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
.
2
,
A
p
r
il
20
25
,
p
p
.
2
1
6
1
~
2
1
7
1
I
SS
N:
2088
-
8
7
0
8
,
DOI
:
1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
1
6
1
-
2
1
7
1
2161
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
O
ptimi
za
tion t
ec
hniques
appli
e
d o
n ima
g
e seg
menta
tion pro
cess
by
predict
io
n of d
a
ta using
data
mi
ning
t
echn
iques
Ra
m
a
ra
j
M
un
ia
pp
a
n
1
,
Sriv
i
dh
y
a
Selv
a
ra
j
2
,
Ra
ni
Va
na
t
h
i G
urus
a
m
y
3
,
Velum
a
ni
Th
iy
a
g
a
r
a
ja
n
1
,
Dhenda
pa
ni
Sa
ba
re
eswa
ra
n
4
, D
a
v
id
P
ra
s
a
nth
5
,
Va
ra
dh
a
ra
j
K
rit
hik
a
6
,
B
ha
a
ra
t
hi
I
la
ng
o
1
,
Dhin
a
k
a
ra
n Sub
ra
m
a
nia
n
1
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
R
a
t
h
i
n
a
m
C
o
l
l
e
g
e
o
f
A
r
t
s
a
n
d
S
c
i
e
n
c
e
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
K
P
R
C
o
l
l
e
g
e
o
f
A
r
t
s Sc
i
e
n
c
e
a
n
d
R
e
s
e
a
r
c
h
,
C
o
i
m
b
a
t
o
r
e
,
I
n
d
i
a
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
r
i
R
a
ma
k
r
i
s
h
n
a
C
A
S
f
o
r
W
o
m
e
n
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
4
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
G
o
v
t
.
C
o
l
l
e
g
e
o
f
A
r
t
s
a
n
d
S
c
i
e
n
c
e
f
o
r
W
o
me
n
,
Ti
r
u
p
p
u
r
,
I
n
d
i
a
5
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
S
h
r
i
N
e
h
r
u
M
a
h
a
V
i
d
y
a
l
a
y
a
C
o
l
l
e
g
e
o
f
A
r
t
s a
n
d
S
c
i
e
n
c
e
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
6
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
A
k
sh
a
y
a
C
o
l
l
e
g
e
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
C
o
i
mb
a
t
o
r
e
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
,
2
0
2
4
R
ev
is
ed
Oct
1
8
,
2
0
2
4
Acc
ep
ted
No
v
2
0
,
2
0
2
4
Th
e
re
se
a
rc
h
wo
rk
p
re
se
n
ts
a
n
e
n
h
a
n
c
e
d
m
e
th
o
d
th
a
t
c
o
m
b
in
e
s
r
u
le
-
b
a
se
d
c
o
lo
r
ima
g
e
se
g
m
e
n
tatio
n
with
fu
z
z
y
d
e
n
sit
y
-
b
a
se
d
sp
a
ti
a
l
c
lu
ste
rin
g
o
f
a
p
p
li
c
a
ti
o
n
s
with
n
o
ise
(
F
DBSC
AN
).
Th
is
tec
h
n
i
q
u
e
e
n
h
a
n
c
e
s
su
p
e
r
-
p
i
x
e
l
ro
b
u
stn
e
ss
a
n
d
imp
r
o
v
e
s
o
v
e
ra
ll
ima
g
e
q
u
a
li
ty
,
o
ffe
ri
n
g
a
m
o
re
e
ffe
c
ti
v
e
so
lu
ti
o
n
f
o
r
ima
g
e
se
g
m
e
n
tatio
n
.
Th
e
stu
d
y
is
s
p
e
c
ifi
c
a
ll
y
a
p
p
l
i
e
d
to
t
h
e
c
h
a
ll
e
n
g
i
n
g
a
n
d
n
o
v
e
l
tas
k
o
f
p
r
e
d
ictin
g
th
e
a
g
e
o
f
ti
g
e
rs
fro
m
c
a
m
e
ra
trap
ima
g
e
s,
a
c
rit
ica
l
issu
e
in
th
e
e
m
e
rg
in
g
field
o
f
wil
d
li
fe
re
se
a
rc
h
.
T
h
e
ta
sk
is
fra
u
g
h
t
wit
h
c
h
a
ll
e
n
g
e
s,
p
a
rti
c
u
l
a
rly
d
u
e
to
v
a
riati
o
n
s
in
ima
g
e
sc
a
le
a
n
d
th
ick
n
e
ss
.
P
r
o
p
o
se
d
m
e
th
o
d
s
d
e
m
o
n
stra
te
th
a
t
sig
n
ifi
c
a
n
t
imp
ro
v
e
m
e
n
ts
o
v
e
r
e
x
isti
n
g
tec
h
n
iq
u
e
s
th
ro
u
g
h
th
e
b
ro
a
d
e
r
se
t
o
f
p
a
ra
m
e
ters
o
f
m
in
a
n
d
m
a
x
to
a
c
h
ie
v
e
su
p
e
ri
o
r
se
g
m
e
n
tatio
n
re
su
lt
s.
Th
e
p
ro
p
o
se
d
a
p
p
r
o
a
c
h
o
p
ti
m
ize
s
se
g
m
e
n
tati
o
n
b
y
in
te
g
ra
ti
n
g
f
u
z
z
y
c
l
u
ste
rin
g
wi
th
r
u
le
-
b
a
se
d
tec
h
n
iq
u
e
s,
lea
d
i
n
g
to
imp
r
o
v
e
d
a
c
c
u
ra
c
y
a
n
d
e
fficie
n
c
y
i
n
p
ro
c
e
ss
in
g
c
o
lo
r
ima
g
e
s.
Th
is
i
n
n
o
v
a
ti
o
n
c
o
u
l
d
g
re
a
tl
y
b
e
n
e
fit
fu
r
th
e
r
re
se
a
rc
h
a
n
d
a
p
p
li
c
a
ti
o
n
s
i
n
re
a
l
-
wo
rld
sc
e
n
a
rio
s.
A
d
d
i
ti
o
n
a
ll
y
,
t
h
e
sc
a
le
a
n
d
th
ick
n
e
ss
v
a
riatio
n
s
o
f
th
e
p
re
se
n
t
b
a
rra
c
u
d
a
p
a
n
o
ra
m
a
k
n
o
wle
d
g
e
b
a
se
o
f
fe
r
m
a
n
y
a
d
v
a
n
tag
e
s
o
v
e
r
o
th
e
r
e
n
h
a
n
c
e
m
e
n
t
stra
teg
ies
th
a
t
h
a
v
e
b
e
e
n
p
r
o
p
o
se
d
f
o
r
th
e
u
se
o
f
th
e
se
tec
h
n
i
q
u
e
s.
T
h
e
e
x
p
e
rime
n
ts
sh
o
w
t
h
a
t
th
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
c
a
n
u
ti
li
z
e
a
wi
d
e
r
ra
n
g
e
o
f
p
a
ra
m
e
ters
to
a
c
h
i
e
v
e
b
e
tt
e
r
se
g
m
e
n
tatio
n
re
su
lt
s.
K
ey
w
o
r
d
s
:
C
las
s
if
icatio
n
C
lu
s
ter
in
g
C
o
lo
r
im
ag
e
s
eg
m
en
tatio
n
Den
s
ity
-
b
ased
s
p
atial
clu
s
ter
in
g
o
f
ap
p
licatio
n
s
with
n
o
is
e
Fu
zz
lo
g
ic
Patter
n
m
in
in
g
Per
f
o
r
m
an
ce
m
etr
ics
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
:
R
am
ar
aj
Mu
n
iap
p
an
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
R
ath
in
am
C
o
lleg
e
o
f
A
r
ts
an
d
Scien
ce
C
o
im
b
ato
r
e
-
21
,
T
am
il Na
d
u
,
I
n
d
ia
E
m
ail:
r
am
ar
aj.
p
h
d
cs@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
s
em
p
lo
y
e
d
ca
n
ch
allen
g
in
g
to
th
e
clu
s
ter
d
ata
p
o
i
n
ts
b
ased
o
n
p
ar
ticu
lar
ch
ar
ac
te
r
is
tics
.
C
lu
s
ter
in
g
alg
o
r
ith
m
s
,
in
clu
d
in
g
K
-
Me
an
s
an
d
h
ier
a
r
ch
ical
,
ar
e
e
x
ten
s
iv
ely
u
tili
ze
d
,
o
f
f
er
in
g
ef
f
ec
tiv
e
s
o
lu
tio
n
s
t
o
th
ese
ch
allen
g
es
th
r
o
u
g
h
t
h
e
ap
p
licatio
n
o
f
clu
s
ter
in
g
co
n
ce
p
ts
[
1
]
.
T
h
e
y
can
no
t
b
u
n
c
h
to
g
eth
er
i
n
lig
h
t
o
f
t
h
eir
d
i
f
f
er
en
t
d
en
s
ities
.
T
h
e
p
r
o
p
o
s
ed
clu
s
ter
in
g
al
g
o
r
it
h
m
will
b
e
f
o
cu
s
ed
o
n
th
e
h
y
p
o
th
esis
th
at
h
ig
h
-
d
en
s
ity
lo
ca
tio
n
s
ar
e
clu
s
ter
ed
ar
o
u
n
d
o
n
e
an
o
th
er
to
co
n
s
titu
te
a
s
in
g
le
-
co
lo
r
g
r
o
u
p
wh
en
is
o
lated
b
y
th
ic
k
en
in
g
d
is
tr
icts
[
2
]
.
T
h
is
tech
n
iq
u
e
an
aly
ze
s
th
e
l
o
ca
l
d
e
n
s
ity
o
f
d
ata
p
o
in
ts
with
in
clu
s
ter
s
,
en
ab
lin
g
th
e
id
en
tific
atio
n
o
f
clu
s
ter
s
in
lar
g
e
s
p
atial
d
atasets
b
ased
o
n
c
o
lo
r
d
ata.
I
t
h
elp
s
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
.
2
,
Ap
r
il
20
25
:
2
1
6
1
-
2
1
7
1
2162
p
in
p
o
in
t
th
e
clu
s
ter
g
r
o
u
p
m
o
s
t
lik
ely
to
f
o
r
m
[
3
]
.
T
h
e
two
k
ey
p
ar
am
eter
s
r
eq
u
i
r
ed
ar
e
E
p
s
ilo
n
an
d
M
in
Po
in
ts
,
wh
ich
d
ef
in
e
th
e
r
ad
iu
s
an
d
d
e
n
s
ity
th
r
esh
o
ld
f
o
r
ev
alu
atin
g
t
h
e
n
eig
h
b
o
r
h
o
o
d
o
f
ea
ch
d
ata
p
o
in
t.
T
h
ese
p
ar
am
eter
s
h
elp
in
ac
cu
r
ately
ass
ess
in
g
th
e
clu
s
ter
's
d
en
s
ity
b
y
d
eter
m
in
in
g
h
o
w
m
an
y
n
eig
h
b
o
r
in
g
p
o
in
ts
f
all
with
in
a
s
p
ec
if
ied
d
is
tan
ce
ar
o
u
n
d
ea
ch
p
o
in
t.
Min
Po
in
ts
is
th
e
b
ase
n
u
m
b
er
o
f
p
o
in
ts
th
at
n
ee
d
to
b
e
in
a
cir
cle
f
o
r
th
e
h
i
g
h
lig
h
ted
i
n
f
o
r
m
atio
n
to
b
e
co
n
s
id
er
e
d
th
e
ce
n
ter
p
o
i
n
t
in
th
e
lis
t
[
4
]
.
I
n
d
en
s
ity
-
b
a
s
ed
s
p
atial
clu
s
ter
in
g
o
f
ap
p
licatio
n
s
with
n
o
is
e
(
DB
SC
AN)
,
th
e
m
in
im
u
m
n
u
m
b
er
o
f
d
ata
p
o
in
ts
r
eq
u
ir
e
d
with
in
a
h
y
p
er
s
p
h
e
r
e
is
ter
m
ed
Min
Po
in
ts
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
ca
teg
o
r
iz
es
d
ata
p
o
in
ts
with
in
a
n
ep
s
il
o
n
r
a
d
iu
s
as
co
r
e,
b
o
r
d
er
,
o
r
n
o
is
e
p
o
in
ts
.
C
o
r
e
p
o
in
ts
ar
e
th
o
s
e
s
u
r
r
o
u
n
d
ed
b
y
at
least
Min
Po
i
n
ts
with
in
th
eir
n
eig
h
b
o
r
h
o
o
d
r
ad
iu
s
[
5
]
.
A
p
o
in
t
is
v
iewe
d
as
th
e
b
o
u
n
d
ar
y
p
o
in
t
in
t
h
e
ev
e
n
t
th
at
th
e
q
u
an
tity
o
f
p
o
in
ts
o
f
in
ter
est
is
n
o
t
an
ex
ac
t
q
u
an
t
ity
o
f
p
o
in
ts
,
an
d
a
p
o
in
t
is
v
iewe
d
as
co
m
m
o
tio
n
o
n
th
e
o
f
f
ch
a
n
ce
th
at
th
er
e
co
u
ld
b
e
n
o
d
if
f
er
en
t
d
ata
o
f
in
ter
est
in
s
id
e
an
ep
s
ilo
n
s
p
an
th
an
th
e
r
e
is
in
an
y
d
ata
o
f
in
ter
est
[
6
]
.
C
o
r
e
p
o
in
ts
,
wh
ich
ar
e
d
ep
icte
d
b
y
t
h
e
co
lo
r
r
e
d
,
ar
e
all
d
ata
p
o
i
n
ts
th
at
h
av
e
at
least
t
h
r
ee
p
o
in
ts
in
th
e
cir
cle,
i
n
clu
d
in
g
t
h
em
s
elv
es.
T
h
e
E
u
clid
e
an
d
is
tan
ce
is
u
s
ed
b
y
DB
SC
AN
to
lo
ca
te
d
ata
p
o
in
ts
in
s
p
ac
e.
B
u
t
o
th
er
d
is
tan
ce
s
ar
e
ca
lcu
lated
b
y
th
e
co
l
o
r
s
in
an
im
ag
e,
s
u
ch
as th
e
wid
e
cir
cu
lar
d
is
tan
ce
,
wh
ich
ca
n
u
s
ed
to
lo
ca
tin
g
g
e
o
g
r
ap
h
ical
d
ata
[
7
]
.
E
v
en
th
o
u
g
h
,
it h
as n
ee
d
to
d
o
it m
u
ltip
le
tim
es in
o
u
r
ca
lcu
la
tio
n
s
,
it o
n
ly
n
ee
d
s
to
lo
o
k
at
t
h
e
en
tire
d
ataset
o
n
ce
[
8
]
.
2.
RE
VI
E
W
O
F
L
I
T
E
RA
T
UR
E
Nu
m
er
o
u
s
ap
p
r
o
ac
h
es
h
av
e
b
ee
n
in
v
esti
g
ated
f
o
r
im
ag
e
s
e
g
m
en
tatio
n
,
with
m
u
ch
o
f
th
e
r
esear
ch
ce
n
ter
ed
o
n
d
if
f
e
r
en
t
s
eg
m
en
tatio
n
tech
n
o
lo
g
ies.
T
h
e
in
n
o
v
ativ
e
an
d
u
n
co
n
v
en
tio
n
al
w
o
r
k
cu
r
r
en
tly
b
ein
g
co
n
d
u
cte
d
in
im
a
g
e
p
r
o
ce
s
s
in
g
is
p
ar
ticu
la
r
ly
in
tr
i
g
u
in
g
.
Yan
g
et
a
l.
[
8
]
d
e
v
elo
p
e
d
a
n
o
v
el
a
n
d
e
f
f
icien
t
K
-
h
y
p
er
lin
e
in
clu
s
ter
in
g
b
ased
co
lo
r
im
a
g
e
s
eg
m
e
n
tatio
n
s
(
C
B
C
I
S)
s
tr
ateg
y
th
at
r
elics
r
esis
tan
t
to
v
icis
s
itu
d
es
in
illu
m
in
atio
n
,
it
h
as
b
ee
n
d
em
o
n
s
tr
ated
f
o
r
co
l
o
r
im
ag
e
class
if
icatio
n
as
a
h
y
p
er
lin
e
cl
u
s
ter
in
g
s
o
lu
tio
n
f
o
r
co
l
o
r
im
ag
e
class
if
icatio
n
in
th
e
v
is
u
al
f
ield
,
wh
ich
is
u
s
ed
to
id
en
tify
co
lo
r
i
m
ag
es
in
th
e
v
is
u
al
f
ield
.
R
am
ar
aj
an
d
Nir
aim
ath
i
[
9
]
p
r
esen
ted
a
f
ew
is
s
u
es
with
in
th
e
v
ar
iety
im
a
g
e
d
iv
i
s
io
n
.
W
ith
th
e
f
iv
e
is
s
u
es
th
at
wer
e
d
is
cu
s
s
ed
in
t
h
e
co
lo
r
im
a
g
e
s
eg
m
en
tatio
n
,
p
r
o
p
o
s
ed
s
o
lu
tio
n
s
ar
e
tak
e
n
i
n
to
co
n
s
id
er
atio
n
.
Z
h
u
et
a
l.
[
1
0
]
s
u
m
m
ed
u
p
th
e
v
ar
io
u
s
ap
p
r
o
ac
h
es
to
i
m
ag
e
s
eg
m
en
tatio
n
th
at
h
a
v
e
b
ee
n
u
s
ed
in
th
is
s
itu
atio
n
.
Yan
et
a
l.
[
1
1
]
d
escr
ib
ed
a
n
ew
f
r
am
ewo
r
k
f
o
r
co
m
p
a
r
in
g
v
ar
i
o
u
s
clu
s
ter
in
g
m
eth
o
d
s
f
o
r
s
eg
m
en
tin
g
p
ix
els o
f
an
im
a
g
e
s
.
C
h
e
n
e
t
a
l
.
[
1
2
]
h
a
s
p
r
o
p
o
s
ed
n
e
w
a
d
a
p
t
i
v
e
m
e
t
h
o
d
s
f
o
r
e
s
t
i
m
a
t
i
n
g
i
n
it
i
a
l
p
a
r
a
m
e
t
e
r
s
i
n
i
m
a
g
e
s
e
g
m
e
n
t
a
ti
o
n
b
y
u
t
i
l
i
z
i
n
g
a
n
i
m
p
r
o
v
e
d
k
-
m
e
a
n
s
c
l
u
s
t
e
r
i
n
g
a
l
g
o
r
i
t
h
m
.
Z
h
a
n
g
e
t
a
l
.
[
1
3
]
h
a
s
p
r
e
s
e
n
t
e
d
t
h
e
M
u
l
t
i
-
F
e
a
t
u
r
es
F
u
s
i
o
n
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
a
l
g
o
r
it
h
m
,
w
h
i
c
h
is
u
s
e
d
o
n
h
i
g
h
-
r
e
s
o
l
u
t
i
o
n
s
e
n
s
i
n
g
i
m
a
g
e
s
t
h
a
t
c
o
n
t
a
i
n
e
d
m
o
r
e
i
n
f
o
r
m
a
t
i
o
n
a
b
o
u
t
t
h
e
s
p
a
t
i
a
l
r
el
a
ti
o
n
s
h
i
p
s
b
e
t
we
e
n
g
r
o
u
n
d
o
b
j
e
c
t
s
t
h
a
n
l
o
w
-
r
es
o
lu
t
i
o
n
i
m
a
g
e
s
.
T
h
is
a
l
g
o
r
i
t
h
m
w
as
i
d
e
n
ti
f
y
i
n
g
t
h
e
l
o
c
a
t
i
o
n
o
f
o
b
j
e
c
ts
i
n
t
h
e
i
m
a
g
e
t
h
a
t
we
r
e
b
e
i
n
g
v
i
ew
e
d
.
H
u
an
g
e
t
a
l
.
[
1
4
]
w
e
r
e
g
i
v
e
n
t
w
o
-
w
a
y
c
l
u
s
t
e
r
i
n
g
b
a
s
e
d
o
n
t
h
e
l
e
a
s
t
c
r
o
s
s
i
n
g
t
r
e
e
a
n
d
D
B
S
C
A
N
c
a
l
c
u
l
a
t
i
o
n
s
f
o
r
p
i
c
t
u
r
e
d
i
v
i
s
i
o
n
.
D
u
b
e
y
e
t
a
l
.
[
1
5
]
p
r
e
s
e
n
t
e
d
t
h
e
i
m
a
g
e
s
e
g
m
e
n
t
at
i
o
n
-
b
a
s
e
d
cl
u
s
t
e
r
i
n
g
t
ec
h
n
i
q
u
e
a
n
d
s
e
v
e
r
a
l
cl
u
s
t
e
r
i
n
g
s
t
r
a
te
g
i
es
a
r
e
d
i
s
c
u
s
s
e
d
.
R
a
m
a
r
aj
a
n
d
N
i
r
a
i
m
a
t
h
i
[
1
6
]
h
a
s
p
r
o
p
o
s
e
d
u
s
i
n
g
D
B
S
C
A
N
f
o
r
r
e
a
l
-
t
i
m
e
im
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
b
a
s
e
d
o
n
s
u
p
e
r
-
p
i
x
e
ls
.
S
u
d
a
n
a
e
t
a
l
.
[
1
7
]
h
a
s
p
r
o
p
o
s
e
d
t
h
e
DB
SC
AN
al
g
o
r
i
t
h
m
w
a
s
e
m
p
l
o
y
e
d
t
o
c
l
u
s
t
e
r
i
m
a
g
es
c
o
n
t
a
i
n
i
n
g
n
u
m
e
r
o
u
s
i
n
t
r
i
c
at
e
B
a
li
n
e
s
e
c
h
a
r
a
c
t
e
r
s
w
it
h
i
n
a
s
in
g
l
e
l
a
r
g
e
i
m
a
g
e
.
W
an
g
et
a
l.
[
1
8
]
d
e
m
o
n
s
tr
ate
d
u
s
in
g
a
n
ew
m
eth
o
d
to
s
eg
m
en
t
im
ag
es
v
er
y
ef
f
ec
tiv
el
y
b
ased
o
n
th
e
clu
s
ter
in
g
alg
o
r
ith
m
s
b
ein
g
p
r
esen
ted
,
p
r
im
ar
ily
f
o
r
u
s
e
in
ap
p
licatio
n
s
in
v
o
lv
in
g
im
ag
es o
f
th
e
s
am
e
s
ize
an
d
s
h
ap
e
as
th
e
im
ag
e
its
elf
.
R
am
ar
aj
an
d
Nir
aim
ath
i
[
1
9
]
p
r
esen
ted
th
e
v
ar
io
u
s
clu
s
ter
in
g
s
tr
ateg
ies
th
at
ar
e
u
tili
ze
d
to
ch
ar
ac
ter
ize
th
e
o
r
g
an
izatio
n
o
f
n
an
o
s
ca
le
ass
e
m
b
lies
in
im
ag
es
o
b
tain
ed
th
r
o
u
g
h
lo
ca
lizatio
n
m
icr
o
s
co
p
y
.
Said
et
a
l.
[
2
0
]
d
em
o
n
s
tr
ated
a
m
eth
o
d
f
o
r
co
l
o
r
-
b
ased
im
a
g
e
s
eg
m
en
tatio
n
to
d
iv
id
e
co
l
o
r
s
in
t
o
s
eg
m
en
ts
.
T
h
e
p
r
o
ce
s
s
o
f
s
p
litt
in
g
u
p
an
im
ag
e
in
to
d
is
tin
ct
r
eg
io
n
s
wh
e
r
e
ea
c
h
p
ix
el
h
as
s
im
ilar
ch
ar
ac
ter
is
tics
is
k
n
o
wn
as im
ag
e
s
eg
m
en
tatio
n
.
I
n
s
tu
d
y
b
y
C
h
en
a
et
a
l.
[
2
1
]
in
t
h
is
co
n
tex
t,
a
n
o
v
el
co
l
o
r
im
ag
e
s
eg
m
en
tatio
n
alg
o
r
i
th
m
ca
lled
m
ea
n
s
h
if
t
h
ier
ar
ch
ical
clu
s
ter
in
g
(
MSHC)
was
in
tr
o
d
u
ce
d
.
C
o
n
g
an
d
Hiep
[
2
2
]
h
ad
p
r
esen
ted
a
v
er
s
atile
an
d
s
o
lo
b
u
n
ch
in
g
ap
p
r
o
ac
h
in
lig
h
t
o
f
Vo
r
o
n
o
i
lo
ca
les
,
wh
ich
co
u
ld
b
e
ap
p
lied
to
tak
e
ca
r
e
o
f
th
e
v
ar
iety
o
f
im
ag
e
d
iv
is
io
n
is
s
u
es.
Sh
i
et
a
l.
[
2
3
]
a
b
r
an
d
-
n
ew
p
ix
el
in
t
en
s
ity
clu
s
ter
in
g
alg
o
r
ith
m
f
o
r
m
u
lti
-
lev
el
im
ag
e
s
eg
m
en
tatio
n
was
u
n
v
eiled
.
J
in
g
a
et
a
l.
[
2
4
]
also
d
is
cu
s
s
ed
th
e
d
if
f
er
e
n
t
clu
s
ter
in
g
tec
h
n
iq
u
es
f
o
r
c
h
an
g
in
g
th
e
s
tan
d
ar
d
f
u
zz
y
o
b
jectiv
e
f
u
n
ctio
n
b
y
u
p
d
atin
g
th
e
m
e
m
b
er
s
h
ip
an
d
clu
s
ter
ce
n
tr
o
id
s
.
T
h
e
p
er
f
o
r
m
an
ce
s
tu
d
y
o
f
im
ag
e
s
eg
m
en
tatio
n
tech
n
iq
u
es
h
as
b
ee
n
d
escr
ib
e
d
b
y
Kh
alee
l
et
a
l.
[
2
5
]
.
B
ai
et
a
l.
[
2
6
]
v
ar
io
u
s
ap
p
licatio
n
s
o
f
th
e
im
ag
e
s
eg
m
en
tatio
n
p
r
o
b
lem
in
co
m
p
u
t
er
v
is
io
n
an
d
im
ag
e
p
r
o
ce
s
s
in
g
wer
e
p
r
esen
ted
.
Fah
r
u
d
in
et
a
l.
[
2
7
]
i
n
r
ec
en
t
y
ea
r
s
,
th
e
e
n
h
an
ce
d
s
u
p
p
o
r
t
v
ec
to
r
clu
s
ter
in
g
alg
o
r
ith
m
h
as
g
ain
ed
s
ig
n
if
ican
t
in
ter
est
f
o
r
co
lo
r
im
ag
e
s
eg
m
en
tatio
n
,
p
ar
ticu
lar
ly
ac
r
o
s
s
v
ar
io
u
s
ap
p
licatio
n
f
ield
s
.
R
ed
d
y
et
a
l.
[
2
8
]
u
s
ed
th
e
f
u
zz
y
cl
u
s
ter
in
g
m
eth
o
d
f
o
r
co
lo
r
im
a
g
e
s
eg
m
en
tatio
n
,
p
r
o
d
u
cin
g
a
s
in
g
le
im
ag
e
with
u
n
if
o
r
m
c
o
lo
r
.
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
Op
timiz
a
tio
n
tech
n
iq
u
es a
p
p
l
ied
o
n
ima
g
e
s
eg
men
ta
tio
n
p
r
o
ce
s
s
b
y
…
(
R
a
ma
r
a
j Mu
n
ia
p
p
a
n
)
2163
3.
M
E
T
H
O
D
T
h
e
p
ix
el
clu
s
ter
in
g
h
eu
r
is
tic
d
eter
m
in
es
th
e
to
tal
n
u
m
b
er
o
f
clu
s
ter
s
b
ased
o
n
th
e
ex
p
ec
ted
p
atter
n
o
f
r
elate
d
n
o
d
es
u
s
in
g
a
n
ew
alg
o
r
ith
m
ca
lled
f
u
zz
y
d
en
s
ity
-
b
ased
s
p
atial
clu
s
ter
in
g
o
f
ap
p
licatio
n
s
with
noi
s
e
(
FDB
SC
A
N)
.
T
h
is
ap
p
r
o
ac
h
aid
s
i
n
ac
c
u
r
ately
i
d
en
ti
f
y
in
g
an
d
g
r
o
u
p
i
n
g
cl
u
s
ter
s
with
in
th
e
d
ata.
T
h
e
FDB
S
C
AN
clu
s
ter
in
g
alg
o
r
i
th
m
u
s
es
th
e
n
o
tio
n
o
f
d
en
s
ity
r
ea
ch
ab
ilit
y
r
ath
er
th
an
m
ass
o
r
d
is
tan
ce
r
ea
ch
ab
ilit
y
to
id
e
n
tify
a
clu
s
t
er
.
3
.
1
.
F
DB
SCA
N
c
lus
t
er
i
ng
T
h
e
FDB
SC
AN
clu
s
ter
in
g
alg
o
r
ith
m
o
f
f
er
s
a
s
o
p
h
is
ticated
ap
p
r
o
ac
h
to
p
r
ed
ictin
g
th
e
ag
e
o
f
tig
er
s
f
r
o
m
ca
m
er
a
t
r
ap
im
a
g
es.
FDB
S
C
AN
en
h
an
ce
s
th
e
c
o
n
v
e
n
tio
n
al
DB
SC
AN
ap
p
r
o
ac
h
b
y
in
teg
r
atin
g
f
u
zz
y
m
em
b
er
s
h
ip
f
u
n
ctio
n
s
,
wh
ic
h
allo
w
f
o
r
a
m
o
r
e
n
u
a
n
ce
d
class
if
icatio
n
o
f
d
ata
p
o
in
ts
in
to
clu
s
ter
s
[
2
9
]
.
FDB
S
C
AN
o
p
er
ates
b
y
e
v
al
u
atin
g
th
e
d
e
n
s
ity
o
f
d
ata
p
o
in
ts
with
in
a
s
p
ec
if
ie
d
r
a
d
iu
s
,
ϵ
an
d
m
id
p
o
in
ts
,
ap
p
ly
in
g
f
u
zz
y
l
o
g
ic
to
h
an
d
le
u
n
ce
r
tain
ties
an
d
v
ar
iati
o
n
s
in
th
e
d
ata.
U
n
lik
e
co
n
v
en
tio
n
al
clu
s
ter
in
g
m
eth
o
d
s
th
at
ass
ig
n
d
ata
p
o
in
ts
to
d
is
cr
ete
clu
s
ter
s
,
FDB
SC
AN
p
r
o
v
id
es
a
d
eg
r
ee
o
f
m
em
b
er
s
h
ip
f
o
r
ea
ch
p
o
in
t,
r
ef
lectin
g
its
p
o
ten
tial a
s
s
o
ciatio
n
with
m
u
ltip
le
clu
s
te
r
s
[
3
0
]
.
T
h
is
is
p
ar
ticu
lar
ly
b
e
n
ef
icial
in
h
an
d
lin
g
th
e
v
ar
iab
ilit
y
an
d
c
o
m
p
lex
ity
o
f
n
atu
r
al
im
ag
es.
I
n
s
tead
o
f
s
tr
ictly
ass
ig
n
in
g
ea
ch
p
o
in
t
to
a
s
in
g
le
clu
s
ter
o
r
lab
elin
g
it
as n
o
is
e,
FDB
SC
A
N
ass
ig
n
s
a
d
eg
r
ee
o
f
m
em
b
er
s
h
ip
to
ea
c
h
clu
s
ter
.
T
h
is
f
lex
i
b
ilit
y
h
elp
s
m
a
n
ag
e
th
e
in
h
er
en
t
u
n
ce
r
tain
ty
an
d
v
ar
iab
ilit
y
in
r
ea
l
-
wo
r
ld
d
atas
ets.
C
o
n
s
eq
u
en
tly
,
u
n
d
er
s
tan
d
in
g
h
o
w
to
ch
o
o
s
e
th
e
ap
p
r
o
p
r
iate
E
p
s
ilo
n
an
d
Min
Po
in
ts
v
alu
es
is
cr
itical.
T
h
e
FDB
SC
AN
alg
o
r
ith
m
s
o
u
tp
u
t
is
s
ig
n
if
ica
n
tly
alter
ed
b
y
s
m
all
ch
an
g
es
in
th
ese
v
alu
es.
Min
Po
in
ts
s
h
o
u
ld
h
av
e
a
v
alu
e
th
at
is
at
least
o
n
e
h
ig
h
er
th
a
n
th
e
d
ataset's n
u
m
b
er
o
f
d
im
en
s
io
n
s
.
≥
+
1
(
1
)
Sin
ce
th
is
will
m
ak
e
ea
ch
p
o
i
n
t
a
d
is
tin
ct
clu
s
ter
,
it
m
ak
es
n
o
s
en
s
e
to
tak
e
Min
Po
in
ts
as
1
.
I
n
m
o
s
t
ca
s
es,
it
n
ee
d
s
to
b
e
at
least
3
.
I
f
th
e
v
alu
e
o
f
an
ep
s
ilo
n
ch
o
s
en
is
to
o
lo
w,
m
o
r
e
clu
s
ter
s
will
b
e
f
o
r
m
ed
.
An
d
m
o
r
e
d
ata
p
o
in
ts
co
n
s
id
er
e
d
to
b
e
n
o
is
y
will b
ec
o
m
e
av
ailab
le
f
o
r
f
u
r
th
er
an
aly
s
is
.
3
.
2
.
Rea
cha
bil
it
y
a
nd
c
o
nn
ec
t
iv
it
y
T
h
e
FDSC
A
N
clu
s
ter
in
g
alg
o
r
ith
m
,
wh
en
ap
p
lied
to
th
e
task
o
f
tig
er
ag
e
p
r
ed
ictio
n
,
em
p
h
asizes
th
e
im
p
o
r
tan
ce
o
f
r
ea
c
h
ab
ilit
y
an
d
co
n
n
ec
tiv
ity
with
in
t
h
e
d
ata.
T
h
r
o
u
g
h
th
ese
co
n
ce
p
ts
,
th
e
alg
o
r
ith
m
ef
f
ec
tiv
ely
g
r
o
u
p
s
s
im
ilar
d
ata
p
o
in
ts
,
en
s
u
r
in
g
th
at
clu
s
ter
s
f
o
r
m
ed
ar
e
b
o
th
c
o
h
esiv
e
a
n
d
m
ea
n
in
g
f
u
l.
T
h
is
ap
p
r
o
ac
h
en
h
an
ce
s
th
e
ac
cu
r
a
cy
o
f
p
r
ed
ictio
n
s
b
y
en
s
u
r
in
g
t
h
at
th
e
alg
o
r
ith
m
ca
n
id
en
tify
s
u
b
tle
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
in
th
e
d
ata,
wh
ich
ar
e
cr
u
cial
f
o
r
ac
cu
r
atel
y
esti
m
atin
g
th
e
ag
e
o
f
tig
er
s
f
r
o
m
ca
m
er
a
t
r
ap
im
ag
es.
T
h
r
o
u
g
h
th
e
im
p
lem
e
n
tatio
n
o
f
FDSC
AN,
th
e
r
esear
ch
ac
h
ie
v
es
m
o
r
e
r
eliab
le
a
n
d
p
r
ec
is
e
clu
s
ter
in
g
,
d
ir
ec
tly
co
n
tr
i
b
u
tin
g
t
o
th
e
im
p
r
o
v
e
d
p
r
e
d
ictio
n
o
f
tig
er
a
g
es in
th
e
f
ield
o
f
wild
life
r
esear
c
h
.
Her
e,
if
th
e
d
is
tan
ce
(
,
)
=
,
is
a
co
r
e
p
o
i
n
t,
th
en
u
s
in
g
an
d
M
in
Po
in
ts
,
p
o
in
t
ca
n
b
e
d
en
s
ity
-
r
ea
ch
ab
le
d
ir
ec
tly
f
r
o
m
p
o
in
t
as
Fig
u
r
e
1
illu
s
tr
ate
s
.
I
n
th
is
ca
s
e,
ca
n
b
e
r
ea
c
h
ed
d
ir
ec
tly
b
y
d
en
s
ity
f
r
o
m
,
b
u
t
th
e
o
p
p
o
s
ite
is
n
o
t
tr
u
e:
A
c
h
ain
o
f
p
o
in
ts
1
,
2
,
3
,
.
.
.
,
an
d
1
=
an
d
=
m
ak
es
+
1
d
ir
ec
tly
d
en
s
ity
-
r
ea
c
h
ab
le
f
r
o
m
,
wh
ich
m
ea
n
s
th
at
a
p
o
in
t
is
d
en
s
ity
-
r
ea
ch
ab
le
f
r
o
m
a
p
o
in
t
in
ter
m
s
o
f
ep
s
ilo
n
,
M
in
Po
in
ts
.
€
(
)
=
D
d
is
t
|
(
,
)
€
d
ef
in
es
th
e
€
(
r
ea
d
as
E
p
s
)
-
n
eig
h
b
o
r
h
o
o
d
o
f
a
p
o
in
t
p
.
I
t
is
p
o
s
s
ib
le
to
ass
er
t
th
at
X
is
d
en
s
ity
-
r
ea
ch
ab
le
f
r
o
m
Y
b
ec
au
s
e
b
o
th
X
a
n
d
Y
ar
e
r
ea
ch
ab
le
f
r
o
m
O
;
h
o
wev
e
r
,
th
is
is
n
o
t
th
e
ca
s
e
f
o
r
th
e
o
th
e
r
two
d
im
en
s
io
n
s
.
Fig
u
r
e
2
d
ep
icts
th
e
d
ir
ec
t
d
en
s
ity
-
r
ea
ch
ab
le
co
l
o
r
f
u
n
ctio
n
.
I
f
th
er
e
ar
e
two
p
o
in
ts
,
p
an
d
q
,
th
e
p
o
in
t
q
is
d
ir
ec
tly
d
en
s
ity
-
r
ea
ch
ab
le
f
r
o
m
t
h
e
o
th
er
p
o
in
t
as
lo
n
g
as
it
is
n
o
t
m
o
r
e
th
an
a
ce
r
tain
d
is
tan
ce
,
l
ik
e
€
;
T
h
at
is
,
q
is
in
th
e
€
-
n
ei
g
h
b
o
r
h
o
o
d
o
f
p
.
I
f
1
=
an
d
=
,
th
en
th
e
p
o
in
t
q
h
as a
d
e
n
s
ity
th
at
ca
n
b
e
r
ea
ch
ed
f
r
o
m
p
,
an
d
if
p
is
s
u
r
r
o
u
n
d
ed
b
y
m
an
y
p
o
in
ts
,
lik
e
1
,
2
,
3
,
.
.
.
,
th
en
ea
ch
p
o
in
t
+
1
ca
n
b
e
r
ea
ch
ed
d
ir
ec
tly
f
r
o
m
p
.
Fo
r
d
en
s
ity
-
co
n
n
ec
ted
s
y
s
tem
s
,
as
s
h
o
wn
in
Fig
u
r
e
3
:
d
en
s
ity
-
r
ea
ch
ab
le
r
elatio
n
s
h
i
p
s
ar
e
n
o
t sy
m
m
etr
ical.
T
h
e
p
o
in
t q
m
ay
b
e
at
th
e
ed
g
e
o
f
a
clu
s
ter
b
ec
au
s
e
it lac
k
s
en
o
u
g
h
n
eig
h
b
o
r
s
to
b
e
co
n
s
id
er
ed
d
en
s
e
o
n
its
o
wn
.
T
wo
p
o
in
ts
p
an
d
q
a
r
e
d
en
s
ity
-
co
n
n
ec
ted
if
th
e
r
e
is
a
p
o
in
t o
t
h
at
ca
n
b
e
r
ea
ch
e
d
f
r
o
m
b
o
th
p
o
in
ts
p
a
n
d
q
.
Fig
u
r
e
4
d
ep
icts
th
e
f
u
zz
y
DB
S
C
AN
-
b
ased
clu
s
ter
in
g
m
et
h
o
d
u
s
ed
to
d
eter
m
in
e
th
e
tig
er
'
s
ag
e.
T
o
elim
in
ate
th
e
s
ca
le
-
d
ep
en
d
en
c
y
is
s
u
e
an
d
o
b
tain
g
lo
b
al
v
alu
es in
d
ep
en
d
en
t o
f
th
e
r
an
g
e
o
f
p
ix
el
d
ata,
th
e
d
ata
ar
e
n
o
r
m
alize
d
f
o
r
th
e
p
a
r
am
e
ter
s
an
d
Min
Pts
.
=
2
.
(
2
)
T
h
er
e
ar
e
two
c
o
o
r
d
i
n
ates
b
etwe
en
Min
Pts
an
d
ε
v
alu
es
ar
e
f
ix
ed
.
Fo
r
ex
am
p
le,
=
|
(
;
)
|
,
is
w
h
er
e
=
|
1
…
.
1
|
in
wh
ich
|
(
;
1
)
|
d
en
o
tes
th
e
s
et'
s
f
u
zz
y
c
ar
d
in
ality
,
(
;
1
)
.
T
h
e
p
r
o
ce
s
s
's
o
u
tco
m
e
m
ay
v
ar
y
d
ep
en
d
i
n
g
o
n
th
e
c
h
o
ice
m
ad
e
b
y
th
e
f
u
n
ctio
n
,
wh
ic
h
m
a
y
b
e
an
y
f
u
zz
y
n
eig
h
b
o
r
h
o
o
d
f
u
n
ctio
n
.
L
ik
ew
is
e,
2
is
o
b
tain
ed
b
y
(
3
)
.
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
.
2
,
Ap
r
il
20
25
:
2
1
6
1
-
2
1
7
1
2164
2
=
(
3
)
Fo
r
a
co
n
s
tan
t
ε
1
,
th
e
f
u
zz
y
n
e
ig
h
b
o
r
h
o
o
d
s
et
o
f
p
o
in
t
x
∈
X
is
f
o
r
m
ed
b
y
(
4
)
:
(
,
1
)
=
{
<
.
(
)
>
|
∈
,
(
)
≥
1
|
}
(
4
)
A
f
u
zz
y
co
r
e
p
o
i
n
t is o
b
tain
ed
b
y
(
5
)
:
(
;
1
,
2
)
≡
∑
(
)
≥
2
∈
(
;
1
)
.
(
5
)
Fig
u
r
e
1
.
Sp
lEp
s
Fig
u
r
e
2
.
C
o
lEp
s
Fig
u
r
e
3
.
C
o
n
n
ec
ted
Fig
u
r
e
4
.
Fu
zz
y
b
ased
DB
SC
AN
clu
s
ter
in
g
alg
o
r
ith
m
As
a
r
esu
lt,
th
e
f
u
zz
y
DB
SC
AN
m
eth
o
d
m
a
y
b
e
m
o
r
e
r
es
is
tan
t
to
th
e
d
ataset'
s
s
ca
le
a
n
d
d
e
n
s
ity
v
ar
iatio
n
s
.
T
h
e
i
n
itial
s
tep
in
u
s
in
g
f
u
zz
y
DB
SC
AN
to
d
eter
m
in
e
a
tig
er
'
s
ag
e
is
to
lo
ad
im
ag
es.
I
t
h
as
two
p
ar
am
eter
s
:
M
in
Pts
,
wh
ich
i
n
d
icate
s
th
e
d
en
s
ity
o
f
p
o
in
ts
t
h
at
s
er
v
e
as
t
h
e
co
r
e
p
o
in
ts
,
an
d
M
ax
Pts
,
wh
ich
in
d
icate
s
th
e
m
ax
im
u
m
d
is
tan
ce
b
etwe
en
a
d
ata
o
b
ject
an
d
th
e
im
ag
e
th
at
d
ef
in
es n
eig
h
b
o
r
in
g
p
o
in
ts
.
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
Op
timiz
a
tio
n
tech
n
iq
u
es a
p
p
l
ied
o
n
ima
g
e
s
eg
men
ta
tio
n
p
r
o
ce
s
s
b
y
…
(
R
a
ma
r
a
j Mu
n
ia
p
p
a
n
)
2165
3
.
3
.
Co
m
pu
t
ing
p
o
ints
FB
DS
C
AN
c
lu
s
ter
in
g
alg
o
r
ith
m
,
th
e
p
r
o
ce
s
s
o
f
co
m
p
u
t
in
g
p
o
in
ts
p
lay
s
a
v
ital
f
r
a
g
m
en
t
in
ac
cu
r
ately
p
r
e
d
ictin
g
th
e
ag
e
o
f
tig
er
s
.
T
h
e
alg
o
r
ith
m
d
eter
m
in
es
th
e
co
m
p
ac
tn
ess
o
f
ar
g
u
m
en
ts
with
in
a
s
p
ec
if
ic
r
ad
iu
s
an
d
u
s
es
th
i
s
to
f
o
r
m
clu
s
ter
s
.
T
h
e
f
u
zz
y
m
em
b
e
r
s
h
ip
f
u
n
ctio
n
allo
ws
f
o
r
a
d
eg
r
ee
o
f
u
n
ce
r
tain
ty
in
t
h
e
ass
ig
n
m
en
t
o
f
p
o
in
ts
to
clu
s
ter
s
,
wh
ic
h
is
p
ar
ticu
lar
ly
u
s
ef
u
l
i
n
h
a
n
d
lin
g
th
e
i
n
h
er
en
t
v
ar
iab
ilit
y
in
tig
er
im
ag
es.
T
h
e
co
r
e
co
n
ce
p
t
ca
n
b
e
m
ath
em
atica
lly
r
ep
r
esen
ted
b
y
th
e
d
e
n
s
ity
f
u
n
ctio
n
(
)
,
wh
er
e
(
)
is
a
d
ata
p
o
in
t in
th
e
f
e
atu
r
e
s
p
ac
e:
(
)
=
∑
=
1
(
‖
−
‖
2
2
2
)
(
6
)
Her
e,
is
th
e
wh
o
le
am
o
u
n
t o
f
p
o
in
ts
,
r
ep
r
esen
ts
th
e
n
eig
h
b
o
r
in
g
d
ata
p
o
in
ts
with
in
th
e
r
ad
iu
s
an
d
is
a
s
m
o
o
th
in
g
p
ar
am
eter
th
at
c
o
n
tr
o
ls
th
e
s
p
r
ea
d
o
f
t
h
e
Gau
s
s
ian
f
u
n
ctio
n
.
On
ce
th
e
d
en
s
ity
is
co
m
p
u
ted
,
th
e
alg
o
r
ith
m
ap
p
lies
f
u
zz
y
lo
g
ic
to
ass
ig
n
m
em
b
er
s
h
ip
v
alu
e
s
to
ea
ch
p
o
in
t,
e
n
ab
lin
g
it
to
h
an
d
le
n
o
is
e
an
d
o
u
tlier
s
m
o
r
e
ef
f
ec
tiv
el
y
.
B
y
o
p
tim
izin
g
t
h
ese
clu
s
ter
s
th
r
o
u
g
h
FB
DS
C
AN,
th
e
alg
o
r
ith
m
en
h
a
n
ce
s
its
ab
ilit
y
to
p
r
ed
ict
tig
er
ag
e
b
y
id
en
tif
y
in
g
r
elev
an
t
p
atter
n
s
with
in
th
e
im
ag
e
d
ata.
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
in
co
r
p
o
r
ates
a
tig
er
im
ag
e
d
atab
ase,
m
ak
in
g
MA
T
L
AB
to
o
l
u
s
ag
e
ea
s
ier
.
T
h
is
d
atab
ase
co
n
tain
s
o
v
er
1
,
0
0
0
im
ag
es
f
r
o
m
ca
m
er
a
tr
a
p
s
an
d
o
th
er
s
o
u
r
ce
s
in
d
if
f
e
r
en
t
s
izes
an
d
f
o
r
m
ats.
I
m
ag
es
o
f
tig
er
s
f
r
o
m
v
ar
io
u
s
ag
e
g
r
o
u
p
s
a
r
e
all
ca
teg
o
r
ized
with
in
th
e
s
am
e
class
,
en
s
u
r
in
g
a
c
o
n
s
is
ten
t
an
d
ef
f
icien
t a
n
aly
s
is
p
r
o
ce
s
s
.
4
.
1
.
Co
m
pu
t
a
t
io
na
l
c
o
m
plex
it
y
W
h
en
ev
alu
ated
in
ter
m
s
o
f
ti
m
e
er
u
d
itio
n
a
n
aly
s
is
to
n
o
r
m
alize
th
eir
s
im
u
lated
ef
f
icien
c
y
,
th
e
p
o
les
ap
ar
t
clu
s
ter
tech
n
iq
u
e
was
f
o
u
n
d
to
b
e
co
m
p
u
tatio
n
ally
co
m
p
lex
an
d
to
b
e
m
o
r
e
ef
f
icie
n
t
th
an
th
e
s
tan
d
ar
d
clu
s
ter
in
g
tech
n
iq
u
e.
T
h
e
a
b
ilit
y
to
cr
ea
te
h
ier
ar
ch
ies
in
b
u
n
ch
i
n
g
ap
p
r
o
ac
h
es
was
co
n
s
tr
u
ed
as
a
g
iv
en
co
m
p
u
tatio
n
al
co
n
v
o
lu
tio
n
eq
u
atio
n
,
wh
e
r
ea
s
th
e
f
u
zz
y
b
a
s
ed
DB
SC
AN
clu
s
ter
in
g
alg
o
r
ith
m
n
ec
ess
itates
f
ewe
r
s
tep
s
to
b
e
p
er
f
o
r
m
e
d
in
a
g
iv
en
cl
u
s
ter
in
g
m
eth
o
d
.
(
(
−
∑
−
1
=
0
)
2
)
(
7
)
Hen
ce
,
r
ep
r
esen
ts
th
e
to
tal
n
u
m
b
er
o
f
co
lo
r
p
ix
els,
d
en
o
t
es
th
e
n
u
m
b
er
o
f
clu
s
ter
s
,
a
n
d
in
d
icate
s
th
e
n
u
m
b
er
o
f
iter
atio
n
s
ap
p
lied
t
o
.
Fig
u
r
e
5
d
em
o
n
s
tr
ates
th
e
ef
f
ec
t
o
f
s
p
atial
e
p
s
ilo
n
(
E
PS
)
an
d
c
o
lo
r
E
PS
as
p
a
r
a
m
eter
s
ar
e
d
eter
m
in
ed
.
T
h
e
im
ag
e
d
ata
b
ase
is
th
e
f
o
cu
s
o
f
th
is
ef
f
icien
t
FDB
SC
AN
clu
s
ter
in
g
s
tr
ateg
y
.
T
h
e
s
h
ar
p
ch
an
g
e
in
th
e
k
-
d
is
t
v
alu
e
is
s
i
m
ilar
to
th
e
co
r
r
ec
t
E
p
s
ilo
n
v
alu
e.
Min
Pts
:
T
h
e
n
u
m
b
er
o
f
d
im
en
s
io
n
s
D
in
th
e
d
ata
s
et
ca
n
b
e
u
s
ed
to
ca
lcu
late
a
m
in
im
u
m
Min
Pts
as
f
o
llo
ws:
Min
Pt
s
D+
1
.
I
t
m
ak
es
n
o
s
en
s
e
to
s
et
Min
P
ts
to
a
lo
w
v
al
u
e
o
f
1
,
s
in
ce
th
e
n
ea
ch
p
o
in
t
will
alr
ea
d
y
b
e
a
clu
s
ter
o
n
its
o
wn
.
W
ith
Min
Pts
≤
2
,
T
h
e
r
esu
lt
will
b
e
eq
u
iv
alen
t
to
m
u
ltip
le
lev
els
o
f
g
r
o
u
p
i
n
g
u
s
in
g
a
s
in
g
le
co
n
n
ec
tio
n
m
etr
ic,
with
th
e
d
en
d
r
o
g
r
a
m
cu
t a
t
lev
el
ε.
ε:
Usi
n
g
a
k
-
d
is
tan
ce
g
r
ap
h
,
wh
ic
h
p
l
o
ts
th
e
d
is
ta
n
ce
to
t
h
e
k
=
Min
Pts
-
1
n
ea
r
est
n
eig
h
b
o
r
in
o
r
d
er
f
r
o
m
th
e
lar
g
est to
th
e
s
m
allest v
alu
e,
th
e
v
alu
e
o
f
th
e
d
is
tan
ce
ca
n
th
en
b
e
ch
o
s
en
.
Fig
u
r
e
5
.
Pix
el
clu
s
ter
in
g
b
ase
d
o
n
tig
e
r
ag
e
g
r
o
u
p
o
n
k
=
2
,
k
=
4
,
k
=
6
,
p
lo
t v
alu
es
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
.
2
,
Ap
r
il
20
25
:
2
1
6
1
-
2
1
7
1
2166
4
.
2
.
Ag
e
predict
io
n
o
f
t
he
re
a
l t
i
m
e
t
ig
er
i
m
a
g
e
Pre
d
ictin
g
th
e
ag
e
o
f
tig
er
s
b
ased
o
n
th
eir
im
ag
es
in
v
o
l
v
es
s
eg
m
en
tin
g
th
e
im
ag
e
in
to
r
elev
an
t
r
eg
io
n
s
an
d
a
n
aly
zin
g
t
h
e
p
ix
el
attr
ib
u
tes
to
d
er
iv
e
m
ea
n
in
g
f
u
l
p
atter
n
s
.
T
h
e
u
n
d
er
ly
in
g
p
r
in
cip
le
is
th
at
as
tig
er
s
ag
e,
th
e
ch
ar
ac
ter
is
tics
o
f
t
h
eir
f
u
r
,
s
u
c
h
as
th
e
d
en
s
ity
o
f
s
tr
ip
es,
co
lo
r
in
te
n
s
ity
,
an
d
tex
tu
r
e,
m
ay
ch
an
g
e.
T
h
e
im
a
g
e
o
f
a
tig
er
ca
n
b
e
r
ep
r
esen
ted
as
a
m
atr
ix
o
f
p
ix
els,
wh
er
e
ea
ch
p
ix
el
h
as
th
r
ee
co
lo
r
co
m
p
o
n
en
ts
(
R
GB
)
.
L
et
(
,
)
r
e
p
r
esen
t
th
e
p
ix
el
in
ten
s
ity
a
t
co
o
r
d
in
ates
(
,
)
in
th
e
im
ag
e
.
T
h
e
s
eg
m
en
tatio
n
p
r
o
ce
s
s
ca
n
b
e
e
x
p
r
ess
ed
as a
f
u
n
ctio
n
th
at
ass
ig
n
s
ea
ch
p
ix
el
to
a
clu
s
ter
:
(
,
)
=
∑
(
,
)
.
(
(
,
)
)
=
1
(
8
)
wh
er
e
(
,
)
is
th
e
s
eg
m
en
ted
o
u
tp
u
t
at
p
ix
el
(
,
)
.
(
,
)
is
th
e
m
em
b
e
r
s
h
ip
v
alu
e
o
f
p
ix
el
(
,
)
b
elo
n
g
in
g
to
clu
s
ter
(
r
an
g
in
g
f
r
o
m
0
to
1
in
f
u
zz
y
clu
s
ter
in
g
)
.
(
(
,
)
)
is
th
e
f
u
n
ctio
n
th
at
r
e
p
r
es
en
ts
th
e
ch
ar
ac
ter
is
tics
(
lik
e
m
ea
n
o
r
v
ar
ian
ce
)
o
f
clu
s
ter
.
T
h
is
d
if
f
er
en
ce
r
ep
r
esen
ts
th
e
s
p
atial
s
ep
ar
atio
n
n
ee
d
ed
b
etwe
en
p
ix
els
h
an
d
led
b
y
th
e
ce
lls
an
d
th
o
s
e
in
in
co
r
r
ec
t
f
r
am
es
o
f
(
)
.
E
s
s
en
tially
,
it
m
ea
s
u
r
es
h
o
w
well
th
e
tech
n
iq
u
e
ca
n
d
is
tin
g
u
is
h
b
etwe
en
p
ix
els
in
v
ar
io
u
s
f
r
am
es.
T
o
ass
ess
o
v
er
all
s
eg
m
en
tatio
n
p
r
ec
is
io
n
,
d
iv
id
e
th
ese
v
alu
es
b
y
th
e
to
t
al
n
u
m
b
er
o
f
p
ix
els
(
=
∑
=
∑
)
,
.
T
h
is
ca
lcu
latio
n
in
v
o
lv
es
d
eter
m
in
i
n
g
(
∑
)
,
wh
ich
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
p
ix
els
in
th
e
tig
er
im
ag
e
d
atab
ase
th
at
alig
n
with
th
e
ag
e
class
if
icatio
n
s
in
th
e
g
r
o
u
n
d
tr
u
th
.
=
∑
−
∑
.
=
1
,
=
1
,
=
1
=
1
,
=
1
,
=
1
2
−
∑
.
=
1
,
=
1
,
=
1
(
9
)
Fo
r
ex
am
p
le,
d
en
o
tes
th
e
f
u
n
d
am
en
tal
E
u
clid
ea
n
d
is
tan
ce
,
is
th
e
to
tal
n
u
m
b
er
o
f
p
i
x
els
in
an
im
ag
e,
an
d
m
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
r
ed
,
g
r
ee
n
,
b
lu
e
(
R
GB
)
co
lo
r
class
es.
T
h
e
to
tal
n
u
m
b
er
o
f
co
r
r
ec
tly
class
if
ied
p
ix
els
in
a
tig
er
im
ag
e
is
in
d
icate
d
as
.
Ad
d
itio
n
ally
,
ea
ch
co
lo
r
p
i
x
el'
s
th
r
esh
o
ld
v
alu
e
was
s
et
to
a
s
p
ec
if
ic
tig
er
wh
en
d
eter
m
i
n
in
g
th
e
ag
e
t
h
r
esh
o
ld
f
o
r
th
e
ti
g
er
im
ag
e
.
T
h
e
n
u
m
b
er
o
f
p
ix
els
in
ea
ch
r
o
w
an
d
co
lu
m
n
is
r
ep
r
esen
ted
b
y
an
d
r
esp
ec
tiv
ely
.
T
h
e
d
ata
ab
o
v
e
ar
e
s
o
r
ted
b
y
y
ea
r
,
as
s
h
o
wn
in
T
ab
le
1
.
T
o
co
m
p
ar
e
with
t
h
e
d
if
f
er
e
n
t
p
ar
am
eter
lik
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F
-
m
ea
s
u
r
e
is
u
s
ed
to
ev
alu
ate
to
p
r
ed
ict
th
e
ag
e
o
f
th
e
tig
e
r
an
d
f
in
d
th
e
ef
f
icien
t o
f
th
e
ab
o
v
e
m
etr
ics.
T
h
e
h
i
g
h
est
p
r
ec
is
io
n
is
9
4
.
3
p
er
ce
n
t,
wh
ile
th
e
lo
west
p
r
ec
is
io
n
is
9
2
%.
T
h
e
l
o
west
r
ec
all
is
9
1
%,
wh
ile
th
e
h
ig
h
est
r
ec
all
is
9
4
%.
T
h
e
l
o
west
F
-
m
ea
s
u
r
e
is
9
1
.
6
%,
wh
ile
th
e
h
ig
h
est
is
9
3
.
5
%
.
T
h
e
tab
le'
s
s
im
ilar
ity
m
ea
s
u
r
es
ar
e
s
lig
h
tly
ex
cited
wh
en
co
m
p
a
r
ed
to
ea
ch
o
th
e
r
.
T
h
e
m
o
s
t
elev
ated
ac
cu
r
ac
y
is
9
4
.
3
%
f
o
r
E
u
clid
ea
n
an
d
m
o
s
t
n
o
tewo
r
th
y
r
e
v
iew
is
9
4
%
f
o
r
b
o
th
c
o
m
p
ar
a
b
ilit
y
m
ea
s
u
r
es
as
city
b
lo
ck
an
d
C
h
eb
y
s
h
ev
,
a
n
d
th
e
m
o
s
t
ele
v
ated
F
-
m
ea
s
u
r
e
is
9
3
.
5
%
i
n
E
u
clid
ea
n
a
n
d
th
e
least
is
f
o
u
n
d
in
th
e
clo
s
en
ess
m
ea
s
u
r
es o
n
p
lain
as to
co
n
tr
a
s
t a
n
d
o
th
er
o
n
e.
T
ab
le
1
.
Dif
f
e
r
en
t p
ar
a
m
eter
s
ch
ec
k
ed
with
1
y
ea
r
tig
e
r
im
a
g
e
d
ata
b
ase
A
g
e
S
M
R
PV
RV
F
M
V
1
y
e
a
r
CBV
9
2
%
9
4
%
9
3
%
CCV
9
3
%
9
4
%
9
3
.
5
%
EV
9
4
.
3
%
9
1
%
9
2
.
6
5
%
MV
9
2
%
9
1
.
2
%
9
1
.
6
%
N
o
t
e
:
S
M
R
-
s
i
mi
l
a
r
i
t
y
m
e
a
s
u
r
e
s
,
P
V
-
p
r
e
c
i
s
i
o
n
v
a
l
u
e
,
RV
-
r
e
c
a
l
l
v
a
l
u
e
,
F
M
V
:
F
-
mea
s
u
r
e
s
v
a
l
u
e
Ad
d
itio
n
ally
,
T
ab
le
1
ev
alu
ate
s
th
e
co
n
s
is
ten
cy
o
f
clu
s
ter
in
g
ac
cu
r
ac
y
f
o
r
d
if
f
er
en
t
tig
e
r
i
m
ag
e
ag
es.
I
t
h
ig
h
li
g
h
ts
s
p
ec
if
ic
f
u
n
ctio
n
s
s
u
ch
as
city
b
lo
c
k
,
C
h
eb
y
s
h
ev
d
is
tan
ce
,
Min
k
o
wsk
i
d
is
tan
ce
,
an
d
o
th
e
r
d
is
tan
ce
m
ea
s
u
r
es,
u
s
in
g
clu
s
ter
in
g
m
etr
ics
lik
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
F
-
m
ea
s
u
r
e.
T
h
e
e
x
p
er
im
en
tal
r
esu
lts
ar
e
illu
s
tr
ated
in
Fig
u
r
e
6
.
T
h
e
f
o
llo
win
g
d
ata
ar
e
s
o
r
ted
b
y
y
ea
r
in
th
e
tig
er
im
ag
e
d
ata
b
ase,
as
s
h
o
wn
in
T
a
b
le
2
.
C
o
n
s
is
ten
tly
,
th
e
n
u
m
b
e
r
o
f
clu
s
ter
s
is
tak
en
to
b
e
th
r
ee
.
T
h
e
h
ig
h
est
p
r
e
cisi
o
n
r
ec
o
r
d
e
d
in
th
e
s
ec
o
n
d
y
ea
r
is
9
3
%,
wh
ile
th
e
lo
west
p
r
ec
is
io
n
is
9
2
%.
T
h
e
lo
west
r
ec
all
is
9
0
%,
wh
ile
th
e
h
ig
h
est
r
ec
all
is
0
.
9
4
.
T
h
e
lo
west
F
-
m
ea
s
u
r
e
is
9
1
.
5
%
,
wh
ile
th
e
h
ig
h
est
is
9
3
%
.
W
h
en
co
m
p
ar
ed
to
ea
c
h
o
f
th
e
s
im
ilar
ity
m
ea
s
u
r
es
in
t
h
e
tab
le,
is
s
lig
h
tly
s
atis
f
ied
.
T
h
e
r
esu
lts
ar
e
co
m
p
letely
d
if
f
er
en
t
f
r
o
m
th
o
s
e
o
f
th
e
p
r
ev
i
o
u
s
y
ea
r
,
d
esp
ite
th
e
u
n
if
o
r
m
ch
an
g
e
i
n
th
e
s
ec
o
n
d
y
ea
r
.
C
ity
b
lo
c
k
s
h
av
e
th
e
h
i
g
h
est
p
r
ec
is
io
n
at
9
3
%,
Min
k
o
wsk
i
h
as
th
e
h
i
g
h
est
r
ec
all
at
9
4
%,
a
n
d
Min
k
o
wsk
i
h
as
th
e
h
ig
h
est
F
-
m
ea
s
u
r
e
at
9
3
.
5
%
,
wh
ile
s
im
ilar
ity
m
ea
s
u
r
es
o
n
th
e
tab
u
lar
ar
e
th
e
lo
west
wh
en
co
m
p
ar
ed
to
o
th
e
r
m
eth
o
d
s
.
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
Op
timiz
a
tio
n
tech
n
iq
u
es a
p
p
l
ied
o
n
ima
g
e
s
eg
men
ta
tio
n
p
r
o
ce
s
s
b
y
…
(
R
a
ma
r
a
j Mu
n
ia
p
p
a
n
)
2167
Similar
ity
-
b
ased
clu
s
ter
in
g
ca
n
ef
f
ec
tiv
ely
p
r
e
d
ict
th
e
ag
e
o
f
tig
er
im
ag
es,
as
d
em
o
n
s
tr
a
ted
b
y
th
e
d
etailed
m
etr
ics
f
o
r
city
b
l
o
c
k
,
C
h
eb
y
s
h
e
v
,
Mi
n
k
o
wsk
i,
a
n
d
E
u
clid
ea
n
d
is
tan
ce
s
in
T
a
b
le
2
.
Acc
u
r
ac
y
is
ass
es
s
ed
u
s
in
g
clu
s
ter
in
g
in
d
i
ca
to
r
s
s
u
ch
as
f
it
r
ate,
r
ec
all,
an
d
F
-
v
alu
e.
T
h
e
r
esu
lts
o
f
th
ese
ex
p
er
im
en
ts
ar
e
illu
s
tr
ated
in
Fig
u
r
e
7
.
Fig
u
r
e
6
.
Nu
m
er
o
u
s
s
im
ilar
ity
m
etr
ics ar
e
u
s
ed
o
n
FDB
SC
A
N
with
o
n
e
-
y
ea
r
tig
er
im
ag
e
T
ab
le
2
.
Ap
p
lied
FDB
SC
A
N
with
d
if
f
er
en
t similar
ity
m
ea
s
u
r
es u
s
in
g
two
-
y
ea
r
tig
er
im
a
g
e
A
g
e
S
M
R
PV
RV
F
M
V
2
y
e
a
r
s
CBV
9
3
%
9
0
%
9
1
.
5
%
CCV
9
1
%
9
2
%
9
1
.
5
%
EV
9
2
%
9
3
%
9
2
.
5
%
MV
9
2
%
9
4
%
9
3
%
Fig
u
r
e
7
.
Dif
f
e
r
en
t similar
ity
m
etr
ics ar
e
u
s
ed
o
n
FDB
S
C
A
N
with
2
nd
-
y
ea
r
s
tig
er
im
a
g
e
As
p
er
T
ab
le
3
,
th
e
in
f
o
r
m
atio
n
is
ar
r
an
g
ed
y
e
ar
wis
e.
Ov
er
th
e
co
u
r
s
e
o
f
1
5
y
ea
r
s
,
th
e
lo
west
p
r
ec
is
io
n
was
9
2
%,
wh
ile
t
h
e
h
ig
h
est
p
r
ec
is
io
n
was
9
3
%.
T
h
e
lo
west
r
ec
all
r
ate
is
9
0
.
1
0
%,
wh
ile
th
e
h
ig
h
est
r
ec
all
is
9
5
.
5
%.
T
h
e
lo
west
a
n
d
h
ig
h
est
F
-
m
ea
s
u
r
es
ar
e
9
1
.
0
5
%
an
d
9
4
%,
r
esp
ec
tiv
ely
.
W
h
en
co
m
p
ar
ed
to
ea
ch
o
f
th
e
s
im
ilar
ity
m
ea
s
u
r
e
s
in
th
e
tab
le,
is
s
lig
h
tly
s
atis
f
ied
.
T
h
e
1
5
th
y
ea
r
s
ee
s
a
co
n
s
is
ten
t
ch
an
g
e,
b
u
t
th
e
o
u
tco
m
es
ar
e
co
m
p
letely
d
if
f
er
en
t
f
r
o
m
th
o
s
e
o
f
th
e
p
r
ev
io
u
s
y
ea
r
.
T
h
e
city
b
lo
ck
h
as
th
e
h
ig
h
est
p
r
ec
is
io
n
o
f
9
3
%,
th
e
h
i
g
h
e
s
t
r
ec
all
o
f
9
5
%,
th
e
h
ig
h
es
t
F
-
m
ea
s
u
r
e
o
f
9
4
%,
a
n
d
th
e
lo
west
s
im
ilar
ity
m
ea
s
u
r
es o
n
th
e
tab
u
lar
to
c
o
m
p
ar
e
with
o
th
e
r
o
n
es.
T
ab
le
4
p
r
esen
ts
th
e
co
n
s
is
ten
cy
o
f
v
a
r
io
u
s
clu
s
ter
in
g
m
at
r
ices,
in
clu
d
in
g
r
o
o
t
m
ea
n
s
q
u
ar
e
er
r
o
r
(
R
MSE
)
v
alu
es,
p
r
ed
ictio
n
tim
e
in
ter
v
als,
an
d
im
ag
e
an
aly
s
is
tim
e,
f
o
r
b
o
th
estab
lis
h
ed
an
d
im
p
r
o
v
e
d
m
eth
o
d
s
.
T
h
e
clu
s
ter
in
g
r
esu
l
ts
ar
e
p
r
esen
ted
g
r
ap
h
ically
wh
en
ev
er
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
wer
e
u
tili
ze
d
an
d
p
r
o
d
u
ce
d
s
u
p
e
r
io
r
r
esu
lts
th
at
wer
e
s
ig
n
if
ican
tly
m
o
r
e
ac
cu
r
ate
an
d
ef
f
icien
t.
I
n
f
u
zz
y
b
ased
DB
SC
AN
clu
s
ter
in
g
,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as th
e
h
ig
h
est ac
cu
r
ac
y
r
a
tin
g
o
f
a
n
y
o
f
th
e
th
r
ee
m
eth
o
d
s
test
ed
.
92%
93%
9
4
.
3
0
%
92%
94%
94%
91%
9
1
.
2
0
%
93%
9
3
.
5
0
%
9
2
.
6
5
%
9
1
.
6
0
%
8
8
%
9
0
%
9
2
%
9
4
%
9
6
%
CBV
CCV
EV
MV
1
y
e
a
r
Ag
e
P
er
ce
nta
g
e
M
ea
s
ures
O
ne
y
ear
t
i
ger
PV
RV
F
M
V
93%
91%
92%
92%
90%
92%
93%
94%
9
1
.
5
0
%
9
1
.
5
0
%
9
2
.
5
0
%
93%
8
8
%
8
9
%
9
0
%
9
1
%
9
2
%
9
3
%
9
4
%
9
5
%
CBV
CCV
EV
MV
2
y
e
a
r
Ac
c
u
r
a
c
y
Per
c
e
n
ta
g
e
M
e
a
su
r
e
s
O
v
er
a
ll
P
er
f
o
rm
a
nce
o
f
T
w
o
y
ea
r
T
ig
er
im
a
g
e
da
t
a
s
et
FM
V
RV
PV
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
.
2
,
Ap
r
il
20
25
:
2
1
6
1
-
2
1
7
1
2168
T
ab
le
3
.
FDB
SC
AN
u
s
ed
d
if
f
er
en
t c
lu
s
ter
in
g
s
im
ilar
ity
ap
p
r
o
ac
h
es o
n
ti
g
er
im
ag
e
d
ataset
A
g
e
S
M
R
PV
RV
F
M
V
1
5
y
e
a
r
s
CBV
9
3
%
9
5
%
9
4
%
CCV
9
2
%
9
1
%
9
1
.
5
%
EV
9
3
%
9
3
%
9
3
%
MV
9
2
%
9
0
.
1
0
%
9
1
.
0
5
%
T
ab
le
4
.
E
v
alu
atio
n
o
f
en
h
an
c
ed
clu
s
ter
in
g
m
etr
ics
A
c
c
u
r
a
c
y
v
a
l
u
e
R
M
S
E
v
a
l
u
e
Ti
me
p
r
o
c
e
ss
I
mag
e
r
e
t
r
i
e
v
a
l
p
r
o
c
e
ss
P
r
e
v
a
i
l
i
n
g
8
4
.
4
8
9
P
r
e
v
a
i
l
i
n
g
0
.
7
6
5
8
8
9
P
r
e
v
a
i
l
i
n
g
3
.
2
7
4
9
2
P
r
e
v
a
i
l
i
n
g
2
.
5
1
En
h
a
n
c
e
d
8
5
.
9
0
4
En
h
a
n
c
e
d
0
.
6
7
8
4
6
7
En
h
a
n
c
e
d
2
.
4
5
6
6
5
7
En
h
a
n
c
e
d
1
.
8
6
T
ab
le
3
m
ea
s
u
r
es
th
e
ac
cu
r
ac
y
o
f
s
im
ilar
ity
-
b
ased
clu
s
ter
in
g
,
u
s
in
g
s
im
ilar
ity
f
u
n
ctio
n
s
s
u
ch
as
city
b
lo
ck
,
C
h
eb
y
s
h
e
v
d
is
tan
ce
,
Min
k
o
wsk
i
d
is
tan
ce
,
an
d
E
u
clid
ea
n
d
is
tan
ce
.
C
lu
s
ter
in
g
in
d
icato
r
s
lik
e
p
r
ec
is
io
n
,
r
ec
all,
an
d
th
e
F
-
m
ea
s
u
r
e
a
r
e
e
m
p
lo
y
ed
t
o
ev
alu
ate
th
ese
f
u
n
ctio
n
s
'
ef
f
ec
tiv
en
ess
in
p
r
ed
ictin
g
th
e
ag
e
o
f
tig
er
im
ag
es.
T
h
e
r
esu
lts
o
f
th
ese
ex
p
er
im
en
ts
ar
e
illu
s
tr
ated
in
Fig
u
r
e
8
.
Fig
u
r
e
9
co
m
p
ar
es
th
e
ac
cu
r
ac
y
,
p
r
o
ce
s
s
in
g
tim
e,
an
d
im
a
g
e
s
ea
r
ch
p
er
f
o
r
m
an
ce
o
f
th
e
ti
g
er
im
ag
e
d
atab
ase
with
b
o
th
th
e
p
r
o
p
o
s
ed
an
d
ex
is
tin
g
m
eth
o
d
s
.
T
a
b
le
4
d
eta
ils
th
e
r
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Fig
u
r
e
8
.
I
ll
u
s
tr
ate
o
n
FDB
SC
AN
u
s
ed
with
d
if
f
er
en
t c
l
u
s
ter
in
g
s
im
ilar
ity
m
eth
o
d
s
ap
p
lied
th
e
tig
er
im
ag
e
Fig
u
r
e
9
.
C
o
m
p
a
r
is
o
n
o
f
o
v
e
r
all
p
er
f
o
r
m
a
n
ce
m
ea
s
u
r
es
5.
CO
NCLU
SI
O
N
I
n
co
n
clu
s
io
n
,
th
is
r
esear
ch
i
n
tr
o
d
u
ce
s
a
s
o
p
h
is
ticated
ap
p
r
o
ac
h
u
tili
zin
g
f
u
zz
y
clu
s
ter
in
g
m
o
d
els,
p
ar
ticu
lar
ly
FDB
SC
AN,
to
e
n
h
an
ce
th
e
ac
cu
r
ac
y
an
d
ef
f
icien
cy
o
f
p
r
ed
ictin
g
tig
er
ag
e
b
ased
o
n
co
lo
r
attr
ib
u
tes
f
r
o
m
ca
m
e
r
a
tr
ap
i
m
ag
es.
C
o
m
p
ar
ed
t
o
th
e
latest
s
tatis
t
ical
m
eth
o
d
s
,
o
u
r
a
p
p
r
o
ac
h
ex
ce
ls
in
b
o
t
h
p
r
ec
is
io
n
an
d
s
p
ee
d
,
o
f
f
er
in
g
a
s
ig
n
if
ican
t
im
p
r
o
v
em
en
t
i
n
th
e
v
is
u
al
p
r
esen
tatio
n
a
n
d
an
aly
s
is
o
f
im
ag
e
93%
92%
93%
92%
95%
91%
93%
9
0
.
1
0
%
94%
9
1
.
5
0
%
93%
9
1
.0
5
%
8
6
%
8
8
%
9
0
%
9
2
%
9
4
%
9
6
%
CBV
CCV
EV
MV
1
5
y
e
a
r
A
g
e
Pe
r
c
e
n
tag
e
S
i
mi
l
ar
i
ty
In
d
e
x
O
V
E
R
A
L
L
P
E
R
F
O
R
M
A
N
C
E
O
F
1
5
Y
E
A
R
T
I
G
E
R
I
M
A
G
E
D
A
T
A
S
E
T
PV
RV
F
M
V
84.489
0.765889
3.27492
2.51
85.904
0.678467
2.456657
1.86
0
50
100
A
c
c
u
racy
V
a
l
u
e
R
MS
E
V
a
l
u
e
T
i
me
Pro
c
e
s
s
Ima
g
e
R
e
tr
i
e
val
Pro
c
e
s
s
A
c
c
u
r
ac
y
Value
s
M
e
asu
r
e
s
O
v
er
all
p
r
ocess
Pre
vail
i
n
g
E
n
h
an
c
e
d
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
Op
timiz
a
tio
n
tech
n
iq
u
es a
p
p
l
ied
o
n
ima
g
e
s
eg
men
ta
tio
n
p
r
o
ce
s
s
b
y
…
(
R
a
ma
r
a
j Mu
n
ia
p
p
a
n
)
2169
d
atab
ases
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
au
to
m
atin
g
tig
er
ag
e
d
eter
m
in
atio
n
th
r
o
u
g
h
im
ag
e
d
atab
ases
h
as
b
ee
n
s
u
cc
ess
f
u
lly
ac
h
iev
ed
b
y
p
r
o
c
ess
in
g
o
v
er
1
,
0
0
0
r
ea
l
-
tim
e
im
ag
es
o
f
tig
er
s
i
n
th
eir
n
atu
r
al
f
o
r
est
h
ab
itats
.
T
h
is
ex
ten
s
iv
e
d
ataset
in
clu
d
es
a
d
iv
er
s
e
r
an
g
e
o
f
a
d
u
lt
s
p
ec
im
e
n
s
an
d
is
an
aly
ze
d
b
ased
o
n
d
is
tin
ctiv
e
f
ea
tu
r
es
s
u
ch
as
s
tr
ip
es,
s
k
in
to
n
es,
an
d
o
v
er
all
co
l
o
r
v
ar
iatio
n
s
.
T
h
r
o
u
g
h
class
if
y
in
g
im
a
g
es
in
to
d
if
f
er
en
t
ag
e
g
r
o
u
p
s
,
wh
en
th
e
m
eth
o
d
ef
f
ec
tiv
el
y
g
r
o
u
p
s
tig
er
s
ac
co
r
d
in
g
to
th
eir
ag
e.
T
h
e
r
esear
c
h
is
s
tr
u
c
tu
r
ed
in
to
d
etailed
s
ec
tio
n
s
th
at
elu
cid
ate
th
e
co
r
r
elatio
n
b
etwe
en
co
lo
r
ch
ar
a
cter
is
tics
an
d
ag
e
d
eter
m
in
ati
o
n
,
s
h
o
wca
s
in
g
t
h
e
m
eth
o
d
'
s
r
o
b
u
s
tn
ess
an
d
ap
p
li
ca
b
ilit
y
.
T
h
is
in
n
o
v
atio
n
n
o
t
o
n
ly
a
d
v
an
ce
s
t
h
e
f
ield
o
f
im
ag
e
p
r
o
ce
s
s
in
g
b
u
t
also
p
r
o
v
id
es
v
alu
ab
le
in
s
ig
h
ts
f
o
r
wild
life
r
esear
ch
an
d
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
,
o
f
f
er
in
g
a
s
ig
n
if
ican
t
co
n
tr
ib
u
tio
n
to
b
o
th
th
e
o
r
etica
l a
n
d
p
r
ac
tical
asp
ec
ts
o
f
a
g
e
p
r
ed
ictio
n
in
tig
e
r
s
.
RE
F
E
R
E
NC
E
S
[
1
]
K
.
G
a
u
t
a
m
a
n
d
R
.
S
i
n
g
h
a
i
,
“
C
o
l
o
r
i
ma
g
e
se
g
me
n
t
a
t
i
o
n
u
s
i
n
g
p
a
r
t
i
c
l
e
s
w
a
r
m
o
p
t
i
m
i
z
a
t
i
o
n
i
n
l
a
b
c
o
l
o
r
sp
a
c
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
ri
n
g
D
e
v
e
l
o
p
m
e
n
t
a
n
d
Re
se
a
r
c
h
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
3
7
3
–
3
7
7
,
2
0
1
8
.
[
2
]
E.
H
u
a
n
g
e
t
a
l
.
,
“
O
c
c
l
u
s
i
o
n
-
r
e
s
i
st
a
n
t
i
n
st
a
n
c
e
se
g
m
e
n
t
a
t
i
o
n
o
f
p
i
g
l
e
t
s
i
n
f
a
r
r
o
w
i
n
g
p
e
n
s
u
s
i
n
g
c
e
n
t
e
r
c
l
u
s
t
e
r
i
n
g
n
e
t
w
o
r
k
,
”
C
o
m
p
u
t
e
rs
a
n
d
E
l
e
c
t
r
o
n
i
c
s
i
n
A
g
r
i
c
u
l
t
u
r
e
,
v
o
l
.
2
1
0
,
J
u
l
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
a
g
.
2
0
2
3
.
1
0
7
9
5
0
.
[
3
]
X
.
Li
u
,
C
.
H
u
,
a
n
d
P
.
L
i
,
“
A
u
t
o
mat
i
c
se
g
m
e
n
t
a
t
i
o
n
o
f
o
v
e
r
l
a
p
p
e
d
p
o
p
l
a
r
se
e
d
l
i
n
g
l
e
a
v
e
s
c
o
m
b
i
n
i
n
g
M
a
s
k
R
-
C
N
N
a
n
d
D
B
S
C
A
N
,
”
C
o
m
p
u
t
e
rs
a
n
d
El
e
c
t
ro
n
i
c
s i
n
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
1
7
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
0
.
1
0
5
7
5
3
.
[
4
]
T.
C
z
e
r
n
i
a
w
s
k
i
,
B
.
S
a
n
k
a
r
a
n
,
M
.
N
a
h
a
n
g
i
,
C
.
H
a
a
s
,
a
n
d
F
.
L
e
i
t
e
,
“
6
D
D
B
S
C
A
N
-
b
a
s
e
d
s
e
g
me
n
t
a
t
i
o
n
o
f
b
u
i
l
d
i
n
g
p
o
i
n
t
c
l
o
u
d
s
f
o
r
p
l
a
n
a
r
o
b
j
e
c
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
Au
t
o
m
a
t
i
o
n
i
n
C
o
n
s
t
ru
c
t
i
o
n
,
v
o
l
.
8
8
,
p
p
.
4
4
–
5
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
u
t
c
o
n
.
2
0
1
7
.
1
2
.
0
2
9
.
[
5
]
K
.
M
a
r
d
a
n
i
a
n
d
K
.
M
a
g
h
o
o
l
i
,
“
E
n
h
a
n
c
i
n
g
r
e
t
i
n
a
l
b
l
o
o
d
v
e
s
sel
se
g
me
n
t
a
t
i
o
n
i
n
me
d
i
c
a
l
i
m
a
g
e
s
u
si
n
g
c
o
m
b
i
n
e
d
s
e
g
me
n
t
a
t
i
o
n
mo
d
e
s
e
x
t
r
a
c
t
e
d
b
y
D
B
S
C
A
N
a
n
d
m
o
r
p
h
o
l
o
g
i
c
a
l
r
e
c
o
n
s
t
r
u
c
t
i
o
n
,
”
Bi
o
m
e
d
i
c
a
l
S
i
g
n
a
l
Pr
o
c
e
ssi
n
g
a
n
d
C
o
n
t
r
o
l
,
v
o
l
.
6
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
b
s
p
c
.
2
0
2
1
.
1
0
2
8
3
7
.
[
6
]
N
.
H
a
n
a
f
i
a
n
d
H
.
S
a
a
d
a
t
f
a
r
,
“
A
f
a
st
D
B
S
C
A
N
a
l
g
o
r
i
t
h
m
f
o
r
b
i
g
d
a
t
a
b
a
se
d
o
n
e
f
f
i
c
i
e
n
t
d
e
n
si
t
y
c
a
l
c
u
l
a
t
i
o
n
,
”
E
x
p
e
r
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
3
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
7
5
0
1
.
[
7
]
X
.
H
u
a
n
g
,
T.
M
a
,
C
.
Li
u
,
a
n
d
S
.
Li
u
,
“
G
r
i
T
-
D
B
S
C
A
N
:
a
s
p
a
t
i
a
l
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
f
o
r
v
e
r
y
l
a
r
g
e
d
a
t
a
b
a
ses,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
4
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
3
.
1
0
9
6
5
8
.
[
8
]
S
.
Y
a
n
g
,
P
.
L
i
,
H
.
X
.
W
e
n
,
Y
.
X
i
e
,
a
n
d
Z.
H
e
,
“
K
-
h
y
p
e
r
l
i
n
e
c
l
u
s
t
e
r
i
n
g
-
b
a
se
d
c
o
l
o
r
i
m
a
g
e
s
e
g
m
e
n
t
a
t
i
o
n
r
o
b
u
s
t
t
o
i
l
l
u
m
i
n
a
t
i
o
n
c
h
a
n
g
e
s
,
”
S
y
m
m
e
t
ry
,
v
o
l
.
1
0
,
n
o
.
1
1
,
2
0
1
8
,
d
o
i
:
1
0
.
3
3
9
0
/
sy
m1
0
1
1
0
6
1
0
.
[
9
]
M
.
R
a
mar
a
j
a
n
d
S
.
N
i
r
a
i
ma
t
h
i
,
“
C
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
si
s
o
f
p
r
o
p
o
se
d
me
t
h
o
d
s
f
o
r
a
n
a
l
y
si
n
g
c
o
l
o
r
p
i
x
e
l
b
a
se
d
i
m
a
g
e
se
g
m
e
n
t
a
t
i
o
n
u
si
n
g
t
i
g
e
r
i
ma
g
e
d
a
t
a
s
e
t
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Re
s
e
a
r
c
h
,
v
o
l
.
7
,
n
o
.
9
,
p
p
.
2
4
5
–
2
5
2
,
2
0
1
8
.
[
1
0
]
Q
.
Z
h
u
,
X
.
Ta
n
g
,
a
n
d
A
.
El
a
h
i
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
t
h
e
n
o
v
e
l
h
a
r
m
o
n
y
sea
r
c
h
o
p
t
i
mi
z
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
D
B
S
C
A
N
c
l
u
s
t
e
r
i
n
g
,
”
Ex
p
e
rt
S
y
st
e
m
s w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
1
.
1
1
5
0
5
4
.
[
1
1
]
M
.
Y
a
n
,
Y
.
C
h
e
n
,
Y
.
C
h
e
n
,
G
.
Ze
n
g
,
X
.
H
u
,
a
n
d
J
.
D
u
,
“
A
l
i
g
h
t
w
e
i
g
h
t
w
e
a
k
l
y
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
se
g
me
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
i
m
b
a
l
a
n
c
e
d
i
ma
g
e
b
a
s
e
d
o
n
r
o
t
a
t
i
o
n
d
e
n
s
i
t
y
p
e
a
k
s,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
st
e
m
s
,
v
o
l
.
2
4
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
sy
s
.
2
0
2
2
.
1
0
8
5
1
3
.
[
1
2
]
C
.
C
h
e
n
,
J.
G
u
o
,
Y
.
Li
,
a
n
d
L
.
X
u
,
“
S
e
g
me
n
t
a
t
i
o
n
-
b
a
se
d
h
i
e
r
a
r
c
h
i
c
a
l
i
n
t
e
r
p
o
l
a
t
i
o
n
f
i
l
t
e
r
u
s
i
n
g
b
o
t
h
g
e
o
m
e
t
r
i
c
a
n
d
r
a
d
i
o
me
t
r
i
c
f
e
a
t
u
r
e
s
f
o
r
Li
D
A
R
p
o
i
n
t
c
l
o
u
d
s
o
v
e
r
c
o
m
p
l
e
x
s
c
e
n
a
r
i
o
s,
”
Me
a
s
u
remen
t
:
J
o
u
r
n
a
l
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
Me
a
s
u
reme
n
t
C
o
n
f
e
d
e
r
a
t
i
o
n
,
v
o
l
.
2
1
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
me
a
s
u
r
e
me
n
t
.
2
0
2
3
.
1
1
2
6
6
8
.
[
1
3
]
Y
.
Z
h
a
n
g
,
Y
.
Zh
a
n
g
,
L
.
F
a
n
,
a
n
d
N
.
W
a
n
g
,
“
F
a
s
t
a
n
d
a
c
c
u
r
a
t
e
su
p
e
r
p
i
x
e
l
seg
m
e
n
t
a
t
i
o
n
a
l
g
o
r
i
t
h
m
w
i
t
h
a
g
u
i
d
a
n
c
e
i
ma
g
e
,
”
I
m
a
g
e
a
n
d
Vi
s
i
o
n
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
2
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
m
a
v
i
s.
2
0
2
2
.
1
0
4
5
9
6
.
[
1
4
]
Y
.
H
u
a
n
g
,
W
.
J.
H
u
a
n
g
,
X
.
L.
X
i
a
n
g
,
a
n
d
J.
J
.
Y
a
n
,
“
A
n
e
m
p
i
r
i
c
a
l
s
t
u
d
y
o
f
p
e
r
so
n
a
l
i
z
e
d
a
d
v
e
r
t
i
si
n
g
r
e
c
o
m
me
n
d
a
t
i
o
n
b
a
s
e
d
o
n
D
B
S
C
A
N
c
l
u
s
t
e
r
i
n
g
o
f
si
n
a
w
e
i
b
o
u
ser
-
g
e
n
e
r
a
t
e
d
c
o
n
t
e
n
t
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
8
3
,
p
p
.
3
0
3
–
3
1
0
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
2
1
.
0
2
.
0
6
3
.
[
1
5
]
S
.
K
.
D
u
b
e
y
a
n
d
S
.
V
i
j
a
y
,
“
A
r
e
v
i
e
w
o
f
i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
u
s
i
n
g
c
l
u
st
e
r
i
n
g
m
e
t
h
o
d
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
A
p
p
l
i
e
d
En
g
i
n
e
e
ri
n
g
Re
s
e
a
rc
h
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
2
4
8
4
–
2
4
8
9
,
2
0
1
8
.
[
1
6
]
M
.
R
a
maraj
a
n
d
S
.
N
i
r
a
i
mat
h
i
,
“
En
h
a
n
c
e
d
i
mag
e
seg
men
t
a
t
i
o
n
t
o
i
n
f
e
r
t
h
e
a
g
e
o
f
t
h
e
t
i
g
e
r
u
si
n
g
f
u
z
z
y
m
o
d
i
f
i
e
d
K
-
mea
n
s
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
m
(
F
M
K
M
C
A
)
,
”
Re
sea
rch
J
o
u
rn
a
l
o
f
Ph
a
rm
a
c
e
u
t
i
c
a
l
,
Bi
o
l
o
g
i
c
a
l
a
n
d
C
h
e
m
i
c
a
l
S
c
i
e
n
c
e
s
,
v
o
l
.
1
0
,
n
o
.
2
,
2019.
[
1
7
]
O
.
S
u
d
a
n
a
,
I
.
K
.
G
.
D
.
P
u
t
r
a
,
M
.
S
u
d
a
r
ma,
R
.
S
.
H
a
r
t
a
t
i
,
a
n
d
A
.
W
i
r
d
i
a
n
i
,
“
I
mag
e
c
l
u
st
e
r
i
n
g
o
f
c
o
mp
l
e
x
b
a
l
i
n
e
se
c
h
a
r
a
c
t
e
r
w
i
t
h
D
B
S
C
A
N
a
l
g
o
r
i
t
h
m,
”
J
o
u
r
n
a
l
o
f
E
n
g
i
n
e
e
ri
n
g
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
,
n
o
.
1
,
p
p
.
5
4
8
–
5
5
8
,
2
0
1
8
.
[
1
8
]
Y
.
W
a
n
g
,
X
.
Y
a
n
g
,
L.
Z
h
a
n
g
,
X
.
F
a
n
,
Q
.
Y
e
,
a
n
d
L.
F
u
,
“
I
n
d
i
v
i
d
u
a
l
t
r
e
e
se
g
me
n
t
a
t
i
o
n
a
n
d
t
r
e
e
-
c
o
u
n
t
i
n
g
u
si
n
g
su
p
e
r
v
i
s
e
d
c
l
u
st
e
r
i
n
g
,
”
C
o
m
p
u
t
e
r
s
a
n
d
E
l
e
c
t
r
o
n
i
c
s i
n
Ag
r
i
c
u
l
t
u
r
e
,
v
o
l
.
2
0
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
mp
a
g
.
2
0
2
3
.
1
0
7
6
2
9
.
[
1
9
]
M
.
R
a
mar
a
j
a
n
d
S
.
N
i
r
a
i
m
a
t
h
i
,
“
D
e
si
g
n
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
s
o
f
c
o
l
o
r
p
i
x
e
l
b
a
s
e
d
i
ma
g
e
s
e
g
m
e
n
t
a
t
i
o
n
u
s
i
n
g
e
n
h
a
n
c
e
d
d
a
t
a
c
l
u
st
e
r
i
n
g
a
l
g
o
r
i
t
h
ms
t
o
a
p
p
l
y
i
n
g
o
n
t
i
g
e
r
i
m
a
g
e
d
a
t
a
s
e
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
of
P
u
re
and
A
p
p
l
i
e
d
Ma
t
h
e
m
a
t
i
c
s
,
v
o
l
.
1
1
9
,
n
o
.
1
8
,
p
p
.
2
7
1
9
–
2
7
3
9
,
2
0
1
8
.
[
2
0
]
N
.
S
.
B
.
M
a
t
S
a
i
d
,
H
.
M
a
d
z
i
n
,
S
.
K
.
A
l
i
,
a
n
d
N
.
S
.
B
e
n
g
,
“
C
o
mp
a
r
i
s
o
n
o
f
c
o
l
o
r
-
b
a
se
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s
i
n
b
a
n
a
n
a
l
e
a
f
d
i
s
e
a
se
s
c
l
a
s
si
f
i
c
a
t
i
o
n
u
si
n
g
S
V
M
a
n
d
K
-
NN,
”
I
n
d
o
n
e
si
a
n
J
o
u
rn
a
l
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
2
4
,
n
o
.
3
,
p
p
.
1
5
2
3
–
1
5
3
3
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
e
c
s
.
v
2
4
.
i
3
.
p
p
1
5
2
3
-
1
5
3
3
.
[
2
1
]
H
.
C
h
e
n
,
M
.
Li
a
n
g
,
W
.
Li
u
,
W
.
W
a
n
g
,
a
n
d
P
.
X
.
Li
u
,
“
A
n
a
p
p
r
o
a
c
h
t
o
b
o
u
n
d
a
r
y
d
e
t
e
c
t
i
o
n
f
o
r
3
D
p
o
i
n
t
c
l
o
u
d
s
b
a
s
e
d
o
n
D
B
S
C
A
N
c
l
u
s
t
e
r
i
n
g
,
”
P
a
t
t
e
r
n
Re
c
o
g
n
i
t
i
o
n
,
v
o
l
.
1
2
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
a
t
c
o
g
.
2
0
2
1
.
1
0
8
4
3
1
.
[
2
2
]
V
.
D
.
C
o
n
g
a
n
d
T
.
T.
H
i
e
p
,
“
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
-
b
a
se
d
o
b
j
e
c
t
c
l
a
ssi
f
i
c
a
t
i
o
n
f
o
r
r
o
b
o
t
a
r
m
sy
s
t
e
m
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
3
,
n
o
.
5
,
p
p
.
5
0
4
7
–
5
0
5
3
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
5
.
p
p
5
0
4
7
-
5
0
5
3
.
[
2
3
]
P
.
S
h
i
,
L.
G
u
o
,
H
.
C
u
i
,
a
n
d
L.
C
h
e
n
,
“
G
e
o
m
e
t
r
i
c
c
o
n
s
i
st
e
n
t
f
u
z
z
y
c
l
u
s
t
e
r
e
n
sem
b
l
e
w
i
t
h
m
e
m
b
e
r
s
h
i
p
r
e
c
o
n
s
t
r
u
c
t
i
o
n
f
o
r
i
m
a
g
e
seg
m
e
n
t
a
t
i
o
n
,
”
D
i
g
i
t
a
l
S
i
g
n
a
l
Pr
o
c
e
ss
i
n
g
:
A
Re
v
i
e
w
J
o
u
r
n
a
l
,
v
o
l
.
1
3
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
sp
.
2
0
2
2
.
1
0
3
9
0
1
.
[
2
4
]
W
.
Ji
n
g
,
C
.
Z
h
a
o
,
a
n
d
C
.
Ji
a
n
g
,
“
A
n
i
m
p
r
o
v
e
me
n
t
me
t
h
o
d
o
f
D
B
S
C
A
N
a
l
g
o
r
i
t
h
m
o
n
c
l
o
u
d
c
o
m
p
u
t
i
n
g
,
”
Pr
o
c
e
d
i
a
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
1
4
7
,
p
p
.
5
9
6
–
6
0
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
r
o
c
s.
2
0
1
9
.
0
1
.
2
0
8
.
[
2
5
]
A
.
D
.
K
h
a
l
e
e
l
e
t
a
l
.
,
“
P
a
t
t
e
r
n
r
e
c
o
n
f
i
g
u
r
a
b
l
e
d
i
e
l
e
c
t
r
i
c
r
e
s
o
n
a
t
o
r
a
n
t
e
n
n
a
u
s
i
n
g
c
a
p
a
c
i
t
o
r
l
o
a
d
i
n
g
f
o
r
i
n
t
e
r
n
e
t
o
f
t
h
i
n
g
s
a
p
p
l
i
c
a
t
i
o
n
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
4
1
4
5
–
4
1
5
1
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
4
.
p
p
4
1
4
5
-
4
1
5
1
.
[
2
6
]
X
.
B
a
i
,
Z
.
X
i
e
,
X
.
X
u
,
a
n
d
Y
.
X
i
a
o
,
“
A
n
a
d
a
p
t
i
v
e
t
h
r
e
sh
o
l
d
f
a
s
t
D
B
S
C
A
N
a
l
g
o
r
i
t
h
m
w
i
t
h
p
r
e
ser
v
e
d
t
r
a
j
e
c
t
o
r
y
f
e
a
t
u
r
e
p
o
i
n
t
s
f
o
r
v
e
ss
e
l
t
r
a
j
e
c
t
o
r
y
c
l
u
st
e
r
i
n
g
,
”
O
c
e
a
n
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
8
0
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
o
c
e
a
n
e
n
g
.
2
0
2
3
.
1
1
4
9
3
0
.
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
.
2
,
Ap
r
il
20
25
:
2
1
6
1
-
2
1
7
1
2170
[
2
7
]
A
.
E.
F
a
h
r
u
d
i
n
,
E
n
d
a
r
k
o
,
K
.
A
i
n
,
a
n
d
A
.
R
u
b
i
y
a
n
t
o
,
“
En
h
a
n
c
e
d
i
m
a
g
e
r
e
c
o
n
st
r
u
c
t
i
o
n
o
f
e
l
e
c
t
r
i
c
a
l
i
mp
e
d
a
n
c
e
t
o
mo
g
r
a
p
h
y
u
s
i
n
g
si
mu
l
t
a
n
e
o
u
s
a
l
g
e
b
r
a
i
c
r
e
c
o
n
st
r
u
c
t
i
o
n
t
e
c
h
n
i
q
u
e
a
n
d
K
-
me
a
n
s
c
l
u
st
e
r
i
n
g
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
4
,
p
p
.
3
9
8
7
–
3
9
9
7
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
4
.
p
p
3
9
8
7
-
3
9
9
7
.
[
2
8
]
S
.
S
.
R
e
d
d
y
,
V
.
V
.
R
.
M
.
R
a
o
,
K
.
S
r
a
v
a
n
i
,
a
n
d
S
.
N
r
u
s
i
mh
a
d
r
i
,
“
I
mag
e
q
u
a
l
i
t
y
e
v
a
l
u
a
t
i
o
n
:
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
i
ma
g
e
q
u
a
l
i
t
y
o
f
a
c
t
u
a
l
i
m
a
g
e
s
b
y
u
s
i
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
m
o
d
e
l
s
,
”
B
u
l
l
e
t
i
n
o
f
El
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
3
,
n
o
.
2
,
p
p
.
1
1
7
2
–
1
1
8
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
3
i
2
.
5
9
4
7
.
[
2
9
]
A
.
A
sh
r
a
f
,
A
.
S
o
p
h
i
a
n
,
A
.
A
.
S
h
a
f
i
e
,
T.
S
.
G
u
n
a
w
a
n
,
a
n
d
N
.
N
.
I
smai
l
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
-
b
a
s
e
d
p
a
v
e
m
e
n
t
c
r
a
c
k
d
e
t
e
c
t
i
o
n
,
c
l
a
ss
i
f
i
c
a
t
i
o
n
,
a
n
d
c
h
a
r
a
c
t
e
r
i
z
a
t
i
o
n
:
a
r
e
v
i
e
w
,
”
Bu
l
l
e
t
i
n
o
f
El
e
c
t
r
i
c
a
l
En
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
3
6
0
1
–
3
6
1
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
2
i
6
.
5
3
4
5
.
[
3
0
]
E.
L.
C
a
h
a
p
i
n
,
B
.
A
.
M
a
l
a
b
a
g
,
C
.
S
.
S
a
n
t
i
a
g
o
,
J.
L.
R
e
y
e
s,
G
.
S
.
Le
g
a
sp
i
,
a
n
d
K
.
L.
A
d
r
a
l
e
s,
“
C
l
u
st
e
r
i
n
g
o
f
s
t
u
d
e
n
t
s
a
d
mi
ss
i
o
n
d
a
t
a
u
s
i
n
g
k
-
m
e
a
n
s,
h
i
e
r
a
r
c
h
i
c
a
l
,
a
n
d
D
B
S
C
A
N
a
l
g
o
r
i
t
h
ms
,
”
B
u
l
l
e
t
i
n
o
f
E
l
e
c
t
ri
c
a
l
En
g
i
n
e
e
r
i
n
g
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
v
o
l
.
1
2
,
n
o
.
6
,
p
p
.
3
6
4
7
–
3
6
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
e
e
i
.
v
1
2
i
6
.
4
8
4
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
m
a
r
a
j
Mu
n
ia
p
p
a
n
is
wo
r
k
in
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
Ra
th
i
n
a
m
Co
ll
e
g
e
o
f
Arts
a
n
d
S
c
ie
n
c
e
,
Co
imb
a
to
re
.
He
h
o
l
d
s
a
P
h
.
D
.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
fro
m
Bh
a
ra
th
iar
Un
iv
e
rsit
y
in
2
0
2
0
with
a
sp
e
c
ializa
ti
o
n
in
d
a
ta
m
in
in
g
with
ima
g
e
p
ro
c
e
ss
in
g
a
n
d
f
u
z
z
y
lo
g
ic
in
ima
g
e
a
n
a
ly
sis.
His
re
se
a
rc
h
a
re
a
s
a
re
d
a
ta
m
in
in
g
,
ima
g
e
p
ro
c
e
ss
in
g
,
fu
z
z
y
l
o
g
ic,
p
a
t
tern
re
c
o
g
n
it
i
o
n
,
a
n
d
d
e
e
p
lea
rn
in
g
c
o
n
c
e
p
ts.
He
h
a
s
p
u
b
li
sh
e
d
n
u
m
e
ro
u
s res
e
a
rc
h
a
rti
c
les
in
re
p
u
ted
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls an
d
h
a
s a
lso
fil
e
d
p
a
ten
ts
in
th
e
sa
m
e
field
.
He
is
a
re
v
iew
e
r
fo
r
m
a
n
y
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls,
in
c
l
u
d
i
n
g
IEE
E,
AST
E
S
J,
a
n
d
JERS
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
m
a
ra
j.
p
h
d
c
s@
g
m
a
il
.
c
o
m
,
ra
m
a
ra
j.
p
h
d
c
s1
2
3
@g
m
a
il
.
c
o
m
.
S
r
iv
id
h
y
a
S
e
lv
a
r
a
j
is
wo
rk
i
n
g
a
s
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
i
n
t
h
e
d
e
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
KPR
Co
ll
e
g
e
o
f
Arts
S
c
ien
c
e
a
Re
se
a
rc
h
,
Co
imb
a
to
re
.
S
h
e
h
a
s
m
o
re
th
a
n
a
d
e
c
a
d
e
o
f
tea
c
h
i
n
g
e
x
p
e
r
ien
c
e
in
d
iffere
n
t
v
e
rti
c
a
ls.
S
h
e
is
a
re
v
iew
e
r
i
n
v
a
ri
o
u
s
in
tern
a
ti
o
n
a
l
j
o
u
r
n
a
ls
a
n
d
li
fe
-
ti
m
e
m
e
m
b
e
r
in
IAENG
.
He
r
re
se
a
rc
h
a
re
a
in
c
lu
d
e
s
d
a
ta
m
in
in
g
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
d
e
e
p
lea
rn
in
g
.
S
h
e
h
a
s
a
b
o
u
t
1
0
+
r
e
se
a
rc
h
p
a
p
e
rs
p
u
b
li
sh
e
d
i
n
n
a
ti
o
n
a
l
a
n
d
i
n
tern
a
ti
o
n
a
l
jo
u
rn
a
ls
.
S
h
e
a
lso
p
re
se
n
ted
m
o
re
t
h
a
n
1
5
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s
a
n
d
a
l
s
o
p
u
b
li
sh
e
d
m
a
n
y
b
o
o
k
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
id
h
y
a
sa
i1
4
@g
m
a
il
.
c
o
m
.
Ra
n
i
V
a
n
a
th
i
G
u
r
u
sa
m
y
is
c
u
rre
n
tl
y
w
o
rk
i
n
g
a
s
a
p
r
o
fe
ss
o
r
a
n
d
h
e
a
d
a
t
S
ri
Ra
m
a
k
rish
n
a
CAS
fo
r
Wo
m
e
n
.
S
h
e
h
a
s
b
e
e
n
a
ss
o
c
iate
d
with
th
e
sa
m
e
c
o
ll
e
g
e
fo
r
th
e
las
t
2
4
y
e
a
rs.
S
h
e
re
c
e
iv
e
d
h
e
r
P
h
.
D.
in
c
o
m
p
u
ter
sc
ien
c
e
fr
o
m
Bh
a
ra
th
i
a
r
Un
iv
e
rsity
in
2
0
1
3
.
He
r
a
re
a
s
o
f
re
se
a
rc
h
in
c
lu
d
e
d
a
ta
s
c
ien
c
e
,
m
o
b
il
e
a
d
h
o
c
n
e
two
rk
s,
c
lo
u
d
c
o
m
p
u
ti
n
g
,
n
e
two
rk
se
c
u
rit
y
,
a
n
d
o
n
l
in
e
e
d
u
c
a
ti
o
n
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
m
o
re
t
h
a
n
3
0
p
a
p
e
rs
in
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
jo
u
rn
a
ls,
i
n
c
lu
d
in
g
S
COPUS
,
Th
o
m
so
n
Re
u
ters
,
UG
C,
a
n
d
IEE
E,
a
n
d
h
a
s
a
ls
o
p
re
se
n
ted
a
t
v
a
rio
u
s
n
a
ti
o
n
a
l
a
n
d
in
tern
a
ti
o
n
a
l
c
o
n
fe
re
n
c
e
s.
He
r
late
st
b
o
o
k
p
u
b
li
c
a
ti
o
n
is
o
n
th
e
to
p
ic
o
f
m
u
lt
ime
d
ia
sy
ste
m
s.
S
h
e
re
c
e
iv
e
d
₹
6
,
0
0
,
0
0
0
f
u
n
d
i
n
g
a
ss
istan
c
e
fro
m
ICS
S
R
IM
P
RES
S
i
n
2
0
1
9
.
S
h
e
wa
s
a
wa
rd
e
d
th
e
“
Re
se
a
rc
h
Aw
a
rd
”
b
y
Bh
a
ra
t
h
iar
Un
iv
e
rsit
y
o
n
Na
ti
o
n
a
l
S
c
ie
n
c
e
Da
y
in
2
0
2
1
.
S
h
e
is
th
e
c
u
rre
n
t
v
ice
-
p
re
sid
e
n
t
o
f
th
e
S
RCW
a
l
u
m
n
i
a
ss
o
c
iatio
n
a
n
d
t
h
e
re
se
a
rc
h
c
o
o
rd
i
n
a
to
r
o
f
S
RCW.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
n
ics
@s
rc
w.ac
.
in
.
Ve
lu
m
a
n
i
Th
i
y
a
g
a
r
a
ja
n
is
wo
rk
i
n
g
a
s
a
n
a
ss
istan
t
p
r
o
fe
ss
o
r
in
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
t
Ra
th
in
a
m
Co
ll
e
g
e
o
f
Arts
a
n
d
S
c
ien
c
e
(Au
to
n
o
m
o
u
s),
Co
imb
a
t
o
re
6
4
1
0
2
1
fro
m
1
4
-
09
-
2
0
2
0
to
ti
ll
d
a
te.
He
h
a
s g
o
t
m
o
re
th
a
n
1
2
y
e
a
rs o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
He
h
a
s
o
b
tai
n
e
d
h
is
B.
S
c
.
(CT),
M
.
S
c
.
(
CS
),
M
.
P
h
il
a
n
d
M
BA
d
e
g
re
e
s
fr
o
m
P
e
ri
y
a
r
Un
i
v
e
rsity
S
a
lem
,
Tam
il
Na
d
u
,
In
d
ia.
He
h
a
s
o
b
ta
in
e
d
h
is
B.
Ed
.
De
g
re
e
fro
m
In
d
ira
Ga
n
d
h
i
Na
ti
o
n
a
l
Op
e
n
Un
iv
e
rsity
(IG
NO
U)
a
t
De
lh
i,
h
is
M
.
S
c
.
(
P
sy
c
h
o
lo
g
y
)
fro
m
M
a
d
ra
s
Un
iv
e
rsity
M
a
d
ra
s,
Tam
il
Na
d
u
,
I
n
d
ia.
He
h
a
s
o
b
tain
e
d
h
is
P
h
.
D
.
in
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
M
a
n
o
n
m
a
n
iam
S
u
n
d
a
ra
n
a
r
Un
iv
e
rsity
a
t
Ti
ru
n
e
lv
e
ll
i,
Tam
il
Na
d
u
,
In
d
ia.
His
a
re
a
o
f
in
tere
st
i
s
ima
g
e
p
ro
c
e
ss
in
g
re
se
a
rc
h
d
irec
ti
o
n
s
i
n
v
o
lv
e
d
k
n
o
wle
d
g
e
d
isc
o
v
e
ry
a
n
d
d
a
ta
m
in
in
g
,
p
a
tt
e
rn
re
c
o
g
n
it
io
n
,
k
n
o
wle
d
g
e
-
b
a
se
d
n
e
u
ra
l
n
e
tw
o
rk
s,
so
ftwa
re
e
n
g
i
n
e
e
rin
g
a
n
d
I
o
T.
He
h
a
s
p
u
b
li
sh
e
d
m
o
re
th
a
n
1
5
p
a
p
e
rs
i
n
to
p
m
o
st
in
tern
a
ti
o
n
a
l
p
e
e
r
-
re
v
iew
e
d
jo
u
rn
a
ls
a
n
d
c
o
n
fe
re
n
c
e
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
v
e
lu
m
a
n
i4
6
@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.