I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
,
p
p
.
1
2
7
6
~
1
2
8
3
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
11
i
2
.
p
p
1
2
7
6
-
1
2
8
3
1276
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Visua
l,
n
a
v
ig
a
tion a
nd
c
o
mm
unica
tion a
id f
o
r
v
isua
l
ly
i
m
pa
ire
d
p
erso
n
Sa
g
o
r
Sa
ha
,
F
a
rha
n H
o
s
s
a
in Sh
a
k
a
l
,
M
ufr
a
t
h
M
a
h
m
o
o
d
De
p
a
rt
m
e
n
t
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
E
n
g
in
e
e
rin
g
,
A
m
e
rica
n
In
tern
a
ti
o
n
a
l
Un
iv
e
rsity
,
Ba
n
g
lad
e
s
h
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
A
p
r
2
,
2
0
2
0
R
ev
i
s
ed
J
u
l 1
5
,
2
0
2
0
A
cc
ep
ted
Sep
2
2
,
2
0
2
0
T
h
e
lo
ss
o
f
v
isio
n
re
stra
in
e
d
t
h
e
v
isu
a
ll
y
i
m
p
a
ired
p
e
o
p
le
f
ro
m
p
e
rf
o
r
m
in
g
th
e
ir
d
a
il
y
tas
k
.
T
h
is
issu
e
h
a
s
imp
e
d
e
d
t
h
e
ir
f
re
e
-
m
o
v
e
m
e
n
t
a
n
d
t
u
rn
e
d
t
h
e
m
in
to
d
e
p
e
n
d
e
n
t
a
p
e
rso
n
.
P
e
o
p
l
e
in
th
is
se
c
to
r
d
id
n
o
t
f
a
c
e
te
c
h
n
o
l
o
g
ies
re
v
a
m
p
in
g
th
e
ir
situ
a
ti
o
n
s
.
W
it
h
th
e
a
d
v
e
n
t
o
f
c
o
m
p
u
ter
v
isio
n
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
th
e
situ
a
ti
o
n
im
p
ro
v
e
d
to
a
g
re
a
t
e
x
ten
t
.
T
h
e
p
ro
p
o
u
n
d
e
d
d
e
sig
n
is
a
n
im
p
lem
e
n
tatio
n
o
f
a
w
e
a
ra
b
le
d
e
v
ice
w
h
ich
is
c
a
p
a
b
le
o
f
p
e
rf
o
r
m
in
g
a
lo
t
o
f
f
e
a
tu
re
s.
It
is
e
m
p
lo
y
e
d
to
p
r
o
v
id
e
v
isu
a
l
i
n
stin
c
t
b
y
re
c
o
g
n
izin
g
o
b
jec
ts,
id
e
n
t
ify
in
g
th
e
fa
c
e
o
f
c
h
o
ice
s.
T
h
e
d
e
v
ic
e
ru
n
s
a
p
re
-
trai
n
e
d
m
o
d
e
l
to
c
l
a
ss
ify
c
o
m
m
o
n
o
b
jec
ts
f
ro
m
h
o
u
se
h
o
l
d
i
tem
s
to
a
u
to
m
o
b
il
e
s
it
e
m
s.
Op
ti
c
a
l
c
h
a
ra
c
ter
r
e
c
o
g
n
it
io
n
a
n
d
G
o
o
g
le
tran
sla
te
w
e
r
e
e
x
e
c
u
ted
t
o
re
a
d
a
n
y
tex
t
f
ro
m
i
m
a
g
e
a
n
d
c
o
n
v
e
rt
sp
e
e
c
h
o
f
th
e
u
se
r
to
tex
t
re
sp
e
c
ti
v
e
l
y
.
Be
sid
e
s,
th
e
u
se
r
c
a
n
se
a
rc
h
f
o
r
a
n
i
n
tere
sti
n
g
to
p
ic
b
y
th
e
c
o
m
m
a
n
d
in
t
h
e
f
o
rm
o
f
sp
e
e
c
h
.
A
d
d
it
io
n
a
ll
y
,
u
lt
ra
so
n
ic
s
e
n
so
rs
w
e
r
e
k
e
p
t
f
i
x
e
d
a
t
th
re
e
p
o
siti
o
n
s
to
se
n
se
th
e
o
b
sta
c
le
d
u
r
in
g
n
a
v
ig
a
ti
o
n
.
T
h
e
d
isp
lay
a
tt
a
c
h
e
d
h
e
lp
in
c
o
m
m
u
n
ica
ti
o
n
w
it
h
d
e
a
f
p
e
rso
n
a
n
d
G
P
S
a
n
d
G
S
M
m
o
d
u
le
a
id
in
trac
in
g
th
e
u
se
r.
A
ll
th
e
se
f
e
a
tu
re
s
ru
n
b
y
v
o
ice
c
o
m
m
a
n
d
s
w
h
ich
a
re
p
a
ss
e
d
th
ro
u
g
h
th
e
m
icro
p
h
o
n
e
o
f
a
n
y
e
a
rp
h
o
n
e
.
T
h
e
v
isu
a
l
in
p
u
t
is
re
c
e
iv
e
d
th
ro
u
g
h
t
h
e
c
a
m
e
ra
a
n
d
th
e
c
o
m
p
u
tatio
n
tas
k
is
p
ro
c
e
ss
e
d
in
th
e
ra
sp
b
e
rry
p
i
b
o
a
rd
.
Ho
w
e
v
e
r,
th
e
d
e
v
ice
se
e
m
e
d
to
b
e
e
ffe
c
ti
v
e
d
u
rin
g
th
e
tes
t
a
n
d
v
a
li
d
a
ti
o
n
.
K
ey
w
o
r
d
s
:
B
lin
d
-
d
ea
f
co
m
m
u
n
icatio
n
Face
id
en
ti
f
icatio
n
Hu
m
an
-
co
m
p
u
ter
in
ter
ac
tio
n
Ob
j
ec
t r
ec
o
g
n
itio
n
Ob
s
tacle
av
o
id
an
ce
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
:
Sag
o
r
Sah
a
Dep
ar
t
m
en
t o
f
E
lectr
i
ca
l a
n
d
E
lectr
o
n
ics E
n
g
i
n
ee
r
in
g
Am
er
ica
n
I
n
t
er
n
a
tio
n
al
U
n
i
v
e
r
it
y
B
an
g
lad
esh
4
0
8
/1
Ku
r
ato
li Kh
ilk
h
et,
Dh
a
k
a
-
1
2
2
9
,
B
an
g
lad
esh
E
m
ail: sa
g
ar
s
a
h
a4
5
5
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
o
n
ly
o
r
g
a
n
w
h
ich
r
ea
cts
to
lig
h
t
a
n
d
p
er
m
its
v
is
io
n
is
th
e
h
u
m
an
e
y
e.
T
h
e
h
u
m
an
e
y
e
p
la
y
s
a
m
aj
o
r
in
o
b
tain
i
n
g
v
i
s
u
al
in
f
o
r
m
atio
n
.
L
ac
k
o
f
s
i
g
h
t
m
a
y
j
eo
p
ar
d
ize
th
e
v
is
u
all
y
i
m
p
air
ed
p
eo
p
le
to
g
et
th
e
task
co
m
p
leted
.
T
h
er
e
ar
e
2
8
5
m
illi
o
n
v
i
s
u
al
l
y
i
m
p
a
ir
ed
p
eo
p
le
g
lo
b
ally
ac
co
r
d
in
g
to
th
e
W
o
r
ld
Hea
lth
Or
g
an
iza
tio
n
(
W
HO)
[
1
]
.
Am
o
n
g
t
h
ese
p
eo
p
le,
3
9
m
illi
o
n
p
eo
p
le
ar
e
b
lin
d
an
d
2
4
6
m
il
li
o
n
p
eo
p
le
h
av
e
lo
w
o
r
p
o
o
r
v
is
io
n
.
Ho
w
e
v
er
,
t
h
e
f
i
g
u
r
e
i
s
e
x
p
ec
t
ed
to
b
e
d
o
u
b
le
b
y
2
0
2
0
[
1
]
.
T
h
e
f
o
r
e
m
o
s
t
r
ea
s
o
n
b
eh
i
n
d
t
h
e
v
is
u
al
lo
s
s
o
r
i
m
p
air
m
e
n
t
is
m
ai
n
l
y
g
la
u
co
m
a
(
2
%),
u
n
o
p
er
ated
ca
tar
ac
t
(
3
3
%)
an
d
u
n
co
r
r
ec
ted
r
ef
r
ac
tiv
e
er
r
o
r
s
:
asti
g
m
at
is
m
o
r
h
y
p
er
o
p
ia,
m
y
o
p
ia
(
4
3
%).
Ov
er
all,
8
0
%
o
f
th
e
all
th
e
v
i
s
u
al
im
p
a
ir
m
e
n
ts
ca
n
b
e
p
r
ev
en
ted
o
r
cu
r
ed
[
2
]
.
W
H
O
also
r
ep
o
r
ted
th
at
p
eo
p
le
w
it
h
s
e
n
s
o
r
y
d
is
ab
ilit
ie
s
af
f
e
ct
5
.
3
%
o
f
th
e
w
o
r
ld
p
o
p
u
latio
n
an
d
9
.
3
%
o
f
t
h
e
wo
r
ld
p
o
p
u
latio
n
f
o
r
au
d
itio
n
a
n
d
v
i
s
io
n
i
m
p
air
m
en
ts
r
esp
ec
t
iv
el
y
[
3
]
.
T
h
er
e
ar
e
ce
r
tain
tr
ain
i
n
g
p
r
o
g
r
a
m
s
f
o
r
v
is
u
all
y
i
m
p
air
ed
p
eo
p
le
w
h
ic
h
in
v
o
lv
e
m
e
m
o
r
izi
n
g
n
u
m
er
o
u
s
in
f
o
r
m
atio
n
f
o
r
th
eir
p
o
in
t
o
f
i
n
ter
est
(
i.e
m
al
l
s
,
b
u
s
ter
m
in
al
s
,
s
c
h
o
o
ls
etc.
)
.
C
o
n
s
eq
u
e
n
tl
y
,
it
i
n
cr
ea
s
es
t
h
eir
f
r
u
s
tr
at
io
n
lev
e
l
in
t
h
eir
li
v
e
s
.
O
v
er
all,
t
h
eir
m
o
b
ilit
y
a
n
d
q
u
alit
y
o
f
li
f
e
ar
e
af
f
ec
ted
[
4
]
.
A
lo
t
o
f
r
e
s
ea
r
ch
is
b
ei
n
g
co
n
d
u
cted
r
eg
ar
d
in
g
p
o
o
r
v
is
io
n
o
r
lo
s
s
o
f
v
i
s
io
n
i
n
t
h
e
f
ield
o
f
m
ed
ic
al
tr
ea
t
m
e
n
t
a
n
d
tech
n
o
lo
g
ical
i
m
p
r
o
v
e
m
en
t.
Fe
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
V
is
u
a
l,
n
a
vig
a
tio
n
a
n
d
c
o
mmu
n
ica
tio
n
a
i
d
fo
r
visu
a
lly
imp
a
i
r
ed
p
ers
o
n
(
S
a
g
o
r
S
a
h
a
)
1277
p
ap
er
s
h
av
e
b
ee
n
cr
it
icall
y
a
n
al
y
ze
d
i
n
ter
m
s
o
f
t
h
eir
f
ea
tu
r
es
a
n
d
ap
p
r
o
ac
h
to
th
e
s
o
l
u
tio
n
.
K
iu
r
u
et
a
l.
p
r
esen
ted
a
m
o
b
ile
tech
n
o
lo
g
y
as
s
is
t
iv
e
d
e
v
ice
t
h
at
u
s
e
s
r
a
d
ar
tech
n
o
lo
g
y
a
n
d
p
r
o
v
id
ed
clin
ical
in
v
es
tig
a
tio
n
r
esu
lt
s
in
ter
m
s
o
f
p
o
r
tab
ilit
y
an
d
o
r
ien
ta
tio
n
[
5
]
.
Hu
et
a
l.
r
ev
ea
led
th
e
s
tate
o
f
ar
t
i
n
ter
m
s
o
f
f
ea
t
u
r
e,
m
et
h
o
d
,
an
d
tech
n
o
lo
g
y
o
f
th
e
ex
is
ti
n
g
in
n
o
v
atio
n
s
s
o
f
ar
.
T
h
e
r
esear
ch
also
ex
h
ib
its
t
h
a
t
u
s
er
s
ar
e
m
o
s
tl
y
aler
ted
b
y
v
ib
r
atio
n
o
r
au
d
io
as
a
f
ee
d
b
ac
k
[
6
]
.
Kim
p
r
o
p
o
s
e
d
a
w
ea
r
ab
le
d
ev
ice
th
at
ca
n
ex
tr
ac
t
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
c
h
ar
ac
ter
s
u
s
ed
i
n
t
h
e
r
o
ad
an
d
also
r
ec
o
g
n
ize
th
e
r
o
ad
s
i
g
n
s
[
7
]
.
L
a
n
et
a
l.
al
s
o
d
esig
n
ed
a
r
o
b
u
s
t
d
esig
n
f
o
r
d
etec
tin
g
t
h
e
p
u
b
li
c
s
ig
n
w
it
h
I
n
tel
E
d
is
o
n
b
ein
g
th
e
b
r
ain
o
f
th
e
s
y
s
te
m
[
8
]
.
A
b
d
u
r
r
as
y
id
et
a
l.
p
r
esen
ted
a
w
ea
r
ab
le
d
ev
ice
t
h
at
ca
n
s
e
n
s
e
o
b
s
tacle
a
n
d
r
ec
o
g
n
ize
t
h
e
o
b
j
ec
t u
s
i
n
g
t
e
m
p
la
te
m
atc
h
i
n
g
m
et
h
o
d
[
9
]
.
R
aj
alak
s
h
m
i
et
a
l.
p
r
o
p
o
s
ed
th
e
s
a
m
e
tec
h
n
o
lo
g
y
b
u
t
i
m
p
le
m
e
n
ted
o
b
j
ec
t
r
ec
o
g
n
itio
n
w
it
h
a
co
n
v
o
l
u
tio
n
n
eu
r
al
n
et
w
o
r
k
[
1
0
]
.
Gu
e
v
ar
r
a
et
a
l.
d
ev
e
lo
p
ed
a
ca
n
e
w
it
h
f
e
w
u
l
tr
aso
n
ic
s
e
n
s
o
r
s
to
g
e
t
t
h
e
id
ea
o
f
o
b
s
tacle
s
in
d
i
f
f
er
e
n
t
o
r
ien
tatio
n
s
as
w
e
ll
as
s
en
s
e
asce
n
d
in
g
a
n
d
d
esc
en
d
in
g
s
tair
s
a
n
d
r
ec
eiv
e
f
ee
d
b
ac
k
th
r
o
u
g
h
v
o
ice
n
o
tific
atio
n
[
1
1
]
.
R
ak
s
h
a
n
a
a
n
d
C
h
itra
p
r
o
p
o
s
ed
a
s
y
s
te
m
to
n
o
tify
t
h
e
o
b
s
tacle
an
d
r
ea
d
th
e
n
e
w
s
p
ap
er
b
y
o
p
tical
ch
ar
ac
ter
r
ec
o
g
n
itio
n
[
1
2
]
.
Mo
h
an
ap
r
iy
a
d
ev
i
s
e
d
a
s
y
s
te
m
w
h
ic
h
is
ca
p
ab
le
o
f
d
etec
tin
g
o
b
j
ec
t
an
d
tr
af
f
ic
s
ig
n
al
p
atter
n
w
it
h
in
s
t
alled
ca
m
er
a
an
d
s
e
n
s
o
r
s
.
T
h
e
f
ea
tu
r
e
o
f
lo
ca
tin
g
n
ea
r
b
y
p
la
ce
s
i
s
also
av
ailab
le
[
1
3
]
.
Dh
ee
r
a
j
et
a
l.
p
r
o
v
id
ed
an
au
to
m
ated
r
ea
l
-
ti
m
e
s
y
s
te
m
f
o
r
co
lo
r
b
lin
d
n
es
s
u
s
in
g
r
asp
b
er
r
y
p
i
an
d
p
i
ca
m
er
a
[
1
4
]
.
A
n
za
r
u
s
et
a
l.
p
r
o
p
o
s
ed
a
s
o
lu
tio
n
f
o
r
th
e
b
lin
d
r
ea
d
er
w
h
er
e
tap
p
ed
w
o
r
d
s
ar
e
au
d
ib
ly
f
ed
to
th
e
u
s
er
[
1
5
]
.
Ku
m
ar
et
a
l.
d
esig
n
ed
a
b
u
s
e
m
b
ar
k
i
n
g
s
y
s
te
m
f
o
r
th
e
b
li
n
d
u
s
i
n
g
a
r
ad
io
-
f
r
eq
u
en
c
y
id
en
ti
f
icatio
n
.
T
h
e
d
ev
ice
also
p
r
o
v
id
es
s
af
e
n
a
v
i
g
atio
n
p
r
o
v
id
ed
b
y
th
e
u
ltra
s
o
n
ic
s
e
n
s
o
r
s
[
1
6
]
.
Sh
ar
m
a
et
a
l
.
d
ev
is
ed
a
v
ir
t
u
al
e
y
e
f
o
r
th
e
b
lin
d
w
it
h
f
o
u
r
u
l
tr
aso
n
ic
s
en
s
o
r
s
,
SD
ca
r
d
an
d
h
ea
d
p
h
o
n
es
to
p
r
o
v
id
e
t
h
e
o
b
s
tacle
f
r
o
m
v
ar
io
u
s
o
r
ien
tat
i
o
n
s
in
t
h
e
en
v
ir
o
n
m
e
n
t
[
1
7
]
.
Kh
a
n
a
m
et
a
l.
p
r
o
p
o
s
ed
ass
is
tiv
e
s
h
o
es
f
o
r
b
lin
d
p
eo
p
le
w
ith
an
u
ltra
s
o
n
ic
s
en
s
o
r
f
o
r
d
etec
tin
g
b
elo
w
-
kn
ee
o
b
s
tacle
s
[
1
8
]
.
Nis
h
aij
ith
et
a
l
.
d
esig
n
ed
a
s
m
ar
t
ca
p
w
ea
r
ab
le
d
ev
ice
f
o
r
t
h
e
b
lin
d
to
r
ec
o
g
n
ize
co
m
m
o
n
o
b
j
ec
ts
u
s
in
g
s
d
_
m
o
b
ile
n
et_
v
1
_
co
co
_
1
1
_
0
6
_
2
0
1
7
p
r
e
-
tr
ain
ed
m
o
d
el.
I
t
is
clai
m
ed
to
r
u
n
at
a
f
aster
s
p
ee
d
w
ith
g
o
o
d
ac
cu
r
ac
y
[
1
9
]
.
Ki
m
et
a
l.
d
esig
n
ed
an
o
b
j
ec
t
d
etec
tin
g
d
ev
ice
alo
n
g
w
it
h
a
w
ar
n
i
n
g
f
o
r
o
bs
tacle
av
o
id
an
ce
[
2
0
]
.
Vasan
th
et
a
l
.
d
esig
n
ed
a
s
elf
-
ass
is
tiv
e
d
e
v
ice
f
o
r
cr
ea
tin
g
th
e
co
m
m
u
n
icatio
n
b
et
w
ee
n
b
lin
d
an
d
d
ea
f
s
u
p
p
o
r
ted
I
OT
[
2
1
]
.
Ma
iti
et
a
l.
ex
h
ib
ited
a
u
n
iq
u
e
d
esig
n
b
y
p
r
o
d
u
cin
g
a
w
ea
r
ab
le
h
e
l
m
e
t
-
s
h
ap
ed
d
ev
ice
w
it
h
r
an
g
e
f
i
n
d
er
m
o
d
u
les
a
n
d
C
C
D
ca
m
er
as
f
o
r
o
b
s
tr
u
ctio
n
an
d
i
m
a
g
e.
So
lar
p
an
el
s
an
d
p
iezo
elec
tr
ics
d
ev
ices
w
er
e
u
s
ed
to
ch
ar
g
e
t
h
e
s
y
s
te
m
[
2
2
]
.
T
o
m
iti
g
ate
t
h
e
i
s
s
u
es
f
ac
ed
b
y
b
li
n
d
p
eo
p
le,
a
w
ea
r
ab
le
d
ev
ice
w
as
co
n
s
tr
u
cted
u
s
i
n
g
ac
r
y
lic
m
ater
ials
.
Face
r
ec
o
g
n
itio
n
h
as
b
ee
n
p
er
f
o
r
m
ed
alo
n
g
w
it
h
co
m
m
o
n
o
b
j
ec
t
r
ec
o
g
n
itio
n
.
Ultr
aso
n
ic
s
en
s
o
r
s
h
av
e
b
ee
n
p
lace
d
to
p
r
o
v
id
e
q
u
ick
r
esp
o
n
s
e
to
t
h
e
o
b
s
ta
cle.
Fu
r
t
h
er
m
o
r
e,
u
s
er
s
ca
n
p
lay
m
u
s
ic,
s
ea
r
c
h
W
ik
ip
ed
ia
w
ith
r
eq
u
est
m
o
d
u
le
an
d
r
ea
d
s
ca
n
n
ed
o
r
p
r
in
te
d
d
o
cu
m
en
t
s
w
i
th
th
e
h
elp
o
f
o
p
tical
c
h
ar
ac
ter
r
ec
o
g
n
itio
n
.
T
h
e
d
ev
ice
is
also
s
u
p
p
o
r
ted
w
it
h
a
c
h
atb
o
t s
y
s
t
e
m
to
p
r
o
ce
s
s
s
p
ec
i
f
ic
co
m
m
a
n
d
s
as
r
eq
u
i
r
ed
.
As
a
p
r
o
ce
s
s
o
r
,
a
r
asp
b
er
r
y
p
i
b
o
ar
d
h
as
b
ee
n
u
s
ed
w
i
th
a
L
o
g
i
tech
ca
m
er
a.
T
h
e
w
h
o
le
s
y
s
te
m
i
s
s
u
p
p
lied
p
o
w
er
f
r
o
m
t
h
e
d
c
-
d
c
b
u
ck
co
n
v
er
ter
,
w
h
ich
r
ec
ei
v
es p
o
w
er
f
r
o
m
2
2
0
0
m
Ah
b
atter
y
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
e
m
b
ed
d
ed
f
ea
tu
r
es
in
t
h
e
s
y
s
te
m
ar
e
all
r
u
n
b
y
v
o
ice
c
o
m
m
a
n
d
s
.
T
h
e
b
lo
ck
d
ia
g
r
a
m
s
h
o
w
n
i
n
Fig
u
r
e
1
r
ep
r
esen
t
s
t
h
e
f
ea
t
u
r
e
an
d
m
et
h
o
d
o
lo
g
y
f
o
llo
w
ed
.
T
h
e
d
ev
ice
al
w
a
y
s
r
eq
u
ir
es
a
co
n
s
ta
n
t
in
ter
n
e
t
co
n
n
ec
tio
n
to
p
r
o
ce
s
s
th
e
co
m
m
an
d
.
T
h
r
ee
u
ltra
s
o
n
ic
s
en
s
o
r
s
p
lace
d
at
th
e
r
ig
h
t,
f
r
o
n
t
a
n
d
lef
t
aler
t
t
h
e
u
s
er
ab
o
u
t
th
e
o
b
s
tacle
in
th
e
en
v
ir
o
n
m
e
n
t.
T
h
e
u
s
er
ca
n
id
en
tify
m
u
ltip
le
p
e
o
p
le
o
f
h
is
o
r
h
er
c
h
o
ice.
B
esid
es,
th
e
u
s
er
ca
n
al
s
o
r
ec
o
g
n
ize
th
e
co
m
m
o
n
o
b
j
ec
ts
.
B
i
-
d
ir
ec
tio
n
al
co
m
m
u
n
icatio
n
w
it
h
d
ea
f
p
er
s
o
n
s
is
al
s
o
p
o
s
s
ib
le.
Mo
r
eo
v
er
,
th
e
G
P
S
an
d
GSM
m
o
d
u
les
allo
w
t
h
e
u
s
er
to
b
e
t
r
ac
k
ed
b
y
h
is
o
r
h
er
m
e
m
b
er
.
T
h
e
m
e
m
b
er
ca
n
g
e
t
t
h
e
ex
ac
t
lo
ca
tio
n
o
f
h
is
c
u
r
r
en
t
p
o
s
itio
n
.
T
h
e
u
s
er
ca
n
li
s
te
n
to
m
u
s
i
c
an
d
also
r
ef
er
to
W
ik
ip
ed
ia
f
o
r
an
y
k
i
n
d
o
f
in
f
o
r
m
at
io
n
.
T
h
e
w
ea
r
ab
le
d
ev
ic
e
is
s
h
o
w
n
i
n
Fi
g
u
r
e
2
(
a)
an
d
i
m
p
le
m
e
n
tatio
n
i
n
Fig
u
r
e
2
(
b
)
.
T
h
e
ea
r
p
h
o
n
e
is
co
n
n
ec
ted
to
th
e
au
d
io
p
o
r
t
o
f
r
asp
b
er
r
y
p
i.
T
h
e
elec
tr
ical
s
ec
tio
n
an
d
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
v
o
l
v
ed
in
t
h
is
d
e
v
ice
ar
e
in
s
ec
tio
n
s
2
.
1
an
d
2
.
2
r
esp
ec
tiv
el
y
.
2
.
1
.
H
a
rdw
a
re
a
nd
co
nn
ec
t
io
ns
R
asp
b
er
r
y
P
i:
T
h
is
p
r
o
to
t
y
p
i
n
g
b
o
ar
d
,
r
asp
b
er
r
y
p
i
m
a
k
es
u
s
e
o
f
B
r
o
ad
co
m
B
C
M2
8
3
7
S
o
c
an
d
h
a
s
1
.
2
GHz
6
4
q
u
ad
-
co
r
e
A
R
M
C
o
r
tex
-
A
5
3
p
r
o
ce
s
s
o
r
.
T
h
is
m
o
d
el
h
as
a
ca
p
ac
it
y
o
f
1
GB
R
A
M,
2
.
4
GHz
Wi
-
Fi.1
1
n
(
1
5
0
Mb
it/s
)
an
d
B
lu
eto
o
th
4
.
1
(
2
4
Mb
it/s
)
.
C
a
m
er
a:
T
h
e
L
o
g
i
tech
C
2
7
0
w
a
s
p
ic
k
ed
b
ec
au
s
e
o
f
its
lo
w
p
r
ice,
im
ag
e
r
eso
lu
tio
n
o
f
6
4
0
x
4
8
0
an
d
v
id
eo
r
eso
lu
tio
n
o
f
1
2
8
0
x
7
2
0
.
I
t a
ls
o
h
as a
f
i
x
ed
t
y
p
e
o
f
f
o
cu
s
a
n
d
s
tan
d
ar
d
len
s
w
it
h
a
b
u
ilt
-
i
n
m
icr
o
p
h
o
n
e.
L
it
h
i
u
m
p
o
l
y
m
er
b
atter
y
w
it
h
B
u
ck
co
n
v
er
ter
:
A
r
ec
h
ar
g
ea
b
le
b
atter
y
w
i
th
a
to
tal
o
f
12
V
(
v
o
lt)
an
d
2
A
(
a
m
p
er
e)
w
er
e
u
s
ed
.
T
h
is
v
o
ltag
e
w
a
s
p
ass
ed
th
r
o
u
g
h
t
h
e
b
u
ck
co
n
v
er
ter
an
d
as
an
o
u
tp
u
t
5
V
(
v
o
lt)
an
d
2
A
(
a
m
p
er
e)
w
er
e
r
ec
eiv
ed
wh
ich
w
a
s
s
u
p
p
lied
to
th
e
s
y
s
te
m
.
Ultr
aso
n
ic
s
e
n
s
o
r
:
T
h
e
t
w
o
ey
e
-
lik
e
s
tr
u
ct
u
r
e
s
er
v
es
as
tr
an
s
m
itter
an
d
r
ec
eiv
er
.
T
h
e
d
is
tan
ce
i
s
ca
lcu
lated
b
y
m
ea
s
u
r
i
n
g
t
h
e
t
i
m
e
ta
k
e
n
to
r
ec
eiv
e
th
e
r
e
f
le
cted
w
a
v
e.
I
ts
o
p
er
atin
g
c
u
r
r
en
t
a
n
d
v
o
lta
g
e
ar
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
:
1
2
7
6
-
1283
1278
15
m
A
(
m
i
lli
-
a
m
p
er
e)
an
d
5
V
(
v
o
lt)
an
d
m
o
d
u
latio
n
o
f
wav
e
f
r
eq
u
e
n
c
y
i
s
4
0
Hz.
I
t
als
o
ca
n
m
ea
s
u
r
e
th
e
d
is
tan
ce
o
f
2
c
m
to
4
0
0
c
m
.
E
lectr
ical
s
etu
p
o
f
t
h
e
s
y
s
te
m
i
s
s
h
o
w
n
in
F
ig
u
r
e
3
.
Fig
u
r
e
1
.
Ov
er
v
ie
w
o
f
th
e
s
y
s
t
e
m
b
lo
ck
d
iag
r
a
m
(
a)
(
b
)
Fig
u
r
e
2
.
(
a)
T
h
e
cu
s
to
m
-
m
ad
e
d
ev
ice
w
i
th
all
t
h
e
eq
u
ip
m
e
n
ts
an
d
(
b
)
i
m
p
le
m
e
n
atio
n
o
f
th
e
d
ev
ice
Fig
u
r
e
3
.
E
lectr
ical
s
etu
p
o
f
t
h
e
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
V
is
u
a
l,
n
a
vig
a
tio
n
a
n
d
c
o
mmu
n
ica
tio
n
a
i
d
fo
r
visu
a
lly
imp
a
i
r
ed
p
ers
o
n
(
S
a
g
o
r
S
a
h
a
)
1279
2
.
2
.
F
ea
t
ures w
it
h a
lg
o
rit
h
m
2
.
2
.
1
.
O
bje
ct
re
c
o
g
nitio
n
T
en
s
o
r
f
lo
w
A
P
I
is
u
s
u
all
y
p
r
ef
er
r
ed
f
o
r
o
b
j
ec
t
r
ec
o
g
n
itio
n
.
T
h
is
A
P
I
is
s
elec
ted
b
ec
au
s
e
it
ca
n
id
en
ti
f
y
o
b
j
ec
ts
w
it
h
b
o
u
n
d
in
g
b
o
x
es
in
i
m
a
g
e
s
an
d
v
id
eo
s
.
I
t
i
m
p
le
m
e
n
ts
a
p
r
e
-
tr
ain
ed
m
o
d
el
av
ailab
le
a
n
d
ca
n
ea
s
il
y
r
ec
o
g
n
ize
o
b
j
ec
ts
u
p
to
8
0
ca
teg
o
r
ies.
I
t
h
as
i
m
p
r
o
v
ed
th
e
ac
cu
r
ac
y
le
v
el
o
n
a
lar
g
e
s
et
o
f
o
b
j
ec
t
class
i
f
icatio
n
[
2
0
]
.
Am
o
n
g
t
h
e
p
r
e
-
tr
ai
n
ed
m
o
d
el
s
f
o
u
n
d
i
n
T
ab
le
1
,
s
s
d
lite_
m
o
b
ilen
et
v
2
_
co
co
w
a
s
p
ick
ed
b
ec
au
s
e
i
t
ca
n
m
ai
n
tai
n
t
h
e
b
ala
n
ce
b
et
w
ee
n
s
p
ee
d
an
d
ac
c
u
r
ac
y
.
I
t
is
f
o
u
n
d
to
r
u
n
at
th
e
h
ig
h
e
s
t
s
p
ee
d
o
f
2
7
m
s
.
Mo
r
eo
v
er
,
its
b
est
d
ev
ice
lo
w
-
co
s
t
d
e
v
ice
li
k
e
r
asp
b
er
r
y
p
i
as
th
e
m
o
d
el
b
ei
n
g
lig
h
ter
(
1
4
.
7
MB
)
m
ak
e
s
t
h
e
co
m
p
u
tatio
n
m
u
ch
ea
s
ier
an
d
f
aster
.
T
h
e
SS
D
ar
ch
itect
u
r
e
is
f
a
m
o
u
s
co
n
v
o
l
u
tio
n
a
l
n
e
u
r
al
n
et
w
o
r
k
b
ec
au
s
e
o
f
t
w
o
co
m
p
o
n
e
n
ts
.
O
n
e
i
s
t
h
e
f
ea
tu
r
e
e
x
tr
ac
to
r
an
d
t
h
e
o
th
er
is
t
h
e
b
o
u
n
d
in
g
b
o
x
p
r
ed
icto
r
.
T
h
e
b
ase
n
et
w
o
r
k
,
f
ea
t
u
r
e
e
x
tr
ac
to
r
is
a
tr
u
n
ca
ted
clas
s
i
f
icatio
n
n
et
wo
r
k
o
f
V
GG
-
1
6
.
T
h
e
b
o
u
n
d
in
g
b
o
x
p
r
ed
icto
r
is
a
co
m
b
i
n
atio
n
o
f
s
m
a
ll
co
n
v
o
lu
tio
n
al
f
ilter
s
u
s
ed
to
p
r
ed
ict
t
h
e
s
co
r
e,
ca
teg
o
r
y
a
n
d
b
o
x
o
f
f
s
et
s
f
o
r
a
f
i
x
ed
s
et
o
f
d
ef
au
l
t b
o
u
n
d
i
n
g
b
o
x
e
s
[
2
3
]
.
T
ab
le
1
.
P
r
e
-
tr
ain
ed
m
o
d
els
with
s
p
ee
d
an
d
ac
cu
r
ac
y
M
o
d
e
l
n
a
me
S
p
e
e
d
(
ms)
C
O
C
O
mA
P
(
me
a
n
a
v
e
r
a
g
e
p
r
e
c
i
si
o
n
)
ssd
_
mo
b
i
l
e
n
e
t
_
v
1
_
c
o
c
o
30
21
ssd
_
mo
b
i
l
e
n
e
t
_
v
2
_
c
o
c
o
31
22
ssd
_
mo
b
i
l
e
n
e
t
_
v
1
_
f
p
n
_
c
o
c
o
56
32
ssd
_
i
n
c
e
p
t
i
o
n
_
v
2
_
c
o
c
o
42
24
ssd
l
i
t
e
_
mo
b
i
l
e
n
e
t
_
v
2
_
c
o
c
o
27
22
2
.
2
.
2
.
F
a
ce
re
c
o
g
nitio
n
Fo
r
id
en
tif
icatio
n
Op
en
C
V
al
o
n
g
w
it
h
f
ac
e_
r
ec
o
g
n
itio
n
m
o
d
u
le
h
as
b
ee
n
i
m
p
le
m
e
n
ted
w
h
ic
h
h
a
s
ac
cu
r
ac
y
u
p
to
9
9
%.
T
h
er
e
ar
e
m
a
n
y
w
a
y
s
o
f
p
er
f
o
r
m
in
g
f
ac
e
r
ec
o
g
n
itio
n
li
k
e
lin
ea
r
d
is
cr
i
m
i
n
ate
an
al
y
s
i
s
,
p
r
in
cip
al
co
m
p
o
n
e
n
t
an
al
y
s
is
an
d
h
id
d
en
Ma
r
k
o
v
m
o
d
el
[
2
4
]
.
E
ac
h
h
as
a
d
if
f
er
en
t
m
et
h
o
d
,
a
d
v
an
tag
e
s
an
d
d
is
ad
v
an
ta
g
es.
T
h
e
m
et
h
o
d
o
f
t
h
e
p
r
o
p
o
s
ed
f
ac
e
id
en
ti
f
ica
tio
n
s
y
s
te
m
is
s
h
o
w
n
i
n
Fi
g
u
r
e
4
.
I
n
th
e
f
i
g
u
r
e
b
elo
w
,
t
h
r
ee
k
e
y
s
tep
s
ar
e
id
e
n
ti
f
ied
an
d
d
i
s
cu
s
s
ed
.
T
h
e
y
ar
e
f
ac
e
d
etec
tio
n
,
f
ac
ial
f
ea
tu
r
e
ex
tr
ac
tio
n
an
d
f
ac
e
r
ec
o
g
n
itio
n
.
I
n
t
h
e
i
n
it
ial
s
te
p
o
f
f
ac
e
d
etec
t
io
n
,
a
f
ac
e
c
an
b
e
d
etec
ted
eit
h
er
b
y
a
g
eo
m
e
tr
y
-
b
ased
f
ac
e
d
etec
to
r
o
r
a
co
l
o
r
-
b
ased
f
ac
e
d
etec
to
r
.
Ge
o
m
etr
y
-
b
a
s
ed
f
a
ce
d
etec
tio
n
is
ef
f
icie
n
t
f
o
r
f
r
o
n
tal
f
ac
e
s
b
u
t
it
is
d
if
f
ic
u
lt
to
i
m
p
le
m
e
n
t
f
o
r
co
m
p
lex
f
ac
e
s
.
Ho
w
ev
er
,
co
lo
r
-
b
ased
f
ac
e
d
etec
tio
n
h
a
s
b
ee
n
ef
f
icien
t
an
d
p
r
o
v
e
d
to
b
e
f
as
ter
.
Facial
r
e
g
io
n
b
as
ed
o
n
s
k
i
n
co
lo
r
is
cr
o
p
p
ed
f
r
o
m
t
h
e
i
n
p
u
t
i
m
ag
e.
T
h
e
o
b
ta
in
ed
r
eg
io
n
i
s
t
h
e
n
r
esized
in
to
an
8
x
8
p
ix
el
i
m
a
g
e
to
m
a
k
e
th
e
f
ac
e
r
ec
o
g
n
i
ti
o
n
s
y
s
te
m
s
ca
le
i
n
th
e
v
ar
ian
t.
Nex
t,
h
i
s
to
g
r
a
m
eq
u
aliza
tio
n
is
ap
p
lied
to
in
cr
ea
s
e
th
e
b
r
ig
h
tn
e
s
s
an
d
co
n
tr
ast.
T
h
er
e
ar
e
m
a
n
y
s
tep
s
f
o
r
f
ac
ial
f
ea
t
u
r
e
ex
tr
ac
tio
n
li
k
e
d
is
cr
ete
w
a
v
ele
t
tr
an
s
f
o
r
m
(
DW
T
)
,
d
is
cr
ete
co
s
in
e
tr
an
s
f
o
r
m
(
DC
T
)
an
d
So
b
el
ed
g
e
d
etec
tio
n
.
T
h
ese
tech
n
iq
u
es
r
ep
r
ese
n
t
t
h
e
i
m
a
g
es
w
i
th
a
lar
g
e
s
et
o
f
f
ea
tu
r
es.
T
h
e
f
ea
t
u
r
es
o
f
all
i
m
ag
e
s
ar
e
ex
tr
ac
ted
an
d
s
to
r
ed
i
n
to
t
h
e
f
ea
t
u
r
e
v
e
cto
r
.
On
ce
t
h
e
f
ea
t
u
r
e
v
ec
to
r
o
f
al
l
i
m
a
g
es
is
f
o
r
m
ed
,
th
e
s
e
v
ec
to
r
s
ar
e
t
h
e
n
s
to
r
ed
in
to
th
e
s
to
r
ag
e
d
ev
ice
.
W
h
en
t
h
e
u
s
er
ca
p
tu
r
es
a
n
i
m
a
g
e
t
h
e
f
ea
t
u
r
es
v
ec
to
r
s
ar
e
co
m
p
ar
ed
to
th
e
f
ea
t
u
r
e
v
ec
to
r
s
s
to
r
ed
in
t
h
e
d
atab
ase
an
d
th
e
p
er
s
o
n
i
s
id
en
t
if
ied
[
2
5
]
.
T
h
e
r
esu
lt o
f
t
h
e
tes
ted
i
m
ag
e
i
s
s
h
o
wn
in
s
ec
tio
n
3
.
Fig
u
r
e
4
.
Deta
iled
w
o
r
k
i
n
g
o
f
th
e
f
ac
e
r
ec
o
g
n
itio
n
m
o
d
u
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
:
1
2
7
6
-
1283
1280
2
.
2
.
3
.
Dea
f
-
bli
nd
co
m
m
u
nica
t
io
n
T
h
e
p
r
o
b
lem
ar
i
s
es
h
er
e
w
h
e
n
th
er
e
i
s
n
o
m
ed
iu
m
b
et
w
ee
n
th
e
d
ea
f
an
d
t
h
e
b
lin
d
.
T
o
a
id
th
e
is
s
u
e
an
L
C
D
m
o
n
ito
r
is
u
s
ed
.
T
h
e
liv
e
s
p
ee
ch
v
ia
m
icr
o
p
h
o
n
e
i
s
s
en
t
to
th
e
Go
o
g
le
A
P
I
s
er
v
e
r
w
h
ic
h
tr
an
s
f
o
r
m
s
th
e
s
p
ee
ch
in
to
tex
t
a
n
d
it
is
d
is
p
la
y
ed
i
n
th
e
m
o
n
ito
r
as
s
h
o
w
n
i
n
s
ec
tio
n
3
.
T
h
e
p
r
o
ce
s
s
w
il
l
i
m
p
le
m
en
t
t
h
e
R
eq
u
est
p
r
o
ce
d
u
r
e
p
r
o
to
c
o
l
to
s
en
d
t
h
e
en
co
d
ed
au
d
io
to
Go
o
g
le
A
P
I
an
d
t
h
e
co
n
v
er
ted
tex
t
is
s
e
n
t
b
ac
k
t
o
th
e
r
asp
b
er
r
y
p
i u
s
i
n
g
r
ep
ea
te
d
r
eq
u
est p
r
o
to
co
l
[
2
3
]
.
T
h
e
d
etailed
p
r
o
ce
d
u
r
e
is
g
iv
e
n
in
F
ig
u
r
e
5
.
Fig
u
r
e
5
.
T
h
e
p
r
o
ce
s
s
o
f
co
m
m
u
n
icat
io
n
b
et
w
ee
n
cl
ien
t a
n
d
s
er
v
er
2
.
2
.
4
.
O
ptic
a
l
cha
ra
c
t
er
re
co
g
nitio
n
T
h
e
o
p
en
s
o
u
r
ce
p
y
tes
s
er
ac
t
e
n
g
i
n
e
w
a
s
u
s
ed
to
r
ea
d
an
y
s
c
an
n
ed
o
r
p
r
in
ted
d
o
cu
m
en
t.
I
t
ca
n
d
etec
t
m
o
r
e
t
h
a
n
1
0
0
lan
g
u
a
g
es
o
u
t
o
f
th
e
b
o
x
a
n
d
it
i
s
m
ain
l
y
e
m
p
lo
y
ed
Go
o
g
le
s
p
a
m
d
etec
tio
n
.
T
h
e
v
o
ice
co
m
m
a
n
d
i
s
u
s
ed
to
in
i
tialize
th
e
p
r
o
g
r
a
m
.
T
h
e
i
m
ag
e
is
ca
p
tu
r
ed
.
T
h
e
tex
t
o
f
th
e
s
ca
n
n
ed
i
m
a
g
e
i
s
co
n
v
er
ted
to
au
d
io
b
y
u
s
i
n
g
te
x
t
-
to
-
s
p
ee
ch
(
T
T
S)
en
g
in
e,
w
h
ich
i
s
also
k
n
o
w
n
as sp
ee
c
h
s
y
n
te
s
is
[
1
5
]
.
2
.
2
.
5
.
A
lg
o
rit
h
m
w
it
h ultr
a
s
o
nic sens
o
r
As
th
r
ee
s
e
n
s
o
r
s
ar
e
p
lace
d
in
th
r
ee
d
if
f
er
en
t
o
r
ien
tatio
n
,
t
h
e
s
u
b
j
ec
t
g
ets
w
id
e
an
g
le
p
r
o
tectio
n
f
r
o
m
th
e
o
b
s
tacle
s
.
Se
v
e
n
co
m
b
i
n
a
tio
n
s
ar
e
d
r
a
w
n
w
ith
t
h
e
s
en
s
o
r
s
.
Fo
r
ex
a
m
p
le
i
f
f
r
o
n
t
s
e
n
s
o
r
an
d
le
f
t
s
e
n
s
o
r
d
etec
t
th
e
o
b
s
tacle
,
th
e
s
u
b
j
ec
t
is
g
u
id
ed
t
o
m
o
v
e
r
i
g
h
t
.
T
ab
le
2
p
r
o
v
id
e
v
i
v
id
k
n
o
w
led
g
e
ab
o
u
t
t
h
e
co
m
b
i
n
atio
n
s
w
h
er
e
1
m
ea
n
s
o
b
s
tacle
d
etec
ted
an
d
0
m
ea
n
s
n
o
o
b
s
tacle
.
T
ab
le
2
.
C
o
m
b
in
a
tio
n
d
r
a
w
n
w
it
h
t
h
e
r
ea
d
i
n
g
s
o
f
3
s
e
n
s
o
r
s
C
o
n
d
i
t
i
o
n
L
e
f
t
S
o
n
a
r
R
i
g
h
t
S
o
n
a
r
F
o
r
w
a
r
d
S
o
n
a
r
D
i
r
e
c
t
i
o
n
R
e
sp
o
n
s
i
v
e
f
e
e
d
b
a
c
k
t
i
me
d
u
r
i
n
g
c
a
se
(
s)
C
a
se
1
1
1
0
F
o
r
w
a
r
d
1
.
6
9
C
a
se
2
1
0
1
R
i
g
h
t
1
.
7
6
C
a
se
3
0
1
1
L
e
f
t
1
.
7
3
C
a
se
4
1
0
0
R
i
g
h
t
o
r
F
o
r
w
a
r
d
2
.
6
C
a
se
5
0
1
0
L
e
f
t
o
r
f
o
r
w
a
r
d
2
.
3
C
a
se
6
0
0
1
L
e
f
t
o
r
R
i
g
h
t
2
.
1
C
a
se
7
1
1
1
B
a
c
k
1
.
7
1
2
.
2
.
6
.
Sa
f
t
ey
f
ea
t
ures
w
it
h G
P
S a
nd
G
SM
m
o
d
ule
Glo
b
al
s
y
s
te
m
f
o
r
m
o
b
ile
(
GSM)
an
d
g
lo
b
al
s
y
s
te
m
p
o
s
i
ti
o
n
in
g
(
GP
S)
ar
e
th
e
tw
o
d
ev
i
ce
s
m
o
d
u
le
co
n
tr
o
lled
w
it
h
atg
m
e
g
a3
2
8
p
m
icr
o
co
n
tr
o
ller
to
ch
ec
k
th
e
u
s
er
’
s
cu
r
r
e
n
t
p
o
s
itio
n
.
T
h
e
g
u
ar
d
ian
o
r
m
e
m
b
er
o
f
th
e
u
s
er
ca
n
m
es
s
ag
e
w
ith
a
k
e
y
w
o
r
d
to
k
n
o
w
t
h
e
ex
ac
t
l
o
ca
tio
n
in
r
etu
r
n
.
T
h
e
latitu
d
e
s
an
d
lo
n
g
it
u
d
es
ar
e
m
es
s
ag
ed
b
ac
k
i
n
s
u
ch
a
w
a
y
t
h
at
it s
h
o
w
s
t
h
e
u
s
er
in
Go
o
g
l
e
m
ap
ap
p
licatio
n
in
p
h
o
n
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
V
is
u
a
l,
n
a
vig
a
tio
n
a
n
d
c
o
mmu
n
ica
tio
n
a
i
d
fo
r
visu
a
lly
imp
a
i
r
ed
p
ers
o
n
(
S
a
g
o
r
S
a
h
a
)
1281
3.
RE
SU
L
T
S
A
ND
D
I
SCU
SS
I
O
NS
T
h
e
r
esu
lt
s
o
f
ea
ch
s
ec
t
io
n
ar
e
g
i
v
e
n
b
elo
w
w
i
th
a
n
al
y
s
i
s
.
O
v
er
all,
t
h
e
d
e
v
ice
h
a
s
e
x
h
ib
ited
p
r
o
m
i
s
in
g
r
es
u
lt
s
o
n
i
m
p
le
m
e
n
tatio
n
.
T
h
er
e
is
a
r
esu
lt
o
f
m
in
u
te
d
etails
in
t
h
e
s
ec
tio
n
o
f
o
b
j
ec
t
r
ec
o
g
n
itio
n
an
d
th
e
ab
ili
t
y
to
s
p
ea
k
t
h
e
m
u
ltip
le
f
ac
es
i
n
a
f
r
a
m
e.
T
h
e
o
p
en
-
s
o
u
r
ce
s
o
f
t
w
ar
e
b
y
te
s
s
er
ac
t
ca
n
au
d
ib
l
y
an
s
w
er
th
e
w
r
itte
n
tex
t
o
r
p
r
in
ted
d
o
cu
m
en
t
ac
cu
r
atel
y
.
T
h
e
s
en
s
o
r
p
o
s
itio
n
ed
at
th
r
ee
p
lace
s
p
r
o
v
id
es
s
m
o
o
th
n
a
v
ig
a
tio
n
esp
ec
iall
y
in
s
id
e
a
h
o
m
e
as
t
h
er
e
is
a
v
er
y
f
as
t
r
esp
o
n
s
e
i
n
all
r
esp
e
ct.
T
h
e
m
ec
h
an
ical
s
tr
u
ct
u
r
e
o
f
th
e
d
e
v
ice
is
b
u
ilt
in
s
u
ch
a
w
a
y
t
h
at
th
e
u
s
er
ca
n
ea
s
il
y
w
ea
r
it li
k
e
s
u
n
g
la
s
s
e
s
.
3
.
1
.
O
bje
ct
re
co
g
nitio
n
T
h
e
test
h
a
s
b
ee
n
p
er
f
o
r
m
ed
in
t
w
o
ca
s
e
s
.
I
m
a
g
e
w
i
t
h
le
s
s
ite
m
s
s
h
o
w
ed
in
Fi
g
u
r
e
6
(
a)
an
d
m
o
r
e
ite
m
s
s
h
o
w
ed
in
F
i
g
u
r
e
6
(
b
)
.
I
t
d
is
tin
g
u
is
h
ed
f
air
l
y
w
ell
a
n
d
class
i
f
ied
t
h
e
o
b
j
ec
ts
ac
cu
r
atel
y
.
T
h
e
r
esp
o
n
s
e
ti
m
e
co
m
p
ar
e
d
to
o
th
er
m
o
d
els is
v
er
y
f
a
s
t.
(
a)
(
b
)
Fig
u
r
e
6
.
Ob
j
ec
t
r
ec
o
g
n
itio
n
:
(
a)
o
b
j
ec
t r
ec
o
g
n
itio
n
w
it
h
less
ite
m
s
a
n
d
(
b
)
o
b
j
ec
t r
ec
o
g
n
iti
o
n
in
d
en
s
e
ite
m
s
3
.
2
.
F
a
ce
re
co
g
nitio
n
T
h
e
s
y
s
te
m
w
a
s
tr
ain
ed
w
it
h
t
w
o
d
i
f
f
er
e
n
t
f
ac
es.
D
u
e
to
h
i
g
h
ac
c
u
r
ac
y
,
s
y
s
te
m
ca
n
p
r
ed
ict
ex
ac
tl
y
th
e
n
u
m
b
er
o
f
f
ac
es i
n
a
f
r
a
m
e
as sh
o
w
n
in
Fig
u
r
e
7
.
(
a)
(
b
)
Fig
u
r
e
7
.
Face
r
ec
o
g
n
itio
n
:
(
a)
f
ac
e
id
en
ti
f
icatio
n
in
s
ep
ar
ate
i
m
ag
e
s
an
d
(
b
)
f
ac
e
id
en
ti
f
ica
tio
n
in
t
h
e
s
a
m
e
f
r
a
m
e
3
.
3
.
O
ptic
a
l
cha
r
a
ct
er
re
co
g
nitio
n
A
r
a
n
d
o
m
i
m
a
g
e
w
a
s
f
ed
in
t
o
th
e
s
y
s
te
m
,
r
esu
lt
w
a
s
o
u
t
s
tan
d
i
n
g
f
o
r
p
r
in
ted
o
r
t
y
p
ed
i
m
a
g
e
a
s
s
h
o
w
n
in
F
ig
u
r
e
8
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
11
,
No
.
2
,
A
p
r
il
2
0
2
1
:
1
2
7
6
-
1283
1282
Fig
u
r
e
8
.
C
o
n
v
er
s
io
n
te
x
t i
m
a
g
e
t
o
au
d
io
b
y
p
y
tes
s
er
ac
t so
f
t
w
ar
e
3
.
4
.
B
lin
d
-
dea
f
co
m
m
u
nica
t
io
n
T
h
e
d
ev
ice
is
ca
p
ab
le
o
f
co
n
v
er
tin
g
s
h
o
r
t
r
esp
o
n
s
e
o
f
b
lin
d
to
tex
t
w
h
ic
h
is
d
is
p
la
y
ed
in
L
C
D.
T
h
e
d
elay
t
i
m
e
f
o
r
r
ep
r
esen
ti
n
g
t
h
e
tex
t i
n
th
e
L
C
D
is
1
.
5
-
2
s
ec
o
n
d
s
d
ep
en
d
in
g
o
n
t
h
e
s
p
ee
d
o
f
t
h
e
in
ter
n
et.
A
f
e
w
co
n
v
er
s
atio
n
s
ar
e
g
i
v
e
n
b
elo
w
in
Fi
g
u
r
e
9
.
Fig
u
r
e
9
.
Sp
ee
ch
co
n
v
er
ted
to
tex
t u
s
i
n
g
s
p
ee
ch
en
g
i
n
e
s
y
n
th
esis
3
.
5
.
O
t
her
f
ea
t
ures
Fig
u
r
e
s
1
0
(
a)
an
d
1
0
(
b
)
s
h
o
w
th
e
s
a
f
et
y
o
p
tio
n
s
u
p
p
o
r
ted
b
y
GP
S
an
d
GSM
m
o
d
u
le
a
n
d
o
p
tio
n
o
f
f
i
n
d
in
g
i
n
f
o
r
m
atio
n
r
e
g
ar
d
in
g
a
to
p
ic
r
esp
ec
tiv
el
y
.
I
t
is
s
ee
n
th
at
t
h
e
m
e
m
b
er
s
e
n
t
a
k
e
y
w
o
r
d
an
d
th
e
lo
ca
tio
n
r
ep
lied
as a
r
esu
lt.
(
a)
(
b
)
Fig
u
r
e
1
0
.
T
h
e
s
af
et
y
o
p
tio
n
s
u
p
p
o
r
ted
b
y
GP
S a
n
d
GSM
m
o
d
u
le
an
d
o
p
tio
n
o
f
f
i
n
d
in
g
i
n
f
o
r
m
atio
n
r
eg
ar
d
in
g
a
to
p
ic
r
esp
ec
tiv
el
y
:
(
a)
tr
ac
k
in
g
u
s
er
’
s
p
o
s
itio
n
a
n
d
(
b
)
s
ee
k
in
g
i
n
f
o
r
m
atio
n
i
n
t
h
e
w
eb
w
it
h
co
m
m
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
V
is
u
a
l,
n
a
vig
a
tio
n
a
n
d
c
o
mmu
n
ica
tio
n
a
i
d
fo
r
visu
a
lly
imp
a
i
r
ed
p
ers
o
n
(
S
a
g
o
r
S
a
h
a
)
1283
4.
CO
NCLU
SI
O
N
T
h
e
d
ev
ice
w
as
s
u
cc
e
s
s
f
u
ll
y
i
m
p
le
m
e
n
ted
a
n
d
r
esu
lt
s
w
er
e
ap
p
r
o
x
im
a
tel
y
clo
s
e.
Du
r
i
n
g
t
h
e
test
,
t
h
e
s
ize
an
d
w
ei
g
h
t o
f
t
h
e
d
ev
ice
w
er
e
f
o
u
n
d
to
b
e
th
e
o
n
l
y
is
s
u
es
as s
u
g
g
e
s
ted
b
y
p
ar
ticip
an
t
.
T
h
e
s
u
cc
ess
o
f
t
h
i
s
s
y
s
te
m
ca
n
b
e
attr
ib
u
ted
to
lo
w
er
co
s
t
an
d
p
o
r
tab
ilit
y
w
h
e
n
co
m
p
ar
ed
to
o
th
er
d
ev
ices.
W
ith
th
e
h
elp
o
f
t
h
is
d
ev
ice,
p
eo
p
le
ca
n
n
o
w
id
en
ti
f
y
f
ac
e
s
,
r
ec
o
g
n
ize
a
lo
n
g
lis
t
o
f
o
b
j
ec
ts
.
B
e
s
id
es,
th
e
d
ev
ice
allo
w
s
f
r
ee
d
o
m
to
m
o
v
e
i
n
d
o
o
r
ea
s
il
y
m
ai
n
tai
n
in
g
a
d
is
ta
n
ce
o
f
1
0
c
m
.
I
t
also
allo
w
s
p
eo
p
le
to
r
ea
d
a
n
y
p
r
in
ted
te
x
t
o
r
n
e
w
s
p
ap
er
.
I
n
ca
s
e
o
f
e
m
er
g
e
n
c
y
,
th
e
u
s
er
ca
n
b
e
tr
ac
ed
a
n
d
th
e
e
x
ac
t
lo
ca
tio
n
ca
n
b
e
f
o
u
n
d
.
T
h
e
f
ea
t
u
r
es
ar
e
r
u
n
b
y
v
o
ice
co
m
m
a
n
d
w
h
ich
m
ak
e
s
it e
a
s
ier
f
o
r
t
h
e
u
s
er
.
W
h
en
co
m
p
ar
ed
a
g
ain
s
t o
th
er
p
u
b
lis
h
ed
w
o
r
k
s
,
t
h
e
d
ev
ice
f
ar
ed
w
ell
d
u
e
to
th
e
n
u
m
b
er
o
f
f
ea
t
u
r
es
an
d
ac
cu
r
ac
y
.
T
h
e
co
m
b
in
atio
n
s
o
f
t
h
e
f
e
atu
r
es
in
t
h
e
s
y
s
te
m
w
er
e
n
o
t
f
o
u
n
d
in
a
n
y
o
t
h
er
w
o
r
k
.
T
h
e
d
ev
ice
is
f
o
u
n
d
to
s
o
lv
e
a
n
u
m
b
er
o
f
p
r
o
b
le
m
s
i
n
th
eir
d
aily
l
iv
e
s
.
RE
F
E
R
E
NC
E
S
[1
]
K.
P
a
ti
l
,
Q.
Ja
w
a
d
w
a
la
a
n
d
F
.
C.
S
h
u
,
"
De
sig
n
a
n
d
Co
n
stru
c
ti
o
n
o
f
El
e
c
tro
n
ic
A
id
f
o
r
V
isu
a
ll
y
I
m
p
a
ired
P
e
o
p
le,"
IEE
E
T
ra
n
sa
c
ti
o
n
s
o
n
Hu
ma
n
-
M
a
c
h
in
e
S
y
ste
ms
,
v
o
l.
4
8
,
n
o
.
2
,
p
p
.
1
7
2
-
1
8
2
,
2
0
1
8
.
[2
]
T
.
V
.
M
a
taró
e
t
a
l
.
,
"
A
n
a
ss
isti
v
e
m
o
b
il
e
sy
ste
m
su
p
p
o
rti
n
g
b
li
n
d
a
n
d
v
isu
a
l
im
p
a
ired
p
e
o
p
le
w
h
e
n
a
re
o
u
td
o
o
r,
"
IEE
E
3
r
d
In
ter
n
a
ti
o
n
a
l
F
o
ru
m
o
n
Res
e
a
rc
h
a
n
d
T
e
c
h
n
o
l
o
g
ies
fo
r
S
o
c
iety
a
n
d
In
d
u
stry
,
2
0
1
7
,
p
p
.
1
-
6
.
[3
]
F.
S
o
rg
in
i,
R.
Ca
li
o
,
M
.
C.
Ca
r
ro
z
z
a
a
n
d
C.
M.
Od
d
o
.
,
"
Ha
p
ti
c
-
a
ss
isti
v
e
tec
h
n
o
lo
g
ies
f
o
r
a
u
d
i
ti
o
n
a
n
d
v
isio
n
se
n
so
ry
d
isa
b
il
it
ies
,
"
Disa
b
il
it
y
a
n
d
Re
h
a
b
il
it
a
ti
o
n
:
Assistive
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
3
,
n
o
.
4
,
p
p
.
3
9
4
-
4
2
1
,
2
0
1
7
.
[4
]
A
.
Ga
n
z
,
e
t
a
l.
,
"
P
ERCE
P
T
In
d
o
o
r
Na
v
ig
a
ti
o
n
S
y
st
e
m
f
o
r
th
e
Bli
n
d
a
n
d
V
is
u
a
ll
y
I
m
p
a
ir
e
d
:
Arc
h
it
e
c
tu
re
a
n
d
Ex
p
e
rime
n
tatio
n
,
"
I
n
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
T
e
lem
e
d
ici
n
e
a
n
d
A
p
p
li
c
a
ti
o
n
s,
v
o
l.
2
0
1
2
,
p
p
.
1
-
1
2
,
2
0
1
2
.
[5
]
T.
Kiu
ru
,
e
t
a
l.
,
"
A
ss
isti
v
e
d
e
v
i
c
e
f
o
r
o
rien
tatio
n
a
n
d
m
o
b
il
it
y
o
f
th
e
v
isu
a
ll
y
i
m
p
a
ired
b
a
se
d
o
n
m
il
li
m
e
ter
w
a
v
e
ra
d
a
r
tec
h
n
o
l
o
g
y
-
c
li
n
ica
l
in
v
e
stig
a
ti
o
n
re
su
l
ts,"
Co
g
e
n
t
E
n
g
i
n
e
e
rin
g
,
2
0
1
8
.
[6
]
M.
Hu
,
Y.
C
h
e
n
,
G
.
Zh
a
i,
Z
.
G
a
o
a
n
d
L
.
F
a
n
,
"
A
n
o
v
e
r
v
ie
w
o
f
a
ss
isti
v
e
d
e
v
ic
e
s
f
o
r
b
li
n
d
a
n
d
v
is
u
a
ll
y
i
m
p
a
ired
p
e
o
p
le
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ro
b
o
ti
c
s a
n
d
Au
t
o
ma
ti
o
n
,
v
o
l.
3
4
,
n
o
.
5
,
p
p
.
58
0
-
5
9
8
,
2
0
1
9
.
[7
]
J.
Kim
,
"
A
p
p
li
c
a
ti
o
n
o
n
c
h
a
ra
c
ter
re
c
o
g
n
it
io
n
sy
ste
m
o
n
ro
a
d
sig
n
f
o
r
v
isu
a
ll
y
i
m
p
a
ired
:
c
a
se
stu
d
y
a
p
p
ro
a
c
h
a
n
d
f
u
tu
re
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
),
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
7
7
8
-
7
8
5
,
2
0
2
0
.
[8
]
F.
L
a
n
,
G
.
Zh
a
i
a
n
d
W
.
L
in
,
"
L
ig
h
t
w
e
ig
h
t
s
m
a
rt
g
las
s
s
y
ste
m
w
it
h
a
u
d
io
a
id
f
o
r
v
isu
a
ll
y
i
m
p
a
ired
p
e
o
p
le,"
T
ENCON 2
0
1
5
-
2
0
1
5
IEE
E
Reg
i
o
n
1
0
Co
n
fer
e
n
c
e
,
2
0
1
5
,
p
p
.
1
-
4.
[9
]
A.
A
b
d
u
rra
s
y
id
,
I.
In
d
rian
t
o
a
n
d
R.
A
rian
to
,
"
De
te
c
ti
o
n
o
f
i
m
m
o
v
a
b
le
o
b
jec
ts
o
n
v
isu
a
ll
y
i
m
p
a
ired
p
e
o
p
le
w
a
lk
in
g
a
id
s,"
T
EL
KOM
NIKA
T
e
lec
o
mm
u
n
ica
ti
o
n
,
Co
mp
u
ti
n
g
,
El
e
c
tro
n
ics
a
n
d
Co
n
tro
l
,
v
o
l.
1
7
,
n
o
.
2
,
p
p
.
580
-
5
8
5
,
2
0
1
9
.
[1
0
]
R.
Ra
jala
k
sh
m
i,
e
t
a
l.
,
“
S
m
a
rt
Na
v
ig
a
ti
o
n
S
y
ste
m
f
o
r
th
e
V
isu
a
ll
y
I
m
p
a
ired
Us
in
g
T
e
n
so
r
f
lo
w,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
A
d
v
a
n
c
e
Res
e
a
rc
h
a
n
d
In
n
o
v
a
ti
v
e
Id
e
a
s a
n
d
in
Ed
u
c
a
ti
o
n
,
v
o
l
4
,
n
o
.
2
,
p
p
.
2
9
7
6
-
2
9
8
9
,
2
0
1
8
.
[1
1
]
E.
C.
G
u
e
v
a
rr
a
,
M
.
I.
R.
Ca
m
a
m
a
a
n
d
G
.
V.
Cru
z
a
d
o
,
"
De
v
e
lo
p
m
e
n
t
o
f
g
u
id
in
g
c
a
n
e
w
it
h
v
o
ice
n
o
ti
f
ica
ti
o
n
f
o
r
v
isu
a
ll
y
im
p
a
ired
in
d
iv
id
u
a
ls
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
a
n
d
Co
m
p
u
ter
E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
8
,
n
o
.
1
,
p
p
.
1
0
4
-
1
1
2
,
2
0
1
8
.
[1
2
]
K.
R.
Ra
k
sh
a
n
a
a
n
d
C.
Ch
it
ra
,
"
A
S
m
a
rt
Na
v
g
u
id
e
S
y
ste
m
f
o
r
V
isu
a
ll
y
I
m
p
a
ired
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
In
n
o
v
a
ti
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Exp
l
o
rin
g
E
n
g
in
e
e
rin
g
(
IJ
IT
EE
),
v
o
l.
8
,
n
o
.
6
3
,
p
p
.
1
8
2
-
1
8
4
,
2
0
1
9
.
[1
3
]
R.
M
o
h
a
n
a
p
riy
a
,
U.
Nir
m
a
la
a
n
d
C.
P
.
P
risc
il
la,
"
S
m
a
rt
v
isio
n
fo
r
th
e
b
li
n
d
p
e
o
p
le,"
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
El
e
c
tro
n
ics
a
n
d
Co
mm
u
n
ica
t
io
n
E
n
g
i
n
e
e
rin
g
,
v
o
l.
5
,
n
o
.
7
,
p
p
.
2
0
1
4
-
2
0
1
7
,
2
0
1
6
.
[1
4
]
K.
Dh
e
e
ra
j,
S
.
A.
K.
Jilan
i
a
n
d
S
.
J.
Hu
ss
a
in
,
"
R
eal
-
ti
m
e
a
u
to
m
a
t
e
d
g
u
id
a
n
c
e
s
y
ste
m
to
d
e
tec
t
a
n
d
lab
e
l
c
o
lo
r
f
o
r
c
o
lo
r
b
li
n
d
p
e
o
p
le u
sin
g
ra
sp
b
e
rr
y
P
i,
"
S
S
RG
I
n
t.
J
.
o
f
El
e
c
t
.
a
n
d
C
o
mm
u.
E
n
g
i
n
e
e
,
v
o
l.
2
,
n
o
.
1
1
,
p
p
.
11
-
1
4
,
2
0
1
5
.
[1
5
]
S
.
A
.
S
a
b
a
b
a
n
d
M
.
H.
A
sh
m
a
fe
e
,
"
Bli
n
d
Re
a
d
e
r:
A
n
i
n
telli
g
e
n
t
a
s
sista
n
t
f
o
r
b
li
n
d
,
"
1
9
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
(
ICCIT
)
,
2
0
1
6
,
p
p
.
2
2
9
-
2
3
4
.
[1
6
]
C.
S.
k
u
m
a
r
a
n
d
Y.
R.
Ku
m
a
r,
"
Bu
s
E
m
b
a
rk
in
g
S
y
ste
m
f
o
r
V
isu
a
l
Im
p
a
ired
P
e
o
p
le
u
sin
g
Ra
d
io
-
F
re
q
u
e
n
c
y
Id
e
n
ti
f
ica
ti
o
n
,
"
S
S
RG
I
n
t.
J
.
o
f
El
e
c
tro
n
ics
a
n
d
C
o
mm
u
n
ic
a
ti
o
n
E
n
g
in
e
e
rin
g
,
v
o
l.
4
,
n
o
.
4
,
p
p
.
10
-
1
5
,
2
0
1
7
.
[1
7
]
P.
S
h
a
rm
a
a
n
d
S
.
L.
S
h
im
i
,
"
De
si
g
n
a
n
d
d
e
v
e
lo
p
m
e
n
t
o
f
v
irt
u
a
l
e
y
e
f
o
r
th
e
b
l
in
d
,
"
In
t.
J
.
Of
I
n
n
o
v
a
t
ive
Res
e
a
rc
h
In
El
e
c
tr
ica
l,
El
e
c
tro
n
ics
,
In
stru
me
n
ta
ti
o
n
A
n
d
Co
n
tro
l
En
g
in
e
e
rin
g
,
v
o
l.
3
,
n
o
.
3
,
p
p
.
26
-
3
3
,
2
0
1
5
.
[1
8
]
A.
Kh
a
n
a
m
,
A
.
Du
b
e
y
a
n
d
B.
M
ish
ra
,
"
S
m
a
rt
a
ss
isti
v
e
sh
o
e
s
f
o
r
b
li
n
d
p
e
o
p
le
,
"
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
Res
e
a
rc
h
in
S
c
ien
c
e
a
n
d
E
n
g
i
n
e
e
rin
g
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
1
9
5
-
1
9
9
,
2
0
1
8
.
[1
9
]
A
.
Nish
a
ji
th
,
J.
Niv
e
d
h
a
,
S
.
S
.
Na
ir
a
n
d
J
.
M
o
h
a
m
m
e
d
S
h
a
ff
i,
"
S
m
a
rt
Ca
p
-
Wea
ra
b
le
V
isu
a
l
G
u
id
a
n
c
e
S
y
ste
m
f
o
r
Bli
n
d
,
"
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
I
n
v
e
n
ti
v
e
Res
e
a
rc
h
in
Co
m
p
u
ti
n
g
A
p
p
li
c
a
ti
o
n
s
,
2
0
1
8
,
p
p
.
2
7
5
-
2
7
8
.
[2
0
]
Kim
,
Bo
n
g
jae
,
S
e
o
,
Hy
e
o
n
tae
a
n
d
Kim
,
Je
o
n
g
-
Do
n
g
,
“
De
sig
n
a
n
d
im
p
lem
e
n
tatio
n
o
f
a
we
a
ra
b
l
e
d
e
v
ice
f
o
r
th
e
b
li
n
d
b
y
u
sin
g
d
e
e
p
lea
rn
in
g
b
a
se
d
o
b
jec
t
re
c
o
g
n
it
i
o
n
,
”
Co
n
f.
In
t
e
rn
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ter
sc
ien
c
e
a
n
d
it
s A
p
p
li
c
a
ti
o
n
,
2
0
1
7
,
p
p
.
1
0
0
8
-
1
0
1
3
.
[2
1
]
K.
V
a
sa
n
t
h
M
a
c
h
a
rla
M
o
u
n
ik
a
a
n
d
R.
V
a
ra
th
a
ra
jan
,
“
A
S
e
lf
As
sisti
v
e
De
v
i
c
e
f
o
r
De
a
f
&
Bli
n
d
P
e
o
p
le
Us
in
g
IOT
,
”
J
o
u
rn
a
l
o
f
M
e
d
ica
l
S
y
ste
ms
,
p
p
.
1
-
8
,
2
0
1
9
.
[2
2
]
M
.
M
a
it
i,
e
t
a
l.
,
"
In
telli
g
e
n
t
e
lec
tro
n
ic
e
y
e
f
o
r
v
isu
a
ll
y
i
m
p
a
ired
p
e
o
p
le,"
8
t
h
An
n
u
a
l
In
d
u
stri
a
l
A
u
to
ma
ti
o
n
a
n
d
El
e
c
tro
me
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
Co
n
fer
e
n
c
e
,
2
0
1
7
,
p
p
.
3
9
-
4
2
.
[2
3
]
H.
F
a
n
e
t
a
l.
,
"
A
Re
a
l
-
T
i
m
e
Ob
jec
t
De
tec
ti
o
n
A
c
c
e
lera
to
r
w
it
h
Co
m
p
re
ss
e
d
S
S
DL
it
e
o
n
F
P
GA
,
"
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Fi
e
ld
-
Pro
g
r
a
mm
a
b
le T
e
c
h
n
o
lo
g
y
(
FP
T
)
,
2
0
1
8
,
p
p
.
1
4
-
21.
[2
4
]
M.
M
a
d
h
u
ra
m
,
e
t
a
l.
,
"
F
a
c
e
D
e
tec
ti
o
n
a
n
d
Re
c
o
g
n
it
io
n
Us
in
g
Op
e
n
CV
,
"
In
ter
n
a
ti
o
n
a
l
Res
e
a
rc
h
J
o
u
rn
a
l
o
f
En
g
i
n
e
e
rin
g
a
n
d
T
e
c
h
n
o
lo
g
y
(
IRJ
ET
),
v
o
l.
5
,
n
o
.
1
0
,
p
p
4
7
7
-
4
7
7
,
2
0
1
8
.
[2
5
]
N.
S
o
n
i,
M
.
K
u
m
a
r
a
n
d
G
.
M
a
th
u
r,
"
F
a
c
e
Re
c
o
g
n
it
io
n
u
si
n
g
S
O
M
Ne
u
ra
l
Ne
tw
o
rk
w
it
h
Diff
e
r
e
n
t
F
a
c
ial
F
e
a
tu
re
Ex
tra
c
ti
o
n
T
e
c
h
n
iq
u
e
s,"
In
ter
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
li
c
a
ti
o
n
s,
v
o
l
.
7
6
,
n
o
.
3
,
p
p
.
7
-
11
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.