T
E
L
K
O
M
N
I
K
A
T
elec
o
m
m
un
ica
t
io
n,
Co
m
pu
t
ing
,
E
lect
ro
nics
a
nd
Co
ntr
o
l
Vo
l.
1
8
,
No
.
6
,
Dec
em
b
er
2
0
2
0
,
p
p
.
2
9
2
1
~
2
9
2
7
I
SS
N:
1
6
9
3
-
6
9
3
0
,
ac
cr
ed
ited
First Gr
ad
e
b
y
Kem
en
r
is
tek
d
i
k
ti,
Dec
r
ee
No
: 2
1
/E/KPT
/2
0
1
8
DOI
: 1
0
.
1
2
9
2
8
/TE
L
KOM
NI
K
A.
v
1
8
i
6
.
1
6
1
4
9
2921
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//jo
u
r
n
a
l.u
a
d
.
a
c.
id
/in
d
ex
.
p
h
p
/TELK
OM
N
I
K
A
Vein palm
r
ecog
nition mo
del using
fusio
n of f
ea
tures
Q
a
s
s
im
Abd Al
-
hu
s
s
a
in H
a
d
i
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Co
ll
a
g
e
o
f
C
o
m
p
u
ter S
c
ien
c
e
a
n
d
In
f
o
rm
a
ti
o
n
Tec
h
n
o
lo
g
y
,
Un
iv
e
rsit
y
o
f
Al
-
Qa
d
isiy
a
h
,
Ira
q
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
r
2
6
,
2
0
2
0
R
ev
is
ed
Ma
y
2
2
,
2
0
2
0
Acc
ep
ted
J
u
n
1
2
,
2
0
2
0
On
e
o
f
th
e
m
o
st
p
ro
m
isi
n
g
m
e
c
h
a
n
ism
s
in
th
e
field
o
f
se
c
u
rit
y
a
n
d
i
n
fo
rm
a
ti
o
n
sa
fe
ty
is
a
u
th
e
n
ti
c
a
ti
o
n
b
a
se
d
o
n
p
a
lm
v
e
in
.
T
h
e
m
a
in
re
a
so
n
s
t
h
a
t
v
e
in
p
a
lm
b
e
c
o
m
e
s
a
n
a
u
th
e
n
ti
c
a
ti
o
n
m
e
th
o
d
is
b
e
c
a
u
se
o
f
it
s
d
isti
n
c
ti
v
e
p
ri
v
a
c
y
,
a
s
it
is
d
iffi
c
u
lt
t
o
m
a
n
ip
u
late
o
r
c
h
a
n
g
e
i
ts
re
su
lt
s,
b
e
c
a
u
se
o
f
th
e
lo
c
a
ti
o
n
o
f
th
e
v
e
i
n
with
in
th
e
p
a
lm.
Wi
th
t
h
e
u
se
o
f
t
h
is
tec
h
n
o
l
o
g
y
,
it
h
a
s
b
e
c
o
m
e
e
a
sy
to
m
a
in
tain
d
a
ta
fr
o
m
u
n
a
u
t
h
o
r
ize
d
a
c
c
e
s
s
a
n
d
u
n
wa
n
ted
p
e
rso
n
s.
In
th
is
w
o
rk
p
ro
p
o
se
d
m
o
d
e
l
a
re
su
g
g
e
ste
d
th
a
t
c
o
n
tain
fo
u
r
sta
g
e
s
to
re
a
c
h
th
e
re
su
lt
s:
in
th
e
first
sta
g
e
is
th
e
p
re
-
p
ro
c
e
ss
in
g
sta
g
e
wh
e
re
h
isto
g
ra
m
e
q
u
a
ti
o
n
wa
s
u
se
d
to
e
n
h
a
n
c
e
th
e
ima
g
e
a
n
d
th
e
p
r
o
p
e
rti
e
s
a
re
sh
o
wn
,
th
e
s
e
c
o
n
d
s
tag
e
is
th
e
e
x
trac
ti
n
g
t
h
e
p
ro
p
e
rti
e
s
wh
e
re
,
G
a
b
o
r
fil
ter
a
n
d
2
-
d
isc
re
te
wa
v
e
let
fil
ters
a
re
su
g
g
e
ste
d
f
o
r
fe
a
tu
re
s
e
x
trac
ti
o
n
,
wh
e
re
it
is
c
o
n
sid
e
re
d
o
n
e
o
f
th
e
m
o
st
imp
o
rtan
t
fi
lt
e
rs
u
se
d
to
e
x
trac
t
th
e
fe
a
tu
re
s,
a
s
we
ll
a
s
in
th
e
th
ir
d
sta
g
e
"
P
CA
"
a
re
u
se
d
fo
r
d
a
ta o
r
fe
a
tu
re
s
re
d
u
c
ti
o
n
,
b
e
c
a
u
se
o
f
it
s
a
d
v
a
n
ta
g
e
s
i
n
a
n
a
l
y
z
in
g
th
e
fe
a
tu
re
s
a
n
d
re
d
u
c
in
g
th
e
sp
a
c
in
g
b
e
twe
e
n
th
e
m
.
As
fo
r
th
e
las
t
sta
g
e
,
th
e
Eu
c
li
d
e
a
n
d
istan
c
e
u
se
d
t
o
m
e
a
su
re
th
e
s
p
a
c
in
g
.
Th
e
re
su
lt
s
we
re
a
c
c
e
p
tab
le
a
n
d
c
o
n
v
i
n
c
in
g
,
sin
c
e
th
e
sim
il
a
ri
ty
ra
ti
o
9
6
.
2
%
.
T
h
e
se
re
su
lt
s
we
re
o
b
tain
e
d
a
fter
se
v
e
ra
l
tes
ts
a
n
d
u
si
n
g
t
h
e
G
a
b
o
r
fil
ter
wit
h
2
D
-
d
isc
re
te
wa
v
e
let
tran
sfo
rm
a
n
d
p
ri
n
c
ip
a
l
c
o
m
p
o
n
e
n
t
a
n
a
ly
sis
(
P
CA
)
,
I
g
o
t
th
e
b
e
st r
e
su
lt
s.
K
ey
w
o
r
d
s
:
E
u
clid
ea
n
d
is
tan
ce
Gab
o
r
f
ilter
Palm
v
ien
R
ec
o
g
n
itio
n
W
av
elet
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
:
Qass
im
Ab
d
Al
-
h
u
s
s
ain
Had
i
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
C
o
llag
e
o
f
C
o
m
p
u
ter
Sci
en
ce
a
n
d
I
n
f
o
r
m
atio
n
T
ec
h
n
o
lo
g
y
,
Un
iv
er
s
ity
o
f
Al
-
Qad
is
iy
ah
,
Al
Diwan
iy
ah
,
I
r
aq
.
E
m
ail:
Alzb
y
d
y
q
asm
5
@
g
m
ail
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
Hu
m
an
s
h
av
e
tr
ied
in
th
e
p
ast
to
ac
ce
s
s
an
d
d
ev
is
e
t
o
o
ls
th
r
o
u
g
h
wh
ich
t
o
m
ai
n
tain
th
eir
p
r
o
p
er
ty
an
d
p
r
iv
ate
m
o
n
e
y
as
well
a
s
th
eir
p
lace
s
an
d
b
ec
au
s
e
th
e
tech
n
o
l
o
g
y
was
n
o
t
at
th
e
lev
el
r
eq
u
ir
ed
to
r
eso
r
t
to
to
o
ls
b
u
t n
o
t th
e
r
eq
u
ir
e
d
s
ec
u
r
ity
as th
ey
wen
t to
th
e
k
ey
s
an
d
lo
ck
s
to
m
ain
tain
th
e
s
ec
u
r
ity
o
f
th
eir
p
r
o
p
er
ty
f
r
o
m
th
e
ar
r
iv
al
o
f
u
n
au
th
o
r
ized
p
eo
p
le
[
1
]
.
W
ith
th
e
a
d
v
an
ce
m
en
t
o
f
tim
e
an
d
th
e
m
ar
k
e
d
ad
v
an
ce
m
en
t
o
f
tech
n
o
lo
g
y
,
m
o
r
e
s
ec
u
r
ity
to
o
l
s
h
av
e
em
er
g
ed
,
as
p
r
o
g
r
ess
h
a
s
b
ee
n
a
v
illa
in
th
e
f
ield
o
f
I
n
t
er
n
et
n
etwo
r
k
s
an
d
th
e
u
s
e
o
f
m
o
d
er
n
tec
h
n
o
l
o
g
ie
s
f
r
o
m
c
o
m
p
u
te
r
s
,
m
o
b
ile
d
ev
i
ce
s
,
an
d
o
t
h
er
s
.
B
u
t
at
th
e
s
am
e
tim
e,
th
ese
d
e
v
ices
n
ee
d
p
r
o
g
r
am
s
an
d
m
eth
o
d
s
t
o
v
er
if
y
th
e
id
en
tity
o
f
th
e
u
s
er
,
to
f
o
llo
w
t
h
e
en
tr
y
ef
f
ec
tiv
e
ly
an
d
s
ec
u
r
ely
an
d
p
r
ev
en
t
u
n
au
th
o
r
ized
p
e
r
s
o
n
s
f
r
o
m
ac
ce
s
s
in
g
th
e
r
eq
u
ir
ed
d
ata.
Per
h
ap
s
o
n
e
o
f
t
h
e
m
o
s
t
p
r
o
m
in
e
n
t
s
cien
ce
s
u
s
ed
in
th
is
f
ield
is
th
e
v
ital
m
ea
s
u
r
es
f
o
r
d
eter
m
in
in
g
th
e
id
en
tity
o
f
th
e
u
s
er
an
d
v
a
lid
atin
g
th
em
[
2
]
.
T
h
e
id
en
tity
o
f
th
e
au
th
o
r
ize
d
p
er
s
o
n
ca
n
b
e
co
n
f
ir
m
ed
b
y
p
r
o
v
id
in
g
ac
ce
p
ta
b
le
an
d
co
n
s
id
er
ed
ev
id
en
ce
th
at
th
e
s
p
ec
if
ied
co
n
d
itio
n
s
f
o
r
a
cc
ess
in
g
th
e
d
ata
ar
e
f
u
lf
illed
.
Per
h
ap
s
th
e
m
o
s
t
p
r
o
m
in
en
t
tech
n
iq
u
es
u
s
ed
to
m
ain
tain
th
e
s
ec
u
r
ity
a
n
d
in
te
g
r
ity
o
f
d
ata
f
r
o
m
u
n
au
th
o
r
iz
ed
ac
ce
s
s
is
th
e
p
atter
n
o
f
th
e
p
alm
v
ein
,
wh
er
e
th
e
v
en
o
u
s
p
atter
n
s
ar
e
lo
ca
te
d
in
th
e
p
alm
an
d
it is
o
n
e
o
f
t
h
e
m
o
s
t secu
r
e
tech
n
iq
u
es b
ec
au
s
e
it is
d
if
f
icu
lt to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
1
8
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
292
1
-
292
7
2922
s
teal
an
d
m
an
ip
u
late
th
em
a
f
ter
all
th
e
v
ein
is
u
n
d
er
th
e
s
k
in
an
d
is
n
o
t
af
f
ec
te
d
b
y
t
h
e
ad
v
a
n
ce
m
en
t
o
f
a
p
er
s
o
n
'
s
ag
e
an
d
ca
n
n
o
t
b
e
u
s
ed
as
an
alter
n
ativ
e
to
it
[
3
]
.
T
h
e
ch
ar
ac
ter
is
tics
u
s
ed
b
y
t
h
e
v
ein
d
ep
en
d
o
n
s
ev
er
al
f
ilter
s
to
e
x
tr
ac
t
th
e
m
o
s
t
im
p
o
r
tan
t
f
ea
tu
r
es,
th
e
Ga
b
o
r
f
ilter
,
an
d
th
e
Gau
s
s
ian
f
il
ter
.
T
h
e
p
atter
n
o
f
p
alm
v
ein
s
i
n
th
e
s
ec
u
r
ity
f
ield
ca
n
b
e
c
o
n
s
id
er
ed
o
n
e
o
f
th
e
a
r
ea
s
th
at
ca
n
b
e
d
ev
elo
p
ed
an
d
u
tili
ze
d
to
m
ai
n
tain
d
ata
s
ec
u
r
ity
an
d
in
teg
r
ity
b
ec
au
s
e
it
i
s
co
n
s
id
er
ed
o
n
e
o
f
th
e
m
o
s
t
p
r
o
m
is
in
g
m
eth
o
d
s
in
th
is
f
ield
[
4
]
.
T
h
e
d
ata
b
ase
u
s
ed
i
n
th
is
wo
r
k
s
elec
ted
f
r
o
m
th
e
in
s
titu
te
o
f
co
n
tr
o
l
an
d
in
f
o
r
m
atio
n
en
g
in
ee
r
in
g
,
Po
zn
a
n
Un
iv
er
s
ity
o
f
T
ec
h
n
o
lo
g
y
,
Po
l
an
d
[
5]
.
2.
RE
L
AT
E
D
WO
RK
T
h
e
r
esear
ch
er
in
th
e
p
r
o
p
o
s
ed
wo
r
k
,
h
e
is
s
u
g
g
ested
an
d
s
tu
d
y
in
g
th
e
v
ein
p
alm
r
ec
o
g
n
itio
n
,
m
ajo
r
ly
th
is
wo
r
k
is
d
iv
id
ed
in
to
t
h
r
ee
p
h
ases
:
I
n
th
e
f
ir
s
t
s
tag
e,
wh
ich
is
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
tag
e
wh
er
e
u
s
in
g
C
L
AHE
an
d
2
-
D
Gau
s
s
ian
h
ig
h
p
ass
f
ilter
to
en
h
an
ce
th
e
e
n
tire
im
ag
es.
I
n
th
e
s
ec
o
n
d
p
h
ase,
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
.
Sev
er
al
f
ilter
s
wer
e
u
s
ed
,
p
er
h
ap
s
th
e
m
o
s
t p
r
o
m
i
n
en
t o
f
wh
i
ch
is
th
e
Gab
o
r
f
ilter
,
w
h
ich
is
co
n
s
id
er
ed
a
f
ilter
to
ex
tr
ac
t
f
ea
tu
r
es f
r
o
m
th
e
v
ei
n
.
Me
c
h
a
n
is
m
s
ca
n
b
e
u
s
ed
to
r
ed
u
ce
t
h
e
d
im
e
n
s
io
n
b
etwe
en
th
e
s
et
o
f
f
ea
t
u
r
es
an
d
s
h
o
w
th
e
p
r
o
p
er
ties
b
etter
,
an
d
th
e
m
o
s
t
im
p
o
r
tan
t
o
f
th
ese
m
ec
h
an
is
m
s
ar
e
u
s
ed
p
r
in
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A
)
an
d
lin
ea
r
d
is
cr
im
in
an
t
an
aly
s
is
(
L
DA
)
.
I
n
th
e
last
s
tag
e,
th
e
m
a
tch
in
g
p
r
o
ce
s
s
tak
es
p
lace
,
u
s
in
g
E
u
clid
ea
n
d
is
tan
ce
as
a
m
in
im
u
m
d
is
tan
ce
,
wh
ich
is
o
n
e
o
f
th
e
m
o
s
t
p
r
o
m
i
n
e
n
t
m
ec
h
an
is
m
s
f
o
r
m
ea
s
u
r
in
g
s
im
ilar
ity
an
d
h
e
h
as a
ch
iev
ed
9
4
.
4
9
% a
cc
u
r
ac
y
[
1
]
.
T
h
e
r
esear
ch
e
r
in
[
6
]
wo
r
k
,
th
ey
ar
e
f
o
cu
s
in
g
o
n
v
ei
n
p
alm
r
ec
o
g
n
iti
o
n
b
ased
o
n
SUR
F
as
a
f
ea
tu
r
es
ex
tr
ac
tio
n
th
e
p
r
o
p
o
s
ed
m
o
d
e
l
was
d
o
n
e
th
r
o
u
g
h
th
r
ee
s
tag
es
to
v
er
if
y
id
en
tity
in
th
e
f
i
r
s
t
s
tag
e,
th
e
im
ag
es
wer
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
th
e
h
is
to
g
r
am
eq
u
aliza
tio
n
,
an
d
in
th
e
s
ec
o
n
d
s
tag
e,
th
e
f
ea
tu
r
es
wer
e
ex
tr
ac
ted
th
r
o
u
g
h
th
r
ee
alg
o
r
ith
m
s
s
ca
le
in
v
ar
ian
t
f
ea
tu
r
e
tr
an
s
f
o
r
m
(
SIFT
)
,
s
p
ee
d
ed
-
u
p
r
o
b
u
s
t
f
ea
tu
r
es
(
SU
R
F)
an
d
af
f
in
e
-
SIFT
(
ASI
FT)
,
an
d
in
th
e
last
s
tag
e,
th
e
E
u
clid
ea
n
d
is
tan
ce
u
s
ed
to
v
er
if
y
th
e
s
im
ilar
ity
,
wh
e
r
e
g
o
o
d
r
esu
lts
ap
p
ea
r
e
d
in
th
e
p
er
f
o
r
m
an
ce
b
etwe
en
Priv
ate
d
atab
ase
an
d
m
u
lti
-
s
p
ec
tr
u
m
d
atab
ase,
Acc
o
r
d
in
g
to
th
e
r
esu
lts
,
we
m
ay
co
n
clu
d
e
t
h
at
th
e
p
r
o
p
o
s
ed
v
ei
n
im
ag
in
g
s
y
s
tem
d
o
es
n
o
t
p
r
o
d
u
ce
s
u
s
p
icio
u
s
u
n
r
elate
d
v
ein
ar
ea
s
wh
ich
m
ig
h
t
cr
ea
te
an
o
th
er
cl
in
ical
p
r
o
b
le
m
f
o
r
t
h
e
p
atien
ts
[
6
]
.
T
h
e
r
esear
ch
e
r
in
[
7
]
wo
r
k
,
h
e
is
p
r
esen
t
th
e
s
y
s
tem
to
v
er
if
y
th
e
p
alm
v
ein
i
n
th
e
p
r
o
p
o
s
ed
wo
r
k
wh
er
e
in
th
e
f
ir
s
t
s
tag
e
a
ca
n
d
i
d
ate
Gau
s
s
ian
-
s
ec
o
n
d
ly
d
er
iv
a
tiv
e
(
GSD)
is
p
r
o
p
o
s
ed
to
im
p
r
o
v
e
th
e
v
ein
im
ag
e
an
d
th
e
n
i
n
th
e
s
ec
o
n
d
s
tag
e
w
h
ich
is
th
e
s
tag
e
o
f
e
x
tr
ac
tin
g
f
ea
t
u
r
es
th
e
Ga
b
o
r
f
ilter
is
u
s
ed
as
a
f
ilter
an
d
also
th
e
u
s
e
o
f
Fis
h
er
an
aly
s
is
to
ex
tr
ac
t th
e
ad
v
an
ta
g
es f
r
o
m
in
t
r
av
en
o
u
s
(
Gab
o
r
Fis
h
er
v
ein
f
ea
tu
r
e
(
GFVF
)
)
as it
is
u
s
ed
in
th
e
last
s
tag
e,
th
e
co
s
in
e
f
u
n
ctio
n
p
o
ck
et
c
o
m
p
l
etely
to
m
ea
s
u
r
e
th
e
s
im
ilar
ity
an
d
m
a
k
e
s
u
r
e
o
f
th
e
m
atch
i
n
g
p
r
o
ce
s
s
[
7
]
.
I
n
r
e
s
ea
r
ch
[
4
]
,
a
m
o
d
er
n
m
et
h
o
d
h
as
b
ee
n
p
r
o
p
o
s
ed
to
d
ef
in
e
th
e
id
en
tity
o
f
th
e
p
alm
v
ein
:
as
a
f
ir
s
t
s
tag
e,
th
e
p
r
ese
n
tatio
n
m
et
h
o
d
was
u
s
ed
to
im
p
r
o
v
e
th
e
im
ag
es
a
n
d
th
en
a
G
ab
o
r
f
ilter
was
u
s
ed
as
a
f
ilter
to
ex
tr
ac
t
th
e
f
ea
t
u
r
es
an
d
Fis
h
er
'
s
an
aly
s
is
d
is
cr
im
in
ated
(
FDA)
was
u
s
ed
to
r
ed
u
ce
th
e
s
p
ac
i
n
g
b
etwe
en
th
e
ch
ar
ac
ter
is
tics
o
f
t
h
e
d
ir
ec
tio
n
s
an
d
th
en
in
th
e
last
s
tag
e
it
wa
s
u
s
ed
E
u
clid
ea
n
d
is
tan
ce
to
m
ea
s
u
r
e
th
e
s
im
i
lar
ity
an
d
f
in
d
o
u
t t
h
e
r
esu
lts
[
4
]
.
3.
P
RO
P
O
SE
D
M
O
D
E
L
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
co
n
s
is
ts
o
f
f
o
u
r
p
h
ases
:
th
e
f
ir
s
t
p
h
ase
p
r
ep
r
o
ce
s
s
in
g
b
ased
o
n
ad
ap
tiv
e
h
is
to
g
r
am
eq
u
aliza
tio
n
,
in
th
e
s
ec
o
n
d
p
h
ase
f
ea
tu
r
e
ex
tr
ac
tio
n
b
ased
o
n
two
d
if
f
er
en
t
tech
n
iq
u
es
Gab
o
r
f
ilter
lin
er
an
d
2
D
-
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
,
an
d
co
m
b
in
e
th
e
f
ea
tu
r
es
to
ac
h
iev
e
a
p
r
o
m
is
in
g
r
esu
lt.
I
n
th
e
th
ir
d
p
h
ase
u
s
ed
"PC
A"
as
f
ea
tu
r
e
r
ed
u
ctio
n
,
to
s
elec
t
an
d
s
u
m
m
ar
ize
th
e
g
o
o
d
f
ea
tu
r
es
an
d
u
n
iq
u
e
f
ea
tu
r
es.
I
n
th
e
last
p
h
ase,
th
e
m
in
im
u
m
d
is
tan
ce
is
test
ed
to
f
in
d
th
e
s
im
ilar
ity
o
n
e
o
f
th
e
m
o
s
t
f
am
o
u
s
tech
n
iq
u
es
is
u
s
ed
in
th
e
p
r
o
p
o
s
e
d
m
o
d
el
is
E
u
clid
ea
n
d
is
tan
ce
.
Fig
u
r
e
1
s
h
o
ws th
e
p
r
o
p
o
s
ed
m
o
d
el
p
h
ases
.
3
.
1
.
P
re
pro
ce
s
s
ing
ba
s
ed
o
n a
da
ptiv
e
his
t
o
g
ra
m e
qu
a
liza
t
io
n
T
h
e
ad
ap
tiv
e
h
is
to
g
r
am
eq
u
at
io
n
is
u
s
ed
to
im
p
r
o
v
e
th
e
im
ag
e
an
d
e
n
h
a
n
ce
it
b
ef
o
r
e
th
e
p
h
ase
o
f
p
ar
t
o
f
p
r
ep
r
o
ce
s
s
in
g
,
b
u
t
a
f
ter
th
e
p
r
o
ce
s
s
o
f
r
ef
o
r
m
u
latin
g
an
d
u
p
d
ati
n
g
it
was
u
s
ed
o
n
a
lar
g
e
s
ca
le
[
8
]
.
T
h
e
id
ea
o
f
th
e
ad
a
p
tiv
e
h
is
to
g
r
am
eq
u
atio
n
is
s
u
m
m
ar
ized
as
f
o
llo
ws,
th
e
m
ain
i
m
ag
e
is
d
iv
id
ed
in
t
o
two
im
ag
es.
Usi
n
g
th
e
p
r
o
b
a
b
ilit
y
d
en
s
ity
f
u
n
ctio
n
,
th
e
tw
o
s
u
b
-
im
ag
es
ar
e
th
e
n
eq
u
a
li
ze
d
,
an
d
in
t
h
e
last
s
tag
e,
o
b
tain
ed
th
e
r
esu
lts
in
o
n
e
im
a
g
e
af
ter
th
e
t
wo
-
im
ag
e
eq
u
atio
n
p
r
o
ce
s
s
[
9
]
.
C
o
n
s
id
er
ed
as
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
f
e
atu
r
es
o
f
th
e
ad
ap
tiv
e
h
is
to
g
r
am
is
th
e
p
r
eser
v
atio
n
o
f
th
e
co
m
p
o
n
en
t
s
an
d
b
r
i
g
h
tn
es
s
o
f
th
e
im
ag
es,
f
o
r
d
ir
ec
t
u
s
e
[
1
0
]
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
u
s
e
d
ad
ap
tiv
e
h
is
to
g
r
a
m
eq
u
al
izatio
n
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
,
wh
ich
w
o
u
ld
im
p
r
o
v
e
th
e
im
ag
e,
as
th
e
h
is
to
g
r
am
eq
u
atio
n
is
o
n
e
o
f
t
h
e
tec
h
n
iq
u
es
d
e
v
o
ted
t
o
im
p
r
o
v
in
g
t
h
e
v
ascu
lar
ex
tr
ac
tio
n
,
an
d
t
h
is
is
wh
y
n
o
te
d
i
ts
wid
esp
r
ea
d
u
s
e
in
th
is
f
ield
[
1
1
]
,
Fig
u
r
e
2
s
h
o
ws
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
p
h
ase
r
esu
lt.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
V
ein
p
a
lm
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
fu
s
io
n
o
f fe
a
tu
r
es
(
Qa
s
s
i
m
A
b
d
A
l
-
h
u
s
s
a
in
Ha
d
i
)
2923
Fig
u
r
e
1
.
Pro
p
o
s
ed
s
y
s
tem
lay
o
u
t
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
(
a
)
O
r
ig
in
al
im
a
g
e
,
(
b
)
H
is
to
g
r
am
o
f
th
e
o
r
ig
in
al
i
m
ag
e
,
(
c)
E
n
h
a
n
ce
d
im
ag
e
,
(
d
)
H
is
to
g
r
a
m
o
f
en
h
an
ce
d
im
ag
e
3
.
2
.
F
e
a
t
ure
ex
t
r
a
ct
io
n ba
s
e
d o
n G
a
bo
r
f
ilte
r
a
nd
2
D
-
dis
cr
et
e
wa
v
elet
t
r
a
ns
f
o
rm
T
h
e
s
tag
e
o
f
f
ea
tu
r
es e
x
tr
ac
tin
g
o
f
p
alm
v
ein
p
atter
n
r
ec
o
g
n
itio
n
s
y
s
tem
is
o
n
e
o
f
th
e
m
o
s
t
im
p
o
r
tan
t
s
tag
es
d
u
e
to
its
im
p
o
r
tan
ce
in
id
en
tify
in
g
an
d
an
aly
zin
g
tis
s
u
e.
I
n
th
is
p
h
ase,
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
r
elied
o
n
th
e
Gab
o
r
f
ilter
an
d
th
e
2
D
-
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
:
3
.
2
.
1
.
G
a
bo
r
f
ilte
r
T
h
e
Gab
o
r
f
ilter
is
o
n
e
o
f
th
e
m
o
s
t
f
am
o
u
s
f
ilter
s
u
s
ed
to
ex
tr
ac
t
th
e
f
ea
tu
r
es
f
r
o
m
th
e
p
alm
v
ein
,
as
it
is
u
s
ed
to
an
aly
ze
th
e
tex
tu
r
e
an
d
esti
m
ate
th
e
co
n
tr
ast
in
th
e
v
ein
as
well
as
it
is
u
s
ed
to
an
aly
ze
th
e
tis
s
u
e,
it is
m
o
r
e
lik
ely
th
at
th
e
u
s
e
o
f
th
e
Gab
o
r
f
ilter
is
u
s
ed
in
im
ag
e
p
r
o
ce
s
s
in
g
b
ec
au
s
e
o
f
th
e
n
o
is
e
p
r
esen
t
d
u
e
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
1
8
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
292
1
-
292
7
2924
th
e
lo
w
co
n
tr
ast
o
f
th
e
im
ag
es
o
f
th
e
p
alm
v
ein
.
[
1
]
,
T
h
er
e
ar
e
s
ev
er
al
ch
ar
ac
ter
is
tics
o
f
th
e
Gab
o
r
f
ilter
.
Per
h
ap
s
th
e
m
o
s
t
p
r
o
m
in
en
t
is
th
e
tu
n
ab
le
f
ilter
p
r
ess
u
r
e
f
ilter
p
as
s
in
ad
d
itio
n
to
th
at,
it
co
n
s
is
ts
o
f
m
u
ltip
le
m
ea
s
u
r
em
en
ts
[
4
]
.
E
x
p
er
im
en
ts
h
av
e
p
r
o
v
en
th
at
Gab
o
r
f
ilter
s
ar
e
p
o
wer
f
u
l
in
d
ef
in
in
g
p
r
o
p
er
ties
,
s
o
th
ey
h
av
e
b
ee
n
u
s
ed
wid
ely
in
m
ec
h
an
ical
f
ield
s
,
to
o
b
tain
s
ig
n
if
ican
t
tex
tu
r
e
in
f
o
r
m
atio
n
[
12
]
.
T
h
r
o
u
g
h
th
e
s
tu
d
y
o
f
th
e
Gab
o
r
f
ilter
,
it
ca
n
b
e
d
iv
id
ed
in
to
two
m
ain
p
ar
ts
:
th
e
f
ir
s
t
p
ar
t
is
u
s
u
ally
ca
lled
th
e
r
ea
l
p
ar
t,
as
well
as
it
is
ca
lled
th
e
s
y
m
m
etr
ical
p
ar
t,
th
r
o
u
g
h
wh
ich
it
an
aly
ze
s
th
e
h
ills
in
its
f
o
r
m
,
an
d
th
e
o
th
er
p
ar
t
is
th
e
im
ag
in
ar
y
p
ar
t
wh
ic
h
is
u
s
u
ally
u
s
ed
f
o
r
ed
g
e
an
aly
s
is
an
d
is
also
ca
lled
th
e
s
y
m
m
etr
ic
s
tr
an
g
e
p
ar
t,
th
er
e
is
u
s
u
ally
in
Dar
k
s
p
o
ts
ca
n
u
s
e
th
e
s
y
m
m
etr
ic
p
ar
t
to
ex
tr
ac
t
f
ea
tu
r
es
f
r
o
m
th
em
[
7
]
.
A
two
-
d
im
en
s
io
n
al
Gab
o
r
f
ilter
is
a
two
-
co
m
p
o
n
en
t
co
m
b
in
ed
to
g
eth
er
r
ea
l
p
ar
t
an
d
im
ag
in
ar
y
p
ar
t.
A
co
m
p
lex
p
lan
e
wav
e
an
d
a
Gau
s
s
ian
-
s
h
ap
ed
f
u
n
ctio
n
.
As s
h
o
wn
in
(
1
)
,
(
,
)
=
(
1
2
)
e
xp
[
−
1
2
(
2
2
+
2
2
)
+
2
]
(
1
)
wh
er
e
б
x
“a
n
d
б
y
d
en
o
te
th
e
s
ca
lin
g
p
ar
am
eter
s
o
f
th
e
f
ilter
in
th
e
h
o
r
izo
n
tal
(
x
)
an
d
v
er
tical
(
y
)
d
ir
ec
tio
n
s
,
an
d
W
d
en
o
tes
th
e
ce
n
tr
al
f
r
eq
u
en
cy
o
f
th
e
f
ilter
.
T
h
e
Fo
u
r
ier
tr
an
s
f
o
r
m
o
f
th
e
Gab
o
r
f
u
n
ctio
n
g
(
x
,
y
)
”
is
d
ef
in
ed
as:
(
,
)
=
[
−
1
2
(
(
−
)
2
2
+
2
2
)
]
(
2
)
w
h
er
e
s
u
2
x
=
1
/
an
d
v
2
y
=
1/
.
T
h
e
Gab
o
r
f
ilter
h
as
two
-
p
ar
t
im
ag
in
ar
y
an
d
r
ea
l
p
ar
t.
T
h
e
im
ag
in
ar
y
p
ar
t
“o
d
d
s
y
m
m
etr
ic
”
,
Gab
o
r
f
ilter
is
u
s
ed
f
o
r
ed
g
e
d
etec
tio
n
.
T
h
e
r
ea
l
p
ar
t
“e
v
en
s
y
m
m
etr
ic”
Gab
o
r
f
ilter
is
m
o
s
tly
u
s
ed
f
o
r
d
etec
tin
g
th
e
r
id
g
e
in
th
e
im
ag
e
[
1
,
4
]
.
T
h
e
Gab
o
r
f
ilter
u
s
es
y
o
u
to
an
aly
ze
th
e
tis
s
u
e,
m
ea
n
in
g
th
at
it
an
aly
ze
s
m
ain
ly
ju
s
t
th
e
p
r
esen
ce
o
f
ce
r
tain
f
r
eq
u
en
cy
co
n
ten
t
o
f
th
e
im
ag
e,
esp
ec
ially
th
e
p
r
esen
ce
o
f
tr
en
d
s
in
th
e
p
o
in
t a
r
ea
o
r
ar
ea
o
f
an
aly
s
is
[
1
3
]
.
3
.
3
.
2
.
2D
-
dis
cr
et
e
wa
v
elet
t
r
a
ns
f
o
rm
2D
-
d
is
cr
ete
wav
el
et
tr
an
s
f
o
r
m
is
co
n
s
id
er
ed
an
im
p
o
r
tan
t
m
eth
o
d
o
f
ex
tr
ac
tin
g
f
ea
tu
r
es,
as
it
is
o
n
e
o
f
th
e
f
ilter
in
g
f
ac
to
r
s
,
an
d
it
ca
n
b
e
co
n
s
id
er
ed
th
e
m
o
s
t
p
o
p
u
lar
,
b
ec
au
s
e
o
f
its
ch
ar
ac
ter
is
tics
,
p
er
h
ap
s
th
e
m
o
s
t
p
r
o
m
in
en
t
o
f
wh
ich
is
th
e
ap
p
r
o
v
ed
tr
an
s
f
o
r
m
atio
n
o
f
im
ag
e
co
m
p
r
ess
io
n
[
14
]
.
W
av
elets
ar
e
o
f
ten
u
s
ed
to
r
ed
u
ce
2
-
D
lig
h
t
s
ig
n
als,
s
o
h
ad
n
o
ted
th
at
th
ey
ar
e
u
s
ed
in
im
ag
e
p
r
o
ce
s
s
in
g
ex
ten
s
iv
ely
to
f
ilter
o
u
t
n
o
is
e,
esp
ec
ially
wh
ite
Gau
s
s
ian
n
o
is
e
[
15
]
.
T
o
im
p
lem
en
t th
e
p
r
o
p
o
s
ed
co
m
p
r
ess
io
n
p
r
o
ce
s
s
,
a
Haa
r
wa
v
elet
o
r
Dau
b
ec
h
ies wa
v
elet
ca
n
b
e
u
s
ed
wh
er
e
a
h
ig
h
p
er
ce
n
tag
e
o
f
th
e
im
ag
e
co
m
p
r
ess
io
n
p
r
o
ce
s
s
is
ac
h
iev
ed
,
as
is
cu
s
to
m
ar
y
in
th
e
im
ag
e
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
u
s
ed
to
wr
ap
th
e
MA
T
L
AB
en
v
ir
o
n
m
en
tal
co
m
p
u
tin
g
.
As is
,
th
is
th
in
g
is
p
r
o
p
o
r
tio
n
al
to
th
e
p
ix
el
v
alu
es
o
f
th
e
s
q
u
ar
es
[
14
]
.
I
f
th
e
r
etain
ed
en
er
g
y
is
1
0
0
%,
th
is
h
ap
p
en
s
wh
en
th
e
th
r
esh
o
ld
v
alu
e
is
ze
r
o
,
an
d
th
is
m
ea
n
s
th
at
th
e
in
f
o
r
m
atio
n
h
as
n
o
t
ch
an
g
ed
.
On
th
e
co
n
tr
ar
y
,
if
th
e
v
alu
e
ch
an
g
es
an
d
th
e
en
er
g
y
is
lo
s
t,
th
is
is
k
n
o
wn
as
lo
s
s
o
f
p
r
ess
u
r
e
[
16
]
.
W
av
elet
an
aly
s
is
is
a
s
im
p
le
p
o
r
tio
n
th
at
id
en
tical
an
d
im
itativ
e
co
p
ies
o
f
th
e
o
r
ig
i
n
al
(
o
r
n
ativ
e)
w
av
elet.
On
ce
ch
ec
k
e
d
th
e
wav
e
im
ag
es,
ar
e
ca
n
ed
clea
r
ly
n
o
tice
th
e
s
ig
n
s
with
s
h
ar
p
ch
an
g
es
th
at
ca
n
b
e
b
etter
an
aly
ze
d
u
s
in
g
ir
r
eg
u
lar
wav
es
[
1
7
,
18
]
.
2D
-
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
tech
n
o
lo
g
y
is
u
s
ed
f
o
r
n
o
is
e
an
d
d
ata
co
m
p
r
ess
io
n
as
well
as
f
o
r
s
ig
n
al
an
aly
s
is
,
i
t
also
h
as
a
s
im
p
le
wav
e
s
tr
u
ctu
r
e,
wh
ich
m
ak
es
it
a
f
av
o
u
r
ite
i
n
wav
e
an
aly
s
is
,
an
d
r
ed
u
ce
d
d
ata
s
iz
e
[
19
]
.
W
h
en
u
s
in
g
d
is
cr
ete
wav
elet
tr
an
s
f
o
r
m
s
,
th
e
wav
elets
ar
e
co
n
v
er
ted
in
to
f
r
eq
u
en
cy
d
ata
an
d
d
iv
id
ed
in
to
two
b
an
d
s
:
a
lo
wer
f
r
eq
u
en
cy
b
an
d
an
d
a
h
ig
h
er
f
r
eq
u
en
cy
b
an
d
Als
o
,
th
e
wav
es
ar
e
s
im
ilar
to
th
e
wav
es with
v
ib
r
atio
n
s
th
at
h
av
e
to
o
b
s
er
v
e
wid
e
n
in
g
ar
o
u
n
d
th
e
o
r
ig
in
al
[
2
0
]
.
3
.
3
.
3
.
F
ea
t
ure
re
du
ct
io
n ba
s
ed
o
n
pri
ncipa
l c
o
m
po
nent
a
na
ly
s
is
(
P
CA
)
Prin
cip
al
co
m
p
o
n
en
t
an
aly
s
is
(
PC
A)
u
s
ed
as
a
p
o
s
t
-
ex
tr
ac
tio
n
f
ea
tu
r
e
an
aly
s
is
to
r
ed
u
ce
th
e
d
is
tan
ce
b
etwe
en
d
ata
v
alu
es,
an
d
it
is
co
n
s
id
er
ed
o
n
e
o
f
t
h
e
s
tatis
tical
an
aly
s
is
m
eth
o
d
s
[
7
]
.
T
h
is
m
eth
o
d
u
s
es
a
v
er
tical
tr
an
s
f
o
r
m
atio
n
to
co
n
v
er
t
a
s
et
o
f
d
if
f
er
en
t
n
u
m
er
ical
v
alu
es
(
th
at
ar
e
lin
ea
r
ly
r
elate
d
)
to
a
s
et
o
f
n
o
n
lin
ea
r
l
y
lin
ea
r
ly
r
elate
d
n
u
m
er
ical
v
alu
es
ca
lled
b
asic
co
m
p
o
n
en
ts
[
21
]
.
I
t
i
s
s
en
s
itiv
e
to
th
e
p
r
o
ce
s
s
o
f
ch
an
g
in
g
th
e
r
elativ
e
s
ize
o
f
th
e
b
asic
co
m
p
o
n
en
ts
.
T
h
e
tr
an
s
f
o
r
m
ed
co
r
e
co
m
p
o
n
en
ts
m
u
s
t
b
e
less
o
r
eq
u
al
to
th
e
f
ea
tu
r
es
b
ef
o
r
e
th
e
co
n
v
er
s
io
n
,
s
o
th
e
PC
A
is
a
p
r
o
ce
s
s
to
clar
if
y
th
e
f
ea
tu
r
es
m
o
r
e
b
ef
o
r
e
th
e
m
atch
in
g
p
r
o
ce
ss
[
22
]
.
Prin
c
ip
le
co
m
p
o
n
en
t
an
aly
s
is
is
u
s
ed
to
s
im
p
lify
d
ata
b
y
lin
ea
r
co
n
v
er
s
io
n
to
n
ew
d
im
en
s
io
n
s
with
a
m
ax
im
u
m
n
u
m
b
er
o
f
v
ar
iab
les
s
o
th
at
th
e
n
ew
d
im
en
s
io
n
s
co
n
s
is
t
o
f
b
asic
co
m
p
o
n
en
ts
th
at
ar
e
co
m
p
atib
le
with
th
e
r
an
g
e
o
f
s
en
s
o
r
s
[
2
3
]
.
3
.
3
.
4
.
M
ini
m
um
m
a
t
ching
b
a
s
ed
o
n
E
ucli
dea
n dis
t
a
nce
I
n
th
is
s
tag
e,
th
e
ch
ar
ac
ter
is
tics
an
d
s
im
ilar
ities
ar
e
m
ea
s
u
r
ed
.
T
h
e
u
s
e
o
f
th
e
E
u
clid
ea
n
d
is
tan
ce
is
d
u
e
to
th
e
Py
th
ag
o
r
ea
n
p
r
in
cip
le,
wh
er
e
it
in
d
icate
s
th
e
lo
ca
tio
n
o
f
two
p
o
in
ts
o
n
o
n
e
lin
e
an
d
th
e
id
en
tific
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
V
ein
p
a
lm
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
fu
s
io
n
o
f fe
a
tu
r
es
(
Qa
s
s
i
m
A
b
d
A
l
-
h
u
s
s
a
in
Ha
d
i
)
2925
o
f
o
n
e
o
f
t
h
e
p
o
in
ts
to
b
e
th
e
m
ain
p
o
in
t.
T
h
e
len
g
th
o
f
th
e
d
ir
ec
tio
n
b
etwe
en
th
e
two
p
o
in
ts
is
m
ea
s
u
r
ed
b
y
th
e
d
is
tan
ce
alo
n
e
an
d
th
r
o
u
g
h
wh
ich
th
e
o
r
ig
in
al
d
ir
ec
tio
n
will
b
e
d
eter
m
in
ed
[
24
]
.
I
n
th
is
p
r
o
p
o
s
ed
wo
r
k
,
th
e
E
u
clid
ea
n
eq
u
atio
n
is
u
s
ed
to
m
ea
s
u
r
e
th
e
s
im
ilar
ity
b
etwe
en
th
e
p
r
o
p
er
ties
o
f
th
e
im
ag
es
en
ter
ed
an
d
th
e
im
ag
es
in
th
e
d
atab
ase
[2
5
]
.
T
h
e
E
u
clid
ea
n
d
is
tan
ce
b
etwe
en
two
p
o
in
ts
,
x
1
,
an
d
x
2
,
with
j
d
im
en
s
io
n
s
,
ca
n
b
e
ca
lcu
lated
as
s
h
o
w
in
(
3
)
.
I
n
en
g
in
ee
r
in
g
co
n
ce
p
ts
,
th
e
eq
u
atio
n
ca
n
b
e
illu
s
tr
a
ted
as
a
s
tr
aig
h
t
lin
e
co
n
s
is
tin
g
o
f
two
o
ils
,
wh
er
e
k
ar
ate
co
o
r
d
in
ates
ar
e
u
s
ed
as
s
y
m
b
o
ls
o
f
th
ese
p
o
in
ts
th
r
o
u
g
h
wh
ich
th
e
s
tr
aig
h
t
lin
e
is
f
o
r
m
ed
.
_
=
√
∑
(
1
−
2
)
2
1
(
3
)
4.
E
XP
E
R
I
M
E
N
T
A
L
RE
SUL
T
AND
ANA
L
YS
I
S
I
n
th
e
p
r
o
p
o
s
ed
m
o
d
el
th
e
ex
p
er
im
en
tal
test
o
f
th
is
wo
r
k
im
p
lem
en
ted
an
d
test
ed
o
n
PUT
Vein
p
alm
d
ataset
[
1
]
,
th
e
to
tal
n
u
m
b
er
o
f
en
tire
im
ag
es
co
n
s
is
ted
o
f
1
,
2
0
0
p
ictu
r
es,
th
e
im
ag
es
wer
e
co
llected
f
r
o
m
th
e
r
ig
h
t
h
an
d
an
d
th
e
lef
t
h
an
d
f
r
o
m
5
0
v
o
lu
n
teer
s
an
d
th
e
p
ictu
r
es
wer
e
tak
en
th
r
o
u
g
h
3
s
ess
io
n
s
4
p
ictu
r
es
ea
ch
tim
e
with
at
least
o
n
e
wee
k
b
etwe
en
ea
ch
s
ess
io
n
,
th
e
ex
p
er
im
en
ts
wer
e
ca
r
r
ied
o
u
t
an
d
th
er
ef
o
r
e
to
d
eter
m
in
e
th
e
id
en
tity
o
f
th
e
u
s
er
an
d
k
n
o
win
g
th
e
au
th
o
r
ized
p
er
s
o
n
[
1
]
.
T
h
e
f
ir
s
t
ex
p
er
im
e
n
tal
r
esu
lt
o
f
th
e
d
ataset
is
a
p
r
ep
r
o
ce
s
s
in
g
b
ased
o
n
ad
ap
tiv
e
h
is
to
g
r
am
eq
u
aliza
tio
n
to
en
h
an
ce
th
e
v
is
ib
ilit
y
o
f
v
ein
u
ten
s
ils
to
d
etec
t
th
e
f
ea
tu
r
es.
Fig
u
r
e
2
s
h
o
ws
th
e
s
tep
s
o
f
en
h
an
ce
m
en
t
o
f
ea
ch
im
ag
e
with
th
eir
h
is
to
g
r
am
.
T
h
e
s
ec
o
n
d
ex
p
er
im
en
t
is
f
ea
tu
r
e
ex
tr
ac
tio
n
b
ased
o
n
th
e
f
u
s
io
n
o
f
th
e
Gab
o
r
f
ilter
an
d
2
D
d
wt
co
ef
f
icien
t
to
ex
tr
ac
t
th
e
o
p
tim
al
f
ea
tu
r
es
o
f
ea
ch
v
ein
im
ag
es,
th
e
r
aw
f
ea
tu
r
es
o
f
th
e
im
ag
es
ar
e
r
ed
u
cin
g
it
b
y
u
s
in
g
PC
A.
T
h
e
ac
cu
r
ac
y
o
f
th
e
d
ataset
b
ased
o
n
m
u
ltip
le
alg
o
r
ith
m
te
ch
n
iq
u
e
s
h
o
ws in
T
ab
le
1
.
T
h
e
t
e
s
t
i
n
g
p
h
a
s
e
w
a
s
i
m
p
l
e
m
e
n
t
e
d
o
n
d
i
f
f
e
r
e
n
t
c
a
s
e
s
a
s
s
h
o
w
n
a
b
o
v
e
,
f
o
r
b
o
t
h
e
n
h
a
n
c
e
d
l
e
f
t
a
n
d
r
i
g
h
t
-
h
a
n
d
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
e
d
b
a
s
e
d
o
n
d
i
f
f
e
r
e
n
t
t
e
c
h
n
i
q
u
e
s
.
F
i
r
s
t
i
h
a
v
e
p
r
o
p
o
s
e
d
G
a
b
o
r
c
o
e
f
f
i
c
i
e
n
t
s
a
s
f
e
a
t
u
r
e
s
s
t
a
n
d
a
l
o
n
e
a
s
t
h
e
t
a
b
l
e
s
h
o
w
s
t
h
e
a
c
c
u
r
a
c
y
w
a
s
8
5
.
5
f
o
r
a
r
i
g
h
t
h
a
n
d
a
n
d
8
4
f
o
r
l
e
f
t
.
A
s
w
e
l
l
a
s
w
h
e
n
u
s
e
d
2
D
-
D
W
T
a
s
f
e
a
t
u
r
e
s
t
h
e
a
c
c
u
r
a
c
y
w
a
s
h
i
g
h
e
r
t
h
a
n
t
h
e
f
i
r
s
t
e
x
p
e
r
i
m
e
n
t
a
l
t
e
s
t
o
n
f
e
a
t
u
r
e
s
s
e
l
e
c
t
i
o
n
a
n
d
e
x
t
r
a
c
t
i
o
n
.
T
h
e
n
t
h
e
p
r
e
v
i
o
u
s
f
e
a
t
u
r
e
s
t
e
c
h
n
i
q
u
e
s
a
r
e
t
e
s
t
e
d
w
i
t
h
P
C
A
a
s
a
f
e
a
t
u
r
e
s
r
e
d
u
c
t
i
o
n
t
h
e
p
e
r
f
o
r
m
a
n
c
e
a
c
c
u
r
a
c
y
w
a
s
a
p
r
o
m
i
s
i
n
g
a
n
d
t
h
e
h
i
g
h
e
r
a
c
c
u
r
a
c
y
w
a
s
9
6
%
,
f
i
n
a
l
l
y
,
t
h
e
f
e
a
t
u
r
e
s
b
a
s
e
d
o
n
f
u
s
i
o
n
c
o
e
f
f
i
c
i
e
n
t
o
f
b
o
t
h
f
e
a
t
u
r
e
s
e
x
t
r
a
c
t
i
o
n
t
e
c
h
n
i
q
u
e
s
w
a
s
t
h
e
h
i
g
h
e
s
t
w
i
t
h
9
6
%
a
n
d
9
6
.
2
%
f
o
r
b
o
t
h
r
i
g
h
t
a
n
d
l
e
f
t
v
e
i
n
p
a
l
m
.
T
h
e
r
e
c
e
i
v
e
r
o
p
e
r
a
t
i
n
g
c
h
a
r
a
c
t
e
r
i
s
t
i
c
(
R
O
C
)
o
f
t
h
e
f
a
l
s
e
a
c
c
e
p
t
r
a
t
e
a
n
d
f
a
l
s
e
r
e
j
e
c
t
r
a
t
e
s
h
o
w
s
t
h
e
o
p
t
i
m
a
l
t
h
r
e
s
h
o
l
d
o
f
4
.
7
o
f
t
h
e
r
e
c
o
g
n
i
t
i
o
n
.
F
i
g
u
r
e
3
a
n
d
F
i
g
u
r
e
4
s
h
o
w
s
t
h
e
R
O
C
c
u
r
v
e
f
o
r
r
i
g
h
t
a
n
d
l
e
f
t
v
e
i
n
p
a
l
m
i
m
a
g
e
s
.
T
h
e
s
u
m
m
a
r
y
o
f
c
o
m
p
a
r
i
n
g
t
h
e
a
c
c
u
r
a
c
y
t
h
a
t
a
c
h
i
e
v
e
d
b
y
t
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
,
w
i
t
h
o
t
h
e
r
t
e
c
h
n
i
q
u
e
s
,
a
s
s
h
o
w
n
i
n
T
a
b
l
e
2
.
T
h
e
p
r
o
p
o
s
e
d
m
o
d
e
l
a
c
h
i
e
v
e
s
h
i
g
h
e
r
a
c
c
u
r
a
c
y
w
h
e
n
u
s
e
d
f
u
s
i
o
n
o
f
f
e
a
t
u
r
e
s
t
h
a
n
t
h
e
r
e
f
r
e
n
c
e
[
1
]
.
T
ab
le
1
.
Acc
u
r
ac
y
r
esu
lt o
f
th
e
PUT
v
ein
D
a
t
a
s
e
t
F
e
a
t
u
r
e
s
b
a
se
d
o
n
G
a
b
o
r
F
e
a
t
u
r
e
s
b
a
se
d
o
n
w
a
v
e
l
e
t
W
a
v
e
l
e
t
+
P
C
A
G
a
b
o
r
+
P
C
A
F
u
si
o
n
o
f
G
a
b
o
r
a
n
d
w
a
v
e
l
e
t
F
u
si
o
n
o
f
G
a
b
o
r
a
n
d
w
a
v
e
l
e
t
+
P
C
A
R
i
g
h
t
p
a
l
m
I
mag
e
8
5
.
5
88
94
9
5
.
6
6
95
96
Le
f
t
p
a
l
m
I
mag
e
84
87
95
96
9
6
.
6
9
6
.
2
Fig
u
r
e
3
.
R
OC
C
u
r
v
e
f
o
r
r
ig
h
t
h
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
1
6
9
3
-
6
9
3
0
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
,
Vo
l.
1
8
,
No
.
6
,
Dec
em
b
e
r
2
0
2
0
:
292
1
-
292
7
2926
Fig
u
r
e
4
.
R
OC
C
u
r
v
e
f
o
r
lef
t
h
an
d
T
ab
le
2
.
Mo
d
el
co
m
p
ar
is
o
n
b
a
s
ed
o
n
ac
cu
r
ac
y
A
l
g
o
r
i
t
h
m
Le
f
t
h
a
n
d
R
i
g
h
t
h
a
n
d
M
.
A
b
e
d
[
1
]
96
9
5
.
6
6
P
r
o
p
o
se
d
m
o
d
e
l
9
6
.
6
96
5.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
th
e
p
r
o
p
o
s
ed
m
o
d
el
th
at
ar
e
s
u
g
g
ested
ar
e
test
ed
th
e
p
er
f
o
r
m
an
ce
b
ased
o
n
th
e
d
atab
ase,
th
e
im
ag
es
ar
e
s
elec
ted
f
r
o
m
t
h
e
I
n
s
titu
te
o
f
T
ec
h
n
o
l
o
g
y
C
o
n
tr
o
l,
Un
iv
e
r
s
ity
o
f
Po
zn
a
n
,
P
o
lan
d
,
wh
e
r
e
th
ey
test
ed
th
e
p
alm
o
f
th
e
h
a
n
d
as
a
s
y
s
tem
f
o
r
in
t
r
a
v
en
o
u
s
id
en
tific
atio
n
(
PUT)
.
T
h
e
d
atab
ase
co
n
s
is
ts
o
f
1
2
0
0
p
ictu
r
es,
h
alf
o
f
th
em
a
r
e
f
o
r
th
e
r
i
g
h
t
h
an
d
an
d
th
e
o
t
h
er
f
o
r
th
e
lef
t
h
an
d
.
W
as
d
o
n
e
in
th
r
ee
s
ess
io
n
s
f
o
u
r
p
ictu
r
es
f
o
r
ea
ch
p
er
s
o
n
,
an
d
at
least
o
n
e
wee
k
b
etwe
en
ea
ch
s
er
ies,
th
e
p
ictu
r
es
i
n
th
e
PUT
d
atab
ase
h
av
e
a
s
ize
o
f
1
2
8
0
*
9
6
0
r
eso
lu
tio
n
an
d
is
s
av
ed
as
a
2
4
-
b
it
b
itm
ap
f
ile,
in
th
is
wo
r
k
th
e
p
r
o
p
o
s
ed
m
o
d
el
h
as
u
s
e
Gab
o
r
f
ilter
an
d
wav
elet
as
a
f
u
s
io
n
f
ea
tu
r
es
b
ec
au
s
e
of
th
e
f
u
s
io
n
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
o
f
r
ec
o
g
n
itio
n
wh
e
n
we
u
s
ed
b
o
t
h
alg
o
r
ith
m
an
d
it
s
ac
h
iev
ed
9
6
.
2
% a
cc
u
r
ac
y
,
c
o
m
p
ar
in
g
with
Gab
o
r
o
r
wav
e
let.
T
h
e
tr
ain
in
g
an
d
test
in
g
co
n
tain
5
0
%
o
f
th
e
im
ag
es
in
th
e
d
ataset.
I
n
th
e
last
p
h
ase
u
s
ed
E
u
clid
ea
n
d
is
tan
ce
to
m
ea
s
u
r
e
th
e
s
im
ilar
ity
,
th
e
r
esu
lts
wer
e
g
o
o
d
an
d
i
d
en
tical
.
RE
F
E
R
E
NC
E
S
[1
]
Ab
e
d
,
M
o
h
a
m
m
e
d
Ha
m
z
a
h
,
“
Wr
ist
a
n
d
p
a
lm
v
e
in
p
a
tt
e
rn
re
c
o
g
n
it
io
n
u
sin
g
g
a
b
o
r
f
il
ter
,
”
J
o
u
rn
a
l
o
f
AL
-
Qa
d
isiya
h
fo
r c
o
mp
u
ter
sc
ien
c
e
a
n
d
ma
t
h
e
m
a
ti
c
s
,
v
o
l.
9
,
n
o
.
1
,
p
p
.
4
9
-
6
0
,
2
0
1
7
.
[2
]
P
a
n
,
M
i
,
a
n
d
Wen
x
io
n
g
Ka
n
g
,
“
P
a
lm
v
e
in
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
th
r
e
e
lo
c
a
l
in
v
a
rian
t
fe
a
tu
re
e
x
trac
ti
o
n
a
l
g
o
rit
h
m
s
,”
Ch
in
e
se
Co
n
fer
e
n
c
e
o
n
Bi
o
me
tric
Rec
o
g
n
it
io
n
,
p
p
.
1
1
6
-
1
2
4
,
2
0
1
1
.
[3
]
Tah
m
a
se
b
i,
P
e
jma
n
,
Ard
e
sh
ir
He
z
a
rk
h
a
n
i,
a
n
d
M
o
jt
a
b
a
M
o
rta
z
a
v
i
,
“
Ap
p
li
c
a
ti
o
n
o
f
d
isc
rimin
a
n
t
a
n
a
ly
sis
f
o
r
a
lt
e
ra
ti
o
n
se
p
a
ra
ti
o
n
;
su
n
g
u
n
c
o
p
p
e
r
d
e
p
o
sit,
Eas
t
Az
e
rb
a
ij
a
n
,
I
ra
n
,
”
A
u
stra
li
a
n
J
o
u
rn
a
l
o
f
Ba
s
ic
a
n
d
A
p
p
li
e
d
S
c
ien
c
e
s
,
v
o
l
.
4
,
n
o
.
4
,
5
6
4
-
5
7
6
,
2
0
1
0
.
[4
]
Al
-
ju
b
o
o
ri
,
e
t
a
l
.
,
“
P
a
lm
v
e
in
v
e
rifi
c
a
ti
o
n
u
si
n
g
G
a
b
o
r
fil
ter
,
”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
Iss
u
e
s
,
v
o
l.
1
0
,
n
o
.
1
,
2
0
1
3
.
[5
]
Ka
b
a
c
iń
sk
i,
Ra
fa
ł,
a
n
d
M
a
teu
sz
K
o
wa
lsk
i
,
“
H
u
m
a
n
v
e
i
n
p
a
tt
e
rn
c
o
r
re
latio
n
-
a
c
o
m
p
a
riso
n
o
f
se
g
m
e
n
t
a
ti
o
n
m
e
th
o
d
s
,”
Co
mp
u
ter
Rec
o
g
n
i
ti
o
n
S
y
ste
m
s
,
v
o
l.
4
,
p
p
.
5
1
-
59
,
2
0
1
1
.
[6
]
P
a
n
,
M
i
,
a
n
d
Wen
x
io
n
g
Ka
n
g
,
“
P
a
lm
v
e
in
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
th
r
e
e
lo
c
a
l
in
v
a
rian
t
fe
a
tu
re
e
x
trac
ti
o
n
a
l
g
o
rit
h
m
s.
”
Ch
in
e
se
Co
n
fer
e
n
c
e
o
n
Bi
o
me
tric
Rec
o
g
n
it
io
n
,
p
p
.
1
1
6
-
1
2
4
,
2
0
1
1
.
[7
]
Al
-
Ju
b
o
o
ri,
Al
i
M
o
h
si
n
,
Xia
n
g
q
i
a
n
Wu
,
a
n
d
Qiu
sh
i
Zh
a
o
.
“
Bio
m
e
tri
c
a
u
th
e
n
ti
c
a
ti
o
n
s
y
ste
m
b
a
se
d
o
n
p
a
lm
v
e
i
n
.
”
2
0
1
3
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Co
mp
u
ter
S
c
ien
c
e
s a
n
d
A
p
p
li
c
a
ti
o
n
s
,
p
p
.
5
2
-
58
,
2
0
1
3
.
[8
]
M
a
rti
n
e
z
,
Do
m
i
n
iq
u
e
,
“
On
li
n
e
a
d
a
p
ti
v
e
h
isto
g
ra
m
e
q
u
a
li
z
a
ti
o
n
.
”
Ne
u
ra
l
Ne
two
rk
s
f
o
r
S
ig
n
a
l
Pro
c
e
ss
in
g
VII
I.
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
9
9
8
IE
EE
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
S
o
c
iety
W
o
rk
sh
o
p
(C
a
t.
N
o
.
9
8
T
H
8
3
7
8
)
,
p
p
.
5
3
1
-
5
3
8
,
1
9
9
8
.
[9
]
Csa
p
o
d
i,
M
ά
rto
n
,
a
n
d
Tam
ά
s
Ro
sk
a
,
“
Ad
a
p
ti
v
e
h
ist
o
g
ra
m
e
q
u
a
li
z
a
ti
o
n
wit
h
c
e
ll
u
lar
n
e
u
ra
l
n
e
two
rk
s
,”
1
9
9
6
Fo
u
rt
h
IEE
E
In
ter
n
a
ti
o
n
a
l
W
o
rk
s
h
o
p
o
n
Ce
ll
u
la
r Ne
u
ra
l
Ne
tw
o
rk
s a
n
d
th
e
ir
Ap
p
li
c
a
t
io
n
s P
ro
c
e
e
d
in
g
s (CNNA
-
9
6
)
,
p
p
.
8
1
-
8
6
,
1
9
9
6
.
[1
0
]
Ra
u
t,
S
h
riram
D.,
a
n
d
Vik
a
s
T
.
Hu
m
b
e
.
“
S
tatisti
c
a
l
a
n
a
ly
sis
o
f
r
e
su
lt
in
g
p
a
lm
v
e
in
ima
g
e
t
h
ro
u
g
h
e
n
h
a
n
c
e
m
e
n
t
o
p
e
ra
ti
o
n
s
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
ti
o
n
E
n
g
in
e
e
rin
g
a
n
d
E
lec
tro
n
ic
Bu
si
n
e
ss
,
v
o
l.
5
,
n
o
.
6
,
p
p
.
47
-
5
4
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
T
E
L
KOM
NI
KA
T
elec
o
m
m
u
n
C
o
m
p
u
t E
l Co
n
tr
o
l
V
ein
p
a
lm
r
ec
o
g
n
itio
n
mo
d
el
u
s
in
g
fu
s
io
n
o
f fe
a
tu
r
es
(
Qa
s
s
i
m
A
b
d
A
l
-
h
u
s
s
a
in
Ha
d
i
)
2927
[1
1
]
S
h
a
m
su
d
e
e
n
,
F
o
u
sia
M
.
,
a
n
d
G
.
Ra
ju
.
“
A
n
o
v
e
l
e
q
u
a
li
z
a
ti
o
n
sc
h
e
m
e
fo
r
th
e
se
lec
ti
v
e
e
n
h
a
n
c
e
m
e
n
t
o
f
o
p
t
ica
l
d
isc
a
n
d
c
u
p
re
g
io
n
s
a
n
d
b
a
c
k
g
ro
u
n
d
su
p
p
re
ss
io
n
in
f
u
n
d
u
s
ima
g
e
ry
,”
T
e
l
e
c
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ter
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
n
o
.
4
,
p
p
.
1
7
1
5
-
1
7
2
2
,
2
0
1
9
.
[1
2
]
F
isc
h
e
r
M
.
,
M
.
R
y
b
n
ice
k
,
a
n
d
S
.
Tj
o
a
,
“
A
n
o
v
e
l
p
a
lm
v
e
i
n
re
c
o
g
n
it
io
n
a
p
p
r
o
a
c
h
b
a
se
d
o
n
e
n
h
a
n
c
e
d
l
o
c
a
l
G
a
b
o
r
b
in
a
ry
p
a
tt
e
rn
s
h
ist
o
g
ra
m
se
q
u
e
n
c
e
,”
2
0
1
2
1
9
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fe
re
n
c
e
o
n
S
y
ste
ms
,
S
ig
n
a
ls
a
n
d
Im
a
g
e
Pro
c
e
ss
in
g
(IW
S
S
IP)
,
p
p
.
4
2
9
-
4
3
2
,
2
0
1
2
.
[1
3
]
Na
z
a
rk
e
v
y
c
h
M
.
,
Oliarn
y
k
R.
,
Dm
y
tru
k
S
.
,
“
An
ima
g
e
s
fi
lt
ra
-
t
io
n
u
sin
g
t
h
e
Ate
b
-
G
a
b
o
r
m
e
th
o
d
,”
2
0
1
7
1
2
th
In
ter
n
a
t
io
n
a
l
S
c
ien
ti
fi
c
a
n
d
T
e
c
h
-
n
ica
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
S
c
ien
c
e
s
a
n
d
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
ies
(CS
IT
)
,
v
o
l.
1
,
p
p
.
2
0
8
-
2
1
1
,
2
0
1
7
.
[1
4
]
Wan
g
,
Li
n
g
y
u
,
a
n
d
G
ra
h
a
m
Lee
d
h
a
m
,
“
Ne
a
r
-
a
n
d
fa
r
-
in
fra
re
d
im
a
g
in
g
f
o
r
v
e
in
p
a
tt
e
r
n
b
io
m
e
tri
c
s
,”
2
0
0
6
IE
EE
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
V
id
e
o
a
n
d
S
i
g
n
a
l
B
a
se
d
S
u
rv
e
il
la
n
c
e
,
p
p
.
5
2
-
52
,
2
0
0
6
.
[
1
5
]
T
h
e
H
o
n
g
K
o
n
g
P
o
l
y
t
e
c
h
n
i
c
U
n
i
v
e
r
s
i
t
y
(
P
o
l
y
U
)
,
2
0
1
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
:
/
/
w
w
w
4
.
c
o
m
p
.
p
o
l
y
u
.
e
d
u
.
h
k
/
~
b
i
o
m
e
t
r
i
c
s
/
H
y
p
e
r
s
p
e
c
t
r
a
l
P
a
l
m
p
r
i
n
t
/
H
S
P
.
h
t
m
.
[1
6
]
G
u
p
ta,
Dip
a
lee
,
a
n
d
S
id
d
h
a
rt
h
a
Ch
o
u
b
e
y
.
"
Disc
re
te wa
v
e
let
tran
sfo
rm
fo
r
ima
g
e
p
ro
c
e
ss
in
g
, “
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Eme
rg
i
n
g
T
e
c
h
n
o
lo
g
y
a
n
d
Ad
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
3
,
pp.
5
9
8
-
602
,
2
0
1
5
.
[
1
7
]
S
i
n
g
h
,
P
r
i
y
a
n
k
a
,
P
r
i
t
i
S
i
n
g
h
,
a
n
d
R
a
k
e
s
h
K
u
m
a
r
S
h
a
r
m
a
,
“
J
P
E
G
i
m
a
g
e
c
o
m
p
r
e
s
s
i
o
n
b
a
s
e
d
o
n
b
i
o
r
t
h
o
g
o
n
a
l
,
c
o
i
f
l
e
t
s
a
n
d
d
a
u
b
e
c
h
i
e
s
w
a
v
e
l
e
t
f
a
m
i
l
i
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
-
7
,
2
0
1
1
.
[1
8
]
Ab
e
d
,
M
o
h
a
m
m
e
d
Ha
m
z
a
h
,
“
Iris
re
c
o
g
n
it
i
o
n
m
o
d
e
l
b
a
se
d
o
n
P
ri
n
c
ip
a
l
Co
m
p
o
n
e
n
t
a
n
a
ly
sis
a
n
d
2
lev
e
l
Ha
a
r
wa
v
e
let
tran
sfo
rm
:
Ca
se
st
u
d
y
CUH
K
a
n
d
UTIRIS
iri
s
d
a
ta
b
a
se
s
,
”
J
o
u
rn
a
l
o
f
Co
ll
e
g
e
o
f
E
d
u
c
a
ti
o
n
/W
a
sit
,
v
o
l.
1
,
n
o
.
2
7
,
pp.
4
8
5
-
500
,
2
0
1
7
.
[1
9
]
M
.
S
c
h
imm
a
c
k
,
S
.
Ng
u
y
e
n
,
P
.
M
e
rc
o
re
l
li
,
“
Im
p
lem
e
n
ted
wa
v
e
let
p
a
c
k
e
t
tree
b
a
se
d
d
e
n
o
isin
g
a
lg
o
rit
h
m
in
b
u
s
si
g
n
a
ls
o
f
a
we
a
ra
b
le se
n
so
ra
rra
y
,”
J
o
u
rn
a
l
o
f
Ph
y
sic
s
-
Co
n
fer
e
n
c
e
S
e
rie
s
,
v
o
l.
6
5
9
,
n
o
.
1
,
p
p
.
1
2
-
21
,
2
0
1
5
.
[2
0
]
Altah
e
r,
Am
m
a
r
Wi
sa
m
,
a
n
d
S
a
b
a
h
Kh
u
d
h
a
ir
A
b
b
a
s
,
“
Im
a
g
e
p
ro
c
e
ss
in
g
a
n
a
ly
sis
o
f
si
g
m
o
id
a
l
Ha
d
a
m
a
rd
wa
v
e
let
with
P
CA
t
o
d
e
tec
t
h
id
d
e
n
o
b
jec
t
,
”
T
EL
KOM
NIK
A
T
e
l
e
c
o
mm
u
n
ica
ti
o
n
Co
m
p
u
t
in
g
El
e
c
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l.
1
8
,
n
o
.
3
,
p
p
.
1
2
1
6
-
1
2
2
3
,
2
0
2
0
.
[2
1
]
Aliza
d
e
h
,
e
t
a
l.
,
“
Distin
c
t
t
y
p
e
s
o
f
d
iff
u
se
larg
e
B
-
c
e
ll
l
y
m
p
h
o
m
a
i
d
e
n
ti
fied
b
y
g
e
n
e
e
x
p
re
ss
io
n
p
ro
f
il
in
g
,
”
Na
t
u
re
,
v
o
l.
4
0
3
,
n
o
.
6
7
6
9
,
p
p
.
5
0
3
-
5
1
1
,
2
0
0
0
.
[2
2
]
Ib
ra
h
im,
e
t
a
l.
,
“
A
fil
ter
b
a
n
k
b
a
se
d
a
p
p
ro
a
c
h
fo
r
ro
tati
o
n
i
n
v
a
r
ian
t
fin
g
e
r
p
rin
t
re
c
o
g
n
i
ti
o
n
,
”
J
o
u
rn
a
l
o
f
S
i
g
n
a
l
Pro
c
e
ss
in
g
S
y
ste
ms
,
v
o
l.
6
8
,
n
o
.
3
,
p
p
.
4
0
1
-
4
1
4
,
2
0
1
2
.
[2
3
]
S
u
d
a
rm
a
ji
,
e
t
a
l
.
,
“
Th
e
a
p
p
li
c
a
ti
o
n
o
f
g
e
n
e
ra
l
M
OS
g
a
s
se
n
so
rs
fo
r
d
isc
rimin
a
ti
n
g
fo
r
m
a
li
n
c
o
n
ten
t
,
”
T
e
l
e
c
o
mm
u
n
ica
ti
o
n
,
Co
m
p
u
ter
,
E
lec
tro
n
ics
a
n
d
C
o
n
tr
o
l
,
v
o
l
.
1
6
,
n
o
.
6
,
p
p
.
2
9
0
5
-
2
9
1
2
,
De
c
e
m
b
e
r
2
0
1
8
.
[2
4
]
D
i
n
g
,
C
h
r
i
s
,
a
n
d
X
i
a
o
f
e
n
g
H
e
,
“
K
-
m
e
a
n
s
c
l
u
s
t
e
r
i
n
g
v
i
a
p
r
i
n
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
s
i
s
,”
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
T
w
e
n
t
y
-
f
i
rs
t
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
M
a
c
h
in
e
L
e
a
rn
i
n
g
,
2
0
0
4
.
[2
5
]
Al
-
Ju
b
o
o
ri,
e
t
a
l
.
,
“
P
a
lm
v
e
in
v
e
rifi
c
a
ti
o
n
u
sin
g
m
u
lt
ip
le fea
tu
re
s
a
n
d
lo
c
a
li
ty
p
re
se
rv
in
g
p
ro
jec
ti
o
n
,
”
T
h
e
S
c
ien
ti
fi
c
W
o
rld
J
o
u
rn
a
l
,
v
o
l.
2
0
1
4
,
n
o
.
1
,
2
0
1
4
.
Evaluation Warning : The document was created with Spire.PDF for Python.