I
nte
rna
t
io
na
l J
o
urna
l o
f
Rec
o
nfig
ura
ble a
nd
E
m
bedd
e
d Sy
s
t
em
s
(
I
J
RE
S)
Vo
l.
10
,
No
.
3
,
N
o
v
em
b
e
r
2
0
2
1
,
p
p
.
2
30
~
2
3
6
I
SS
N
: 2
0
8
9
-
4
8
6
4
,
DOI
: 1
0
.
1
1
5
9
1
/ij
r
es
.
v
10
.i
3
.
p
p
2
30
-
2
3
6
230
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
r
es.ia
esco
r
e.
co
m
Im
a
g
e process
ing
using
a reconfig
u
ra
ble platform
:
P
re
-
pro
cess
ing
block
ha
rdwa
re archit
e
cture
Chira
nje
ev
i G
.
N
.
,
Su
bh
a
s
h
K
ulk
a
rni
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
E
n
g
i
n
e
e
rin
g
,
P
E
S
I
T
-
Ba
n
g
a
lo
re
S
o
u
th
Ca
m
p
u
s,
Ka
r
n
a
tak
a
,
In
d
ia
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
26
,
2
0
21
R
ev
is
ed
M
ay
2
7
,
2
0
21
Acc
ep
ted
J
u
n
22
,
2
0
21
Re
a
l
ti
m
e
ima
g
e
p
ro
c
e
ss
in
g
is
a
c
h
a
ll
e
n
g
i
n
g
tas
k
i
n
wh
ic
h
fe
tch
i
n
g
th
e
su
b
ima
g
e
re
q
u
ires
o
ffse
t
m
e
m
o
r
y
a
c
c
e
ss
a
p
a
rt
fro
m
c
o
re
p
r
o
c
e
ss
in
g
n
e
e
d
s.
Th
is
p
a
p
e
r
a
ims
a
t
o
v
e
rc
o
m
in
g
th
e
o
ffse
t
n
e
e
d
s
fo
r
m
e
m
o
ry
a
d
d
re
ss
i
n
g
i
n
p
re
-
p
ro
c
e
ss
in
g
b
lo
c
k
s.
A
n
o
t
h
e
r
fe
a
tu
re
o
f
th
is
p
re
se
n
t
wo
rk
is
to
a
p
p
e
n
d
in
g
th
e
ima
g
e
d
a
ta
with
c
u
st
o
m
ize
d
a
lg
o
rit
h
m
ic
re
e
q
u
i
p
m
e
n
ts
v
iz
d
u
p
li
c
a
ti
n
g
,
z
e
ro
p
a
d
d
i
n
g
.
F
o
r
K
x
K
k
e
rn
e
l
siz
e
,
t
h
e
p
r
o
p
o
se
d
h
a
rd
wa
re
a
rc
h
it
e
c
tu
re
c
a
n
b
e
p
ro
g
ra
m
m
e
d
to
fe
tch
K
p
i
x
e
ls
i
n
o
n
e
c
y
c
le,
re
d
u
c
in
g
t
h
e
d
a
ta
a
c
c
e
ss
t
ime
.
Re
su
lt
s
h
a
v
e
b
e
e
n
c
o
m
p
a
re
d
with
so
ftwa
re
-
b
a
se
d
p
r
o
c
e
ss
in
g
f
o
r
K
x
K
sp
a
ti
a
l
fil
terin
g
.
p
e
rfo
rm
a
n
c
e
in
d
ica
tes
sig
n
ifi
c
a
n
t
ti
m
in
g
imp
r
o
v
e
m
e
n
t
u
si
n
g
p
ro
p
o
se
d
p
re
-
p
r
o
c
e
ss
in
g
h
a
r
d
wa
re
b
lo
c
k
.
K
ey
w
o
r
d
s
:
B
lo
ck
m
em
o
r
y
ac
ce
s
s
B
o
u
n
d
ar
y
p
ad
d
i
n
g
Ker
n
el
ar
ch
itectu
r
e
Mu
lti
-
b
y
te
f
etch
in
g
Pre
-
p
r
o
ce
s
s
in
g
b
lo
c
k
R
ec
o
n
f
ig
u
r
ab
le
h
ar
d
war
e
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
C
h
ir
an
jeev
i G
.
N.
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
co
m
m
u
n
icatio
n
E
n
g
in
ee
r
in
g
PESI
T
-
B
an
g
alo
r
e
So
u
th
C
am
p
u
s
Af
f
iliated
to
Vis
v
eswar
ay
a
T
ec
h
n
o
lo
g
ical
Un
iv
er
s
ity
,
B
elg
au
m
B
an
g
alo
r
e,
Kar
n
atak
a
,
I
n
d
ia
E
m
ail: c
h
ir
an
jeev
ig
n
@
p
es.e
d
u
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ajo
r
ity
o
f
th
e
tim
e,
im
a
g
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
/ar
ch
itectu
r
e
[
1
]
,
[
2
]
p
er
f
o
r
m
b
est
wh
en
g
iv
e
n
s
p
ec
if
ic
ty
p
es
o
f
d
ata
as
in
p
u
ts
.
Ho
wev
er
,
in
th
e
v
ast
m
ajo
r
ity
o
f
in
s
tan
ce
s
,
th
e
in
p
u
t
p
ictu
r
e
f
ails
to
m
ee
t
cr
itical
r
eq
u
ir
em
en
ts
.
Prio
r
to
th
e
ap
p
licatio
n
-
s
p
ec
if
ic
p
r
o
c
ess
in
g
[
3
]
,
p
r
ep
r
o
c
ess
in
g
tak
e
s
p
lace
.
T
h
e
im
ag
e
s
to
r
ag
e
p
r
o
b
lem
is
a
s
ig
n
if
ican
t
is
s
u
e
in
im
ag
e
p
r
o
ce
s
s
in
g
.
Ma
n
y
im
ag
e
f
ile
f
o
r
m
ats
h
av
e
b
ee
n
d
e
v
elo
p
ed
o
v
er
t
h
e
y
ea
r
s
with
th
e
aim
o
f
r
ep
r
esen
tin
g
im
a
g
es
in
a
s
tr
ea
m
lin
ed
an
d
p
r
em
iu
m
m
an
n
er
th
at
ca
n
b
e
u
s
ed
o
n
a
v
ar
iety
o
f
p
latf
o
r
m
s
[
4
]
.
Acc
o
r
d
in
g
to
p
r
e
p
r
o
ce
s
s
in
g
,
d
if
f
e
r
en
t
im
ag
es
o
f
th
e
s
am
e
ty
p
e
c
an
h
a
v
e
a
d
if
f
er
en
t
s
ca
le
o
f
s
ig
n
al
in
ten
s
ities
.
T
h
e
o
p
er
atio
n
s
th
at
ar
e
u
s
u
ally
n
ee
d
ed
p
r
i
o
r
to
th
e
m
ain
d
ata
o
p
er
atio
n
s
in
I
P
[
5
]
co
r
e
ar
e
g
r
o
u
p
ed
as
p
r
ep
r
o
ce
s
s
in
g
f
u
n
ctio
n
s
.
H
ar
d
war
e
ar
ch
itectu
r
e
is
u
s
ed
as
th
e
in
it
ial
m
eth
o
d
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
b
lo
c
k
in
im
a
g
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
with
a
h
i
g
h
er
d
eg
r
ee
o
f
ac
c
u
r
ac
y
i
n
r
ea
d
in
g
p
i
x
el
v
alu
es
in
th
is
s
tu
d
y
.
As
a
r
esu
lt,
th
ese
im
ag
es
ar
e
p
r
o
ce
s
s
ed
in
s
u
ch
a
wa
y
th
at
th
ey
ca
n
b
e
u
s
ed
f
o
r
o
p
e
r
atio
n
s
,
r
ed
u
cin
g
d
ata
s
to
r
a
g
e
ac
ce
s
s
tim
e
[6
]
-
[
8
]
.
Pre
-
p
r
o
ce
s
s
in
g
o
f
ten
en
tails
th
e
elim
in
atio
n
o
f
u
n
n
ec
ess
ar
y
o
r
ir
r
elev
an
t r
eg
i
o
n
s
,
as we
ll a
s
th
e
en
h
a
n
ce
m
en
t o
f
co
n
t
r
ast an
d
s
er
v
ice
f
ea
tu
r
es lik
e
ze
r
o
p
a
d
d
in
g
.
Dig
ital
im
ag
es
co
n
tain
in
g
a
f
in
ite
s
et
o
f
im
ag
e
co
m
p
o
n
en
t
s
,
u
s
u
ally
k
n
o
wn
as
p
ix
els,
a
r
e
u
s
ed
to
d
is
p
lay
two
-
d
im
en
s
io
n
al
im
ag
es.
Dig
ital
im
ag
e
p
r
o
ce
s
s
in
g
allo
ws
f
o
r
th
e
r
etr
iev
al,
d
eliv
er
y
,
an
d
r
ep
r
esen
tatio
n
o
f
im
ag
e
d
ata
in
a
h
u
m
an
-
r
ea
d
ab
le
f
o
r
m
at
[
9
]
.
I
n
th
e
im
p
lem
e
n
tatio
n
ar
ea
s
o
f
im
ag
e
p
r
o
ce
s
s
in
g
,
a
v
ar
iety
o
f
tech
n
iq
u
es
ar
e
ap
p
lied
to
th
e
ch
o
s
e
n
im
ag
e
d
ata
s
et
f
o
r
im
ag
e
p
r
e
-
p
r
o
ce
s
s
in
g
.
T
h
is
wo
r
k
h
as
p
r
o
p
o
s
ed
a
tech
n
iq
u
e
to
im
p
r
o
v
e
m
em
o
r
y
r
ea
d
an
d
wr
ite
o
p
er
atio
n
s
,
wh
ich
ar
e
n
ee
d
ed
b
y
I
P
co
r
es.
T
h
e
ch
o
s
en
p
r
e
-
p
r
o
ce
s
s
in
g
h
ar
d
war
e
b
lo
c
k
h
as
p
r
o
v
en
to
b
e
th
e
m
o
s
t
ef
f
ec
tiv
e
m
eth
o
d
f
o
r
r
ea
d
in
g
p
ix
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4
8
6
4
I
ma
g
e
p
r
o
ce
s
s
in
g
u
s
in
g
a
r
ec
o
n
fig
u
r
a
b
le
p
la
tfo
r
m:
P
r
e
-
p
r
o
c
ess
in
g
b
lo
ck
h
a
r
d
w
a
r
e
… (
C
h
ir
a
n
jeev
i G
.
N
.
)
231
v
alu
es
in
g
r
o
u
p
o
r
co
n
ca
ten
at
ed
f
o
r
m
with
k
er
n
el
-
d
ef
in
ed
s
ize.
FP
GAs
h
av
e
b
ec
o
m
e
th
e
f
u
lly
in
d
ep
en
d
e
n
t
im
p
lem
en
tatio
n
f
r
am
ewo
r
k
f
o
r
a
n
u
m
b
er
o
f
co
m
p
u
ter
v
is
io
n
ap
p
licatio
n
s
d
u
e
to
ad
v
a
n
ce
m
en
ts
in
FP
GA
tech
n
o
lo
g
y
[
1
0
]
.
T
h
is
r
esear
ch
p
ap
er
is
o
r
g
an
i
ze
d
as
f
o
llo
ws.
Sectio
n
2
d
is
cu
s
s
es
ab
o
u
t
Pre
p
r
o
ce
s
s
in
g
B
lo
ck
s
in
I
m
ag
e
Pro
ce
s
s
in
g
,
Sectio
n
3
e
x
p
lain
s
clea
r
ly
ab
o
u
t
Pre
p
r
o
c
ess
in
g
b
lo
ck
Har
d
war
e
Ar
ch
it
ec
tu
r
e
u
s
ed
f
o
r
t
h
is
r
esear
ch
wo
r
k
.
Sectio
n
4
s
h
o
ws
Pre
-
p
r
o
ce
s
in
g
b
lo
ck
m
em
o
r
y
.
s
ec
tio
n
5
s
h
o
ws
E
x
p
er
im
e
n
tal
ev
alu
atio
n
o
v
er
r
ec
o
n
f
ig
u
r
ab
le
p
latf
o
r
m
ca
r
r
i
ed
th
r
o
u
g
h
o
u
t
th
e
p
r
ep
r
o
c
ess
in
g
p
r
o
ce
s
s
.
Fin
ally
,
s
ec
tio
n
6
co
n
clu
d
es
th
e
r
esear
ch
wo
r
k
with
its
f
in
d
in
g
s
.
2.
P
RE
P
RO
CE
SS
I
NG
B
L
O
C
K
S IN I
M
AG
E
P
RO
C
E
SS
I
NG
Pr
ep
ar
atio
n
o
f
d
ata
is
th
e
p
r
i
m
ar
y
g
o
al
o
f
m
o
s
t
p
r
ep
r
o
c
ess
i
n
g
s
y
s
tem
s
.
So
th
at
f
o
llo
win
g
b
lo
ck
s
ca
n
m
ak
e
o
p
tim
u
m
u
s
e
o
f
th
e
m
.
T
h
e
m
ain
aim
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
is
to
en
h
an
ce
t
h
e
im
ag
e'
s
q
u
ality
[
1
1
]
,
[
1
2
]
s
o
th
at
we
ca
n
p
r
o
p
er
l
y
an
aly
z
e
it.
W
e
ca
n
r
em
o
v
e
u
n
wan
t
ed
d
is
to
r
tio
n
s
[
1
3
]
an
d
im
p
r
o
v
e
s
o
m
e
f
ea
tu
r
es
(
r
ec
o
n
s
tr
u
ctio
n
an
d
r
eg
r
ess
io
n
)
[
1
4
]
,
[
1
5
]
th
at
a
r
e
ess
en
tial
f
o
r
th
e
a
p
p
licatio
n
we'
r
e
wo
r
k
in
g
o
n
b
y
p
r
ep
r
o
ce
s
s
in
g
.
T
h
o
s
e
ch
ar
ac
te
r
is
tics
ca
n
d
if
f
er
d
ep
en
d
i
n
g
o
n
th
e
ap
p
licatio
n
s
o
th
at
o
th
er
t
y
p
es
o
f
alg
o
r
it
h
m
s
[
1
6
]
ca
n
u
s
e
th
em
e
f
f
ec
tiv
ely
(
g
en
er
al
im
ag
e
p
r
o
ce
s
s
in
g
,
im
a
g
e
en
h
a
n
ce
m
en
t,
o
r
im
ag
e
an
a
ly
s
is
)
.
T
h
e
en
o
r
m
o
u
s
am
o
u
n
t
o
f
in
f
o
r
m
atio
n
n
ee
d
ed
t
o
d
ep
ict
im
ag
es
is
o
n
e
o
f
th
eir
m
o
s
t
d
is
tin
g
u
is
h
in
g
f
ea
tu
r
es (
ar
ch
itectu
r
e
u
s
in
g
V
ed
ic
co
m
p
u
tin
g
)
[
1
7
]
.
E
v
en
a
g
r
a
y
-
s
ca
le
im
ag
e
with
a
m
o
d
e
r
ate
r
eso
lu
tio
n
,
s
u
ch
as 5
1
2
b
y
5
1
2
,
r
eq
u
ir
es 5
1
2
*
5
1
2
*
8
=
2
*
1
0
6
b
its
to
r
ep
r
esen
t.
As a
r
esu
lt,
in
o
r
d
er
to
s
to
r
e
an
d
tr
an
s
m
it d
ig
ital
im
ag
es
(
u
s
in
g
XSG
b
lo
ck
s
)
[
1
8
]
,
s
o
m
e
ty
p
e
o
f
im
a
g
e
co
m
p
r
ess
io
n
an
d
im
ag
e
e
d
g
e
d
ete
ctio
n
[
1
9
]
o
r
th
e
u
s
e
o
f
p
r
e
-
p
r
o
c
ess
in
g
h
ar
d
war
e
is
r
eq
u
ir
ed
.
W
ith
in
FP
G
A
p
r
e
p
r
o
ce
s
s
in
g
s
u
b
-
s
y
s
tem
s
(
DSP
m
o
d
u
les)
[
2
0
]
,
al
g
o
r
ith
m
s
ev
o
lv
e
f
r
o
m
s
tan
d
ar
d
s
o
f
twar
e
-
s
u
itab
le
r
ep
r
esen
tatio
n
s
[
2
1
]
t
o
m
o
r
e
h
ar
d
war
e
-
f
r
ien
d
ly
o
n
es,
wh
ich
ca
n
co
m
p
letely
ex
p
lo
it
d
ata
p
ar
allelis
m
[
2
2
]
,
[
2
3
]
ac
r
o
s
s
ap
p
licatio
n
-
s
p
ec
if
ic
h
ar
d
w
ar
e
ar
ch
itectu
r
es(sig
n
al
an
d
v
id
eo
p
r
o
ce
s
s
in
g
ar
ch
itectu
r
e)
[
2
4
]
,
wh
ic
h
ar
e
o
f
ten
s
ig
n
if
ica
n
tly
d
i
f
f
er
en
t
f
r
o
m
th
e
co
n
v
en
tio
n
al
Vo
n
Ne
u
m
an
n
m
o
d
el,
s
u
ch
as d
ataf
lo
w
[
2
5
]
.
T
h
e
aim
o
f
th
e
ar
ch
itectu
r
e
is
to
p
r
e
p
ar
e
d
ata
a
n
d
m
ak
e
im
a
g
e
p
r
o
ce
s
s
in
g
ac
tiv
ities
ea
s
ier
[
2
6
]
,
[
2
7
]
.
T
h
e
g
en
er
al
s
tr
u
ctu
r
e
o
f
th
e
s
tr
ateg
y
s
u
g
g
ested
in
th
is
s
tu
d
y
is
d
ep
icted
in
Fig
u
r
e
1
.
T
h
e
im
ag
e
p
r
elim
in
ar
y
p
r
e
-
p
r
o
ce
s
s
in
g
m
eth
o
d
an
d
th
e
im
ag
e
s
cr
ee
n
in
g
alg
o
r
ith
m
a
r
e
th
e
f
o
u
n
d
atio
n
s
o
f
th
is
ar
tic
le.
F
ig
u
re
1
.
Arc
h
it
e
c
tu
re
o
f
th
e
w
o
r
k
3.
P
RE
P
RO
CE
SS
I
NG
B
L
O
C
K
M
E
M
O
RY
Desig
n
o
f
p
r
ep
r
o
ce
s
s
in
g
b
lo
c
k
m
em
o
r
y
,
two
co
n
s
tr
ain
ts
n
ee
d
to
b
e
tak
en
ca
r
e
f
r
o
m
th
e
u
s
er
en
d
.
T
h
e
f
ir
s
t
o
n
e
is
wr
itin
g
o
n
e
p
i
x
el
v
alu
e
wh
ich
is
o
f
o
n
e
b
y
te
in
to
th
e
m
em
o
r
y
at
ea
ch
cl
o
c
k
cy
cle
o
f
t
h
e
tar
g
et
d
ev
ice.
T
h
e
s
ec
o
n
d
o
n
e
is
th
e
s
ize
o
f
th
e
in
p
u
t
im
ag
e
(
ex
am
p
le:
5
1
2
*
5
1
2
)
.
T
h
e
m
ain
tar
g
et
we
ar
e
co
n
s
id
er
in
g
in
th
is
b
lo
c
k
m
e
m
o
r
y
is
f
le
x
ib
ilit
y
in
m
o
d
if
y
in
g
th
e
s
ize
o
f
k
er
n
el
d
u
r
i
n
g
r
ea
d
an
d
wr
ites
o
p
er
atio
n
s
.
T
h
e
ab
ilit
y
to
ch
o
o
s
e
th
e
k
er
n
el
s
ize
d
u
r
in
g
r
ea
d
o
p
er
atio
n
s
is
s
ee
n
a
s
a
b
en
ef
it
o
v
er
th
e
in
b
u
ilt
I
P
co
r
e
m
o
d
el.
A
d
etail
th
e
I
P c
o
r
e
ca
n
ac
ce
s
s
th
e
d
ata
in
ter
m
s
o
f
2
powers
b
it [
i.e
.
2
,
4
,
8
,
1
6
,
3
2
,
6
4
]
d
ata
d
u
r
in
g
r
ea
d
o
p
er
atio
n
,
b
u
t
in
th
e
p
r
o
p
o
s
ed
d
esig
n
it
ca
n
ac
ce
s
s
b
ased
o
n
th
e
k
e
r
n
el
r
e
q
u
ir
em
e
n
ts
an
d
n
o
t
r
eser
v
e
d
to
an
y
s
p
ec
if
ic
v
alu
es.
A
g
en
er
al
8
b
it
p
ix
el
v
alu
e
*
k
er
n
el
s
ize
is
th
e
d
ata
ac
ce
s
s
ed
d
u
r
in
g
r
ea
d
o
p
er
atio
n
.
3
.
1
.
Writ
e
m
o
de
As
in
d
icate
d
b
y
th
e
a
d
d
r
ess
p
o
in
ter
,
o
n
e
p
ix
el
o
f
d
ata
i
s
wr
itten
in
to
th
e
m
em
o
r
y
d
u
r
in
g
th
is
o
p
er
atio
n
with
r
eg
ar
d
to
th
e
cl
o
ck
cy
cle.
3
.
2
.
Rea
d
m
o
de
T
o
g
et
ar
o
u
n
d
th
e
f
ir
s
t
-
in
f
ir
s
t
-
out
(
FIFO
)
p
ar
a
d
ig
m
,
th
e
p
r
o
p
o
s
ed
h
ar
d
war
e
ar
c
h
itectu
r
e
ac
tiv
ates
r
ea
d
o
p
er
atio
n
s
‘
N'
tim
es d
ep
e
n
d
in
g
o
n
th
e
u
s
er
'
s
n
ee
d
s
.
T
h
e
r
ea
d
o
p
er
atio
n
iter
atio
n
is
ac
tiv
ated
b
ased
o
n
th
e
k
er
n
el
s
ize.
Fo
r
e
x
am
p
le,
if
th
e
k
er
n
el
s
ize
is
3
b
y
3
,
th
e
v
a
lu
es
f
r
o
m
th
r
ee
ad
jace
n
t
p
o
s
it
io
n
s
ar
e
r
ea
d
.
T
h
is
will
d
ec
id
e
wh
eth
er
en
o
u
g
h
d
ata
is
av
ailab
le
f
o
r
I
P
co
r
e
ar
ch
itectu
r
e.
T
h
e
u
s
er
m
u
s
t
s
p
ec
if
y
th
e
m
e
m
o
r
y
Pre
p
ro
ce
ss
i
n
g
b
l
o
ck
ha
rdw
a
re
I
n
p
u
t
:
a
n
i
m
a
g
e
u
s
u
a
l
l
y
co
m
i
n
g
fr
o
m
c
amer
a
O
u
t
p
u
t
:
a
n
i
m
ag
e
m
ea
n
t
t
o
b
e
a
s
o
u
r
ce
i
n
p
u
t
t
o
i
m
a
g
e
p
r
o
ce
ss
i
n
g
co
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
20
89
-
4
8
6
4
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
10
,
No
.
3
,
No
v
em
b
er
2
0
2
1
:
2
30
–
2
3
6
232
h
ar
d
war
e
lo
ca
tio
n
f
r
o
m
wh
ic
h
we
will
r
ea
d
.
T
h
at
is
,
th
e
r
ea
d
o
u
tp
u
t
is
ex
tr
ac
ted
as
a
c
o
n
ca
t
en
atio
n
o
f
th
r
ee
-
p
ix
el
d
ata
v
alu
es
h
ig
h
lig
h
ted
b
y
th
e
r
ea
d
p
o
i
n
ter
f
r
o
m
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
b
lo
ck
h
ar
d
war
e.
Fin
ally
,
d
ata
was
ac
ce
s
s
ed
s
im
u
ltan
eo
u
s
ly
f
r
o
m
all
th
r
ee
lo
ca
tio
n
s
.
3
.
3
.
Addi
t
io
na
l us
er
cho
ice
Ar
o
u
n
d
th
e
ed
g
es
o
f
an
im
ag
e,
im
ag
e
p
ad
d
in
g
ad
d
s
n
e
w
p
ix
els.
W
h
en
ad
v
an
ce
d
f
ilter
in
g
m
eth
o
d
s
ar
e
u
s
ed
,
th
e
b
o
r
d
er
p
r
o
v
id
es
s
p
ac
e
f
o
r
a
n
n
o
tatio
n
s
o
r
s
er
v
es
as
a
b
o
u
n
d
a
r
y
.
As
u
s
er
p
r
e
f
er
en
ce
i
n
p
u
ts
,
th
e
th
r
ee
s
ep
ar
ate
ca
s
e
s
tu
d
ies ar
e
u
s
ed
.
3
.
4
.
Dupl
ica
t
e
mo
de
T
wo
r
o
ws
an
d
two
co
lu
m
n
s
h
av
e
b
ee
n
ad
d
e
d
.
T
h
e
f
ir
s
t
r
o
w
'
s
an
d
last
r
o
w
'
s
p
ix
el
v
alu
es
ar
e
co
p
ied
f
o
r
th
e
n
ew
r
o
w
th
at
c
o
m
es
b
ef
o
r
e
t
h
e
f
ir
s
t
r
o
w
an
d
af
ter
th
e
last
r
o
w,
r
esp
ec
tiv
ely
w
h
ich
is
in
d
icate
d
in
Fig
u
r
e
2
.
Similar
ly
,
th
e
v
alu
es
o
f
th
e
f
ir
s
t
an
d
las
t
co
lu
m
n
s
o
f
th
e
o
r
ig
in
al
im
ag
e
a
r
e
co
p
ied
to
th
e
n
ew
co
lu
m
n
s
.
L
ea
d
in
g
t
o
th
e
ca
s
c
ad
in
g
o
f
two
a
d
d
itio
n
al
r
o
ws
an
d
two
a
d
d
itio
n
al
c
o
lu
m
n
s
,
th
e
im
ag
e
w
o
u
ld
b
e
5
1
4
b
y
5
1
4
af
ter
d
u
p
licatio
n
.
3
.
5
.
Z
er
o
pa
dd
ing
Ad
d
itio
n
al
r
o
ws
ar
e
ad
d
e
d
,
wi
th
all
p
ix
el
v
al
u
es
s
et
to
ze
r
o
wh
ich
is
in
d
icate
d
in
Fig
u
r
e
3
.
Similar
ly
,
co
lu
m
n
s
with
a
p
ix
el
v
alu
e
o
f
ze
r
o
ar
e
in
tr
o
d
u
ce
d
.
3
.
6
.
No
n dup
lica
t
e
mo
de
Fo
r
I
P
co
r
e
o
p
er
atio
n
s
,
f
u
n
cti
o
n
with
ex
is
tin
g
/ig
n
o
r
e
th
e
b
o
u
n
d
a
r
ies
in
th
is
ca
s
e
m
o
d
el.
I
g
n
o
r
e
th
e
v
alu
e
o
f
th
e
ed
g
e
p
ix
el
an
d
co
m
p
u
te
f
o
r
th
o
s
e
p
ix
els
th
at
h
av
e
all
o
f
th
eir
n
eig
h
b
o
r
s
wh
ich
ar
e
h
ig
h
lig
h
te
d
in
Fig
u
r
e
4
.
F
ig
u
r
e
2
.
Du
p
licate
m
o
d
e:
Or
i
g
in
al
im
ag
e
v
/s
with
p
a
d
d
in
g
ex
tr
a
r
o
w
a
n
d
co
l
F
ig
u
r
e
3
.
Z
e
r
o
p
a
d
d
in
g
m
o
d
es:
Or
ig
in
al
im
ag
e
v
/s
with
p
a
d
d
in
g
ex
tr
a
r
o
w
an
d
co
l f
illed
wi
th
ze
r
o
Fig
u
r
e
4
.
No
n
-
Du
p
licate
m
o
d
e:
R
em
ain
s
s
am
e
as o
r
ig
in
al
im
ag
e
(
n
o
ad
d
itio
n
al
r
o
w
a
n
d
c
o
l)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4
8
6
4
I
ma
g
e
p
r
o
ce
s
s
in
g
u
s
in
g
a
r
ec
o
n
fig
u
r
a
b
le
p
la
tfo
r
m:
P
r
e
-
p
r
o
c
ess
in
g
b
lo
ck
h
a
r
d
w
a
r
e
… (
C
h
ir
a
n
jeev
i G
.
N
.
)
233
4.
E
XP
E
R
I
M
E
N
T
A
L
E
VA
L
U
AT
I
O
N
O
V
E
R
RE
CO
NF
I
G
URAB
L
E
P
L
AT
F
O
R
M
On
an
FP
GA,
h
ar
d
war
e
d
esig
n
s
tr
ateg
ies
s
u
ch
as
p
ar
allelis
m
an
d
p
ip
elin
in
g
ar
e
f
ea
s
ib
le,
wh
ich
ar
e
n
o
t
p
o
s
s
ib
le
in
d
ed
icate
d
DSP
m
o
d
u
les.
T
h
e
u
s
e
o
f
r
ec
o
n
f
ig
u
r
ab
le
h
ar
d
war
e
to
im
p
lem
e
n
t
im
ag
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
r
e
d
u
ce
s
tim
e
-
to
-
m
ar
k
et
co
s
ts
,
allo
ws
f
o
r
r
a
p
id
p
r
o
to
ty
p
in
g
o
f
c
o
m
p
lex
alg
o
r
ith
m
s
,
an
d
s
im
p
lifie
s
d
eb
u
g
g
in
g
an
d
v
er
i
f
icatio
n
.
As
a
r
esu
lt,
FP
GAs
ar
e
an
ex
ce
llen
t
alter
n
ativ
e
f
o
r
r
ea
l
-
tim
e
im
ag
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
.
Ver
ilo
g
co
d
i
n
g
is
u
s
ed
in
th
is
r
esear
ch
p
ap
er
to
b
u
ild
th
e
p
r
e
p
r
o
ce
s
s
in
g
h
ar
d
war
e
ar
ch
itectu
r
e
.
T
h
e
v
e
r
if
icatio
n
o
f
f
u
n
ctio
n
a
lity
is
ca
r
r
ied
o
u
t
o
n
r
ec
o
n
f
i
g
u
r
ab
le
h
ar
d
war
e
with
th
e
h
elp
o
f
d
esig
n
f
lo
w
d
iag
r
am
wh
ich
is
s
h
o
wn
in
Fi
g
u
r
e
5.
T
h
is
is
th
e
ex
ter
n
al
v
iew
th
a
t
is
in
clu
d
ed
in
th
e
5
b
y
5
k
er
n
el
s
h
o
wn
in
Fig
u
r
e
6
.
T
h
e
o
u
tp
u
t
is
in
d
icate
d
as
4
0
b
its
in
th
is
ca
s
e.
I
n
o
n
e
clo
c
k
cy
cl
e,
th
at'
s
5
tim
es
th
e
8
-
b
it
p
ix
el
v
alu
e
wh
ich
d
ep
icts
in
t
h
e
ab
o
v
e
f
i
g
u
r
e.
I
t is h
av
in
g
ac
ce
s
s
to
all
th
e
ex
ter
n
al
in
p
u
t
an
d
o
u
tp
u
t
p
in
s
.
Fig
u
r
e
5
.
Desig
n
f
lo
w
f
o
r
p
r
e
p
r
o
ce
s
s
in
g
ar
ch
itectu
r
e
o
f
th
e
w
o
r
k
Fig
u
r
e
6
.
E
x
ter
n
al
v
iew
f
o
r
p
r
ep
r
o
ce
s
s
in
g
ar
ch
itectu
r
e
o
f
t
h
e
wo
r
k
Fig
u
r
e
7
d
ep
icts
,
R
eg
is
ter
-
tr
an
s
f
er
lev
el
(
R
T
L
)
is
a
d
esig
n
ab
s
tr
ac
tio
n
f
o
r
m
o
d
elin
g
a
s
y
n
ch
r
o
n
o
u
s
d
ig
ital
cir
cu
it
in
ter
m
s
o
f
th
e
f
lo
w
o
f
d
ig
ital
s
ig
n
als
(
d
a
ta)
b
etwe
en
h
a
r
d
war
e
r
eg
is
ter
s
an
d
th
e
lo
g
ica
l
o
p
er
atio
n
s
p
e
r
f
o
r
m
ed
o
n
th
o
s
e
s
ig
n
als in
d
ig
ital c
ir
cu
it d
esig
n
.
I
n
p
u
t
i
m
a
g
e
5
1
2
b
y
5
1
2
B
l
o
c
k
m
e
mo
r
y
B
a
se
d
o
n
k
e
r
n
e
l
si
z
e
C
h
o
o
se
[
(
3
*
3
)
,
(
5
*
5
)
….
.
(
K
*
K
)
]
Wr
i
t
e
R
e
a
d
A
d
d
i
t
i
o
n
a
l
u
ser
c
h
o
i
c
e
0
0
:
D
u
p
l
i
c
a
t
i
o
n
0
1
:
Z
e
r
o
p
a
d
d
i
n
g
1
0
:
N
o
n
d
u
p
l
i
c
a
t
i
n
g
C
h
o
i
c
e
o
f
d
i
f
f
e
r
e
n
t
o
p
e
r
a
t
i
o
n
s
i
n
I
P
c
o
r
e
[
S
mo
o
t
h
,
B
l
u
r
,
E
n
h
a
n
c
e
]
O
u
t
p
u
t
i
ma
g
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
20
89
-
4
8
6
4
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
10
,
No
.
3
,
No
v
em
b
er
2
0
2
1
:
2
30
–
2
3
6
234
T
h
e
f
in
d
in
g
s
f
r
o
m
Fig
u
r
e
8
,
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
o
f
FP
GA
-
b
ased
r
ec
o
n
f
ig
u
r
ab
le
s
y
s
tem
s
in
im
ag
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
,
d
em
o
n
s
tr
atin
g
a
s
ig
n
if
ican
t
s
p
ee
d
u
p
o
v
er
s
o
f
twar
e
v
er
s
io
n
s
as
o
p
er
atio
n
s
b
ec
o
m
e
m
o
r
e
co
m
p
le
x
.
T
h
en
,
u
s
in
g
o
u
r
s
ch
em
e,
we
will
b
e
ab
le
to
r
elax
th
e
n
u
m
b
e
r
o
f
o
p
er
atio
n
s
in
a
r
ea
l
-
tim
e
ap
p
licatio
n
,
en
a
b
lin
g
u
s
to
in
co
r
p
o
r
ate
m
o
r
e
co
m
p
lex
al
g
o
r
ith
m
s
.
Fig
u
r
e
7
.
R
T
L
d
esig
n
f
o
r
p
r
ep
r
o
ce
s
s
in
g
ar
ch
itectu
r
e
o
f
th
e
w
o
r
k
Fig
u
r
e
8
.
Utilizatio
n
r
e
p
o
r
t f
o
r
p
r
ep
r
o
ce
s
s
in
g
ar
ch
itectu
r
e
o
f
th
e
wo
r
k
5.
RE
SU
L
T
S
A
ND
D
IS
CU
SS
I
O
N
C
o
n
v
o
lu
tio
n
is
a
g
en
er
al
-
p
u
r
p
o
s
e
im
ag
e
f
ilter
ef
f
ec
t
th
at
d
eter
m
in
es
th
e
v
alu
e
o
f
th
e
ce
n
te
r
p
ix
el
b
y
ad
d
in
g
th
e
weig
h
ted
v
alu
es
o
f
all
its
n
eig
h
b
o
r
s
.
T
h
e
p
r
o
d
u
ct
o
f
co
n
v
o
lu
tio
n
o
f
5
1
2
*
5
1
2
im
ag
e
m
atr
ix
with
k
er
n
el
o
f
[
(
3
*
3
)
,
(
5
*
5
)
…
(
K*
K)
]
is
a
n
ew
m
o
d
if
ied
f
ilter
ed
im
ag
e.
Ov
er
lap
th
e
k
er
n
el
o
n
to
p
o
f
th
e
im
ag
e,
ca
lcu
late
th
e
p
r
o
d
u
ct
o
f
th
e
m
u
tu
ally
o
v
e
r
lap
p
in
g
p
ix
els
an
d
th
eir
s
u
m
in
ea
c
h
ca
s
e,
an
d
th
e
r
esu
lt
will
b
e
th
e
v
alu
e
o
f
t
h
e
o
u
t
p
u
t p
ix
el
at
th
a
t p
ar
ticu
lar
lo
ca
tio
n
Fig
u
r
e
9
d
ep
icts
in
p
u
t
p
ix
els
b
ein
g
wr
itten
in
to
m
em
o
r
y
an
d
ac
ce
s
s
ed
th
r
o
u
g
h
a
r
ea
d
o
p
e
r
atio
n
;
th
e
ab
o
v
e
r
esu
lts
ar
e
f
o
r
a
3
b
y
3
m
atr
ix
k
er
n
el.
I
n
o
th
er
wo
r
d
s
,
it'
s
tu
r
n
in
g
o
n
t
h
e
co
n
s
ec
u
tiv
e
r
ea
d
o
p
er
atio
n
th
r
ee
tim
es in
a
r
o
w.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
I
SS
N:
2089
-
4
8
6
4
I
ma
g
e
p
r
o
ce
s
s
in
g
u
s
in
g
a
r
ec
o
n
fig
u
r
a
b
le
p
la
tfo
r
m:
P
r
e
-
p
r
o
c
ess
in
g
b
lo
ck
h
a
r
d
w
a
r
e
… (
C
h
ir
a
n
jeev
i G
.
N
.
)
235
Fig
u
r
e
9
.
Simu
latio
n
r
esu
lts
f
o
r
p
r
ep
r
o
ce
s
s
in
g
ar
ch
itectu
r
e
o
f
th
e
wo
r
k
6.
CO
NCLU
SI
O
N
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
u
s
ed
in
th
is
s
tu
d
y
aid
s
in
th
e
a
cc
ess
o
f
d
ata
r
eq
u
ir
e
d
b
y
t
h
e
I
P c
o
r
e
an
d
th
e
en
h
a
n
ce
m
en
t
o
f
im
ag
e
q
u
ality
b
y
th
e
u
s
e
o
f
v
ar
i
o
u
s
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
s
.
T
h
e
f
in
d
in
g
s
a
r
e
an
aly
ze
d
an
d
ch
ec
k
e
d
with
a
s
tan
d
ar
d
r
ec
o
n
f
ig
u
r
ab
le
p
latf
o
r
m
(
Z
y
n
q
b
o
a
r
d
)
,
a
n
d
th
e
c
o
n
s
is
ten
cy
in
ter
m
s
o
f
h
ar
d
war
e
u
tili
za
tio
n
is
also
e
v
alu
ated
(
ar
ea
)
T
h
e
f
o
cu
s
o
f
th
is
r
esear
ch
is
to
co
n
ce
n
tr
a
te
o
n
s
elec
tin
g
th
e
ap
p
r
o
p
r
iate
m
em
o
r
y
o
p
er
atio
n
s
,
s
u
ch
as
m
u
ltip
le
r
ea
d
an
d
w
r
ite
tech
n
iq
u
es,
as
wel
l
as
tak
i
n
g
in
t
o
ac
co
u
n
t
t
h
e
u
s
er
'
s
ch
o
ice
o
f
k
er
n
el
s
ize
as
a
p
r
im
ar
y
in
p
u
t.
No
t
o
n
ly
d
o
e
s
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
tech
n
i
q
u
e
m
in
im
ize
m
em
o
r
y
ac
ce
s
s
tim
e.
T
h
e
in
f
o
r
m
atio
n
g
ath
er
e
d
as
a
r
esu
lt
o
f
t
h
is
p
r
o
ce
s
s
co
u
ld
b
e
u
s
ef
u
l
in
f
u
r
th
er
in
g
th
is
s
tu
d
y
.
FP
GA
s
as
d
e
p
lo
y
m
e
n
t
r
ec
o
n
f
ig
u
r
a
b
le
p
latf
o
r
m
s
f
o
r
h
ig
h
-
lev
el
im
ag
e
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
in
clu
d
e
ef
f
icien
t m
ap
p
i
n
g
o
f
h
ig
h
-
lev
e
l d
escr
ip
tio
n
s
o
f
im
a
g
e
f
r
am
es
to
lo
w
-
lev
el
m
em
o
r
y
s
y
s
tem
s
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
wo
r
k
is
b
ein
g
d
o
n
e
at
t
h
e
PESI
T
B
an
g
alo
r
e
So
u
th
C
am
p
u
s
'
s
R
esear
ch
C
en
ter
o
f
E
lectr
o
n
ics
an
d
C
o
m
m
u
n
icatio
n
s
,
w
h
ich
is
r
ec
o
g
n
ized
a
n
d
af
f
iliate
d
b
y
Vis
v
esv
ar
ay
a
T
ec
h
n
o
l
o
g
ical
Un
iv
er
s
ity
B
elag
av
i,
Kar
n
atak
a,
I
n
d
ia.
RE
F
E
R
E
NC
E
S
[1
]
T.
F.
S
m
it
h
a
n
d
M
.
S
.
Wate
rm
a
n
,
"
I
d
e
n
ti
fica
ti
o
n
o
f
c
o
m
m
o
n
m
o
lec
u
lar
su
b
se
q
u
e
n
c
e
’s,
"
J
o
u
rn
a
l
o
f
M
o
lec
u
l
a
r
Bi
o
lo
g
y
(J
M
B)
,
v
o
l.
1
4
7
,
n
o
.
1
,
p
p
.
1
9
5
–
1
9
7
,
1
9
8
1
,
d
o
i:
1
0
.
1
0
1
6
/
0
0
2
2
-
2
8
3
6
(8
1
)9
0
0
8
7
-
5.
[2
]
R.
Nik
h
il
,
"
Bl
u
e
sp
e
c
sy
ste
m
v
e
ri
lo
g
:
Eff
icie
n
t
,
c
o
rre
c
t
RTL
fro
m
h
ig
h
le
v
e
l
sp
e
c
ifi
c
a
ti
o
n
s,
"
Pro
c
e
e
d
in
g
s.
S
e
c
o
n
d
ACM
a
n
d
IEE
E
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Fo
rm
a
l
M
e
th
o
d
s
a
n
d
M
o
d
e
ls
fo
r
Co
-
De
sig
n
,
2
0
0
4
.
M
E
M
OCO
DE
'
0
4
.
,
2
0
0
4
,
p
p
.
6
9
-
7
0
,
d
o
i:
1
0
.
1
1
0
9
/M
EM
COD
.
2
0
0
4
.
1
4
5
9
8
1
8
.
[3
]
R.
S
h
o
u
p
,
"
P
a
ra
m
e
teriz
e
d
c
o
n
v
o
l
u
ti
o
n
fil
terin
g
in
a
f
ield
p
r
o
g
ra
m
m
a
b
le
g
a
te
a
rra
y
i
n
terv
a
l
,
"
T
e
c
h
n
i
c
a
l
Rep
o
rt
,
P
a
l
o
Alto
,
Ca
li
f
o
rn
ia,
1
9
9
3
.
[4
]
H.
S
.
Ne
o
h
a
n
d
A.
Ha
z
a
n
c
h
u
k
,
"
Ad
a
p
ti
v
e
e
d
g
e
d
e
tec
ti
o
n
f
o
r
re
a
l
-
ti
m
e
v
i
d
e
o
p
ro
c
e
ss
in
g
u
si
n
g
F
P
G
As
,
"
Glo
b
a
l
S
ig
n
a
l
Pro
c
e
ss
in
g
,
v
o
l.
7
,
n
o
.
3
,
p
p
.
2
-
3
,
2
0
0
4
[5
]
J.
Wan
g
,
S
.
Z
h
o
n
g
,
L.
Ya
n
a
n
d
Z.
Ca
o
,
"
An
e
m
b
e
d
d
e
d
sy
ste
m
-
on
-
c
h
ip
a
rc
h
it
e
c
t
u
re
fo
r
r
eal
-
ti
m
e
v
isu
a
l
d
e
tec
ti
o
n
a
n
d
m
a
tch
i
n
g
,
"
i
n
I
EE
E
T
ra
n
s
a
c
t
io
n
s
o
n
Circ
u
it
s
a
n
d
S
y
ste
ms
fo
r
Vi
d
e
o
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
2
4
,
n
o
.
3
,
p
p
.
5
2
5
-
5
3
8
,
M
a
rc
h
2
0
1
4
,
d
o
i:
1
0
.
1
1
0
9
/T
CS
V
T.
2
0
1
3
.
2
2
8
0
0
4
0
.
[6
]
P
.
M
o
n
d
a
l,
P
.
K.
Biswa
l
a
n
d
S
.
Ba
n
e
rjee
,
"
F
P
G
A
b
a
se
d
a
c
c
e
le
ra
ted
3
D
a
ffin
e
tran
sfo
rm
fo
r
r
e
a
l
-
ti
m
e
ima
g
e
p
ro
c
e
ss
in
g
a
p
p
l
ica
ti
o
n
s,
"
C
o
mp
u
ter
s
&
El
e
c
trica
l
E
n
g
in
e
e
rin
g
,
v
o
l.
4
9
,
p
p
.
6
9
-
8
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j.
c
o
m
p
e
lec
e
n
g
.
2
0
1
5
.
0
4
.
0
1
7
.
[7
]
E.
Ka
d
ric,
D.
Lak
a
ta
a
n
d
A.
De
h
o
n
,
"
Im
p
a
c
t
o
f
p
a
ra
ll
e
li
sm
a
n
d
m
e
m
o
ry
a
rc
h
it
e
c
tu
re
o
n
F
P
G
A
c
o
m
m
u
n
i
c
a
ti
o
n
e
n
e
rg
y
,
"
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
Rec
o
n
fi
g
u
ra
b
le
T
e
c
h
n
o
l
o
g
y
a
n
d
S
y
ste
ms
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
1
-
2
3
,
2
0
1
6
,
d
o
i:
1
0
.
1
1
4
5
/
2
8
5
7
0
5
7
.
[8
]
I.
Ka
u
r,
L.
R
o
h
il
la,
A.
Na
g
p
a
l
,
B
.
P
a
n
d
e
y
,
a
n
d
S
.
S
h
a
rm
a
,
"
Diffe
r
e
n
t
c
o
n
fig
u
ra
ti
o
n
o
f
l
o
w
-
p
o
we
r
m
e
m
o
ry
d
e
sig
n
u
sin
g
c
a
p
a
c
it
a
n
c
e
sc
a
li
n
g
o
n
2
8
-
n
m
field
-
p
r
o
g
ra
m
m
a
b
le
g
a
te
a
rr
a
y
,
"
i
n
S
y
ste
m
a
n
d
Arc
h
it
e
c
tu
re
,
S
.
K
.
M
u
tt
o
o
S
p
rin
g
e
r:
Ne
w Yo
r
k
,
2
0
1
8
,
p
p
.
1
5
1
–
1
6
1
.
[9
]
L.
P
e
z
z
a
ro
ss
a
,
A.
T.
Kriste
n
se
n
,
M
.
S
c
h
o
e
b
e
rl
a
n
d
J
.
S
p
a
rsø
,
"
Us
i
n
g
d
y
n
a
m
ic
p
a
rti
a
l
re
c
o
n
fig
u
ra
ti
o
n
o
f
F
P
G
As
in
re
a
l
-
ti
m
e
sy
ste
m
s,
"
M
icr
o
p
ro
c
e
ss
o
rs
a
n
d
M
icr
o
sy
ste
ms
,
v
o
l
.
6
1
,
1
9
8
-
2
0
6
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/
j.
m
icp
ro
.
2
0
1
8
.
0
5
.
0
1
7
.
[1
0
]
S
.
D.
Bro
w
n
,
R.
J.
F
ra
n
c
is,
J.
R
o
se
,
a
n
d
Z.
G.
Vra
n
e
sic
,
Fi
e
ld
Pro
g
ra
mm
a
b
le
Ga
te
Arra
y
s
,
v
o
l
.
1
8
0
,
S
p
ri
n
g
e
r
S
c
ien
c
e
&
Bu
sin
e
ss
M
e
d
ia
,
1
9
9
2
.
[1
1
]
S
.
Hira
i
,
M
.
Zak
o
u
ji
,
T.
Tsu
b
o
i
,
"
Im
p
lem
e
n
ti
n
g
ima
g
e
p
r
o
c
e
ss
in
g
a
lg
o
rit
h
m
s
o
n
F
P
G
A
-
b
a
se
d
re
a
lt
ime
v
isio
n
sy
ste
m
,
"
Pro
c
.
1
1
th
S
y
n
t
h
e
sis
a
n
d
S
y
ste
m
In
teg
ra
ti
o
n
o
f
M
ix
e
d
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
(
S
AS
I
M
I
2
0
0
3
)
,
Hiro
sh
ima
,
Ap
r
.
2
0
0
3
,
p
p
.
3
7
8
-
3
8
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
20
89
-
4
8
6
4
I
n
t J Reco
n
f
ig
u
r
a
b
le
&
E
m
b
ed
d
ed
Sy
s
t
,
Vo
l.
10
,
No
.
3
,
No
v
em
b
er
2
0
2
1
:
2
30
–
2
3
6
236
[1
2
]
C.
To
rre
s
-
Hu
it
z
il
a
n
d
M
.
A.
Nu
ñ
o
-
M
a
g
a
n
d
a
,
"
Are
a
ti
m
e
e
ff
icie
n
t
imp
lem
e
n
tatio
n
o
f
l
o
c
a
l
a
d
a
p
ti
v
e
ima
g
e
th
re
sh
o
l
d
i
n
g
in
re
c
o
n
fi
g
u
ra
b
le
h
a
rd
wa
re
,"
AC
M
S
IGAR
CH
C
o
mp
u
ter
Arc
h
it
e
c
tu
re
Ne
ws
,
v
o
l
.
4
2
,
n
o
.
4
,
p
p
.
3
3
–
3
8
,
2
0
1
4
,
d
o
i:
1
0
.
1
1
4
5
/
2
6
9
3
7
1
4
.
2
6
9
3
7
2
1
.
[1
3
]
Jo
h
n
C.
Ru
ss
,
T
h
e
ima
g
e
p
ro
c
e
ss
in
g
h
a
n
d
b
o
o
k
,
6
th
ed
,
CRC P
re
ss
,
2
0
1
1
[1
4
]
A.
S
u
n
g
h
e
e
th
a
,
R.
S
h
a
rm
a
R.
,
"
A
n
o
v
e
l
Ca
p
sN
e
t
b
a
se
d
ima
g
e
re
c
o
n
stru
c
ti
o
n
a
n
d
re
g
re
ss
io
n
a
n
a
ly
sis
,
"
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
Ima
g
e
Pro
c
e
ss
in
g
(J
II
P)
,
v
o
l.
2
,
n
o
.
0
3
,
1
5
6
-
1
6
4
,
2
0
2
0
,
d
o
i:
1
0
.
3
6
5
4
8
/
ji
ip
.
2
0
2
0
.
3
.
0
0
6
.
[1
5
]
Zai
n
a
lab
e
d
in
Na
v
a
b
i,
Dig
it
a
l
d
e
si
g
n
a
n
d
imp
lem
e
n
ta
ti
o
n
wit
h
fi
e
ld
p
ro
g
r
a
mm
a
b
le
d
e
v
ice
s
,
USA:
S
p
r
in
g
e
r,
2
0
1
1
.
[1
6
]
P
.
L
y
sa
g
h
t,
B
.
Bl
o
d
g
e
t,
J.
M
a
so
n
,
J.
Yo
u
n
g
a
n
d
B
.
Bri
d
g
f
o
rd
,
"
I
n
v
it
e
d
p
a
p
e
r
:
En
h
a
n
c
e
d
a
rc
h
i
tec
tu
re
s,
d
e
sig
n
m
e
th
o
d
o
lo
g
ies
a
n
d
CAD
t
o
o
ls
fo
r
d
y
n
a
m
ic
re
c
o
n
fi
g
u
ra
ti
o
n
o
f
Xil
in
x
F
P
G
As
,
"
2
0
0
6
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Fi
e
ld
Pro
g
ra
mm
a
b
le L
o
g
ic
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
2
0
0
6
,
p
p
.
1
-
6
,
d
o
i:
1
0
.
1
1
0
9
/
F
P
L.
2
0
0
6
.
3
1
1
1
8
8
.
[1
7
]
G
.
N.
Ch
iran
jee
v
i
a
n
d
S
.
Ku
l
k
a
rn
i,
"
P
i
p
e
li
n
e
a
rc
h
it
e
c
tu
re
f
o
r
N=
K*
2
L
Bit
m
o
d
u
lar
ALU:
Ca
se
stu
d
y
b
e
twe
e
n
c
u
rre
n
t
g
e
n
e
ra
ti
o
n
c
o
m
p
u
ti
n
g
a
n
d
v
e
d
ic
c
o
m
p
u
ti
n
g
,
"
2
0
2
1
6
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
fo
r
Co
n
v
e
rg
e
n
c
e
in
T
e
c
h
n
o
l
o
g
y
(I
2
CT
)
,
2
0
2
1
,
p
p
.
1
-
4
,
d
o
i:
1
0
.
1
1
0
9
/I
2
CT
5
1
0
6
8
.
2
0
2
1
.
9
4
1
7
9
1
7
.
[1
8
]
B.
S
.
Du
r
g
a
k
e
ri
a
n
d
G
.
N.
Ch
iran
jee
v
i,
"
Im
p
lem
e
n
ti
n
g
ima
g
e
p
ro
c
e
ss
in
g
a
lg
o
r
it
h
m
s
u
si
n
g
Xi
li
n
x
sy
ste
m
g
e
n
e
ra
to
r
with
re
a
l
ti
m
e
c
o
n
stra
i
n
ts,
"
2
0
1
9
4
th
I
n
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Rec
e
n
t
T
re
n
d
s
o
n
El
e
c
tro
n
ic
s,
In
fo
rm
a
t
io
n
,
Co
mm
u
n
ica
ti
o
n
&
T
e
c
h
n
o
l
o
g
y
(R
T
EICT
)
,
2
0
1
9
,
p
p
.
2
3
0
-
2
3
4
,
d
o
i:
1
0
.
1
1
0
9
/R
TE
ICT4
6
1
9
4
.
2
0
1
9
.
9
0
1
6
9
6
2
.
[1
9
]
S.
Ra
v
i,
B.
A
.
Ra
h
im
,
F
.
s
h
a
ik
,
"
F
P
G
A
b
a
se
d
d
e
sig
n
a
n
d
imp
le
m
e
n
tatio
n
o
f
ima
g
e
e
d
g
e
d
e
tec
ti
o
n
u
si
n
g
Xili
n
x
sy
ste
m
g
e
n
e
ra
to
r
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
in
e
e
rin
g
T
re
n
d
s
a
n
d
T
e
c
h
n
o
l
o
g
y
(IJ
ET
T
)
,
v
o
l.
4
,
n
o
.
1
0
,
p
p
.
4
6
5
7
-
4
6
6
0
,
Oc
t
2
0
1
3
.
[2
0
]
N
.
P
.
Ra
u
t
a
n
d
A.
V.
G
o
k
h
a
le,
"
F
P
G
A
imp
lem
e
n
tatio
n
f
o
r
im
a
g
e
p
r
o
c
e
ss
in
g
a
lg
o
r
it
h
m
s
u
sin
g
Xili
n
x
sy
ste
m
g
e
n
e
ra
t
or
,
"
IOS
R
J
o
u
rn
a
l
o
f
V
L
S
I
a
n
d
S
ig
n
a
lP
r
o
c
e
ss
in
g
,
v
o
l.
2
,
n
o
.
4
,
p
p
.
2
6
-
36
,
2
0
1
3
,
d
o
i:
1
0
.
9
7
9
0
/
4
2
0
0
-
0
2
4
2
6
3
6
.
[2
1
]
V.
C
.
De
e
p
th
i
a
n
d
P
.
S
.
P
ra
d
a
d
,
"
M
e
d
ica
l
ima
g
e
fu
si
o
n
u
si
n
g
X
il
in
x
sy
ste
m
g
e
n
e
ra
to
r
in
F
P
G
A,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
VL
S
I
S
y
ste
m De
sig
n
a
n
d
C
o
mm
u
n
ica
ti
o
n
S
y
ste
ms
,
v
o
l
.
4
,
no
.
1
0
,
p
p
.
0
9
9
0
-
0
9
9
3
,
2
0
1
6
.
[2
2
]
C
.
G
.
Na
r
a
sim
h
a
m
u
rth
y
a
n
d
S
.
Ku
lk
a
rn
i
,
"
Va
li
d
a
ti
o
n
o
f
th
e
F
P
G
A
-
b
a
s
e
d
ima
g
e
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s
u
sin
g
th
e
e
fficie
n
t
to
o
l
li
k
e
Xili
n
x
d
e
v
ice
g
e
n
e
ra
to
rs
,
"
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Eme
rg
i
n
g
T
re
n
d
s
in
En
g
in
e
e
rin
g
Res
e
a
rc
h
,
v
o
l.
9
,
n
o
.
4
,
p
p
.
4
3
1
-
4
3
4
,
2
0
2
1
,
d
o
i:
1
0
.
3
0
5
3
4
/i
jete
r/2
0
2
1
/
1
6
9
4
2
0
2
1
.
[2
3
]
C.
Li
,
R.
H
u
a
n
g
,
Z.
Di
n
g
,
J.
C
.
G
a
ten
b
y
,
D.
N.
M
e
tax
a
s a
n
d
J.
C.
G
o
re
,
"
A
lev
e
l
se
t
m
e
th
o
d
fo
r
ima
g
e
se
g
m
e
n
tatio
n
in
th
e
p
re
se
n
c
e
o
f
i
n
ten
sit
y
in
h
o
m
o
g
e
n
e
it
ies
with
a
p
p
l
ica
ti
o
n
to
M
RI,
"
i
n
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
I
ma
g
e
Pro
c
e
ss
in
g
,
v
o
l.
2
0
,
n
o
.
7
,
p
p
.
2
0
0
7
-
2
0
1
6
,
Ju
l
.
2
0
1
1
,
d
o
i:
1
0
.
1
1
0
9
/T
IP
.
2
0
1
1
.
2
1
4
6
1
9
0
.
[2
4
]
A.
Bo
se
a
n
d
K.
M
a
li
,
"
F
u
z
z
y
-
b
a
s
e
d
a
rti
fc
ial
b
e
e
c
o
lo
n
y
o
p
ti
m
iza
ti
o
n
f
o
r
g
ra
y
ima
g
e
se
g
m
e
n
tatio
n
,
"
S
i
g
n
a
l,
Im
a
g
e
a
n
d
Vi
d
e
o
Pr
o
c
e
ss
in
g
,
v
o
l
.
10
,
p
p
.
1
0
8
9
-
1
0
9
6
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
0
7
/s
1
1
7
6
0
-
0
1
6
-
0
8
6
3
-
z
.
[2
5
]
Q
.
Liu
,
M
.
Jia
n
g
,
P
.
Ba
i
,
a
n
d
G
.
Ya
n
g
,
"
A
n
o
v
e
l
lev
e
l
se
t
m
o
d
e
l
with
a
u
to
m
a
ted
in
it
ializa
ti
o
n
a
n
d
c
o
n
tr
o
ll
i
n
g
p
a
ra
m
e
ters
fo
r
m
e
d
ica
l
ima
g
e
se
g
m
e
n
tatio
n
,
"
Co
mp
u
ter
ize
d
M
e
d
i
c
a
l
Ima
g
in
g
Gr
a
p
h
ics
,
v
o
l.
48
,
p
p
.
21
-
29
,
2
0
1
6
,
d
o
i:
1
0
.
1
0
1
6
/j
.
c
o
m
p
m
e
d
ima
g
.
2
0
1
5
.
1
2
.
0
0
5
.
[2
6
]
M
.
S
.
F
a
rid
,
M
.
Lu
c
e
n
tef
o
rte
a
n
d
M
.
G
ra
n
g
e
tt
o
,
"
DO
S
T:
A d
istri
b
u
ted
o
b
jec
t
se
g
m
e
n
tatio
n
t
o
o
l
,"
M
u
lt
ime
d
ia
T
o
o
ls
a
n
d
Ap
p
li
c
a
ti
o
n
s v
o
l
u
me
,
v
o
l.
7
7
,
p
p
.
2
0
8
3
9
–
2
0
8
6
2
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
0
7
/s1
1
0
4
2
-
0
1
7
-
5
5
4
6
-
4.
[2
7
]
M
.
N.
Qu
re
sh
i
a
n
d
M
.
V.
Ah
a
m
a
d
,
"
A
n
imp
r
o
v
e
d
m
e
th
o
d
fo
r
ima
g
e
se
g
m
e
n
tatio
n
u
si
n
g
K
-
m
e
a
n
s
c
lu
ste
rin
g
wi
th
n
e
u
tro
s
o
p
h
ic l
o
g
ic
,
"
Pro
c
e
d
i
a
Co
mp
u
ter
S
c
ien
c
e
,
v
o
l
.
1
3
2
,
p
p
.
5
3
4
–
5
4
0
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
c
s.
2
0
1
8
.
0
5
.
0
0
6
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Chi
r
a
n
je
e
v
i
G
.
N
re
c
e
iv
e
d
h
is
Ba
c
h
e
lo
r
in
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
E
n
g
i
n
e
e
rin
g
fr
o
m
Visv
e
sv
a
ra
y
a
Tec
h
n
o
lo
g
ica
l
u
n
i
v
e
rsity
,
Be
lg
a
u
m
,
Ka
rn
a
tak
a
,
In
d
ia,
i
n
2
0
1
0
a
n
d
M
.
Tec
h
i
n
VLS
I
De
sig
n
fro
m
Na
ti
o
n
a
l
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
Ka
rn
a
tak
a
(NITK
S
u
ra
th
k
a
l)
,
Ka
rn
a
tak
a
,
In
d
ia
in
2
0
1
2
.
C
u
rre
n
tl
y
wo
rk
i
n
g
a
s
As
sist
a
n
t
P
ro
fe
ss
o
r
a
t
P
ES
Un
iv
e
rsit
y
EC
Ca
m
p
u
s
(P
ES
I
T
Ba
n
g
a
lo
re
S
o
u
th
Ca
m
p
u
s);
Ba
n
g
a
lo
re
,
Ka
rn
a
tak
a
,
I
n
d
ia.
Are
a
s
o
f
i
n
tere
st
a
re
i
n
th
e
field
o
f
VLS
I,
F
P
G
A
a
n
d
Im
a
g
e
p
ro
c
e
ss
in
g
a
p
p
li
c
a
ti
o
n
s.
Cu
rre
n
t
ly
t
h
e
re
se
a
rc
h
in
tere
st
in
lo
w
p
o
we
r
VLS
I,
F
P
G
A an
d
M
e
d
ica
l
Im
a
g
e
p
ro
c
e
ss
in
g
.
S
u
b
h
a
sh
K
u
lk
a
r
n
i
o
b
tai
n
e
d
P
h
D
d
e
g
re
e
in
2
0
0
2
fr
o
m
E&ECE
De
p
a
rtme
n
t,
In
d
ian
I
n
stit
u
te
o
f
Tec
h
n
o
l
o
g
y
,
Kh
a
ra
g
p
u
r
,
In
d
ia.
H
e
c
o
m
p
lete
d
h
is
M
a
ste
rs’
d
e
g
re
e
fro
m
CEDT,
I
n
d
ian
In
stit
u
te
o
f
S
c
ien
c
e
,
Ba
n
g
a
l
o
re
in
1
9
9
5
with
El
e
c
tro
n
ic
De
sig
n
a
n
d
T
e
c
h
n
o
l
o
g
y
sp
e
c
ializa
ti
o
n
.
He
c
o
m
p
le
ted
B.
E
in
ECE
fr
o
m
P
DA
Co
ll
e
g
e
o
f
En
g
in
e
e
rin
g
,
G
u
lb
a
rg
a
,
Ka
rn
a
tak
a
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
Im
a
g
e
P
ro
c
e
ss
in
g
,
Co
n
tro
l
S
y
ste
m
s,
a
n
d
Hig
h
-
S
p
e
e
d
Arc
h
it
e
c
tu
re
s
u
sin
g
Ve
d
ic
M
a
th
s.
He
h
a
s b
e
e
n
in
t
o
tea
c
h
in
g
in
El
e
c
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
E
n
g
in
e
e
rin
g
si
n
c
e
1
9
8
9
.
He
is
p
re
se
n
tl
y
wo
rk
in
g
a
s
P
rin
c
ip
a
l
a
n
d
P
ro
fe
ss
o
r
in
EC
E
a
t
P
ES
I
T
Ba
n
g
a
lo
re
S
o
u
th
Ca
m
p
u
s,
Ba
n
g
a
lo
re
.
He
h
a
s
g
u
i
d
e
d
9
P
h
D
S
c
h
o
lars
ti
ll
d
a
te
a
n
d
h
a
s
p
u
b
li
s
h
e
d
1
2
0
Re
se
a
rc
h
Article
s
i
n
Jo
u
rn
a
ls an
d
C
o
n
fe
re
n
c
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.