I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
5
,
Octo
b
er
20
25
,
p
p
.
4
3
9
5
~
4
4
0
8
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
3
9
5
-
4
4
0
8
4395
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
To
mo
g
ra
phic
ima
g
e re
co
nstruc
tion
enha
ncemen
t
th
r
o
ug
h
media
n f
il
tering a
nd
K
-
mea
ns clus
t
ering
Ng
uy
en
Q
ua
ng
H
uy
,
Ng
uy
en
T
ruo
ng
T
ha
ng
I
n
st
i
t
u
t
e
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
V
i
e
t
n
a
m
A
c
a
d
e
my
o
f
S
c
i
e
n
c
e
a
n
d
Te
c
h
n
o
l
o
g
y
,
H
a
n
o
i
,
V
i
e
t
n
a
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
3
,
2
0
2
4
R
ev
is
ed
J
u
l 4
,
2
0
2
5
Acc
ep
ted
J
u
l 1
2
,
2
0
2
5
Ultras
o
u
n
d
to
m
o
g
ra
p
h
y
is
a
p
o
w
e
rfu
l
a
n
d
wid
e
ly
u
ti
li
z
e
d
ima
g
i
n
g
tec
h
n
i
q
u
e
in
th
e
field
o
f
m
e
d
ica
l
d
iag
n
o
stics
.
Its
n
o
n
-
in
v
a
siv
e
n
a
t
u
re
a
n
d
h
i
g
h
se
n
siti
v
it
y
in
d
e
tec
ti
n
g
sm
a
ll
o
b
jec
ts
m
a
k
e
it
a
n
in
v
a
lu
a
b
le
to
o
l
fo
r
h
e
a
lt
h
c
a
re
p
ro
fe
ss
io
n
a
ls.
H
o
we
v
e
r,
a
sig
n
ifi
c
a
n
t
c
h
a
ll
e
n
g
e
a
ss
o
c
iate
d
with
u
lt
ra
so
u
n
d
to
m
o
g
ra
p
h
y
is
th
a
t
t
h
e
re
c
o
n
stru
c
ted
ima
g
e
s
o
fte
n
c
o
n
tain
n
o
ise
.
Th
is
n
o
ise
c
a
n
se
v
e
re
ly
c
o
m
p
r
o
m
ise
th
e
a
c
c
u
ra
c
y
a
n
d
in
ter
p
re
tab
il
it
y
o
f
th
e
d
iag
n
o
stic
i
n
fo
rm
a
ti
o
n
d
e
riv
e
d
fr
o
m
th
e
se
ima
g
e
s.
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
n
d
ri
g
o
r
o
u
sl
y
e
v
a
l
u
a
te
th
e
a
p
p
l
ica
ti
o
n
o
f
a
m
e
d
ian
fil
ter
t
o
a
d
d
re
ss
a
n
d
m
it
ig
a
te
n
o
ise
a
rti
fa
c
ts
in
th
e
r
e
c
o
n
stru
c
ted
ima
g
e
s
o
b
tai
n
e
d
th
ro
u
g
h
th
e
d
isto
rte
d
b
o
r
n
i
tera
ti
v
e
m
e
th
o
d
(
DBIM).
T
h
e
p
r
ima
ry
a
im
is
to
e
n
h
a
n
c
e
t
h
e
q
u
a
li
t
y
o
f
t
h
e
se
ima
g
e
s
a
n
d
th
e
re
b
y
imp
ro
v
e
d
iag
n
o
stic
re
li
a
b
il
it
y
.
Th
e
e
ffe
c
ti
v
e
n
e
ss
o
f
o
u
r
p
ro
p
o
se
d
n
o
ise
re
d
u
c
ti
o
n
a
p
p
ro
a
c
h
is
q
u
a
n
ti
tati
v
e
ly
a
ss
e
ss
e
d
u
si
n
g
th
e
n
o
rm
a
li
z
e
d
e
rro
r
e
v
a
l
u
a
ti
o
n
m
e
tri
c
,
wh
ich
p
ro
v
id
e
s
a
p
re
c
ise
m
e
a
su
re
o
f
imp
ro
v
e
m
e
n
t
in
ima
g
e
q
u
a
li
ty
.
F
u
rt
h
e
rm
o
re
,
t
o
e
n
h
a
n
c
e
th
e
in
terp
re
ta
b
il
it
y
a
n
d
u
ti
l
it
y
o
f
th
e
re
c
o
n
stru
c
ted
ima
g
e
s,
we
in
c
o
rp
o
ra
te
a
b
a
sic
m
a
c
h
in
e
lea
rn
in
g
tec
h
n
i
q
u
e
k
n
o
wn
a
s
K
-
m
e
a
n
s
c
lu
ste
ri
n
g
.
T
h
is
m
e
th
o
d
is
e
m
p
lo
y
e
d
t
o
a
u
to
m
a
ti
c
a
ll
y
se
g
m
e
n
t
t
h
e
re
c
o
n
str
u
c
ted
i
m
a
g
e
s
in
t
o
d
isti
n
c
t
re
g
i
o
n
s
th
a
t
re
p
re
se
n
t
o
b
jec
ts,
b
a
c
k
g
ro
u
n
d
,
a
n
d
n
o
ise
.
He
n
c
e
,
it
fa
c
il
it
a
tes
a
c
lea
re
r
d
e
li
n
e
a
ti
o
n
o
f
d
iffere
n
t
c
o
m
p
o
n
e
n
ts
wit
h
in
th
e
ima
g
e
s.
Ou
r
re
su
lt
s
d
e
m
o
n
stra
te
t
h
a
t
K
-
m
e
a
n
s
c
lu
ste
rin
g
,
w
h
e
n
a
p
p
li
e
d
to
ima
g
e
s
p
ro
c
e
ss
e
d
with
th
e
p
r
o
p
o
se
d
m
e
d
ian
fil
ter
m
e
th
o
d
,
e
ffe
c
ti
v
e
ly
d
e
li
n
e
a
tes
th
e
se
re
g
io
n
s
wit
h
a
sig
n
ifi
c
a
n
t
re
d
u
c
ti
o
n
o
f
n
o
ise
.
T
h
is
c
o
m
b
i
n
a
ti
o
n
n
o
t
o
n
l
y
e
n
h
a
n
c
e
s
ima
g
e
c
larity
b
u
t
a
lso
e
n
su
re
s
t
h
a
t
c
rit
ica
l
d
iag
n
o
s
ti
c
d
e
tails
a
re
p
re
se
rv
e
d
a
n
d
m
o
re
e
a
sily
i
n
terp
re
ted
b
y
m
e
d
ica
l
p
r
o
fe
ss
io
n
a
ls.
T
h
e
su
b
sta
n
ti
a
l
re
d
u
c
ti
o
n
in
n
o
ise
a
c
h
iev
e
d
t
h
ro
u
g
h
o
u
r
a
p
p
r
o
a
c
h
u
n
d
e
rsc
o
re
s
it
s
p
o
ten
ti
a
l
f
o
r
imp
r
o
v
i
n
g
t
h
e
a
c
c
u
ra
c
y
a
n
d
re
li
a
b
il
it
y
o
f
u
lt
ra
so
u
n
d
to
m
o
g
ra
p
h
y
in
m
e
d
ica
l
d
iag
n
o
st
ics
.
K
ey
w
o
r
d
s
:
Dis
to
r
ted
b
o
r
n
iter
ativ
e
m
eth
o
d
I
m
ag
e
r
ec
o
n
s
tr
u
ctio
n
K
-
m
ea
n
s
clu
s
ter
in
g
Me
d
ian
f
ilter
Ultr
aso
u
n
d
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
:
Ng
u
y
en
Qu
a
n
g
Hu
y
I
n
s
titu
te
o
f
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Vietn
a
m
Aca
d
em
y
o
f
S
cien
ce
an
d
T
ec
h
n
o
lo
g
y
1
8
Ho
an
g
Qu
o
c
Viet,
C
au
Gia
y
Dis
tr
ict,
Ha
n
o
i,
Vietn
am
E
m
ail: q
u
an
g
h
u
y
7
8
8
9
@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Acc
o
r
d
in
g
to
alar
m
i
n
g
s
tatis
tics
f
r
o
m
th
e
W
o
r
ld
Hea
lt
h
Or
g
an
izatio
n
(
W
HO)
,
ap
p
r
o
x
im
ately
1
0
m
illi
o
n
wo
m
e
n
wo
r
ld
wid
e
s
u
cc
u
m
b
to
b
r
ea
s
t
ca
n
ce
r
ea
ch
y
ea
r
.
T
h
is
s
tag
g
er
in
g
f
ig
u
r
e
u
n
d
e
r
s
co
r
es
th
e
cr
itical
im
p
o
r
tan
ce
o
f
ea
r
ly
d
etec
tio
n
in
th
e
b
attle
ag
ai
n
s
t
th
is
p
er
v
asiv
e
d
is
ea
s
e.
E
ar
ly
d
etec
tio
n
is
n
o
t
j
u
s
t
b
en
ef
icial
b
u
t
ca
n
b
e
life
-
s
av
i
n
g
,
as
it
s
ig
n
if
ican
tly
en
h
a
n
ce
s
s
u
r
v
iv
al
r
ates
—
p
o
ten
tially
i
n
cr
ea
s
in
g
th
em
b
y
u
p
to
2
5
%
[
1
]
.
T
h
er
ef
o
r
e,
id
e
n
tify
in
g
a
b
n
o
r
m
al
tu
m
o
r
s
wh
i
le
th
ey
ar
e
s
till
in
th
eir
ea
r
ly
s
tag
es
is
ab
s
o
lu
tely
cr
u
cial.
Ma
m
m
o
g
r
a
p
h
y
[
2
]
i
s
a
wid
ely
em
p
lo
y
ed
s
cr
ee
n
in
g
to
o
l
f
o
r
b
r
ea
s
t
ca
n
ce
r
,
p
ar
ticu
lar
ly
am
o
n
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
3
9
5
-
4
4
0
8
4396
p
o
s
tm
en
o
p
a
u
s
al
wo
m
en
.
Ho
w
ev
er
,
its
e
f
f
ec
tiv
en
ess
is
n
o
tab
ly
r
e
d
u
ce
d
in
wo
m
en
u
n
d
er
th
e
ag
e
o
f
5
0
.
T
h
is
ag
e
g
r
o
u
p
ty
p
ically
h
as
d
e
n
s
er
b
r
ea
s
t
tis
s
u
e,
wh
ich
p
o
s
es
a
s
ig
n
if
ican
t
ch
allen
g
e
f
o
r
m
am
m
o
g
r
a
p
h
y
.
T
h
e
d
en
s
e
tis
s
u
e
p
r
o
v
id
es
less
co
n
tr
ast,
m
ak
in
g
it
d
if
f
ic
u
lt
to
d
et
ec
t
s
m
all
tu
m
o
r
s
.
As
a
r
esu
lt,
m
an
y
ca
s
es
m
ay
b
e
m
is
s
ed
,
d
elay
in
g
cr
itical
tr
ea
t
m
en
t.
I
n
co
n
tr
ast,
u
ltra
s
o
u
n
d
tech
n
o
lo
g
y
p
r
esen
ts
a
h
ig
h
ly
p
r
o
m
is
in
g
alter
n
ativ
e
f
o
r
b
r
ea
s
t
ca
n
ce
r
d
iag
n
o
s
is
in
y
o
u
n
g
er
wo
m
en
.
Un
lik
e
m
am
m
o
g
r
ap
h
y
,
u
ltra
s
o
u
n
d
ca
n
p
en
etr
ate
d
en
s
e
b
r
ea
s
t
tis
s
u
e
an
d
v
is
u
alize
s
m
all
tu
m
o
r
s
th
at
m
ig
h
t
o
th
er
wis
e
r
e
m
ain
u
n
d
etec
ted
.
T
h
is
m
ak
es
it
a
v
alu
ab
le
to
o
l
f
o
r
ea
r
ly
d
iag
n
o
s
is
an
d
in
ter
v
en
ti
o
n
in
wo
m
en
wh
o
ar
e
u
n
d
e
r
5
0
.
T
h
e
a
b
ilit
y
o
f
u
ltra
s
o
u
n
d
to
ef
f
ec
tiv
ely
id
e
n
tify
th
ese
s
m
all
tu
m
o
r
s
co
u
ld
lead
to
ea
r
lier
an
d
m
o
r
e
ac
c
u
r
ate
d
i
ag
n
o
s
es,
u
ltima
tely
im
p
r
o
v
in
g
s
u
r
v
iv
al
r
ates
an
d
o
u
tco
m
es
f
o
r
th
is
d
em
o
g
r
ap
h
i
c
[
3
]
.
T
h
u
s
,
in
teg
r
atin
g
u
ltra
s
o
u
n
d
in
to
r
o
u
tin
e
s
cr
ee
n
in
g
p
r
o
to
co
ls
f
o
r
y
o
u
n
g
er
wo
m
en
co
u
ld
b
e
a
g
a
m
e
-
ch
a
n
g
er
in
th
e
f
ig
h
t
ag
ai
n
s
t
b
r
ea
s
t
ca
n
ce
r
,
p
o
ten
tially
s
av
in
g
co
u
n
tles
s
liv
es
ea
ch
y
ea
r
.
Ultr
aso
u
n
d
with
f
r
eq
u
en
cies
r
an
g
i
n
g
f
r
o
m
1
to
2
0
MH
z
[
4
]
is
o
n
e
o
f
th
e
m
o
s
t
w
id
ely
u
s
e
d
p
ar
ad
ig
m
s
in
b
i
o
m
ed
ical
im
a
g
in
g
d
u
e
to
its
s
af
ety
,
n
o
n
in
v
asiv
en
ess
,
an
d
n
o
n
-
io
n
izin
g
n
atu
r
e,
m
ak
in
g
it
an
in
v
alu
ab
le
to
o
l
f
o
r
clin
ical
d
i
ag
n
o
s
is
.
T
h
is
im
ag
in
g
m
o
d
al
ity
h
as
g
ain
ed
ex
ten
s
iv
e
ap
p
l
icatio
n
in
m
ed
ical
s
ettin
g
s
,
b
ein
g
u
tili
ze
d
f
o
r
a
wid
e
r
an
g
e
o
f
p
u
r
p
o
s
es,
f
r
o
m
o
b
s
tetr
ics
to
ca
r
d
io
lo
g
y
an
d
b
ey
o
n
d
.
Desp
ite
its
wid
esp
r
ea
d
u
s
e,
c
o
n
v
e
n
tio
n
al
u
ltra
s
o
u
n
d
m
ac
h
i
n
es
r
ely
o
n
r
ef
lecte
d
s
ig
n
als,
wh
ich
p
r
esen
t
a
s
ig
n
if
ican
t
lim
itatio
n
:
th
ey
ca
n
n
o
t
ac
cu
r
a
tely
r
ep
r
o
d
u
ce
s
tr
u
ctu
r
es
s
m
aller
th
an
th
e
wav
ele
n
g
th
o
f
th
e
u
ltra
s
o
u
n
d
wa
v
es.
I
n
co
n
tr
ast,
th
e
u
ltra
s
o
u
n
d
to
m
o
g
r
a
p
h
ic
m
eth
o
d
o
f
f
er
s
a
s
u
p
er
io
r
im
ag
i
n
g
ap
p
r
o
ac
h
with
n
u
m
er
o
u
s
ad
v
an
tag
es
o
v
er
tr
ad
itio
n
al
t
ec
h
n
iq
u
es
s
u
c
h
as
X
-
r
ay
[
5
]
,
co
m
p
u
ted
to
m
o
g
r
ap
h
y
(
C
T
)
[
6
]
,
an
d
m
ag
n
etic
r
eso
n
an
ce
im
a
g
in
g
(
MRI)
[
7
]
.
Ultr
aso
u
n
d
to
m
o
g
r
ap
h
y
o
p
er
ates
o
n
th
e
p
r
in
ci
p
le
o
f
b
ac
k
s
ca
tter
,
en
ab
lin
g
it
to
r
eso
lv
e
s
tr
u
ctu
r
es
s
m
aller
th
an
th
e
wav
ele
n
g
th
o
f
th
e
in
cid
en
t
wav
e.
T
h
is
ca
p
ab
ilit
y
s
ets
it
ap
ar
t
f
r
o
m
tr
ad
itio
n
al
im
ag
in
g
m
et
h
o
d
s
,
wh
ich
p
r
im
ar
ily
r
ely
o
n
ec
h
o
tech
n
iq
u
es.
B
y
lev
er
ag
in
g
m
at
er
ial
p
r
o
p
er
ties
s
u
ch
as
s
o
u
n
d
co
n
tr
ast,
atten
u
atio
n
,
an
d
d
e
n
s
ity
,
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
ca
n
ef
f
ec
tiv
ely
id
e
n
tify
an
d
v
is
u
alize
s
m
all
-
s
ized
o
b
jects
with
in
th
e
b
o
d
y
.
T
h
ese
a
d
v
an
ce
d
im
a
g
i
n
g
ca
p
ab
ilit
ies
n
o
t
o
n
ly
en
h
a
n
ce
th
e
ac
cu
r
ac
y
o
f
d
iag
n
o
s
es
b
u
t
also
e
x
p
an
d
th
e
p
o
ten
tial
ap
p
licatio
n
s
o
f
u
l
tr
aso
u
n
d
in
m
e
d
ical
p
r
ac
tice.
Fo
r
i
n
s
tan
ce
,
th
e
im
p
r
o
v
e
d
r
eso
l
u
tio
n
a
n
d
co
n
t
r
ast
ca
n
aid
in
ea
r
ly
d
etec
tio
n
o
f
tu
m
o
r
s
,
d
etailed
im
ag
in
g
o
f
s
o
f
t
tis
s
u
es,
an
d
p
r
ec
is
e
ass
e
s
s
m
en
t
o
f
b
lo
o
d
f
lo
w.
C
o
n
s
eq
u
en
tly
,
u
ltr
aso
u
n
d
to
m
o
g
r
ap
h
y
r
ep
r
ese
n
ts
a
s
ig
n
if
ican
t
ad
v
an
ce
m
e
n
t
in
m
ed
ical
im
ag
in
g
,
o
f
f
e
r
in
g
a
co
m
b
in
atio
n
o
f
s
af
ety
,
ef
f
icien
cy
,
an
d
d
etaile
d
r
eso
lu
tio
n
th
at
is
u
n
m
atch
ed
b
y
m
an
y
o
th
er
im
a
g
in
g
tech
n
o
lo
g
ies.
Ultr
aso
u
n
d
to
m
o
g
r
ap
h
y
ty
p
i
ca
lly
em
p
lo
y
s
th
e
B
o
r
n
ap
p
r
o
x
im
atio
n
,
wh
ich
ass
u
m
es
th
at
th
e
s
ca
tter
in
g
f
ield
is
s
ig
n
if
ican
tly
s
m
aller
co
m
p
ar
ed
to
th
e
in
ci
d
en
t
f
ield
.
T
h
is
ap
p
r
o
x
im
atio
n
is
wid
ely
ac
ce
p
ted
an
d
h
as b
ec
o
m
e
a
f
o
u
n
d
atio
n
a
l c
o
n
ce
p
t in
th
e
f
ield
.
I
n
th
e
r
ea
lm
o
f
d
if
f
r
ac
tio
n
to
m
o
g
r
a
p
h
y
,
th
e
d
is
to
r
ted
b
o
r
n
iter
ativ
e
m
eth
o
d
(
DB
I
M)
is
p
ar
ticu
lar
ly
p
o
p
u
lar
d
u
e
to
its
ef
f
ec
tiv
en
ess
in
h
an
d
lin
g
co
m
p
lex
s
ca
tter
in
g
p
r
o
b
lem
s
[
8
]
–
[
1
0
]
.
C
u
r
r
en
tly
,
th
e
m
ain
ap
p
licatio
n
o
f
th
is
tech
n
iq
u
e
is
o
n
ly
f
o
r
b
r
ea
s
t
im
ag
in
g
in
w
o
m
en
t
o
d
etec
t
ca
n
ce
r
-
ca
u
s
in
g
ce
lls
[
1
1
]
–
[
1
3
]
.
Ho
wev
e
r
,
th
e
im
ag
in
g
p
r
o
ce
s
s
is
o
f
ten
p
lag
u
e
d
b
y
i
n
h
er
e
n
t
n
o
is
e,
wh
ich
ca
n
co
m
p
r
o
m
is
e
th
e
e
f
f
icac
y
an
d
clar
ity
o
f
DB
I
M
-
r
ec
o
n
s
tr
u
cted
im
a
g
es.
T
o
a
d
d
r
ess
th
is
is
s
u
e,
we
in
tr
o
d
u
ce
a
m
e
d
ian
f
ilter
in
g
te
ch
n
iq
u
e
aim
ed
at
r
ed
u
cin
g
n
o
i
s
e
with
o
u
t
co
m
p
r
o
m
is
in
g
th
e
s
tr
u
ctu
r
al
in
teg
r
it
y
o
f
th
e
im
ag
es.
Ou
r
s
tu
d
y
in
v
o
lv
es
s
ev
er
al
k
ey
s
tep
s
:
th
e
ac
q
u
is
itio
n
o
f
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
ic
d
ata,
th
e
r
ec
o
n
s
tr
u
ctio
n
o
f
th
ese
d
ata
u
s
in
g
th
e
DB
I
M
m
eth
o
d
,
an
d
t
h
e
s
u
b
s
eq
u
en
t
a
p
p
licatio
n
o
f
t
h
e
m
ed
ian
f
ilter
to
th
e
r
ec
o
n
s
tr
u
cted
im
ag
es.
W
e
m
eticu
lo
u
s
ly
an
aly
ze
th
e
im
p
ac
t
o
f
th
e
m
ed
ian
f
ilter
o
n
n
o
is
e
r
ed
u
ctio
n
an
d
o
v
er
all
im
ag
e
q
u
ality
.
T
o
q
u
an
titativ
ely
ass
es
s
th
e
ef
f
ec
ti
v
en
ess
o
f
o
u
r
ap
p
r
o
ac
h
,
we
em
p
lo
y
ev
alu
atio
n
m
etr
ics
s
u
ch
as
n
o
r
m
alize
d
e
r
r
o
r
,
wh
ich
p
r
o
v
id
es
a
r
o
b
u
s
t
m
ea
s
u
r
e
o
f
n
o
is
e
r
ed
u
ctio
n
ef
f
icac
y
.
Mo
r
eo
v
er
,
v
ar
io
u
s
s
o
lu
tio
n
s
lev
er
a
g
in
g
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
en
h
an
ce
th
e
q
u
ality
o
f
u
ltra
s
o
u
n
d
im
ag
es
[
1
4
]
–
[
1
8
]
.
T
h
ese
ap
p
r
o
ac
h
es
o
f
te
n
in
v
o
l
v
e
co
m
p
lex
co
m
p
u
tatio
n
al
tec
h
n
iq
u
es
to
im
p
r
o
v
e
im
ag
e
clar
ity
an
d
d
iag
n
o
s
tic
ac
cu
r
ac
y
.
B
y
in
teg
r
atin
g
m
e
d
ian
f
ilter
in
g
with
DB
I
M
an
d
ex
p
lo
r
in
g
m
ac
h
in
e
lear
n
in
g
en
h
an
ce
m
en
ts
,
o
u
r
s
tu
d
y
aim
s
to
p
r
o
v
id
e
a
co
m
p
r
e
h
en
s
iv
e
s
o
lu
tio
n
to
th
e
ch
allen
g
es
p
o
s
ed
b
y
n
o
is
e
in
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
o
u
r
p
r
o
p
o
s
ed
m
eth
o
d
s
ig
n
if
ica
n
tly
r
ed
u
ce
s
n
o
is
e
wh
ile
m
ain
tain
in
g
th
e
ess
en
t
ial
s
tr
u
ctu
r
al
d
etails
o
f
th
e
im
ag
es,
th
u
s
im
p
r
o
v
in
g
t
h
e
o
v
er
all
q
u
ality
an
d
r
eliab
ilit
y
o
f
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
ic
im
ag
in
g
.
I
n
ad
d
itio
n
to
d
e
v
is
in
g
an
im
ag
e
r
esto
r
atio
n
alg
o
r
ith
m
in
D
B
I
M
u
tili
zin
g
th
e
m
ed
ian
f
ilte
r
,
th
is
s
tu
d
y
also
ad
v
o
ca
tes
f
o
r
th
e
u
tili
za
t
io
n
o
f
a
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
to
s
eg
m
en
t
th
e
r
ec
o
n
s
tr
u
cted
im
ag
e
in
to
d
is
tin
ct
d
o
m
ain
s
o
f
o
b
ject,
b
a
ck
g
r
o
u
n
d
,
an
d
n
o
is
e.
I
m
a
g
e
s
eg
m
en
tatio
n
is
a
cr
itical
task
i
n
im
ag
e
p
r
o
ce
s
s
in
g
,
an
d
wh
ile
th
er
e
ar
e
s
ev
er
al
s
o
p
h
is
ticated
alg
o
r
ith
m
s
av
ai
lab
le
f
o
r
th
is
p
u
r
p
o
s
e
—
s
u
ch
as
m
ea
n
-
s
h
if
t,
th
e
wate
r
s
h
ed
alg
o
r
ith
m
,
g
r
a
p
h
c
u
t,
r
eg
io
n
g
r
o
win
g
,
th
e
ac
tiv
e
co
n
to
u
r
m
o
d
el,
co
n
v
o
lu
tio
n
al
n
eu
r
al
n
etwo
r
k
s
(
C
NN)
,
U
-
Net,
an
d
f
u
zz
y
C
-
m
ea
n
s
clu
s
ter
in
g
—
th
e
s
im
p
licity
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
o
f
K
-
m
ea
n
s
clu
s
ter
in
g
m
ak
e
it
t
h
e
p
r
e
f
er
r
ed
ch
o
ice
f
o
r
th
is
s
tu
d
y
.
E
ac
h
o
f
t
h
ese
ad
v
a
n
ce
d
alg
o
r
ith
m
s
h
as
its
o
wn
s
tr
en
g
th
s
an
d
ap
p
licatio
n
s
;
h
o
wev
er
,
th
eir
co
m
p
le
x
ity
o
f
ten
d
em
an
d
s
s
ig
n
if
ican
t
co
m
p
u
tat
io
n
al
r
eso
u
r
ce
s
a
n
d
ex
p
er
tis
e,
wh
ich
m
a
y
n
o
t
b
e
n
ec
ess
ar
y
f
o
r
t
h
e
s
eg
m
en
tatio
n
n
ee
d
s
in
t
h
is
co
n
tex
t.
T
h
u
s
,
a
s
tr
aig
h
tf
o
r
wa
r
d
m
ac
h
in
e
lear
n
in
g
ap
p
r
o
ac
h
,
K
-
m
ea
n
s
clu
s
ter
in
g
,
is
em
p
lo
y
e
d
to
au
to
m
atica
lly
d
iv
id
e
th
e
r
ec
o
n
s
tr
u
cted
im
ag
e
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
-
8
7
0
8
To
mo
g
r
a
p
h
ic
ima
g
e
r
ec
o
n
s
tr
u
ctio
n
en
h
a
n
ce
men
t t
h
r
o
u
g
h
med
ia
n
…
(
N
g
u
ye
n
Qu
a
n
g
Hu
y
)
4397
in
to
d
is
tin
ct
d
o
m
ain
s
r
e
p
r
e
s
en
tin
g
o
b
jects,
b
ac
k
g
r
o
u
n
d
,
an
d
n
o
is
e.
K
-
m
ea
n
s
clu
s
ter
in
g
o
p
er
ates
b
y
p
ar
titi
o
n
in
g
th
e
im
ag
e
d
ata
in
t
o
clu
s
ter
s
b
ased
o
n
p
ix
el
in
ten
s
ity
v
alu
es,
en
s
u
r
in
g
th
at
p
ix
els
with
in
th
e
s
am
e
clu
s
ter
ar
e
m
o
r
e
s
im
ilar
to
ea
c
h
o
th
er
th
an
to
th
o
s
e
in
d
if
f
er
en
t
clu
s
ter
s
.
T
h
is
m
eth
o
d
is
n
o
t
o
n
ly
ef
f
icien
t
b
u
t
also
h
ig
h
ly
ef
f
ec
tiv
e
f
o
r
th
e
p
u
r
p
o
s
e
o
f
th
is
s
tu
d
y
.
T
h
e
r
esu
lts
d
em
o
n
s
tr
ate
th
at
K
-
m
ea
n
s
clu
s
ter
in
g
ef
f
ec
tiv
ely
d
is
cr
im
in
ates
th
e
r
eg
io
n
s
in
im
ag
es
o
b
tai
n
ed
v
ia
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
s
ig
n
if
i
ca
n
tly
r
ed
u
ci
n
g
th
e
p
r
esen
ce
o
f
n
o
is
e
in
th
e
r
ec
o
v
er
ed
im
ag
es.
T
h
is
en
h
an
ce
m
en
t
in
im
ag
e
q
u
ality
u
n
d
er
s
co
r
es
th
e
p
o
ten
tial
o
f
co
m
b
in
in
g
m
ed
ian
f
ilter
in
g
with
K
-
m
ea
n
s
clu
s
ter
in
g
f
o
r
im
p
r
o
v
e
d
im
ag
e
s
eg
m
en
tatio
n
an
d
r
esto
r
atio
n
in
u
ltra
s
o
u
n
d
t
o
m
o
g
r
ap
h
y
.
W
h
ile
th
e
DB
I
M
is
a
p
o
wer
f
u
l
in
v
e
r
s
io
n
f
r
a
m
ewo
r
k
f
o
r
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
,
it
is
h
ig
h
ly
s
en
s
itiv
e
to
n
o
is
e
in
th
e
m
ea
s
u
r
ed
d
ata,
o
f
te
n
p
r
o
d
u
cin
g
a
r
tifa
cts
th
at
o
b
s
cu
r
e
s
tr
u
ctu
r
al
b
o
u
n
d
ar
ies.
C
u
r
r
en
t
m
eth
o
d
s
eith
e
r
a
p
p
ly
p
o
s
t
-
p
r
o
ce
s
s
in
g
f
ilter
s
af
ter
r
ec
o
n
s
tr
u
ctio
n
o
r
r
ely
o
n
co
m
p
u
tatio
n
ally
in
ten
s
iv
e
d
ee
p
lear
n
in
g
m
o
d
els,
b
o
th
o
f
wh
ic
h
p
o
s
e
lim
itatio
n
s
in
r
ea
l
-
tim
e
o
r
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
ap
p
li
ca
tio
n
s
.
T
h
is
s
tu
d
y
ad
d
r
ess
es
th
at
g
ap
b
y
em
b
e
d
d
in
g
a
co
m
p
u
tatio
n
ally
ef
f
ici
en
t
m
ed
ian
f
ilter
in
g
s
tep
with
in
ea
ch
iter
atio
n
o
f
DB
I
M,
th
er
eb
y
r
ed
u
cin
g
n
o
is
e
ac
cu
m
u
latio
n
ea
r
ly
in
th
e
r
e
co
n
s
tr
u
ctio
n
p
r
o
ce
s
s
.
Ad
d
itio
n
ally
,
we
in
tr
o
d
u
ce
K
-
m
ea
n
s
clu
s
ter
in
g
as
a
p
o
s
t
-
r
ec
o
n
s
tr
u
ctio
n
s
eg
m
en
tatio
n
t
o
o
l
to
d
elin
ea
te
m
ea
n
in
g
f
u
l
r
eg
io
n
s
in
th
e
im
a
g
e
with
o
u
t
r
eq
u
ir
in
g
an
n
o
tated
t
r
ain
in
g
d
ata.
T
o
g
eth
er
,
th
ese
en
h
an
ce
m
en
ts
f
o
r
m
a
lig
h
tweig
h
t
y
et
ef
f
ec
tiv
e
f
r
am
ewo
r
k
f
o
r
im
p
r
o
v
in
g
i
m
a
g
e
q
u
ality
in
p
r
ac
tical
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
ic
s
y
s
tem
s
.
T
h
e
r
em
ain
d
e
r
o
f
th
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws.
Sectio
n
2
p
r
esen
ts
th
e
th
eo
r
etica
l
f
o
u
n
d
atio
n
o
f
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
,
d
escr
ib
es
th
e
DB
I
M
,
an
d
in
tr
o
d
u
ce
s
th
e
p
r
o
p
o
s
ed
e
n
h
an
ce
m
en
t
f
r
am
ew
o
r
k
in
teg
r
atin
g
m
e
d
ian
f
ilter
in
g
a
n
d
K
-
m
ea
n
s
clu
s
ter
in
g
.
Secti
o
n
3
p
r
o
v
id
es
th
e
s
im
u
latio
n
s
etu
p
,
ev
alu
atio
n
m
etr
ics,
an
d
ex
p
er
i
m
en
tal
r
e
s
u
lts
co
m
p
ar
in
g
th
e
p
r
o
p
o
s
e
d
m
eth
o
d
with
co
n
v
en
tio
n
al
DB
I
M
an
d
d
u
al
-
f
r
eq
u
e
n
cy
DB
I
M.
Sectio
n
4
d
is
cu
s
s
es
th
e
k
ey
f
in
d
in
g
s
,
c
o
m
p
ar
es
with
r
elate
d
wo
r
k
,
a
d
d
r
ess
es
lim
itatio
n
s
,
an
d
o
u
tlin
es d
i
r
ec
tio
n
s
f
o
r
f
u
t
u
r
e
r
esear
ch
.
Fin
ally
,
s
ec
tio
n
5
co
n
clu
d
es th
e
p
ap
er
.
2.
M
E
T
H
O
D
T
h
e
tr
an
s
ce
iv
er
co
n
f
ig
u
r
atio
n
d
iag
r
am
illu
s
tr
ates
th
e
s
etu
p
o
f
th
e
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
s
y
s
tem
u
tili
ze
d
in
th
e
DB
I
M
,
d
ep
ict
ed
in
Fig
u
r
e
1
.
T
h
is
d
iag
r
am
d
elin
ea
tes
th
e
ar
r
an
g
e
m
en
t
o
f
tr
an
s
m
itter
s
an
d
r
ec
eiv
er
s
with
in
th
e
s
y
s
tem
.
T
h
e
o
b
ject
u
n
d
e
r
in
v
esti
g
atio
n
i
s
a
m
in
u
te
cy
lin
d
r
ical
en
tity
p
o
s
itio
n
ed
with
in
an
ex
p
an
s
iv
e
an
d
u
n
if
o
r
m
m
ed
iu
m
(
in
th
is
ca
s
e,
a
wate
r
en
v
ir
o
n
m
en
t)
.
Ou
r
p
r
im
ar
y
aim
is
to
cr
ea
te
a
co
m
p
r
eh
e
n
s
iv
e
im
ag
e
o
f
th
is
cy
lin
d
r
ical
o
b
ject,
d
esig
n
ate
d
as
th
e
r
eg
i
o
n
o
f
in
ter
est
(
R
OI
)
.
T
h
is
R
OI
is
m
eticu
lo
u
s
ly
p
ar
titi
o
n
e
d
in
to
×
s
q
u
ar
es,
with
ea
ch
s
q
u
a
r
e
r
ep
r
esen
tin
g
a
p
ix
el,
all
s
ized
u
n
if
o
r
m
ly
at
h
.
T
h
e
co
n
f
ig
u
r
atio
n
in
clu
d
es
t
r
an
s
m
itter
s
an
d
r
ec
eiv
er
s
.
T
h
e
cr
u
x
o
f
o
u
r
an
aly
s
is
lies
i
n
th
e
o
b
jectiv
e
f
u
n
ctio
n
(
)
,
wh
ich
is
d
eter
m
i
n
ed
b
y
(
1
)
:
(
⃗
)
=
{
(
2
)
2
(
1
1
2
−
1
0
2
)
⃗
≤
0
⃗
>
(
1
)
wh
er
e
1
r
ep
r
esen
ts
th
e
s
p
ee
d
o
f
wav
e
p
r
o
p
ag
atio
n
th
r
o
u
g
h
th
e
o
b
ject,
wh
ile
0
s
tan
d
s
f
o
r
th
e
s
p
ee
d
o
f
p
r
o
p
a
g
atio
n
in
th
e
wate
r
m
ed
iu
m
.
Me
an
wh
ile,
th
e
v
ar
iab
le
d
en
o
tes
th
e
u
ltra
s
o
n
ic
wav
e
f
r
eq
u
en
c
y
an
d
a
s
ig
n
if
ies th
e
r
ad
iu
s
o
f
t
h
e
o
b
je
ct.
L
et's
im
ag
in
e
an
ex
p
a
n
s
iv
e
r
e
alm
ch
ar
ac
ter
ized
b
y
a
u
n
if
o
r
m
m
ed
iu
m
,
s
u
ch
as
an
en
d
less
ex
p
an
s
e
o
f
wate
r
with
a
g
iv
en
wav
e
n
u
m
b
er
r
e
p
r
esen
ted
as
0
.
I
n
t
h
is
co
n
tex
t,
th
e
g
o
v
er
n
in
g
eq
u
atio
n
f
o
r
th
e
p
r
o
p
a
g
atio
n
o
f
wav
es with
in
t
h
is
s
y
s
tem
ca
n
b
e
s
u
cc
in
ctly
e
x
p
r
ess
ed
as
(
2
)
:
2
(
⃗
)
+
0
2
(
⃗
)
=
−
∅
(
⃗
)
−
(
⃗
)
(
⃗
)
(
2
)
wh
er
e
(
⃗
)
r
ep
r
esen
ts
th
e
a
g
g
r
e
g
ate
s
o
u
n
d
p
r
ess
u
r
e
th
r
o
u
g
h
o
u
t
th
e
g
iv
e
n
s
p
ac
e,
w
h
ile
∅
i
n
c
(
r
⃗
)
s
ig
n
if
ies
th
e
s
o
u
n
d
s
o
u
r
ce
,
with
r
⃗
d
en
o
tin
g
th
e
p
o
s
itio
n
al
v
ec
to
r
.
T
h
e
r
eso
lu
tio
n
o
f
(
2
)
b
ec
o
m
es
f
e
asib
le
th
r
o
u
g
h
th
e
u
tili
za
tio
n
o
f
Gr
ee
n
'
s
f
u
n
ctio
n
0
(
r
⃗
)
:
(
⃗
)
=
(
⃗
)
−
(
⃗
)
=
∫
(
′
⃗
⃗
⃗
)
(
′
⃗
⃗
⃗
)
0
(
⃗
,
′
⃗
⃗
⃗
⃗
)
′
⃗
⃗
⃗
⃗
Ω
(
3
)
wh
er
e
(
⃗
)
r
ep
r
esen
ts
th
e
s
ca
tter
in
g
p
r
ess
u
r
e,
wh
ic
h
s
ig
n
if
ies
th
e
p
r
ess
u
r
e
r
esu
ltin
g
f
r
o
m
t
h
e
s
ca
tter
in
g
p
h
en
o
m
en
o
n
.
C
o
n
v
e
r
s
ely
,
(
⃗
)
d
e
n
o
tes
th
e
in
cid
e
n
t
wav
e
p
r
ess
u
r
e
g
e
n
er
ated
b
y
th
e
s
o
u
r
ce
∅
i
n
c
(
r
⃗
)
.
T
h
e
p
ar
am
eter
Ω
p
er
tain
s
to
th
e
s
p
at
ial
ex
ten
t o
f
th
e
o
b
ject
in
ten
d
e
d
f
o
r
i
m
ag
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
3
9
5
-
4
4
0
8
4398
Fig
u
r
e
1
.
T
r
an
s
ce
iv
er
co
n
f
ig
u
r
atio
n
d
iag
r
am
Giv
en
th
e
ass
u
m
p
tio
n
o
f
a
u
n
i
f
o
r
m
e
n
v
ir
o
n
m
en
t
s
u
r
r
o
u
n
d
in
g
th
e
o
b
ject,
th
e
Gr
ee
n
f
u
n
ctio
n
is
f
o
u
n
d
to
b
e
p
r
o
p
o
r
tio
n
al
to
th
e
ze
r
o
-
o
r
d
er
Han
k
el
f
u
n
ctio
n
,
d
en
o
t
ed
as
0
(
2
)
(
0
)
o
r
(
−
0
)
/
,
ex
ten
d
in
g
to
b
o
th
two
-
d
im
en
s
io
n
al
an
d
th
r
ee
-
d
im
en
s
io
n
al
s
p
ac
es.
E
q
u
atio
n
(
3
)
d
elin
ea
tes
th
e
f
o
r
war
d
p
r
o
b
lem
e
q
u
atio
n
,
s
er
v
in
g
th
e
p
u
r
p
o
s
e
o
f
co
m
p
u
tin
g
th
e
p
r
ess
u
r
e
at
an
y
p
o
in
t
o
u
ts
id
e
Ω
,
o
n
ce
t
h
e
a
g
g
r
e
g
ate
p
r
ess
u
r
e
f
o
r
all
⃗
with
in
Ω
h
as b
ee
n
d
eter
m
in
ed
.
0
(
⃗
=
(
⃗
)
2
−
0
2
E
q
u
atio
n
(
3
)
len
d
s
its
elf
to
d
is
cr
etiza
tio
n
th
r
o
u
g
h
th
e
m
eth
o
d
o
f
m
o
m
en
ts
(
Mo
M)
[
8
]
,
wh
er
ein
it
ca
n
b
e
r
e
p
r
esen
ted
in
m
atr
ix
f
o
r
m
.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
t
r
an
s
f
o
r
m
in
g
th
e
co
n
tin
u
o
u
s
eq
u
a
tio
n
s
in
to
a
d
is
cr
ete
f
o
r
m
s
u
itab
le
f
o
r
c
o
m
p
u
tatio
n
al
an
aly
s
is
.
B
y
d
is
cr
etizin
g
(
3
)
u
s
in
g
Mo
M,
we
d
er
iv
e
a
m
atr
ix
e
q
u
atio
n
g
o
v
er
n
in
g
th
e
ca
lcu
latio
n
o
f
s
o
u
n
d
p
r
ess
u
r
e
with
in
th
e
r
eg
io
n
o
f
in
te
r
est (
R
OI
)
:
̅
=
(
̅
−
̅
.
(
̅
)
)
(
4
)
T
h
e
ca
lcu
latio
n
o
f
s
ca
tter
in
g
p
r
ess
u
r
e
o
u
ts
id
e
th
e
R
OI
ar
ea
is
p
er
f
o
r
m
ed
as
(
5
)
:
̅
=
̅
.
(
̅
)
.
̅
(
5
)
wh
er
e
̅
r
ep
r
esen
ts
th
e
id
en
tit
y
m
atr
ix
,
an
d
(
•
)
d
en
o
tes
th
e
d
iag
o
n
aliza
tio
n
o
p
er
ato
r
,
̅
em
e
r
g
es
as
th
e
m
atr
ix
em
b
o
d
y
in
g
co
ef
f
icien
t
s
p
er
tin
en
t
to
th
e
Gr
ee
n
f
u
n
c
tio
n
0
(
,
′
)
o
r
ig
in
atin
g
f
r
o
m
ea
ch
p
ix
el
p
o
in
t
to
war
d
s
th
e
r
ec
eiv
er
.
C
o
n
v
er
s
ely
,
̅
em
b
o
d
ies
co
ef
f
icien
ts
ass
o
ciate
d
with
th
e
Gr
ee
n
f
u
n
ctio
n
0
(
,
′
)
d
elin
ea
tin
g
in
ter
ac
tio
n
s
b
etwe
en
p
ix
els.
B
o
th
̅
an
d
̅
m
atr
ices u
n
d
er
g
o
ca
lcu
latio
n
as
(
6
)
:
(
⃗
,
⃗
)
=
∫
0
(
⃗
,
′
⃗
⃗
⃗
⃗
)
(
′
⃗
⃗
⃗
⃗
)
′
⃗
⃗
⃗
⃗
(
6
)
h
er
e,
(
′
⃗
⃗
⃗
⃗
)
r
ep
r
esen
ts
th
e
b
asic
s
in
c
f
u
n
ctio
n
.
I
n
th
e
in
v
er
s
e
p
r
o
b
lem
,
o
u
r
o
b
jectiv
e
is
to
d
ete
r
m
in
e
(
r
⃗
)
g
iv
en
a
s
et
o
f
m
ea
s
u
r
em
en
ts
o
f
th
e
s
o
u
n
d
f
ield
(
⃗
,
)
with
in
th
e
s
ca
tter
in
g
r
eg
io
n
.
Ho
wev
e
r
,
if
th
e
wa
v
e
n
u
m
b
er
(
⃗
)
is
u
n
k
n
o
wn
,
t
h
en
(
3
)
ca
n
n
o
t b
e
d
ir
ec
tly
u
tili
ze
d
t
o
c
o
m
p
u
te
t
h
e
o
b
ject
f
u
n
ctio
n
b
e
ca
u
s
e
(
⃗
,
)
,
wh
er
e
r
⃗
∈
Ω
,
is
also
u
n
k
n
o
wn
.
I
n
tr
o
d
u
ci
n
g
t
h
e
f
u
n
ctio
n
(
⃗
)
in
t
o
co
n
s
id
er
atio
n
,
E
q
u
atio
n
(
3
)
ca
n
b
e
r
ef
o
r
m
u
lated
as
(
7
)
:
(
,
⃗
⃗
⃗
)
=
,
(
⃗
)
+
∫
∆
(
′
⃗
⃗
⃗
⃗
)
(
′
⃗
⃗
⃗
⃗
,
)
(
⃗
,
′
⃗
⃗
⃗
⃗
)
′
⃗
⃗
⃗
⃗
Ω
(
7
)
with
in
th
is
co
n
tex
t,
th
e
s
y
m
b
o
l
(
′
⃗
⃗
⃗
⃗
,
)
d
en
o
tes
th
e
s
o
u
n
d
p
r
ess
u
r
e
co
r
r
esp
o
n
d
i
n
g
to
th
e
wav
e
n
u
m
b
e
r
f
u
n
ctio
n
(
⃗
)
,
,
(
⃗
)
r
ep
r
esen
ts
th
e
s
o
u
n
d
p
r
ess
u
r
e
u
p
to
th
e
b
ac
k
g
r
o
u
n
d
wav
e
n
u
m
b
e
r
(
⃗
)
an
d
∆
(
⃗
)
=
(
⃗
)
−
(
⃗
)
(
8
)
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
-
8
7
0
8
To
mo
g
r
a
p
h
ic
ima
g
e
r
ec
o
n
s
tr
u
ctio
n
en
h
a
n
ce
men
t t
h
r
o
u
g
h
med
ia
n
…
(
N
g
u
ye
n
Qu
a
n
g
Hu
y
)
4399
(
⃗
)
=
k
r
2
(
⃗
)
−
k
0
2
(
9
)
I
n
o
r
d
e
r
to
tr
an
s
f
o
r
m
th
e
in
v
e
r
s
e
p
r
o
b
lem
in
to
a
lin
ea
r
f
o
r
m
th
at
in
co
r
p
o
r
ates
th
e
u
n
k
n
o
w
n
f
u
n
ctio
n
(
⃗
)
,
we
em
p
lo
y
th
e
f
ir
s
t
-
o
r
d
er
B
o
r
n
ap
p
r
o
x
im
atio
n
m
eth
o
d
,
w
h
er
ein
(
,
⃗
⃗
⃗
)
≈
,
(
⃗
)
=
(
,
⃗
⃗
⃗
)
.
T
h
is
ap
p
r
o
x
im
atio
n
f
ac
ilit
ates
th
e
s
im
p
lific
atio
n
o
f
th
e
co
m
p
lex
r
elatio
n
s
h
ip
b
etwe
en
th
e
m
e
asu
r
ed
d
ata
an
d
th
e
u
n
k
n
o
wn
f
u
n
ctio
n
(
⃗
)
,
e
n
ab
lin
g
a
m
o
r
e
tr
ac
tab
le
s
o
lu
tio
n
to
b
e
o
b
tain
e
d
.
B
y
ad
o
p
tin
g
th
is
m
eth
o
d
,
we
ef
f
ec
tiv
ely
lin
ea
r
ize
th
e
p
r
o
b
le
m
as
(
1
0
)
:
(
,
⃗
⃗
⃗
)
−
(
,
⃗
⃗
⃗
)
≈
∫
∆
(
′
⃗
⃗
⃗
⃗
)
(
′
⃗
⃗
⃗
⃗
,
)
(
⃗
,
′
⃗
⃗
⃗
⃗
)
′
⃗
⃗
⃗
⃗
(
1
0
)
E
q
u
atio
n
(
1
0
)
s
er
v
es
as
th
e
f
o
u
n
d
atio
n
al
in
v
er
s
e
p
r
o
b
lem
eq
u
atio
n
.
W
h
en
a
s
p
ec
if
ic
v
alu
e
f
o
r
(
⃗
)
is
s
elec
ted
,
it
en
ab
les
th
e
co
m
p
u
tatio
n
o
f
(
,
⃗
⃗
⃗
)
an
d
(
⃗
,
′
⃗
⃗
⃗
⃗
)
u
tili
zin
g
th
e
f
o
r
war
d
p
r
o
b
lem
a
p
p
r
o
ac
h
.
C
en
tr
al
to
(
1
0
)
lies
th
e
u
n
k
n
o
wn
v
ar
iab
le
(
⃗
)
,
wh
ich
en
ca
p
s
u
l
ates
v
ital
in
f
o
r
m
atio
n
.
Mo
r
eo
v
er
,
(
1
0
)
h
o
ld
s
th
e
p
o
ten
tial f
o
r
d
is
cr
etiza
tio
n
th
r
o
u
g
h
th
e
m
et
h
o
d
o
f
m
o
m
en
ts
(
Mo
M)
as
(
1
1
)
,
(
1
2
)
:
̅
=
̅
.
̅
(
1
1
)
M
̅
=
U
̅
.
D
(
̅
)
(
1
2
)
I
n
th
is
co
n
te
x
t,
̅
r
ep
r
esen
ts
th
e
d
if
f
er
e
n
ce
b
etwe
en
two
v
ec
to
r
s
,
wh
er
e
̅
d
en
o
tes
th
e
v
ec
to
r
c
o
n
tain
in
g
th
e
v
alu
es
o
f
th
e
p
r
e
d
icted
s
ca
tter
in
g
f
ield
(
,
⃗
⃗
⃗
)
,
an
d
̅
,
d
en
o
tes
th
e
v
ec
to
r
c
o
n
tain
in
g
th
e
v
alu
es
o
f
th
e
m
ea
s
u
r
ed
s
ca
tter
in
g
f
ield
(
,
⃗
⃗
⃗
)
.
E
s
s
en
tially
,
̅
q
u
an
tifie
s
th
e
d
ev
iatio
n
b
etwe
en
th
e
p
r
ed
ict
ed
an
d
m
ea
s
u
r
ed
s
ca
tter
in
g
f
ield
s
.
Ad
d
itio
n
ally
,
̅
s
tan
d
s
f
o
r
an
o
th
er
v
ec
to
r
co
m
p
r
is
in
g
th
e
v
alu
es o
f
(
⃗
)
.
No
ted
th
at
th
e
u
n
k
n
o
wn
v
ec
t
o
r
̅
co
n
s
is
ts
o
f
×
v
ar
iab
les,
wh
ich
co
r
r
esp
o
n
d
s
to
th
e
n
u
m
b
er
o
f
p
ix
els
with
in
th
e
R
OI
.
T
h
e
p
r
o
ce
s
s
o
f
esti
m
atin
g
th
e
o
b
ject
f
u
n
ctio
n
in
v
o
lv
es
iter
ativ
e
p
r
o
ce
d
u
r
es
th
at
iter
ativ
ely
u
p
d
ate
th
e
elem
en
t
s
o
f
̅
to
c
o
n
v
e
r
g
e
to
war
d
s
th
e
o
p
tim
al
s
o
l
u
tio
n
.
T
h
ese
iter
a
tiv
e
p
r
o
c
ess
es
ar
e
ess
en
tial
f
o
r
ac
cu
r
ately
r
ec
o
n
s
tr
u
ctin
g
th
e
o
b
ject
f
u
n
ctio
n
f
r
o
m
th
e
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
d
ata,
as
th
e
y
r
ef
in
e
th
e
esti
m
atio
n
o
f
p
ix
el
v
alu
es with
in
th
e
R
OI
,
en
h
a
n
c
in
g
th
e
o
v
er
all
q
u
ality
o
f
th
e
r
ec
o
n
s
tr
u
cted
im
ag
e
.
̅
n
=
̅
(
n
−
1
)
+
∆
̅
(
n
−
1
)
,
(
1
3
)
at
th
e
cu
r
r
en
t
s
tep
,
̅
an
d
̅
(
−
1
)
d
en
o
te
th
e
o
b
ject
f
u
n
ctio
n
s
r
e
p
r
e
s
en
tin
g
th
e
p
r
esen
t
an
d
p
r
ev
i
o
u
s
s
tates,
r
esp
ec
tiv
ely
.
T
o
q
u
a
n
tify
t
h
e
v
ar
iatio
n
b
etwe
en
th
ese
s
tates,
we
co
m
p
u
te
̅
,
s
ig
n
if
y
in
g
th
e
c
h
an
g
e
i
n
̅
,
wh
ich
ca
n
b
e
d
eter
m
in
e
d
b
y
ad
d
r
ess
in
g
th
e
l
2
n
o
n
lin
ea
r
r
eg
u
lar
iza
tio
n
p
r
o
b
lem
.
T
h
is
p
r
o
b
lem
aim
s
to
o
p
tim
ize
th
e
r
eg
u
lar
izatio
n
p
a
r
am
eter
to
m
in
im
ize
th
e
d
is
cr
ep
an
cy
b
etwe
en
̅
an
d
̅
(
−
1
)
,
th
er
eb
y
p
r
o
v
id
i
n
g
i
n
s
ig
h
t
in
to
th
e
ev
o
lu
tio
n
o
f
th
e
o
b
jec
t
f
u
n
ctio
n
s
ac
r
o
s
s
iter
atio
n
s
.
C
o
n
s
eq
u
en
tly
,
th
is
ap
p
r
o
ac
h
f
ac
ilit
ates
a
co
m
p
r
eh
e
n
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
iter
ativ
e
p
r
o
ce
s
s
,
e
n
h
an
cin
g
th
e
ef
f
ec
tiv
e
n
ess
o
f
th
e
o
p
tim
izatio
n
s
ch
em
e
in
ac
h
iev
in
g
co
n
v
er
g
e
n
ce
to
war
d
s
an
o
p
tim
al
s
o
lu
tio
n
.
Δ
̅
=
a
r
g
min
∆
̅
‖
∆
̅
sc
t
−
M
t
̅
̅
̅
̅
∆
̅
‖
2
2
+
ϵ
‖
∆
̅
‖
2
2
,
(
1
4
)
h
er
e,
∆
̅
r
e
p
r
esen
ts
a
v
ec
to
r
o
f
d
i
m
en
s
io
n
s
×
1
,
en
ca
p
s
u
latin
g
th
e
d
is
p
ar
ities
b
etwe
en
th
e
an
ticip
ated
an
d
ac
tu
al
s
ca
tter
ed
u
ltra
s
o
u
n
d
s
ig
n
als.
C
o
n
cu
r
r
e
n
tly
,
̅
d
en
o
tes
th
e
s
y
s
tem
m
atr
ix
with
d
im
en
s
io
n
s
×
2
.
L
astl
y
,
ϵ
s
er
v
es
as
th
e
r
eg
u
la
r
izatio
n
p
ar
am
eter
,
in
f
lu
en
ci
n
g
th
e
r
eg
u
la
r
izatio
n
p
r
o
ce
s
s
with
in
th
e
s
y
s
tem
.
T
h
is
p
ar
am
eter
p
lay
s
a
cr
u
cial
r
o
le
in
b
alan
cin
g
th
e
tr
ad
e
-
o
f
f
b
etwe
en
f
itti
n
g
th
e
o
b
s
er
v
ed
d
ata
an
d
co
n
tr
o
llin
g
th
e
c
o
m
p
lex
ity
o
f
th
e
s
o
lu
tio
n
.
Ad
ju
s
tin
g
ϵ
a
llo
ws
f
o
r
th
e
f
in
e
-
tu
n
in
g
o
f
th
e
r
ec
o
n
s
tr
u
ctio
n
p
r
o
ce
s
s
,
en
s
u
r
in
g
o
p
tim
al
r
es
u
lts
tailo
r
ed
to
th
e
s
p
ec
if
ic
ch
ar
ac
ter
is
tics
o
f
th
e
u
ltra
s
o
u
n
d
to
m
o
g
r
a
p
h
y
s
y
s
tem
u
n
d
er
co
n
s
id
er
atio
n
.
T
h
e
r
ef
o
r
e,
u
n
d
e
r
s
tan
d
in
g
an
d
a
p
p
r
o
p
r
iately
s
elec
tin
g
th
e
v
alu
e
o
f
ϵ
ar
e
f
u
n
d
am
en
ta
l
s
tep
s
in
ac
h
iev
in
g
ac
cu
r
ate
an
d
r
eliab
le
r
ec
o
n
s
tr
u
ctio
n
s
.
I
n
th
e
co
n
tex
t
o
f
a
two
-
d
im
e
n
s
io
n
al
s
ce
n
ar
io
,
th
e
in
cid
en
t
p
r
ess
u
r
e
co
r
r
esp
o
n
d
i
n
g
to
a
ze
r
o
-
o
r
d
er
B
ess
e
l b
ea
m
ca
n
b
e
s
u
cc
in
ctly
ex
p
r
ess
ed
as
(
1
5
)
:
i
n
c
=
J
0
(
k
0
|
r
−
r
k
|
)
,
(
1
5
)
h
er
e,
0
r
ef
er
s
to
th
e
ze
r
o
th
-
o
r
d
er
B
ess
el
f
u
n
ctio
n
,
th
e
ter
m
|
−
|
d
en
o
tes
th
e
E
u
clid
ea
n
d
is
tan
ce
b
etwe
en
th
e
tr
an
s
m
itter
an
d
th
e
th
p
o
in
t
with
in
th
e
R
OI
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
3
9
5
-
4
4
0
8
4400
T
h
e
m
e
d
i
a
n
f
i
l
t
e
r
i
s
wi
d
e
l
y
u
t
i
li
z
e
d
i
n
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
d
u
e
to
i
t
s
n
u
m
e
r
o
u
s
a
d
v
a
n
t
a
g
e
s
,
p
a
r
t
i
c
u
l
a
r
l
y
i
n
t
h
e
r
e
a
l
m
s
o
f
n
o
is
e
r
e
d
u
c
t
i
o
n
a
n
d
i
m
a
g
e
f
e
a
t
u
r
e
p
r
es
e
r
v
a
ti
o
n
.
W
h
e
n
it
c
o
m
es
t
o
n
o
is
e
r
ed
u
c
t
i
o
n
,
t
h
e
m
e
d
i
a
n
f
i
l
t
e
r
s
t
a
n
d
s
o
u
t
f
o
r
i
ts
e
f
f
ic
a
cy
i
n
a
d
d
r
e
s
s
i
n
g
v
a
r
i
o
u
s
t
y
p
es
o
f
n
o
i
s
e
p
r
es
e
n
t
i
n
i
m
a
g
es
,
s
u
c
h
a
s
s
al
t
-
a
n
d
-
p
e
p
p
e
r
n
o
i
s
e
a
n
d
i
m
p
u
ls
e
n
o
is
e
.
B
y
s
u
b
s
t
i
t
u
ti
n
g
p
i
x
e
l
v
a
l
u
es
wi
t
h
th
e
m
e
d
i
a
n
v
a
l
u
e
d
e
r
i
v
e
d
f
r
o
m
n
e
i
g
h
b
o
r
i
n
g
p
i
x
e
l
s
,
t
h
e
f
i
l
t
e
r
e
f
f
e
c
t
i
v
el
y
e
l
i
m
i
n
at
es
o
u
t
l
i
e
r
s
a
n
d
i
r
r
e
g
u
l
a
r
it
i
es
i
n
d
u
c
e
d
b
y
n
o
i
s
e
,
r
e
s
u
l
t
i
n
g
i
n
a
m
o
r
e
r
e
f
i
n
e
d
a
n
d
c
l
e
a
n
e
r
i
m
a
g
e
.
I
n
t
e
r
m
s
o
f
p
r
e
s
e
r
v
i
n
g
e
d
g
e
s
a
n
d
i
n
t
r
i
c
at
e
d
e
t
a
i
ls
,
t
h
e
m
e
d
i
a
n
f
i
lt
e
r
o
f
f
e
r
s
d
i
s
t
i
n
c
t
a
d
v
a
n
t
a
g
es
o
v
e
r
m
e
a
n
f
i
l
t
e
r
s
,
w
h
i
c
h
t
e
n
d
to
b
l
u
r
e
d
g
e
s
a
n
d
f
i
n
e
f
e
a
t
u
r
e
s
.
D
u
e
t
o
t
h
e
i
n
h
e
r
e
n
t
r
o
b
u
s
t
n
e
s
s
o
f
t
h
e
m
e
d
i
a
n
v
a
l
u
e
t
o
e
x
t
r
e
m
e
v
al
u
e
s
,
t
h
e
f
il
t
e
r
e
x
c
e
l
s
i
n
r
e
ta
i
n
i
n
g
t
h
e
s
t
r
u
c
t
u
r
a
l
in
t
e
g
r
i
t
y
o
f
t
h
e
i
m
a
g
e
w
h
i
l
e
c
o
n
c
u
r
r
e
n
t
l
y
r
e
d
u
c
i
n
g
n
o
i
s
e
,
m
a
k
i
n
g
i
t
p
a
r
t
ic
u
l
a
r
l
y
s
u
i
t
a
b
l
e
f
o
r
a
p
p
l
i
c
a
ti
o
n
s
w
h
e
r
e
e
d
g
e
p
r
e
s
e
r
v
a
t
i
o
n
is
p
a
r
a
m
o
u
n
t
.
F
u
r
t
h
e
r
m
o
r
e
,
t
h
e
m
e
d
i
a
n
f
i
lt
e
r
b
o
as
t
s
a
s
t
r
ai
g
h
t
f
o
r
w
a
r
d
i
m
p
l
e
m
e
n
t
a
t
i
o
n
p
r
o
c
e
s
s
,
r
e
n
d
e
r
i
n
g
it
r
e
la
t
i
v
el
y
e
as
y
t
o
d
e
p
l
o
y
a
n
d
c
o
m
p
u
t
a
t
i
o
n
a
l
l
y
e
f
f
i
ci
e
n
t
.
T
h
is
s
i
m
p
li
c
it
y
r
e
n
d
e
r
s
i
t
a
f
a
v
o
r
e
d
o
p
t
i
o
n
f
o
r
r
e
a
l
-
t
i
m
e
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
t
as
k
s
,
e
s
p
e
c
i
al
l
y
w
h
e
n
c
o
n
f
r
o
n
t
e
d
w
i
th
f
i
l
t
e
r
w
i
n
d
o
ws
o
f
m
o
d
e
r
a
t
e
s
iz
e
.
C
o
n
s
e
q
u
e
n
tl
y
,
t
h
e
v
e
r
s
a
ti
l
ity
a
n
d
e
f
f
i
c
i
e
n
c
y
o
f
t
h
e
m
e
d
i
a
n
f
i
lt
e
r
m
a
k
e
it
an
i
n
d
i
s
p
e
n
s
a
b
l
e
t
o
o
l
i
n
v
a
r
io
u
s
i
m
a
g
e
p
r
o
c
e
s
s
i
n
g
a
p
p
l
ica
t
i
o
n
s
,
c
o
n
t
r
i
b
u
t
i
n
g
s
i
g
n
i
f
i
c
a
n
t
l
y
t
o
e
n
h
a
n
c
i
n
g
i
m
ag
e
q
u
a
l
i
t
y
a
n
d
e
x
t
r
a
c
ti
n
g
p
e
r
t
i
n
e
n
t
i
n
f
o
r
m
a
t
i
o
n
.
Alg
o
r
ith
m
1
o
u
tlin
es
th
e
p
r
o
c
ed
u
r
e
f
o
r
th
e
f
ilter
ed
d
is
to
r
ted
b
o
r
n
iter
ativ
e
m
eth
o
d
(
Fil
ter
ed
DB
I
M)
.
T
h
is
m
eth
o
d
in
c
o
r
p
o
r
ates
a
s
er
ies
o
f
s
tep
s
to
ef
f
ec
tiv
ely
a
d
d
r
ess
n
o
is
e
ar
tifa
cts
in
th
e
r
e
co
n
s
tr
u
cted
im
ag
es
.
I
n
itially
,
th
e
alg
o
r
ith
m
b
eg
i
n
s
b
y
ac
q
u
ir
in
g
th
e
n
o
is
y
in
p
u
t
im
ag
e
b
y
u
s
in
g
th
e
DB
I
M.
Su
b
s
eq
u
en
tly
,
it
ap
p
lies
a
m
e
d
ian
f
ilter
to
th
e
i
n
p
u
t
im
a
g
e
to
r
e
d
u
ce
t
h
e
n
o
is
e
p
r
esen
t.
Fo
llo
win
g
t
h
e
n
o
is
e
r
ed
u
ctio
n
s
tep
,
th
e
f
ilter
ed
im
ag
e
u
n
d
er
g
o
es
r
ec
o
n
s
tr
u
ctio
n
u
s
in
g
th
e
DB
I
M,
wh
ich
aim
s
to
p
r
o
d
u
ce
a
clea
r
e
r
r
ep
r
esen
tatio
n
o
f
th
e
u
n
d
e
r
ly
in
g
s
tr
u
ctu
r
e.
T
h
r
o
u
g
h
o
u
t
th
is
p
r
o
ce
s
s
,
th
e
alg
o
r
ith
m
iter
ativ
ely
r
ef
in
es
th
e
r
ec
o
n
s
tr
u
cted
im
a
g
e
u
n
til
a
s
atis
f
ac
to
r
y
lev
el
o
f
ac
c
u
r
ac
y
is
ac
h
iev
e
d
.
B
y
in
teg
r
ati
n
g
th
e
m
e
d
ian
f
ilter
in
g
tech
n
i
q
u
e
in
t
o
t
h
e
DB
I
M
f
r
am
ewo
r
k
,
th
e
alg
o
r
ith
m
en
h
an
ce
s
th
e
q
u
ality
o
f
th
e
r
e
co
n
s
tr
u
cted
im
a
g
es,
th
u
s
im
p
r
o
v
in
g
th
e
o
v
e
r
all
ef
f
ec
tiv
en
ess
o
f
th
e
u
ltra
s
o
u
n
d
to
m
o
g
r
a
p
h
y
im
ag
in
g
s
y
s
tem
.
Alg
o
r
ith
m
1
.
T
h
e
Fil
ter
ed
DB
I
M
Set up the transceiver configuration for imaging system
Opt initial values:
̅
(
)
=
̅
(
0
)
and
0
=
by (15)
For
=
1
,
do
1. Determine
̅
and
̅
2. Determine
,
̅
corresponding to
̅
(
)
by (4, 5)
3. Determine
∆
̅
by (11)
4. Determine
∆
̅
(
)
by
(14)
5. Determine
̅
(
+
1
)
=
̅
(
)
+
∆
̅
(
)
6. Remove noise for
̅
(
+
1
)
by
median filter.
End For
T
h
e
r
esu
ltin
g
im
a
g
e
en
c
o
m
p
a
s
s
es
ar
ea
s
r
ep
r
esen
tin
g
th
e
o
b
ject,
b
ac
k
g
r
o
u
n
d
,
an
d
n
o
is
e,
p
r
o
v
id
in
g
cr
u
cial
in
s
ig
h
ts
in
to
th
e
u
n
d
e
r
ly
in
g
s
tr
u
ct
u
r
e
o
f
th
e
d
ata.
T
h
u
s
,
th
e
co
n
tin
u
ed
u
tili
za
tio
n
o
f
th
e
K
-
m
ea
n
s
clu
s
ter
in
g
m
eth
o
d
aim
s
to
d
el
in
ea
te
th
ese
r
eg
io
n
s
au
to
m
ati
ca
lly
,
f
ac
ilit
atin
g
th
e
i
d
en
tific
atio
n
o
f
an
o
m
al
o
u
s
o
b
jects
an
d
th
e
o
b
s
er
v
atio
n
o
f
r
eg
i
o
n
s
h
ea
v
ily
af
f
ec
ted
b
y
n
o
is
e.
K
-
m
ea
n
s
clu
s
ter
in
g
s
tan
d
s
as
a
wid
ely
em
p
lo
y
ed
alg
o
r
ith
m
f
o
r
im
ag
e
s
eg
m
en
tatio
n
,
task
ed
with
p
ar
titi
o
n
in
g
an
im
a
g
e
in
to
d
i
s
tin
ct
s
eg
m
en
ts
o
r
r
eg
io
n
s
,
th
er
eb
y
aid
in
g
in
th
e
ex
tr
ac
tio
n
o
f
m
ea
n
i
n
g
f
u
l
in
f
o
r
m
atio
n
.
T
h
is
alg
o
r
ith
m
allo
ca
tes
ea
ch
p
ix
el
to
o
n
e
o
f
clu
s
ter
s
b
ased
o
n
its
in
ten
s
ity
v
alu
es,
ef
f
ec
t
iv
ely
g
r
o
u
p
in
g
to
g
eth
e
r
p
i
x
els
with
s
im
ilar
ch
ar
ac
ter
is
tics
.
I
n
o
u
r
s
im
u
lat
io
n
s
ce
n
ar
io
,
we
o
p
t
f
o
r
a
cl
u
s
ter
co
u
n
t
(
K)
o
f
th
r
ee
,
alig
n
in
g
with
th
e
th
r
ee
s
p
ec
if
ic
r
eg
io
n
s
o
f
in
ter
est:
th
e
ar
ea
co
n
tain
in
g
th
e
o
b
ject,
th
e
b
ac
k
g
r
o
u
n
d
ar
ea
,
an
d
th
e
n
o
is
e
-
af
f
ec
ted
ar
ea
.
T
h
is
d
elib
er
ate
ch
o
ice
en
ab
les
a
f
o
cu
s
ed
an
aly
s
is
o
f
ea
ch
r
e
g
io
n
,
allo
win
g
f
o
r
a
m
o
r
e
n
u
a
n
ce
d
u
n
d
e
r
s
tan
d
in
g
o
f
th
e
u
n
d
er
l
y
in
g
d
ata
d
is
tr
ib
u
tio
n
an
d
e
n
h
an
ci
n
g
th
e
ac
c
u
r
a
cy
o
f
s
u
b
s
eq
u
en
t p
r
o
ce
s
s
in
g
s
tep
s
.
T
o
clar
if
y
t
h
e
co
n
tr
ib
u
tio
n
s
,
we
s
u
m
m
ar
ize
th
e
p
r
o
p
o
s
ed
m
eth
o
d
as
f
o
llo
ws.
T
h
e
co
r
e
in
n
o
v
atio
n
lies
in
in
teg
r
atin
g
a
2
D
m
e
d
i
an
f
ilter
d
ir
ec
tly
in
to
th
e
iter
ativ
e
r
ec
o
n
s
tr
u
ctio
n
lo
o
p
o
f
DB
I
M.
Af
ter
ea
ch
DB
I
M
iter
atio
n
,
th
e
r
ec
o
n
s
tr
u
cted
o
b
ject
f
u
n
ctio
n
is
d
e
n
o
is
ed
u
s
in
g
a
m
e
d
ian
f
ilter
to
s
u
p
p
r
ess
lo
ca
lized
n
o
is
e
with
o
u
t
b
l
u
r
r
in
g
cr
itic
al
s
tr
u
ctu
r
al
ed
g
es.
T
h
is
in
tr
a
-
lo
o
p
f
ilter
in
g
r
ed
u
ce
s
er
r
o
r
ac
cu
m
u
latio
n
an
d
im
p
r
o
v
es c
o
n
v
er
g
e
n
ce
s
tab
ilit
y
.
On
ce
th
e
f
in
al
im
ag
e
is
o
b
ta
in
ed
,
we
ap
p
ly
K
-
m
ea
n
s
clu
s
ter
in
g
(
with
K
=
3
)
to
s
eg
m
en
t
th
e
im
ag
e
in
to
d
is
tin
ct
zo
n
es:
th
e
o
b
ject
(
tar
g
et)
,
t
h
e
h
o
m
o
g
en
e
o
u
s
b
ac
k
g
r
o
u
n
d
,
an
d
r
esid
u
al
n
o
is
e.
T
h
is
p
o
s
t
-
p
r
o
ce
s
s
in
g
s
tep
is
d
esig
n
ed
to
en
h
a
n
ce
th
e
in
te
r
p
r
etab
ilit
y
o
f
th
e
r
ec
o
n
s
tr
u
ct
io
n
an
d
to
is
o
late
r
elev
an
t d
iag
n
o
s
tic
f
ea
tu
r
es.
T
h
e
alg
o
r
ith
m
ic
w
o
r
k
f
l
o
w
is
o
u
tlin
ed
in
Alg
o
r
ith
m
1
an
d
v
ali
d
ated
in
Sectio
n
3
.
3.
SI
M
UL
A
T
I
O
N
S AN
D
R
E
S
UL
T
S
T
h
e
s
im
u
latio
n
p
ar
am
eter
s
f
o
r
th
is
s
tu
d
y
e
n
co
m
p
ass
v
ar
io
u
s
f
ac
ets
ess
en
tial
f
o
r
th
e
ac
cu
r
at
e
d
ep
ictio
n
o
f
u
ltra
s
o
u
n
d
to
m
o
g
r
ap
h
y
.
Sp
ec
if
ically
,
th
e
in
cid
e
n
t
f
r
eq
u
en
c
y
f
is
s
et
a
t
1
MH
z
in
o
r
d
er
to
s
atis
f
y
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
-
8
7
0
8
To
mo
g
r
a
p
h
ic
ima
g
e
r
ec
o
n
s
tr
u
ctio
n
en
h
a
n
ce
men
t t
h
r
o
u
g
h
med
ia
n
…
(
N
g
u
ye
n
Qu
a
n
g
Hu
y
)
4401
th
e
B
o
r
n
ap
p
r
o
x
im
atio
n
c
o
n
d
i
tio
n
.
T
o
e
n
s
u
r
e
c
o
m
p
r
e
h
en
s
iv
e
co
v
e
r
ag
e,
b
o
t
h
th
e
n
u
m
b
e
r
o
f
tr
a
n
s
m
itter
s
(
N
t
)
an
d
th
e
n
u
m
b
er
o
f
r
ec
eiv
e
r
s
(
N
r
)
,
co
llectiv
ely
d
ef
in
i
n
g
th
e
n
u
m
b
er
o
f
m
ea
s
u
r
e
m
en
ts
(
N
t
×
N
r
)
,
ar
e
m
eticu
lo
u
s
ly
ca
lib
r
ated
.
Mo
r
eo
v
er
,
t
o
ac
h
iev
e
r
o
b
u
s
t
co
n
v
er
g
en
ce
an
d
p
r
ec
is
e
r
ec
o
n
s
tr
u
ctio
n
,
a
to
tal
o
f
N
sum
=
5
iter
atio
n
s
ar
e
iter
ativ
ely
ex
ec
u
ted
.
T
h
e
s
p
atial
r
eso
lu
tio
n
with
in
th
e
r
eg
io
n
o
f
in
ter
est
is
f
in
ely
p
ar
titi
o
n
ed
in
to
N
=
12
p
ix
el
s
p
er
ax
is
,
th
er
eb
y
y
ield
in
g
N
2
=
144
v
ar
iab
les
in
two
-
d
im
en
s
io
n
al
s
p
ac
e.
Ad
d
itio
n
ally
,
th
e
s
ca
tter
in
g
a
r
ea
d
iam
eter
,
s
p
an
n
in
g
1
0
m
m
,
an
d
th
e
s
o
u
n
d
co
n
tr
ast
s
et
a
t
1
0
%
ar
e
tailo
r
ed
.
Fin
ally
,
th
e
d
is
tan
ce
s
f
r
o
m
b
o
t
h
tr
an
s
m
itter
s
an
d
r
ec
eiv
e
r
s
to
th
e
ce
n
ter
o
f
th
e
o
b
ject
ar
e
d
e
f
in
ed
at
6
0
m
m
.
T
o
s
im
u
late
r
ea
lis
tic
co
n
d
itio
n
s
,
we
in
co
r
p
o
r
ate
d
ad
d
iti
v
e
Gau
s
s
ian
n
o
is
e
in
to
th
e
m
ea
s
u
r
e
d
s
ca
tter
ed
f
ield
d
ata.
Sp
ec
i
f
ically
,
we
ad
d
e
d
ze
r
o
-
m
ea
n
Gau
s
s
ian
n
o
is
e
with
a
s
tan
d
ar
d
d
e
v
iatio
n
co
r
r
esp
o
n
d
in
g
to
5
% o
f
th
e
m
ax
im
u
m
am
p
litu
d
e
o
f
th
e
m
ea
s
u
r
ed
s
ig
n
al.
T
h
is
c
h
o
ice
r
ef
le
cts
th
e
ty
p
ical
n
o
is
e
en
co
u
n
ter
e
d
in
p
r
ac
tical
u
ltra
s
o
u
n
d
s
y
s
tem
s
,
in
clu
d
in
g
ele
ctr
o
n
ic
n
o
is
e,
am
p
lifie
r
-
in
d
u
c
ed
v
ar
iatio
n
s
,
an
d
en
v
ir
o
n
m
en
tal
d
is
tu
r
b
a
n
ce
s
d
u
r
in
g
wav
e
p
r
o
p
a
g
atio
n
.
Fig
u
r
e
2
d
ep
icts
th
e
id
ea
l
in
v
er
s
e
-
s
ca
tter
in
g
p
atter
n
r
eq
u
ir
i
n
g
r
ec
o
n
s
tr
u
ctio
n
.
Fig
u
r
e
3
illu
s
tr
ates
th
e
n
o
r
m
alize
d
er
r
o
r
o
b
s
er
v
ed
af
t
er
N
sum
iter
atio
n
s
o
f
b
o
th
th
e
co
n
v
e
n
tio
n
al
DB
I
M
an
d
th
e
f
ilter
ed
DB
I
M
f
o
r
N
t
=
N
r
=6
.
I
t
is
ev
id
e
n
t
f
r
o
m
th
e
o
v
e
r
all
tr
en
d
t
h
at
th
e
f
ilter
e
d
DB
I
M
co
n
s
is
ten
tly
s
u
r
p
ass
es
th
e
co
n
v
en
tio
n
al
DB
I
M
in
ter
m
s
o
f
r
ed
u
ci
n
g
n
o
r
m
alize
d
er
r
o
r
.
T
h
is
tr
en
d
u
n
d
e
r
s
co
r
es
th
e
s
ig
n
i
f
ican
t
co
n
tr
ib
u
tio
n
o
f
th
e
f
ilter
in
g
p
r
o
ce
s
s
with
in
th
e
DB
I
M
f
r
am
ewo
r
k
to
war
d
s
e
n
h
an
cin
g
ac
cu
r
ac
y
a
n
d
f
ac
ili
tatin
g
co
n
v
er
g
en
ce
ac
r
o
s
s
m
u
ltip
le
iter
atio
n
s
.
No
t
ab
ly
,
wh
en
co
m
p
a
r
in
g
t
h
e
two
ap
p
r
o
a
ch
es,
th
e
f
ilter
e
d
DB
I
M
ex
h
ib
its
r
ed
u
ce
d
p
er
ce
n
tag
es
in
n
o
r
m
alize
d
e
r
r
o
r
f
r
o
m
th
e
in
itial
iter
atio
n
t
o
th
e
f
if
th
iter
atio
n
,
am
o
u
n
tin
g
to
6
.
8
4
%,
3
6
.
7
3
%,
5
1
.
9
5
%,
5
8
.
5
2
%,
an
d
6
2
.
7
8
%,
r
esp
ec
tiv
ely
.
T
h
ese
r
ed
u
ce
d
p
er
ce
n
tag
es
s
er
v
e
as
q
u
an
titativ
e
in
d
icato
r
s
o
f
th
e
en
h
an
ce
m
e
n
t
ac
h
iev
ed
b
y
th
e
f
ilter
ed
DB
I
M.
Hig
h
er
r
ed
u
ctio
n
p
er
ce
n
tag
es
s
ig
n
if
y
a
m
o
r
e
ef
f
icac
io
u
s
f
ilter
in
g
p
r
o
ce
s
s
,
lead
in
g
to
a
co
n
s
id
er
ab
le
d
ec
r
ea
s
e
in
n
o
r
m
alize
d
er
r
o
r
a
n
d
co
n
s
eq
u
en
tly
,
en
h
a
n
ce
d
ac
cu
r
ac
y
.
T
h
is
d
is
ce
r
n
ib
le
im
p
r
o
v
e
m
en
t
in
ac
cu
r
ac
y
co
m
p
ar
ed
to
th
e
co
n
v
e
n
tio
n
al
DB
I
M
h
ig
h
lig
h
ts
th
e
ef
f
icac
y
o
f
th
e
f
ilter
in
g
p
r
o
ce
s
s
th
r
o
u
g
h
o
u
t th
e
iter
atio
n
s
,
a
p
h
en
o
m
e
n
o
n
f
u
r
th
e
r
elu
cid
ated
in
Fig
u
r
e
4
.
Fig
u
r
e
2
.
I
d
ea
l in
v
e
r
s
e
s
ca
tter
tar
g
et
F
i
g
u
r
e
3
.
N
o
r
m
a
l
i
ze
d
e
r
r
o
r
a
f
t
er
i
t
e
r
a
t
i
o
n
s
o
f
t
h
e
c
o
n
v
e
n
t
i
o
n
a
l
D
B
I
M
a
n
d
f
il
t
e
r
e
d
DB
I
M
w
h
en
N
t
=
N
r
=
6
I
d
e
a
l
o
b
j
e
c
t
f
u
n
c
t
i
o
n
2
4
6
8
10
12
2
4
6
8
10
12
1
1
.
5
2
2
.
5
3
3
.
5
4
4
.
5
5
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
N
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
N
o
r
m
a
l
i
z
e
d
e
r
r
o
r
C
o
n
v
e
n
t
i
o
n
a
l
D
B
I
M
Fi
l
t
e
r
e
d
D
B
I
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
3
9
5
-
4
4
0
8
4402
It
e
r
a
t
i
o
n
s
C
o
n
v
e
n
t
i
o
n
a
l
D
B
IM
Fi
l
t
e
r
e
d
D
B
IM
1
2
3
4
5
Fig
u
r
e
4
.
R
ec
o
v
e
r
ed
im
ag
es a
f
ter
ea
ch
iter
atio
n
o
f
th
e
c
o
n
v
e
n
tio
n
al
DB
I
M
an
d
f
ilter
ed
DB
I
M
wh
en
N
t
=
N
r
=6
Fig
u
r
e
5
illu
s
tr
ates
th
e
ev
o
lu
tio
n
o
f
n
o
r
m
alize
d
er
r
o
r
o
v
er
m
u
ltip
le
iter
atio
n
s
o
f
b
o
th
th
e
co
n
v
en
tio
n
al
DB
I
M
an
d
th
e
f
ilter
ed
DB
I
M
m
eth
o
d
s
with
=
=
1
0
.
I
n
itially
,
d
u
r
in
g
th
e
f
ir
s
t
iter
atio
n
,
th
e
f
ilter
ed
DB
I
M
ex
h
ib
its
a
m
o
d
est
y
et
d
is
ce
r
n
ib
le
d
ec
r
ea
s
e
in
n
o
r
m
alize
d
e
r
r
o
r
,
am
o
u
n
tin
g
t
o
ap
p
r
o
x
im
ately
0
.
9
7
%
co
m
p
ar
ed
to
th
e
co
n
v
en
tio
n
al
DB
I
M.
As
th
e
iter
atio
n
s
p
r
o
g
r
ess
,
th
e
s
u
p
er
io
r
ity
o
f
t
h
e
f
ilter
ed
DB
I
M
b
ec
o
m
es
in
cr
e
asin
g
ly
ev
id
en
t.
B
y
t
h
e
f
in
al
iter
atio
n
,
it
ac
h
iev
es
a
r
em
a
r
k
ab
le
r
ed
u
ctio
n
o
f
ap
p
r
o
x
im
ately
8
6
.
3
9
%
in
n
o
r
m
alize
d
er
r
o
r
co
m
p
ar
e
d
to
th
e
co
n
v
en
tio
n
al
DB
I
M.
T
h
is
co
n
s
is
ten
t
o
u
tp
er
f
o
r
m
an
ce
is
o
b
s
er
v
e
d
t
h
r
o
u
g
h
o
u
t
all
iter
atio
n
s
,
with
r
ed
u
ctio
n
s
r
an
g
i
n
g
f
r
o
m
0
.
9
7
%
to
8
6
.
3
9
%.
T
h
e
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
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
-
8
7
0
8
To
mo
g
r
a
p
h
ic
ima
g
e
r
ec
o
n
s
tr
u
ctio
n
en
h
a
n
ce
men
t t
h
r
o
u
g
h
med
ia
n
…
(
N
g
u
ye
n
Qu
a
n
g
Hu
y
)
4403
tr
en
d
u
n
d
e
r
s
co
r
es
a
s
ig
n
if
ican
t
an
d
escalatin
g
en
h
an
c
em
en
t
in
p
er
f
o
r
m
an
ce
as
iter
atio
n
s
ad
v
an
ce
,
u
n
d
er
s
co
r
i
n
g
th
e
ef
f
icac
y
o
f
th
e
f
ilter
in
g
m
ec
h
an
is
m
with
in
th
e
DB
I
M
f
r
am
ewo
r
k
.
Mo
r
eo
v
er
,
Fig
u
r
e
6
p
r
o
v
id
es
a
v
is
u
al
r
ep
r
esen
tat
io
n
in
d
icatin
g
th
e
co
n
v
er
g
en
ce
o
f
th
e
r
ec
o
v
e
r
y
f
u
n
ctio
n
to
war
d
s
th
e
id
ea
l
o
b
jectiv
e
f
u
n
ctio
n
af
ter
ea
ch
iter
atio
n
.
T
h
is
co
n
v
er
g
en
ce
s
u
g
g
ests
th
at
th
e
f
ilter
ed
DB
I
M
m
eth
o
d
s
tead
ily
ap
p
r
o
ac
h
es
th
e
d
esire
d
o
u
tco
m
e
with
ea
ch
s
u
cc
ess
iv
e
iter
at
io
n
,
f
u
r
t
h
er
af
f
ir
m
i
n
g
its
ef
f
icac
y
an
d
p
o
te
n
tial
f
o
r
p
r
ac
tical
ap
p
licatio
n
in
u
ltra
s
o
u
n
d
to
m
o
g
r
a
p
h
y
.
Fig
u
r
e
7
illu
s
tr
ates
th
e
p
r
o
g
r
ess
io
n
o
f
n
o
r
m
alize
d
e
r
r
o
r
th
r
o
u
g
h
o
u
t
N
sum
iter
atio
n
s
f
o
r
b
o
th
th
e
co
n
v
en
tio
n
al
DB
I
M
an
d
th
e
f
i
lter
ed
DB
I
M
wh
en
N
t
=
N
r
=1
2
.
I
n
th
e
in
itial
iter
atio
n
,
th
e
n
o
r
m
alize
d
er
r
o
r
s
f
o
r
th
e
co
n
v
en
tio
n
al
an
d
f
ilter
e
d
DB
I
M
ar
e
r
ec
o
r
d
ed
as
0
.
9
6
9
7
an
d
0
.
9
4
7
2
,
r
esp
ec
tiv
ely
.
C
o
n
v
er
s
ely
,
in
th
e
f
in
a
l
iter
atio
n
,
th
e
n
o
r
m
alize
d
er
r
o
r
s
f
o
r
th
e
co
n
v
en
tio
n
al
an
d
f
ilter
ed
DB
I
M
d
ec
r
ea
s
e
to
0
.
1
7
1
1
an
d
0
.
0
9
3
4
,
r
esp
ec
tiv
ely
.
No
tab
ly
,
d
u
r
i
n
g
th
e
in
itial
iter
atio
n
,
th
e
d
is
cr
ep
an
cy
i
n
n
o
r
m
alize
d
er
r
o
r
b
etwe
en
th
e
two
m
eth
o
d
s
r
em
ain
s
m
in
im
al,
with
th
e
f
ilter
ed
DB
I
M
ex
h
i
b
itin
g
a
s
lig
h
t
ad
v
an
tag
e,
s
h
o
wca
s
in
g
a
2
.
3
2
%
r
ed
u
ctio
n
in
n
o
r
m
alize
d
e
r
r
o
r
co
m
p
ar
e
d
to
th
e
co
n
v
en
tio
n
al
DB
I
M
ap
p
r
o
ac
h
.
Ho
wev
er
,
as
th
e
iter
atio
n
s
p
r
o
g
r
ess
,
t
h
e
s
u
p
e
r
io
r
ity
o
f
th
e
f
ilter
ed
DB
I
M
b
ec
o
m
es
m
o
r
e
p
r
o
n
o
u
n
ce
d
.
B
y
t
h
e
f
in
al
it
er
atio
n
,
th
e
f
ilter
ed
DB
I
M
o
u
tp
er
f
o
r
m
s
th
e
co
n
v
en
tio
n
al
DB
I
M
s
ig
n
if
ican
tly
,
d
em
o
n
s
tr
atin
g
a
n
o
tab
le
4
5
.
4
0
%
r
ed
u
ctio
n
i
n
n
o
r
m
alize
d
er
r
o
r
.
T
h
is
co
n
s
is
ten
t
p
atter
n
o
f
im
p
r
o
v
ed
p
e
r
f
o
r
m
an
ce
is
o
b
s
er
v
ed
ac
r
o
s
s
all
iter
atio
n
s
,
with
th
e
d
is
p
ar
ity
b
etwe
en
th
e
two
m
eth
o
d
s
b
ec
o
m
in
g
m
o
r
e
ev
id
en
t
to
war
d
s
t
h
e
en
d
o
f
t
h
e
p
r
o
ce
s
s
.
Fo
r
a
co
m
p
r
eh
e
n
s
iv
e
v
is
u
aliza
tio
n
o
f
th
is
tr
e
n
d
,
r
ef
er
to
Fig
u
r
e
8
,
wh
ich
f
u
r
th
er
elu
cid
ates
th
e
wid
en
in
g
g
a
p
in
p
er
f
o
r
m
an
ce
b
etwe
en
th
e
co
n
v
en
tio
n
al
an
d
f
ilter
ed
DB
I
M
a
p
p
r
o
ac
h
es.
An
aly
s
is
r
ev
ea
ls
th
at
Fig
u
r
es
3
,
5
,
an
d
7
illu
s
tr
ate
th
e
n
o
r
m
alize
d
er
r
o
r
f
o
llo
win
g
N
sum
ite
r
atio
n
s
f
o
r
b
o
th
th
e
c
o
n
v
e
n
tio
n
al
DB
I
M
an
d
th
e
f
ilter
ed
DB
I
M
u
n
d
er
d
if
f
er
e
n
t
s
ce
n
ar
io
s
,
s
p
ec
if
i
ca
lly
f
o
r
N
t
=
N
r
=6
,
N
t
=
N
r
=1
0
,
an
d
N
t
=
N
r
=1
2
,
r
esp
ec
tiv
ely
.
No
tab
ly
,
a
s
ig
n
if
ican
t
d
ec
r
ea
s
e
in
n
o
r
m
alize
d
er
r
o
r
is
o
b
s
er
v
ed
f
o
r
th
e
ca
s
es
wh
er
e
N
t
=
N
r
=6
,
N
t
=
N
r
=1
0
,
i
n
d
icatin
g
th
e
c
o
n
s
id
er
a
b
le
ef
f
icac
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
wh
e
n
th
e
n
u
m
b
er
o
f
m
ea
s
u
r
em
en
ts
is
less
th
an
th
e
n
u
m
b
er
o
f
v
ar
iab
les.
T
h
is
o
b
s
er
v
atio
n
alig
n
s
with
p
r
ac
tical
s
ce
n
ar
io
s
in
h
ig
h
-
r
eso
lu
tio
n
i
m
ag
in
g
,
w
h
er
e
s
u
ch
co
n
d
itio
n
s
f
r
eq
u
e
n
tly
o
cc
u
r
d
u
e
to
v
ar
io
u
s
co
n
s
tr
ain
ts
.
C
o
n
s
eq
u
en
tly
,
th
e
f
in
d
i
n
g
s
s
u
g
g
est
th
e
p
o
ten
tial
r
o
b
u
s
tn
ess
an
d
ap
p
licab
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
ac
r
o
s
s
a
r
an
g
e
o
f
p
r
ac
tical
s
ettin
g
s
in
t
h
e
f
ield
o
f
im
ag
in
g
.
Fig
u
r
e
9
illu
s
tr
ates
th
e
c
o
m
p
ar
is
o
n
b
etwe
en
th
e
i
d
ea
l,
r
ec
o
n
s
tr
u
cted
,
a
n
d
s
eg
m
en
ted
im
ag
e
s
o
b
tain
e
d
u
s
in
g
b
o
th
th
e
co
n
v
en
tio
n
al
DB
I
M
an
d
th
e
f
ilter
ed
DB
I
M
m
eth
o
d
s
f
o
r
two
s
ce
n
ar
io
s
:
wh
en
N
t
=
N
r
=6
an
d
N
t
=
N
r
=1
0
af
ter
N
sum
iter
atio
n
s
.
I
n
th
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
,
t
h
r
ee
clu
s
ter
s
(
K
)
ar
e
u
tili
ze
d
t
o
r
e
p
r
esen
t
d
is
tin
ct
r
eg
io
n
s
with
in
th
e
im
ag
es:
th
o
s
e
co
n
tain
in
g
o
b
jects,
b
ac
k
g
r
o
u
n
d
ar
ea
s
,
an
d
n
o
is
e.
T
h
e
o
u
tco
m
es
in
d
icate
a
n
o
tab
le
d
i
f
f
er
en
ce
b
etwe
en
th
e
two
m
eth
o
d
s
.
T
h
e
im
ag
e
r
e
co
n
s
tr
u
cted
v
ia
th
e
co
n
v
en
tio
n
al
DB
I
M
ap
p
r
o
ac
h
ex
h
ib
its
s
u
b
s
tan
tial
n
o
is
e
in
te
r
f
er
en
ce
,
with
n
o
is
e
ar
tifa
cts
ap
p
ar
en
t
with
in
b
o
th
th
e
o
b
je
ct
an
d
s
p
r
ea
d
ac
r
o
s
s
th
e
b
ac
k
g
r
o
u
n
d
.
C
o
n
v
er
s
ely
,
th
e
r
ec
o
n
s
tr
u
cted
im
ag
e
o
b
tai
n
ed
th
r
o
u
g
h
th
e
f
ilter
ed
DB
I
M
m
eth
o
d
d
is
p
lay
s
m
in
im
al
n
o
is
e
p
r
esen
ce
,
s
h
o
wca
s
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
th
is
tech
n
iq
u
e
in
n
o
is
e
r
ed
u
ctio
n
.
Fu
r
th
er
m
o
r
e,
th
e
r
esu
ltin
g
im
ag
e
f
r
o
m
th
e
f
il
ter
ed
DB
I
M
clo
s
ely
r
esem
b
les
th
e
id
ea
l
im
ag
e,
u
n
d
er
s
c
o
r
in
g
th
e
ac
cu
r
ate
s
ep
ar
atio
n
o
f
o
b
ject
an
d
b
ac
k
g
r
o
u
n
d
r
e
g
io
n
s
ac
h
iev
ed
th
r
o
u
g
h
K
-
m
ea
n
s
clu
s
ter
in
g
.
T
h
is
s
tar
k
ly
co
n
tr
asts
with
th
e
co
n
v
en
tio
n
al
DB
I
M
m
eth
o
d
,
wh
e
r
e
ev
e
n
a
f
ter
th
e
f
in
al
iter
atio
n
,
th
e
d
ec
o
m
p
o
s
ed
o
b
ject
n
o
tab
l
y
d
ev
iates
f
r
o
m
th
e
id
ea
l
r
ef
er
e
n
ce
im
ag
e.
T
h
ese
f
in
d
in
g
s
e
m
p
h
asize
th
e
s
u
p
e
r
io
r
n
o
is
e
r
ed
u
ctio
n
ca
p
ab
ilit
ies
an
d
o
v
e
r
all
ef
f
ec
tiv
en
ess
o
f
t
h
e
f
ilter
ed
DB
I
M
m
eth
o
d
in
im
ag
e
r
ec
o
n
s
tr
u
ctio
n
co
m
p
ar
ed
t
o
its
co
n
v
en
tio
n
al
co
u
n
ter
p
a
r
t.
Fig
u
r
e
5
.
No
r
m
alize
d
er
r
o
r
a
f
ter
iter
atio
n
s
o
f
t
h
e
co
n
v
en
tio
n
al
DB
I
M
an
d
f
ilter
ed
DB
I
M
wh
en
=
=
10
1
1
.
5
2
2
.
5
3
3
.
5
4
4
.
5
5
0
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
N
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
N
o
r
m
a
l
i
z
e
d
e
r
r
o
r
C
o
n
v
e
n
t
i
o
n
a
l
D
B
I
M
Fi
l
t
e
r
e
d
D
B
I
M
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
5
,
Octo
b
e
r
20
25
:
4
3
9
5
-
4
4
0
8
4404
It
e
r
a
t
i
o
n
s
C
o
n
v
e
n
t
i
o
n
a
l
D
B
IM
Fi
l
t
e
r
e
d
D
B
IM
1
2
3
4
5
F
i
g
u
r
e
6
.
R
e
c
o
v
e
r
e
d
i
m
a
g
e
s
a
f
te
r
e
a
c
h
i
t
e
r
at
i
o
n
o
f
t
h
e
c
o
n
v
e
n
ti
o
n
a
l
DB
I
M
a
n
d
f
i
l
te
r
e
d
DB
I
M
w
h
e
n
N
t
=
N
r
=
10
Fig
u
r
e
7
.
No
r
m
alize
d
er
r
o
r
a
f
ter
N
sum
iter
atio
n
s
o
f
th
e
co
n
v
e
n
tio
n
al
DB
I
M
an
d
f
ilter
ed
DB
I
M
wh
en
N
t
=N
r
=1
2
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
2
4
6
8
10
12
1
1
.
5
2
2
.
5
3
3
.
5
4
4
.
5
5
0
0
.
1
0
.
2
0
.
3
0
.
4
0
.
5
0
.
6
0
.
7
0
.
8
0
.
9
1
N
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
s
N
o
r
m
a
l
i
z
e
d
e
r
r
o
r
C
o
n
v
e
n
t
i
o
n
a
l
D
B
I
M
Fi
l
t
e
r
e
d
D
B
I
M
Evaluation Warning : The document was created with Spire.PDF for Python.