I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
201
4
,
p
p
.
121
~
128
I
SS
N:
2252
-
8938
121
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
A
I
O
pti
ca
l Chara
cte
r Rec
o
g
nition o
f
O
f
f
-
Line
Ty
ped a
nd
H
a
ndw
ritt
en Eng
lish T
ex
t
Using
M
o
rpho
lo
g
ica
l and T
e
m
pla
t
e
M
a
tching Techni
ques
O
la
k
a
n
m
i O
la
da
y
o
O
De
p
a
rtme
n
t
o
f
El
e
c
tri
c
a
l
&
El
e
c
tro
n
ic E
n
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
o
f
I
b
a
d
a
n
Nig
e
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
2
3
,
2
0
1
4
R
ev
i
s
ed
A
u
g
9
,
2
0
1
4
A
cc
ep
ted
A
u
g
2
1
,
2
0
1
4
T
h
e
e
x
isten
c
e
o
f
se
v
e
ra
l
d
o
c
u
m
e
n
ts
in
h
ist
o
rica
l
a
rc
h
iv
e
s
w
h
ich
n
e
e
d
to
b
e
e
d
it
e
d
a
n
d
st
o
re
d
i
n
a
c
o
m
p
u
t
e
r
h
a
s
b
e
e
n
o
n
e
o
f
th
e
d
r
iv
e
s
o
f
Op
ti
c
a
l
Ch
a
ra
c
ter
Re
a
d
e
r
(OCR)
re
se
a
rc
h
.
Earlier
sc
a
n
n
e
r
h
a
s
b
e
e
n
u
se
d
to
a
c
h
iev
e
th
is
ted
i
o
u
s
tas
k
h
o
w
e
v
e
r
sc
a
n
n
e
r
o
n
ly
p
ro
d
u
c
e
s
p
i
c
tu
re
im
a
g
e
s
o
f
th
e
d
o
c
u
m
e
n
ts.
T
h
is
m
a
k
e
s
th
e
d
o
c
u
m
e
n
ts
u
n
re
a
d
a
b
le
a
n
d
u
n
-
e
d
it
a
b
le
th
ro
u
g
h
o
th
e
r
w
o
rd
p
ro
c
e
ss
in
g
a
p
p
li
c
a
ti
o
n
s.
T
h
is
p
a
p
e
r
p
r
o
p
o
se
d
a
n
O
CR
s
y
ste
m
w
h
ich
c
o
n
v
e
rts
o
ff
li
n
e
t
y
p
e
d
a
n
d
h
a
n
d
w
rit
ten
tex
ts
in
to
th
e
ir
e
d
it
a
b
le
tex
tu
a
l
re
p
re
se
n
tatio
n
s.
T
h
e
m
o
rp
h
o
lo
g
i
c
a
l
c
o
r
re
latio
n
tec
h
n
iq
u
e
im
p
ro
v
e
s
th
e
m
a
p
p
in
g
a
n
d
re
c
o
g
n
it
i
o
n
e
f
f
icie
n
c
y
o
f
th
e
OCR s
y
ste
m
.
K
ey
w
o
r
d
:
Han
d
w
r
itte
n
E
n
g
lis
h
T
ex
t
Mo
r
p
h
o
lo
g
ical
Of
f
-
L
in
e
T
y
p
ed
Op
tical
C
h
ar
ac
ter
R
ec
o
g
n
itio
n
T
em
p
late
Ma
tch
in
g
T
ec
h
n
iq
u
es
Co
p
y
rig
h
t
©
2
0
1
4
In
stit
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
:
Ok
ala
n
m
i O
lad
a
y
o
O
,
Dep
ar
t
e
m
en
t o
f
E
lectr
ical
an
d
E
lectr
o
n
ic
E
n
g
in
ee
r
i
n
g
,
R
m
.
6
,
Facu
lt
y
o
f
T
ec
h
n
o
lo
g
y
,
Un
i
v
er
s
it
y
o
f
I
b
ad
an
Ni
g
er
ia.
E
m
ail:
o
la
k
an
m
i.o
lad
a
y
o
@
u
i.
ed
u
.
n
g
1.
I
NT
RO
D
UCT
I
O
N
I
t
h
as
b
ec
o
m
e
a
tr
e
n
d
to
d
o
cu
m
en
t
m
o
s
t
o
f
t
h
e
d
o
cu
m
e
n
ts
i
n
t
h
e
ar
ch
iv
e
s
u
s
i
n
g
s
ca
n
n
er
,
h
o
w
ev
er
,
th
ese
d
o
cu
m
en
ts
ca
n
n
o
t
b
e
ed
ited
o
r
r
ea
d
th
er
ea
f
ter
b
y
co
m
p
u
ter
s
y
s
te
m
s
.
Du
e
to
th
e
f
ac
t
th
at
s
ca
n
n
er
s
ca
n
s
d
o
cu
m
en
ts
as
an
i
m
a
g
e
n
o
t
as
en
co
d
ed
s
et
o
f
ch
ar
ac
te
r
s
.
OC
R
s
y
s
te
m
d
o
es
elec
tr
o
n
ic
tr
an
s
lat
io
n
o
f
h
an
d
w
r
itte
n
o
r
p
r
in
ted
tex
t
in
t
o
m
ac
h
i
n
e
en
co
d
ed
tex
t.
OC
R
is
w
id
el
y
u
s
ed
to
co
n
v
er
t
b
o
o
k
s
an
d
d
o
cu
m
e
n
t
s
in
to
elec
tr
o
n
ic
f
iles
a
n
d
to
co
m
p
u
ter
ize
a
r
ec
o
r
d
k
ee
p
in
g
s
y
s
te
m
i
n
an
o
f
f
ice.
OC
R
m
a
k
es
it
p
o
s
s
ib
le
to
e
d
it
s
u
c
h
d
o
cu
m
en
t,
s
ea
r
ch
f
o
r
a
w
o
r
d
o
r
p
h
r
ase,
s
to
r
e
it
m
o
r
e
co
m
p
ac
tl
y
,
d
is
p
la
y
o
r
p
r
in
t
a
co
p
y
a
n
d
ap
p
l
y
tech
n
iq
u
es
s
u
ch
a
s
m
ac
h
i
n
e
tr
an
s
latio
n
,
te
x
t
-
to
-
s
p
ee
c
h
an
d
tex
t
m
in
in
g
to
it.
O
C
R
s
t
u
d
y
w
a
s
s
tar
ted
b
y
T
y
u
r
i
n
a
R
u
s
s
ia
n
s
cie
n
ti
s
t
(
A.
J
ain
an
d
Kar
u
2
0
0
6
)
.
T
h
e
f
ir
s
t
m
o
d
er
n
c
h
ar
ac
ter
r
ec
o
g
n
iz
er
s
ap
p
ea
r
ed
in
t
h
e
m
id
d
le
o
f
t
h
e
1
9
4
0
s
w
it
h
t
h
e
d
ev
e
lo
p
m
en
t
o
f
t
h
e
d
i
g
it
al
co
m
p
u
ter
.
T
h
e
ea
r
l
y
w
o
r
k
o
n
t
h
e
a
u
to
m
a
tic
r
ec
o
g
n
itio
n
o
f
ch
ar
ac
ter
s
h
as
b
ee
n
co
n
ce
n
tr
ated
eit
h
er
u
p
o
n
w
ell
p
r
in
ted
te
x
t
o
r
u
p
o
n
s
m
all
s
et
o
f
w
el
l
d
is
tin
g
u
is
h
ed
h
a
n
d
w
r
itte
n
te
x
t
o
r
s
y
m
b
o
ls
,
a
lth
o
u
g
h
,
s
u
cc
es
s
f
u
l
b
u
t
h
ad
b
ee
n
i
m
p
le
m
e
n
te
d
m
o
s
tl
y
f
o
r
L
ati
n
ch
ar
ac
ter
s
a
n
d
n
u
m
er
als.
A
l
s
o
s
o
m
e
s
t
u
d
ies
o
n
J
ap
an
ese,
C
h
in
e
s
e,
Heb
r
e
w
,
I
n
d
ia
n
an
d
A
r
ab
ic
ch
ar
ad
es
an
d
n
u
m
er
als
i
n
b
o
th
p
r
in
ted
a
n
d
h
an
d
w
r
it
ten
ca
s
e
s
w
er
e
also
co
n
s
id
er
ed
b
y
s
o
m
e
O
C
R
s
y
s
te
m
s
.
T
h
e
d
ev
elo
p
m
en
t
s
i
n
O
C
R
u
n
ti
l
1
9
8
0
s
s
u
f
f
er
ed
f
r
o
m
lac
k
o
f
ad
v
an
ce
d
al
g
o
r
ith
m
,
p
o
w
er
f
u
l
c
o
m
p
u
ti
n
g
h
ar
d
w
ar
e
an
d
o
p
tical
d
ev
ices.
W
ith
t
h
e
o
u
t
w
ar
d
ex
p
lo
s
io
n
o
n
t
h
e
co
m
p
u
ti
n
g
tech
n
o
l
o
g
y
d
ev
elo
p
m
en
t,
th
e
p
r
ev
io
u
s
l
y
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
ies
f
o
u
n
d
a
f
er
tile
e
n
v
ir
o
n
m
en
t
f
o
r
r
a
p
id
g
r
o
w
t
h
i
n
m
an
y
ap
p
licati
o
n
ar
ea
s
.
P
r
esen
tl
y
,
r
en
e
w
ed
v
ig
o
u
r
s
ar
e
b
ein
g
p
u
t
in
th
e
o
p
tical
ch
ar
ac
ter
r
ec
o
g
n
i
tio
n
r
esear
ch
.
O
n
e
o
f
t
h
es
e
is
r
ec
o
g
n
itio
n
o
f
p
r
in
ted
an
d
h
an
d
w
r
itte
n
d
o
cu
m
en
ts
.
Mo
r
e
s
o
p
h
is
tica
ted
alg
o
r
ith
m
s
w
h
ic
h
u
tili
ze
ad
v
a
n
ce
d
m
et
h
o
d
o
lo
g
ies ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
2
1
–
1
2
8
122
b
ein
g
d
e
v
elo
p
ed
.
I
n
t
h
is
w
o
r
k
t
w
o
m
e
th
o
d
o
lo
g
ies
ar
e
co
m
b
in
ed
to
ac
h
iev
e
an
ef
f
icie
n
t
O
C
R
s
y
s
te
m
w
h
ic
h
w
il
l b
e
ab
le
to
r
ec
o
g
n
ize
o
f
f
-
li
n
e
t
y
p
ed
an
d
h
a
n
d
w
r
itte
n
d
o
cu
m
e
n
t
s
.
T
h
e
r
em
a
in
i
n
g
p
ar
t
o
f
th
is
p
a
p
er
is
ar
r
an
g
ed
a
s
f
o
llo
w
s
:
s
e
ctio
n
2
is
t
h
e
r
ev
ie
w
o
f
r
elate
d
w
o
r
k
s
o
n
OC
R
s
y
s
te
m
s
a
n
d
m
e
th
o
d
o
lo
g
ies.
T
h
e
d
esig
n
m
et
h
o
d
o
lo
g
y
a
n
d
w
o
r
k
i
n
g
p
r
i
n
cip
le
o
f
th
e
p
r
o
p
o
s
e
OC
R
s
y
s
te
m
ar
e
e
x
p
lain
ed
i
n
s
ec
tio
n
3
.
Sectio
n
4
co
n
t
ain
s
t
h
e
test
r
esu
lts
a
n
d
co
n
cl
u
s
io
n
.
2.
RE
L
AT
E
D
WO
RK
OC
R
ca
n
b
e
d
escr
ib
ed
as
o
n
e
o
f
th
e
ap
p
licatio
n
s
o
f
p
atter
n
r
ec
o
g
n
itio
n
.
I
t
w
id
e
ac
ce
p
tab
ilit
y
i
s
d
u
e
to
v
ar
io
u
s
e
x
is
ti
n
g
d
o
cu
m
e
n
t
atio
n
c
h
alle
n
g
e
s
w
h
ic
h
O
C
R
s
y
s
te
m
s
ar
e
ab
le
to
s
o
l
v
e.
O
C
R
s
y
s
te
m
s
ca
n
b
e
class
i
f
ied
ac
co
r
d
in
g
to
t
w
o
cla
s
s
i
f
icatio
n
m
e
tr
ics;
d
a
ta
ac
q
u
i
s
itio
n
m
et
h
o
d
an
d
te
x
t/
la
n
g
u
a
g
e
t
y
p
e.
T
h
e
O
C
R
m
et
h
o
d
o
lo
g
ies
d
ep
en
d
g
r
ea
tl
y
o
n
th
e
t
y
p
e
o
f
th
e
eq
u
ip
m
e
n
t
u
s
ed
f
o
r
d
ata
ac
q
u
is
itio
n
an
d
th
e
k
i
n
d
o
f
tex
t
t
h
e
d
ata
ar
e
r
ep
r
esen
ted
w
it
h
.
O
C
R
d
ata
ac
q
u
i
s
itio
n
s
y
s
te
m
s
m
a
y
b
e
o
n
li
n
e
o
r
o
f
f
-
lin
e
d
ata
ac
q
u
is
itio
n
s
y
s
te
m
.
Of
f
-
lin
e
d
ata
ac
q
u
i
s
itio
n
ca
p
tu
r
es
d
ata
f
r
o
m
p
ap
er
th
r
o
u
g
h
o
p
tical
s
ca
n
n
er
s
o
r
ca
m
er
as
wh
er
ea
s
o
n
-
li
n
e
d
ata
ac
q
u
is
itio
n
s
y
s
te
m
s
u
s
e
t
h
e
d
i
g
itizer
w
h
ich
d
ir
ec
tl
y
ca
p
t
u
r
e
w
r
iti
n
g
w
it
h
th
e
o
r
d
er
o
f
th
e
s
tr
o
k
es,
s
p
ee
d
,
p
en
u
p
an
d
d
o
w
n
i
n
f
o
r
m
ati
o
n
.
O
n
-
lin
e
OC
R
is
ad
ap
ti
v
e
i
n
th
e
s
en
s
e
th
a
t
i
m
m
ed
iate
f
ee
d
b
ac
k
is
g
i
v
en
b
y
t
h
e
w
r
iter
w
h
o
s
e
co
r
r
ec
tio
n
s
ca
n
b
e
u
s
ed
to
f
u
r
t
h
er
tr
ain
t
h
e
r
e
co
g
n
izer
.
A
p
ar
t
f
r
o
m
t
h
i
s
,
it
i
n
v
o
l
v
es
v
er
y
li
ttle
p
r
o
ce
s
s
in
g
.
Op
er
atio
n
s
u
c
h
as
s
m
o
o
t
h
i
n
g
,
s
eg
m
e
n
tatio
n
,
d
e
-
s
la
n
ti
n
g
,
d
e
-
s
k
e
w
i
n
g
an
d
f
ea
tu
r
e
e
x
tr
ac
tio
n
o
p
er
atio
n
s
s
u
ch
as
li
n
e
o
r
ien
t
atio
n
,
lo
o
p
s
co
r
n
er
s
an
d
cu
s
p
d
etec
tio
n
ar
e
ea
s
ier
w
it
h
th
e
p
en
tr
aj
ec
to
r
y
d
ata
th
an
o
n
p
i
x
el
i
m
ag
e
s
.
Ho
w
e
v
er
,
o
n
-
lin
e
OC
R
s
y
s
te
m
r
eq
u
ir
es
a
s
p
ec
ial
p
e
n
an
d
tab
lo
id
w
h
ich
ar
e
n
o
t
co
m
f
o
r
tab
le
an
d
n
atu
r
al
to
u
s
ed
as
p
en
an
d
p
a
p
er
.
A
p
ar
t
f
r
o
m
t
h
is
,
it
ca
n
n
o
t
b
e
u
s
ed
to
co
n
v
er
t
p
r
in
ted
o
r
h
an
d
w
r
itte
n
d
o
cu
m
en
ts
o
n
p
a
p
er
s
(
Ull
m
an
n
1
9
8
7
)
.
Of
f
-
lin
e
OC
R
s
y
s
te
m
d
o
es
r
ec
o
g
n
itio
n
o
n
t
h
e
b
it
s
p
atter
n
f
o
r
b
o
th
p
r
in
ted
an
d
h
a
n
d
w
r
itte
n
tex
t.
T
h
e
b
it
p
atter
n
is
r
ep
r
esen
ted
b
y
a
m
atr
i
x
o
f
p
ix
el
s
.
T
h
is
m
atr
i
x
m
a
y
b
e
o
f
lar
g
e
s
ize.
I
n
o
r
d
er
to
m
a
k
e
t
h
e
p
atter
n
co
n
s
is
ten
t
m
o
s
t
o
f
t
h
e
s
ca
n
n
e
r
s
ar
e
s
tan
d
ar
d
ized
to
1
0
0
to
1
6
0
0
d
o
ts
p
er
in
ch
(
F
u
k
u
n
a
g
a
1
9
9
0
)
.
M
o
s
t
o
f
th
e
r
esear
ch
w
o
r
k
s
ar
e
o
n
o
f
f
-
li
n
e
OC
R
s
y
s
te
m
s
b
ec
a
u
s
e
it
allo
w
s
p
r
ev
io
u
s
l
y
p
r
in
ted
o
r
h
an
d
w
r
itte
n
te
x
ts
to
b
e
p
r
o
ce
s
s
ed
an
d
r
ec
o
g
n
ized
.
So
m
e
o
f
th
e
d
ev
elo
p
ed
o
f
f
-
li
n
e
OC
R
s
y
s
te
m
s
ar
e
p
o
s
tal
ad
d
r
ess
r
ea
d
in
g
,
c
h
eq
u
e
s
o
r
tin
g
,
s
h
o
r
t h
a
n
d
tr
an
s
cr
ip
tio
n
,
r
ea
d
in
g
aid
f
o
r
v
is
u
al
-
i
m
p
ai
r
ed
.
Var
io
u
s
r
esear
ch
w
o
r
k
s
h
ad
b
ee
n
d
o
n
e
o
n
v
ar
iet
y
o
f
m
eth
o
d
o
lo
g
ies
th
at
ar
e
u
s
ed
in
OC
R
s
y
s
te
m
s
.
No
t o
n
l
y
t
h
i
s
,
s
e
v
er
al
w
o
r
k
s
h
ad
b
ee
n
d
o
n
e
o
n
v
ar
io
u
s
ap
p
licatio
n
s
o
f
OC
R
s
u
c
h
as p
late
n
u
m
b
er
r
ec
o
g
n
i
tio
n
,
d
if
f
er
e
n
t
la
n
g
u
a
g
es
te
x
t
r
ec
o
g
n
i
tio
n
.
Fo
r
ex
a
m
p
le,
(
Mo
h
a
m
m
ed
n
.
d
.
)
u
s
ed
te
m
p
late
m
atch
i
n
g
ap
p
r
o
ac
h
to
id
en
ti
f
y
Mu
s
n
ad
c
h
ar
ac
ter
s
wh
ich
is
co
n
s
id
er
ed
as
b
asi
s
f
o
r
A
r
ab
ic
la
n
g
u
a
g
e.
He
ex
tr
ac
ted
an
d
n
o
r
m
alize
d
Mu
s
n
ad
ch
ar
ac
ter
s
f
r
o
m
in
p
u
t
i
m
ag
e.
T
h
e
e
x
tr
ac
ted
ch
ar
ac
t
er
w
as
co
m
p
ar
ed
to
ea
ch
te
m
p
late
in
th
e
d
atab
ase
to
f
in
d
t
h
e
clo
s
est r
ep
r
esen
ta
ti
o
n
o
f
th
e
i
n
p
u
t c
h
ar
ac
ter
u
s
in
g
2
-
D
co
r
r
elatio
n
co
ef
f
ic
ien
t a
p
p
r
o
ac
h
.
I
n
(
H
u
an
g
,
L
ea
r
n
ed
-
Miller
an
d
Mc
C
all
u
m
n
.
d
.
)
cr
y
p
to
g
r
a
m
al
g
o
r
i
t
h
m
w
as
e
n
g
a
g
ed
to
i
m
p
le
m
en
t
OC
R
s
y
s
te
m
.
C
r
y
p
to
g
r
a
m
al
g
o
r
ith
m
g
r
o
u
p
s
s
i
m
ilar
ch
ar
ac
t
er
s
in
t
h
e
d
o
cu
m
en
t
a
n
d
s
o
l
v
es
a
cr
y
p
to
g
r
a
m
to
ass
i
g
n
lab
els
to
clu
s
ter
s
o
f
c
h
ar
ac
ter
s
.
W
ith
t
h
i
s
m
e
th
o
d
,
n
o
ch
ar
ac
ter
m
o
d
el
i
s
n
ee
d
ed
an
d
ca
n
ar
b
itra
r
il
y
h
an
d
le
a
n
y
f
o
n
t
s
t
y
le
s
.
Ho
w
e
v
er
,
it
w
a
s
d
is
co
v
er
ed
th
at
t
h
i
s
ap
p
r
o
ac
h
ca
n
n
o
t
h
an
d
le
n
u
m
er
als,
p
u
n
ct
u
atio
n
m
ar
k
s
an
d
u
p
p
er
ca
s
e.
In
(
Ka
m
alj
it
a
n
d
B
alp
r
ee
t
Ma
y
2
0
1
3
)
,
a
m
o
r
p
h
o
lo
g
ical
a
p
p
r
o
ac
h
w
as
ad
o
p
ted
to
id
en
tify
p
late
n
u
m
b
er
.
T
h
eir
i
m
p
le
m
e
n
tat
io
n
w
as a
b
le
to
id
en
ti
f
y
th
e
f
ir
s
t c
h
ar
ac
ter
o
f
th
e
p
late
n
u
m
b
er
.
3.
O
CR
M
E
T
H
O
DO
L
O
G
Y
OC
R
is
t
h
e
s
cie
n
ce
th
at
en
t
ails
th
e
d
escr
ip
tio
n
o
r
class
if
icatio
n
o
f
ch
ar
ac
ter
m
ea
s
u
r
e
m
en
ts
th
a
t
u
s
u
all
y
b
ased
o
n
s
o
m
e
m
o
d
els.
OC
R
is
o
n
e
o
f
t
h
e
ca
te
g
o
r
ies
o
f
i
m
a
g
e
r
ec
o
g
n
i
tio
n
.
T
h
er
e
ar
e
v
ar
io
u
s
ch
ar
ac
ter
r
ec
o
g
n
itio
n
m
et
h
o
d
s
u
s
ed
in
d
ev
elo
p
in
g
ch
ar
ac
ter
r
ec
o
g
n
izer
.
T
h
ese
m
e
th
o
d
s
a
r
e:
n
eu
r
al
n
et
w
o
r
k
,
m
o
m
e
n
t
b
ased
ap
p
r
o
ac
h
,
co
n
to
u
r
b
ased
ap
p
r
o
ac
h
,
tem
p
lat
e
m
atc
h
in
g
a
n
d
m
o
r
p
h
o
lo
g
ic
al
ap
p
r
o
ac
h
.
I
n
th
is
w
o
r
k
te
m
p
late
m
atc
h
in
g
an
d
m
o
r
p
h
o
lo
g
ical
tec
h
n
iq
u
es a
r
e
u
s
ed
to
r
ec
o
g
n
ize
E
n
g
l
is
h
tex
t
s
.
T
em
p
late
m
atc
h
i
n
g
r
ef
er
s
to
th
e
p
r
o
ce
s
s
o
f
d
etec
tin
g
a
n
o
b
j
ec
t
h
av
in
g
a
ce
r
tain
s
ize,
s
h
ap
e
an
d
o
r
ien
tatio
n
in
an
i
m
ag
e
b
y
a
p
p
ly
i
n
g
a
n
o
p
er
ato
r
co
n
tain
i
n
g
p
o
s
iti
v
e
w
ei
g
h
ts
in
a
r
e
g
io
n
r
ese
m
b
li
n
g
th
e
o
b
j
ec
ts
to
b
e
d
etec
ted
an
d
co
n
tai
n
in
g
n
e
g
ati
v
e
w
ei
g
h
t
s
i
n
a
r
eg
io
n
s
u
r
r
o
u
n
d
in
g
t
h
e
p
o
s
i
tiv
e
w
ei
g
h
t
(
R
.
M.
K
Sin
h
a
1
9
9
7
)
.
Mo
r
p
h
o
lo
g
y
as
d
er
iv
ed
f
r
o
m
b
io
lo
g
y
is
a
b
r
an
ch
o
f
b
io
lo
g
y
w
h
ich
d
ea
ls
w
it
h
t
h
e
f
o
r
m
a
n
d
an
i
m
als
a
n
d
p
lan
t
s
.
I
t
is
ad
o
p
ted
in
th
i
s
co
n
te
x
t
a
s
a
to
o
l
f
o
r
ex
tr
ac
tin
g
i
m
a
g
e
co
m
p
o
n
e
n
t
s
th
at
ar
e
u
s
e
f
u
l
i
n
th
e
r
ep
r
esen
ta
tio
n
a
n
d
d
escr
i
p
tio
n
o
f
t
h
e
r
e
g
io
n
s
h
ap
e.
T
h
er
e
ar
e
s
ev
er
al
p
r
o
ce
d
u
r
al
s
tep
s
e
n
g
a
g
ed
i
n
ac
h
iev
in
g
m
o
r
p
h
o
lo
g
ical
tec
h
n
iq
u
e
s
.
T
h
ese
in
cl
u
d
e
f
ilter
in
g
,
th
in
n
i
n
g
,
p
r
u
n
i
n
g
,
er
o
s
io
n
an
d
d
ilatio
n
,
o
p
en
in
g
an
d
clo
s
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
tica
l Ch
a
r
a
cter R
ec
o
g
n
itio
n
o
f
Off
-
Lin
e
Typ
ed
a
n
d
Ha
n
d
w
r
itten
…
(
Ola
ka
n
mi
Ola
d
a
yo
O
)
123
3
.
1
.
T
E
M
P
L
AT
E
M
AT
CH
I
NG
AND
M
O
RP
H
O
L
O
G
I
C
AL
T
E
CH
NI
Q
U
E
T
em
p
late
m
atc
h
i
n
g
an
d
m
o
r
p
h
o
lo
g
ical
tech
n
iq
u
es
a
s
s
tated
ea
r
lier
,
ar
e
OC
R
r
ec
o
g
n
itio
n
t
ec
h
n
iq
u
es
.
T
h
ese
alg
o
r
ith
m
s
in
v
o
lv
e
f
ea
t
u
r
es
ex
tr
ac
tio
n
an
d
class
i
f
ier
.
I
n
te
m
p
late
m
atc
h
i
n
g
i
m
a
g
e
p
ix
els
ar
e
u
s
ed
as
th
e
f
ea
t
u
r
es
b
ein
g
ex
tr
ac
ted
f
r
o
m
b
o
th
th
e
i
n
p
u
t
c
h
ar
ac
ter
an
d
t
h
e
clas
s
i
f
ied
ch
ar
ac
ter
s
.
T
h
e
class
i
f
ier
co
m
p
ar
es
th
e
i
n
p
u
t
ch
ar
ac
ter
f
ea
t
u
r
es
w
i
th
a
s
et
o
f
c
h
ar
ac
ter
te
m
p
la
te
i
n
t
h
e
c
h
ar
ac
ter
clas
s
.
I
n
th
is
c
o
n
tex
t
th
e
ch
ar
ac
ter
class
co
n
ta
in
s
n
u
m
er
als,
u
p
p
er
an
d
lo
w
er
ca
s
es
o
f
E
n
g
li
s
h
ch
ar
ac
ter
s
a
s
s
h
o
w
n
i
n
f
ig
1
an
d
f
ig
.
2
.
T
h
e
ab
s
o
lu
te
v
al
u
e
o
f
th
e
cla
s
s
i
f
ier
p
r
o
ce
d
u
r
e
w
h
ic
h
is
t
h
e
co
r
r
elatio
n
co
ef
f
icie
n
t
b
et
w
ee
n
t
h
e
i
n
p
u
t
c
h
ar
ac
ter
an
d
th
e
co
n
s
id
er
ed
ch
ar
ac
ter
tem
p
late
is
u
s
ed
to
m
o
r
p
h
o
l
o
g
icall
y
d
eter
m
i
n
e
th
e
te
m
p
late
w
ith
a
clo
s
e
s
t
co
r
r
elatio
n
m
atch
.
Fo
r
m
all
y
,
(
1
)
{
(
2
)
T
h
e
tr
an
s
f
o
r
m
a
tio
n
f
u
n
ctio
n
o
n
ch
ar
ac
ter
is
:
E
n
g
l
is
h
ch
ar
ac
ter
s
ar
e
class
if
i
ed
in
to
n
u
m
er
als,
u
p
p
er
an
d
lo
w
er
ca
s
e
s
.
I
n
th
e
c
h
ar
ac
ter
cla
s
s
s
o
m
e
o
f
th
e
ch
ar
ac
ter
s
w
er
e
w
r
itte
n
in
d
if
f
er
en
t
w
a
y
s
i
n
o
r
d
er
to
ac
co
m
m
o
d
ate
d
if
f
er
en
t
w
a
y
s
o
f
w
r
iti
n
g
.
T
h
is
OC
R
s
y
s
te
m
,
as
s
h
o
w
n
in
f
i
g
u
r
e
3
,
is
g
r
o
u
p
ed
in
to
th
r
ee
p
r
o
ce
s
s
i
n
g
le
v
els
w
h
ic
h
ar
e
lo
w
le
v
el
p
r
o
ce
s
s
in
g
,
in
ter
m
ed
iate
lev
e
l
an
d
h
i
g
h
le
v
el
p
r
o
ce
s
s
i
n
g
.
T
h
ese
ar
e
i
m
p
le
m
e
n
ted
u
s
i
n
g
6
4
-
b
it
Ma
tlab
v
er
s
io
n
7
.
8
.
0
.
3
8
7
an
d
th
e
i
n
p
u
t te
x
ts
ar
e
b
u
il
t
w
i
th
p
ain
t b
r
u
s
h
a
n
d
tex
t.
3
.
1
.
1
.
L
O
W
L
E
V
E
L
P
RO
C
E
SS
I
N
G
As
s
h
o
w
n
in
t
h
e
f
i
g
u
r
e
3
,
lo
w
lev
el
p
r
o
ce
s
s
i
n
g
in
v
o
l
v
es
i
m
a
g
e
ac
q
u
i
s
itio
n
an
d
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
t
h
e
ac
q
u
ir
ed
i
m
a
g
es.
I
m
a
g
e
ac
q
u
is
itio
n
s
ta
g
e
ac
q
u
ir
es
i
m
ag
e
o
f
t
h
e
d
o
cu
m
e
n
t
o
r
c
h
ar
ac
ter
s
to
b
e
r
ec
o
g
n
ized
.
Mo
s
t
ti
m
e
i
n
p
u
t
c
h
ar
ac
ter
i
m
a
g
e
is
o
f
f
i
n
ite
r
eso
l
u
tio
n
w
h
ic
h
u
lti
m
atel
y
a
f
f
ec
t
s
th
e
q
u
al
it
y
o
f
i
ts
tr
an
s
f
o
r
m
atio
n
,
th
er
ef
o
r
e,
p
r
e
-
p
r
o
ce
s
s
i
n
g
b
ec
o
m
es
n
ec
es
s
ar
y
.
T
h
e
p
r
e
-
p
r
o
ce
s
s
in
g
s
ta
g
e
in
cl
u
d
es
co
lo
u
r
n
o
r
m
aliza
t
io
n
,
s
ca
li
n
g
f
i
lter
i
n
g
a
n
d
th
i
n
n
i
n
g
.
C
o
lo
u
r
n
o
r
m
aliza
tio
n
is
u
s
ed
to
ch
a
n
g
e
in
p
u
t
ch
ar
ac
ter
f
o
r
eg
r
o
u
n
d
co
lo
u
r
to
b
lack
an
d
b
ac
k
g
r
o
u
n
d
co
lo
u
r
to
w
h
ite.
T
o
ac
h
iev
e
th
i
s
,
h
i
s
to
g
r
a
m
te
ch
n
iq
u
e
w
as
u
s
ed
.
T
h
e
in
p
u
t
ch
ar
ac
ter
w
a
s
u
s
ed
to
f
o
r
m
h
is
to
g
r
a
m
o
f
s
i
n
g
le
cl
ass
w
h
ich
w
a
s
g
r
o
u
p
ed
in
to
in
ter
v
al
s
.
Ov
er
ea
c
h
o
f
t
h
ese
i
n
ter
v
als
a
v
er
tical
r
e
ctan
g
le
i
s
d
r
a
w
n
w
it
h
it
s
ar
ea
p
r
o
p
o
r
tio
n
al
to
t
h
e
n
u
m
b
er
o
f
p
o
in
t
f
a
lli
n
g
in
to
th
at
in
ter
v
al.
T
h
e
lu
m
i
n
a
n
ce
o
f
th
e
i
m
a
g
e
w
as
d
eter
m
i
n
ed
u
s
i
n
g
eq
u
atio
n
3
.
Fig
u
r
e
2
an
d
3
d
ep
ict
th
e
in
p
u
t
i
m
a
g
e
b
ef
o
r
e
an
d
af
ter
n
o
r
m
al
izatio
n
r
esp
ec
tiv
e
l
y
.
No
r
m
a
lizatio
n
al
g
o
r
ith
m
:
1.
Select
th
e
r
ele
v
an
t p
ar
t o
f
t
h
e
ch
ar
ac
ter
.
2.
Dete
r
m
i
n
e
th
e
t
h
r
es
h
o
ld
f
o
r
th
e
co
lo
u
r
n
o
r
m
a
lizatio
n
3.
P
r
o
ce
s
s
th
e
i
m
a
g
e
f
r
o
m
to
p
co
r
n
er
lin
e
b
y
li
n
e
4.
Sto
r
e
th
e
R
,
G,
B
v
al
u
e
o
f
ea
ch
p
ix
el
5.
Dete
r
m
i
n
e
u
s
in
g
eq
u
atio
n
1
6.
I
f
<
th
r
es
h
o
ld
v
al
u
e
th
e
n
t
u
r
n
t
h
e
p
ix
el
b
lack
o
t
h
er
w
is
e
w
h
ite
.
7.
R
ep
ea
t f
o
r
th
e
w
h
o
le
in
p
u
t i
m
ag
e
T
h
e
i
m
ag
e
s
ca
li
n
g
s
ca
les
t
h
e
i
n
p
u
t
c
h
ar
ac
ter
i
m
a
g
e
u
p
o
r
d
o
w
n
d
ep
en
d
in
g
o
n
t
h
e
o
r
ig
i
n
al
s
ize.
T
h
is
w
a
s
d
o
n
e
to
r
ed
u
ce
th
e
r
ec
o
g
n
itio
n
ti
m
e
an
d
er
r
o
r
r
ate
as
l
ar
g
e
ch
ar
ac
ter
i
m
ag
e
s
w
o
u
ld
tak
e
lo
n
g
er
ti
m
e
to
p
r
o
ce
s
s
w
h
ile
s
m
all
i
m
ag
e
m
a
y
b
e
d
i
f
f
ic
u
lt
to
r
ec
o
g
n
ize.
Af
ter
s
ca
li
n
g
th
e
ch
ar
ac
ter
b
ec
o
m
e
s
b
lo
ck
y
a
n
d
h
en
ce
t
h
e
s
m
o
o
th
e
n
i
n
g
f
ilter
i
n
g
s
tag
e
r
e
m
o
v
e
s
th
e
s
p
i
k
e
e
d
g
es.
T
h
is
s
ta
g
e
co
n
tai
n
s
s
m
o
o
th
en
i
n
g
f
i
lter
,
lo
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
2
1
–
1
2
8
124
p
ass
f
i
lter
.
T
h
ese
f
i
lter
s
ar
e
u
s
ed
to
r
ed
u
ce
b
lu
r
r
in
g
a
n
d
n
o
i
s
e.
A
l
s
o
,
i
m
p
le
m
en
ted
in
t
h
e
lo
w
le
v
el
p
r
o
ce
s
s
i
n
g
is
th
e
th
i
n
n
i
n
g
w
h
ic
h
co
n
v
er
t
s
an
y
elo
n
g
ated
p
ar
ts
o
r
s
tr
ip
s
in
t
h
e
i
m
ag
e
r
e
g
ar
d
less
o
f
th
eir
b
its
in
to
n
ar
r
o
w
s
tr
ip
s
th
at
ar
e
o
n
l
y
ab
o
u
t o
n
e
p
ix
el
w
id
e.
3
.
1
.
2
.
I
NT
E
RM
E
DIA
T
E
L
E
VE
L
P
RO
C
E
S
SI
N
G
I
n
ter
m
ed
iate
L
e
v
el
P
r
o
ce
s
s
i
n
g
(
I
L
P
)
i
n
t
h
e
i
n
f
i
g
u
r
e
3
i
n
v
o
lv
es
i
m
a
g
e
r
o
tatio
n
an
d
s
eg
m
en
tatio
n
.
So
m
eti
m
es
in
p
u
t c
h
ar
ac
ter
i
m
ag
e
m
a
y
n
o
t b
e
p
r
o
p
er
ly
ali
g
n
ed
in
a
n
g
u
lar
f
as
h
io
n
w
it
h
r
es
p
ec
t to
th
e
c
h
ar
ac
ter
te
m
p
late
s
e
t.
A
n
i
n
s
tan
ce
o
f
t
h
is
w
i
ll
b
e
co
r
r
ec
ted
b
y
r
ea
li
g
n
th
e
i
m
a
g
e
O
C
R
.
Seg
m
e
n
tati
o
n
w
h
ic
h
f
o
r
m
s
th
e
co
r
e
o
f
I
L
p
r
o
ce
s
s
in
g
s
ta
g
e
p
ar
titi
o
n
s
t
h
e
in
p
u
t
i
m
ag
e
i
n
t
o
its
co
n
s
tit
u
e
n
t
ch
ar
ac
ter
s
.
S
h
o
w
n
b
elo
w
is
t
h
e
alg
o
r
ith
m
u
s
ed
f
o
r
s
e
g
m
e
n
tat
i
o
n
Seg
m
en
tatio
n
al
g
o
r
ith
m
:
1.
Scan
t
h
e
i
m
a
g
e
f
r
o
m
r
ig
h
t to
l
ef
t r
o
w
w
i
s
e
2.
A
d
d
an
d
co
u
n
t a
ll th
e
x
co
o
r
d
in
ates
3.
Dete
r
m
i
n
e
th
e
x
-
co
o
r
d
in
ate
o
f
th
e
ce
n
tr
o
id
u
s
i
n
g
w
h
er
e
n
is
th
e
to
tal
n
u
m
b
er
o
f
th
e
ce
n
tr
o
id
.
4.
Dete
r
m
i
n
e
t
h
e
y
-
co
o
r
d
in
ate
o
f
th
e
ce
n
tr
o
id
u
s
i
n
g
w
h
er
e
n
is
th
e
to
tal
n
u
m
b
er
o
f
th
e
ce
n
tr
o
id
.
3
.
1
.
3
.
RE
P
RE
S
E
N
T
AT
I
O
N
AND
DE
SCRI
P
T
I
O
N
R
ep
r
esen
tat
io
n
m
ap
s
t
h
e
s
c
an
n
ed
c
h
ar
ac
ter
i
m
a
g
e
to
f
o
r
m
s
u
i
tab
le
f
o
r
s
u
b
s
eq
u
e
n
t
co
m
p
u
ter
p
r
o
ce
s
s
in
g
w
h
ile
d
escr
ip
tio
n
i
s
a
f
ea
t
u
r
e
s
elec
tio
n
w
h
ic
h
d
ea
ls
w
it
h
ex
tr
ac
ti
n
g
f
ea
t
u
r
es
i
n
s
o
m
e
q
u
a
n
titati
v
e
m
an
n
er
o
r
d
if
f
er
en
tiati
n
g
o
n
e
class
o
f
o
b
j
ec
ts
f
r
o
m
a
n
o
th
er
.
T
h
is
w
as
ac
h
ie
v
ed
u
s
in
g
i
n
ter
n
al
c
h
ar
ac
ter
is
tic
s
,
th
at
is
,
t
h
e
p
ix
el
s
co
m
p
r
o
m
i
s
i
n
g
t
h
e
r
eg
io
n
.
3
.
1
.
4
.
K
NO
WL
E
D
G
E
B
AS
E
T
h
e
k
n
o
w
led
g
e
b
ase
co
n
tain
s
th
e
n
u
m
b
er
s
,
p
u
n
ct
u
atio
n
,
u
p
p
er
an
d
lo
w
er
ca
s
es
o
f
E
n
g
lis
h
alp
h
ab
ets
as s
ho
w
n
i
n
F
ig
u
r
e
4
a
-
4
b
.
I
t is
b
asicall
y
a
d
atab
ase
o
f
t
y
p
ed
an
d
h
a
n
d
w
r
itte
n
E
n
g
lis
h
alp
h
a
b
ets,
n
u
m
b
er
s
,
an
d
p
u
n
ct
u
atio
n
s
.
I
n
d
iv
id
u
al
ch
ar
a
cter
i
m
ag
e
s
in
t
h
e
k
n
o
w
led
g
e
b
ase
ar
e
u
s
ed
to
g
en
er
ate
th
e
co
r
r
elatio
n
v
alu
es
f
o
r
th
e
in
p
u
t c
h
ar
ac
ter
i
m
a
g
e
an
d
o
u
tp
u
t c
h
a
r
ac
ter
tex
t.
Fig
u
r
e
1
.
Sch
e
m
atic
o
f
t
h
e
o
f
f
-
li
n
e
Op
tical
C
h
ar
ac
ter
R
ea
d
er
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
tica
l Ch
a
r
a
cter R
ec
o
g
n
itio
n
o
f
Off
-
Lin
e
Typ
ed
a
n
d
Ha
n
d
w
r
itten
…
(
Ola
ka
n
mi
Ola
d
a
yo
O
)
125
Fig
u
r
e
2
a.
I
n
p
u
t i
m
a
g
e
c
h
ar
ac
t
er
b
ef
o
r
e
n
o
r
m
aliza
tio
n
Fig
u
r
e
2
b
.
I
n
p
u
t i
m
a
g
e
ch
ar
ac
ter
af
ter
n
o
r
m
aliza
tio
n
Fig
u
r
e
3
a.
OC
R
h
an
d
w
r
itte
n
E
n
g
l
is
h
ch
ar
ac
ter
k
n
o
w
led
g
e
b
a
s
e
Fig
u
r
e
3
b
.
OC
R
t
y
p
ed
E
n
g
li
s
h
ch
ar
ac
ter
k
n
o
w
led
g
e
b
ase.
4.
T
E
ST
AN
D
CO
NCLU
SI
O
N
T
h
e
OC
R
s
y
s
te
m
w
a
s
s
u
b
j
e
cted
to
d
if
f
er
en
t
s
et
o
f
i
n
p
u
t
tex
t
i
m
ag
e
s
in
o
r
d
er
to
d
et
er
m
in
e
i
t
s
r
ec
o
g
n
itio
n
ef
f
icie
n
c
y
.
T
h
e
test
w
a
s
ca
r
r
ied
o
u
t
o
n
b
o
th
ty
p
ed
an
d
h
an
d
w
r
i
tten
i
n
p
u
t
te
x
t
s
.
T
h
e
in
p
u
t
i
m
a
g
es
as
s
h
o
w
n
i
n
F
ig
u
r
e
4
a,
5
a
an
d
6
a
ar
e
d
if
f
er
en
t
s
et
o
f
in
p
u
t
te
x
ts
cr
ea
ted
u
s
i
n
g
th
e
p
ai
n
t
b
r
u
s
h
a
s
p
en
a
n
d
p
ain
t
tex
t
w
h
ic
h
r
ep
r
esen
t
h
an
d
w
r
itt
en
a
n
d
t
y
p
ed
E
n
g
l
is
h
te
x
ts
r
es
p
ec
tiv
el
y
.
T
h
e
o
u
tp
u
t
s
o
f
t
h
e
OC
R
s
y
s
te
m
f
o
r
t
h
e
in
p
u
t
te
x
t
i
m
a
g
e
in
f
i
g
4
a,
5
a
an
d
6
a
ar
e
s
h
o
w
n
in
f
i
g
u
r
e
4
b
,
5
b
an
d
6
b
r
esp
ec
tiv
el
y
.
T
h
e
test
r
es
u
lt
s
w
er
e
q
u
ite
i
m
p
r
es
s
i
v
e.
I
t
w
as
o
b
s
er
v
ed
f
r
o
m
th
e
O
C
R
o
u
tp
u
t
in
f
i
g
.
4
b
th
at
c
h
ar
ac
ter
G
w
as
t
h
e
o
n
l
y
c
h
ar
ac
ter
n
o
t
r
ec
o
g
n
ized
.
T
h
is
s
h
o
w
s
a
n
ac
cu
r
ac
y
o
f
9
9
%
f
o
r
t
h
e
t
y
p
ed
tex
t
w
it
h
e
x
ec
u
tio
n
ti
m
e
o
f
1
1
2
ch
ar
/s
ec
r
ec
o
g
n
itio
n
r
ate.
Als
o
,
f
o
r
in
p
u
t
te
x
t
in
f
ig
.
5
a
it
w
a
s
o
b
s
er
v
ed
f
r
o
m
th
e
OC
R
o
u
tp
u
t
in
f
ig
.
5
b
th
at
j
u
s
t
a
f
e
w
n
u
m
b
er
o
f
c
h
ar
ac
ter
s
w
er
e
n
o
t
p
r
o
p
er
ly
r
ec
o
g
n
ized
(
I
,
G,
co
mma
,
s
p
a
ce
)
.
T
h
e
OC
R
s
y
s
te
m
o
u
tp
u
t
i
n
f
i
g
.
6
b
w
h
ic
h
r
ep
r
esen
t
s
OC
R
o
u
tp
u
t
f
o
r
t
h
e
h
a
n
d
w
r
it
ten
in
p
u
t
tex
t
in
f
ig
.
6
a,
r
ec
o
r
d
ed
an
ac
cu
r
ac
y
o
f
9
0
%.
I
t
w
a
s
o
b
s
er
v
ed
th
at
t
h
e
OC
R
s
y
s
te
m
’
s
p
er
f
o
r
m
a
n
ce
u
n
it
is
in
d
ep
en
d
en
t
an
d
co
n
s
ta
n
t
f
o
r
h
a
n
d
w
r
i
tten
a
n
d
t
y
p
ed
te
x
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
2
1
–
1
2
8
126
i
m
a
g
es
o
f
d
i
f
f
er
e
n
t
s
ize.
A
l
s
o
,
th
e
r
e
s
u
l
t
s
h
o
w
ed
t
h
at
t
h
e
d
ev
elo
p
ed
OC
R
s
y
s
te
m
m
o
r
e
e
f
f
e
ctiv
el
y
r
ec
o
g
n
ized
n
u
m
er
als t
h
a
n
alp
h
ab
ets.
Fig
u
r
e
4
a.
OC
R
i
n
p
u
t o
f
a
s
ca
n
n
ed
i
m
ag
e
te
x
t d
o
cu
m
e
n
t.
Fig
u
r
e
4
b
.
OC
R
o
u
tp
u
t o
f
t
h
e
s
ca
n
n
ed
i
m
a
g
e
te
x
t d
o
cu
m
e
n
t
in
5
a.
Fig
u
r
e
5
a.
OC
R
i
n
p
u
t o
f
a
s
ca
n
n
ed
i
m
ag
e
te
x
t d
o
cu
m
e
n
t
Fig
u
r
e
5
b
.
OC
R
o
u
tp
u
t o
f
t
h
e
s
ca
n
n
ed
i
m
a
g
e
te
x
t d
o
cu
m
e
n
t
in
5
a
I
N
P
U
T
I
M
A
G
E
W
I
T
H
N
O
I
S
E
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
Op
tica
l Ch
a
r
a
cter R
ec
o
g
n
itio
n
o
f
Off
-
Lin
e
Typ
ed
a
n
d
Ha
n
d
w
r
itten
…
(
Ola
ka
n
mi
Ola
d
a
yo
O
)
127
Fig
u
r
e
6
a.
OC
R
i
n
p
u
t o
f
a
s
ca
n
n
ed
h
an
d
w
r
itte
n
i
m
ag
e
te
x
t d
o
cu
m
e
n
t.
Fig
u
r
e
6
b
.
OC
R
o
u
tp
u
t o
f
a
s
c
an
n
ed
h
a
n
d
w
r
itte
n
i
m
ag
e
te
x
t
d
o
cu
m
en
t.
RE
F
E
R
E
NC
E
S
[1
]
A
.
Ja
in
,
a
n
d
K.
Ka
ru
.
"
P
a
g
e
S
e
g
m
e
n
tatio
n
Us
in
g
T
e
x
tu
re
A
n
a
l
y
sis,
P
a
tt
e
r
n
Re
c
o
g
n
it
i
o
n
.
"
2
9
(
2
0
0
6
):
7
4
3
-
7
7
0
[2
]
Du
e
ire L
in
s,
R,
G P
e
re
ira S
il
v
a
,
a
n
d
A
.
R
G
o
m
e
s
e
S
il
v
a
.
"
Asse
ss
in
g
a
n
d
Imp
ro
v
in
g
th
e
Qu
a
li
ty o
f
Do
c
u
me
n
t
Ima
g
e
s
Acq
u
ire
d
wit
h
P
o
rta
b
le
Dig
it
a
l
C
a
me
ra
s."
ICDAR
2
0
0
7
.
Nin
th
In
t
e
rn
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
(V
o
lu
m
e
:2
).
Do
c
u
m
e
n
t
A
n
a
l
y
si
s an
d
Re
c
o
g
n
it
i
o
n
,
2
0
0
7
.
5
6
9
-
5
7
3
[3
]
F
u
k
u
n
a
g
a
,
K.
I
n
tro
d
u
c
ti
o
n
t
o
S
ta
t
isti
c
a
l
P
a
tt
e
rn
Rec
o
g
n
i
ti
o
n
.
1
9
9
0
[4
]
Hu
a
n
g
,
G
a
r
y
,
Eri
k
L
e
a
rn
e
d
-
M
il
ler,
a
n
d
A
n
d
re
w
M
c
Ca
ll
u
m
.
"
Cr
y
to
g
ra
m
De
c
o
d
in
g
f
o
r
Op
ti
c
a
l
Ch
a
ra
c
ter
Re
c
o
g
n
it
io
n
.
"
[5
]
Hu
a
n
g
,
Ka
izh
u
,
Ju
n
S
u
n
,
Y.
Ho
tt
a
,
a
n
d
K.
F
u
ji
m
o
to
.
"
A
n
S
VM
-
Ba
se
d
Hig
h
-
a
c
c
u
r
a
te
Rec
o
g
n
it
i
o
n
Ap
p
ro
a
c
h
f
o
r
Ha
n
d
writ
ten
Nu
me
ra
ls
b
y
Us
in
g
Diff
e
re
n
c
e
Fea
tu
re
s."
ICDAR
2
0
0
7
,
Nin
t
h
In
tern
a
t
io
n
a
l
Co
n
f
e
re
n
c
e
o
n
Do
c
u
m
e
n
t
A
n
a
l
y
si
s an
d
Re
c
o
g
n
it
i
o
n
.
5
8
9
-
5
9
3
[6
]
Ka
m
a
lj
it
,
Ka
u
r,
a
n
d
Ka
u
r
Ba
lp
re
e
t.
"
Ch
a
ra
c
ter
Re
c
o
g
n
it
io
n
o
f
Hi
g
h
S
e
c
u
rit
y
Nu
m
b
e
r
P
late
s
Us
in
g
M
o
rp
h
o
lo
g
ica
l
Op
e
ra
to
r.
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
ri
n
g
T
e
c
h
n
o
lo
g
y
(
IJ
CS
ET
)
4
,
n
o
.
5
(M
a
y
2
0
1
3
)
[7
]
Ku
n
d
u
,
A
.
,
M
c
L
e
a
n
M
IT
RE
Co
rp
.
,
T
.
Hin
e
s,
J.
P
h
il
li
p
s,
a
n
d
B.
D
.
Hu
y
c
k
.
"
Ara
b
ic
Ha
n
d
writ
in
g
Re
c
o
g
n
i
ti
o
n
Us
in
g
Va
ria
b
le
Du
ra
ti
o
n
HM
M
.
"
ICDAR
2
0
0
7
.
Nin
t
h
In
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
.
Do
c
u
m
e
n
t
A
n
a
l
y
sis
a
n
d
Re
c
o
g
n
it
io
n
,
2
0
0
7
[8
]
L
in
,
S
h
a
n
g
-
Hu
n
g
.
"
A
n
In
tro
d
u
c
ti
o
n
to
F
a
c
e
Re
c
o
g
n
it
io
n
T
e
c
h
n
o
lo
g
y
.
"
In
fo
rm
in
g
S
c
ien
c
e
sp
e
c
ia
l
issu
e
o
n
M
u
lt
ime
d
ia
I
n
f
o
rm
in
g
T
e
c
h
n
o
l
o
g
i
e
s
V
o
l
.
3
,
n
o
.
1
(
2
0
0
0
)
[9
]
M
o
h
a
m
m
e
d
,
A
li
Q.
"
Te
m
p
late
M
a
tch
in
g
M
e
th
o
d
f
o
r
Re
c
o
g
n
it
io
n
M
u
sn
a
d
Ch
a
ra
c
ters
b
a
se
d
o
n
Co
rre
lati
o
n
A
n
a
l
y
si
s."
[1
0
]
Na
d
e
e
m
,
Da
n
ish
,
a
n
d
S
a
leh
a
Riz
v
i.
"
Ch
a
ra
c
ter Rec
o
g
n
it
io
n
Us
in
g
T
e
m
p
late
M
a
tch
in
g
.
"
M
.
sc
P
r
o
jec
t
[1
1
]
Na
w
a
z
,
T
a
b
a
ss
a
m
,
S
y
e
d
Am
m
a
r
Ha
ss
a
n
,
S
h
a
h
Na
q
v
i,
Ha
b
ib
u
r
Re
h
m
a
n
,
a
n
d
A
n
o
sh
ia
F
a
iz.
"
Op
ti
c
a
l
Ch
a
ra
c
ter
Re
c
o
g
n
i
ti
o
n
S
y
ste
m
f
o
r
Urd
u
(Na
sk
h
F
o
n
t
)
Us
in
g
P
a
tt
e
rn
M
a
tch
i
n
g
T
e
c
h
n
iq
u
e
.
"
[1
2
]
P
ra
tap
,
R.
L
.
,
L
.
S
a
t
y
a
p
ra
sa
d
,
a
n
d
A
.
S
a
str
y
.
"
M
id
d
le
Z
o
n
e
Co
m
p
o
n
e
n
t
Extra
c
ti
o
n
a
n
d
Rec
o
g
n
it
i
o
n
o
f
T
e
lu
g
u
.
"
ICDAR
2
0
0
7
,
Nin
th
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
n
Do
c
u
m
e
n
t
Im
a
g
e
Do
c
u
m
e
n
t
A
n
a
l
y
sis a
n
d
Re
c
o
g
n
it
io
n
[1
3
]
Qin
g
,
Ch
e
n
,
a
n
d
P
e
tri
u
l
M
Em
i.
"
Op
ti
c
a
l
Ch
a
ra
c
ter Rec
o
g
n
it
io
n
f
o
r
M
o
d
e
l
-
b
a
se
d
Ob
jec
t
Re
c
o
g
n
it
io
n
A
p
p
li
c
a
ti
o
n
s."
[1
4
]
R.
M
.
K
S
i
n
h
a
,
e
t.
a
l.
"
Hy
b
rid
Co
n
tex
tu
a
l
T
e
x
t
Re
c
o
g
n
it
io
n
w
it
h
S
tri
n
g
m
a
tch
in
g
.
"
Pa
tt
e
rn
An
a
lys
i
s
a
n
d
M
a
c
h
i
n
e
In
telli
g
e
n
c
e
(
PA
M
I).
1
9
9
7
.
9
1
5
-
9
2
5
[1
5
]
S
a
q
ib
,
Ra
sh
e
e
d
,
Na
e
e
m
As
a
d
,
a
n
d
Ish
a
q
Om
e
r
.
"
Au
to
ma
ted
Nu
mb
e
r
Pl
a
te
Rec
o
g
n
it
i
o
n
Us
in
g
Ho
u
g
h
L
in
e
s
a
n
d
T
e
mp
la
te M
a
tch
in
g
.
"
P
ro
c
e
e
d
i
n
g
s o
f
W
o
rld
Co
n
g
re
ss
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter S
c
ie
n
c
e
W
CECS
.
2
0
1
2
[1
6
]
S
u
n
,
Ju
n
,
Ka
izh
u
Hu
a
n
g
,
Y.
Ho
tt
a
,
a
n
d
K.
F
u
j
im
o
to
.
"
De
g
r
a
d
e
d
C
h
a
ra
c
ter
Rec
o
g
n
it
i
o
n
b
y
Co
mp
lem
e
n
ta
ry
Cla
ss
if
ier
s
Co
mb
i
n
a
t
io
n
.
"
ICDA
R
2
0
0
7
.
Nin
th
I
n
tern
a
ti
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
.
D
o
c
u
m
e
n
t
A
n
a
l
y
sis
a
n
d
Re
c
o
g
n
it
io
n
,
2
0
0
7
[1
7
]
Ullm
a
n
n
,
J.R.
Ap
p
li
c
a
t
io
n
o
f
Pa
tt
e
rn
Rec
o
g
n
it
io
n
.
CRC
P
re
ss
,
In
c
.
,
1
9
8
7
[1
8
]
Yin
,
X
u
-
Ch
e
n
g
,
Ju
n
S
u
n
,
S
.
Na
o
i
,
a
n
d
K.
F
u
ji
m
o
to
.
"
A
M
u
lt
i
-
S
tag
e
S
trate
g
y
to
P
e
rsp
e
c
ti
v
e
Re
c
ti
f
ic
a
ti
o
n
f
o
r
M
o
b
il
e
P
h
o
n
e
Ca
m
e
ra
-
B
a
se
d
Do
c
u
m
e
n
t
Im
a
g
e
s."
2
0
0
7
B
I
B
L
I
O
G
R
AP
H
Y
O
F
AUT
H
O
RS
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
3
,
Sep
tem
b
er
20
1
4
:
1
2
1
–
1
2
8
128
O.O
Ola
k
a
n
m
i
re
c
e
iv
e
d
th
e
B.
T
e
c
h
in
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
f
ro
m
L
a
d
o
k
e
A
k
in
to
la
Un
iv
e
rsity
o
f
T
e
c
h
n
o
lo
g
y
,
Og
b
o
m
o
sh
o
2
0
0
0
,
M
.
sc
in
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
P
h
.
D.
in
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ic
E
n
g
in
e
e
rin
g
f
ro
m
U
n
iv
e
rsity
o
f
Ib
a
d
a
n
.
He
is
a
lec
tu
re
r
in
t
h
e
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
&
El
e
c
tro
n
ic
En
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
o
f
Ib
a
d
a
n
a
n
d
m
a
jo
r
in
D
a
ta
Co
m
m
u
n
ica
ti
o
n
,
P
a
ra
ll
e
l
&
Distri
b
u
te
d
Co
m
p
u
ti
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.