I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d
Science
s
(
I
J
AAS)
Vo
l.
6
,
No
.
2
,
J
u
n
y
2017
,
p
p
.
98
~
105
I
SS
N:
2252
-
8814
98
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AAS
Writer
Ident
ity R
ecog
nition a
nd C
o
nfir
m
a
tion Usin
g
P
ersia
n
H
a
ndw
ritt
en Tex
ts
Aida
Sh
ei
kh
1
,
H
a
s
s
a
n K
ho
t
a
nlo
u
2
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter,
Qa
z
v
i
n
Bra
n
c
h
,
Isla
m
i
c
A
z
a
d
Un
iv
e
rsity
,
Qa
z
v
in
,
Ira
n
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter,
Bu
-
A
li
S
in
a
U
n
iv
e
rsity
,
Ha
m
e
d
a
n
,
Ira
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
6
,
2
0
1
7
R
ev
i
s
ed
Ma
y
1
2
,
2
0
1
7
A
cc
ep
ted
Ma
y
1
9
,
2
0
1
7
T
h
e
re
a
re
m
a
n
y
w
a
y
s to
re
c
o
g
n
ize
th
e
id
e
n
t
it
y
o
f
in
d
iv
id
u
a
ls
a
n
d
a
u
th
e
n
ti
c
a
te
th
e
m
a
n
d
th
e
m
o
d
e
rn
w
o
rld
stil
l
is
lo
o
k
in
g
f
o
r
u
n
iq
u
e
b
i
o
m
e
tri
c
fe
a
tu
re
s
o
f
h
u
m
a
n
s.
T
h
e
re
c
o
g
n
it
io
n
a
n
d
a
u
t
h
e
n
ti
c
a
ti
o
n
o
f
in
d
iv
i
d
u
a
ls
w
it
h
t
h
e
h
e
lp
o
f
th
e
ir
h
a
n
d
w
rit
in
g
is
re
g
a
rd
e
d
a
s
a
re
s
e
a
rc
h
to
p
ic
in
re
c
e
n
t
y
e
a
rs.
I
t
is
w
id
e
l
y
u
se
d
in
th
e
f
ield
o
f
se
c
u
rit
y
,
le
g
a
l,
a
c
c
e
ss
c
o
n
tro
l
to
sy
ste
m
s
a
n
d
f
in
a
n
c
ial
a
c
ti
v
it
ies
.
T
h
is
th
e
sis
tri
e
s
to
e
x
a
m
in
e
s
th
e
id
e
n
ti
f
ica
ti
o
n
a
n
d
a
u
th
e
n
ti
c
a
ti
o
n
o
f
in
d
iv
id
u
a
ls
in
P
e
rsia
n
(F
a
rsi)
h
a
n
d
w
rit
ten
tex
ts
so
th
a
t
th
e
id
e
n
ti
ty
o
f
th
e
a
u
th
o
r
c
a
n
b
e
d
e
term
in
e
d
w
it
h
a
h
a
n
d
w
rit
ten
tex
t,
a
n
d
in
th
e
a
u
t
h
e
n
ti
c
a
ti
o
n
p
ro
b
lem
,
w
it
h
h
a
v
in
g
t
w
o
h
a
n
d
w
rit
ten
tex
ts,
it
is
d
e
ter
m
in
e
d
th
a
t
w
h
e
th
e
r
b
o
t
h
m
a
n
u
sc
rip
ts
b
e
lo
n
g
to
a
sp
e
c
if
ic
p
e
rso
n
o
r
n
o
t.
T
h
e
p
ro
p
o
se
d
s
y
ste
m
f
o
r
re
c
o
g
n
izin
g
th
e
id
e
n
ti
ty
o
f
th
e
a
u
th
o
r
in
t
h
is
stu
d
y
c
a
n
b
e
d
iv
id
e
d
in
t
o
tw
o
m
a
in
p
a
rts:
o
n
e
p
a
rt
is
in
ten
d
e
d
f
o
r
train
in
g
a
n
d
th
e
o
t
h
e
r
f
o
r
tes
ti
n
g
.
T
o
a
ss
e
ss
th
e
p
e
r
f
o
r
m
a
n
c
e
o
f
in
tro
d
u
c
e
d
c
h
a
ra
c
teristics
,
th
e
Hid
d
e
n
M
a
rk
o
v
M
o
d
e
l
(HM
M
)
is
u
se
d
a
s
th
e
c
l
a
ss
if
i
e
r;
th
u
s,
a
m
o
d
e
l
is
d
e
f
in
e
d
f
o
r
e
a
c
h
a
n
g
u
lar
c
h
a
ra
c
teristic.
T
h
e
d
e
f
in
e
d
a
n
g
u
lar
m
o
d
e
ls
a
re
c
o
n
n
e
c
ted
b
y
a
sp
e
c
if
ic
c
h
a
in
n
e
tw
o
rk
to
f
o
rm
a
c
o
m
p
re
h
e
n
siv
e
d
a
tab
a
se
f
o
r
c
las
sif
ica
ti
o
n
.
T
h
is
d
a
tab
a
se
is
th
e
n
u
se
d
t
o
d
e
te
rm
in
e
a
n
d
a
u
th
e
n
t
ica
te t
h
e
a
u
t
h
o
r.
K
ey
w
o
r
d
:
First k
e
y
w
o
r
d
Seco
n
d
k
e
y
w
o
r
d
T
h
ir
d
k
ey
w
o
r
d
Fo
u
r
th
k
e
y
w
o
r
d
Fif
t
h
k
e
y
w
o
r
d
Co
p
y
rig
h
t
©
201
7
In
s
t
it
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
A
id
a
S
h
ei
k
h
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
,
Qaz
v
in
B
r
an
c
h
,
I
s
la
m
ic
A
za
d
U
n
iv
er
s
it
y
,
Qaz
v
in
,
I
r
an
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
is
er
a,
s
ec
u
r
it
y
an
d
in
f
o
r
m
atio
n
p
r
o
tectio
n
is
co
n
s
id
e
r
ed
a
b
ig
ch
allen
g
e
o
f
h
u
m
a
n
it
y
i
n
th
e
m
o
d
er
n
w
o
r
ld
.
I
d
en
ti
f
y
in
g
w
r
i
ter
s
f
r
o
m
t
h
eir
h
a
n
d
w
r
it
in
g
h
a
s
r
ec
en
t
l
y
b
ec
o
m
e
a
co
n
s
id
er
a
b
le
an
d
i
n
ter
esti
n
g
s
u
b
j
ec
t
in
id
en
ti
t
y
r
ec
o
g
n
itio
n
.
Am
o
n
g
b
eh
a
v
io
r
al
f
ea
tu
r
es,
h
an
d
w
r
iti
n
g
i
s
ea
s
il
y
ac
h
iev
e
d
an
d
s
t
u
d
ies
s
h
o
w
th
at
d
i
f
f
er
en
t
i
n
d
iv
id
u
als
h
a
v
e
d
if
f
er
en
t
h
an
d
w
r
iti
n
g
s
[
1
,
2
]
.
T
h
er
ef
o
r
e,
id
en
tify
i
n
g
a
n
d
co
n
f
ir
m
in
g
th
e
id
en
t
it
y
o
f
in
d
i
v
id
u
al
s
u
s
i
n
g
t
h
eir
h
a
n
d
w
r
iti
n
g
h
a
s
b
ee
n
a
r
esear
ch
f
o
cu
s
i
n
r
ec
en
t
y
ea
r
s
a
n
d
its
m
aj
o
r
ap
p
licatio
n
is
in
s
ec
u
r
it
y
a
n
d
leg
al
i
s
s
u
es,
co
n
tr
o
llin
g
s
y
s
te
m
s
ac
ce
s
s
,
an
d
f
in
a
n
cial
ac
tiv
ities
.
T
h
e
id
en
tit
y
r
ec
o
g
n
itio
n
p
r
o
b
lem
ai
m
s
to
s
p
ec
if
y
t
h
e
id
en
tit
y
o
f
th
e
w
r
iter
,
g
i
v
en
a
h
an
d
w
r
itte
n
tex
t
an
d
t
h
e
id
en
tit
y
co
n
f
ir
m
atio
n
p
r
o
b
lem
ai
m
s
to
s
p
ec
if
y
w
h
et
h
er
t
w
o
g
iv
e
n
h
a
n
d
w
r
itte
n
tex
ts
h
a
v
e
b
ee
n
w
r
it
ten
b
y
o
n
e
i
n
d
iv
id
u
al.
Gen
er
al
l
y
,
g
r
ap
h
o
lo
g
y
e
x
p
er
ts
an
al
y
ze
an
d
in
v
e
s
ti
g
ate
h
a
n
d
w
r
itte
n
tex
ts
.
A
lt
h
o
u
g
h
h
u
m
a
n
in
ter
v
en
tio
n
in
s
o
lv
in
g
th
i
s
p
r
o
b
lem
is
a
n
ef
f
ec
ti
v
e
ap
p
r
o
ac
h
,
it is
co
s
tl
y
an
d
tiri
n
g
d
u
e
t
o
th
e
n
at
u
r
e
o
f
h
u
m
an
b
ei
n
g
s
.
Mo
s
t
co
n
d
u
cted
s
tu
d
ies
i
n
w
r
iter
id
en
tit
y
r
ec
o
g
n
itio
n
a
n
d
co
n
f
ir
m
atio
n
h
av
e
b
ee
n
o
f
f
li
n
e
an
d
s
ig
n
at
u
r
e
-
b
ased
o
n
li
n
e
m
et
h
o
d
s
ar
e
m
o
r
e
co
m
m
o
n
i
n
id
en
tit
y
r
ec
o
g
n
itio
n
.
Mo
s
t
s
tu
d
ies
in
id
en
t
it
y
r
ec
o
g
n
itio
n
f
o
cu
s
o
n
t
h
e
E
n
g
lis
h
la
n
g
u
a
g
e
a
n
d
th
er
e
h
a
s
b
ee
n
f
e
w
s
tu
d
ies
r
e
g
ar
d
in
g
A
r
ab
ic
an
d
P
er
s
ia
n
h
an
d
w
r
itte
n
tex
ts
in
co
m
p
ar
is
o
n
to
t
h
e
E
n
g
lis
h
lan
g
u
ag
e.
A
cc
o
r
d
in
g
l
y
,
t
h
is
p
ap
er
b
r
ief
l
y
s
tu
d
ie
s
t
h
e
w
id
el
y
u
s
ed
m
et
h
o
d
s
i
n
L
ati
n
a
n
d
P
er
s
ian
tex
ts
a
n
d
co
m
p
ar
es
th
ese
m
e
th
o
d
s
a
n
d
ap
p
licati
o
n
f
o
r
t
h
e
P
er
s
ia
n
lan
g
u
a
g
e.
Fin
al
l
y
,
an
o
n
l
in
e
m
eth
o
d
is
in
tr
o
d
u
ce
d
an
d
p
r
ese
n
ted
f
o
r
id
en
tit
y
r
ec
o
g
n
itio
n
a
n
d
co
n
f
ir
m
atio
n
f
o
r
P
er
s
ian
tex
t
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Wr
ite
r
I
d
en
tity R
ec
o
g
n
itio
n
a
n
d
C
o
n
fir
ma
tio
n
Usi
n
g
P
ers
ia
n
Ha
n
d
w
r
itten
Texts
(
A
id
a
S
h
ei
kh
)
99
2.
P
RE
VIOU
S WO
RK
S
R
ev
ie
w
in
g
co
n
d
u
cted
s
t
u
d
ies
an
d
p
ap
er
s
s
h
o
w
s
t
h
at
t
h
e
y
m
o
s
tl
y
i
n
v
e
s
ti
g
ate
w
r
it
er
id
en
tit
y
r
ec
o
g
n
itio
n
b
as
ed
o
n
h
a
n
d
w
r
i
tten
te
x
ts
a
n
d
a
li
m
ited
n
u
m
b
er
o
f
m
et
h
o
d
s
ar
e
in
tr
o
d
u
ce
d
f
o
r
d
eter
m
in
in
g
a
n
d
co
n
f
ir
m
i
n
g
id
e
n
tit
y
.
T
h
is
m
a
y
b
e
b
ec
au
s
e
in
tr
o
d
u
ci
n
g
an
e
f
f
icie
n
t
s
o
l
u
tio
n
f
o
r
id
en
ti
t
y
r
e
co
g
n
itio
n
ca
n
a
ls
o
in
cl
u
d
e
a
r
eliab
le
a
p
p
r
o
ac
h
f
o
r
id
en
tit
y
co
n
f
ir
m
at
io
n
.
I
n
w
h
at
f
o
llo
w
s
,
th
e
m
o
s
t
i
m
p
o
r
tan
t
p
r
o
p
o
s
ed
m
eth
o
d
s
ar
e
in
tr
o
d
u
ce
d
in
th
e
d
o
m
ai
n
o
f
h
a
n
d
w
r
iti
n
g
r
ec
o
g
n
itio
n
.
Ho
r
izo
n
tal
an
d
v
er
tical
v
ie
ws
h
a
v
e
b
ee
n
w
id
el
y
u
s
ed
i
n
id
en
tify
i
n
g
E
n
g
lis
h
an
d
P
er
s
ian
te
x
ts
.
A
cc
o
r
d
in
g
l
y
,
Z
o
is
et
al.
[
3
]
p
r
o
p
o
s
e
a
tex
t
d
ep
en
d
en
t
m
et
h
o
d
f
o
r
i
d
en
tit
y
r
ec
o
g
n
itio
n
.
I
n
th
i
s
m
et
h
o
d
,
th
e
v
er
tical
v
ie
w
h
is
to
g
r
a
m
o
f
a
w
o
r
d
`
s
i
m
ag
e
is
p
r
o
ce
s
s
ed
an
d
th
e
co
n
s
id
er
ed
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
u
s
in
g
m
o
r
p
h
o
lo
g
y
o
p
er
ato
r
s
.
B
en
s
i
f
a
et
al.
[
4
]
in
v
esti
g
ate
id
en
tit
y
r
ec
o
g
n
itio
n
i
n
f
o
r
m
o
f
a
tex
t
-
b
ased
in
f
o
r
m
atio
n
r
etr
iev
al
p
r
o
b
lem
.
I
n
t
h
i
s
m
eth
o
d
,
f
ea
t
u
r
es
ar
e
r
etr
iev
ed
b
ased
o
n
th
e
t
y
p
e
o
f
th
e
u
s
ed
d
ata
a
n
d
t
h
u
s
,
t
h
is
m
et
h
o
d
is
ea
s
il
y
g
e
n
er
alize
d
to
o
th
er
lan
g
u
a
g
es,
i
n
cl
u
d
in
g
A
r
ab
ic,
P
er
s
ian
,
etc.
R
ef
er
e
n
ce
[
5
]
p
r
o
p
o
s
es
a
m
eth
o
d
f
o
r
id
en
ti
t
y
r
ec
o
g
n
itio
n
an
d
co
n
f
ir
m
atio
n
,
w
h
ich
i
s
b
ased
o
n
Ma
r
k
o
v
`
s
h
id
d
en
m
o
d
el.
I
n
th
is
m
o
d
el,
f
o
r
ea
ch
w
r
it
er
,
an
HM
M
m
o
d
el
is
co
n
s
id
er
ed
an
d
ea
ch
co
r
r
esp
o
n
d
in
g
m
o
d
el
i
s
tr
ain
ed
u
s
i
n
g
s
a
m
p
le
s
o
f
t
h
e
w
r
it
er
`
s
h
an
d
w
r
iti
n
g
.
T
h
er
ef
o
r
e,
ea
ch
HM
M
m
o
d
el
w
o
r
k
s
as a
n
e
x
p
er
t,
w
h
o
is
ab
l
e
to
r
ec
o
g
n
ize
th
e
h
an
d
w
r
iti
n
g
o
f
a
ce
r
tain
in
d
i
v
id
u
al.
R
ef
er
e
n
ce
[
6
]
in
tr
o
d
u
ce
s
a
m
eth
o
d
f
o
r
w
r
iter
id
en
tit
y
r
ec
o
g
n
i
tio
n
t
h
at
ex
tr
ac
t
s
f
ea
t
u
r
es
f
r
o
m
t
h
e
i
m
a
g
e
o
f
t
h
e
h
a
n
d
w
r
itte
n
tex
t
u
s
i
n
g
ed
g
es
i
n
f
o
r
m
atio
n
.
T
h
e
in
tr
o
d
u
ce
d
f
ea
t
u
r
es
i
n
d
icate
d
ir
ec
tio
n
ch
an
g
e
s
d
u
r
in
g
t
h
e
w
r
iti
n
g
p
r
o
ce
s
s
.
I
n
f
ac
t,
t
h
e
m
ain
n
o
tio
n
o
f
t
h
i
s
m
et
h
o
d
is
t
h
at
t
h
e
w
r
iti
n
g
p
r
o
ce
s
s
co
n
s
tit
u
tes
o
f
a
s
et
o
f
p
en
h
its
a
n
d
th
e
s
p
ec
i
f
ic
atio
n
s
o
f
t
h
i
s
p
r
o
ce
s
s
ca
n
b
e
ac
h
iev
ed
b
y
e
x
tr
ac
ti
n
g
t
h
e
ed
g
e
s
in
f
o
r
m
atio
n
.
I
n
a
p
ap
er
b
y
au
t
h
o
r
[
7
]
,
a
n
e
w
m
e
th
o
d
i
s
p
r
o
p
o
s
ed
f
o
r
f
ea
t
u
r
e
e
x
tr
ac
tio
n
f
r
o
m
h
an
d
w
r
iti
n
g
s
.
O
n
e
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
is
t
h
e
n
f
ea
tu
r
e
e
x
tr
ac
tio
n
m
et
h
o
d
th
at
ex
tr
ac
ts
f
ea
tu
r
e
s
in
d
icat
in
g
s
tr
ai
g
h
t
li
n
es
a
n
d
cu
r
v
e
s
u
s
ed
i
n
h
a
n
d
w
r
iti
n
g
s
.
T
h
e
af
o
r
em
e
n
tio
n
ed
m
et
h
o
d
s
ar
e
th
e
b
asic
p
r
o
p
o
s
e
alg
o
r
ith
m
s
i
n
h
a
n
d
w
r
iti
n
g
r
ec
o
g
n
itio
n
.
T
ab
le
1
b
r
ief
l
y
p
r
esen
ts
s
o
m
e
o
f
t
h
e
wr
iter
id
en
tit
y
r
ec
o
g
n
itio
n
p
ap
er
s
u
s
in
g
d
if
f
er
en
t a
lg
o
r
it
h
m
s
.
T
a
b
e
1
:
W
r
i
te
r
I
d
en
ti
ty
R
ec
o
g
n
iti
o
n
P
a
p
er
s
Usi
n
g
Dif
f
er
en
t A
lg
o
r
ith
m
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l
.
6
,
No
.
2
,
J
u
n
y
201
7
:
98
–
1
0
5
100
3.
T
H
E
S
T
RUC
T
UR
E
O
F
T
H
E
RE
CO
G
N
I
T
I
O
N
SYS
T
E
M
Han
d
w
r
iti
n
g
as
a
b
eh
a
v
io
r
al
f
ea
t
u
r
e
is
v
er
y
d
ep
en
d
en
t
o
n
b
r
ain
p
er
f
o
r
m
a
n
ce
a
n
d
it
is
a
f
f
ec
ted
b
y
s
ev
er
al
co
m
p
lex
f
ac
to
r
s
,
li
k
e
t
r
ain
in
g
,
p
h
y
s
ical
s
tat
u
s
,
en
v
ir
o
n
m
e
n
tal
an
d
m
e
n
tal
co
n
d
itio
n
s
o
f
th
e
i
n
d
iv
id
u
al.
T
h
er
ef
o
r
e,
in
w
r
i
ter
id
en
tit
y
r
ec
o
g
n
itio
n
,
f
ea
t
u
r
es
s
h
o
u
ld
b
e
d
is
cu
s
s
ed
th
a
t
in
d
icate
th
e
d
i
f
f
er
en
ce
s
b
et
w
ee
n
d
if
f
er
e
n
t
h
a
n
d
w
r
iti
n
g
s
.
I
n
ad
d
itio
n
,
A
r
ab
ic
an
d
P
er
s
ian
h
an
d
w
r
i
tin
g
s
h
av
e
s
e
v
er
al
d
if
f
er
en
ce
s
f
r
o
m
L
ati
n
h
an
d
w
r
iti
n
g
.
P
er
s
ian
an
d
A
r
ab
ic
h
an
d
w
r
itin
g
s
ar
e
in
h
er
e
n
tl
y
co
n
ti
n
u
o
u
s
an
d
o
v
er
h
ea
d
s
an
d
u
n
d
er
lin
e
s
p
r
ev
en
t t
h
e
ap
p
licatio
n
o
f
m
et
h
o
d
s
th
a
t r
eq
u
ir
e
f
u
ll se
g
m
en
t
atio
n
.
T
h
e
s
h
ap
es o
f
P
er
s
ia
n
a
n
d
A
r
ab
ic
alp
h
ab
ets
ar
e
a
f
u
n
ctio
n
o
f
t
h
eir
lo
ca
tio
n
i
n
th
e
w
o
r
d
an
d
t
h
er
e
m
a
y
b
e
d
if
f
er
en
t
f
o
r
m
s
o
f
ea
ch
al
p
h
ab
et
in
d
i
f
f
er
e
n
t
lo
ca
tio
n
s
,
in
cl
u
d
in
g
th
e
b
eg
i
n
n
in
g
,
m
id
d
le,
an
d
en
d
in
g
o
f
t
h
e
w
o
r
d
o
r
as
a
s
ep
ar
ate
alp
h
ab
et.
So
m
e
P
er
s
ian
alp
h
ab
ets
h
av
e
o
n
e,
t
w
o
,
o
r
th
r
ee
d
o
ts
ab
o
v
e
o
r
b
elo
w
t
h
e
m
.
P
er
s
ian
a
n
d
A
r
ab
ic
h
a
n
d
w
r
iti
n
g
s
h
a
v
e
m
an
y
p
r
in
t f
o
n
t
s
an
d
h
an
d
w
r
iti
n
g
s
t
y
les.
3
.
1
.
T
he
P
ro
po
s
ed
Alg
o
rit
h
m
Sin
ce
o
u
r
g
o
al
is
to
p
r
o
p
o
s
e
an
a
u
to
m
atic
w
r
i
ter
id
en
t
it
y
r
ec
o
g
n
it
io
n
m
et
h
o
d
an
d
t
h
e
r
e
ar
e
n
o
co
n
s
tr
ain
ts
i
n
t
h
e
co
n
s
id
er
e
d
h
an
d
w
r
iti
n
g
s
,
w
e
ca
n
n
o
t
u
s
e
m
et
h
o
d
s
t
h
at
r
eq
u
ir
e
au
to
m
at
ic
an
d
f
u
ll
s
eg
m
e
n
tatio
n
o
f
tex
t
in
to
w
o
r
d
s
an
d
alp
h
ab
ets.
T
h
e
g
e
n
er
al
s
tr
u
c
tu
r
e
o
f
t
h
is
m
eth
o
d
i
n
clu
d
es
f
o
u
r
s
ta
g
es:
co
llectin
g
t
h
e
h
a
n
d
w
r
iti
n
g
s
a
m
p
les,
p
r
ep
r
o
ce
s
s
in
g
a
n
d
cr
ea
te
th
e
b
i
n
ar
y
i
m
a
g
e,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
w
r
i
ter
id
en
tit
y
r
ec
o
g
n
it
io
n
o
r
co
n
f
ir
m
atio
n
u
s
i
n
g
p
atter
n
r
ec
o
g
n
iti
o
n
m
et
h
o
d
s
.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
co
n
s
id
er
ed
th
e
h
an
d
w
r
itte
n
te
x
t
as
a
n
i
m
ag
e.
T
h
is
m
et
h
o
d
is
ev
al
u
ated
u
s
i
n
g
t
h
e
h
an
d
w
r
iti
n
g
s
o
f
7
0
in
d
iv
id
u
al
s
an
d
r
es
u
lt
s
in
d
icate
th
a
t th
e
p
r
o
p
o
s
ed
m
et
h
o
d
is
h
i
g
h
l
y
e
f
f
icie
n
t f
o
r
P
er
s
ian
h
a
n
d
w
r
itte
n
tex
ts
.
3
.
1
.
1
.
Sa
m
ple C
o
llect
io
n
I
n
o
r
d
er
to
ev
alu
ate
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
t
h
e
o
th
er
i
n
v
e
s
tig
a
ted
ap
p
r
o
ac
h
es,
7
0
in
d
iv
i
d
u
als
w
i
t
h
d
if
f
er
e
n
t
ed
u
ca
t
io
n
,
ag
e,
a
n
d
g
en
d
er
w
er
e
as
k
ed
to
f
ill
th
e
d
esig
n
ed
f
o
r
m
s
w
it
h
t
h
eir
n
o
r
m
al
h
a
n
d
w
r
i
tin
g
.
T
h
ese
in
d
iv
id
u
als
w
er
e
s
elec
t
in
g
f
r
o
m
o
r
d
in
ar
y
p
eo
p
le.
Fo
r
ev
alu
atio
n
,
th
e
i
n
d
iv
id
u
als
w
er
e
as
k
ed
to
w
r
it
e
t
w
o
d
eter
m
i
n
ed
tex
ts
,
w
h
ic
h
ar
e
in
o
n
e
p
ar
ag
r
ap
h
a
n
d
i
n
clu
d
e
v
ar
io
u
s
w
o
r
d
s
.
T
h
e
d
eter
m
i
n
ed
tex
ts
ar
e
p
r
esen
ted
in
f
ig
u
r
e
1
an
d
2
.
Fig
u
r
e
1
.
T
h
e
I
m
ag
e
o
f
th
e
F
ir
s
t H
an
d
w
r
itte
n
T
ex
t
T
h
e
f
o
r
m
s
d
o
n
o
t
h
av
e
lin
e
s
;
h
o
w
ev
er
,
th
e
i
n
d
iv
id
u
als
w
er
e
ask
ed
to
w
r
ite
alo
n
g
s
tr
aig
h
t
h
o
r
izo
n
tal
lin
es.
No
n
e
th
ele
s
s
,
it
w
as
o
b
s
er
v
ed
w
as
s
o
m
e
f
o
r
m
s
h
ad
til
ted
lin
es;
in
m
o
s
t
f
o
r
m
s
,
h
o
wev
er
,
th
e
lin
e
s
w
er
e
al
m
o
s
t
a
lig
n
a
s
tr
ai
g
h
t
li
n
e.
Af
ter
co
llecti
n
g
t
h
e
f
o
r
m
s
,
al
l
w
er
e
s
ca
n
n
ed
as
g
r
a
y
s
ca
le
i
m
ag
es
w
i
th
r
eso
lu
tio
n
300d
p
i.
3
.
1
.
2
.
P
re
pro
ce
s
s
ing
a
nd
cr
ea
t
e
bi
na
ry
i
m
a
g
es
I
n
o
r
d
er
to
p
r
o
p
o
s
e
an
ef
f
icie
n
t
m
et
h
o
d
f
o
r
w
r
iter
id
en
tit
y
r
e
co
g
n
itio
n
,
f
ea
t
u
r
es
s
h
o
u
ld
b
e
co
n
s
id
er
ed
th
at
i
n
d
icate
t
h
e
d
if
f
er
e
n
ce
s
o
f
d
if
f
er
e
n
t
h
an
d
w
r
it
in
g
s
.
I
n
t
h
is
m
et
h
o
d
,
an
g
u
lar
f
ea
t
u
r
es
(
in
8
an
g
le
s
,
0
,
2
0
,
4
0
,
6
0
,
8
0
,
1
0
0
,
1
2
0
,
an
d
1
4
0
d
eg
r
ee
s
)
ar
e
f
ir
s
t e
x
tr
ac
ted
a
n
d
co
m
p
ar
ed
f
o
r
ea
ch
i
m
a
g
e
p
ag
e.
I
(
x
,
y
)
is
t
h
e
r
es
u
lti
n
g
i
m
a
g
e
f
r
o
m
p
r
ep
r
o
ce
s
s
in
g
,
w
h
i
ch
is
a
b
i
n
ar
y
i
m
a
g
e.
First
,
clo
s
in
g
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
ar
e
ap
p
lied
to
b
in
ar
y
i
m
ag
e
I
.
g
i:
i
s
th
e
i
-
t
h
i
m
ag
e
r
es
u
lti
n
g
f
r
o
m
clo
s
in
g
o
p
er
atio
n
s
w
it
h
co
n
s
tr
u
cti
n
g
ele
m
e
n
t
Si,
w
h
ic
h
h
a
s
t
h
e
s
a
m
e
d
i
m
en
s
i
o
n
s
a
s
t
h
e
i
n
p
u
t
i
m
a
g
e
I
.
I
:
t
h
e
b
i
n
ar
ized
in
p
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Wr
ite
r
I
d
en
tity R
ec
o
g
n
itio
n
a
n
d
C
o
n
fir
ma
tio
n
Usi
n
g
P
ers
ia
n
Ha
n
d
w
r
itten
Texts
(
A
id
a
S
h
ei
kh
)
101
i
m
a
g
e.
Si:
t
h
e
i
-
t
h
co
m
p
o
n
e
n
t
.
C
o
m
p
o
n
e
n
ts
ar
e
d
ir
ec
t
li
n
es
w
it
h
d
i
f
f
er
en
t
an
g
le
s
.
Fi
g
u
r
es
3
to
5
p
r
esen
ts
an
ex
a
m
p
le
o
f
an
g
u
lar
s
p
ec
if
icat
i
o
n
s
ex
tr
ac
ted
f
r
o
m
ea
ch
i
m
a
g
e
.
As
w
e
ca
n
s
ee
,
f
o
r
m
o
s
t
a
n
g
le
s
,
th
ese
s
p
ec
if
ica
tio
n
s
h
a
v
e
d
if
f
er
en
t
p
atter
n
s
f
o
r
d
if
f
er
en
t
i
m
ag
e
s
an
d
b
y
i
n
f
er
r
in
g
th
ese
d
i
f
f
er
e
n
ce
s
,
f
ea
tu
r
es
ca
n
b
e
in
tr
o
d
u
ce
d
t
h
at
ca
n
r
ec
o
g
n
ize
th
e
h
a
n
d
w
r
itin
g
.
So
m
e
o
f
t
h
e
u
s
ab
le
f
ea
t
u
r
es
i
n
clu
d
e
1
-
th
e
n
u
m
b
er
o
f
r
e
m
ain
in
g
b
lack
o
b
j
ec
ts
in
th
e
i
m
a
g
e
r
es
u
lti
n
g
f
r
o
m
a
n
g
le
e
x
tr
ac
tio
n
o
p
er
atio
n
.
Fo
r
in
s
tan
ce
f
o
r
a
4
0
d
eg
r
ee
s
an
g
le,
it i
s
clea
r
th
at
th
e
i
m
ag
e
h
as
m
o
r
e
b
lack
s
p
o
ts
.
2
-
T
h
e
len
g
th
o
f
th
e
r
e
m
ain
in
g
o
b
j
ec
ts
f
r
o
m
th
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
p
er
atio
n
.
3
-
T
h
e
to
tal
ar
ea
o
f
b
lac
k
lo
c
atio
n
s
o
f
t
h
e
i
m
ag
e
r
esu
lti
n
g
f
r
o
m
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
o
p
er
atio
n
.
Fig
u
r
e
2
.
T
h
e
im
a
g
e
o
f
t
h
e
Se
co
n
d
h
an
d
w
r
itte
n
te
x
t
Fig
u
r
e
3
.
An
g
u
lar
s
p
ec
i
f
icatio
n
s
o
f
0
d
eg
r
ee
s
f
o
r
th
e
i
m
a
g
e
o
f
a
h
a
n
d
w
r
iti
n
g
Fig
u
r
e
4
.
An
g
u
lar
Sp
ec
i
f
icatio
n
s
o
f
4
0
Deg
r
ee
s
f
o
r
th
e
I
m
a
g
e
o
f
A
Ha
n
d
w
r
iti
n
g
Fig
u
r
e
5
.
An
g
u
lar
Sp
ec
i
f
icatio
n
s
o
f
8
0
Deg
r
ee
s
f
o
r
th
e
I
m
a
g
e
o
f
A
Ha
n
d
w
r
iti
n
g
Su
b
s
eq
u
e
n
tl
y
,
t
h
e
an
g
u
lar
s
p
e
cif
icatio
n
o
f
ea
ch
i
m
a
g
e
is
e
x
t
r
ac
ted
f
o
r
d
if
f
er
en
t
a
n
g
le
s
o
f
t
h
e
n
u
m
b
er
2
h
an
d
w
r
iti
n
g
o
f
t
h
e
co
llect
ed
s
a
m
p
les
a
s
f
i
g
u
r
e
2
.
Mo
r
eo
v
er
,
w
e
ca
n
a
ls
o
u
s
e
a
c
o
m
b
i
n
atio
n
o
f
t
h
e
af
o
r
e
m
e
n
tio
n
ed
f
ea
t
u
r
es.
Fo
r
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
ta
g
e,
t
h
e
n
u
m
b
er
o
f
le
n
g
th
o
f
th
e
r
e
m
ai
n
in
g
b
lack
o
b
j
ec
ts
is
u
s
ed
as th
e
co
m
p
o
n
en
t.
T
h
is
f
ea
tu
r
e
i
s
co
m
p
u
ted
a
n
d
co
m
p
ar
ed
f
o
r
th
e
h
an
d
w
r
iti
n
g
s
o
f
t
w
o
i
n
d
iv
id
u
als t
h
at
th
er
e
ar
e
t
w
o
d
if
f
er
e
n
t
h
an
d
w
r
itin
g
s
f
r
o
m
ea
ch
in
d
i
v
id
u
al.
A
s
w
e
ca
n
s
ee
in
tab
le
2
,
th
e
d
i
f
f
er
en
ce
o
f
f
ea
tu
r
e
s
b
et
w
ee
n
th
e
h
an
d
w
r
it
in
g
s
o
f
an
in
d
i
v
id
u
al
i
s
s
m
aller
t
h
an
t
h
at
o
f
t
w
o
d
i
f
f
er
e
n
t i
n
d
iv
id
u
als
3
.
1
.
3
.
F
ea
t
ure
E
x
t
ra
ct
io
n
Af
ter
th
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e,
f
ea
t
u
r
e
ex
tr
ac
tio
n
is
p
er
f
o
r
m
ed
f
o
r
ea
ch
i
m
a
g
e
ex
tr
ac
ted
f
r
o
m
an
g
u
lar
s
p
ec
if
icat
io
n
s
,
s
ep
ar
atel
y
w
i
th
co
m
p
o
n
e
n
ts
i
n
f
o
r
m
o
f
l
in
e
s
w
it
h
d
i
f
f
er
en
t
len
g
th
s
,
w
h
ic
h
ar
e
co
n
s
id
er
ed
3
to
4
0
in
th
is
r
ese
ar
ch
,
s
o
th
at
th
e
o
b
s
er
v
atio
n
s
eq
u
en
ce
(
f
ea
tu
r
e
v
ec
to
r
)
o
f
ea
ch
h
a
n
d
w
r
itte
n
te
x
t
is
ac
h
ie
v
ed
.
Fin
all
y
,
t
h
is
o
b
s
er
v
atio
n
s
eq
u
en
ce
is
s
en
t
to
a
ch
ain
n
et
w
o
r
k
to
r
ec
o
g
n
ize
th
e
id
en
tit
y
o
f
t
h
e
w
r
iter
;
h
o
w
e
v
er
,
it
s
h
o
u
ld
b
e
n
o
r
m
alize
d
b
ef
o
r
e
s
en
d
i
n
g
it
to
th
e
class
i
f
icatio
n
s
ta
g
e.
Mo
r
eo
v
er
,
w
h
e
n
th
e
d
is
cr
ete
h
id
d
en
Ma
r
k
o
v
m
o
d
el
is
u
s
ed
f
o
r
clas
s
i
f
icatio
n
,
t
h
e
i
n
p
u
t
v
al
u
es
s
h
o
u
ld
b
e
d
i
s
cr
ete.
T
h
er
ef
o
r
e,
a
q
u
an
tizat
io
n
o
p
er
atio
n
is
u
s
e
d
.
A
f
ea
t
u
r
e
v
ec
to
r
w
it
h
in
te
g
er
v
al
u
es
in
r
an
g
e
[
0
,
1
0
0
]
is
co
n
s
id
er
ed
in
th
e
i
m
p
le
m
en
ted
id
en
tit
y
r
ec
o
g
n
it
io
n
s
y
s
te
m
f
o
r
ea
ch
a
n
g
u
lar
s
p
ec
if
icatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l
.
6
,
No
.
2
,
J
u
n
y
201
7
:
98
–
1
0
5
102
T
ab
le
2
.
C
alcu
latin
g
Feat
u
r
es
f
o
r
th
e
Ha
n
d
w
r
it
in
g
s
o
f
T
w
o
I
n
d
iv
id
u
als
N
u
mb
e
r
o
f
c
o
mp
o
n
e
n
t
s
r
e
mai
n
e
d
f
r
o
m F
i
r
st
H
a
n
d
w
r
i
t
i
n
g
o
f
S
e
c
o
n
d
p
e
r
so
n
N
u
mb
e
r
o
f
c
o
mp
o
n
e
n
t
s
r
e
mai
n
e
d
f
r
o
m F
i
r
st
H
a
n
d
w
r
i
t
i
n
g
o
f
S
e
c
o
n
d
p
e
r
so
n
N
u
mb
e
r
o
f
c
o
mp
o
n
e
n
t
s
r
e
mai
n
e
d
f
r
o
m
S
e
c
o
n
d
H
a
n
d
w
r
i
t
i
n
g
o
f
f
i
r
st
p
e
r
so
n
N
u
mb
e
r
o
f
c
o
mp
o
n
e
n
t
s
r
e
mai
n
e
d
f
r
o
m
F
i
r
st
H
a
n
d
w
r
i
t
i
n
g
o
f
f
i
r
st
p
e
r
so
n
A
n
g
l
e
s
74
64
50
34
0
1
5
9
1
4
7
1
6
3
1
6
6
20
1
6
6
1
4
6
2
1
4
1
9
9
40
40
35
1
0
1
1
0
4
60
33
29
79
83
80
11
13
23
25
1
0
0
7
4
7
5
1
2
0
8
10
15
15
1
4
0
4.
P
RO
P
O
SI
NG
A
M
O
DE
L
F
O
R
ANG
U
L
AR
SP
E
CIF
I
C
AT
I
O
N
T
h
e
p
r
o
p
o
s
ed
w
r
iter
id
en
t
it
y
r
ec
o
g
n
itio
n
s
y
s
te
m
is
d
iv
id
ed
in
to
t
w
o
m
a
in
s
ec
t
io
n
s
u
s
ed
f
o
r
tr
ain
in
g
an
d
test
i
n
g
.
I
n
o
r
d
er
to
in
cr
ea
s
e
ac
cu
r
ac
y
an
d
s
ec
u
r
it
y
,
t
h
e
co
n
s
tr
u
c
ted
m
o
d
els
ar
e
e
m
b
ed
d
ed
in
a
ch
ain
n
et
w
o
r
k
,
w
h
ich
p
r
esen
t
s
a
cr
ed
ib
le
tex
t
i
m
ag
e
f
o
r
an
g
u
l
ar
s
p
ec
if
icatio
n
s
.
I
n
th
is
r
ese
ar
ch
,
ea
ch
an
g
u
lar
s
p
ec
if
icatio
n
i
s
co
n
s
id
er
ed
a
s
a
s
ep
ar
ate
m
o
d
el.
T
h
e
d
i
s
cr
ete
lef
t
to
r
i
g
h
t
h
id
d
en
Ma
r
k
o
v
m
o
d
el
[
1
8
]
w
it
h
a
f
o
r
w
ar
d
i
n
g
s
tate
is
u
s
ed
to
im
p
le
m
e
n
t
ea
c
h
an
g
u
lar
s
p
ec
if
icatio
n
m
o
d
el.
I
n
o
r
d
er
to
tr
ain
th
e
m
o
d
el,
it
is
n
ec
es
s
ar
y
to
co
m
p
u
te
t
h
e
r
ela
ted
p
ar
am
eter
s
,
λ
={
A
,
B
,
π},
u
s
in
g
eq
u
atio
n
s
1
,
2
,
an
d
3
.
T
h
er
ef
o
r
e,
it
is
o
n
l
y
n
ec
es
s
ar
y
f
o
r
th
e
co
n
s
id
er
ed
an
g
u
lar
s
p
ec
i
f
icatio
n
af
ter
t
h
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
ta
g
e
an
d
p
r
o
v
id
in
g
th
e
f
ea
t
u
r
e
v
ec
to
r
(
o
b
s
er
v
atio
n
s
eq
u
e
n
ce
o
_
i)
to
u
s
e
th
e
th
r
ee
eq
u
atio
n
s
ab
o
v
e
to
ex
tr
ac
t th
e
p
ar
a
m
eter
s
o
f
th
e
m
o
d
el.
(
1
)
(
2
)
(
3
)
4
.
1
.
F
ea
t
ure
E
x
t
ra
ct
io
n
T
h
e
B
au
m
W
elch
al
g
o
r
ith
m
i
s
u
s
ed
to
tr
ain
HM
M
p
ar
a
m
e
ter
s
[
1
8
]
.
I
t
m
ea
n
s
t
h
at
λ
=
{
,
,
}
is
u
s
ed
to
p
r
esen
t
ea
ch
an
g
u
lar
s
p
ec
if
icatio
n
m
o
d
el.
T
h
e
i
n
iti
al
s
tate
d
i
s
tr
ib
u
tio
n
o
f
th
e
m
o
d
els
ar
e
=
{
}
,
w
h
er
e
1
=
1
an
d
=
0
f
o
r
1
<
≤
.
Mo
r
eo
v
er
,
N
is
th
e
n
u
m
b
er
o
f
s
tates
i
n
t
h
e
co
r
r
esp
o
n
d
in
g
m
o
d
el.
Fo
r
th
e
tr
an
s
it
io
n
p
r
o
b
ab
ilit
y
m
atr
i
x
=
{
,
}
,
in
itiall
y
,
=
,
+
1
=
,
+
2
=
0
.
5
f
o
r
1
≤
<
an
d
,
=
0
w
h
er
e
≠
+
1
,
≠
,
an
d
≠
+
2
.
Mo
r
eo
v
er
,
,
is
eq
u
al
to
o
n
e.
4
.
2
.
P
ro
po
s
ing
a
Cha
in Ne
t
w
o
rk
f
o
r
T
ra
ini
ng
M
o
dels
A
c
h
ai
n
n
et
w
o
r
k
o
f
a
n
g
u
lar
s
p
ec
if
icatio
n
s
i
s
u
s
ed
to
i
n
cr
ea
s
e
t
h
e
ac
cu
r
ac
y
a
n
d
s
ec
u
r
it
y
o
f
t
h
e
w
r
iter
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
`
s
o
u
tp
u
t a
n
d
co
n
s
tr
ain
t
h
e
s
ea
r
ch
s
p
ac
e.
T
h
e
ch
ai
n
n
et
w
o
r
k
is
d
iv
id
ed
in
to
a
s
e
t o
f
s
u
b
-
m
o
d
els
{
D
1
,
D
2
,
…
,
D
n
}
b
ased
o
n
th
e
an
g
l
es.
S
u
b
s
eq
u
e
n
tl
y
,
ea
ch
m
o
d
el
is
i
n
d
ex
ed
as
,
b
ased
o
n
it
s
p
ar
ts
.
Su
b
-
m
o
d
els
ar
e
e
m
b
ed
d
ed
in
a
ch
a
in
n
et
w
o
r
k
ca
lled
WN
k
,
i
,
w
h
ic
h
p
r
ese
n
ts
th
e
tex
t
i
m
a
g
es,
a
n
d
th
e
y
ar
e
co
n
n
ec
ted
t
h
r
o
u
g
h
s
p
ec
i
f
i
c
p
ath
s
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
th
e
id
e
n
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
f
o
r
s
ea
r
ch
in
g
a
w
r
iter
o
n
th
e
c
h
ai
n
n
e
t
w
o
r
k
is
as
f
o
llo
w
s
.
Fir
s
t,
u
s
i
n
g
t
h
e
m
e
th
o
d
,
w
h
ich
w
a
s
ex
p
la
in
ed
in
t
h
e
f
ea
t
u
r
e
ex
tr
a
ctio
n
m
et
h
o
d
,
th
e
o
b
s
er
v
atio
n
s
eq
u
e
n
ce
O
s
=
[
o
1
,
o
2
,
…
,
o
k
]
is
o
b
tain
ed
f
o
r
t
h
e
i
m
ag
e
o
f
a
h
an
d
w
r
itte
n
te
x
t.
I
n
th
i
s
eq
u
atio
n
,
p
(
SW
i
|
O
i
)
=
p
(
O
i
|
SW
i
)
p
(
SW
i
)
/
p
(
O
i
)
[
1
8
]
.
M
o
r
e
o
v
er
,
f
o
r
s
i
m
p
licit
y
,
w
e
a
s
s
u
m
e
th
at
all
p
ar
ts
o
f
th
e
tex
t
i
m
a
g
e
o
cc
u
r
w
ith
t
h
e
s
a
m
e
p
r
o
b
ab
ili
t
y
alo
n
g
th
e
ch
ai
n
s
`
p
ath
.
T
h
er
ef
o
r
e,
p
(
O
i
)
is
th
e
s
a
m
e
f
o
r
all
p
ar
ts
o
f
t
h
e
i
m
a
g
e
te
x
t
an
d
t
h
e
p
r
o
b
le
m
is
r
ed
u
ce
d
to
m
ax
i
m
iz
in
g
p
(
O
i
|
SW
i
)
,
w
h
ic
h
ca
n
b
e
ef
f
ec
tiv
e
l
y
co
m
p
u
ited
b
y
th
e
Viter
b
i
A
lg
o
r
it
h
m
f
o
r
n
et
w
o
r
k
WN
k
,
i
.
Fin
all
y
,
eq
u
atio
n
4
is
u
s
ed
to
s
ea
r
ch
wr
iter
w
i
n
k
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Wr
ite
r
I
d
en
tity R
ec
o
g
n
itio
n
a
n
d
C
o
n
fir
ma
tio
n
Usi
n
g
P
ers
ia
n
Ha
n
d
w
r
itten
Texts
(
A
id
a
S
h
ei
kh
)
103
W
=
a
r
gma
x
∏
P
(
O
i
|
SW
i
,
WN
k
,
i
)
k
i
=
1
(
4
)
5.
I
M
P
L
E
M
E
NT
AT
I
O
N
O
F
T
H
E
P
RO
P
O
SE
D
A
L
G
O
R
I
T
H
M
I
n
th
i
s
r
esear
ch
,
all
s
i
m
u
latio
n
is
p
er
f
o
r
m
ed
u
s
in
g
Ma
tlab
R
2
0
1
3
a
o
n
w
i
n
d
o
w
s
7
o
p
er
at
in
g
s
y
s
te
m
an
d
2
.
3
0
GHz
I
n
tel
C
o
r
e
i5
p
r
o
ce
s
s
o
r
.
R
es
u
lt
s
o
f
e
x
tr
ac
ti
n
g
th
e
c
o
m
p
o
n
e
n
t
s
b
ased
o
n
a
n
g
u
lar
s
p
ec
i
f
icatio
n
s
s
h
o
w
t
h
at
f
o
r
P
er
s
ian
h
a
n
d
w
r
i
tten
te
x
ts
,
f
ea
t
u
r
es a
r
e
ab
o
u
t t
h
e
s
a
m
e
t
h
r
o
u
g
h
o
u
t th
e
tex
t.
F
o
r
in
s
tan
ce
,
f
o
r
a
4
0
d
eg
r
ee
s
an
g
le,
i
m
a
g
es
w
it
h
m
ax
i
m
u
m
co
m
p
o
n
e
n
t
h
a
v
e
d
if
f
e
r
en
t
p
ix
el
len
g
t
h
s
.
Af
ter
th
e
p
r
e
-
p
r
o
ce
s
s
i
n
g
s
ta
g
e,
f
o
r
ea
ch
i
m
ag
e
e
x
tr
ac
ted
s
ep
ar
atel
y
f
r
o
m
th
e
a
n
g
u
lar
s
p
ec
i
f
icatio
n
w
it
h
li
n
e
co
m
p
o
n
e
n
ts
an
d
d
if
f
er
en
t
p
ix
e
l
len
g
th
s
,
w
h
ic
h
i
s
co
n
s
id
er
ed
3
to
4
0
in
th
i
s
r
esear
ch
,
f
ea
tu
r
e
ex
tr
ac
tio
n
is
p
er
f
o
r
m
ed
to
p
r
o
v
id
e
th
e
o
b
s
er
v
atio
n
s
eq
u
e
n
ce
(
f
ea
tu
r
e
v
ec
to
r
)
co
r
r
esp
o
n
d
in
g
to
ea
ch
h
an
d
w
r
itte
n
te
x
t.
Su
b
s
eq
u
e
n
tl
y
,
f
o
r
ea
c
h
w
r
iter
,
a
le
f
t
to
r
ig
h
t
HM
M
is
co
n
s
id
er
ed
in
w
h
ic
h
t
h
e
in
i
tial
n
o
d
e
is
ze
r
o
d
eg
r
ee
s
an
d
t
h
e
e
n
d
n
o
d
e
is
1
4
0
d
eg
r
ee
s
w
i
th
a
2
0
d
eg
r
ee
s
s
tep
.
Af
ter
t
h
e
f
ea
tu
r
e
e
x
tr
ac
tio
n
s
ta
g
e,
f
o
r
th
e
f
ir
s
t
h
an
d
w
r
iti
n
g
o
f
ea
ch
w
r
iter
,
t
h
e
s
tate
c
h
a
n
g
e
p
r
o
b
ab
ilit
y
m
at
r
ic
an
d
s
y
m
b
o
l
o
b
s
er
v
atio
n
p
r
o
b
ab
ilit
y
m
a
tr
ix
is
cr
ea
ted
,
w
h
ic
h
is
co
n
s
id
er
ed
th
e
in
p
u
t
o
f
th
e
HM
M.
P
ar
am
e
ter
s
ar
e
tr
ain
ed
u
s
in
g
th
e
B
au
m
–
W
elc
h
alg
o
r
it
h
m
o
n
th
e
ex
tr
ac
ted
f
ea
t
u
r
es.
I
n
t
h
ese
co
m
p
u
tat
io
n
s
,
th
e
m
a
x
i
m
u
m
lear
n
i
n
g
iter
atio
n
is
co
n
s
id
er
ed
1
0
0
.
I
n
o
r
d
e
r
to
class
i
f
y
a
s
eq
u
e
n
ce
to
o
n
e
o
f
th
e
K
cla
s
s
e
s
,
K
HH
M
m
o
d
els
ar
e
tr
ain
ed
f
o
r
ea
ch
cla
s
s
.
Su
b
s
eq
u
en
tl
y
,
L
L
v
alu
e
s
ar
e
co
m
p
u
ted
u
s
i
n
g
t
h
e
HM
M
T
o
o
lb
o
x
[
1
5
]
o
f
MI
T
.
I
f
t
h
e
i
-
th
m
o
d
el
i
s
t
h
e
m
o
s
t
s
i
m
ilar
,
t
h
e
s
eq
u
en
ce
b
elo
n
g
s
to
clas
s
i.
in
s
tatis
t
ics
,
th
e
lo
g
li
k
eli
h
o
o
d
f
u
n
c
tio
n
i
s
a
f
u
n
ctio
n
o
f
s
ta
tis
tica
l
m
o
d
el`
s
p
ar
a
m
e
ter
s
th
at
p
lay
s
a
k
e
y
r
o
le
in
i
n
f
er
e
n
tial
s
tatis
t
ics.
I
n
o
r
d
er
to
r
u
n
th
e
p
r
o
p
o
s
e
al
g
o
r
ith
m
to
r
ec
o
g
n
ize
an
d
co
n
f
ir
m
th
e
id
en
ti
t
y
o
f
t
h
e
w
r
iter
,
a
s
p
ec
if
ic
h
an
d
w
r
iti
n
g
o
f
a
w
r
iter
i
s
s
ele
cted
;
th
e
s
ec
o
n
d
h
an
d
w
r
iti
n
g
o
f
t
h
e
s
a
m
e
w
r
i
ter
is
th
e
n
co
m
p
ar
ed
u
s
i
n
g
HM
M
T
o
o
lb
o
x
.
Su
b
s
eq
u
en
tl
y
,
t
h
e
s
e
co
n
d
h
an
d
w
r
iti
n
g
o
f
an
o
t
h
er
w
r
iter
is
s
elec
ted
an
d
its
L
L
m
ea
s
u
r
e
is
co
m
p
u
ted
.
I
n
th
i
s
s
ec
tio
n
,
t
h
e
o
u
tp
u
t
o
f
th
e
p
r
o
p
o
s
ed
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
is
co
m
p
ar
ed
u
n
d
er
d
if
f
er
e
n
t
cir
cu
m
s
ta
n
ce
s
.
I
n
th
e
s
e
ex
p
er
i
m
en
ts
,
f
r
o
m
t
h
e
to
tal
7
0
s
a
m
p
les,
5
0
ar
e
s
elec
ted
f
o
r
tr
ain
in
g
an
d
th
e
r
e
m
ain
in
g
2
0
ar
e
s
elec
ted
f
o
r
test
in
g
.
T
h
is
co
m
p
ar
i
s
o
n
is
p
er
f
o
r
m
ed
f
o
r
d
if
f
er
en
t
tr
ain
i
n
g
co
n
d
iti
o
n
s
,
in
cl
u
d
in
g
t
h
e
p
ar
am
eter
s
o
f
co
m
p
o
n
e
n
ts
`
an
g
les,
tr
ain
in
g
d
u
r
atio
n
,
etc.
th
e
p
r
ec
is
io
n
is
co
m
p
u
ted
b
ased
o
n
th
e
p
er
ce
n
tag
e
o
f
co
r
r
ec
tl
y
r
ec
o
g
n
ized
s
a
m
p
l
es
d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
e
r
o
f
r
ec
o
g
n
i
tio
n
s
.
T
ab
le
3
p
r
e
s
en
t
s
t
h
ese
r
e
s
u
lt
s
.
As
w
e
ca
n
s
ee
,
t
h
e
h
i
g
h
est
p
r
ec
is
io
n
r
ate
o
f
id
en
tit
y
r
ec
o
g
n
itio
n
f
o
r
th
e
tr
ai
n
in
g
d
ata
is
r
esu
lted
w
h
e
n
th
e
n
u
m
b
er
o
f
co
m
p
o
n
e
n
t
`
s
a
n
g
l
e
ch
a
n
g
e
s
i
s
eq
u
al
to
7
o
r
1
2
an
d
th
e
co
m
p
o
n
e
n
t
len
g
t
h
is
eq
u
al
to
9
o
r
1
0
.
W
h
er
ea
s
,
f
o
r
t
h
e
test
d
ata,
th
e
n
u
m
b
er
o
f
co
m
p
o
n
e
n
t
`
s
an
g
le
ch
an
g
es
is
eq
u
al
to
1
2
an
d
t
h
e
co
m
p
o
n
e
n
t le
n
g
th
is
eq
u
al
to
9
.
T
a
b
le
3
.
C
o
m
p
a
r
is
o
n
o
f
r
esu
l
ts
f
o
r
d
if
f
e
r
en
t
HHM
t
r
a
in
in
g
c
o
n
d
iti
o
n
s
p
r
e
c
i
si
o
n
r
a
t
e
o
f
i
d
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
L
e
a
r
n
i
n
g
T
i
me
(
S
e
c
o
n
d
)
c
o
mp
o
n
e
n
t
l
e
n
g
t
h
n
u
m
b
e
r
o
f
c
o
mp
o
n
e
n
t
`
s
a
n
g
l
e
c
h
a
n
g
e
s
(
∆θ)
T
e
st
D
a
t
a
L
e
a
r
n
i
n
g
D
a
t
a
6
3
%
9
9
%
8
0
4
17
4
7
5
%
9
8
%
4
4
4
13
7
7
8
%
9
8
%
3
2
0
10
10
8
1
%
9
4
%
2
6
6
9
12
7
7
%
8
9
%
2
1
3
8
15
7
4
%
8
4
%
1
7
7
7
17
7
3
%
7
8
%
1
6
0
6
20
6
5
%
7
1
%
1
2
4
5
25
5
7
%
6
1
%
1
0
6
4
30
6.
E
VA
L
UA
T
I
O
N
Sin
ce
,
t
h
er
e
h
a
s
b
ee
n
n
o
s
ta
n
d
ar
d
d
atab
ase
f
o
r
P
e
r
s
ian
h
a
n
d
w
r
iti
n
g
tex
t
s
a
n
d
th
e
r
ele
v
a
n
t
p
u
b
lis
h
ed
p
ap
er
s
ea
ch
h
a
v
e
a
d
if
f
er
en
t
d
atab
ase,
th
e
A
r
ab
ic
h
an
d
w
r
it
in
g
d
atab
ase
i
n
r
e
f
er
en
ce
[
1
7
]
is
u
s
ed
to
e
v
al
u
ate
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
is
d
atab
ase
co
n
s
is
ts
o
f
4
p
ag
es
i
n
A
r
ab
ic
o
f
1
0
0
0
f
o
r
m
s
o
f
h
a
n
d
w
r
i
tin
g
s
,
w
h
ic
h
ar
e
co
llected
f
r
o
m
1
0
0
0
f
e
m
ale
a
n
d
m
ale
w
r
iter
s
i
n
t
h
e
co
u
n
tr
y
w
it
h
d
i
f
f
er
en
t
ag
e
s
,
1
5
to
7
0
.
A
b
o
u
t
6
5
%
o
f
t
h
ese
f
o
r
m
s
ar
e
f
illed
b
y
i
n
d
i
v
id
u
al
s
w
i
th
ag
e
s
i
n
r
a
n
g
e
1
6
to
2
5
.
F
o
r
ea
c
h
in
d
iv
id
u
al,
t
h
er
e
ar
e
f
o
u
r
i
m
a
g
es
o
f
h
a
n
d
w
r
iti
n
g
s
w
it
h
d
i
f
f
er
en
t
co
n
tex
ts
i
n
r
es
o
lu
tio
n
s
3
0
0
an
d
6
0
0
d
p
i.
R
e
ad
in
g
s
i
g
n
s
an
d
s
y
m
b
o
ls
ar
e
r
ar
ely
o
b
s
er
v
ed
i
n
th
ese
te
x
ts
.
Af
ter
s
ca
n
n
i
n
g
th
e
f
o
r
m
s
a
n
d
p
er
f
o
r
m
i
n
g
p
r
e
-
p
r
o
ce
s
s
i
n
g
o
p
er
atio
n
s
,
th
e
r
esear
c
h
er
s
,
w
h
o
h
a
v
e
co
llected
th
is
d
atab
ase
[
1
6
]
,
h
av
e
tr
an
s
f
o
r
m
ed
th
e
m
i
n
to
b
in
ar
y
i
m
a
g
e
s
u
s
in
g
t
h
e
Ot
s
u
th
r
e
s
h
o
ld
in
g
al
g
o
r
ith
m
an
d
th
e
y
h
av
e
al
s
o
r
em
o
v
ed
th
e
n
o
is
e.
T
h
e
tilt
m
o
d
if
ica
tio
n
o
p
er
atio
n
s
ar
e
p
er
f
o
r
m
e
d
b
ef
o
r
e
ex
tr
ac
tin
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l
.
6
,
No
.
2
,
J
u
n
y
201
7
:
98
–
1
0
5
104
p
ar
ag
r
ap
h
s
f
r
o
m
t
h
e
i
m
a
g
es.
Af
ter
id
en
ti
f
y
i
n
g
t
h
e
p
o
s
s
ib
le
lin
es,
t
h
e
X
-
Y
co
o
r
d
in
atio
n
o
f
ea
ch
ex
tr
ac
ted
lin
e
an
d
th
eir
r
e
g
r
ess
io
n
i
s
o
b
tain
ed
to
co
m
p
u
te
t
h
eir
s
lo
p
es.
At
th
e
n
e
x
t
s
ta
g
e,
p
ar
ag
r
ap
h
s
a
r
e
ex
tr
ac
ted
.
Sin
ce
,
th
er
e
ar
e
m
an
y
d
o
ts
a
n
d
o
v
er
h
ea
d
s
b
et
w
ee
n
t
h
e
li
n
es
in
A
r
ab
ic,
th
e
s
u
b
s
id
iar
y
co
m
p
o
n
e
n
ts
ar
e
f
ir
s
t
r
e
m
o
v
ed
an
d
o
n
l
y
t
h
e
p
r
i
m
ar
y
co
m
p
o
n
en
t
s
r
e
m
a
in
(
i
n
th
e
r
e
f
er
en
c
e
p
ap
er
,
th
is
p
ar
t
is
ca
lled
Par
t
o
f
A
r
ab
ic
W
o
r
d
(
P
A
W
)
)
.
T
h
e
im
a
g
e
i
s
th
e
n
d
iv
id
ed
in
to
s
ev
er
al
v
er
tical
s
tr
ip
s
.
T
h
e
lin
es
o
f
ea
c
h
s
tr
i
p
ar
e
id
en
tif
ied
an
d
f
i
n
a
ll
y
,
d
o
ts
a
n
d
o
v
er
h
ea
d
s
ar
e
ad
d
ed
to
th
e
s
tr
ip
s
.
T
h
e
w
o
r
d
s
o
f
ea
c
h
lin
e
ar
e
id
e
n
ti
f
ied
b
y
f
in
d
i
n
g
t
h
e
w
h
ite
s
p
ac
es
b
et
w
ee
n
w
o
r
d
s
.
Mo
r
eo
v
er
,
th
e
d
i
v
i
s
io
n
p
o
s
itio
n
s
ar
e
id
en
ti
f
ied
b
y
f
i
n
d
in
g
s
a
h
y
p
o
th
etica
l
s
p
ac
e
m
o
r
e
th
an
1
0
p
ix
els.
A
t
th
e
n
e
x
t
s
ta
g
e,
th
e
t
ex
t
i
n
s
er
ted
in
th
e
f
o
r
m
s
is
e
v
al
u
ated
in
th
r
ee
p
h
ase
s
.
T
h
is
is
p
er
f
o
r
m
ed
b
y
h
u
m
a
n
p
er
s
o
n
n
el.
I
n
t
h
e
p
er
f
o
r
m
ed
r
esear
ch
,
r
es
u
lts
o
f
4
8
0
8
,
9
3
8
,
an
d
9
6
6
lin
e
s
ar
e
r
esp
ec
tiv
el
y
d
ed
icate
d
to
tr
ain
i
n
g
,
v
alid
atio
n
,
an
d
te
s
t
s
ets.
T
h
e
h
a
n
d
w
r
it
ten
tex
t
is
r
ec
o
g
n
iz
ed
u
s
i
n
g
d
is
cr
ete
le
f
t
to
r
ig
h
t
HM
M
w
i
th
B
ak
is
to
p
o
lo
g
y
a
n
d
u
s
i
n
g
HT
K.
I
n
f
ac
t,
t
h
e
s
h
ap
e
o
f
ea
ch
ch
ar
ac
ter
is
co
n
s
id
er
ed
as
a
class
d
u
r
i
n
g
tr
ai
n
i
n
g
.
T
h
e
id
en
tifie
d
ch
ar
ac
ter
s
w
it
h
s
i
m
ilar
s
h
ap
es
ar
e
p
lace
d
i
n
o
n
e
clas
s
.
I
n
s
u
m
,
1
4
9
clas
s
es
ar
e
co
n
s
id
er
ed
.
Sev
er
al
s
tati
s
tic
s
f
ea
t
u
r
es
ar
e
ex
tr
ac
ted
f
r
o
m
th
e
li
n
es
i
m
a
g
es
u
s
i
n
g
t
h
e
s
lid
i
n
g
w
i
n
d
o
w
tech
n
iq
u
e,
w
h
er
e
w
i
n
d
o
w
s
ar
e
co
n
s
id
er
ed
w
i
th
d
if
f
er
e
n
t
le
n
g
th
s
.
Ho
w
e
v
er
,
th
e
b
est
r
es
u
lt
is
ac
h
ie
v
ed
b
y
th
e
s
lid
in
g
w
i
n
d
o
w
w
it
h
len
g
t
h
4
an
d
s
h
ar
ed
s
p
a
ce
2
.
Af
ter
t
h
e
e
x
tr
ac
tio
n
,
f
ea
tu
r
es
ar
e
q
u
a
n
tized
i
n
t
h
e
l
in
ea
r
co
d
eb
o
o
k
u
s
i
n
g
to
p
-
d
o
w
n
cl
u
s
ter
i
n
g
.
T
ab
le
4
p
r
esen
ts
th
e
r
ec
o
g
n
i
tio
n
r
ate
r
esu
lts
o
f
th
e
al
g
o
r
ith
m
in
r
ef
er
en
ce
[
1
6
]
,
th
e
m
u
lti
-
la
y
er
p
er
ce
p
tr
o
n
n
eu
r
al
n
et
w
o
r
k
,
an
d
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
ab
le
4
.
C
o
m
p
ar
is
o
n
o
f
th
e
P
r
ec
is
io
n
R
e
s
u
lts
o
f
th
e
P
r
o
p
o
s
ed
A
lg
o
r
ith
m
o
n
t
h
e
Han
d
w
r
i
tin
g
Data
b
ase
T
e
st
A
c
c
.
(
%)
T
r
a
i
n
i
n
g
A
c
c
.
(
%)
ر
اک
ش
و
ر
5
1
.
7
3
5
1
.
4
R
e
f
r
e
n
c
e
[
1
6
]
34
28
M
L
P
5
8
.
7
6
1
.
5
P
r
o
p
o
se
d
a
l
g
o
r
i
t
h
m
Sin
ce
t
h
is
r
e
s
ea
r
ch
ai
m
ed
to
p
r
o
p
o
s
e
a
d
y
n
a
m
ic
(
s
m
o
o
th
a
n
d
au
to
m
atic)
m
eth
o
d
an
d
n
o
li
m
itat
io
n
s
ar
e
co
n
s
id
er
ed
f
o
r
th
e
t
y
p
e
o
f
t
h
e
in
v
e
s
ti
g
ated
h
a
n
d
w
r
i
tin
g
s
,
w
e
d
o
n
o
t
co
n
s
id
er
m
et
h
o
d
s
th
at
r
eq
u
ir
e
t
h
e
au
to
m
at
ic
s
e
g
m
en
tatio
n
o
f
t
h
e
tex
t
in
to
w
o
r
d
s
a
n
d
letter
s
.
T
h
e
ch
ar
ac
ter
is
tic
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
i
s
co
m
p
atib
l
e
w
i
th
t
h
e
s
tr
u
ct
u
r
e
o
f
P
er
s
ian
h
a
n
d
w
r
itten
te
x
t
s
.
T
h
is
m
e
th
o
d
i
s
i
n
tr
o
d
u
ce
d
as
a
n
ap
p
r
o
ac
h
to
te
x
t
-
d
ep
en
d
en
t
id
en
ti
t
y
r
ec
o
g
n
itio
n
.
Of
co
u
r
s
e,
co
n
s
id
er
in
g
t
h
e
i
m
ag
e
s
r
es
u
lti
n
g
f
r
o
m
a
n
g
u
lar
s
p
ec
if
icatio
n
s
,
it
is
clea
r
t
h
at
t
h
ese
f
ea
t
u
r
es
ar
e
ab
o
u
t
th
e
s
a
m
e
th
r
o
u
g
h
o
u
t th
e
te
x
t a
n
d
th
u
s
,
t
h
is
m
et
h
o
d
ca
n
also
b
e
u
s
ed
as
an
in
d
ep
en
d
en
t
m
et
h
o
d
.
7.
CO
NCLU
SI
O
NS
Featu
r
e
ex
tr
ac
tio
n
is
o
n
e
o
f
th
e
d
eter
m
i
n
i
n
g
s
tag
e
s
o
f
i
n
c
r
ea
s
in
g
th
e
id
e
n
tit
y
r
ec
o
g
n
iti
o
n
r
ate
in
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
s
.
E
x
tr
ac
ted
f
ea
t
u
r
es
s
h
o
u
ld
in
d
i
ca
te
th
e
d
i
f
f
er
e
n
t
o
f
a
n
i
n
d
iv
i
d
u
al`
s
h
a
n
d
w
r
iti
n
g
f
r
o
m
th
at
o
f
o
th
er
s
an
d
th
er
e
s
h
o
u
ld
also
b
e
m
in
i
m
a
l
d
if
f
er
en
ce
b
et
w
ee
n
h
a
n
d
w
r
i
tten
te
x
ts
o
f
an
in
d
i
v
id
u
al.
T
h
is
r
esear
ch
e
m
p
lo
y
s
a
co
m
b
in
atio
n
o
f
ed
g
e
d
ir
ec
tio
n
d
i
s
tr
ib
u
tio
n
a
n
d
ed
g
e
a
x
i
s
d
is
tr
ib
u
tio
n
f
e
at
u
r
es
to
ex
tr
ac
t
f
ea
tu
r
e
s
,
as
w
el
l
as
t
h
e
h
id
d
en
Ma
r
k
o
v
Mo
d
el.
An
g
u
lar
s
p
ec
if
icatio
n
m
o
d
el
s
ar
e
c
o
n
n
ec
ted
t
h
r
o
u
g
h
a
s
p
ec
if
ic
ch
a
in
n
et
w
o
r
k
to
in
cr
ea
s
e
th
e
ac
cu
r
ac
y
a
n
d
s
ec
u
r
it
y
o
f
th
e
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
.
Mo
r
eo
v
er
,
a
d
atab
ase
p
r
o
v
id
ed
b
y
7
0
d
if
f
er
en
t
w
r
iter
s
w
a
s
u
s
ed
to
tr
ain
a
n
d
ev
al
u
ate
th
e
s
y
s
te
m
.
C
o
n
s
id
er
in
g
t
h
e
r
es
u
lts
,
t
h
e
ad
v
an
ta
g
e
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
as
f
o
llo
w
s
:
1.
Usi
n
g
a
co
m
b
i
n
atio
n
o
f
ed
g
e
d
ir
ec
tio
n
d
is
tr
ib
u
tio
n
a
n
d
ed
g
e
ax
i
s
d
is
tr
ib
u
tio
n
f
ea
t
u
r
es
at
th
e
f
ea
tu
r
e
ex
tr
ac
tio
n
s
tag
e.
2.
T
h
e
au
to
n
o
m
y
o
f
t
h
e
p
r
o
p
o
s
ed
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
,
p
ar
ticu
lar
l
y
a
t
t
h
e
f
ea
tu
r
e
e
x
t
r
ac
tio
n
s
ta
g
e
(
s
in
ce
,
m
a
n
u
al
f
ea
tu
r
e
e
x
tr
ac
ti
o
n
is
o
v
er
w
h
el
m
in
g
an
d
ti
m
e
-
co
n
s
u
m
i
n
g
)
.
3.
I
n
cr
ea
s
in
g
th
e
ac
c
u
r
ac
y
an
d
cr
ed
ib
ilit
y
o
f
th
e
id
en
tit
y
r
ec
o
g
n
itio
n
s
y
s
te
m
d
u
e
to
u
s
in
g
t
h
e
ch
ai
n
n
et
w
o
r
k
at
t
h
e
tr
ain
i
n
g
s
ta
g
e.
4.
E
li
m
i
n
ati
n
g
th
e
n
ee
d
f
o
r
th
e
s
eg
m
e
n
tat
io
n
s
ta
g
e
at
t
h
e
f
ea
t
u
r
e
ex
tr
ac
tio
n
s
ta
g
e.
Sin
ce
t
h
e
w
r
iter
id
en
tit
y
r
ec
o
g
n
itio
n
p
r
o
b
le
m
is
p
er
f
o
r
m
ed
f
o
r
th
e
f
ir
s
t ti
m
e
u
s
i
n
g
P
er
s
ian
h
an
d
w
r
itte
n
te
x
ts
w
it
h
th
e
p
r
o
p
o
s
ed
f
ea
tu
r
e
ex
tr
ac
tio
n
m
et
h
o
d
,
th
e
r
esu
lts
o
f
th
is
p
ap
er
ar
e
p
r
o
m
is
i
n
g
.
Mo
r
eo
v
er
,
th
e
p
r
o
p
o
s
ed
f
ea
tu
r
es
ar
e
g
lo
b
al
f
ea
t
u
r
es
a
n
d
th
e
r
esu
lt
s
ca
n
b
e
i
m
p
r
o
v
ed
b
y
e
x
tr
ac
ti
n
g
a
n
d
co
m
b
i
n
i
n
g
d
i
f
f
er
en
t
f
ea
t
u
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
Wr
ite
r
I
d
en
tity R
ec
o
g
n
itio
n
a
n
d
C
o
n
fir
ma
tio
n
Usi
n
g
P
ers
ia
n
Ha
n
d
w
r
itten
Texts
(
A
id
a
S
h
ei
kh
)
105
RE
F
E
R
E
NC
E
S
[1
]
S
.
N.
S
ri
h
a
ri,
H.A
ro
ra
,
S
.
H.
Ch
a
a
n
d
S
.
lee
.
In
d
iv
id
u
a
li
ty
o
f
h
a
n
d
w
ri
ti
n
g
.
J
o
u
r
n
a
l
o
f
Fo
re
n
sic
S
c
ien
c
e
s
.
2
0
0
2
;
4
7
(4
)
:
1
-
1
7
.
[2
]
S
.
N.
S
rih
a
ri
,
H.A
ro
ra
,
S
.
H.
Ch
a
a
n
d
S
.
lee
,
"
In
d
iv
id
u
a
li
ty
o
f
h
a
n
d
w
r
it
in
g
:
a
v
a
li
d
a
ti
o
n
stu
d
y
,
"
IEE
E
P
ro
c
.
Of
6
th
In
t
.
c
o
n
f.
o
n
Do
c
u
me
n
t
An
a
lys
is
a
n
d
Rec
o
g
n
it
io
n
,
p
p
.
1
0
6
-
1
0
9
,
2
0
0
1
.
[3
]
E.
N.Z
o
is,
V
.
A
n
a
sta
ss
o
p
o
u
lo
s
,
“
M
o
rp
h
o
l
o
g
ica
l
w
a
v
e
f
o
r
m
c
o
d
in
g
fo
r
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
,
”
P
a
tt
e
rn
Rec
o
g
n
it
i
o
n
,
v
o
l.
3
3
,
p
p
.
3
8
5
-
3
9
8
,
2
0
0
0
.
[4
]
A
.
Be
n
si
f
a
,
T
.
P
a
q
u
e
t
a
n
d
L
.
He
u
t
te,
"
Ha
n
d
w
rit
ten
d
o
c
u
m
e
n
t
a
n
a
ly
sis
f
o
r
a
u
to
m
a
ti
c
w
rit
e
r
re
c
o
g
n
it
io
n
,
"
El
e
c
tro
n
ic
L
e
tt
e
rs
o
n
C
o
mp
u
ter
Vi
sio
n
a
n
d
I
ma
g
e
An
a
lys
is
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
7
2
-
8
6
,
2
0
0
5
.
[5
]
A
.
S
c
h
lap
b
a
c
h
a
n
d
H
.
Bu
n
k
e
,
“
Us
in
g
HMM
-
b
a
se
d
re
c
o
g
n
it
io
n
f
o
r
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
a
n
d
v
e
rif
ica
ti
o
n
,
”
IEE
E
Pr
o
c
o
f
٩
th
I
n
t.
W
o
rk
sh
o
p
o
n
fro
n
ti
e
rs
i
n
h
a
n
d
writi
n
g
Rec
o
g
n
i
ti
o
n
,
p
p
.
1
6
7
-
1
7
2
,
2
0
0
4
.
[6
]
M
.
Bu
lac
u
,
L
.
S
c
h
o
m
a
k
e
r,
"
W
rit
e
r
sty
le
f
ro
m
o
rien
ted
e
d
g
e
f
ra
g
m
e
n
ts,
"
p
ro
c
.
1
0
t
h
I
n
t.
C
o
n
f
.
Co
m
p
u
ter
An
a
lys
is
o
f
ima
g
e
s a
n
d
Pa
tt
e
r
n
s
,
p
p
.
4
6
0
-
4
6
9
,
2
0
0
3
.
[7
]
G
o
ln
a
z
G
h
ias
i,
Re
z
a
S
a
fa
b
a
k
h
s
h
,
“
A
n
E
ff
icie
n
t
M
e
th
o
d
f
o
r
O
ff
li
n
e
T
e
x
t
In
d
e
p
e
n
d
e
n
t
W
rit
e
r
Id
e
n
ti
f
ica
ti
o
n
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
P
a
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
1
0
.
[8
]
Bu
lac
u
,
M
.
,
S
c
h
o
m
a
k
e
r,
L
.
,
V
u
u
rp
ij
l,
L
.
W
rit
e
r
id
e
n
ti
f
ica
ti
o
n
u
si
n
g
e
d
g
e
-
b
a
se
d
d
irec
ti
o
n
a
l
f
e
a
tu
re
s,
in
:
S
e
v
e
n
t
h
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
D
o
c
u
me
n
t
A
n
a
lys
is
a
n
d
Rec
o
g
n
it
i
o
n
(
ICDAR).
20
0
5
.
[9
]
Nie
ls,
R.
,
G
o
o
tj
e
n
,
F
.
Vu
u
r
p
ij
l
,
L
.
"
W
rit
e
r
Id
e
n
ti
f
ica
ti
o
n
t
h
ro
u
g
h
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l:
T
h
e
A
l
lo
g
ra
p
h
W
e
ig
h
t
V
e
c
to
r,
"
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
Fro
n
ti
e
rs
in
Ha
n
d
writ
in
g
Rec
o
g
n
it
io
n
,
p
p
.
4
8
1
-
4
8
6
,
2
0
0
8
.
[1
0
]
B.
He
ll
i,
M
.
E
.
M
o
g
h
a
d
d
a
m
,
“
A
te
x
t
-
in
d
e
p
e
n
d
e
n
t
P
e
rsia
n
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
sy
ste
m
u
sin
g
L
CS
b
a
se
d
c
las
sif
ier”
,
in
:
IEE
E
In
ter
n
a
ti
o
n
a
l
S
y
mp
o
si
u
m o
n
S
i
g
n
a
l
Pr
o
c
e
ss
in
g
a
n
d
In
fo
rm
a
t
io
n
T
e
c
h
n
o
lo
g
y
,
IS
S
P
IT
2
0
0
8
.
[1
1
]
S
o
ley
m
a
n
i
Ba
g
h
sh
a
h
,
M
.
,
Ba
g
h
e
ri
S
h
o
u
ra
k
i,
S
.
Ka
sa
e
i,
S
.
a
n
o
v
e
l
f
u
z
z
y
c
las
sif
i
e
r
u
sin
g
f
u
z
z
y
L
V
Q
to
re
c
o
g
n
ize
o
n
li
n
e
P
e
rsia
n
h
a
n
d
w
rit
in
g
,
in
:
S
e
c
o
n
d
IEE
E
Co
n
fer
e
n
c
e
o
n
I
n
fo
rm
a
ti
o
n
a
n
d
Co
mm
u
n
ica
t
io
n
T
e
c
h
n
o
lo
g
y
(
ICT
T
A)
,
2
0
0
6
.
[1
2
]
He
ll
i,
B.
M
o
g
h
a
d
d
a
m
,
M
.
E.
P
e
rsia
n
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
u
sin
g
e
x
t
e
n
d
e
d
G
a
b
o
r
f
il
ter,
in
:
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Im
a
g
e
A
n
a
lys
is
a
n
d
Rec
o
g
n
it
i
o
n
(
ICIAR
)
,
2
0
0
8
.
[1
3
]
R.
S
a
d
e
g
h
i
.
S
.
M
o
g
h
a
d
d
a
m
,
M
.
E.
T
e
x
t
-
in
d
e
p
e
n
d
e
n
t
P
e
rsia
n
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
u
sin
g
f
u
z
z
y
c
lu
ste
r
in
g
A
p
p
ro
a
c
h
,
in
:
I
n
ter
n
a
t
io
n
a
l
C
o
n
-
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
M
a
n
a
g
e
me
n
t
a
n
d
E
n
g
in
e
e
rin
g
(
ICIM
E),
M
a
la
y
sia
.
2
0
0
9
.
[1
4
]
G
o
ln
a
z
G
h
ias
i,
Re
z
a
S
a
fa
b
a
k
h
s
h
,
“
A
n
E
ff
icie
n
t
M
e
th
o
d
f
o
r
O
ff
li
n
e
T
e
x
t
In
d
e
p
e
n
d
e
n
t
W
rit
e
r
Id
e
n
ti
f
ica
ti
o
n
”
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
P
a
tt
e
rn
Rec
o
g
n
it
io
n
,
2
0
1
0
.
[1
5
]
h
tt
p
:
//
ww
w
.
c
s.u
b
c
.
c
a
/~
m
u
rp
h
y
k
/S
o
f
tw
a
r
e
/HM
M
/h
m
m
_
u
sa
g
e
.
h
t
m
l
[1
6
]
KH
A
TT
:
S
.
A
.
M
a
h
m
o
u
d
,
I.
A
h
m
a
d
,
W
.
A
l
-
K
h
a
ti
b
,
M
.
A
lsh
a
y
e
b
,
M
.
T
a
n
v
ir
P
a
rv
e
z
,
V
.
M
ä
rg
n
e
r,
G
.
A
.
F
in
k
,
”
A
n
o
p
e
n
A
ra
b
ic o
f
f
li
n
e
h
a
n
d
w
rit
ten
t
e
x
t
d
a
tab
a
se
”
,
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
,
v
o
l.
4
7
,
n
o
.
3
,
p
p
.
1
0
9
6
–
1
1
1
2
,
M
a
rc
h
2
0
1
4
.
[1
7
]
h
tt
p
:
//
k
h
a
tt
.
i
d
e
a
s2
se
rv
e
.
n
e
t/
in
d
e
x
.
p
h
p
[1
8
]
S
c
h
lap
b
a
c
h
,
A
.
,
Bu
n
k
e
,
H.
Us
in
g
HMM
b
a
se
d
re
c
o
g
n
ize
r
s
f
o
r
w
rit
e
r
id
e
n
ti
f
ica
ti
o
n
a
n
d
v
e
rif
ica
ti
o
n
,
in
:
Pro
c
e
e
d
in
g
s
–
In
ter
n
a
ti
o
n
a
l
W
o
rk
sh
o
p
o
n
Fr
o
n
ti
e
rs
in
H
a
n
d
writi
n
g
Rec
o
g
n
it
io
n
,
IW
F
HR,
T
o
k
y
o
,
p
p
.
1
6
7
–
1
7
2
,
2
0
0
4
.
[1
9
]
A
.
Be
n
sifa
,
T
.
P
a
q
u
e
t
a
n
d
L
.
He
u
tt
e
,
"
A
W
rit
e
r
id
e
n
ti
f
ica
ti
o
n
a
n
d
v
e
rif
ic
a
ti
o
n
sy
ste
m
,
"
Pa
tt
e
rn
Rec
o
g
n
it
i
o
n
L
a
tt
e
rs
,
v
o
l.
2
6
,
n
o
.
1
3
,
p
p
.
2
0
8
0
-
2
0
9
2
,
2
0
0
5
.
[2
0
]
Ra
f
ie
e
,
A
.
,
M
o
tav
a
ll
i,
H.
Of
f
-
L
in
e
W
rit
e
r
Re
c
o
g
n
it
io
n
f
o
r
F
a
rsi
tex
t.
In
:
6
t
h
M
e
x
ica
n
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
,
S
p
e
c
ial
S
e
ss
io
n
,
p
p
.
1
9
3
-
1
9
7
,
2
0
0
7
.
Evaluation Warning : The document was created with Spire.PDF for Python.