
e
q
u
alit
y
b
u
t
th
e
au
t
h
o
r
s
h
a
v
e
r
ep
o
r
ted
th
is
m
o
d
el
to
b
e
w
o
r
k
i
n
g
w
it
h
an
ti
-
f
o
r
en
s
ic
s
p
r
in
cip
les.
C
ar
v
alh
o
et
al.
[
1
2
]
ex
p
lo
r
ed
v
ar
io
u
s
tr
an
s
f
o
r
m
a
ti
o
n
-
o
r
ien
ted
p
r
i
n
cip
les
to
d
eter
m
i
n
e
i
m
a
g
e
ill
u
m
i
n
an
t
m
ap
s
a
n
d
co
m
e
u
p
w
it
h
a
n
o
v
el
f
o
r
en
s
ic
tec
h
n
iq
u
e
wh
ich
ap
p
lies
s
ta
tis
tica
l
d
is
tr
i
b
u
tio
n
p
r
o
p
er
ties
to
lo
ca
te
th
e
f
o
r
g
ed
r
eg
io
n
.
T
h
e
au
th
o
r
s
h
a
v
e
clai
m
ed
th
at
it
ac
h
ie
v
es
cla
s
s
i
f
icatio
n
ac
cu
r
ac
y
o
f
9
4
%
an
d
8
4
%
r
es
p
ec
tiv
el
y
.
A
n
o
v
e
l
th
eo
r
etica
l
ap
p
r
o
ac
h
f
o
r
b
lin
d
f
o
r
en
s
ics
o
f
d
ig
i
tal
i
m
a
g
es
u
s
in
g
g
eo
m
etr
ic
tr
an
s
f
o
r
m
atio
n
is
p
r
esen
ted
in
th
e
s
tu
d
y
o
f
C
h
en
e
t
al.
[
1
3
]
.
On
e
th
e
o
t
h
er
h
a
n
d
[
1
4
]
also
f
o
cu
s
ed
o
n
t
h
e
s
a
m
e
b
u
t
it
b
as
icall
y
co
n
s
id
er
s
m
ed
ian
f
ilter
i
n
g
f
o
r
d
ig
ital
i
m
a
g
es.
S
ta
m
m
et
al.
[
1
5
]
b
asically
e
x
p
lo
r
ed
th
e
ar
ea
o
f
an
ti
-
f
o
r
en
s
ics
an
d
f
o
r
m
u
la
te
a
f
r
a
m
e
w
o
r
k
to
e
li
m
in
ate
co
m
p
r
e
s
s
io
n
f
i
n
g
er
p
r
in
t
s
f
r
o
m
a
d
ig
ital
i
m
a
g
e,
tr
a
n
s
f
o
r
m
atio
n
co
ef
f
icie
n
t
s
.
C
ao
et
al.
[
1
6
]
f
o
cu
s
ed
o
n
th
e
im
a
g
e
v
i
s
u
al
q
u
alit
y
e
n
h
a
n
ce
m
en
t
at
th
e
s
a
m
e
ti
m
e
also
tar
g
eted
to
en
f
o
r
ce
ef
f
ec
tiv
e
i
m
a
g
e
f
o
r
en
s
ic
s
w
it
h
J
P
E
G
co
m
p
r
ess
io
n
a
n
d
p
i
x
e
l
v
al
u
e
m
ap
p
i
n
g
p
r
in
cip
les.
E
x
ten
s
i
v
e
s
i
m
u
la
tio
n
o
u
tco
m
e
f
u
r
th
er
clai
m
ed
it
s
e
f
f
icien
c
y
to
w
ar
d
s
o
b
j
ec
tify
i
n
g
f
o
r
g
ed
lo
ca
tio
n
s
.
[
1
7
-
2
0
]
als
o
h
av
e
f
o
cu
s
ed
o
n
th
e
s
i
m
ilar
p
r
o
b
lem
w
it
h
t
h
e
o
r
etica
l
as
w
ell
a
s
e
x
p
er
i
m
e
n
tal
d
is
c
u
s
s
io
n
.
Si
m
ilar
l
y
,
C
o
n
o
tter
et
al.
[
2
1
]
d
ev
elo
p
ed
a
n
o
v
el
f
o
r
en
s
ic
tech
n
iq
u
e
w
h
ic
h
u
ti
lizes
p
r
o
b
a
b
il
it
y
o
f
d
is
tr
ib
u
tio
n
s
o
f
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
atio
n
(
D
C
T
)
to
ex
tr
ac
t
u
n
d
er
l
y
i
n
g
k
n
o
w
led
g
e
f
r
o
m
i
m
a
g
e
attr
ib
u
tes.
T
h
e
s
t
u
d
y
also
d
esig
n
s
a
n
ef
f
icien
t c
la
s
s
i
f
ier
w
h
ic
h
ca
n
e
x
tr
ac
t
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
es
f
r
o
m
a
n
i
m
a
g
e
o
b
j
ec
t
w
ith
o
u
t a
f
f
ec
tin
g
t
h
e
q
u
alit
y
o
f
th
e
d
ata.
Hig
h
li
g
h
ts
o
f
t
h
e
s
tu
d
y
ca
r
r
ied
o
u
t
b
y
[
2
2
]
an
d
[
2
3
]
also
p
r
o
v
id
es
an
in
s
ig
h
t
i
n
to
lear
n
i
n
g
ap
p
r
o
ac
h
es
f
o
r
ef
f
ec
ti
v
e
d
ec
is
io
n
f
u
s
io
n
e
n
ab
led
i
m
a
g
e
f
o
r
en
s
ic
s
.
T
h
ai
et
al.
[
2
4
]
also
p
r
e
s
en
t
s
a
n
o
v
el
i
m
ag
e
f
o
r
en
s
ic
s
tec
h
n
iq
u
e
w
h
er
e
J
P
E
G
q
u
an
tizatio
n
p
la
y
s
a
cr
u
c
i
al
r
o
le.
Mu
r
t
h
y
et
al.
[
2
5
]
h
av
e
d
e
m
o
n
s
tar
ted
a
tech
n
iq
u
e.
R
ed
d
y
e
t
al.
[
2
6
]
h
av
e
d
e
m
o
n
s
tar
ted
co
m
p
ar
ativ
e
s
tu
d
y
o
f
co
m
m
o
n
ed
g
e
r
ec
o
g
n
iza
tio
n
al
g
o
r
ith
m
b
y
u
s
i
n
g
p
r
e
-
p
r
o
ce
s
s
i
n
g
m
e
th
o
d
.
Ku
m
ar
a
n
d
Ki
s
h
o
r
e
[
2
7
]
h
av
e
p
r
esen
ted
ca
teg
o
r
izatio
n
o
f
I
n
d
ian
c
lass
ical
d
an
ce
m
u
d
r
a
b
y
u
s
i
n
g
HOG
c
h
ar
ac
ter
is
tic
a
n
d
SVM
clas
s
i
f
i
er
.
T
h
e
an
al
y
s
i
s
o
f
t
h
e
m
o
s
t
l
y
ci
ted
ex
itin
g
liter
at
u
r
es
clea
r
l
y
r
ev
ea
ls
t
h
e
f
ac
t
t
h
at
th
er
e
i
s
s
till
a
g
a
p
ex
is
t
in
g
w
h
e
n
b
o
th
q
u
ali
t
y
f
ac
to
r
an
d
i
m
ag
e
f
o
r
e
n
s
ic
s
ar
e
co
n
ce
r
n
ed
.
Ver
y
f
e
w
s
t
u
d
ies
ar
e
f
o
u
n
d
w
h
ic
h
co
m
p
lete
l
y
ad
d
r
ess
es
th
e
p
r
o
b
le
m
o
f
i
m
a
g
e
f
o
r
en
s
ic
s
b
y
i
n
co
r
p
o
r
atin
g
i
m
a
g
e
q
u
alit
y
e
n
h
a
n
ce
m
en
t
p
r
o
ce
s
s
.
I
t
is
also
o
b
s
er
v
ed
th
at
m
o
s
t
o
f
th
e
e
x
is
ti
n
g
ar
ch
i
v
es
ar
e
th
e
o
r
etica
ll
y
illu
s
tr
ated
w
h
er
e
n
o
b
en
ch
m
ar
k
i
n
g
h
as
b
ee
n
r
ep
o
r
ted
w
it
h
r
esp
ec
t to
co
m
p
u
tatio
n
al,
q
u
alit
y
an
d
cla
s
s
i
f
icatio
n
ac
cu
r
ac
y
a
s
p
ec
ts
.
T
h
e
ex
is
t
in
g
i
m
a
g
e
f
o
r
en
s
ic
a
p
p
r
o
ac
h
es
v
er
y
les
s
l
ik
el
y
in
c
o
r
p
o
r
ate
d
m
ac
h
i
n
e
lear
n
i
n
g
,
s
p
ec
if
icall
y
un
-
s
u
p
er
v
i
s
ed
lear
n
i
n
g
b
ased
s
o
lu
tio
n
s
f
o
r
th
e
d
etec
tio
n
o
f
f
o
r
g
ed
r
eg
io
n
w
h
ic
h
is
a
p
r
i
m
e
asp
ec
t
to
w
ar
d
s
s
p
ee
d
in
g
u
p
th
e
p
r
o
ce
s
s
w
it
h
h
ig
h
er
ac
cu
r
ac
y
.
T
h
er
ef
o
r
e
th
e
p
r
o
b
lem
s
tate
m
en
t
in
t
h
is
co
n
tex
t
ca
n
b
e
f
r
a
m
ed
as:
“
De
s
ig
n
i
n
g
a
n
effic
ien
t
a
n
d
in
tellig
en
t
co
mp
u
ta
tio
n
a
l
mo
d
el
to
s
tr
en
g
th
en
th
e
ima
g
e
f
o
r
en
s
ic
a
s
p
ec
t
f
r
o
m
b
o
th
co
mp
u
ta
tio
n
a
n
d
q
u
a
lity o
f th
e
ima
g
e
view
-
p
o
i
n
t is ve
r
y
mu
ch
ch
a
lle
n
g
in
g
”
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
7
4
-
3
4
7
9
3476
2.
E
M
P
I
RICAL
S
YST
E
M
DE
SI
G
N
AND
M
O
DE
L
I
N
G
2
.
1
.
P
ro
ce
s
s
o
f
s
elec
t
io
n o
f
inp
ut
da
t
a
T
h
is
co
m
p
u
tat
io
n
al
p
r
o
ce
s
s
i
s
m
o
d
eled
to
s
e
lect
s
p
ec
i
f
ic
f
ile
w
it
h
s
p
ec
if
ic
d
ata
t
y
p
e
(
file
data
Type
)
f
r
o
m
a
d
is
k
d
r
i
v
e
lo
ca
tio
n
(
d
L
oC
)
b
y
i
n
co
r
p
o
r
atin
g
a
f
i
lter
izatio
n
m
ec
h
an
is
m
.
I
n
th
e
s
u
cc
es
s
f
u
l
f
ile
t
y
p
e
s
elec
tio
n
,
th
e
p
r
o
ce
s
s
r
etu
r
n
s
t
w
o
d
if
f
er
e
n
t stri
n
g
w
h
ic
h
co
n
tai
n
s
Ob
j
nam
e
a
n
d
Ob
j
path
.
T
h
e
T
ab
le
1
s
h
o
w
s
s
elec
tio
n
o
f
a
test
in
p
u
t
d
ata
f
ile
w
h
ich
i
s
a
f
ac
ia
l
o
b
j
ec
t
o
f
.
jp
g
ex
ten
s
i
o
n
.
I
t
also
s
h
o
w
s
t
h
e
o
u
tco
m
e
o
f
th
e
n
u
m
er
ical
co
m
p
u
tin
g
p
r
o
ce
s
s
wh
er
e
v
al
u
es
o
f
r
esp
ec
ti
v
e
s
ize
o
f
th
e
d
ata
f
ile
w
it
h
r
esp
ec
t
to
p
ar
am
eter
s
b
y
tes
an
d
class
ar
e
h
ig
h
li
g
h
ted
.
On
th
e
co
m
p
letio
n
o
f
th
is
n
u
m
er
ical
co
m
p
u
tatio
n
p
r
o
ce
s
s
th
e
f
u
n
ct
io
n
f
Obj
S
electi
on
(
)
r
etu
r
n
s
t
w
o
d
if
f
er
en
t
s
tr
i
n
g
s
s
u
ch
as
Ob
j
nam
e
[]
1×
10
an
d
Ob
j
path
[]
1×
52
ar
e
d
is
cu
s
s
ed
f
u
r
th
er
.
T
ab
le
1
.
Selectio
n
o
f
a
Tes
t O
b
j
I
n
p
u
t
D
a
t
a
/
O
b
j
f
i
l
e
da
t
a
T
y
pe
(
e
x
t
e
n
si
o
n
)
S
i
z
e
o
n
d
i
s
k
B
y
t
e
s
C
l
a
ss
T
e
st
D
obj
.
j
p
g
1
9
4
×
2
5
9
×
3
1
5
0
7
3
8
U
i
n
t
8
2
.
2
.
P
ro
ce
s
s
o
f
decla
ring
f
ile
des
cr
ipto
r
(
f
des
)
I
n
th
i
s
p
r
o
ce
s
s
a
s
tr
in
g
v
ar
ia
b
le
n
a
m
ed
f
des
o
f
s
ize
1
×1
6
is
cr
ea
ted
b
y
co
n
ca
ten
ati
n
g
t
wo
d
if
f
er
en
t
s
tr
in
g
o
b
j
ec
ts
Ob
j
nam
e
[]
1
×
10
a
n
d
Ob
j
path
[]
1×
52
w
h
ic
h
g
e
n
er
ali
ze
s
t
h
e
ad
d
r
ess
o
f
t
h
e
s
p
ec
if
ic
in
p
u
t
d
ata
w
h
ic
h
is
also
ca
n
b
e
r
ef
er
r
ed
as
d
L
oC.
2
.
3
.
Nu
m
er
ica
l c
o
m
p
uta
t
io
n o
f
a
da
t
a
o
bje
ct
(
Do
bj)
I
n
th
i
s
p
r
o
ce
s
s
a
d
ata
o
b
j
ec
t
D
obj
is
cr
ea
ted
b
y
p
er
f
o
r
m
i
n
g
q
u
an
t
izatio
n
a
n
d
s
a
m
p
l
in
g
o
f
a
s
p
ec
if
ied
d
ata
f
ile
d
escr
ip
to
r
D
obj
.
Af
ter
th
at
a
n
u
m
er
ical
r
ep
r
esen
tatio
n
o
f
t
h
e
D
obj
is
al
s
o
co
m
p
u
ted
.
2
.
4
.
Det
ec
t
io
n o
f
m
a
j
o
r
O
bj
(
m
O
bj)
I
n
th
is
p
r
o
ce
s
s
a
u
s
er
d
ef
i
n
e
d
f
u
n
ctio
n
is
ca
lled
w
h
er
e
m
aj
o
r
o
b
j
ec
ts
ar
e
cr
o
p
p
ed
b
y
i
n
v
o
k
i
n
g
a
p
ac
k
ag
e
ca
lled
v
is
io
n
v
.
v
b
asicall
y
d
etec
ts
o
b
j
ec
t
u
s
i
n
g
Vio
la
-
J
o
n
es
alg
o
r
it
h
m
.
F
u
r
th
er
it
also
co
m
p
u
tes
b
o
u
n
d
ar
y
b
o
x
v
a
lu
e
s
(
B
B
v
)
b
ased
o
n
th
e
n
u
m
b
er
o
f
Ob
j
.
Fu
r
t
h
er
it
cr
o
p
s
th
e
D
Obj
w
i
th
r
esp
ec
t
to
t
h
e
B
B
v
d
ef
in
ed
.
T
h
e
c
r
o
p
p
e
d
d
ata
(
m
O
bj
)
f
u
r
t
h
er
s
av
ed
i
n
to
a
d
atab
ase
f
ile
m
Obj
(
9
0
×1
2
6
×3
)
u
in
t8
.
ij
i
i
j
j
obj
m
m
m
m
m
m
m
m
m
m
...
.
.
.
...
.
.
.
.
.
.
...
...
|
|
2
1
2
22
21
1
12
11
2
.
5
.
P
ro
ce
s
s
o
f
s
ub
o
bje
ct
det
ec
t
io
n f
ro
m
m
a
j
o
r
O
bj
T
h
e
s
u
b
o
b
j
ec
t
w
h
ic
h
i
s
al
s
o
ter
m
ed
a
s
S
u
b
obj
m
Obj
ex
tr
ac
ted
w
i
th
r
esp
ec
t
to
R
OI
a
n
d
o
p
ti
m
ized
o
u
tp
u
t
r
esp
o
n
s
e
(
OP
R
)
.
T
h
e
i
m
ag
e
f
o
r
en
s
ics
h
er
e
ap
p
lies
a
s
et
o
f
co
m
p
u
tatio
n
a
l
s
tep
s
to
o
p
ti
m
ize
th
e
p
er
f
o
r
m
a
n
ce
ass
o
ciate
d
w
i
th
th
e
m
aj
o
r
o
b
j
ec
t d
etec
tio
n
ac
cu
r
ac
y
.
T
h
e
m
aj
o
r
o
b
j
ec
t
d
et
ec
to
r
o
p
e
r
ates
w
it
h
th
e
s
i
g
n
i
f
ica
n
t
f
ea
tu
r
es
a
n
d
attr
ib
u
tes
to
cr
o
p
th
e
m
aj
o
r
o
b
j
e
ct
attr
ib
u
tes
w
h
ic
h
p
la
y
a
v
er
y
cr
u
cial
r
o
le
w
h
ile
p
er
f
o
r
m
in
g
t
h
e
ass
e
s
s
m
e
n
t o
f
i
m
ag
e
f
o
r
en
s
ics.
Fin
all
y
u
s
in
g
th
e
b
o
u
n
d
ar
y
b
o
x
attr
ib
u
te
s
,
t
h
e
m
Obj
is
ex
tr
ac
ted
w
ith
t
h
e
n
eg
lig
ib
le
co
m
p
u
tatio
n
a
l
co
m
p
le
x
it
y
a
n
d
th
e
cr
o
p
p
ed
r
e
g
io
n
at
tr
ib
u
tes
g
et
e
x
tr
ac
ted
.
T
h
e
u
n
s
u
p
er
v
i
s
ed
lear
n
i
n
g
p
r
o
ce
s
s
i
n
t
h
is
co
n
tex
t
u
s
e
s
i
n
-
b
u
ilt
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
tr
ai
n
in
g
m
ec
h
a
n
is
m
w
i
th
d
ata
p
atter
n
f
o
llo
w
ed
i
n
v
i
s
u
al
d
escr
ip
to
r
s
to
m
ak
e
t
h
e
cla
s
s
i
f
icatio
n
p
r
o
ce
s
s
m
u
c
h
i
n
tel
lig
e
n
t.
T
h
e
F
ig
u
r
e
1
s
h
o
w
s
a
b
lo
c
k
-
b
ased
r
ep
r
esen
tat
io
n
to
d
ep
ict
th
e
id
ea
o
f
th
e
co
n
ce
p
t
w
h
ic
h
is
i
m
p
o
s
ed
in
th
e
p
r
o
p
o
s
ed
u
n
-
s
u
p
er
v
is
ed
lear
n
i
n
g
-
b
as
ed
im
a
g
e
f
o
r
en
s
ic
s
m
et
h
o
d
o
lo
g
y
w
h
ile
q
u
alit
y
as
s
ess
m
en
t o
f
th
e
i
m
a
g
e
also
p
la
y
s
a
v
ital r
o
le.
T
h
e
F
ig
u
r
e
1
clea
r
l
y
ex
h
ib
i
ts
th
e
b
lo
ck
b
ased
a
r
ch
itect
u
r
al
d
esig
n
o
f
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
I
t
b
asicall
y
in
co
r
p
o
r
ates
a
f
u
n
ctio
n
al
it
y
w
h
ic
h
en
ab
le
s
th
e
v
is
u
al
d
escr
ip
to
r
s
to
ex
tr
ac
t
s
ig
n
i
f
ica
n
t
f
ea
t
u
r
e
s
f
r
o
m
ea
ch
b
lo
ck
o
f
t
h
e
d
ata
o
b
j
ec
t
o
r
m
Obj
.
He
r
e
ea
ch
v
ec
to
r
b
asicall
y
co
m
p
o
s
ed
o
f
s
p
atia
l
co
lo
r
in
f
o
r
m
atio
n
ass
o
ciate
d
w
ith
t
h
e
co
r
r
esp
o
n
d
in
g
b
lo
ck
s
.
T
h
ese
s
i
g
n
i
f
ican
t
ex
tr
a
cted
f
ea
t
u
r
es
ar
e
u
s
ed
to
tr
ain
th
e
u
n
s
u
p
er
v
is
ed
class
if
ier
to
m
a
k
e
it
m
o
r
e
in
tel
lig
e
n
t
f
o
r
g
ettin
g
in
s
ig
h
t
i
n
to
th
e
u
n
d
er
l
y
i
n
g
attr
ib
u
tes
o
f
a
m
aj
o
r
o
b
j
ec
t.
T
h
e
tr
ain
in
g
an
d
a
test
i
n
g
m
o
d
elin
g
also
i
n
tr
o
d
u
ce
d
h
er
e
d
u
r
in
g
t
h
e
co
n
ce
p
tu
a
lizati
o
n
o
f
th
e
id
ea
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
efficien
t c
o
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
b
a
la
n
ce
th
e
tr
a
d
e
-
o
f
f b
etw
ee
n
ima
g
e
fo
r
en
s
ics
.
..
(
S
h
a
s
h
id
h
a
r
T M)
3477
I
f
th
e
lear
n
i
n
g
p
r
o
ce
s
s
f
i
n
d
s
an
y
in
d
icatio
n
w
h
ich
s
tate
s
t
h
at
t
h
er
e
ex
i
s
ts
s
i
m
ilar
it
y
o
f
p
atter
n
i
n
b
et
w
ee
n
th
e
v
is
u
al
d
escr
ip
to
r
-
o
r
ien
ted
v
ec
to
r
s
,
th
e
n
it
r
ef
lects
th
a
t
co
u
n
ter
f
ei
t
is
p
er
f
o
r
m
ed
to
th
e
co
r
r
esp
o
n
d
in
g
b
lo
ck
attr
ib
u
te
s
w
h
ich
g
o
t
s
i
m
ilar
p
atter
n
s
.
Du
r
in
g
th
e
p
r
o
ce
s
s
o
p
er
atio
n
th
e
co
lo
r
o
b
j
ec
t
g
et
co
n
v
er
ted
in
to
8
-
b
it
g
r
a
y
lev
el
to
o
p
tim
ize
t
h
e
ti
m
e
co
m
p
lex
it
y
lev
el
p
r
io
r
p
er
f
o
r
m
in
g
i
m
ag
e
f
o
r
en
s
ics.
T
h
e
ea
s
e
o
f
co
m
p
u
tati
o
n
b
as
icall
y
s
p
ee
d
s
u
p
t
h
e
co
m
p
u
t
atio
n
at
th
e
lear
n
in
g
p
r
o
ce
s
s
w
h
er
e
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
a
n
d
tr
ain
in
g
g
et
p
er
f
o
r
m
ed
s
i
m
u
lta
n
eo
u
s
l
y
to
p
r
o
v
id
e
m
o
r
e
i
n
s
i
g
h
t
i
n
to
u
n
d
er
l
y
in
g
f
ac
ts
as
s
o
ciate
d
w
it
h
d
ata
o
b
j
ec
t
an
d
m
Obj
b
lo
ck
in
g
attr
ib
u
te
s
.
Fu
r
t
h
er
,
th
e
d
ata
o
b
j
ec
t
d
etec
ted
is
p
r
o
ce
s
s
ed
th
r
o
u
g
h
a
3
x
3
m
ea
n
f
il
ter
k
er
n
el
to
m
ak
e
it
b
lu
r
g
r
a
y
le
v
el
d
ata
o
b
j
ec
t
at
th
e
f
ir
s
t
s
tep
.
T
h
e
v
is
u
al
d
escr
ip
to
r
m
et
h
o
d
s
w
h
ich
ex
tr
ac
ts
th
e
v
is
u
al
p
r
o
p
er
ties
f
r
o
m
th
e
o
b
j
ec
t
b
asicall
y
ap
p
lies
a
b
lu
r
r
in
g
p
r
o
ce
s
s
as
t
h
e
r
e
is
a
r
ea
s
o
n
lies
b
eh
in
d
.
I
t b
asicall
y
at
te
m
p
t
s
t
o
m
i
n
i
m
ize
t
h
e
n
e
g
li
g
ib
le
v
ar
iatio
n
s
a
m
o
n
g
th
e
ad
j
ac
en
t p
ix
els.
O
b
j
e
c
t
I
n
p
u
t
M
o
d
u
l
e
I
m
a
g
e
F
o
r
e
n
s
i
c
s
f
o
r
M
a
j
o
r
O
b
j
e
c
t
D
e
t
e
c
t
i
o
n
M
a
j
o
r
O
b
j
e
c
t
C
r
o
p
p
i
n
g
D
e
f
i
n
e
b
o
u
n
d
a
r
y
B
o
x
v
a
l
u
e
s
V
i
s
u
a
l
i
z
a
t
i
o
n
P
a
r
a
m
e
t
e
r
s
V
i
s
u
a
l
D
e
s
c
r
i
p
t
o
r
s
O
b
j
e
c
t
n
a
m
e
,
p
a
t
h
T
e
s
t
i
n
g
o
f
t
h
e
s
y
s
t
e
m
A
p
p
l
y
U
n
s
u
p
e
r
v
i
s
e
d
L
e
a
r
n
i
n
g
f
o
r
m
a
j
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
Fig
u
r
e
1
.
T
h
e
ar
ch
itectu
r
al
b
lo
ck
-
b
a
s
ed
s
y
s
te
m
o
v
er
v
ie
w
Ov
er
lap
p
in
g
b
lo
ck
s
o
f
s
ize
8
x
8
o
f
th
e
b
lu
r
r
ed
im
a
g
e
ar
e
th
en
u
s
ed
to
co
m
p
u
te
co
lo
r
v
ec
to
r
s
in
v
is
u
a
l
d
escr
ip
to
r
s
.
T
h
e
d
ata
o
b
j
ec
t
is
s
ca
n
n
ed
i
n
r
o
w
m
aj
o
r
f
r
o
m
le
f
t
to
r
ig
h
t
an
d
to
p
to
b
o
tto
m
.
T
h
e
v
i
s
u
al
d
escr
ip
to
r
s
m
eth
o
d
i
s
d
esi
g
n
e
d
to
ex
tr
ac
t
f
ea
t
u
r
es
f
r
o
m
ea
c
h
b
lo
ck
.
P
ix
el
v
al
u
es
ar
e
d
i
s
c
r
etize
d
in
o
r
d
er
to
m
ap
i
n
te
n
s
it
y
in
to
[
0
−
6
3
]
r
an
g
e.
Vis
u
al
d
escr
ip
to
r
s
o
f
th
e
b
lo
ck
ar
e
d
eter
m
in
ed
ac
co
r
d
i
n
g
to
n
e
w
p
r
o
ce
s
s
.
Vis
u
a
l
d
escr
ip
to
r
s
o
f
ea
c
h
b
l
o
ck
ar
e
o
f
s
ize
1
2
8
,
w
h
er
e
f
i
r
s
t
s
i
x
t
y
-
f
o
u
r
e
le
m
e
n
t
s
r
ep
r
esen
t
t
h
e
n
u
m
b
er
o
f
co
n
s
is
ten
c
y
p
ix
e
ls
o
f
t
h
e
co
r
r
esp
o
n
d
in
g
i
n
ten
s
it
y
v
alu
e
an
d
last
s
ix
t
y
-
f
o
u
r
ele
m
e
n
ts
r
ep
r
esen
t
th
e
n
u
m
b
er
o
f
in
co
h
er
e
n
t
p
ix
e
ls
o
f
t
h
e
co
r
r
esp
o
n
d
in
g
i
n
ten
s
it
y
v
al
u
e
i
n
t
h
e
b
lo
ck
.
T
h
e
n
e
x
t
s
ec
tio
n
o
f
t
h
e
s
t
u
d
y
d
is
c
u
s
s
es
ab
o
u
t
th
e
o
u
tco
m
e
o
b
tai
n
ed
af
ter
s
i
m
u
lati
n
g
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
i
n
a
co
m
p
u
ti
n
g
en
v
i
r
o
n
m
e
n
t
f
o
r
m
aj
o
r
o
b
j
ec
t d
etec
tio
n
w
it
h
co
s
t
-
ef
f
e
ctiv
e
i
m
ag
e
f
o
r
en
s
ics.
3.
E
XP
E
R
I
M
E
NT
A
L
ANA
L
Y
SI
S
T
h
is
s
ec
tio
n
p
r
ese
n
ts
th
e
o
u
t
co
m
e
b
ein
g
ac
co
m
p
lis
h
ed
f
r
o
m
t
h
e
e
x
te
n
s
i
v
e
n
u
m
er
ical
s
i
m
u
lat
io
n
w
h
ic
h
is
ca
r
r
ied
o
u
t
i
n
6
4
-
b
it
w
in
d
o
w
s
s
y
s
te
m
p
o
w
er
b
y
I
n
tel
co
r
e
i5
-
8
2
5
0
U
C
P
U
r
u
n
n
in
g
w
it
h
co
m
p
u
ti
n
g
s
p
ee
d
o
f
1
6
0
GHz
/1
.
8
0
GHz
.
T
h
e
n
u
m
er
ical
s
i
m
u
la
tio
n
f
o
r
t
h
e
ex
p
er
i
m
e
n
tal
s
e
t
u
p
al
s
o
i
m
p
o
s
es
a
m
i
n
i
m
u
m
r
eq
u
ir
e
m
en
t
o
f
4
GB
in
ter
n
al
m
e
m
o
r
y
(
R
A
M)
.
T
h
e
ex
ten
s
i
v
e
co
m
p
ar
ativ
e
a
n
al
y
s
is
ca
r
r
ied
o
u
t
w
it
h
r
esp
ec
t
to
t
w
o
d
if
f
er
en
t
p
r
i
m
e
an
d
s
i
g
n
if
ican
t
p
er
f
o
r
m
a
n
ce
p
ar
a
m
eter
s
w
h
ic
h
ar
e
i)
P
ea
k
S
ig
n
a
l
t
o
N
o
is
e
R
a
tio
(
P
S
N
R
)
an
d
ii)
E
xe
cu
tio
n
Time
to
v
alid
ate
th
e
p
er
f
o
r
m
a
n
ce
f
ac
to
r
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
a
s
co
m
p
ar
ed
to
th
e
ex
is
tin
g
s
y
s
te
m
[
2
1
]
.
T
h
e
co
m
p
ar
ati
v
e
a
n
al
y
s
i
s
a
s
h
ig
h
li
g
h
ted
clea
r
l
y
s
h
o
w
s
th
at
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ac
h
ie
v
e
s
co
n
s
id
er
ab
le
i
m
a
g
e
f
o
r
en
s
ics
w
h
ile
ac
co
m
p
li
s
h
in
g
h
i
g
h
er
P
SNR
v
al
u
es
f
o
r
iter
atio
n
(
1
0
-
90)
as
s
h
o
w
n
i
n
Fig
u
r
e
2
.
T
h
e
p
ea
k
v
alu
e
o
f
th
e
P
SNR
o
b
tain
ed
at
th
e
iter
atio
n
n
u
m
b
er
8
0
.
T
h
e
P
SNR
f
ac
to
r
in
d
icate
s
th
at
th
e
p
r
o
p
o
s
ed
tech
n
iq
u
e
ac
h
i
ev
es
d
etec
tio
n
o
f
m
aj
o
r
o
b
jects
w
it
h
o
u
t
co
m
p
r
o
m
is
i
n
g
th
e
q
u
alit
y
f
ac
to
r
ass
o
ciate
d
w
it
h
t
h
e
test
ed
o
b
ject
d
u
r
in
g
i
m
ag
e
f
o
r
en
s
ics.
I
t
is
a
ls
o
f
o
u
n
d
t
h
at
i
n
th
e
ca
s
e
o
f
e
x
i
s
tin
g
s
y
s
te
m
th
e
P
SNR
v
alu
e
s
ar
e
q
u
ite
les
s
er
.
As
s
h
o
w
n
i
n
th
e
F
i
g
u
r
e
3
,
th
e
s
t
u
d
y
also
ca
r
r
ied
o
u
t
ass
es
s
m
en
t
o
f
th
e
ti
m
e
co
m
p
lex
it
y
o
f
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
.
I
t
s
h
o
w
s
th
at
th
e
co
n
v
er
s
io
n
o
f
o
b
j
ec
t
f
r
o
m
3
-
d
i
m
en
s
io
n
al
s
p
ac
e
to
8
-
b
it
1
-
d
i
m
e
n
s
io
n
al
g
r
a
y
s
ca
le
r
ed
u
ce
t
h
e
d
i
m
en
s
io
n
alit
y
o
f
d
ata
as
s
o
ciate
d
w
ith
th
e
o
b
j
ec
t
w
h
ic
h
r
e
s
u
lt
s
i
n
o
p
ti
m
ized
co
m
p
u
tatio
n
ti
m
e.
I
t
is
also
o
b
s
er
v
ed
th
a
t
t
h
e
cla
s
s
i
f
ier
p
er
f
o
r
m
s
lear
n
in
g
a
n
d
d
etec
ti
o
n
o
f
t
h
e
m
aj
o
r
o
b
j
ec
t
s
i
m
u
lta
n
eo
u
s
l
y
w
it
h
a
f
ea
tu
r
e
ex
tr
ac
tio
n
p
r
o
ce
s
s
w
h
ich
also
lead
s
to
p
o
s
e
n
e
g
li
g
ib
le
co
m
p
u
tatio
n
a
l
o
v
er
h
ea
d
at
th
e
ti
m
e
o
f
s
i
m
u
lat
io
n
.
T
h
e
ab
o
v
e
q
u
an
t
itati
v
e
in
ter
p
r
etatio
n
o
f
f
r
o
m
F
ig
u
r
e
3
clea
r
l
y
s
h
o
w
s
t
h
at
th
e
p
r
o
p
o
s
ed
s
y
s
te
m
ac
co
m
p
lis
h
e
s
v
er
y
less
er
co
m
p
u
tat
io
n
ti
m
e
a
s
c
o
m
p
ar
ed
to
th
e
ex
i
s
ti
n
g
s
y
s
te
m
.
T
h
e
j
u
s
tif
ica
tio
n
s
o
n
th
e
b
as
is
o
f
n
u
m
er
ical
s
i
m
u
latio
n
o
u
tco
m
e
clea
r
l
y
s
h
o
w
s
th
a
t
t
h
e
p
r
o
p
o
s
ed
s
y
s
te
m
ac
h
iev
e
s
h
i
g
h
er
d
e
g
r
ee
o
f
i
m
a
g
e
f
o
r
en
s
ics
w
i
th
o
u
t
af
f
ec
tin
g
th
e
q
u
alit
y
a
s
p
ec
t
ass
o
ciate
d
w
i
th
th
e
i
m
ag
e/o
b
j
ec
t.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
9
,
No
.
5
,
Octo
b
er
2
0
1
9
:
3
4
7
4
-
3
4
7
9
3478
Fig
u
r
e
2
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
n
th
e
b
asis
o
f
P
SNR
(
d
B
)
Fig
u
r
e
3
.
C
o
m
p
ar
ativ
e
a
n
al
y
s
i
s
o
f
ex
ec
u
t
io
n
ti
m
e
(
Sec)
4.
CO
NCLU
SI
O
N
I
n
th
e
cu
r
r
e
n
t
ti
m
e
t
h
er
e
ar
e
v
ar
io
u
s
r
esear
ch
ar
c
h
i
v
es
w
h
i
ch
tal
k
ab
o
u
t
d
i
f
f
er
en
t
t
y
p
es
o
f
f
o
r
en
s
ic
tech
n
iq
u
es
w
h
ic
h
ar
e
f
o
u
n
d
w
ell
-
ca
p
ab
le
o
f
d
etec
tin
g
f
o
r
g
e
d
r
eg
io
n
as
w
e
ll
as
ar
ti
f
ac
ts
f
r
o
m
d
i
f
f
er
en
t
i
m
a
g
e
o
b
j
ec
ts
.
T
h
e
p
r
o
p
o
s
ed
s
tu
d
y
p
r
esen
ts
a
n
an
al
y
tical
f
o
r
m
o
f
co
m
p
u
tat
io
n
al
m
o
d
el
w
h
i
ch
i
m
p
o
s
e
s
h
i
g
h
er
-
d
eg
r
ee
o
f
i
m
a
g
e
f
o
r
en
s
ic
s
to
d
eter
m
i
n
e
co
m
p
u
tatio
n
a
ll
y
ef
f
icien
t
d
etec
tio
n
o
f
m
aj
o
r
o
b
j
ec
ts
w
h
i
le
also
b
alan
ce
s
t
h
e
q
u
alit
y
attr
ib
u
tes
o
f
th
e
i
m
a
g
e
o
b
j
ec
t.
T
h
e
n
u
m
er
ical
s
i
m
u
latio
n
r
ev
ea
l
s
its
e
f
f
icie
n
c
y
i
n
ter
m
s
o
f
co
m
p
u
tatio
n
al
ti
m
e
a
n
d
q
u
alit
y
f
ac
to
r
w
h
ic
h
o
u
tp
er
f
o
r
m
s
th
e
ex
is
ti
n
g
b
aseli
n
e
w
it
h
an
i
m
p
r
o
v
e
m
en
t
o
f
al
m
o
s
t 5
0
%.
RE
F
E
R
E
NC
E
S
[1
]
A
.
T
.
S
.
Ho
a
n
d
S
.
L
i,
“
Ha
n
d
b
o
o
k
o
f
Dig
it
a
l
F
o
re
n
sic
s
o
f
M
u
lt
ime
d
ia
Da
ta
a
n
d
De
v
ic
e
s,
”
Jo
h
n
W
il
e
y
&
S
o
n
s,
2
0
1
5
.
[2
]
H.
T
.
S
e
n
c
a
r
a
n
d
N.
M
e
m
o
n
,
“
D
ig
it
a
l
Im
a
g
e
F
o
re
n
sic
s:
T
h
e
re
is
M
o
re
t
o
a
P
ict
u
re
th
a
n
M
e
e
ts
t
h
e
Ey
e
,
”
S
p
rin
g
e
r
S
c
ien
c
e
&
Bu
sin
e
ss
M
e
d
ia,
2
0
1
2
.
[3
]
R.
P
a
l,
“
In
n
o
v
a
ti
v
e
Re
se
a
rc
h
in
Atten
ti
o
n
M
o
d
e
li
n
g
a
n
d
Co
m
p
u
ter
V
isio
n
A
p
p
li
c
a
ti
o
n
s,
”
IGI Gl
o
b
a
l
,
2
0
1
5
.
[4
]
C.
Ha
rit
h
a
,
e
t
a
l
.
,
“
A
su
rv
e
y
o
n
m
o
d
e
rn
tren
d
s
i
n
ECG
n
o
ise
re
m
o
v
a
l
tec
h
n
iq
u
e
s,
”
2
0
1
6
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Circ
u
it
,
P
o
we
r a
n
d
C
o
mp
u
ti
n
g
T
e
c
h
n
o
lo
g
ies
(
ICCPCT
),
Na
g
e
rc
o
il
,
p
p
.
1
-
7
,
2
0
1
6
.
[5
]
Y.
Zo
u
,
e
t
a
l
.
,
“
A
u
to
m
a
ti
c
Id
e
n
ti
f
ica
ti
o
n
o
f
A
rti
f
a
c
t
-
re
lat
e
d
In
d
e
p
e
n
d
e
n
t
Co
m
p
o
n
e
n
ts
f
o
r
A
rt
if
a
c
t
R
e
m
o
v
a
l
in
EE
G
Re
c
o
rd
in
g
s
,
”
IEE
E
J
Bi
o
me
d
He
a
lt
h
I
n
fo
rm
.
,
v
o
l
/i
ss
u
e
:
20
(
1
)
,
p
p
.
7
3
-
8
1
,
2
0
1
6
.
[6
]
M
.
S
e
a
d
le,
“
Qu
a
n
ti
fy
in
g
Re
se
a
rc
h
In
teg
rit
y
,
”
M
o
rg
a
n
&
Clay
p
o
o
l
P
u
b
l
ish
e
rs,
2
0
1
6
.
[7
]
J.
G
.
R
.
El
w
in
,
e
t
a
l
.
,
“
S
u
rv
e
y
o
n
p
a
ss
iv
e
m
e
th
o
d
s
o
f
i
m
a
g
e
ta
m
p
e
rin
g
d
e
tec
ti
o
n
,
”
2
0
1
0
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mm
u
n
ica
ti
o
n
a
n
d
C
o
mp
u
ta
t
io
n
a
l
I
n
telli
g
e
n
c
e
(
INCOCCI),
Ero
d
e
,
p
p
.
4
3
1
-
4
3
6
,
2
0
1
0
.
[8
]
Z.
Z
.
Hu
a
a
n
d
W
.
W
.
Ya
n
,
‘
A
l
o
ss
les
s
c
o
m
p
re
ss
io
n
m
e
th
o
d
o
f
JP
EG
f
il
e
b
a
se
d
o
n
sh
u
f
f
le
a
lg
o
rit
h
m
,
”
2
0
1
0
2
n
d
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
mp
u
ter
Co
n
tro
l,
S
h
e
n
y
a
n
g
,
p
p
.
1
6
0
-
1
6
2
,
2
0
1
0
.
[9
]
S
h
a
sh
id
h
a
r
T
.
M
.
a
n
d
K.
B.
Ra
m
e
sh
,
“
F
A
RIP
:
F
ra
m
e
w
o
rk
f
o
r
A
rti
f
a
c
t
Re
m
o
v
a
l
f
o
r
Im
a
g
e
P
ro
c
e
ss
in
g
Us
in
g
JP
EG
,”
Co
mp
u
ter
S
c
ien
c
e
On
-
li
n
e
Co
n
fer
e
n
c
e
.
S
p
rin
g
e
r,
Ch
a
m
,
2
0
1
8
.
[1
0
]
S
h
a
sh
id
h
a
r
T
.
M
.
a
n
d
K.
B.
Ra
m
e
sh
,
“
Re
v
ie
w
in
g
th
e
Eff
e
c
ti
v
it
y
F
a
c
to
r
in
Ex
isti
n
g
T
e
c
h
n
i
q
u
e
s
o
f
Im
a
g
e
F
o
re
n
sic
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l
/i
ss
u
e
:
7
(
6
)
,
2
0
1
7
.
[1
1
]
W
.
F
a
n
,
e
t
a
l
.
,
“
M
e
d
ian
F
il
tere
d
Im
a
g
e
Qu
a
li
t
y
En
h
a
n
c
e
m
e
n
t
a
n
d
A
n
ti
-
F
o
re
n
sic
s
v
ia
V
a
riati
o
n
a
l
De
c
o
n
v
o
lu
ti
o
n
,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
f
o
rm
a
ti
o
n
Fo
re
n
sic
s a
n
d
S
e
c
u
rit
y
,
v
o
l
/i
ss
u
e
:
10
(
5
)
,
p
p
.
1
0
7
6
-
1
0
9
1
,
M
a
y
2
0
1
5
.
[1
2
]
T
.
Ca
rv
a
lh
o
,
e
t
a
l
.
,
“
Ill
u
m
in
a
n
t
-
Ba
se
d
T
ra
n
s
f
o
r
m
e
d
S
p
a
c
e
s
f
o
r
Im
a
g
e
F
o
re
n
sic
s,
”
in
I
EE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
11
(
4
)
,
p
p
.
7
2
0
-
7
3
3
,
A
p
r
2
0
1
6
.
[1
3
]
C.
Ch
e
n
,
e
t
a
l
.
,
“
Bli
n
d
F
o
re
n
si
c
s
o
f
S
u
c
c
e
ss
iv
e
G
e
o
m
e
tri
c
T
r
a
n
sf
o
rm
a
ti
o
n
s
in
Dig
it
a
l
Im
a
g
e
s
Us
in
g
S
p
e
c
tral
M
e
th
o
d
:
T
h
e
o
ry
a
n
d
A
p
p
li
c
a
ti
o
n
s,
”
in
IE
EE
T
r
a
n
s
a
c
ti
o
n
s
o
n
Im
a
g
e
Pro
c
e
ss
in
g
,
v
o
l
/
issu
e
:
26
(
6
)
,
p
p
.
2
8
1
1
-
2
8
2
4
,
Ju
n
2
0
1
7
.
[1
4
]
H.
Yu
a
n
,
“
Bli
n
d
F
o
re
n
sic
s
o
f
M
e
d
i
a
n
F
il
teri
n
g
in
Dig
it
a
l
Im
a
g
e
s,
”
in
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
In
f
o
rm
a
ti
o
n
Fo
re
n
sic
s
a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
6
(
4
)
,
p
p
.
1
3
3
5
-
1
3
4
5
,
De
c
2
0
1
1
.
[1
5
]
M
.
C.
S
tam
m
a
n
d
K.
J.
R.
L
iu
,
“
A
n
ti
-
f
o
re
n
sic
s o
f
d
ig
it
a
l
i
m
a
g
e
c
o
m
p
re
ss
io
n
,
”
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
I
n
fo
rm
a
ti
o
n
Fo
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
6
(
3
)
,
p
p
.
1
0
5
0
-
1
0
6
5
,
S
e
p
2
0
1
1
.
[1
6
]
G
.
Ca
o
,
e
t
a
l
.
,
“
Co
n
tras
t
En
h
a
n
c
e
m
e
n
t
-
Ba
se
d
F
o
re
n
sic
s
in
Dig
it
a
l
Im
a
g
e
s,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
fo
rm
a
ti
o
n
Fo
re
n
sic
s a
n
d
S
e
c
u
rity
, v
ol
/i
ss
u
e
:
9
(
3
)
,
p
p
.
5
1
5
-
5
2
5
,
M
a
r
2
0
1
4
.
[1
7
]
W
.
L
u
o
,
e
t
a
l
.
,
“
JP
EG
Err
o
r
A
n
a
ly
sis
a
n
d
Its
A
p
p
li
c
a
ti
o
n
s
to
Dig
it
a
l
Im
a
g
e
F
o
re
n
sic
s,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
, v
ol
/i
ss
u
e
:
5
(
3
)
,
p
p
.
4
8
0
-
4
9
1
,
S
e
p
2
0
1
0
.
[1
8
]
Y.
Hs
u
a
n
d
S
.
C
h
a
n
g
,
“
Ca
m
e
ra
Re
sp
o
n
se
F
u
n
c
ti
o
n
s
f
o
r
Im
a
g
e
F
o
re
n
sic
s:
A
n
A
u
to
m
a
ti
c
A
l
g
o
rit
h
m
f
o
r
S
p
li
c
in
g
De
tec
ti
o
n
,
”
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s
o
n
In
f
o
rm
a
ti
o
n
Fo
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
5
(
4
)
,
p
p
.
8
1
6
-
8
2
5
,
De
c
2
0
1
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
efficien
t c
o
mp
u
ta
tio
n
a
l a
p
p
r
o
a
ch
to
b
a
la
n
ce
th
e
tr
a
d
e
-
o
f
f b
etw
ee
n
ima
g
e
fo
r
en
s
ics
.
..
(
S
h
a
s
h
id
h
a
r
T M)
3479
[1
9
]
A
.
A
.
d
e
Oliv
e
ira
,
e
t
a
l
.,
“
M
u
lt
i
p
l
e
P
a
re
n
t
in
g
P
h
y
lo
g
e
n
y
R
e
latio
n
sh
i
p
s
i
n
Dig
it
a
l
Im
a
g
e
s,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
11
(
2
)
,
p
p
.
3
2
8
-
3
4
3
,
F
e
b
2
0
1
6
.
[2
0
]
G
.
V
a
len
z
ise
,
e
t
a
l
.
,
“
Re
v
e
a
li
n
g
th
e
T
ra
c
e
s
o
f
J
P
EG
Co
m
p
re
ss
io
n
A
n
ti
-
F
o
re
n
sic
s,
”
in
IEE
E
T
r
a
n
sa
c
ti
o
n
s
o
n
In
fo
rm
a
t
io
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
8
(
2
)
,
p
p
.
3
3
5
-
3
4
9
,
F
e
b
2
0
1
3
.
[2
1
]
V
.
C
o
n
o
tt
e
r,
e
t
a
l
.
,
“
F
o
re
n
sic
De
tec
ti
o
n
o
f
P
ro
c
e
ss
in
g
Op
e
ra
to
r
C
h
a
in
s:
Re
c
o
v
e
rin
g
th
e
H
isto
ry
o
f
F
il
tere
d
J
P
EG
Im
a
g
e
s,
”
in
IEE
E
T
ra
n
s
a
c
ti
o
n
s o
n
In
f
o
rm
a
ti
o
n
Fo
re
n
sic
s
a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
10
(
11
)
,
p
p
.
2
2
5
7
-
2
2
6
9
,
2
0
1
5
.
[2
2
]
E.
A
rd
izz
o
n
e
,
e
t
a
l
.
,
“
C
o
p
y
–
M
o
v
e
F
o
rg
e
ry
De
te
c
ti
o
n
b
y
M
a
tch
in
g
T
rian
g
les
o
f
Ke
y
p
o
in
ts,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
fo
rm
a
ti
o
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
,
v
o
l
/i
ss
u
e
:
10
(
10
)
,
p
p
.
2
0
8
4
-
2
0
9
4
,
Oc
t
2
0
1
5
.
[2
3
]
M
.
F
o
n
tan
i,
e
t
a
l
.
,
“
A
F
ra
m
e
w
o
r
k
f
o
r
De
c
isio
n
F
u
sio
n
in
Im
a
g
e
F
o
re
n
sic
s
Ba
se
d
o
n
De
m
p
ste
r
–
S
h
a
f
e
r
T
h
e
o
r
y
o
f
Ev
id
e
n
c
e
,
”
in
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
n
fo
rm
a
ti
o
n
F
o
re
n
sic
s a
n
d
S
e
c
u
rity
, v
ol
/i
ss
u
e
:
8
(
4
)
,
p
p
.
5
9
3
-
6
0
7
,
A
p
r
2
0
1
3
.
[2
4
]
T
.
H.
T
h
a
i,
e
t
a
l
.
,
“
J
P
EG
Qu
a
n
ti
z
a
ti
o
n
S
te
p
Esti
m
a
ti
o
n
a
n
d
Its
A
p
p
li
c
a
ti
o
n
s
t
o
Dig
it
a
l
Im
a
g
e
F
o
re
n
sic
s,
”
in
IE
EE
T
ra
n
sa
c
ti
o
n
s
o
n
In
f
o
rm
a
ti
o
n
Fo
r
e
n
sic
s a
n
d
S
e
c
u
rity
, v
ol
/i
ss
u
e
:
12
(
1
)
,
p
p
.
1
2
3
-
1
3
3
,
Ja
n
2
0
1
7
.
[2
5
]
G
.
S
.
N.
M
u
rth
y
a
n
d
T
.
V
e
e
rra
ju
,
“
A
n
o
v
e
l
a
p
p
ro
a
c
h
b
a
se
d
o
n
d
e
c
re
a
se
d
d
im
e
n
sio
n
a
n
d
re
d
u
c
e
d
g
ra
y
lev
e
l
ra
n
g
e
m
a
tri
x
f
e
a
tu
re
s
f
o
r
sto
n
e
tex
tu
re
c
las
si
f
ica
ti
o
n
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
mp
u
te
r
En
g
in
e
e
rin
g
,
v
o
l/
issu
e
:
7
(
5
),
p
p
.
2
5
0
2
,
2
0
1
7
.
[2
6
]
Re
d
d
y
,
e
t
a
l
.
,
“
Co
m
p
a
ra
ti
v
e
A
n
a
l
y
sis o
f
c
o
m
m
o
n
Ed
g
e
De
te
c
ti
o
n
A
l
g
o
rit
h
m
s
u
sin
g
P
re
-
p
ro
c
e
ss
in
g
T
e
c
h
n
iq
u
e
,”
In
t
.
J
.
El
e
c
tr.
Co
mp
u
t.
En
g
(
IJ
ECE
)
,
v
o
l/
issu
e
:
7
(
5
),
p
p
.
2
5
7
4
-
2
5
8
0
,
2
0
1
7
.
[2
7
]
K.
V
.
V
.
Ku
m
a
r
a
n
d
P
.
V.
V
.
K
ish
o
re
,
“
In
d
ia
n
Clas
sic
a
l
Da
n
c
e
M
u
d
ra
Clas
sif
ica
ti
o
n
Us
in
g
HO
G
F
e
a
tu
re
s
a
n
d
S
V
M
Clas
sif
ier
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
&
Co
mp
u
ter
En
g
i
n
e
e
rin
g
,
v
o
l/
issu
e
:
7
(
5
),
2
0
1
7
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
S
h
a
s
h
id
h
a
r
T
M
.,
Re
se
a
rc
h
S
c
h
o
lar,
V
isv
e
sv
a
ra
y
a
Tec
h
n
o
l
o
g
ica
l
Un
iv
e
rsit
y
Be
lag
a
v
i,
Ka
rn
a
tak
a
,
In
d
ia.
Cu
rre
n
tl
y
p
u
rs
u
in
g
P
h
D
u
n
d
e
r
RV
CE
(
V
T
U),
Ka
rn
a
tak
a
,
In
d
ia.
His
tea
c
h
in
g
e
x
p
e
rien
c
e
is
a
ro
u
n
d
1
1
y
e
a
rs.
Hisre
se
a
rc
h
a
re
a
is
S
ig
n
a
l
P
ro
c
e
ss
in
g
.
He
h
a
s
c
o
m
p
lete
d
h
isM
.
T
e
c
h
(
Dig
it
a
l
e
le
c
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
sy
ste
m
)
f
ro
m
P
ES
I
T
,
Be
n
g
a
lu
ru
,
Ka
rn
a
tak
a
,
In
d
ia.
A
lso
c
o
m
p
lete
d
B.
E.
(El
e
c
tro
n
ics
a
n
d
c
o
m
m
u
n
ica
ti
o
n
),
f
ro
m
S
J
M
IT
,
Ch
irad
u
rg
a
,
Ka
rn
a
tak
a
,
In
d
ia.
K
.
B
.
Ra
m
e
sh
,
A
s
so
c
iate
P
ro
f
e
ss
o
r
a
n
d
He
a
d
,
De
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
In
str
u
m
e
n
tatio
n
En
g
g
.
R
V
c
o
ll
e
g
e
o
f
En
g
in
e
e
ri
n
g
,
Be
n
g
a
lu
ru
,
Ka
rn
a
tak
a
,
In
d
i
a
.
He
h
a
s
c
o
m
p
lete
d
P
h
D
i
n
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
f
ro
m
Ku
v
e
m
p
u
Un
iv
e
rsit
y
.
He
h
a
sa
ro
u
n
d
tw
e
n
t
y
-
th
re
e
y
e
a
rs
(2
3
)
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
E
&
I
En
g
g
.
His
m
a
jo
r
re
se
a
rc
h
a
re
a
is
in
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
n
d
mi
n
o
r
re
se
a
rc
h
a
re
a
is i
n
Bi
o
me
d
ica
l
En
g
in
e
e
rin
g
/
Bi
o
in
fo
rm
a
t
ics
.
Evaluation Warning : The document was created with Spire.PDF for Python.