I
A
E
S
I
n
t
e
r
n
at
io
n
al
Jou
r
n
al
of
A
r
t
if
ic
ia
l
I
n
t
e
ll
ig
e
n
c
e
(
I
J
-
AI
)
V
ol
.
11
, N
o.
1
,
M
a
r
c
h
2022
, pp.
397
~
404
I
S
S
N
:
2252
-
8938
,
D
O
I
:
10.11591/
ij
a
i.
v
11
.i
1
.pp
397
-
404
397
Jou
r
n
al
h
om
e
page
:
ht
tp
:
//
ij
ai
.
ia
e
s
c
or
e
.c
om
Id
e
n
t
i
f
y
t
oot
h
c
on
e
b
e
am
c
om
p
u
t
e
d
t
om
ogr
ap
h
y b
a
se
d
on
c
on
t
ou
r
l
e
t
p
ar
t
i
c
l
e
swar
m
op
t
i
m
i
z
at
i
on
H
ib
a A
d
r
e
e
s
e
Y
ou
n
is
, D
h
af
a
r
S
am
i
H
am
m
ad
i,
A
n
s
a
m
N
az
ar
Y
ou
n
is
C
om
put
e
r
S
c
i
e
nc
e
s
D
e
pa
r
t
m
e
nt
, C
ol
l
e
g
e
of
C
om
put
e
r
S
c
i
e
nc
e
s
a
nd
M
a
t
he
m
a
t
i
c
s
, M
o
s
ul
U
ni
ve
r
s
i
t
y, M
os
ul
, I
r
a
q
A
r
t
ic
le
I
n
f
o
A
B
S
T
R
A
C
T
A
r
ti
c
le
h
is
to
r
y
:
R
e
c
e
iv
e
d
M
a
r
16
,
2021
R
e
vi
s
e
d
D
e
c
16
,
2021
A
c
c
e
pt
e
d
D
e
c
28
,
2021
In
this
paper
certain
type
of
biometric
measurements
h
as
been
used
to
i
dentify
the
cone
beam
computed
tomography
(
CBCT
)
radiograph
of
the
subje
ct
in
a
fast
and
reliable
way.
Where
the
CBCT
radiograph
of
a
person
is
us
ed
as
a
data
and
stored
in
database
for
later
use
in
a
person’s
recognition
proce
ss.
The
aim
of
this
research
is
to
use
various
stages
of
the
preprocessing
operations
of
the
CBCT
radiograph
to
obtain
the
clearest
possible
image
that
will
hel
p
us
in
the
identification
process
more
easily
and
pre
cisely.
The
con
tourlet
transforma
tion
was
used
for
feature
extractio
n
of
each
particula
r
CBCT
image
and
the
results
were
processed
by
a
new
hybrid
particle
swarm
optim
ization
(
PSO
)
named
"
contourl
et
PSO"
algorithm
(CPSO),
w
hich
is
fast
er
and
produce
more
p
recise
(due
to
apply
contourlet
algorithm)
than
trad
itional
PSO.
The
proposed
algorithm
(CPSO)
gave
a
detection
ratio
of
98%
a
fter
its
applicati
on on 1
00 CBC
T radiogr
aphs.
K
e
y
w
o
r
d
s
:
C
B
C
T
C
ont
our
le
t
C
P
S
O
D
ir
e
c
ti
ona
l
f
il
te
r
L
a
pl
a
c
e
'
s
pyr
a
m
id
P
r
e
pr
oc
e
s
s
in
g
PSO
This is an
open
acce
ss artic
le unde
r the
CC BY
-
SA
license.
C
or
r
e
s
pon
di
n
g A
u
th
or
:
H
ib
a
A
dr
e
e
s
e
Y
ouni
s
C
om
put
e
r
S
c
ie
nc
e
s
D
e
p
a
r
tm
e
nt
, C
ol
le
ge
of
C
om
put
e
r
S
c
ie
nc
e
s
a
nd M
a
th
e
m
a
ti
c
s
, M
o
s
ul
U
ni
ve
r
s
it
y
M
os
ul
, I
r
a
q
E
m
a
il
:
hi
ba
a
dr
e
e
s
e
@
uom
os
ul
.e
du.i
q
1.
I
N
T
R
O
D
U
C
T
I
O
N
T
he
pe
r
s
ona
l
s
e
c
r
e
t
id
e
nt
if
ic
a
ti
on
num
be
r
c
a
n
be
lo
s
t,
f
or
g
o
tt
e
n
or
s
im
pl
y
di
f
f
ic
ul
t
to
m
e
m
or
iz
e
.
A
ls
o
it
m
a
y
be
s
to
le
n
or
ha
c
ke
d
on
in
m
a
ny
oc
c
a
s
io
ns
.
T
he
r
e
f
or
e
,
bi
om
e
tr
ic
s
c
a
n
be
us
e
d
f
or
id
e
nt
it
y
a
c
c
e
s
s
a
s
a
n
a
lt
e
r
na
ti
ve
[
1]
,
[
2]
.
T
he
m
a
in
a
dva
nt
a
ge
of
bi
om
e
tr
ic
f
e
a
tu
r
e
s
i
s
th
a
t
th
e
s
e
a
r
e
not
pr
one
to
t
he
f
t
a
nd
lo
s
s
, a
nd
do
not
r
e
ly
on
th
e
m
e
m
or
y
of
th
e
ir
us
e
r
s
.
M
or
e
ove
r
,
bi
om
e
tr
ic
s
,
s
uc
h
a
s
f
in
ge
r
pr
in
ts
,
ir
is
pr
in
t,
ha
nd
ge
om
e
tr
y,
e
a
r
s
ha
pe
, f
a
c
e
a
nd
t
e
e
th
s
c
a
ns
don’
t
c
ha
nge
s
ig
ni
f
ic
a
nt
ly
ove
r
t
im
e
a
nd i
t
is
a
di
f
f
ic
ul
t
f
or
a
pe
r
s
on t
o a
lt
e
r
hi
s
ow
n ph
ys
io
lo
gi
c
a
l
bi
om
e
tr
ic
s
or
im
it
a
te
ot
he
r
i
ndi
vi
dua
ls
.
So
, t
he
bi
om
e
tr
ic
r
e
c
or
d t
ook a
l
ot
of
i
nt
e
r
e
s
t
in
t
he
la
s
t
de
c
a
de
s
a
s
a
s
a
f
e
r
m
e
th
od
f
or
pe
r
s
ona
l
id
e
nt
if
ic
a
ti
on.
E
a
c
h
o
ne
of
th
e
s
e
bi
om
e
tr
ic
r
e
c
or
d
s
ha
s
it
s
a
dva
nt
a
g
e
s
a
nd
di
s
a
dva
nt
a
ge
s
[
1]
.
D
e
nt
a
l
bi
om
e
tr
ic
s
us
e
s
de
nt
a
l
s
tr
uc
tu
r
e
in
f
or
m
a
ti
on
f
o
r
th
e
a
ut
om
a
ti
c
id
e
nt
if
ic
a
ti
on
o
f
hum
a
n
r
e
m
a
in
s
[
3]
.
S
o
th
e
a
im
of
th
is
a
r
ti
c
le
i
s
to
pr
e
s
e
nt
a
m
e
di
c
a
l
s
ys
te
m
f
or
pe
r
s
ona
l
id
e
nt
if
ic
a
ti
on
de
pe
ndi
ng
on
f
or
e
ns
i
c
de
nt
is
tr
y
w
he
r
e
a
n
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nt
s
ys
t
e
m
h
a
ve
b
e
e
n
m
a
d
e
u
s
in
g
th
e
c
one
be
a
m
c
om
put
e
d
to
m
ogr
a
phy
(
C
B
C
T
)
f
or
pe
r
s
ona
l
id
e
nt
if
ic
a
ti
on
,
a
nd
d
e
s
pi
te
th
e
f
a
c
t
th
a
t
te
e
th
s
ha
pe
c
a
n
be
s
ubj
e
c
te
d
to
c
ha
nge
ove
r
t
im
e
,
but
t
he
s
ha
pe
,
s
iz
e
of
j
a
w
a
nd f
a
c
ia
l
bon
e
s
us
ua
ll
y a
r
e
s
ti
ll
c
le
a
r
a
nd
c
ons
t
a
nt
w
it
ho
ut
a
ny
c
ha
nge
,
s
o
th
e
s
e
f
e
a
tu
r
e
s
c
a
n
be
e
f
f
ic
ie
nt
ly
us
e
d
f
or
pe
r
s
on
a
l
id
e
nt
if
ic
a
ti
on
a
nd
in
a
r
ti
f
ic
ia
l
in
te
ll
ig
e
nc
e
a
lg
or
it
hm
s
.
f
or
th
is
r
e
a
s
on
w
e
c
ho
s
e
C
B
C
T
im
a
ge
s
r
a
di
ogr
a
ph
s
a
s
a
da
ta
b
a
s
e
f
or
th
e
pr
opos
e
d
s
y
s
te
m
.
T
he
r
e
s
t
of
th
is
pa
pe
r
is
out
li
ne
d
a
s
sh
ow
n
:
s
e
c
ti
on
2
de
a
ls
w
it
h
r
e
la
te
d
w
or
ks
,
s
e
c
ti
on
3
de
a
ls
w
it
h
CBCT
,
s
e
c
ti
on
4
de
a
ls
w
it
h
c
ont
our
le
t
a
lg
or
it
hm
,
s
e
c
ti
on
5 de
a
ls
w
it
h
t
he
pr
opos
e
d a
lg
or
it
hm
, r
e
s
ul
ts
a
nd a
n
a
ly
s
is
a
r
e
s
how
n i
n
s
e
c
ti
on 6, s
e
c
ti
on
7 de
a
ls
w
it
h c
on
c
lu
s
io
n a
nd f
ut
ur
e
w
or
ks
,
f
in
a
ll
y, t
he
a
c
knowle
dge
m
e
nt
.
D
ig
he
a
nd
S
hr
ir
a
m
in
tr
oduc
e
d
a
m
e
th
od
f
o
r
id
e
nt
if
yi
ng
t
he
in
di
vi
dua
l
id
e
nt
it
y
f
r
om
de
nt
a
l
in
f
or
m
a
ti
on.T
he
pr
opos
e
d
m
e
th
od
in
c
lu
de
d
th
r
e
e
m
a
in
s
t
e
ps
:
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
us
in
g
m
or
phol
ogi
c
a
l
ope
r
a
ti
ons
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
11
, N
o.
1
,
M
a
r
c
h
20
22
:
397
-
404
398
(
m
a
th
e
m
a
ti
c
a
l
m
or
phol
ogy)
,
de
nt
a
l
c
ode
ge
ne
r
a
ti
on, a
nd de
nt
a
l
c
ode
m
a
tc
hi
ng.T
he
m
e
th
od
w
a
s
im
pl
e
m
e
nt
e
d
on
30
X
-
r
a
y
da
ta
b
a
s
e
[
4]
.
K
a
r
unya
e
t
al
.
[
5]
pr
opos
e
d
a
ne
w
s
ys
te
m
w
hi
c
h
c
ons
i
s
ts
of
two
s
ta
g
e
s
:
f
ir
s
t
s
ta
ge
in
c
lu
de
s
e
xt
r
a
c
ti
on of
f
e
a
tu
r
e
s
a
nd t
he
s
e
c
ond s
ta
g
e
i
s
m
a
tc
hi
ng
. I
n t
he
f
i
r
s
t
s
ta
ge
t
he
c
ont
our
m
ode
l
w
a
s
us
e
d
f
or
c
ont
our
e
xt
r
a
c
ti
on.
T
he
s
e
c
ond
s
t
a
ge
in
c
lu
d
e
s
two
s
ub
s
ta
g
e
s
e
v
a
lu
a
ti
on
th
e
di
s
ta
nc
e
s
of
th
e
im
a
ge
s
a
nd
id
e
nt
if
ic
a
ti
on
of
th
e
s
ubj
e
c
t.
T
he
s
ys
t
e
m
w
a
s
a
ppl
ie
d
on
te
n
no
r
m
a
l
im
a
ge
s
a
nd
f
if
ty
-
f
iv
e
or
th
opa
nt
om
a
gr
a
m
(
O
P
G
)
im
a
ge
s
.
R
e
hm
a
n
e
t
al
.
[
6]
pr
e
s
e
nt
e
d
a
n
e
f
f
ic
ie
nt
m
e
th
od
f
or
hum
a
n
a
ut
he
nt
ic
a
ti
on
c
or
r
e
c
tl
y
w
hi
c
h
c
ons
is
ts
of
f
iv
e
m
a
in
pr
oc
e
s
s
in
g
s
ta
ge
s
:
pr
e
pr
oc
e
s
s
in
g,
s
e
g
m
e
nt
a
ti
on,
pr
oc
e
s
s
in
g
s
te
p
s
f
or
s
e
gm
e
nt
a
ti
on,
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
a
nd
bi
om
e
tr
ic
a
na
ly
s
is
.
T
he
m
e
th
od
w
a
s
te
s
te
d
on
c
ol
or
e
d
te
e
th
im
a
ge
s
f
or
14
pe
r
s
ons
a
nd
de
nt
a
l
r
a
di
ogr
a
phs
i
m
a
ge
s
f
or
45 pe
r
s
ons
.
O
kt
a
y
e
t
al
.
[
7]
pr
e
s
e
nt
e
d
a
m
e
th
od
f
or
di
s
ti
ngui
s
hi
ng
hu
m
a
ns
by
c
om
pa
r
in
g
two
-
di
m
e
ns
io
n
pa
nor
a
m
ic
de
nt
a
l
X
-
r
a
y
im
a
ge
s
.
F
ir
s
t
e
a
c
h
to
ot
h
is
de
te
c
te
d
a
nd
la
be
le
d
us
in
g
s
uppor
t
ve
c
to
r
m
a
c
hi
ne
a
nd
gr
a
phi
c
a
l
pr
oba
bi
li
s
ti
c
m
ode
ls
.
T
he
m
a
tc
hi
ng r
a
ti
ngs
be
twe
e
n i
m
a
ge
s
w
e
r
e
c
a
lc
ul
a
te
d b
a
s
e
d on
a
n a
ppe
a
r
a
nc
e
of
th
e
to
ot
h
a
nd
th
e
ge
om
e
tr
ic
s
im
il
a
r
it
ie
s
.
S
ha
ke
r
e
t
al
[
8]
in
tr
od
uc
e
d
a
m
e
th
od
f
or
id
e
nt
it
y
id
e
nt
if
ic
a
ti
on
ba
s
e
d
on
X
-
r
a
y
im
a
ge
.
T
he
m
e
th
od
in
c
lu
de
d
th
r
e
e
s
ta
g
e
s
:
pr
e
pr
oc
e
s
s
in
g,
f
e
a
tu
r
e
e
xt
r
a
c
ti
on,
a
nd
m
a
tc
hi
ng.
T
he
pr
e
pr
oc
e
s
s
in
g
w
a
s
m
e
a
n
,
di
s
ta
nc
e
a
nd
s
ta
nd
a
r
d
de
r
iv
a
ti
on
(
S
T
D
)
,
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
w
a
s
va
r
ia
nc
e
a
nd
pr
in
c
ip
a
l
c
om
pone
nt
a
na
ly
s
i
s
(
P
C
A
)
.
T
he
b
e
s
t
r
e
s
ul
t
s
s
how
e
d
a
n
id
e
nt
if
ic
a
ti
on
r
a
te
of
89
%
.
K
hudhur
e
t
al
.
[
9]
in
tr
oduc
e
d
a
s
ys
te
m
to
c
ons
tr
uc
t
a
da
t
a
ba
s
e
c
ont
a
in
in
g
de
nt
a
l
a
nt
e
m
or
te
m
r
a
di
ogr
a
phi
c
f
e
a
tu
r
e
s
,
la
te
r
us
e
d
f
or
pos
t
m
or
te
m
de
nt
a
l
m
a
tc
hi
ng.
T
he
a
lg
or
it
hm
w
hi
c
h
a
ppl
ie
d
on
X
-
R
a
y
im
a
ge
in
c
lu
de
d
th
r
e
e
s
ta
ge
s
:
s
e
gm
e
nt
a
ti
on
of
im
a
ge
s
,
c
la
s
s
if
ic
a
ti
on
a
nd
e
xt
r
a
c
ti
ng
f
e
a
tu
r
e
s
.
T
he
s
e
f
e
a
tu
r
e
s
w
e
r
e
S
T
D
,
e
ul
e
r
num
be
r
a
nd
a
r
e
a
ta
ke
n
f
r
om
bi
te
-
w
in
g
X
-
r
a
y i
m
a
ge
.
I
n
th
is
r
e
s
e
a
r
c
h
a
hybr
id
m
e
th
od
w
a
s
pr
opos
e
d
f
or
di
s
c
r
im
in
a
ti
on
C
B
C
T
r
a
di
a
ti
on
im
a
ge
s
.
T
h
is
m
e
th
od
is
a
c
om
bi
na
ti
on
of
di
s
c
r
im
in
a
ti
ve
f
e
a
tu
r
e
s
of
c
ont
our
le
t
c
oe
f
f
ic
ie
nt
s
a
nd
in
te
ll
ig
e
nt
f
e
a
tu
r
e
s
of
pa
r
ti
c
le
s
w
a
r
m
opt
im
iz
a
ti
on
(
PSO
)
a
lg
or
it
h
m
.
F
i
r
s
tl
y,
T
he
C
B
C
T
r
a
di
ogr
a
phi
c
im
a
ge
s
w
a
s
pr
e
pr
oc
e
s
s
e
d
th
r
ough
di
f
f
e
r
e
nt
s
te
ps
to
obt
a
in
c
le
a
r
e
s
t
pos
s
ib
le
im
a
ge
T
ha
t
m
a
ke
th
e
i
de
nt
if
ic
a
ti
on
pr
oc
e
s
s
s
im
pl
e
r
a
nd
m
or
e
r
e
li
a
bl
e
.
T
he
n
c
ont
our
le
t
tr
a
ns
f
or
m
a
ti
on
w
a
s
u
s
e
d
f
or
f
e
a
tu
r
e
e
xt
r
a
c
ti
on
of
e
a
c
h
pa
r
ti
c
ul
a
r
C
B
C
T
im
a
g
e
.
F
in
a
ll
y,
th
e
P
S
O
a
lg
or
it
hm
w
a
s
im
pl
e
m
e
nt
e
d
on
th
e
e
xt
r
a
c
te
d
f
e
a
tu
r
e
s
f
or
id
e
nt
if
ic
a
ti
on
pr
oc
e
s
s
.
T
he
ne
w
hybr
id
P
S
O
m
e
th
od
w
a
s
f
a
s
te
r
a
nd
yi
e
ld
e
d
m
or
e
a
c
c
ur
a
te
r
e
s
ul
t,
a
nd
th
e
u
s
e
of
C
B
C
T
r
a
di
ogr
a
phs
im
a
ge
s
w
hi
c
h
gi
ve
s
in
f
or
m
a
ti
on
not
f
ound
w
i
th
th
e
tr
a
di
ti
ona
l
two
-
di
m
e
ns
io
n
im
a
gi
ng
a
dde
d
a
s
tr
e
ngt
h
poi
nt
to
th
e
r
e
s
e
a
r
c
h.
A
ls
o,
th
e
pr
oc
e
s
s
of
hybr
id
iz
in
g
th
e
ps
o
a
lg
or
it
hm
w
it
h
a
c
ont
our
le
t
t
r
a
ns
f
or
m
a
ti
on
a
dde
d
s
tr
e
ngt
h
to
th
e
a
lg
or
it
hm
w
hi
c
h
im
pr
ove
d
th
e
e
f
f
ic
ie
nc
y
of
th
e
a
lg
or
it
hm
.
A
c
om
pa
r
is
on
w
it
h r
e
la
te
d pr
e
vi
ous
s
tu
di
e
s
w
e
r
e
de
s
c
r
ib
e
d i
n
T
a
bl
e
1.
T
a
bl
e
1. C
om
pa
r
is
on
s
w
it
h r
e
l
a
te
d s
tu
di
e
s
No
R
e
s
e
a
r
c
h na
m
e
A
l
gor
i
t
hm
s
/
m
e
t
hods
N
o. of
i
m
a
ge
s
R
e
c
ogni
t
i
on r
a
t
e
1
D
e
nt
a
l
bi
om
e
t
r
i
c
s
f
or
hum
a
n
i
de
nt
i
f
i
c
a
t
i
on
ba
s
e
d
on
de
nt
a
l
w
or
k
a
nd
i
m
a
ge
pr
ope
r
t
i
e
s
i
n
P
e
r
i
a
pi
c
a
l
r
a
di
ogr
a
phs
/
2012
m
a
t
he
m
a
t
i
c
a
l
m
or
phol
ogi
c
a
l
ope
r
a
t
i
ons
30 X
-
r
a
y
i
m
a
ge
s
90%
2
H
um
a
n
i
de
nt
i
f
i
c
a
t
i
on
us
i
ng
de
nt
a
l
bi
om
e
t
r
i
c
s
/
2014
S
ha
pe
r
e
gi
s
t
r
a
t
i
on m
e
t
hod, e
uc
l
i
di
a
n
di
s
t
a
nc
e
t
e
n nor
m
a
l
i
m
a
ge
s
a
nd f
i
f
t
y f
i
ve
O
P
G
i
m
a
ge
s
72%
3
H
um
a
n
i
de
nt
i
f
i
c
a
t
i
on
us
i
ng
de
nt
a
l
bi
om
e
t
r
i
c
a
na
l
ys
i
s
/
2015
D
i
f
f
e
r
e
nt
m
e
t
hods
f
or
s
e
gm
e
nt
a
t
i
on
a
nd f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
c
ol
or
e
d t
e
e
t
h
i
m
a
ge
s
f
or
14
pe
r
s
ons
a
nd de
nt
a
l
r
a
di
ogr
a
phs
i
m
a
ge
s
f
or
45 pe
r
s
ons
E
qua
l
e
r
r
or
r
a
t
e
(
E
E
R
)
88.8%
f
or
c
ol
o
r
e
d
i
m
a
ge
s
85.7%
f
or
de
nt
a
l
r
a
di
ogr
a
phs
.
4
D
e
nt
a
l
X
-
R
a
y
ba
s
e
d
hum
a
n
i
de
nt
i
f
i
c
a
t
i
on
s
ys
t
e
m
f
or
f
or
e
ns
i
c
/
2017
S
t
a
nda
r
d de
vi
a
t
i
on (
S
T
D
)
,
E
ul
e
r
num
be
r
&
a
r
e
a
t
a
ke
n f
r
om
bi
t
e
-
w
i
ng
X
-
r
a
y i
m
a
ge
.
80 I
80 X
-
R
a
y
i
m
a
ge
s
70%
5
H
um
a
n i
de
nt
i
f
i
c
a
t
i
on w
i
t
h de
nt
a
l
pa
nor
a
m
i
c
r
a
di
ogr
a
phi
c
i
m
a
ge
s
/
2018
s
uppor
t
ve
c
t
or
m
a
c
hi
ne
&
gr
a
phi
c
a
l
pr
oba
bi
l
i
s
t
i
c
m
ode
l
s
206 X
-
R
a
y i
m
a
ge
s
of
170 va
r
i
ous
s
ubj
e
c
t
s
r
a
nk
-
1 pr
e
c
i
s
i
on of
81%
r
a
nk
-
2
a
c
c
ur
a
c
y of
89%
6
I
de
nt
i
f
i
c
a
t
i
on
ba
s
e
d
de
nt
a
l
i
m
a
ge
/
2018
M
e
a
n, di
s
t
a
n
c
e
, s
t
a
nda
r
d de
r
i
va
t
i
on
(
S
T
D
)
, va
r
i
a
nc
e
&
pr
i
nc
i
pa
l
c
om
pone
nt
a
na
l
ys
i
s
(
P
C
A
)
75 75 x
-
r
a
y i
m
a
ge
s
be
l
ongi
ng t
o 115
ppe
r
s
ons
(
f
i
ve
f
or
e
ve
r
y pe
r
s
on
89%
7
T
he
us
e
of
c
ont
our
l
e
t
t
r
a
ns
f
or
m
a
t
i
ons
i
n hybr
i
di
z
a
t
i
on a
nd
de
ve
l
opm
e
nt
of
a
n i
nt
e
l
l
i
ge
nt
P
S
O
a
l
gor
i
t
hm
t
o di
s
t
i
ngui
s
h c
bc
t
r
a
di
a
t
i
on i
m
a
ge
/
2020
P
a
r
t
i
c
l
e
s
w
a
r
m
opt
i
m
i
z
a
t
i
on &
c
ont
our
l
e
t
t
r
a
ns
f
or
m
a
t
i
on
100 C
B
C
T
r
a
di
ogr
a
phs
i
m
a
ge
s
98%
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
I
de
nt
if
y
t
oot
h c
one
be
am
c
om
put
e
d
to
m
ogr
aph
y
bas
e
d on
c
ont
our
le
t
par
ti
c
le
…
(
H
ib
a A
dr
e
e
s
e
Y
ouni
s
)
399
2.
T
H
E
C
O
N
E
B
E
A
M
C
O
M
P
U
T
E
D
T
O
M
O
G
R
A
P
H
Y
A
r
a
i
e
t
al
.
[
10]
a
nd
M
oz
z
o
e
t
al
.
[
11]
w
or
ki
ng
s
e
pa
r
a
te
ly
,
pr
e
s
e
nt
e
d
th
e
C
B
C
T
f
or
t
he
or
a
l
a
nd
m
a
xi
ll
of
a
c
ia
l
a
ppl
ic
a
ti
ons
a
nd
li
ke
c
om
put
e
d
to
m
ogr
a
phy
(
CT
)
,
of
f
e
r
e
d
3D
in
ve
s
ti
ga
ti
on
a
nd
in
c
r
e
a
s
in
gl
y
pr
e
c
is
e
im
a
gi
ng
c
ont
r
a
s
te
d
w
it
h
2D
im
a
gi
ng.
T
he
f
in
a
nc
ia
ll
y
s
a
vvy
in
nova
ti
on
of
C
B
C
T
,
pr
om
pt
e
d
qui
c
k
e
nt
r
a
nc
e
in
to
th
e
f
ie
ld
of
de
nt
is
tr
y
w
i
th
in
te
r
e
s
t
f
or
r
e
s
pons
ib
il
it
y
of
de
nt
a
l
e
xpe
r
ts
a
nd
de
nt
a
l
in
s
tr
uc
to
r
s
to
in
ve
s
ti
ga
te
th
e
us
e
s
of
C
B
C
T
in
nova
ti
on.
R
a
di
ogr
a
phi
c
a
s
s
e
s
s
m
e
nt
is
ne
c
e
s
s
a
r
y
in
di
a
gnos
is
tr
e
a
tm
e
nt
pl
a
nni
ng
in
de
nt
is
tr
y.
A
s
id
e
f
r
om
pa
c
ki
ng
th
r
e
e
-
di
m
e
ns
io
na
l
li
f
e
s
tr
uc
tu
r
e
s
of
t
he
z
one
be
in
g
r
a
di
ogr
a
phe
d
in
to
a
two
-
di
m
e
ns
io
na
l
pi
c
tu
r
e
,
2D
im
a
gi
ng
ha
s
m
a
ny
im
por
ta
nt
dr
a
w
ba
c
ks
(
in
c
lu
di
ng
m
a
gni
f
ic
a
ti
on,
di
s
to
r
ti
on,
a
nd
s
upe
r
im
pos
it
io
n)
,
to
ge
th
e
r
pr
om
pt
in
g
di
s
to
r
ti
on
o
f
s
tr
uc
tu
r
e
s
[
12]
.
T
he
a
ppl
ic
a
ti
ons
of
C
B
C
T
in
de
nt
is
tr
y
in
c
lu
de
as
:
i)
i
m
pl
a
nt
ol
ogy:
m
is
s
in
g
t
e
e
th
s
ub
s
ti
tu
ti
on
by
de
nt
a
l
im
pl
a
nt
s
r
e
que
s
ts
pr
e
c
is
e
vi
s
ua
li
z
a
ti
on
of
th
e
s
ur
gi
c
a
l
s
it
e
f
or
th
e
s
uc
c
e
s
s
f
ul
im
pl
a
nt
in
s
ta
ll
a
ti
on
a
nd
to
ke
e
p
a
w
a
y
f
r
om
da
m
a
ge
to
a
dj
a
c
e
nt
im
por
ta
nt
s
tr
uc
tu
r
e
s
;
ii
)
o
r
a
l
a
nd
m
a
xi
ll
of
a
c
ia
l
s
ur
ge
r
y,
or
th
odonti
c
s
,
e
nd
odonti
c
s
,
pe
r
io
dont
ic
s
;
ii
i)
a
ppl
ic
a
ti
on
s
in
te
m
por
om
a
nd
ib
ul
a
r
jo
in
t
di
s
or
de
r
s
;
iv
)
a
ppl
ic
a
ti
on
s
in
f
or
e
ns
ic
de
nt
is
tr
y:
one
of
th
e
pa
r
ts
of
f
or
e
ns
ic
de
nt
is
tr
y
is
a
ge
e
s
ti
m
a
ti
on. E
na
m
e
l
i
s
u
s
ua
ll
y r
e
s
i
s
ta
nt
t
o c
h
a
nge
s
be
yond
or
di
na
r
y w
e
a
r
a
nd t
e
a
r
;
on t
he
ot
he
r
ha
nd, t
he
pul
pode
nt
in
a
l
c
om
pl
e
x
di
s
pl
a
y
s
phys
io
lo
gi
c
a
nd
pa
th
ol
ogi
c
a
la
l
te
r
a
ti
ons
w
it
h
a
gi
n
g.
u
s
ua
ll
y,
to
m
e
a
s
ur
e
th
e
s
e
c
ha
nge
s
,
e
xt
r
a
c
ti
on
a
nd
s
e
gm
e
nt
in
g
of
te
e
th
is
vi
t
a
l,
w
hi
c
h
i
s
n'
t
c
ons
ta
nt
ly
a
pr
a
c
ti
c
a
bl
e
de
c
i
s
io
n.
C
B
C
T
,
c
onve
r
s
e
ly
, pr
ovi
de
s
a
non
-
in
va
s
iv
e
s
ubs
ti
tu
te
;
a
nd v)
v
ir
tu
a
l
tr
e
a
tm
e
nt
pl
a
nni
ng a
nd s
im
ul
a
ti
ons
[
13]
.
3.
C
O
N
T
O
U
R
L
E
T
A
L
G
O
R
I
T
H
M
I
t
is
a
tr
ue
w
a
y
to
r
e
pr
e
s
e
nt
two
-
di
m
e
ns
io
na
l
im
a
ge
s
,
a
nd
i
s
a
ne
w
w
a
y
to
e
f
f
e
c
ti
ve
ly
r
e
pr
e
s
e
nt
th
e
c
ont
our
a
nd
te
xt
ur
e
of
im
a
ge
s
[
14]
.
T
he
tr
a
ns
f
or
m
a
ti
on
c
ons
is
ts
of
two
-
la
ye
r
f
il
te
r
s
,
w
he
r
e
th
e
la
pl
a
c
e
pyr
a
m
id
tr
a
ns
f
or
m
a
ti
on
is
us
e
d
to
a
c
hi
e
ve
m
ul
ti
-
dom
a
in
a
na
ly
s
is
a
nd
obt
a
in
di
s
c
ont
in
uous
poi
nt
s
.
A
f
te
r
th
is
,
th
e
m
ul
ti
di
r
e
c
ti
ona
l
a
na
ly
s
is
is
c
a
r
r
ie
d
out
by
th
e
di
r
e
c
ti
ona
l
f
il
te
r
ba
nk
in
or
de
r
to
c
onne
c
t
th
e
non
-
c
ont
in
uous
poi
nt
s
in
th
e
f
or
m
of
a
li
ne
a
r
s
tr
uc
tu
r
e
[
15]
,
[
16]
.
B
y
in
c
or
por
a
ti
ng
th
e
la
pl
a
c
e
pyr
a
m
id
a
nd
th
e
di
r
e
c
ti
ona
l
f
il
te
r
ba
nk i
t
pr
oduc
e
s
a
m
ul
ti
-
di
r
e
c
ti
on
a
l
f
il
te
r
[
17]
.
3
.1. L
ap
la
c
e
's
p
yr
am
id
O
f
f
e
r
s
th
e
m
e
a
ns
to
a
c
hi
e
ve
m
ul
ti
s
c
a
le
de
c
om
pos
it
io
n.
I
n
e
a
c
h
s
te
p
of
de
c
om
pos
it
io
n
it
p
r
oduc
e
s
a
lo
w
pa
s
s
do
w
ns
a
m
pl
e
d
ve
r
s
io
n
of
th
e
or
ig
in
a
l
im
a
ge
a
nd
a
ba
ndpa
s
s
im
a
ge
.
A
c
o
a
r
s
e
im
a
g
e
w
it
h
lo
w
f
r
e
que
nc
ie
s
a
nd
a
m
or
e
a
c
c
ur
a
te
im
a
ge
w
it
h
a
ddi
ti
ona
l
hi
gh
f
r
e
que
nc
ie
s
in
c
lu
di
ng
poi
nt
di
s
c
ont
in
ui
ti
e
s
a
r
e
pr
oduc
e
d.
T
hi
s
pa
tt
e
r
n
c
a
n
be
r
e
p
e
a
te
d
c
ont
in
uou
s
ly
in
th
e
lo
w
pa
s
s
im
a
g
e
a
nd
is
r
e
s
tr
ic
te
d
onl
y
f
r
om
th
e
s
i
z
e
of
t
he
or
ig
in
a
l
im
a
ge
B
e
c
a
us
e
of
t
he
dow
n
s
a
m
pl
in
g
[
14]
.
3
.2.
D
ir
e
c
t
io
n
al
f
il
t
e
r
b
an
k
T
he
di
r
e
c
ti
ona
l
f
il
te
r
ba
nk
(
D
F
B
)
is
de
s
ig
ne
d
to
obt
a
in
hi
gh
f
r
e
que
nc
y
c
ont
e
nt
s
s
uc
h
a
s
s
m
oot
h
c
ir
c
um
f
e
r
e
nc
e
a
nd
di
r
e
c
ti
ona
l
e
dge
s
[
18]
.
T
he
D
F
B
a
na
ly
z
e
s
e
a
c
h
de
ta
il
e
d
s
ub
-
r
a
nge
f
r
om
la
pl
a
c
e
'
s
pyr
a
m
id
(
LP
)
to
a
num
be
r
o
f
di
r
e
c
ti
ona
l
s
ub
-
r
a
nge
s
. T
he
pa
c
ka
g
e
pa
s
s
in
g i
m
a
ge
s
f
r
om
t
he
L
P
a
r
e
f
e
d i
nt
o D
F
B
s
o t
ha
t
di
r
e
c
ti
ona
l
in
f
or
m
a
ti
on
c
a
n
be
obt
a
in
e
d.
T
he
s
c
h
e
m
e
of
th
e
m
ul
ti
la
ye
r
de
c
om
pos
it
io
n
(
C
ont
our
le
t)
.
T
he
m
e
r
gi
ng be
twe
e
n L
P
a
nd
D
F
B
f
or
m
s
a
dua
l
f
il
te
r
ba
nk w
hi
c
h i
s
c
a
ll
e
d a
pyr
a
m
id
a
l
di
r
e
c
ti
ona
l
f
il
te
r
ba
nk t
ha
t
a
na
ly
z
e
s
th
e
im
a
ge
in
to
di
r
e
c
ti
ona
l
s
ubdom
a
in
s
w
it
h
m
ul
ti
pl
e
s
c
a
le
s
[
14]
,
[
19]
.
F
i
g
ur
e
1
s
how
s
th
e
c
ont
our
le
t
tr
a
ns
f
o
r
m
di
a
gr
a
m
.
F
ig
ur
e
1
.
C
ont
our
le
t
tr
a
ns
f
or
m
di
a
gr
a
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
11
, N
o.
1
,
M
a
r
c
h
20
22
:
397
-
404
400
4.
P
R
O
P
O
S
E
D
A
L
G
O
R
I
T
H
M
4
.1.
P
r
e
p
r
oc
e
s
s
in
g
T
hi
s
i
s
ve
r
y
im
por
ta
nt
s
te
p
w
hi
c
h
in
c
lu
d
e
s
th
e
ba
s
ic
s
te
ps
pe
r
f
or
m
e
d
on
C
B
C
T
im
a
ge
s
.
T
he
s
e
s
te
p
s
im
pr
ove
t
he
i
m
a
ge
qua
li
ty
a
nd f
a
c
il
it
a
te
t
o
us
e
i
n t
he
ne
xt
s
ta
ge
s
. T
he
s
te
ps
of
pr
im
a
r
y pr
oc
e
s
s
in
g i
nc
lu
de
t
he
f
ol
lo
w
in
g F
ig
ur
e
2:
−
T
a
ki
ng C
B
C
T
i
m
a
ge
s
f
or
a
gr
oup
of
pe
r
s
ons
a
nd i
nc
or
por
a
ti
ng
th
e
m
i
nt
o t
he
s
ugge
s
te
d da
ta
ba
s
e
s
ys
te
m
a
s
s
how
n
F
ig
ur
e
2(
a
)
T
he
n
a
ll
th
e
C
B
C
T
im
a
ge
s
w
e
r
e
r
e
a
d
f
r
om
th
e
a
va
il
a
bl
e
s
ys
te
m
da
ta
ba
s
e
s
o
th
e
pr
e
pr
oc
e
s
s
in
g s
ta
r
ts
f
or
e
ve
r
y i
m
a
ge
a
c
c
or
di
ng t
o t
he
f
ol
lo
w
in
g s
te
ps
.
−
T
he
C
B
C
T
i
m
a
g
e
s
a
r
e
c
onv
e
r
te
d f
r
om
(
R
G
B
)
t
o g
r
a
y s
c
a
le
a
s
s
how
n F
ig
ur
e
2(
b)
.
−
I
m
pr
ovi
ng
th
e
gr
a
y
s
c
a
le
im
a
ge
c
ol
or
di
s
tr
ib
ut
io
n
by
c
ha
ngi
ng
c
ol
or
pi
xe
ls
va
lu
e
s
th
r
ough
th
e
us
e
of
c
ont
r
a
s
t
li
m
it
e
d
a
t
a
da
pt
iv
e
hi
s
to
gr
a
m
e
qua
li
z
a
ti
on
(
C
L
A
H
S
)
,
w
hi
c
h
is
one
of
th
e
m
or
phol
ogi
c
a
l
a
lg
or
it
hm
s
w
he
r
e
th
e
r
e
s
ul
t
us
e
d
a
s
a
m
a
s
k
f
or
th
e
ne
xt
[
20
]
.
T
hi
s
s
te
p
im
pr
ove
s
th
e
im
a
ge
to
a
g
r
e
a
t
e
xt
e
nt
s
o
th
e
te
e
th
,
f
a
c
ia
l
bone
s
a
nd
th
e
bone
s
s
ur
r
ounding
th
e
te
e
th
a
ppe
a
r
in
da
r
k
c
ol
or
s
w
it
h
a
hi
ghe
r
c
ont
r
a
s
t
a
s
s
ho
w
n i
n F
ig
ur
e
2(
c
)
.
−
U
s
in
g
a
not
he
r
m
or
phol
ogi
c
a
l
a
lg
or
it
hm
known
a
s
(
E
r
ode
)
a
nd
a
ppl
yi
ng
it
to
th
e
pr
e
vi
ous
m
a
s
k
in
or
de
r
to
r
e
s
to
r
e
th
e
po
s
s
ib
le
lo
s
t
pa
r
ts
of
th
e
im
a
ge
in
th
e
pr
e
vi
ou
s
s
t
a
ge
s
th
r
ough
th
e
us
e
of
S
E
=
1,
a
nd “
di
s
k”
f
unc
ti
on w
he
r
e
t
he
y a
r
e
us
e
d i
n r
a
pi
dl
y
r
e
s
to
r
in
g t
he
l
os
t
pa
r
ts
w
it
hout
a
f
f
e
c
ti
ng t
he
ba
s
ic
f
e
a
tu
r
e
s
of
t
h
e
im
a
ge
[
21]
.
s
o,
th
e
te
e
th
,
ja
w
s
a
nd
f
a
c
i
a
l
bone
s
be
c
om
e
m
or
e
c
l
e
a
r
.
T
hi
s
s
te
p w
il
l
r
e
s
ul
t
to
a
d
a
r
k
im
a
ge
th
a
t
f
oc
us
e
s
on t
he
c
a
vi
ti
e
s
a
nd bon
e
s
a
s
s
how
n i
n F
ig
ur
e
2(
d)
.
−
A
ppl
yi
ng
one
of
th
e
m
or
phol
ogi
c
a
l
m
e
th
od
s
na
m
e
d
(
m
or
phol
ogi
c
a
l
r
e
c
ons
tr
uc
ti
on)
be
twe
e
n
th
e
m
a
s
k
a
nd
im
a
ge
r
e
s
ul
te
d
f
r
om
th
e
pr
e
vi
ous
s
ta
ge
w
he
r
e
th
e
c
ont
a
c
te
d
poi
nt
s
in
th
e
im
a
ge
s
a
r
e
e
xt
r
a
c
te
d
a
nd
r
e
a
r
r
a
nge
d
in
a
ne
w
im
a
ge
[
22]
.
T
hi
s
m
e
th
od
ut
il
iz
e
s
th
e
gr
a
y
c
ol
or
s
in
a
hybr
id
w
a
y
a
nd
r
e
bui
ld
s
th
e
m
in
a
be
tt
e
r
c
ondi
ti
on. T
he
r
e
s
ul
ts
of
t
hi
s
s
ta
ge
c
a
n be
not
ic
e
d i
n
F
ig
ur
e
2(
e
)
.
−
T
he
r
e
s
ul
t
f
r
om
t
hi
s
s
ta
ge
ga
ve
a
c
le
a
r
,
l
e
s
s
noi
s
e
i
m
a
ge
w
hi
c
h c
onc
e
nt
r
a
ti
ng on the
t
e
e
th
a
nd bone
s
. t
h
e
m
or
phol
ogi
c
a
l
m
e
th
ods
a
nd
f
il
te
r
s
a
r
e
c
ons
id
e
r
e
d
e
f
f
e
c
ti
ve
in
t
he
im
a
ge
im
pr
ove
m
e
nt
pr
oc
e
s
s
a
nd
c
ol
or
r
e
di
s
tr
ib
ut
io
n
[
23]
.
−
I
m
pl
e
m
e
nt
in
g
s
ha
r
pe
ni
ng
f
or
im
a
ge
im
pr
ove
m
e
nt
in
or
de
r
t
o
m
a
ke
th
e
bor
de
r
s
be
m
a
r
ke
d
c
l
e
a
r
ly
in
c
lu
di
ng
th
e
e
dge
s
of
th
e
te
e
th
,
bone
s
a
nd
c
a
vi
ti
e
s
.
A
ls
o,
de
nt
a
l
f
il
li
ngs
a
nd
th
e
f
ix
e
d
de
nt
ur
e
s
a
r
e
s
e
e
n
in
a
c
le
a
r
w
hi
te
c
ol
or
a
s
s
ho
w
n i
n F
ig
ur
e
2(
f
)
.
−
T
he
i
m
a
ge
i
s
c
onve
r
te
d t
o bi
na
r
y a
s
s
how
n i
n t
he
F
ig
ur
e
2(
g)
.
−
T
he
bl
a
c
k
r
ow
s
a
nd
c
ol
or
s
s
ur
r
ounding
th
e
te
e
th
s
a
nd
bone
s
a
r
e
de
le
te
d
f
r
om
th
e
C
B
C
T
im
a
ge
s
a
s
s
how
n
in
F
ig
ur
e
2(
h)
.
(
a
)
(
b)
(
c
)
(
d)
(
e
)
(f)
(
g)
(
h)
F
ig
ur
e
2. P
r
e
pr
oc
e
s
s
in
g s
te
ps
r
e
s
ul
ts
f
or
C
B
C
T
i
m
a
ge
, w
he
r
e
(
a
)
t
he
s
our
c
e
i
m
a
ge
of
C
B
C
T
,
(
b)
t
he
C
B
C
T
im
a
ge
a
f
te
r
c
onve
r
te
d f
r
om
(
R
G
B
)
t
o g
r
a
y s
c
a
le
, (
c
)
t
he
C
B
C
T
im
a
ge
a
f
te
r
us
in
g m
or
phol
ogi
c
a
l
a
lg
or
it
hm
s
(
C
L
A
H
S
)
,
(
d)
th
e
C
B
C
T
i
m
a
g
e
a
f
te
r
a
ppl
yi
ng mor
phol
ogi
c
a
l
a
lg
or
it
hm
(
E
r
ode
)
,
(
e
)
t
he
C
B
C
T
i
m
a
ge
a
f
te
r
a
ppl
yi
ng mor
phol
ogi
c
a
l
r
e
c
ons
tr
uc
ti
on, (
f
)
i
m
pl
e
m
e
nt
in
g s
ha
r
p
e
ni
ng f
or
t
he
C
B
C
T
i
m
a
ge
,
(
g)
th
e
pr
e
vi
ous
C
B
C
T
i
m
a
g
e
c
onve
r
te
d t
o bi
na
r
y,
a
nd
(
h)
a
f
te
r
de
le
ti
ng t
he
bl
a
c
k r
ow
s
a
nd c
ol
or
s
s
ur
r
ounding t
he
t
e
e
th
s
a
nd bone
s
f
r
om
out
put
i
m
a
ge
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
I
de
nt
if
y
t
oot
h c
one
be
am
c
om
put
e
d
to
m
ogr
aph
y
bas
e
d on
c
ont
our
le
t
par
ti
c
le
…
(
H
ib
a A
dr
e
e
s
e
Y
ouni
s
)
401
4
.2.
F
e
at
u
r
e
e
xt
r
ac
t
io
n
T
he
e
nha
nc
e
d
im
a
ge
s
r
e
s
ul
te
d
f
r
om
pr
e
vi
ous
s
ta
ge
a
r
e
f
e
d
in
to
2
-
le
ve
l
c
ont
our
le
t
tr
a
ns
f
or
m
a
ti
on
f
or
f
e
a
tu
r
e
e
xt
r
a
c
ti
on.
T
he
c
oe
f
f
ic
ie
nt
s
w
e
r
e
un
iq
ue
f
or
e
a
c
h
in
di
vi
dua
l
im
a
ge
w
hi
c
h
ga
ve
a
di
s
ti
nc
t
f
e
a
tu
r
e
f
or
th
e
pa
r
ti
c
ul
a
r
i
m
a
ge
a
nd t
he
r
e
by he
lp
e
d i
n t
he
ne
xt
s
te
p f
or
r
e
c
ogni
ti
on.
4
.3.
A
p
p
ly
c
on
t
ou
r
le
t
p
ar
t
ic
le
s
w
ar
m
op
t
im
iz
at
io
n
al
gor
it
h
m
T
he
m
a
in
i
de
a
i
s
t
o i
m
it
a
te
t
he
be
ha
vi
or
of
a
ni
m
a
ls
l
ooki
ng f
or
f
ood, s
uc
h
a
s
f
is
h, bi
r
ds
, or
be
e
s
[
24]
.
A
va
r
ie
ty
of
s
im
pl
e
va
r
ia
ti
ons
ha
ve
be
e
n
de
ve
lo
pe
d
in
or
de
r
to
in
c
r
e
a
s
e
th
e
s
pe
e
d
of
c
onve
r
ge
nc
e
a
nd
th
e
c
ons
is
te
nc
y of
t
he
s
ol
ut
io
n f
ound by the
P
S
O
[
25
]
. P
S
O
i
s
de
ve
lo
pe
d f
or
di
s
ti
ngui
s
hi
ng i
m
a
ge
s
e
nt
e
r
e
d e
a
s
il
y
us
in
g e
xt
r
a
c
te
d c
ont
our
le
t
c
oe
f
f
ic
ie
nt
s
a
s
t
he
f
ir
s
t
ge
ne
r
a
ti
on i
n
P
S
O
a
lg
or
it
hm
.
T
he
u
s
e
of
c
ont
our
le
t
c
oe
f
f
ic
ie
nt
s
r
e
s
ul
ti
ng
f
r
om
c
ont
our
le
t
tr
a
ns
f
or
m
a
ti
ons
a
s
in
put
to
th
e
P
S
O
a
lg
or
it
hm
m
a
de
th
e
a
lg
or
i
th
m
f
a
s
te
r
to
r
e
a
c
h
th
e
s
ol
ut
io
n
a
nd
ga
ve
m
or
e
a
c
c
ur
a
te
r
e
s
ul
ts
,
be
c
a
us
e
th
e
in
put
s
to
th
e
a
lg
or
it
hm
a
r
e
c
oe
f
f
ic
ie
nt
s
o
f
a
s
iz
e
le
s
s
th
a
n
th
e
s
iz
e
of
th
e
or
ig
in
a
l
im
a
ge
s
,
a
nd
th
e
r
e
f
or
e
th
e
num
be
r
of
it
e
r
a
ti
on ne
e
de
d t
o r
e
a
c
h t
he
r
e
qui
r
e
d r
e
s
ul
ts
be
c
a
m
e
l
e
s
s
by 1/
10, W
he
r
e
t
he
opt
im
a
l
s
ol
ut
io
n i
s
c
ont
in
uous
ly
s
e
a
r
c
he
d
f
or
in
th
e
s
e
tr
a
ns
a
c
ti
ons
unt
il
it
r
e
a
c
he
s
th
e
id
e
a
l
s
ol
ut
io
n
de
pe
ndi
ng
on
s
e
a
r
c
h
a
nd
r
e
pe
ti
ti
on.
T
he
P
S
O
a
lg
or
it
hm
c
ons
id
e
r
s
e
a
c
h
s
ol
ut
io
n
a
s
a
pa
r
ti
c
le
a
nd
h
a
s
t
w
o
s
ig
ni
f
ic
a
nt
c
h
a
r
a
c
te
r
is
ti
c
s
:
pos
it
io
n
n
a
nd
ve
lo
c
it
y
vi
.
T
he
two
c
ha
r
a
c
t
e
r
is
ti
c
s
a
r
e
r
e
la
te
d
to
e
a
c
h
pa
r
ti
c
l
e
.
S
o
th
a
t
n=
(n
j
1,
n
j
2
…,
nj
N
)
a
nd
vi
=
(
vi
j
1,
vi
j
2,…,vi
j
N
)
,
w
he
r
e
N
r
e
f
le
c
ts
t
he
di
m
e
ns
io
ns
of
t
he
pr
obl
e
m
a
nd a
t
e
a
c
h s
ta
ge
, t
he
pa
r
ti
c
le
s
i
n t
he
s
w
a
r
m
a
r
e
gi
ve
n
a
f
it
ne
s
s
f
unc
ti
on a
t
e
a
c
h s
ta
ge
of
th
e
s
e
a
r
c
h
f
or
a
s
ol
ut
io
n.
T
he
s
pe
e
d
a
nd
lo
c
a
ti
on
va
lu
e
s
a
r
e
m
odi
f
ie
d
in
a
c
c
or
da
nc
e
w
it
h t
he
(1
)
a
nd (
2)
:
v
=
w
∗
v
+
c
1
m
1
(
n
B
e
s
t
−
1
)
+
c
2
m
2
(
p
B
e
s
t
−
1
)
(
1)
n
=
n
+
v
∆
t
(
2)
w
he
r
e
W
:
r
e
pr
e
s
e
nt
s
w
e
ig
ht
of
in
e
r
ti
a
r
e
s
pons
ib
le
f
or
r
e
gul
a
ti
ng
th
e
im
pa
c
t
of
pa
r
ti
c
le
s
on
pa
s
t
ve
lo
c
it
ie
s
;
c
1
,
c
2
:
p
os
it
iv
e
c
ons
ta
nt
s
th
a
t
a
r
e
r
e
f
e
r
r
e
d
to
a
s
pa
r
a
m
e
te
r
s
of
a
c
c
e
le
r
a
ti
on
;
m
1
,
m
2
:
r
a
ndom
va
lu
e
s
in
e
a
c
h
a
ppe
a
r
a
nc
e
t
a
ke
on n
e
w
va
lu
e
s
;
Δ
t:
r
e
pr
e
s
e
nt
s
t
he
t
im
e
s
te
ps
;
B
e
s
t:
i
s
t
h
e
be
s
t
c
ur
r
e
nt
pos
it
io
n t
ha
t
h
a
s
e
nt
e
r
e
d
th
e
pa
r
ti
c
le
or
pa
s
s
e
d
it
unt
il
th
e
pr
e
s
e
nt
m
om
e
nt
;
pB
e
s
tI
t:
is
th
e
be
s
t
c
ur
r
e
nt
lo
c
a
ti
on
r
e
a
c
he
d
or
m
ove
d
by
a
pa
r
ti
c
le
of
ne
ig
hbor
in
g
pa
r
ti
c
le
s
unt
il
th
e
pr
e
s
e
nt
m
om
e
nt
.
T
he
c
ont
our
le
t
P
S
O
(
C
P
S
O
)
a
lg
or
it
hm
ps
e
udo
c
ode
w
il
l
be
:
Input:
C
r
e
a
t
e
c
o
m
m
u
n
i
t
y
m
e
m
b
e
r
s
i
t
e
s
by
i
n
i
t
i
a
l
i
z
e
d
p
o
s
i
t
i
o
n
r
a
n
d
o
m
l
y
o
f
t
h
e
p
r
a
c
t
i
c
e
s
:
n
j
(
0
)
a
n
d
v
e
l
o
c
i
t
y
v
j
(0)
.
O
u
t
p
u
t
:
-
b
e
s
t
p
o
s
i
t
i
o
n
o
f
t
h
e
g
l
o
b
a
l
o
p
t
i
m
a
n
*
.
F(n
j
)
=
f
i
t
n
e
s
s
,
W
h
i
c
h
i
s
c
a
l
c
u
l
a
t
e
d
f
r
o
m
e
q
u
a
t
i
o
n
[
2
6
]
:
SSIM
(
a
,
b)
=
(
(
2μ
_
a
μ
_
b
+
X
_
1
)
(
2σ
_
ab
+
X
_
2
)
)
/
(
(
μ
_
a
^
2
+
μ
_
b
^
2
+
X
_
1
)
(
μ
_
a
^
2
+
μ
_
b
^
2
+
X
_
2
)
)
(
3)
Begin
R
e
p
e
a
t
w
h
i
l
e
m
a
x
n
u
m
b
e
r
o
f
i
t
e
r
a
t
i
o
n
i
s
n
o
t
r
e
a
c
h
e
d
d
o
Begin
F
o
r
j
=
1
t
o
n
u
m
b
e
r
o
f
p
a
r
t
i
c
l
e
s
IF F(n
j
)
<F(n
newj
)
t
h
e
n
n
j
= n
new j
;
U
p
d
a
t
e
v
j
:
u
s
i
n
g
(
1
)
;
U
p
d
a
t
e
n
j
:
u
s
i
n
g
(
2
)
;
j++;
End
End
W
hi
le
f
it
ne
s
s
f
unc
ti
on
f
or
e
a
c
h
m
e
m
b
e
r
of
th
e
pr
im
a
r
y
c
om
m
uni
ty
is
done
us
in
g
th
e
s
im
il
a
r
it
y
s
c
a
le
f
unc
ti
on
(
S
S
I
M
)
,
w
he
r
e
:
μ
a
:
a
ve
r
a
ge
of
a
,
μ
b
:
a
ve
r
a
ge
of
b,
μ
a
2
:
va
r
ia
nc
e
of
a
,
μ
b
2
:
va
r
ia
nc
e
of
b,
σ
ab
:
C
ova
r
ia
nc
e
of
a
a
nd
b,
X
1
,
X
2
,a
r
e
T
w
o
va
r
ia
bl
e
s
t
o a
ll
ow
c
ons
i
s
te
nc
y
in
t
he
pa
r
ti
ti
on pr
oc
e
s
s
w
it
h
a
non
-
s
tr
ong
de
nom
in
a
to
r
.
T
he
f
ol
lo
w
in
g
F
ig
ur
e
3 s
um
m
a
r
ie
s
t
he
w
hol
e
w
or
k
.
5.
R
E
S
U
L
T
S
A
N
D
A
N
A
L
Y
S
I
S
T
he
r
e
s
ul
ts
obt
a
in
e
d
a
f
te
r
pr
oc
e
s
s
in
g
30
di
f
f
e
r
e
nt
C
B
C
T
im
a
ge
s
of
di
f
f
e
r
e
nt
pe
opl
e
us
in
g
th
e
pr
opos
e
d
a
lg
or
it
hm
(
C
P
S
O
)
,
a
s
s
how
n i
n T
a
bl
e
2 a
nd F
ig
ur
e
4
.
It
s
how
e
d 100%
de
te
c
ti
on
r
a
te
i
n t
he
t
r
a
in
in
g s
ta
ge
,
it
is
th
e
opt
im
um
va
lu
e
obt
a
in
e
d
f
r
om
a
ny
r
e
c
ogni
ti
on
s
ys
te
m
.
I
n
th
e
te
s
ti
ng
s
ta
ge
,
a
not
he
r
57
di
f
f
e
r
e
nt
r
a
di
ogr
a
phs
ha
ve
be
e
n
pr
oc
e
s
s
e
d
a
nd
th
e
r
e
s
ul
t
s
w
e
r
e
98%
.
w
h
e
n
m
in
or
c
ha
n
ge
s
to
th
e
r
a
di
ogr
a
ph
s
w
e
r
e
m
a
de
on
13
im
a
ge
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
11
, N
o.
1
,
M
a
r
c
h
20
22
:
397
-
404
402
be
lo
ngi
ng
to
th
e
s
a
m
e
pe
r
s
ons
th
e
s
e
c
ha
nge
s
in
c
lu
de
(
a
c
ha
n
ge
in
th
e
te
e
th
s
uc
h
a
s
e
xt
r
a
c
ti
on,
th
e
pl
a
c
e
m
e
nt
of
f
il
li
ngs
, or
a
c
ha
nge
i
n t
he
di
m
e
ns
io
ns
of
t
he
r
a
di
ogr
a
phs
of
t
he
s
a
m
e
pe
r
s
on)
T
he
r
e
s
ul
t
w
a
s
100%
.
F
ig
ur
e
3.
T
he
w
or
k s
ta
ge
s
T
a
bl
e
2. C
om
pa
r
is
on
s
w
it
h r
e
la
te
d s
tu
di
e
s
N
o. of
pr
oc
e
s
s
i
ng
T
ype
of
pr
oc
e
s
s
i
ng
T
ype
of
da
t
a
s
e
t
N
o. of
i
m
a
ge
s
DR
ER
WR
1
T
r
a
i
ni
ng
f
a
m
i
l
i
a
r
30
100
0
0
2
T
e
s
t
i
ng
f
a
m
i
l
i
a
r
57
98
1.8
5
3
T
e
s
t
i
ng
U
nf
a
m
i
l
i
a
r
(
a
f
t
e
r
c
ha
nge
s
)
13
100
0
0
F
ig
ur
e
4. R
e
s
ul
ts
of
pr
opos
e
d a
lg
or
it
hm
(
C
P
S
O
)
T
he
s
e
r
e
s
ul
ts
s
how
e
d
th
e
s
tr
e
ngt
h
of
th
e
s
ys
te
m
in
id
e
nt
if
yi
ng
de
nt
a
l
r
a
ys
th
r
ough
th
e
us
e
of
pr
im
a
r
y
tr
e
a
tm
e
nt
,
w
hi
c
h
s
how
e
d
th
e
ja
w
s
ve
r
y
c
le
a
r
ly
,
w
it
h
th
e
c
a
nc
e
ll
a
ti
on
of
a
ll
unw
a
nt
e
d
pa
r
ts
.
A
ls
o,
th
e
s
e
hi
gh
pe
r
c
e
nt
a
ge
s
s
how
how
im
por
ta
nt
it
is
to
us
e
t
h
e
c
ont
our
le
t
m
e
th
od
in
th
e
pr
oc
e
s
s
of
e
xt
r
a
c
ti
ng
f
e
a
tu
r
e
s
a
nd
id
e
nt
if
yi
ng
im
por
ta
nt
poi
nt
s
f
r
om
th
e
x
-
r
a
y
im
a
ge
s
a
nd
us
in
g
th
e
m
a
s
in
put
s
to
th
e
pr
opos
e
d
a
lg
or
it
hm
a
nd
obt
a
in
m
a
tc
hi
ng
r
e
s
ul
t
s
in
pr
ope
r
ti
e
s
by
m
e
a
ns
of
th
e
S
S
I
M
e
qua
ti
on,
w
hi
c
h
w
a
s
us
e
d
in
d
e
ve
lo
pi
ng
P
S
O
a
lg
or
it
hm
a
nd r
e
a
c
hi
ng t
he
goa
ls
di
r
e
c
tl
y w
it
h t
he
l
e
a
s
t
m
is
t
a
ke
s
.
T
he
s
c
a
le
us
e
d
to
c
a
lc
ul
a
te
th
e
ove
r
a
ll
de
gr
e
e
s
of
di
s
c
r
im
in
a
ti
on
in
th
e
s
ys
te
m
is
de
te
c
ti
on
r
a
te
(
4
)
.
W
he
r
e
t
hi
s
m
e
a
s
ur
e
r
e
pr
e
s
e
nt
s
t
he
a
bi
li
ty
of
t
he
s
y
s
te
m
t
o i
d
e
nt
if
y t
he
pe
r
s
on
t
o w
hom
t
h
e
i
ns
e
r
te
d de
nt
a
l
r
a
ys
be
lo
ng. T
he
r
e
f
or
e
, i
t
is
c
a
l
c
ul
a
te
d f
r
om
t
he
r
a
ti
o of
t
he
numbe
r
of
c
or
r
e
c
tl
y i
de
nt
if
ie
d de
nt
a
l
x
-
r
a
ys
t
o t
he
t
ot
a
l
num
be
r
of
x
-
r
a
y
i
m
a
ge
s
a
va
il
a
bl
e
in
th
e
s
ys
te
m
da
t
a
s
e
t.
T
he
r
e
f
or
e
,
th
e
hi
ghe
r
pe
r
c
e
nt
a
ge
of
th
is
s
c
a
le
is
c
ons
id
e
r
e
d
a
s
a
gr
e
a
te
r
f
or
c
e
f
or
th
e
s
ys
te
m
to
di
s
c
ove
r
th
e
id
e
nt
it
y
of
th
e
pe
opl
e
to
w
hom
th
e
s
e
r
a
ys
b
e
lo
ng.
T
hus
, t
he
va
lu
e
of
de
te
c
ti
on r
a
te
i
s
c
a
l
c
ul
a
te
d a
s
f
ol
lo
w
s
[
26]
.
D
e
t
e
c
t
io
n
R
a
t
e
(
DR
)
=
(
no
.
of
c
o
r
r
e
c
t
l
y
d
e
t
e
c
t
e
d
s
a
m
p
e
l
s
)
/
(
t
o
t
a
l
no
.
of
s
a
m
p
l
e
s
)
∗
100
(
4
)
T
he
e
xt
e
nt
of
th
e
s
ys
te
m
'
s
e
r
r
or
s
in
id
e
nt
if
yi
ng
pe
opl
e
w
ho
ha
ve
de
nt
a
l
r
a
di
a
ti
on
in
s
e
r
te
d
c
a
n
be
c
a
lc
ul
a
te
d
by
th
e
s
c
a
le
E
r
r
or
R
a
te
,
a
nd
th
a
t
w
a
s
1.8%
,
w
hi
c
h
is
a
s
m
a
ll
pe
r
c
e
nt
a
ge
th
a
t
w
a
s
c
a
lc
ul
a
te
d
by
th
e
(
5
)
.
T
hi
s
s
c
a
l
e
th
e
lo
w
e
r
it
s
v
a
lu
e
,
th
e
hi
ghe
r
th
e
s
ys
te
m
h
a
s
th
e
a
bi
li
ty
to
c
or
r
e
c
tl
y
a
c
hi
e
ve
goa
l
s
,
due
to
th
e
s
tr
e
ngt
h of
t
he
a
lg
or
it
hm
t
o f
in
d t
he
r
ig
ht
t
a
r
ge
t
s
a
nd
a
voi
d a
li
e
n t
a
r
ge
ts
,
T
hi
s
pe
r
c
e
nt
a
ge
c
a
n be
c
a
lc
ul
a
te
d
by t
he
r
a
ti
o of
t
he
numbe
r
o
f
i
m
a
ge
s
t
ha
t
w
e
r
e
not
f
ound
by t
he
s
ys
te
m
f
r
om
a
m
ong the
i
m
a
ge
s
e
nt
e
r
e
d t
o t
he
num
be
r
of
i
m
a
ge
s
i
n t
he
s
ys
te
m
da
ta
s
e
t
[
26]
.
Er
r
o
r
R
a
t
e
=
(
no
.
of
fa
l
s
e
d
e
t
e
c
t
e
d
s
a
m
p
l
e
s
)
/
(
t
o
t
a
l
no
.
of
s
a
m
p
l
e
s
)
∗
100
(
5)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
nt
J
A
r
ti
f
I
nt
e
ll
I
S
S
N
:
2252
-
8938
I
de
nt
if
y
t
oot
h c
one
be
am
c
om
put
e
d
to
m
ogr
aph
y
bas
e
d on
c
ont
our
le
t
par
ti
c
le
…
(
H
ib
a A
dr
e
e
s
e
Y
ouni
s
)
403
A
ls
o, t
he
w
r
ong a
c
c
e
pt
a
nc
e
r
a
te
(
6
)
i
n t
hi
s
s
ys
te
m
w
a
s
5%
, m
e
a
ni
ng t
ha
t
a
ny r
a
di
ogr
a
ph t
ha
t
doe
s
not
e
xi
s
t
in
th
e
r
a
di
ogr
a
ph
da
ta
s
e
t
of
th
e
s
ys
te
m
is
not
a
c
c
e
pt
e
d.
A
nd
th
is
w
a
s
done
a
c
c
or
di
ng
to
th
e
f
ol
lo
w
in
g
f
o
r
m
ul
a
[
27
]
,
[
28]
:
W
r
o
n
g
a
c
c
e
p
t
a
n
c
e
r
a
t
e
=
(
no
.
of
s
a
m
p
l
e
s
a
c
c
e
p
t
e
d
e
r
r
o
r
)
/
(
t
o
t
a
l
no
.
of
im
a
g
e
s
)
∗
100
(
6)
6.
C
O
N
C
L
U
S
I
O
N
T
he
in
it
ia
l
tr
e
a
tm
e
nt
s
ta
ge
s
th
a
t
w
e
r
e
pe
r
f
o
r
m
e
d
on
th
e
im
a
ge
s
c
ont
r
ib
ut
e
d
to
th
e
c
le
a
r
vi
s
ib
il
i
ty
o
f
th
e
r
a
di
ogr
a
ph a
nd i
n
t
ur
n he
lp
e
d
to
obt
a
in
hi
gh
r
e
s
ul
ts
i
n t
he
i
de
nt
if
ic
a
ti
on pr
oc
e
s
s
.
us
in
g c
ont
our
le
t
w
it
h t
he
in
te
ll
ig
e
nt
a
lg
or
it
hm
in
c
r
e
a
s
e
s
th
e
a
bi
l
it
y
of
th
e
a
lg
or
it
hm
to
f
i
nd
th
e
opt
im
a
l
s
ol
ut
io
n
e
f
f
e
c
ti
ve
ly
be
c
a
us
e
it
gi
ve
s
di
s
ti
nc
ti
ve
va
lu
e
s
f
or
e
a
c
h
im
a
ge
,
w
hi
c
h
r
e
pr
e
s
e
nt
th
e
c
ha
r
a
c
te
r
is
ti
c
s
a
nd
pr
ope
r
ti
e
s
of
th
a
t
pa
r
ti
c
ul
a
r
im
a
ge
.
T
he
c
ha
ll
e
nge
s
f
a
c
e
d
w
e
r
e
th
e
li
m
it
e
d
num
be
r
of
im
a
ge
s
a
va
il
a
bl
e
in
th
e
d
a
ta
ba
s
e
w
hi
c
h
w
e
r
e
u
s
e
d
in
th
e
tr
a
in
in
g
a
nd
te
s
ti
ng
s
ta
ge
s
a
nd
di
f
f
ic
ul
ty
di
s
ti
ngui
s
hi
ng
in
t
he
c
a
s
e
of
te
e
th
f
a
ll
in
g
out
due
to
a
c
c
id
e
nt
s
or
in
th
e
c
a
s
e
of
de
nt
a
l
im
pl
a
nt
.
T
he
pr
oc
e
s
s
of
di
s
ti
ngui
s
hi
ng
de
nt
a
l
r
a
ys
is
a
good
w
a
y
to
di
s
ti
ngui
s
h
th
e
id
e
nt
it
y
of
pe
opl
e
,
e
s
p
e
c
ia
ll
y
a
f
te
r
phys
i
c
a
l
c
ha
ng
e
s
h
a
ve
oc
c
ur
r
e
d
to
th
e
e
xt
e
r
na
l
f
e
a
tu
r
e
s
of
th
e
hum
a
n
body
ove
r
ti
m
e
.
T
he
r
a
di
ogr
a
ph
id
e
nt
if
ic
a
ti
on
r
a
te
w
it
h
th
is
s
ys
te
m
w
a
s
hi
gh
c
om
pa
r
in
g
w
it
h
pr
e
vi
ous
r
e
la
te
d
s
tu
di
e
s
,
a
nd
th
us
t
he
hybr
id
iz
a
ti
on of
t
h
e
P
S
O
a
lg
or
it
hm
w
it
h t
he
C
ont
our
le
t
i
s
c
ons
id
e
r
e
d a
s
uc
c
e
s
s
f
ul
hybr
id
iz
a
ti
on.
7.
F
U
T
U
R
E
WORKS
T
he
pos
s
ib
il
it
y
of
m
a
ki
ng
c
ha
nge
s
to
a
num
be
r
of
pa
r
a
m
e
te
r
s
of
th
e
pr
opos
e
d
a
lg
or
it
hm
.
T
hi
s
in
c
lu
de
s
in
c
r
e
a
s
in
g
th
e
num
be
r
of
im
a
ge
s
a
c
qui
r
e
d
by
th
e
CBCT
r
a
ys
,
a
ls
o
in
c
r
e
a
s
in
g
th
e
num
be
r
of
le
ve
ls
in
th
e
c
ont
our
le
t
tr
a
ns
f
or
m
a
ti
on,
w
hi
c
h
le
a
ds
to
an
in
c
r
e
a
s
e
in
th
e
num
be
r
of
f
e
a
tu
r
e
s
(
c
oe
f
f
ic
ie
nt
s
)
in
th
e
im
a
ge
s
a
nd
obs
e
r
ve
th
e
m
a
gni
tu
de
of
th
e
s
e
e
f
f
e
c
ts
on
th
e
r
e
s
ul
ts
.
C
om
pa
r
i
s
on
of
r
e
s
ul
ts
us
in
g
th
e
pr
opos
e
d
a
lg
or
it
hm
on
bot
h
c
onve
nt
io
na
l
a
nd
C
B
C
T
r
a
di
ogr
a
phs
.
D
oi
ng
s
om
e
noi
s
e
on
th
e
im
a
ge
s
a
c
qui
r
e
d
in
th
e
da
ta
ba
s
e
,
a
ppl
yi
ng
to
th
e
m
th
e
s
te
ps
of
th
e
pr
opos
e
d
a
lg
or
it
hm
,
a
nd
obs
e
r
ve
t
he
e
f
f
e
c
t
of
th
is
on
th
e
r
e
s
ul
ts
.
U
s
e
de
nt
a
l
im
a
ge
s
t
o
de
te
r
m
in
e
th
e
i
de
nt
it
y
of
th
e
de
c
e
a
s
e
d
pe
r
s
on
by
m
a
tc
hi
ng
de
nt
a
l
im
a
ge
s
of
th
e
de
c
e
a
s
e
d
pe
r
s
on
pr
ovi
de
d
by
hi
s
r
e
la
ti
ve
s
.
T
h
e
us
e
of
ot
he
r
m
e
th
ods
in
th
e
di
s
c
r
im
in
a
ti
on
pr
oc
e
s
s
,
s
uc
h
as
m
a
c
hi
ne
le
a
r
ni
ng.
A
C
K
N
O
WL
E
D
G
E
M
E
N
T
S
G
r
e
a
t
th
a
nks
to
t
he
U
ni
ve
r
s
it
y of
M
os
ul
f
or
i
ts
s
uppor
t
a
nd a
s
s
i
s
ta
nc
e
dur
in
g m
a
ki
ng t
hi
s
r
e
s
e
a
r
c
h.
R
E
F
E
R
E
N
C
E
S
[
1]
A
.
J
a
i
n,
R
.
B
ol
l
e
,
a
nd
S
.
P
a
nka
nt
i
,
B
i
om
e
t
r
i
c
s
:
pe
r
s
onal
i
de
nt
i
f
i
c
at
i
on
i
n
ne
t
w
or
k
e
d
s
oc
i
e
t
y
.
U
S
A
:
K
l
uw
e
r
A
c
a
de
m
i
c
P
ubl
i
s
he
r
s
,
2006.
[
2]
A
.
M
or
a
l
e
s
,
M
.
A
.
F
e
r
r
e
r
,
a
nd
A
.
K
um
a
r
,
“
I
m
pr
ove
d
pa
l
m
pr
i
nt
a
ut
he
nt
i
c
a
t
i
on
us
i
ng
c
ont
a
c
t
l
e
s
s
i
m
a
gi
ng,”
S
e
p.
2010,
doi
:
10.1109/
B
T
A
S
.2010.5634472.
[
3]
S
J
e
ya
nt
hi
a
nd
N
U
m
a
M
a
he
s
w
a
r
i
a
nd
R
V
e
nka
t
e
s
h,
“
H
um
a
n
i
de
nt
i
f
i
c
a
t
i
o
n
us
i
ng
de
nt
a
l
bi
om
e
t
r
i
c
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
dv
anc
e
d E
ngi
ne
e
r
i
ng and G
l
obal
T
e
c
hnol
ogy
, vol
. 1, no. 5, 2013.
[
4]
S
.
C
.
D
i
ghe
a
nd
R
.
S
hr
i
r
a
m
,
“
D
e
nt
a
l
bi
om
e
t
r
i
c
s
f
or
hum
a
n
i
de
nt
i
f
i
c
a
t
i
on
ba
s
e
d
on
de
nt
a
l
w
or
k
a
nd
i
m
a
ge
pr
ope
r
t
i
e
s
i
n
P
e
r
i
a
pi
c
a
l
r
a
di
og
r
a
phs
,”
N
ov. 2012, doi
:
10.1109/
T
E
N
C
O
N
.2012.6412216.
[
5]
R
.
K
a
r
unya
,
A
.
A
s
ka
r
uni
s
a
,
a
nd
A
.
A
t
hi
r
a
j
a
,
“
H
um
a
n
i
de
nt
i
f
i
c
a
t
i
on
us
i
ng
de
nt
a
l
bi
om
e
t
r
i
c
s
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
A
ppl
i
e
d
E
ngi
ne
e
r
i
ng R
e
s
e
ar
c
h
, vol
. 9, no. 1, pp. 4428
–
4433, 2014.
[
6]
F
.
R
e
hm
a
n,
M
.
U
.
A
kr
a
m
,
K
.
F
a
r
a
z
,
a
nd
N
.
R
i
a
z
,
“
H
um
a
n
i
de
nt
i
f
i
c
a
t
i
on
u
s
i
ng
de
nt
a
l
bi
om
e
t
r
i
c
a
na
l
ys
i
s
,”
i
n
2015
F
i
f
t
h
I
nt
e
r
nat
i
onal
C
onf
e
r
e
nc
e
on
D
i
gi
t
al
I
nf
or
m
at
i
on
and
C
om
m
uni
c
at
i
on
T
e
c
hnol
ogy
and
i
t
s
A
ppl
i
c
at
i
ons
(
D
I
C
T
A
P
)
,
A
p
r
.
2015,
pp.
96
–
100,
doi
:
10.1109/
D
I
C
T
A
P
.
2015.7113178.
[
7]
A
. B
. O
kt
a
y, “
H
um
a
n i
de
nt
i
f
i
c
a
t
i
on w
i
t
h de
nt
a
l
pa
nor
a
m
i
c
r
a
di
ogr
a
phi
c
i
m
a
ge
s
,”
I
E
T
B
i
om
e
t
r
i
c
s
, vol
. 7, no. 4, pp. 349
–
355,
N
ov.
2018, doi
:
10.1049/
i
e
t
-
bm
t
.2017.0078.
[
8]
S
.
H
.
S
ha
ke
r
a
nd
H
.
N
a
j
a
h,
“
I
de
nt
i
f
i
c
a
t
i
on
ba
s
e
d
de
nt
a
l
i
m
a
ge
,”
J
our
nal
of
A
l
-
Q
adi
s
i
y
ah
f
or
c
om
put
e
r
s
c
i
e
nc
e
and
m
at
he
m
at
i
c
s
,
vol
. 10, no. 3, 2018, doi
:
10.29304/
j
qc
m
.2018.10.3.438.
[
9]
S
.
D
h
K
hudhur
a
nd
M
.
S
.
C
r
ooc
k,
“
D
e
nt
a
l
X
-
R
a
y
ba
s
e
d
hum
a
n
i
de
nt
i
f
i
c
a
t
i
on
s
ys
t
e
m
f
or
f
or
e
ns
i
c
,”
E
ngi
ne
e
r
i
ng
and
T
e
c
hnol
og
y
J
our
nal
, vol
. 35
, no. 1, pp. 49
–
60, 2017.
[
10]
Y
. A
r
a
i
, E
. T
a
m
m
i
s
a
l
o, K
. I
w
a
i
, K
. H
a
s
hi
m
ot
o, a
nd K
. S
hi
noda
,
“
D
e
ve
l
opm
e
nt
of
a
c
om
pa
c
t
c
om
put
e
d t
om
ogr
a
phi
c
a
ppa
r
a
t
us
f
or
de
nt
a
l
us
e
,”
D
e
nt
om
a
x
i
l
l
of
ac
i
al
R
adi
ol
ogy
, vol
. 28, no. 4, pp. 245
–
248, 1999, doi
:
10.1038/
s
j
.dm
f
r
.4600448.
[
11]
P
.
M
oz
z
o,
C
.
P
r
oc
a
c
c
i
,
A
.
T
a
c
c
oni
,
P
.
T
i
na
z
z
i
M
a
r
t
i
ni
,
a
nd
I
.
A
.
B
e
r
ga
m
o
A
ndr
e
i
s
,
“
A
ne
w
vol
um
e
t
r
i
c
C
T
m
a
c
hi
ne
f
or
de
nt
a
l
i
m
a
gi
ng
ba
s
e
d
on
t
he
c
one
-
be
a
m
t
e
c
hni
que
:
P
r
e
l
i
m
i
na
r
y
r
e
s
ul
t
s
,”
E
ur
ope
an
R
adi
ol
ogy
,
vol
.
8,
no.
9,
pp.
1558
–
1564,
N
ov.
1998,
doi
:
10.1007/
s
003300050586.
[
12]
W
. C
. S
c
a
r
f
e
a
nd A
.
G
. F
a
r
m
a
n, “
W
ha
t
i
s
c
one
-
be
a
m
C
T
a
nd how
doe
s
i
t
w
or
k
?
,”
D
e
nt
al
C
l
i
ni
c
s
of
N
o
r
t
h A
m
e
r
i
c
a
, vol
. 52, no.
4,
pp. 707
–
730, O
c
t
. 2008, doi
:
10.1016/
j
.c
de
n.2008.05.005.
[
13]
F
.
Y
a
ng,
R
.
J
a
c
obs
,
a
nd
G
.
W
i
l
l
e
m
s
,
“
D
e
nt
a
l
a
ge
e
s
t
i
m
a
t
i
on
t
hr
ou
gh
vol
um
e
m
a
t
c
hi
ng
of
t
e
e
t
h
i
m
a
ge
d
by
c
one
-
be
a
m
C
T
,”
F
or
e
ns
i
c
Sc
i
e
nc
e
I
nt
e
r
nat
i
onal
, vol
. 159, no. 1, pp. S
78
–
S
83, M
a
y 2006, doi
:
10.1016/
j
.f
or
s
c
i
i
nt
.2006.02.031.
[
14]
S
.
K
a
t
s
i
gi
a
nni
s
,
E
.
G
.
K
e
r
a
m
i
da
s
,
a
nd
D
.
M
a
r
oul
i
s
,
“
A
c
ont
our
l
e
t
t
r
a
ns
f
or
m
f
e
a
t
ur
e
e
xt
r
a
c
t
i
on
s
c
he
m
e
f
or
ul
t
r
a
s
ound
t
hyr
oi
d
t
e
xt
ur
e
c
l
a
s
s
i
f
i
c
a
t
i
on,”
F
i
nal
D
r
af
t
-
P
ubl
i
s
he
d
i
n
E
ngi
ne
e
r
i
ng
I
nt
e
l
l
i
ge
nt
Sy
s
t
e
m
s
,
Spe
c
i
al
i
s
s
ue
:
A
r
t
i
f
i
c
i
al
I
nt
e
l
l
i
ge
nc
e
A
ppl
i
c
at
i
ons
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8938
I
nt
J
A
r
ti
f
I
nt
e
ll
, V
ol
.
11
, N
o.
1
,
M
a
r
c
h
20
22
:
397
-
404
404
I
nnov
at
i
ons
, vol
. 18, no. 4, 2010.
[
15]
K
.
I
.
A
l
S
a
i
f
a
nd
M
.
M
.
S
a
l
i
h,
“
T
e
xt
e
m
be
d
di
ng
ba
s
e
d
on
c
ont
our
e
l
e
t
t
r
a
n
s
f
or
m
a
t
i
on
c
oe
f
f
i
c
i
e
nt
s
,”
I
nt
e
r
nat
i
onal
J
ou
r
nal
of
I
nf
or
m
at
i
on T
e
c
hnol
ogy
and B
us
i
ne
s
s
M
anage
m
e
nt
, vol
. 12, no. 1, pp. 60
–
67, 2
013.
[
16]
D
. G
uo a
nd J
. C
he
n, “
T
he
a
ppl
i
c
a
t
i
on of
c
ont
our
l
e
t
t
r
a
ns
f
or
m
t
o
i
m
a
ge
de
noi
s
i
ng,”
P
r
oc
e
di
a E
ngi
ne
e
r
i
ng
, vol
. 15, pp. 2333
–
2338,
2011, doi
:
10.1016/
j
.pr
oe
ng.2011.08.437.
[
17]
D
.
B
.
M
a
l
i
a
nd
J
.
B
.
J
a
dha
v,
“
P
e
r
f
o
r
m
a
nc
e
c
om
pa
r
i
s
on
of
c
ont
our
l
e
t
a
nd
w
a
ve
l
e
t
t
r
a
ns
f
or
m
i
n
de
noi
s
i
ng
of
ul
t
r
a
s
ound
i
m
a
ge
,”
I
nt
e
r
nat
i
onal
J
our
nal
of
D
e
v
e
l
opm
e
nt
R
e
s
e
ar
c
h
,
vol
. 8, no. 10, pp. 23405
–
2340
9, 2018.
[
18]
A
.
A
.
D
a
w
ood,
“
A
C
ont
our
l
e
t
-
B
a
s
e
d
I
m
a
ge
D
e
noi
s
i
ng
T
e
c
hni
que
W
i
t
h
C
oe
f
f
i
c
i
e
nt
T
hr
e
s
hol
d
L
e
ve
l
E
s
t
i
m
a
t
i
on.”
,
T
i
k
r
i
t
J
our
nal
O
f
E
ngi
ne
e
r
i
ng Sc
i
e
nc
e
s
, v
ol
.
20
, n
o.4
, pp.
11
-
22,
M
a
r
c
h
.
2013
.
[
19]
A
.
H
.
H
.
A
l
A
s
a
di
,
“
C
ont
our
l
e
t
t
r
a
ns
f
or
m
ba
s
e
d
m
e
t
hod
f
or
m
e
di
c
a
l
i
m
a
ge
de
n
oi
s
i
ng,”
I
nt
e
r
nat
i
onal
J
our
nal
of
I
m
age
P
r
oc
e
s
s
i
n
g
(
I
J
I
P
)
, vol
. 9, no. 1, pp. 22
–
31, 2015.
[
20]
N
.
M
.
S
a
s
i
a
nd
V
.
K
.
J
a
ya
s
r
e
e
,
“
C
ont
r
a
s
t
l
i
m
i
t
e
d
a
da
pt
i
ve
hi
s
t
ogr
a
m
e
q
ua
l
i
z
a
t
i
on
f
or
qua
l
i
t
a
t
i
ve
e
nha
nc
e
m
e
nt
of
m
yoc
a
r
di
a
l
pe
r
f
us
i
on i
m
a
ge
s
,”
E
ngi
ne
e
r
i
ng
, vol
. 05, no. 10, pp. 326
–
331, 2013, doi
:
10.42
36/
e
ng.2013.510B
066.
[
21]
B
.
G
a
t
os
,
S
.
J
.
P
e
r
a
nt
oni
s
,
N
.
P
a
pa
m
a
r
kos
,
a
nd
I
.
A
ndr
e
a
di
s
,
“
F
a
s
t
i
m
pl
e
m
e
nt
a
t
i
on
of
m
or
phol
ogi
c
a
l
ope
r
a
t
i
ons
u
s
i
ng
bi
na
r
y
i
m
a
g
e
bl
oc
k
de
c
om
pos
i
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
I
m
age
and
G
r
aphi
c
s
,
vol
.
4,
no.
2,
pp.
183
–
202,
A
pr
.
2004,
do
i
:
10.1142/
S
0219467804001361.
[
22]
L
.
V
i
nc
e
nt
,
“
M
or
phol
ogi
c
a
l
gr
a
ys
c
a
l
e
r
e
c
ons
t
r
uc
t
i
on:
D
e
f
i
ni
t
i
on,
e
f
f
i
c
i
e
nt
a
l
gor
i
t
h
m
a
nd
a
ppl
i
c
a
t
i
ons
i
n
i
m
a
ge
a
na
l
ys
i
s
,”
i
n
P
r
oc
e
e
di
ngs
of
t
he
I
E
E
E
C
om
put
e
r
Soc
i
e
t
y
C
onf
e
r
e
nc
e
on
C
om
put
e
r
V
i
s
i
on
and
P
at
t
e
r
n
R
e
c
ogni
t
i
on
,
1992,
vol
.
1992
-
J
une
,
pp.
633
–
635, doi
:
10.1109/
C
V
P
R
.1992.223122.
[
23]
I
.
J
i
ve
t
,
A
.
B
r
i
ndus
e
s
c
u,
a
nd
I
.
B
ogda
nov,
“
I
m
a
ge
c
ont
r
a
s
t
e
nha
nc
e
m
e
nt
us
i
ng
m
or
phol
ogi
c
a
l
de
c
om
pos
i
t
i
on
by
r
e
c
ons
t
r
uc
t
i
on,”
W
SE
A
S T
r
ans
ac
t
i
ons
on C
i
r
c
ui
t
s
and Sy
s
t
e
m
s
, vol
. 7, no. 8, pp. 822
–
831, A
ug.
2008.
[
24]
W
.
R
.
A
bdul
-
A
dhe
e
m
,
“
A
n
e
nha
nc
e
d
pa
r
t
i
c
l
e
s
w
a
r
m
opt
i
m
i
z
a
t
i
on
a
l
gor
i
t
hm
,”
I
nt
e
r
nat
i
onal
J
ou
r
nal
of
E
l
e
c
t
r
i
c
al
and
C
om
put
e
r
E
ngi
ne
e
r
i
ng
, vol
. 9, no. 6, pp. 4904
–
4907, D
e
c
. 2019, doi
:
10.11591/
i
j
e
c
e
.v9i
6.
pp4904
-
4907.
[
25]
D
.
P
a
l
upi
R
i
ni
,
S
.
M
a
r
i
ya
m
S
ha
m
s
uddi
n,
a
nd
S
.
S
ophi
ya
t
i
Y
uha
ni
z
,
“
P
a
r
t
i
c
l
e
s
w
a
r
m
opt
i
m
i
z
a
t
i
on:
t
e
c
hni
que
,
s
y
s
t
e
m
a
nd
c
ha
l
l
e
nge
s
,”
I
nt
e
r
nat
i
onal
J
ou
r
nal
of
C
om
put
e
r
A
ppl
i
c
at
i
ons
, vol
. 14, no. 1, pp. 19
–
27, J
a
n. 2011, doi
:
10.5120/
1810
-
2331.
[
26]
D
.
S
.
H
a
m
m
a
di
,
A
.
N
.
Y
O
U
N
I
S
,
a
nd
F
.
M
.
R
A
M
O
,
“
H
ybr
i
di
z
a
t
i
on
a
nd
m
odi
f
i
c
a
t
i
on
of
t
he
ps
o
a
l
gor
i
t
hm
a
nd
i
t
s
us
e
i
n
pe
r
s
ona
l
r
e
c
ogni
t
i
on by o
pg x
-
r
a
y,”
J
our
nal
of
E
ngi
ne
e
r
i
ng Sc
i
e
nc
e
and T
e
c
hnol
ogy
, vol
. 16, no. 1, pp. 325
–
338, 2021.
[
27]
M
.
J
.
A
l
-
S
ha
m
de
e
n,
A
.
N
.
Y
ouni
s
,
a
nd
H
.
A
.
Y
ouni
s
,
“
M
e
t
a
h
e
ur
i
s
t
i
c
a
l
gor
i
t
hm
f
or
c
a
pi
t
a
l
l
e
t
t
e
r
s
i
m
a
ge
s
r
e
c
ogni
t
i
on,”
I
nt
e
r
nat
i
onal
J
our
nal
of
M
at
he
m
at
i
c
s
and
C
om
put
e
r
Sc
i
e
nc
e
, vol
. 16, no. 2, pp. 577
–
588, 20
20.
[
28]
A
.
N
.
Y
ouni
s
,
“
P
e
r
s
ona
l
i
de
nt
i
f
i
c
a
t
i
on
s
ys
t
e
m
ba
s
e
d
on
m
ul
t
i
bi
om
e
t
r
i
c
de
pe
ndi
ng
on
c
uc
koo
s
e
a
r
c
h
a
l
gor
i
t
hm
,”
J
our
nal
of
P
hy
s
i
c
s
:
C
onf
e
r
e
nc
e
Se
r
i
e
s
, vol
. 1879, no. 2, p. 22080, M
a
y 2021, doi
:
10.108
8/
1742
-
65
96/
1879/
2/
022080.
B
I
O
G
R
A
P
H
I
E
S
O
F
A
U
T
H
O
R
S
Hiba
Adreese
Younis
Graduated
from
the
collag
e
of
computer
sciences
a
n
d
mathematics,
university
of
Mosul,
Iraq
at
2003,
she
worked
as
a
progra
mmer
at
the
same
college
till
2009
when
she
started
studying
masters
of
science
at
the
college
o
f
computer
sciences
and
mathematics
(university o
f Mosul),
then she f
inished MSC.
Degree
at
2011. Now
she works
as
assistan
t
lecturer
at
the
college
of
computer
sciences
and
mathemat
ic
sl
(universi
ty
of
Mo
sul)
specialized
in
multimedia
processing,
she
has
a
research
gate
accou
nt
under
the
name
hiba
adreese
.
Sh
e can be con
tacted at
email:
hibaadreese@uomosul.edu.iq
.
Dhafar
Sami
Hammadi
Graduated
from
the
department
of
com
puter
scienc
e
s
collage
of
computer
sciences
and
mathemat
ics
,
university
of
Mosul
,
Iraq
.
she
worked
as
a
programmer
at
the
same
college
till
2013
when
she
started
studying
masters
of
science
at
the
college
of
computer
sciences
and
mathemat
ics
(universi
ty
of
Mosul),
then
she
finished
MSC.
Degree
at
2016.
Now
She
work
as
assistant
lecturer
at
the
college
of
computer
sciences
and
mathematics
(
university
of
Mosul)
specialized
in
image
processing
a
nd
artificial
intelligence
,
She ca
n be c
ontact
ed at
email:
dhaf
ar_un@
uomosul.edu.iq
.
Ansam
Nazar
Younis
She
has
been
an
assistant
literature
at
department
o
f
computer
sciences,
college
of
computer
sciences
and
mathematics,
the
University
of
Mosul,
Iraq
since
2018,
Graduated
from
the
Computer
Science
and
Mathematics
Collage
at
the
University
of
Mosul,
Iraq
in
2005,
and
worked
as
a
programmer
in
the
same
coll
age
until
2013
when
she
also st
arted stu
dying M
asters of
Science i
n
the same c
ollage, the
n she f
inished MSC. De
gree a
t
2018.
General
expertise
is
computer
science,
and
specialty
is
in
the
area
of
artificial
intelligence
and
image
processing.
She.
She
has
a
research
gate
account
under
the
name
Ansam
Nazar
Younis.
She ca
n be
contacted
at email
:
anyma8@
uomosul.edu.iq
.
Evaluation Warning : The document was created with Spire.PDF for Python.