I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
24
,
No
.
2
,
N
o
v
em
b
e
r
20
21
,
p
p
.
84
3
~
8
52
I
SS
N:
2502
-
4
7
5
2
,
DOI
: 1
0
.
1
1
5
9
1
/ijeecs.v
2
4
.i
2
.
pp
843
-
8
5
2
843
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs.ia
esco
r
e.
co
m
Intruder
det
ectio
n and
rec
o
g
nition
using
dif
fere
n
t
i
ma
g
e
pro
cess
ing
t
echn
i
ques for a
p
ro
a
cti
v
e surv
eilla
nce
Nelso
n C.
Ro
dela
s
1
,
M
elv
i
n A.
B
a
llera
2
1
In
fo
rm
a
ti
o
n
a
n
d
Co
m
m
u
n
ica
ti
o
n
Tec
h
n
o
lo
g
y
De
p
a
rtme
n
t,
Un
i
v
e
rsity
o
f
th
e
Eas
t,
M
a
n
il
a
,
P
h
il
ip
p
i
n
e
s
2
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
Offi
c
e
,
Tec
h
n
o
l
o
g
ica
l
I
n
stit
u
te o
f
th
e
P
h
il
i
p
p
i
n
e
s,
M
a
n
il
a
,
P
h
il
i
p
p
i
n
e
s
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
a
n
14
,
2
0
2
1
R
ev
is
ed
Au
g
31
,
2
0
2
1
Acc
ep
ted
Sep
7
,
2
0
2
1
To
in
n
o
v
a
te
a
p
ro
a
c
ti
v
e
su
r
v
e
il
la
n
c
e
c
a
m
e
ra
,
th
e
re
is
a
n
e
e
d
f
o
r
e
f
ficie
n
t
fa
c
e
d
e
tec
ti
o
n
a
n
d
re
c
o
g
n
it
io
n
a
lg
o
rit
h
m
.
Th
e
re
se
a
rc
h
e
rs
u
se
d
o
n
e
o
f
th
e
Vio
la
-
Jo
n
e
s
a
lg
o
rit
h
m
a
n
d
u
se
d
d
iffere
n
t
ima
g
e
p
ro
c
e
ss
in
g
tec
h
n
i
q
u
e
s
t
o
re
c
o
g
n
ize
in
tru
d
e
rs
o
r
n
o
t
.
T
h
e
g
o
a
l
o
f
th
e
re
se
a
rc
h
is
to
re
c
o
g
n
ize
th
e
fa
ste
st
wa
y
o
n
h
o
w
th
e
h
o
m
e
o
wn
e
rs
will
b
e
i
n
f
o
rm
e
d
if
a
n
i
n
tru
d
e
r
o
r
b
u
r
g
lar
e
n
ters
t
h
e
ir
h
o
m
e
u
si
n
g
a
p
r
o
a
c
ti
v
e
su
r
v
e
il
l
a
n
c
e
d
e
v
ice
.
T
h
is
d
e
v
ice
wa
s
p
r
o
g
ra
m
m
e
d
b
a
se
d
o
n
th
e
d
iffere
n
t
re
c
o
g
n
i
t
io
n
a
lg
o
rit
h
m
s
a
n
d
a
c
rit
e
ria
e
v
a
lu
a
ti
o
n
fra
m
e
wo
rk
th
a
t
c
o
u
ld
re
c
o
g
n
ize
in
tru
d
e
rs
a
n
d
b
u
r
g
lars
a
n
d
th
e
d
e
sig
n
u
se
d
wa
s
d
e
v
e
lo
p
m
e
n
tal
re
se
a
rc
h
to
sa
ti
sfy
th
e
re
se
a
rc
h
p
r
o
b
lem
.
T
h
e
r
e
se
a
rc
h
e
r
s
u
se
d
th
e
Vi
o
la
-
Jo
n
e
s a
lg
o
rit
h
m
fo
r
fa
c
e
d
e
tec
ti
o
n
a
n
d
fiv
e
a
lg
o
rit
h
m
s fo
r
fa
c
e
re
c
o
g
n
it
i
o
n
.
T
h
e
c
rit
e
ria
e
v
a
lu
a
ti
o
n
wa
s
u
se
d
t
o
i
d
e
n
ti
f
y
t
h
e
b
e
st
fa
c
e
re
c
o
g
n
it
i
o
n
a
lg
o
rit
h
m
a
n
d
wa
s
te
ste
d
in
a
re
a
l
-
wo
rl
d
sit
u
a
ti
o
n
a
n
d
c
a
p
tu
re
d
a
se
ries
o
f
ima
g
e
s
c
a
m
e
ra
a
n
d
p
ro
c
e
ss
e
d
b
y
p
ro
a
c
ti
v
e
fa
c
e
d
e
te
c
ti
o
n
a
n
d
re
c
o
g
n
it
i
o
n
.
T
h
e
re
su
lt
sh
o
ws
t
h
a
t
th
e
sy
ste
m
c
a
n
d
e
tec
t
a
n
d
re
c
o
g
n
ize
in
tru
d
e
rs
a
n
d
p
ro
a
c
ti
v
e
l
y
se
n
d
a
n
o
ti
fica
ti
o
n
t
o
t
h
e
h
o
m
e
o
w
n
e
rs
v
ia
m
o
b
il
e
a
p
p
li
c
a
ti
o
n
.
It
is
c
o
n
c
lu
d
e
d
th
a
t
th
e
sy
ste
m
c
a
n
re
c
o
g
n
ize
t
h
e
i
n
t
ru
d
e
rs
a
n
d
p
ro
a
c
ti
v
e
l
y
n
o
ti
fy
th
e
h
o
u
se
h
o
ld
m
e
m
b
e
rs
u
sin
g
th
e
m
o
b
il
e
a
p
p
l
ica
ti
o
n
s
a
n
d
a
c
ti
v
a
te
th
e
a
larm
sy
ste
m
o
f
t
h
e
h
o
u
se
.
K
ey
w
o
r
d
s
:
Ad
aBo
o
s
t
Dee
p
lear
n
in
g
al
g
o
r
ith
m
Op
en
C
V
Pro
ac
tiv
e
ca
m
er
a
Su
r
v
eillan
ce
ca
m
er
a
Vio
la
-
J
o
n
es a
lg
o
r
ith
m
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
:
Nelso
n
C
.
R
o
d
elas
I
n
f
o
r
m
atio
n
an
d
C
o
m
m
u
n
icatio
n
T
ec
h
n
o
lo
g
y
Dep
ar
tm
e
n
t
,
U
n
iv
er
s
ity
o
f
th
e
E
ast
2
2
1
9
C
.
M.
R
ec
to
Av
e
n
u
e,
B
r
g
y
.
4
0
4
,
Z
o
n
e
4
1
,
Sam
p
al
o
c,
Ma
n
ila,
Ph
ilip
p
in
es
E
m
ail:
n
elso
n
.
r
o
d
elas@
u
e.
ed
u
.
p
h
1.
I
NT
RO
D
UCT
I
O
N
I
n
o
u
r
m
o
d
er
n
wo
r
ld
,
t
h
e
r
esu
lt
o
f
o
u
r
ca
p
a
b
ilit
ies
ca
n
b
e
g
r
ea
tly
en
h
an
ce
d
b
y
co
m
p
u
ter
s
.
T
ec
h
n
o
lo
g
y
is
a
v
ital
asp
ec
t
o
f
th
e
h
u
m
a
n
co
n
d
itio
n
[
1
]
.
F
r
o
m
m
o
b
ile
p
h
o
n
es
with
a
lo
t
o
f
ap
p
licatio
n
s
to
s
u
p
er
co
m
p
u
ter
s
th
at
ac
t
as
s
er
v
er
s
o
f
a
m
ass
iv
e
am
o
u
n
t
o
f
u
s
er
s
,
lo
ca
l
ar
ea
n
etwo
r
k
s
to
clo
u
d
tec
h
n
o
lo
g
ies,
an
d
a
lo
t
m
o
r
e.
I
t
is
a
f
ac
t
th
at
th
e
wo
r
ld
is
d
o
m
in
ated
b
y
tech
n
o
l
o
g
y
o
n
an
ex
te
n
s
iv
e
s
ca
le
with
an
ex
p
o
n
e
n
tial
r
ate
o
f
d
e
v
elo
p
m
en
t
b
ec
au
s
e
o
f
cu
r
io
u
s
m
in
d
s
th
at
s
ee
k
in
n
o
v
atio
n
.
Dig
ital
im
ag
e
p
r
o
ce
s
s
in
g
(
DI
P)
is
o
n
e
o
f
th
e
b
r
ea
k
th
r
o
u
g
h
s
in
tech
n
o
lo
g
y
th
at
f
o
cu
s
es
o
n
p
r
o
ce
s
s
in
g
d
ig
ital
s
ig
n
als.
B
ec
au
s
e
o
f
th
e
ch
ea
p
er
co
m
p
u
ter
s
an
d
d
ed
ica
ted
h
ar
d
war
e,
m
o
s
t
o
f
th
e
ad
v
an
ce
d
tech
n
o
lo
g
ies
co
n
ce
r
n
in
g
im
ag
es
an
d
th
ei
r
u
s
es
ar
e
n
o
w
cr
ea
ted
with
th
e
u
s
e
o
f
DI
P
[
2
]
.
W
i
th
th
is
,
im
ag
es
ar
e
d
ig
itized
a
n
d
ca
n
b
e
s
to
r
ed
in
co
m
p
u
ter
s
to
r
ag
e
an
d
o
th
er
s
to
r
ag
e
m
ed
ia
[
2
]
,
[
3
]
f
o
r
p
r
e
-
p
r
o
ce
s
s
in
g
o
f
d
ata
an
d
d
ata
m
in
in
g
[
4
]
.
I
m
ag
e
p
r
o
ce
s
s
in
g
ca
n
f
o
r
m
at
an
d
co
r
r
ec
t d
ata,
im
p
r
o
v
e
v
is
u
al
in
ter
p
r
etatio
n
,
an
d
a
u
to
m
atize
tar
g
et
f
ea
tu
r
es
an
d
c
lass
if
icatio
n
s
[
3
]
.
Fig
u
r
e
1
s
h
o
ws
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
izin
g
f
ac
es.
T
h
e
f
ir
s
t
p
r
o
ce
s
s
is
to
d
etec
t
th
e
f
ac
e,
th
en
ex
tr
ac
t
th
e
d
if
f
er
e
n
t
f
ea
tu
r
es
o
f
th
e
f
ac
e
th
at
m
ak
e
it
u
n
i
q
u
e
an
d
u
s
e
it
f
o
r
r
ec
o
g
n
itio
n
.
L
iv
in
g
in
a
n
ew
er
a
wh
e
r
e
cr
im
es
ar
e
in
cr
ea
s
in
g
,
p
eo
p
le
wan
t
to
s
ec
u
r
e
th
eir
b
el
o
n
g
in
g
s
at
th
eir
h
o
m
es.
I
n
t
h
at
s
ce
n
a
r
io
,
a
p
er
s
o
n
co
u
l
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
84
3
-
8
52
844
h
av
e
a
s
y
s
tem
with
ad
v
an
ce
d
tech
n
o
lo
g
ical
im
p
lem
e
n
tatio
n
f
o
r
a
p
er
s
o
n
n
o
t
to
wo
r
r
y
wh
e
n
th
ey
ar
e
f
ar
f
r
o
m
th
eir
h
o
m
e
[
5
]
.
On
e
ar
ea
o
f
te
ch
n
o
lo
g
y
th
at
co
u
ld
b
e
u
s
ed
i
n
th
at
co
n
tex
t
is
th
e
f
ield
o
f
co
m
p
u
ter
v
is
io
n
u
s
in
g
clo
s
ed
cir
cu
it
telev
is
io
n
(
C
C
T
V)
o
r
s
u
r
v
eillan
ce
ca
m
er
a.
C
C
T
V
h
as
two
g
en
er
atio
n
s
:
a
s
u
r
v
eillan
ce
ca
m
er
a
th
at
h
as
h
u
m
an
in
ter
v
en
tio
n
in
e
v
alu
atin
g
im
ag
es
a
n
d
a
co
m
p
u
ter
-
b
ased
ca
m
er
a
th
at
ca
n
e
v
alu
ate
i
ts
im
ag
es
[
6
]
.
T
h
e
latest
g
e
n
er
at
io
n
o
f
C
C
T
V
u
s
es
a
d
ig
ital
s
y
s
tem
o
f
s
u
r
v
eillan
ce
th
at
s
er
v
es
a
wid
e
r
an
g
e
o
f
r
eq
u
ir
em
e
n
ts
in
ter
m
s
o
f
s
ec
u
r
ity
h
o
wev
e
r
,
s
o
m
e
o
f
t
h
em
p
r
o
d
u
ce
an
in
s
u
f
f
icien
t
im
ag
e
o
r
v
id
e
o
q
u
ality
to
s
u
p
p
o
r
t
th
e
d
etec
tio
n
o
f
cr
im
e
s
.
Als
o
,
th
e
h
u
m
an
f
ac
to
r
is
o
n
e
o
f
th
e
m
ajo
r
is
s
u
es
in
u
s
in
g
C
C
T
V.
I
t
ca
n
b
e
s
aid
th
at
th
e
ex
is
tin
g
C
C
T
V
s
y
s
tem
in
th
e
Ph
ilip
p
in
es
is
r
ea
ctiv
e
in
ter
m
s
o
f
s
u
r
v
eilla
n
ce
.
I
t
m
ea
n
s
th
at
C
C
T
V
o
n
ly
u
s
es
i
t
wh
en
th
e
cr
im
e
is
alr
ea
d
y
d
o
n
e.
An
o
th
er
p
r
o
b
lem
is
th
at
th
e
cr
im
in
a
ls
,
b
ein
g
n
o
to
r
io
u
s
,
an
d
d
o
n
o
t
m
in
d
C
C
T
V,
co
n
tin
u
o
u
s
ly
c
o
m
m
it
a
c
r
im
e
to
s
atis
f
y
th
eir
ev
il
d
o
in
g
s
.
T
h
e
f
ac
e
o
f
a
n
y
in
d
iv
id
u
a
l
m
ay
b
e
ca
u
g
h
t
in
C
C
T
V
b
u
t
its
ab
ilit
y
to
id
en
tify
is
n
o
t
al
way
s
ea
s
y
[
7
]
.
W
h
at
is
n
ee
d
e
d
is
a
s
y
s
tem
th
at
h
elp
s
p
r
ev
en
t
f
u
t
u
r
e
attac
k
s
o
f
cr
im
in
als
[
8
]
.
R
o
b
b
er
s
ar
e
u
s
u
ally
p
eo
p
le
w
h
o
lu
r
k
ar
o
u
n
d
h
o
u
s
es
wh
ich
th
ey
b
eliev
e
h
av
e
a
v
er
y
wea
k
s
ec
u
r
ity
s
y
s
tem
.
W
ea
k
s
ec
u
r
ity
allo
ws
th
e
r
o
b
b
er
s
to
en
ter
th
e
h
o
u
s
es
u
n
n
o
ticed
b
y
th
e
p
eo
p
le
ar
o
u
n
d
th
em
.
So
m
etim
es
th
ey
d
o
it
to
h
o
u
s
es
lo
ca
ted
in
an
e
n
v
ir
o
n
m
en
t
wh
er
e
f
ew
p
eo
p
le
a
r
e
v
is
ib
le
s
o
th
at
t
h
ey
ca
n
e
n
ter
u
n
n
o
ticed
.
W
ith
th
at
s
aid
,
s
o
m
e
r
o
b
b
er
s
d
o
it
b
y
ca
s
u
ally
walk
in
g
in
s
id
e
h
o
m
es
with
o
p
en
o
r
u
n
lo
ck
ed
d
o
o
r
s
wh
ile
p
eo
p
le
th
in
k
th
at
h
e/sh
e
liv
es in
th
at
h
o
u
s
e.
Fig
u
r
e
1
.
Face
r
ec
o
g
n
itio
n
p
r
o
ce
s
s
T
h
e
m
ain
f
o
c
u
s
o
f
th
e
r
esear
ch
is
to
s
ec
u
r
e
th
e
h
o
u
s
e
b
y
d
etec
tin
g
an
d
r
ec
o
g
n
izin
g
i
n
tr
u
d
er
s
a
n
d
b
u
r
g
lar
s
in
r
ea
l
-
tim
e
u
s
in
g
t
h
e
p
r
o
p
o
s
ed
p
r
o
to
ty
p
e
.
I
t
h
as
an
alar
m
s
y
s
tem
,
m
o
b
ile
ap
p
licatio
n
s
,
an
d
d
if
f
er
en
t
im
ag
e
d
etec
tio
n
a
n
d
r
ec
o
g
n
i
tio
n
alg
o
r
ith
m
p
lu
s
cr
iter
ia
ev
alu
atio
n
to
p
r
o
ac
tiv
ely
p
r
o
d
u
ce
r
esu
lts
wh
en
in
tr
u
d
er
s
ar
e
r
ec
o
g
n
ized
.
T
o
g
ath
er
in
s
ig
h
ts
th
at
wo
u
l
d
h
el
p
th
is
r
esear
ch
,
th
e
r
esear
ch
er
s
r
ev
iewe
d
s
ev
er
al
r
ec
en
t
s
tu
d
ies
an
d
liter
atu
r
e
r
elate
d
to
t
h
is
s
tu
d
y
.
T
h
e
id
ea
s
g
ath
er
ed
wer
e
u
s
ed
to
ev
alu
ate
wh
at
is
th
e
b
est
m
eth
o
d
o
l
o
g
y
a
n
d
to
o
ls
th
at
th
e
p
r
o
p
o
n
en
t
u
s
ed
to
s
o
lv
e
t
h
e
p
r
o
b
lem
.
T
h
e
p
r
esen
ce
o
f
a
s
ec
u
r
ity
s
y
s
tem
in
h
o
u
s
eh
o
ld
s
a
n
d
estab
lis
h
m
en
ts
is
im
p
o
r
tan
t
i
n
th
e
co
n
tex
t
o
f
cr
ea
tin
g
s
ec
u
r
ity
s
y
s
tem
s
[
9
]
.
Secu
r
ity
s
y
s
tem
f
o
c
u
s
es
o
n
p
r
o
v
id
in
g
s
ec
u
r
ity
wh
e
n
th
e
h
o
m
eo
wn
er
s
ar
e
awa
y
f
r
o
m
th
eir
h
o
m
e
[
5
]
.
I
t
was
s
tated
th
at
s
h
o
r
t
m
ess
ag
e
s
er
v
ice
(
SMS
)
co
u
ld
p
er
f
o
r
m
r
em
o
te
co
m
m
u
n
icatio
n
b
etwe
en
h
o
m
eo
wn
e
r
s
an
d
h
o
u
s
eh
o
ld
d
ev
ices.
M
o
b
ile
p
h
o
n
es
with
s
h
o
r
t
m
ess
ag
in
g
s
er
v
ice
co
u
ld
b
e
v
er
y
u
s
ef
u
l
wh
en
em
b
ed
d
ed
in
h
o
u
s
eh
o
ld
s
ec
u
r
ity
s
y
s
tem
s
,
wh
er
e
m
ess
ag
es
s
en
t
b
y
s
e
cu
r
ity
s
y
s
tem
s
ar
e
im
m
ed
iately
r
ec
eiv
ed
b
y
h
o
m
eo
wn
er
s
in
th
e
f
o
r
m
o
f
SMS.
Ma
n
y
s
er
v
ices
o
f
f
er
alar
m
m
o
n
ito
r
in
g
t
h
at
allo
ws
h
o
m
eo
wn
e
r
s
to
ac
ce
s
s
th
eir
h
o
m
e
s
ec
u
r
ity
s
y
s
tem
v
ia
th
e
in
ter
n
et
[
1
0
]
.
I
t
co
u
ld
ch
ec
k
th
e
s
tatu
s
o
f
th
e
s
ec
u
r
ity
s
y
s
tem
an
d
v
iew
a
l
iv
e
f
ee
d
o
f
s
u
r
v
eillan
ce
ca
m
er
as.
Ad
v
an
ce
d
s
y
s
tem
s
ev
en
allo
w
its
u
s
er
s
to
co
n
f
ig
u
r
e
s
ec
u
r
ity
co
d
es a
n
d
a
ctiv
ate
o
r
d
ea
ctiv
ate
th
e
s
ec
u
r
i
ty
s
y
s
tem
b
y
u
s
in
g
web
ap
p
lic
atio
n
s
.
B
u
t
th
er
e
is
a
m
o
r
e
m
o
d
er
n
d
ev
elo
p
m
en
t
i
n
th
e
h
o
m
e
s
ec
u
r
ity
s
y
s
tem
wh
ich
is
m
o
b
ile
d
ev
ices
an
d
ap
p
licatio
n
s
th
at
o
f
f
er
p
o
r
tab
ilit
y
.
T
h
e
u
s
e
o
f
m
o
b
il
e
d
ev
ices
an
d
a
m
o
n
ito
r
in
g
s
y
s
tem
o
f
f
er
s
a
n
ew
way
s
o
th
at
p
eo
p
le
co
u
ld
m
o
n
ito
r
t
h
e
s
ec
u
r
ity
o
f
th
eir
b
elo
n
g
in
g
s
an
y
tim
e
an
d
an
y
wh
er
e.
So
m
e
p
r
o
t
o
ty
p
es
u
s
e
f
ac
ial
r
ec
o
g
n
itio
n
in
s
u
r
v
eillan
ce
[
1
1
]
.
T
h
e
m
a
n
u
f
ac
tu
r
er
s
o
f
th
e
h
o
m
e
s
ec
u
r
it
y
s
y
s
tem
h
av
e
s
ev
er
al
way
s
f
o
r
h
o
m
eo
wn
er
s
to
m
o
n
ito
r
th
e
s
ec
u
r
ity
s
y
s
tem
o
f
th
eir
h
o
m
e
e
v
en
wh
en
th
ey
ar
e
f
ar
awa
y
f
r
o
m
t
h
eir
h
o
m
e
[
1
2
]
.
Alar
m
s
y
s
tem
s
n
o
wad
ay
s
co
u
ld
n
o
tify
h
o
m
e
o
wn
er
s
ab
o
u
t
th
e
s
tatu
s
o
f
th
eir
s
ec
u
r
ity
s
y
s
tem
b
y
p
ag
in
g
th
em
.
T
h
er
e
is
an
av
ailab
le
SMS
co
m
m
u
n
icatio
n
h
o
m
e
s
ec
u
r
ity
s
y
s
tem
th
at
m
o
n
ito
r
s
th
e
h
o
u
s
e
u
s
in
g
s
en
s
o
r
s
[
5
]
.
T
h
e
r
esear
ch
er
s
u
s
ed
a
m
icr
o
co
n
tr
o
ller
an
d
gl
o
b
al
s
y
s
tem
f
o
r
m
o
b
iles
(
GSM)
u
n
it
u
s
in
g
a
m
o
b
ile
p
h
o
n
e
t
o
n
o
tify
u
s
er
s
wh
en
an
in
tr
u
s
io
n
o
cc
u
r
s
.
I
t
is
co
n
s
id
er
ed
th
at
t
h
e
d
e
m
a
n
d
f
o
r
h
o
m
e
s
ec
u
r
ity
u
s
in
g
a
n
d
r
o
id
b
ased
p
h
o
n
es
h
as
cr
ea
te
d
a
s
y
s
tem
th
at
s
ec
u
r
es
th
e
m
ain
en
tr
a
n
c
e
o
f
th
e
h
o
m
e
an
d
th
e
ca
r
d
o
o
r
lo
c
k
[
1
3
]
.
T
h
e
s
y
s
tem
also
u
s
ed
B
lu
eto
o
th
tech
n
o
lo
g
y
to
c
o
n
tr
o
l
th
e
d
if
f
er
en
t
ap
p
lian
ce
s
in
s
id
e
th
e
h
o
u
s
e.
I
t
is
also
s
aid
th
at
m
o
s
t
o
f
th
e
alg
o
r
ith
m
s
f
o
r
f
ac
e
r
ec
o
g
n
itio
n
wer
e
d
ev
elo
p
ed
to
en
h
a
n
ce
im
a
g
es
ca
p
tu
r
e
d
f
r
o
m
d
if
f
er
e
n
t
a
p
p
licatio
n
s
l
ik
e
m
ilit
ar
y
tactics,
s
p
ac
ec
r
af
t,
s
ec
u
r
ity
p
u
r
p
o
s
es,
an
d
o
th
er
s
[
1
4
]
.
T
h
ey
d
is
cu
s
s
ed
th
e
d
if
f
er
en
t
f
ac
e
r
ec
o
g
n
itio
n
alg
o
r
ith
m
s
an
d
f
ac
to
r
s
af
f
ec
tin
g
f
ac
e
r
ec
o
g
n
itio
n
.
T
h
ey
s
aid
th
at
th
e
E
ig
en
f
ac
e
alg
o
r
ith
m
was
f
o
cu
s
ed
o
n
th
e
illu
m
in
atio
n
o
f
th
e
im
ag
e;
th
e
g
eo
m
etr
ic
b
as
ed
alg
o
r
ith
m
th
at
was
f
o
cu
s
e
d
o
n
p
er
im
eter
s
,
ar
ea
s
,
an
d
s
eg
m
en
ts
o
f
im
ag
e
f
o
r
m
s
b
ec
au
s
e
o
f
p
o
in
ts
lo
ca
ted
o
n
it;
tem
p
late
m
atch
in
g
alg
o
r
ith
m
r
ec
o
g
n
izes
im
ag
e
u
s
in
g
s
tatis
tica
l
tr
ea
tm
en
t
b
y
c
o
n
v
er
tin
g
im
a
g
e
s
in
to
n
u
m
er
ical
v
alu
es
with
te
m
p
lates
an
d
elim
in
ates
v
ar
ia
n
ce
s
.
T
h
ey
s
aid
th
at
ex
p
r
ess
io
n
s
,
o
cc
u
ltatio
n
o
r
h
i
n
d
r
an
ce
s
in
th
e
ca
p
tu
r
ed
im
a
g
e,
p
o
s
es
o
r
f
ac
e
a
n
g
le,
illu
m
in
atio
n
o
r
lig
h
tn
ess
an
d
d
ar
k
n
ess
o
f
th
e
im
ag
e,
an
d
f
ac
ial
f
ea
tu
r
es we
r
e
th
e
b
asi
c
f
ac
to
r
s
in
f
ac
e
r
ec
o
g
n
itio
n
.
Dee
p
lear
n
in
g
s
h
o
ws
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tr
u
d
er d
etec
tio
n
a
n
d
r
ec
o
g
n
itio
n
u
s
in
g
d
iffer
en
t ima
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es fo
r
… (
N
elso
n
C
.
R
o
d
ela
s
)
845
ex
ce
l
len
t
p
er
f
o
r
m
an
ce
in
f
ac
e
r
ec
o
g
n
itio
n
[
1
5
]
.
H
o
wev
er
,
it
n
ee
d
s
a
lar
g
e
n
u
m
b
er
o
f
in
ter
p
r
eted
tr
ai
n
in
g
d
atasets
.
T
h
e
r
esear
ch
er
s
d
ef
in
ed
a
d
ee
p
lea
r
n
in
g
alg
o
r
ith
m
as
th
e
en
h
a
n
ce
d
alg
o
r
ith
m
o
f
th
e
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
th
at
h
as m
o
r
e
th
an
th
r
ee
h
id
d
en
lay
e
r
s
to
p
er
f
o
r
m
s
elf
-
r
ec
o
g
n
itio
n
o
f
th
e
im
ag
e.
2.
M
E
T
H
O
DO
L
O
G
Y
T
h
e
c
o
n
c
e
p
t
u
a
l
f
r
a
m
ew
o
r
k
w
as
d
es
i
g
n
e
d
a
f
t
e
r
k
n
o
w
i
n
g
t
h
e
d
i
f
f
e
r
e
n
t
g
a
p
s
i
n
d
e
v
e
l
o
p
i
n
g
a
p
r
o
a
c
t
i
v
e
s
u
r
v
e
i
l
l
a
n
ce
c
a
m
e
r
a
.
D
i
f
f
e
r
e
n
t
a
l
g
o
r
i
t
h
m
s
a
n
d
c
r
i
t
e
r
ia
e
v
al
u
a
t
i
o
n
w
e
r
e
c
o
n
s
i
d
e
r
e
d
t
o
c
r
e
a
t
e
t
h
e
s
y
s
t
e
m
.
F
i
g
u
r
e
2
s
h
o
w
s
t
h
e
c
o
n
c
e
p
t
u
a
l
f
r
a
m
e
w
o
r
k
o
f
t
h
e
r
e
s
e
a
r
c
h
.
T
h
e
s
y
s
t
e
m
c
a
p
t
u
r
es
i
m
a
g
es
a
n
d
p
e
r
f
o
r
m
s
d
e
t
e
c
t
i
o
n
o
f
f
a
c
e
s
u
s
i
n
g
t
h
e
Vi
o
l
a
-
J
o
n
es
A
l
g
o
r
i
t
h
m
t
h
r
o
u
g
h
t
h
e
c
a
p
t
u
r
e
d
i
m
a
g
e
s
.
O
n
c
e
t
h
e
s
y
s
t
e
m
d
e
t
e
c
ts
f
a
c
es
c
o
m
i
n
g
f
r
o
m
t
h
e
i
m
a
g
e
s
,
t
h
e
d
e
t
e
c
t
ed
f
a
c
e
s
a
r
e
r
e
c
o
g
n
i
z
e
d
u
s
i
n
g
t
h
e
f
i
v
e
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
a
l
g
o
r
i
t
h
m
s
(
e
i
g
e
n
f
a
c
es
,
f
i
s
h
e
r
f
a
c
es
,
l
o
c
al
b
i
n
a
r
y
p
a
tt
e
r
n
,
t
e
m
p
l
a
t
e
m
a
t
c
h
i
n
g
,
a
n
d
d
e
ep
l
e
a
r
n
i
n
g
)
a
n
d
m
a
t
c
h
it
t
o
t
h
e
d
a
t
a
b
a
s
e
o
f
f
a
c
es
.
T
h
e
s
y
s
te
m
a
ls
o
p
e
r
f
o
r
m
s
t
h
e
cr
i
t
e
r
i
a
e
v
al
u
a
t
i
o
n
t
o
i
d
e
n
t
i
f
y
t
h
e
b
e
s
t
al
g
o
r
i
t
h
m
t
o
b
e
u
s
e
d
i
n
th
e
s
y
s
te
m
.
Dif
f
er
en
t
cr
iter
ia
wer
e
th
e
f
o
l
lo
win
g
:
illu
m
in
atio
n
th
at
m
ea
s
u
r
es
th
e
r
ate
o
f
r
ec
o
g
n
itio
n
i
n
ter
m
s
o
f
lig
h
tin
g
co
n
d
itio
n
o
f
th
e
ca
p
t
u
r
ed
p
ictu
r
e;
th
e
f
ac
ial
an
g
le
-
th
at
m
ea
s
u
r
es
th
e
r
ate
o
f
r
ec
o
g
n
itio
n
in
ter
m
s
o
f
th
e
an
g
le
o
f
t
h
e
d
etec
ted
f
ac
e
;
th
e
lev
el
o
f
co
n
f
id
e
n
ce
o
f
e
ac
h
alg
o
r
ith
m
in
th
e
p
r
o
ce
s
s
o
f
r
ec
o
g
n
itio
n
;
th
e
f
ac
ial
f
ea
tu
r
es o
r
th
e
ch
a
n
g
es o
f
th
e
f
ea
tu
r
e
o
f
th
e
ca
p
tu
r
e
d
f
ac
e;
an
d
th
e
tim
e
co
m
p
le
x
ity
o
r
th
e
tim
e
r
e
q
u
ir
ed
in
r
ec
o
g
n
izin
g
th
e
d
etec
ted
f
a
ce
,
it
iter
ates
u
n
til
th
er
e
ar
e
u
n
m
atch
ed
f
ac
es
d
etec
ted
b
y
th
e
s
y
s
tem
.
T
h
e
s
er
v
er
o
f
th
e
s
y
s
tem
h
as
th
e
ca
p
ab
ili
ty
o
f
v
iewin
g
th
e
lo
g
s
o
f
in
tr
u
s
io
n
an
d
p
r
in
tin
g
th
e
lis
t
o
f
ca
p
tu
r
ed
in
tr
u
d
er
s
.
I
t
s
en
d
s
m
ess
ag
e
s
u
s
in
g
SMS
to
th
e
h
o
m
eo
wn
er
s
wh
e
n
th
e
r
e
i
s
n
o
in
ter
n
et
co
n
n
ec
tio
n
t
o
n
o
tify
th
at
th
er
e
is
an
in
tr
u
d
er
in
th
e
h
o
u
s
e
an
d
to
o
p
en
th
e
m
o
b
ile
ap
p
licatio
n
t
o
v
iew
th
e
ca
p
tu
r
ed
im
ag
e
o
f
th
e
in
tr
u
d
er
;
T
h
e
s
y
s
tem
au
to
m
atica
lly
s
en
d
s
t
h
e
ca
p
tu
r
ed
p
ictu
r
e
to
th
e
th
r
o
u
g
h
clo
u
d
tech
n
o
l
o
g
y
wh
en
th
er
e
is
an
in
ter
n
et
co
n
n
ec
tio
n
.
T
h
e
m
o
b
ile
a
p
p
l
icatio
n
s
ca
n
v
iew
th
e
ca
p
tu
r
ed
p
ictu
r
e
o
f
a
n
in
tr
u
d
er
;
t
h
e
s
y
s
tem
h
as
an
au
to
m
atic
alar
m
s
y
s
tem
wh
e
n
an
in
tr
u
d
er
is
d
etec
ted
an
d
th
e
m
o
b
ile
a
p
p
licatio
n
u
s
er
h
as
t
h
e
p
r
iv
ileg
e
to
t
u
r
n
o
f
f
th
e
alar
m
s
y
s
tem
.
Fig
u
r
e
2
.
C
o
n
ce
p
tu
al
p
ar
a
d
ig
m
2
.
1
.
Resea
rc
h
m
et
ho
d
T
h
e
r
e
s
e
a
r
c
h
e
r
s
u
s
e
d
d
e
v
e
l
o
p
m
e
n
t
a
l
r
e
s
ea
r
c
h
.
A
d
e
v
e
l
o
p
m
e
n
t
a
l
r
e
s
ea
r
c
h
m
e
t
h
o
d
i
s
d
e
f
in
e
d
a
s
t
h
e
s
t
u
d
y
o
f
d
e
s
i
g
n
,
d
e
v
e
l
o
p
m
e
n
t
,
a
n
d
e
v
a
l
u
a
ti
o
n
o
f
p
r
o
d
u
c
t
s
,
p
r
o
g
r
a
m
s
,
a
n
d
p
r
o
c
e
s
s
e
s
t
h
a
t
m
e
e
t
t
h
e
c
r
i
t
e
r
i
a
o
f
e
f
f
e
c
t
i
v
e
n
es
s
a
n
d
c
o
n
s
i
s
t
e
n
c
y
.
T
h
e
e
v
a
l
u
a
t
i
o
n
o
f
t
h
e
f
i
n
a
l
p
r
o
d
u
c
t
i
s
i
m
p
le
m
e
n
t
a
ti
o
n
[
1
6
]
.
I
t
f
a
c
i
l
it
a
t
es
t
h
e
s
t
u
d
y
o
f
n
e
w
t
o
o
l
s
,
m
o
d
e
l
s
,
a
n
d
p
r
o
c
e
d
u
r
e
s
s
o
t
h
a
t
t
h
e
r
es
e
a
r
c
h
e
r
s
c
a
n
a
n
t
i
c
i
p
a
t
e
t
h
e
e
f
f
i
ci
e
n
c
y
an
d
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
t
h
e
s
y
s
t
e
m
.
T
h
e
r
es
e
a
r
c
h
e
r
s
u
s
e
d
a
n
a
g
i
l
e
m
et
h
o
d
o
l
o
g
y
t
h
a
t
is
u
s
e
d
t
o
d
e
v
e
l
o
p
p
r
o
d
u
c
t
s
t
h
r
o
u
g
h
i
t
e
r
a
t
i
o
n
s
o
f
t
h
e
p
r
o
c
e
s
s
.
T
h
is
m
e
t
h
o
d
o
l
o
g
y
i
s
e
f
f
e
c
t
i
v
e
s
p
e
c
i
f
i
c
a
ll
y
w
h
e
n
t
h
e
p
r
o
j
e
c
t
c
a
n
b
e
d
i
v
i
d
e
d
i
n
t
o
m
a
n
y
s
m
a
l
l
t
a
s
k
s
,
w
i
th
l
o
t
s
o
f
c
r
e
at
i
v
i
t
y
,
a
n
d
m
u
s
t
b
e
d
e
v
e
l
o
p
e
d
t
o
f
i
t
w
it
h
t
h
e
s
t
a
k
e
h
o
l
d
e
r
’
s
e
x
p
e
c
t
at
i
o
n
s
.
2
.
2
.
H
a
rdwa
re
dev
ices
A
r
asp
b
er
r
y
p
i
(
R
Pi)
n
o
in
f
r
a
r
ed
f
ilter
(
No
I
R
)
ca
m
e
r
a
with
a
m
in
im
u
m
o
f
8
m
eg
a
p
ix
el
(
MP
)
q
u
ality
was
u
s
ed
to
f
etch
th
e
v
id
eo
f
e
ed
an
d
to
p
r
o
ce
s
s
th
e
v
id
eo
f
e
ed
f
r
a
m
e
b
y
f
r
am
e.
A
ca
m
er
a
with
o
u
t
an
in
f
r
ar
e
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
84
3
-
8
52
846
lig
h
t
f
ilter
co
u
ld
b
e
u
s
ed
at
n
ig
h
t
to
v
is
io
n
to
ca
p
tu
r
e
im
ag
e
s
ev
en
wh
en
it
is
d
ar
k
with
th
e
aid
o
f
an
in
f
r
ar
ed
lig
h
t
-
em
itti
n
g
d
io
d
e
(
LED
)
.
T
h
e
r
asp
b
er
r
y
p
i
3
is
a
cir
cu
it
m
o
d
u
le
th
at
h
as
th
e
ca
p
a
b
ilit
ies
o
f
a
co
m
p
u
ter
.
I
t
h
as
u
n
iv
er
s
al
s
er
ial
b
u
s
(
USB
)
p
o
r
ts
an
d
an
eth
e
r
n
et
p
o
r
t.
T
h
is
is
r
esp
o
n
s
ib
le
f
o
r
co
n
d
u
ctin
g
th
e
co
m
p
ar
i
n
g
an
d
s
en
d
in
g
o
f
e
m
ail
to
th
e
h
o
m
eo
wn
er
c
o
n
tain
in
g
th
e
im
a
g
e
o
f
th
e
s
u
s
p
ec
ted
in
tr
u
d
er
in
s
id
e
th
e
h
o
u
s
e.
T
h
e
in
f
r
ar
ed
(
IR
)
illu
m
in
ato
r
is
th
e
o
n
e
r
esp
o
n
s
ib
le
f
o
r
allo
win
g
th
e
r
asp
b
e
r
r
y
p
i
ca
m
er
a
to
d
etec
t
f
ac
es
in
d
ar
k
p
lace
s
th
at
allo
ws th
e
r
esear
ch
er
s
to
g
et
b
etter
r
esu
lts
an
d
h
ig
h
er
ac
cu
r
ac
y
.
2
.
3
.
So
f
t
wa
re
dev
ices
T
h
e
r
e
s
e
a
r
c
h
e
r
s
u
s
e
d
p
y
t
h
o
n
,
a
h
i
g
h
-
l
e
v
e
l
p
r
o
g
r
a
m
m
i
n
g
l
a
n
g
u
a
g
e
t
o
d
e
v
e
l
o
p
t
h
e
f
a
c
e
r
e
c
o
g
n
i
t
i
o
n
p
r
o
g
r
a
m
.
I
t
w
a
s
i
n
t
e
g
r
a
te
d
w
i
th
t
h
e
o
p
e
n
-
s
o
u
r
c
e
c
o
m
p
u
t
e
r
v
i
s
i
o
n
(
O
p
e
n
C
V
)
l
i
b
r
a
r
y
[
1
7
]
.
Op
e
n
C
V
)
is
a
l
i
b
r
a
r
y
f
o
r
c
o
m
p
u
t
e
r
v
i
s
i
o
n
t
h
a
t
i
s
f
r
e
e.
I
t
c
o
u
l
d
b
e
u
s
e
d
i
n
w
e
b
d
e
v
e
l
o
p
m
e
n
t
w
i
t
h
t
h
e
a
i
d
o
f
d
i
f
f
e
r
e
n
t
f
r
a
m
e
w
o
r
k
s
s
u
c
h
a
s
D
j
a
n
g
o
,
Fl
a
s
k
,
a
n
d
P
y
r
a
m
i
d
.
T
h
e
p
y
r
a
m
i
d
f
r
a
m
ew
o
r
k
w
a
s
u
s
e
d
i
n
d
e
v
e
l
o
p
i
n
g
t
h
e
w
e
b
a
p
p
l
i
ca
t
i
o
n
t
h
a
t
r
e
c
e
i
v
e
d
a
n
d
d
is
p
l
a
y
e
d
t
h
e
r
e
p
o
r
t
s
o
f
i
n
t
r
u
d
e
r
s
d
e
te
c
t
e
d
b
y
t
h
e
u
s
e
r
.
J
Q
u
e
r
y
i
s
a
J
a
v
a
Sc
r
i
p
t
l
i
b
r
a
r
y
u
s
e
d
i
n
w
e
b
a
p
p
l
i
c
a
t
i
o
n
s
t
o
e
a
s
i
l
y
m
a
n
i
p
u
l
a
t
e
w
e
b
p
a
g
e
e
l
e
m
e
n
t
s
.
M
o
n
g
o
D
B
,
a
d
o
c
u
m
e
n
t
-
b
a
s
e
d
d
a
ta
b
a
s
e
m
a
n
a
g
e
m
e
n
t
s
y
s
te
m
,
s
e
r
v
e
s
as
s
t
o
r
a
g
e
o
f
d
a
t
a
t
h
at
is
n
e
c
es
s
a
r
y
f
o
r
t
h
e
f
u
n
c
t
i
o
n
a
l
i
t
y
o
f
t
h
e
p
r
o
t
o
t
y
p
e
.
T
o
c
o
n
n
e
c
t
t
h
e
w
e
b
p
a
g
e
a
n
d
t
h
e
s
e
r
v
e
r
,
as
y
n
c
h
r
o
n
o
u
s
J
a
v
aS
c
r
i
p
t
(
AJ
A
X
)
,
a
n
d
x
t
e
n
s
i
b
l
e
m
a
r
k
u
p
l
a
n
g
u
a
g
e
(
XM
L
)
w
e
r
e
u
s
e
d
t
o
s
e
n
d
a
P
OS
T
r
e
q
u
es
t
t
o
t
h
e
s
e
r
v
e
r
i
n
o
r
d
e
r
t
o
q
u
e
r
y
i
f
a
f
u
g
i
t
i
v
e
i
s
d
e
t
ec
t
e
d
o
r
n
o
t
.
2
.
4
.
Alg
o
rit
hm
s
T
h
e
f
ac
e
d
etec
tio
n
p
r
o
ce
d
u
r
e
was
b
ased
o
n
th
e
f
ea
tu
r
es
o
f
th
e
f
ac
e
(
ey
es,
n
o
s
e
,
an
d
m
o
u
th
)
r
ath
er
th
an
its
p
ix
els
b
ec
au
s
e
f
ea
tu
r
e
-
b
ased
s
y
s
tem
s
ca
n
b
e
o
p
e
r
ated
f
aster
th
an
p
i
x
el
-
b
ased
s
y
s
tem
s
.
I
t
u
s
es
a
Haar
-
lik
e
f
ea
tu
r
e
th
at
p
er
f
o
r
m
s
th
e
s
ca
lar
p
r
o
d
u
ct
o
f
th
e
Haa
r
-
lik
e
tem
p
lates
an
d
th
e
ca
p
tu
r
ed
im
ag
e
as
s
ee
n
in
Fig
u
r
e
3
.
Giv
en
th
e
p
atter
n
X
o
f
im
ag
e
A
with
th
e
s
am
e
s
ize
o
f
N×
N,
it is
d
ef
in
ed
b
y
(
1
)
.
∑
∑
A
(
i,j
)
-
1
X(
i,j
)
1≤
j
≤
N
1≤
i≤
N
is w
hit
e
=
∑
∑
A
(
i,j
)
-
1
X(
i,j
)
1≤
j
≤
N
1≤
i
≤
N
is b
l
a
c
k
(
1
)
T
h
e
im
ag
e
s
h
o
u
ld
b
e
n
o
r
m
ali
ze
d
b
ef
o
r
eh
a
n
d
b
y
its
m
ea
n
s
an
d
v
ar
ian
ce
f
o
r
th
e
d
if
f
er
e
n
t
lig
h
tin
g
p
o
s
itio
n
s
o
f
th
e
ca
p
tu
r
ed
i
m
a
g
e
[
1
8
]
.
T
h
e
in
teg
r
al
im
a
g
e
c
an
b
e
co
m
p
u
ted
u
s
in
g
in
ter
m
ed
iate
in
ter
p
r
etatio
n
f
o
r
th
e
im
ag
e
t
h
at
r
esu
lts
in
a
tr
ain
in
g
s
et
o
f
n
e
g
ati
v
e
a
n
d
p
o
s
itiv
e
im
ag
es.
I
t
is
b
ei
n
g
class
if
ied
u
s
in
g
Ad
aBo
o
s
t
class
if
ier
s
[
1
9
]
th
at
b
o
o
s
t
th
e
class
if
icatio
n
p
e
r
f
o
r
m
an
ce
o
f
a
lear
n
in
g
al
g
o
r
ith
m
.
T
h
e
Ad
a
-
B
o
o
s
t
alg
o
r
ith
m
co
m
b
in
es
all
th
e
w
ea
k
class
if
icatio
n
f
u
n
ctio
n
s
a
n
d
f
o
r
m
s
a
s
tr
o
n
g
er
class
if
ier
an
d
it
ap
p
r
o
ac
h
es
a
tr
ain
in
g
er
r
o
r
o
f
ze
r
o
ex
p
o
n
en
t
ially
in
th
e
n
u
m
b
er
o
f
r
o
u
n
d
s
o
f
tr
ain
in
g
[
1
9
]
,
[
2
0
]
.
Af
ter
p
er
f
o
r
m
in
g
th
e
lea
r
n
in
g
alg
o
r
ith
m
,
th
e
s
y
s
tem
tr
ain
s
c
ascad
e
class
if
ier
s
.
T
h
e
g
o
al
o
f
d
etec
tio
n
an
d
p
er
f
o
r
m
a
n
ce
o
f
th
e
s
y
s
tem
in
d
etec
tin
g
f
ac
e
is
d
ep
en
d
en
t
o
n
th
e
ca
s
ca
d
e
d
esig
n
p
r
o
ce
s
s
.
I
n
b
u
ild
in
g
a
ca
s
ca
d
e
d
etec
to
r
,
th
e
s
y
s
tem
s
elec
ts
th
e
m
ax
im
u
m
ac
ce
p
tab
le
f
alse
-
p
o
s
itiv
e
lay
er
(
f
)
,
an
d
th
e
m
i
n
im
u
m
ac
ce
p
tab
le
d
etec
tio
n
r
ate
p
er
l
ay
er
(
d
)
[
1
8
]
,
[
1
9
]
.
T
h
e
s
y
s
tem
also
s
elec
ts
Ftar
g
et
(
o
v
er
all
f
alse
-
p
o
s
it
iv
e
r
ate)
an
d
in
itializes
th
e
f
alse
p
o
s
itiv
e
an
d
th
e
d
etec
tio
n
r
ate
in
to
o
n
e.
Fig
u
r
e
3
s
h
o
ws
th
e
lo
o
p
i
n
g
co
n
d
itio
n
o
f
th
e
tr
ain
in
g
alg
o
r
ith
m
o
f
a
ca
s
c
ad
e
d
etec
to
r
.
T
h
e
alg
o
r
ith
m
u
s
ed
s
ets
o
f
n
eg
ativ
e
an
d
p
o
s
itiv
e
ex
am
p
les
in
tr
ain
in
g
in
f
ea
t
u
r
es
u
s
in
g
Ad
a
B
o
o
s
t
an
d
ev
alu
ated
c
u
r
r
en
t
c
ascad
e
class
if
ier
s
to
d
eter
m
in
e
f
alse
p
o
s
itiv
e
r
ate
ca
s
ca
d
e
Fi an
d
th
e
d
etec
tio
n
r
ate
Di
[
1
9
]
.
Af
ter
th
e
s
y
s
tem
d
etec
ts
an
y
f
ac
es,
th
e
s
y
s
tem
w
ill
th
en
r
ec
o
g
n
ize
if
th
e
d
etec
ted
f
ac
e
is
an
in
tr
u
d
er
o
r
n
o
t.
Dif
f
er
en
t
alg
o
r
ith
m
s
w
er
e
co
n
s
id
er
ed
i
n
in
tr
u
d
e
r
d
etec
tio
n
.
T
h
e
s
y
s
tem
u
s
ed
a
tem
p
late
-
b
ased
ap
p
r
o
ac
h
to
f
ac
e
r
ec
o
g
n
itio
n
th
at
co
m
p
ar
es
im
ag
es
with
s
ets
o
f
tem
p
lates
f
r
o
m
a
d
atab
ase
[
2
1
]
.
Sets
o
f
tem
p
lates
wer
e
co
n
s
tr
u
cted
u
s
in
g
d
if
f
er
e
n
t
alg
o
r
ith
m
to
o
ls
lik
e
p
r
in
cip
al
c
o
m
p
o
n
en
t
a
n
aly
s
is
(
PC
A)
[
2
2
]
,
[
2
3
]
u
s
in
g
eig
e
n
f
ac
es
alg
o
r
it
h
m
,
lin
ea
r
d
is
cr
im
in
an
t
an
al
y
s
is
(
L
DA)
[
2
4
]
u
s
in
g
f
is
h
er
f
ac
es
alg
o
r
ith
m
,
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
i
n
e
(
SV
M)
[
2
5
]
u
s
in
g
l
o
ca
l
b
i
n
ar
y
p
a
tter
n
h
is
to
g
r
a
m
,
th
e
tem
p
late
m
atch
in
g
al
g
o
r
ith
m
[
2
6
]
,
an
d
th
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
[
1
5
]
.
T
h
e
r
esear
ch
e
r
s
cr
ea
ted
th
e
cr
iter
ia
ev
alu
atio
n
o
f
th
e
s
y
s
tem
to
id
en
tify
th
e
ap
p
r
o
p
r
iate
an
d
b
est
f
ac
e
r
ec
o
g
n
itio
n
alg
o
r
ith
m
to
b
e
u
s
ed
i
n
in
tr
u
d
er
d
et
ec
tio
n
.
T
h
is
cr
iter
ia
ev
alu
atio
n
is
co
m
p
o
s
ed
o
f
illu
m
in
atio
n
,
f
ac
e
d
is
tan
ce
,
tim
e
c
o
m
p
lex
ity
,
c
o
n
f
id
e
n
ce
lev
el,
a
n
d
f
ac
ial
f
ea
tu
r
e.
Fig
u
r
e
4
r
ep
r
esen
ts
th
e
p
s
eu
d
o
co
d
e
o
f
t
h
e
d
if
f
er
e
n
t
cr
iter
ia
in
th
e
s
y
s
tem
.
T
h
e
r
asp
b
er
r
y
p
i
(
R
Pi)
ca
m
er
a
r
ea
d
s
im
ag
es
a
n
d
c
o
n
v
er
ts
th
em
i
n
to
th
e
f
r
am
e
th
e
n
th
e
f
r
am
e
will
b
e
c
o
n
v
e
r
ted
i
n
to
b
lac
k
an
d
wh
ite
f
o
r
m
.
T
h
e
Vio
la
-
J
o
n
es
alg
o
r
it
h
m
will
d
etec
t
th
e
f
ac
e
o
n
t
h
e
f
r
am
e
th
e
n
it
will
b
e
co
m
p
a
r
e
d
to
t
h
e
d
atab
ase
o
f
f
ac
es
an
d
p
er
f
o
r
m
s
th
e
f
iv
e
alg
o
r
ith
m
s
f
o
r
f
ac
e
r
ec
o
g
n
i
tio
n
.
T
h
e
cr
iter
ia
e
v
alu
atio
n
will
ev
alu
ate
th
e
illu
m
in
atio
n
(
d
a
r
k
)
,
an
d
p
er
f
o
r
m
lo
ca
l
b
in
ar
y
p
atter
n
alg
o
r
ith
m
(
lb
p
h
)
,
eig
e
n
f
ac
e
(
eig
e
n
)
,
f
i
s
h
er
f
ac
es
(
f
is
h
er
)
,
an
d
d
ee
p
lear
n
in
g
alg
o
r
ith
m
(
d
l)
.
Fo
r
th
e
f
ac
e
an
g
le,
tem
p
l
ate
m
atch
in
g
,
d
l,
an
d
lb
p
h
will
b
e
ev
alu
ated
.
T
h
e
alg
o
r
ith
m
with
t
h
e
h
ig
h
est
p
e
r
ce
n
tag
e
o
f
in
tr
u
d
er
r
ec
o
g
n
itio
n
will
b
e
d
is
p
lay
ed
in
th
e
o
u
tp
u
t.
T
h
e
ca
m
er
a
ca
p
tu
r
es
an
im
ag
e
t
h
at
s
er
v
es
as
an
in
p
u
t
f
o
r
r
asp
b
e
r
r
y
p
i.
T
h
e
r
asp
b
er
r
y
p
i
th
en
p
r
ep
ar
es
th
e
im
ag
e
to
b
e
p
r
o
ce
s
s
ed
in
to
th
e
f
iv
e
alg
o
r
ith
m
s
.
T
h
e
f
iv
e
alg
o
r
ith
m
s
ar
e
lo
ca
l
b
in
ar
y
p
atter
n
h
is
to
g
r
am
,
f
is
h
er
f
ac
es,
eig
en
f
ac
e
s
,
tem
p
late
m
atch
in
g
,
an
d
d
ee
p
lear
n
i
n
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tr
u
d
er d
etec
tio
n
a
n
d
r
ec
o
g
n
itio
n
u
s
in
g
d
iffer
en
t ima
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es fo
r
… (
N
elso
n
C
.
R
o
d
ela
s
)
847
Fig
u
r
e
3
.
T
r
ain
in
g
al
g
o
r
ith
m
f
o
r
b
u
ild
i
n
g
ca
s
ca
d
e
d
etec
to
r
[
1
9
]
Fig
u
r
e
4
.
Ps
eu
d
o
c
o
d
e
f
o
r
c
r
iter
ia
ev
alu
atio
n
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
m
ain
o
b
jectiv
e
o
f
th
e
r
e
s
ea
r
ch
is
to
in
n
o
v
ate
a
p
r
o
ac
tiv
e
s
u
r
v
eillan
ce
d
e
v
ice
th
at
is
u
s
ed
to
d
etec
t
an
d
r
ec
o
g
n
ize
in
tr
u
d
er
s
.
T
h
is
d
ev
ice
u
s
es
d
if
f
er
en
t
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
i
q
u
es
an
d
cr
iter
ia
ev
alu
atio
n
f
o
r
ac
cu
r
ate
r
ec
o
g
n
itio
n
o
f
in
tr
u
d
er
/s
.
Sp
ec
if
ically
,
th
e
m
ain
o
b
jectiv
es
o
f
th
e
s
y
s
tem
ar
e
to
id
en
tify
th
e
d
if
f
er
en
t im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es th
at
p
r
o
ac
tiv
ely
s
eize
d
im
ag
es f
o
r
s
u
r
v
eillan
ce
,
d
ete
ct
an
d
r
ec
o
g
n
ize
an
in
tr
u
d
er
b
y
d
if
f
er
en
t
im
a
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es,
cr
ea
te
a
f
r
am
ewo
r
k
t
h
at
ch
o
o
s
es
an
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
as
an
alg
o
r
ith
m
to
p
r
o
ac
tiv
ely
p
er
f
o
r
m
s
u
r
v
eill
an
ce
an
d
to
m
o
n
ito
r
a
n
d
n
o
t
if
y
th
e
h
o
u
s
eh
o
l
d
o
wn
er
s
an
d
a
u
th
o
r
ities
u
s
in
g
t
h
e
m
o
b
ile
a
p
p
licatio
n
o
n
ce
th
e
f
t in
cid
en
ts
h
ap
p
en
ed
.
F
i
g
u
r
e
5
s
h
o
ws
t
h
e
s
a
m
p
l
e
r
esu
l
t
o
f
t
h
e
s
y
s
t
e
m
.
T
h
e
s
y
s
t
e
m
w
a
s
t
r
a
i
n
e
d
t
o
d
e
te
c
t
a
n
d
r
e
c
o
g
n
i
z
e
f
a
c
es
o
n
t
h
e
c
a
p
t
u
r
e
d
i
m
a
g
e
s
o
n
t
h
e
s
u
r
v
e
i
l
l
a
n
ce
c
a
m
e
r
a
.
A
f
i
f
t
e
e
n
s
t
a
g
e
c
as
c
a
d
e
d
c
la
s
s
i
f
i
e
r
s
w
e
r
e
t
r
a
i
n
e
d
a
n
d
f
a
l
s
e
l
y
e
l
i
m
i
n
a
te
d
0
.
2
%
o
f
t
h
e
f
a
c
e
p
a
t
t
e
r
n
s
[
2
7
]
.
T
h
e
s
y
s
t
e
m
w
as
e
x
p
e
c
t
e
d
t
o
h
a
v
e
a
f
a
l
s
e
a
l
a
r
m
r
a
t
e
o
f
0
.
0
0
2
1
5
o
r
4
.
1
×
1
0
-
3
3
a
n
d
a
h
i
t
r
a
te
o
f
0
.
9
9
8
1
5
o
r
0
.
9
7
.
T
h
e
s
y
s
te
m
w
as
t
r
a
i
n
e
d
b
y
t
h
e
c
a
p
t
u
r
e
d
p
i
c
t
u
r
e
s
f
r
o
m
t
h
e
c
a
m
e
r
a
w
i
t
h
a
f
a
c
e
t
r
a
i
n
i
n
g
s
e
t
o
f
o
v
e
r
4
,
0
0
0
l
a
b
e
l
e
d
f
a
c
e
s
wi
t
h
a
b
as
e
r
e
s
o
l
u
t
i
o
n
o
f
2
4
×
2
4
p
i
x
e
l
s
.
T
h
e
s
y
s
tem
was
test
ed
in
a
r
ea
l
-
wo
r
ld
s
itu
atio
n
a
n
d
ca
p
tu
r
ed
a
s
er
ie
s
o
f
im
ag
es
u
s
in
g
th
e
s
er
ial
ca
m
er
a
an
d
p
r
o
ce
s
s
ed
b
y
p
r
o
ac
tiv
e
f
ac
e
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
.
Usi
n
g
th
e
d
if
f
e
r
en
t
s
u
b
-
alg
o
r
ith
m
s
an
d
class
if
ier
s
,
th
e
s
y
s
tem
ca
n
au
t
o
m
atica
lly
d
etec
t
f
a
ce
s
o
r
f
ac
es
in
a
s
in
g
le
f
r
am
e.
T
h
e
co
lo
r
o
f
th
e
f
r
am
e
(
b
o
x
o
n
th
e
f
ac
e
)
ca
n
b
e
ed
ited
in
th
e
co
d
e.
T
h
e
s
y
s
tem
p
r
o
d
u
ce
d
a
f
r
am
e
o
r
b
o
x
o
n
th
e
d
ete
cted
f
ac
e.
T
h
e
b
o
x
co
n
tain
s
two
co
l
o
r
s
,
a
r
ec
o
g
n
ized
f
ac
e
f
r
o
m
th
e
d
atab
as
e
r
ep
r
esen
ted
b
y
a
g
r
ee
n
b
o
x
an
d
an
in
tr
u
d
er
r
ep
r
esen
ted
b
y
a
r
e
d
b
o
x
.
T
h
is
r
ec
o
g
n
itio
n
is
d
is
cu
s
s
ed
in
th
e
n
ex
t sectio
n
.
Fig
u
r
e
5
.
Sam
p
le
f
ac
e
d
etec
tio
n
u
s
in
g
Vio
la
-
J
o
n
es
alg
o
r
ith
m
3
.
1
.
De
t
ec
t
io
n
co
ns
t
ra
ints
T
h
e
m
ain
p
u
r
p
o
s
e
o
f
th
e
s
y
s
tem
was
to
d
etec
t
an
d
to
r
ec
o
g
n
ize
i
n
tr
u
d
e
r
e
n
tr
y
in
t
h
e
h
o
u
s
e
in
r
ea
l
-
tim
e
an
d
n
o
tif
y
th
e
o
wn
er
s
an
d
s
en
d
a
p
ictu
r
e
o
f
th
e
ca
p
tu
r
e
d
im
ag
e
.
Ho
wev
e
r
,
m
o
s
t
o
f
t
h
e
in
tr
u
d
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
84
3
-
8
52
848
wo
r
e
a
b
o
n
n
et,
ca
p
,
o
r
ev
e
n
c
o
v
er
h
is
/h
er
f
ac
e
esp
ec
ially
if
th
ey
k
n
o
w
h
o
u
s
eh
o
ld
s
u
r
v
eil
lan
ce
ca
m
er
as.
T
h
e
s
y
s
tem
co
n
s
id
er
ed
th
is
s
ce
n
ar
io
b
y
s
ee
in
g
th
e
m
o
tio
n
d
ete
ctio
n
alg
o
r
ith
m
if
th
e
s
y
s
tem
d
id
n
o
t
d
etec
t
a
n
y
f
ac
e.
T
h
is
alg
o
r
ith
m
was f
o
cu
s
ed
o
n
ea
ch
f
r
a
m
e
p
r
o
d
u
ce
d
b
y
th
e
s
er
ial
ca
m
er
a
an
d
co
m
p
a
r
ed
th
em
all
to
ea
ch
o
th
er
an
d
an
al
y
ze
d
if
th
ese
f
r
am
es
h
av
e
th
e
s
am
e
th
r
esh
o
ld
.
T
h
e
p
s
eu
d
o
co
d
e
f
o
r
m
o
tio
n
d
etec
tio
n
was
ac
tiv
ated
af
ter
s
ea
r
ch
in
g
f
o
r
t
h
e
f
ac
e
[
7
]
.
T
h
e
s
u
r
v
eillan
ce
ca
m
er
a
was
elev
ated
to
a
d
is
tan
ce
o
f
f
iv
e
to
s
i
x
m
eter
s
f
r
o
m
th
e
en
t
r
an
ce
o
f
th
e
h
o
u
s
e
to
ca
p
t
u
r
e
th
e
f
r
a
m
e.
On
ce
d
etec
ted
,
th
e
s
y
s
tem
th
en
n
o
tifie
d
th
e
o
wn
er
s
an
d
was
ask
ed
to
t
r
ig
g
er
th
e
alar
m
b
u
tto
n
.
Af
ter
f
ac
e
d
etec
tio
n
,
th
e
s
y
s
te
m
p
er
f
o
r
m
e
d
f
ac
e
r
ec
o
g
n
itio
n
.
3
.
2
.
F
a
ce
re
co
g
nitio
n r
esu
lt
s
T
h
is
s
ec
tio
n
d
is
cu
s
s
es
h
o
w
th
e
s
y
s
tem
p
er
f
o
r
m
s
a
d
if
f
er
e
n
t
alg
o
r
ith
m
f
o
r
f
ac
e
r
ec
o
g
n
i
tio
n
.
T
h
e
s
y
s
tem
p
er
f
o
r
m
s
f
iv
e
alg
o
r
ith
m
s
in
f
ac
e
r
ec
o
g
n
itio
n
,
an
d
e
ac
h
o
f
th
ese
al
g
o
r
ith
m
s
h
ad
a
u
n
iq
u
e
p
r
o
ce
s
s
in
r
ec
o
g
n
izin
g
th
e
d
etec
ted
im
ag
e.
T
h
e
s
y
s
tem
u
s
ed
th
e
Op
en
C
V
lib
r
ar
y
in
p
er
f
o
r
m
i
n
g
f
ac
e
r
ec
o
g
n
itio
n
.
Op
en
C
V
is
a
cr
o
s
s
-
p
latf
o
r
m
lib
r
ar
y
th
at
f
o
cu
s
es
o
n
th
e
latest
co
m
p
u
ter
v
is
io
n
alg
o
r
ith
m
s
an
d
r
ea
l
-
tim
e
im
ag
e
p
r
o
ce
s
s
in
g
.
I
n
ter
m
s
o
f
t
h
e
d
at
ab
ase,
th
e
r
esear
c
h
er
s
cr
ea
ted
th
e
d
ata
s
et
b
y
u
p
lo
ad
i
n
g
p
ictu
r
es
o
f
f
iv
e
p
er
s
o
n
s
in
f
iv
e
d
if
f
e
r
en
t
p
o
s
es,
illu
m
in
atio
n
s
,
an
d
f
ac
e
an
g
les
f
o
r
test
in
g
p
u
r
p
o
s
es.
Op
en
C
V
cr
ea
ted
a
co
m
m
a
-
s
ep
ar
ated
v
al
u
e
(
C
SV)
f
ile
o
f
th
ese
twen
ty
-
f
iv
e
im
ag
es
s
in
c
e
it
is
th
e
s
im
p
lest
in
d
e
p
en
d
e
n
t
p
latf
o
r
m
th
at
ca
n
b
e
u
s
ed
.
T
ab
le
1
s
h
o
ws
th
e
d
is
tr
ib
u
tio
n
o
f
th
e
p
e
r
ce
n
tag
e
o
f
th
e
s
u
cc
ess
r
ate
o
f
in
tr
u
d
er
r
ec
o
g
n
it
io
n
.
T
h
ese
ar
e
th
e
r
esu
lts
o
f
th
e
test
in
g
f
o
r
ea
ch
alg
o
r
ith
m
an
d
its
s
u
cc
ess
r
ate
in
r
ec
o
g
n
izin
g
in
tr
u
d
e
r
s
wh
o
en
ter
ed
th
e
h
o
u
s
e
u
s
in
g
th
e
d
ataset.
T
h
e
r
esu
lt
s
h
o
ws
th
at
all
o
f
th
em
h
ad
a
h
ig
h
s
u
cc
ess
r
ate.
T
h
e
lo
west
s
u
cc
ess
r
ate
p
er
f
o
r
m
an
ce
was
th
e
te
m
p
late
m
atch
in
g
with
a
r
ate
o
f
8
9
.
1
2
%.
T
h
e
h
ig
h
est
s
u
cc
ess
r
ate
p
er
f
o
r
m
a
n
ce
was
th
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
with
a
r
ate
o
f
9
7
.
3
2
%.
T
ab
le
1
.
I
m
ag
e
in
tr
u
d
er
s
u
cc
e
s
s
r
ate
A
l
g
o
r
i
t
h
m
S
u
c
c
e
ss
R
a
t
e
Ei
g
e
n
f
a
c
e
9
2
.
9
6
F
i
sh
e
r
f
a
c
e
9
3
.
8
4
Lo
c
a
l
B
i
n
a
r
y
P
a
t
t
e
r
n
9
3
.
0
8
Te
mp
l
a
t
e
M
a
t
c
h
i
n
g
8
9
.
1
2
D
e
e
p
Le
a
r
n
i
n
g
9
7
.
3
2
Fig
u
r
e
6
s
h
o
ws th
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
o
f
th
e
n
u
m
b
e
r
o
f
test
in
g
co
n
d
u
cted
u
s
in
g
th
e
s
y
s
tem
an
d
th
e
p
er
ce
n
tag
e
r
ate
o
f
ea
ch
alg
o
r
ith
m
in
r
ec
o
g
n
izin
g
th
e
h
o
m
eo
wn
er
s
o
r
th
e
f
ac
es
th
at
ar
e
s
av
ed
in
th
e
d
atab
ase.
T
h
e
r
esu
lt
s
h
o
ws
t
h
at
th
er
e
is
a
lo
wer
p
er
ce
n
tag
e
r
ate
o
f
d
etec
tin
g
in
tr
u
d
e
r
s
o
n
m
o
s
t
o
f
th
e
a
lg
o
r
ith
m
s
.
Fig
u
r
e
7
r
e
p
r
esen
t
s
th
e
g
r
ap
h
ical
r
ep
r
esen
tatio
n
o
f
in
tr
u
d
er
d
etec
tio
n
an
d
r
ec
o
g
n
itio
n
o
f
d
if
f
er
en
t
alg
o
r
ith
m
s
o
v
er
its
n
u
m
b
er
o
f
test
in
g
.
I
t
r
ec
o
g
n
izes
th
at
th
e
r
e
was
an
in
tr
u
d
er
in
th
e
h
o
u
s
e
.
T
h
e
alar
m
s
y
s
tem
will
th
en
ac
tiv
ate,
an
d
n
o
tifi
ca
ti
o
n
o
f
h
o
m
eo
wn
e
r
s
an
d
g
o
v
er
n
m
e
n
t
au
th
o
r
ities
wer
e
n
o
tifie
d
.
Af
ter
th
e
d
if
f
er
en
t
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
wer
e
p
er
f
o
r
m
ed
,
th
e
s
y
s
tem
p
er
f
o
r
m
ed
cr
iter
ia
ev
alu
atio
n
f
r
am
ewo
r
k
to
r
ec
o
m
m
e
n
d
th
e
b
est alg
o
r
it
h
m
to
s
en
d
im
a
g
es to
th
e
s
y
s
te
m
s
er
v
er
an
d
to
m
o
b
ile
ap
p
lic
atio
n
.
Fig
u
r
e
6
.
Dete
ctio
n
a
n
d
r
ec
o
g
n
itio
n
o
f
h
o
m
e
o
wn
er
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tr
u
d
er d
etec
tio
n
a
n
d
r
ec
o
g
n
itio
n
u
s
in
g
d
iffer
en
t ima
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es fo
r
… (
N
elso
n
C
.
R
o
d
ela
s
)
849
T
ab
le
2
s
h
o
ws
th
e
r
esu
lts
o
f
t
h
e
cr
iter
ia
e
v
alu
atio
n
test
in
g
c
o
n
d
u
cte
d
b
y
ea
ch
cr
iter
io
n
.
I
t
s
h
o
ws
th
at
tem
p
late
m
atch
in
g
an
d
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
r
ec
o
g
n
i
ze
d
th
e
d
ataset
in
th
e
cr
iter
i
a
f
ac
e
an
g
le,
wh
ile
tem
p
late
m
atch
in
g
was
th
e
o
n
ly
alg
o
r
ith
m
u
n
ab
le
to
r
ec
o
g
n
ize
th
e
d
ataset.
On
e
o
f
th
e
r
ea
s
o
n
s
is
th
at
th
is
alg
o
r
ith
m
o
n
ly
m
atch
es
th
e
d
a
taset
an
d
th
e
ca
p
tu
r
ed
im
ag
e
[
2
6
]
.
Sin
ce
th
e
e
n
tire
alg
o
r
ith
m
h
ad
its
p
r
o
ce
d
u
r
e
in
r
ec
o
g
n
izin
g
th
e
im
a
g
e,
it
is
ev
id
en
t
th
at
r
ec
o
g
n
ized
im
ag
es
in
th
eir
co
n
f
id
e
n
ce
lev
el.
Fi
s
h
er
f
ac
e
alg
o
r
ith
m
was
m
o
r
e
ac
cu
r
ate
wh
en
it
co
m
es
to
tim
e
co
m
p
lex
ity
an
d
th
e
d
ee
p
lear
n
in
g
alg
o
r
ith
m
h
ad
a
h
ig
h
er
p
er
ce
n
tag
e
o
f
r
ec
o
g
n
itio
n
in
ter
m
s
o
f
f
ac
ial
f
ea
tu
r
es.
T
h
ese
r
esu
lts
wer
e
u
s
ed
to
o
u
tp
u
t
th
e
im
ag
e
o
n
th
e
m
o
b
ile
ap
p
licatio
n
f
o
r
n
o
tific
atio
n
o
f
in
tr
u
d
er
s
.
T
h
e
r
esu
lt
was
d
if
f
er
en
t
wh
en
th
e
s
y
s
tem
ca
p
tu
r
ed
a
p
ictu
r
e
o
f
th
e
d
etec
ted
in
tr
u
d
er
.
T
h
e
r
esu
lt
o
f
t
h
e
test
in
g
s
h
o
ws
th
e
p
r
o
ce
s
s
o
f
ch
o
o
s
in
g
t
h
e
r
ig
h
t
alg
o
r
ith
m
t
o
b
e
u
s
ed
in
ea
ch
s
ce
n
ar
io
to
p
r
o
ac
tiv
ely
p
er
f
o
r
m
s
u
r
v
eillan
c
e.
I
t
g
av
e
an
ac
cu
r
ate
r
esu
lt
o
f
th
e
im
a
g
e
an
d
th
e
r
ig
h
t
o
u
t
p
u
t
in
n
o
tify
in
g
th
e
h
o
m
e
o
wn
er
s
wh
eth
er
th
e
ca
p
tu
r
e
d
im
a
g
e
is
an
in
tr
u
d
e
r
o
r
n
o
t.
T
h
e
r
esu
lt
also
s
h
o
ws
th
at
d
ee
p
lear
n
in
g
alg
o
r
ith
m
s
ca
n
g
iv
e
h
ig
h
er
p
e
r
ce
n
tag
e
r
esu
lts
in
f
o
u
r
o
u
t o
f
f
iv
e
c
r
iter
i
a
ev
alu
atio
n
.
Fig
u
r
e
7
.
Dete
ctio
n
a
n
d
r
ec
o
g
n
itio
n
o
f
i
n
tr
u
d
e
r
s
T
ab
le
2
.
R
esu
lts
o
f
th
e
s
u
cc
ess
r
ate
o
f
in
tr
u
d
er
r
ec
o
g
n
itio
n
w
ith
cr
iter
ia
ev
alu
atio
n
I
n
%
A
l
g
o
r
i
t
h
m
F
a
c
e
A
n
g
l
e
I
l
l
u
mi
n
a
t
i
o
n
C
o
n
f
i
d
e
n
c
e
L
e
v
e
l
Ti
me
C
o
m
p
l
e
x
i
t
y
F
a
c
i
a
l
F
e
a
t
u
r
e
Ei
g
e
n
f
a
c
e
1
4
.
2
9
9
7
.
1
0
7
4
.
2
9
7
7
.
1
4
8
2
.
8
6
F
i
sh
e
r
f
a
c
e
2
0
.
0
0
7
4
.
2
9
8
0
.
0
0
9
4
.
2
9
1
4
.
2
9
Lo
c
a
l
B
i
n
a
r
y
P
a
t
t
e
r
n
1
1
.
4
3
6
5
.
7
1
7
1
.
4
3
1
8
.
0
0
7
.
0
0
Te
mp
l
a
t
e
M
a
t
c
h
i
n
g
5
4
.
2
9
1
7
.
1
4
7
7
.
1
4
2
5
.
7
1
8
8
.
5
7
D
e
e
p
Le
a
r
n
i
n
g
8
0
.
0
0
9
1
.
4
3
8
8
.
5
7
1
4
.
2
9
9
4
.
2
9
3
.
3
.
H
a
rdwa
re
a
nd
s
o
f
t
wa
r
e
inte
g
ra
t
io
n
T
h
e
s
y
s
tem
was
co
m
p
o
s
ed
o
f
h
ar
d
war
e
d
ev
ices
f
o
r
m
o
n
ito
r
in
g
an
d
n
o
tific
atio
n
.
T
h
ese
d
ev
ices
ar
e
r
asp
b
er
r
y
p
i
,
s
er
ial
ca
m
er
a,
I
R
,
alar
m
,
GSM
m
o
d
u
le
lap
t
o
p
o
r
d
esk
to
p
f
o
r
s
er
v
e
r
an
d
ce
llp
h
o
n
e
with
m
o
b
ile
ap
p
s
o
f
twar
e
in
s
talled
o
n
it.
A
s
er
v
er
ca
n
m
o
n
ito
r
an
d
r
ec
o
r
d
ev
e
n
ts
in
r
ea
l
-
tim
e
an
d
s
av
e
th
em
to
th
e
d
atab
ase.
T
h
e
p
r
o
ce
s
s
o
f
n
o
tifi
ca
tio
n
was d
ep
en
d
en
t
o
n
th
e
d
etec
ted
an
d
r
ec
o
g
n
ized
f
ac
e
o
f
th
e
s
y
s
tem
.
I
t w
ill
n
o
t
f
u
n
ctio
n
wh
en
th
e
r
ec
o
g
n
ized
f
ac
e
is
o
n
th
e
d
atab
ase.
T
h
e
n
o
tific
atio
n
will
o
n
ly
f
u
n
ct
io
n
o
n
c
e
th
e
s
y
s
tem
d
etec
ted
an
d
r
ec
o
g
n
ize
d
th
e
in
tr
u
d
er
.
W
h
en
th
e
s
y
s
tem
d
etec
ted
,
an
in
tr
u
d
er
with
r
ea
l
-
tim
e
d
ate
a
n
d
tim
e,
th
e
s
y
s
tem
th
en
au
to
m
atica
lly
tr
ig
g
er
ed
th
e
alar
m
s
y
s
tem
o
f
th
e
h
o
u
s
e
an
d
th
e
m
o
b
ile
ap
p
lica
tio
n
u
s
er
ca
n
o
n
ly
tu
r
n
o
f
f
th
e
alar
m
.
I
f
th
e
m
o
b
ile
d
ata
is
n
o
t
a
v
ailab
le,
s
in
ce
it
was
ac
tiv
ated
u
s
in
g
th
e
i
n
t
er
n
et,
th
e
r
e
was
a
n
o
tific
atio
n
u
s
in
g
th
e
SMS
in
f
o
r
m
in
g
t
h
at
in
tr
u
d
er
was e
n
ter
in
g
th
e
h
o
u
s
e.
T
h
e
r
esear
ch
er
s
also
test
ed
th
e
p
er
f
o
r
m
an
ce
o
f
d
if
f
e
r
en
t
p
h
y
s
ical
co
m
p
o
n
e
n
ts
o
f
th
e
s
y
s
tem
to
ch
ec
k
th
e
r
eliab
ilit
y
o
f
th
e
d
ev
ices
s
u
ch
as
th
e
ala
r
m
s
y
s
tem
,
SMS
m
ess
ag
in
g
o
f
th
e
GSM
m
o
d
u
le,
th
e
r
an
g
e
o
f
th
e
r
asp
b
er
r
y
p
i
ca
m
er
a,
an
d
th
e
clo
u
d
co
m
p
u
tin
g
s
en
d
i
n
g
ca
p
ab
ilit
ies
o
f
th
e
s
y
s
tem
.
E
n
s
u
r
in
g
th
e
p
r
o
p
e
r
o
p
er
atio
n
s
o
f
th
e
ala
r
m
s
y
s
te
m
an
d
p
r
o
p
e
r
c
o
m
m
u
n
icatio
n
to
th
e
r
asp
b
er
r
y
p
i
is
o
n
e
o
f
th
e
p
u
r
p
o
s
es
o
f
test
in
g
th
e
r
esp
o
n
s
e
tim
e
o
f
th
e
alar
m
s
y
s
tem
.
T
h
e
r
esear
ch
er
s
test
e
d
th
e
alar
m
r
esp
o
n
s
e
tim
e
b
y
tab
u
l
atin
g
th
e
d
elay
tim
e
b
ef
o
r
e
t
h
e
ac
tiv
atio
n
o
f
th
e
alar
m
s
y
s
tem
.
T
h
e
r
esear
ch
er
s
test
ed
2
0
u
n
r
ec
o
g
n
ize
d
im
ag
es.
On
ce
th
e
r
asp
b
er
r
y
p
i
r
ec
o
g
n
ized
an
in
tr
u
d
er
,
it
s
en
t
en
o
u
g
h
elec
tr
ic
ity
to
ac
tiv
ate
th
e
d
elay
m
o
d
u
le
an
d
th
is
d
elay
m
o
d
u
le
tr
ig
g
er
ed
th
e
alar
m
d
e
v
ice
to
b
e
ac
tiv
ated
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
84
3
-
8
52
850
T
h
e
av
er
ag
e
tim
e
r
ec
o
r
d
ed
f
o
r
th
e
r
esp
o
n
s
e
tim
e
was
2
9
.
6
3
s
ec
o
n
d
s
.
I
t
ca
n
b
e
s
aid
th
at
th
e
r
esp
o
n
s
e
tim
e
b
ef
o
r
e
th
e
alar
m
s
y
s
tem
to
b
e
ac
tiv
ated
g
iv
es
a
f
aster
r
ea
ctio
n
ev
en
if
th
e
s
y
s
tem
h
ad
m
an
y
f
u
n
ctio
n
alities
,
p
er
f
o
r
m
ed
alg
o
r
ith
m
s
,
an
d
cr
iter
ia
ev
al
u
atio
n
s
y
s
tem
.
T
h
e
s
y
s
tem
also
h
as
th
e
ca
p
ab
ilit
y
o
f
tex
tin
g
th
e
h
o
m
eo
wn
e
r
s
an
d
g
o
v
er
n
m
e
n
t
au
th
o
r
ities
wh
en
th
e
m
o
b
ile
ap
p
licatio
n
in
th
e
e
v
en
t
th
at
th
e
m
o
b
ile
ap
p
is
n
o
t
co
n
n
ec
te
d
to
th
e
in
t
er
n
et.
T
h
e
r
esear
ch
e
r
s
test
ed
th
e
tim
e
r
esp
o
n
s
e
o
f
th
e
GSM
m
o
d
u
le
b
y
s
en
d
in
g
tex
t
m
ess
ag
es
to
m
o
b
ile
ap
p
licatio
n
u
s
er
s
.
T
h
e
GSM
m
o
d
u
l
e
was
test
ed
b
ased
o
n
t
h
e
elap
s
ed
tim
e
in
s
en
d
in
g
th
e
tex
t
m
ess
ag
e
a
n
d
r
ec
eiv
in
g
th
e
m
ess
ag
e
b
y
th
e
m
o
b
ile
a
p
p
u
s
er
s
.
T
h
e
alar
m
s
y
s
tem
an
d
th
e
GSM
m
o
d
u
l
e
wer
e
s
im
u
ltan
e
o
u
s
ly
ac
tiv
ated
an
d
t
h
e
SMS
m
ess
ag
e
was
“
An
in
tr
u
d
e
r
h
as b
ee
n
d
etec
ted
in
y
o
u
r
h
o
u
s
e.
”
T
h
e
r
esear
ch
er
s
test
ed
twen
ty
u
n
r
ec
o
g
n
ized
im
a
g
es
to
tr
ig
g
er
th
e
s
y
s
tem
th
at
th
e
im
ag
e
is
an
in
tr
u
d
er
.
T
h
e
r
esear
ch
er
s
r
ec
o
r
d
ed
th
e
elap
s
ed
tim
e
in
r
ec
eiv
in
g
th
e
d
a
ta
f
r
o
m
th
e
s
y
s
tem
to
th
e
m
o
b
i
le
p
h
o
n
e
u
s
in
g
th
e
m
o
b
ile
ap
p
licatio
n
.
3
.
4
.
T
esting
re
s
ults
T
h
e
r
esear
ch
er
s
co
n
d
u
cted
tw
en
ty
tr
ials
an
d
tab
u
lated
th
e
tim
e
r
esp
o
n
s
e
o
f
tex
t m
ess
ag
es in
s
ec
o
n
d
s
.
T
h
e
av
er
a
g
e
r
esp
o
n
s
e
tim
e
is
3
4
.
7
6
s
ec
o
n
d
s
.
I
t
is
im
p
o
r
ta
n
t
to
id
e
n
tify
th
e
r
an
g
e
o
f
th
e
r
asp
b
er
r
y
p
i
s
er
ial
ca
m
er
a
in
ter
m
s
o
f
its
d
is
tan
c
e.
T
h
e
r
esear
ch
er
s
test
ed
a
n
d
co
m
p
u
ted
th
e
a
v
er
ag
e
d
is
tan
c
e
o
f
th
e
f
ac
e
im
ag
e
ca
p
tu
r
ed
b
y
th
is
d
ev
ice.
T
h
e
r
esear
ch
er
s
test
ed
th
e
ca
m
er
a
with
an
in
itial
d
is
tan
ce
o
f
4
.
5
in
ch
e
s
an
d
in
cr
ea
s
ed
it
b
y
ad
d
i
n
g
an
o
th
e
r
4
.
5
in
ch
e
s
u
n
til
it r
ea
ch
ed
a
p
o
i
n
t
th
at
t
h
e
ca
m
er
a
ca
n
n
o
l
o
n
g
e
r
r
ec
o
g
n
ize
th
e
im
ag
e.
Fo
r
an
in
ter
v
al
o
f
4
.
5
in
ch
es
f
o
r
ea
ch
test
,
th
e
r
esear
ch
er
s
ca
m
e
u
p
with
a
m
a
x
im
u
m
d
is
tan
ce
/r
an
g
e
o
f
9
4
.
4
9
in
ch
es
o
r
2
.
4
m
eter
s
.
T
h
e
s
y
s
tem
u
s
ed
clo
u
d
c
o
m
p
u
tin
g
i
n
s
en
d
in
g
th
e
d
etec
te
d
an
d
r
ec
o
g
n
ized
in
tr
u
d
er
s
in
to
th
e
h
o
u
s
e.
T
esti
n
g
th
e
av
er
a
g
e
tim
e
r
esp
o
n
s
e
o
f
th
e
clo
u
d
in
s
en
d
in
g
in
f
o
r
m
atio
n
was
test
ed
an
d
tab
u
lated
.
T
h
e
r
esear
ch
er
s
also
test
ed
th
e
lap
s
e
tim
e
f
r
o
m
n
o
tific
atio
n
o
f
c
lo
u
d
tech
n
o
lo
g
y
to
th
e
m
o
b
ile
ap
p
licatio
n
.
Ag
ain
,
th
e
r
esear
ch
er
s
u
s
ed
twen
ty
u
n
r
ec
o
g
n
ized
im
ag
es.
T
h
e
s
y
s
tem
was
co
n
n
ec
ted
to
b
r
o
ad
b
a
n
d
b
ec
a
u
s
e
th
e
r
asp
b
er
r
y
p
i
n
ee
d
ed
a
n
in
t
er
n
et
co
n
n
ec
tio
n
to
co
n
n
ec
t
t
o
th
e
m
o
b
ile
ap
p
licatio
n
.
T
h
e
s
en
d
in
g
ca
p
ab
ilit
y
o
f
th
e
s
y
s
tem
to
its
m
o
b
ile
ap
p
licatio
n
is
d
ep
en
d
en
t
o
n
th
e
s
tr
en
g
th
o
f
th
e
in
ter
n
et
co
n
n
e
ctio
n
.
T
h
e
av
er
a
g
e
r
esp
o
n
s
e
tim
e
o
f
clo
u
d
tech
n
o
lo
g
y
is
1
4
.
2
7
s
ec
o
n
d
s
th
er
e
f
o
r
e,
th
e
r
esear
ch
er
s
co
n
s
id
er
e
d
t
h
e
s
tr
en
g
th
o
f
t
h
e
in
ter
n
et
co
n
n
ec
tio
n
.
T
h
e
r
esear
ch
er
s
m
ad
e
s
u
r
e
t
h
at
all
th
e
f
ea
tu
r
es
o
f
th
e
s
y
s
tem
,
wh
eth
er
p
h
y
s
ical
d
ev
ic
es,
s
er
v
er
f
u
n
ctio
n
ality
,
o
r
m
o
b
ile
ap
p
licatio
n
ar
e
f
u
n
ctio
n
in
g
an
d
p
er
f
o
r
m
in
g
ac
co
r
d
in
g
to
th
e
f
lo
w
o
f
th
e
s
y
s
tem
.
T
h
e
s
er
v
er
o
f
t
h
e
s
y
s
tem
h
as
th
e
c
ap
ab
ilit
y
o
f
p
r
o
v
id
in
g
th
e
lis
t
o
f
d
etec
ted
a
n
d
r
ec
o
g
n
ized
in
tr
u
d
er
s
.
T
h
e
r
ep
o
r
t
was
co
m
p
o
s
ed
o
f
th
e
im
a
g
e
o
f
th
e
in
t
r
u
d
er
,
th
e
r
ate
o
r
p
er
ce
n
tag
e
o
f
in
tr
u
s
io
n
,
an
d
t
h
e
d
ate
-
tim
e
it
was
r
ec
o
g
n
ized
.
I
t
ca
n
also
b
e
s
ee
n
in
th
e
r
ep
o
r
t
th
at
th
e
s
y
s
tem
ca
n
d
etec
t
an
d
r
ec
o
g
n
ize
i
n
tr
u
d
er
s
th
at
wea
r
a
ca
p
,
o
r
e
v
en
th
e
f
ac
e
is
n
o
t
f
u
l
ly
s
ee
n
.
Fig
u
r
e
8
s
h
o
ws th
e
s
am
p
le
in
tr
u
s
io
n
r
ep
o
r
t o
f
th
e
s
y
s
tem
.
T
h
e
s
er
v
er
o
f
th
e
s
y
s
tem
h
as th
e
ca
p
ab
ilit
y
o
f
p
r
o
v
id
in
g
th
e
lis
t
o
f
d
etec
ted
an
d
r
ec
o
g
n
ized
in
tr
u
d
er
s
.
T
h
e
r
ep
o
r
t
in
clu
d
es
th
e
im
ag
e
o
f
th
e
in
tr
u
d
er
,
th
e
r
ate
o
r
p
e
r
ce
n
tag
e
o
f
in
tr
u
s
io
n
,
an
d
t
h
e
d
ate
-
tim
e
it
was
r
e
co
g
n
ized
.
I
t
ca
n
also
b
e
s
ee
n
th
at
th
e
s
y
s
tem
ca
n
d
etec
t a
n
d
r
ec
o
g
n
ize
i
n
tr
u
d
e
r
s
th
at
wea
r
a
ca
p
o
r
ev
e
n
th
e
f
ac
e
is
n
o
t f
u
lly
s
ee
n
.
Fig
u
r
e
8
.
Sam
p
le
i
n
tr
u
s
io
n
r
ep
o
r
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2502
-
4
7
5
2
I
n
tr
u
d
er d
etec
tio
n
a
n
d
r
ec
o
g
n
itio
n
u
s
in
g
d
iffer
en
t ima
g
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es fo
r
… (
N
elso
n
C
.
R
o
d
ela
s
)
851
4.
CO
NCLU
SI
O
N
T
h
e
r
ea
l
-
ti
m
e
r
ec
o
g
n
itio
n
an
d
n
o
tific
atio
n
o
f
h
o
u
s
eh
o
l
d
in
tr
u
d
er
s
is
a
s
y
s
tem
d
ev
elo
p
ed
s
p
ec
if
ically
f
o
r
t
h
e
u
s
e
o
f
h
o
m
eo
wn
e
r
s
.
T
h
e
s
o
f
twar
e
u
s
ed
d
if
f
er
e
n
t
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es.
I
n
tr
u
d
er
n
o
tific
atio
n
,
th
r
o
u
g
h
a
web
-
b
ased
m
o
b
ile
ap
p
licatio
n
,
is
r
ep
o
r
ted
b
y
t
h
e
s
er
v
er
in
r
ea
l
-
tim
e.
Ho
u
s
e
h
o
ld
o
wn
er
s
co
u
ld
r
esp
o
n
d
b
y
id
e
n
tify
in
g
if
th
e
p
er
s
o
n
d
etec
ted
is
an
in
tr
u
d
er
o
r
n
o
t.
I
f
an
in
tr
u
d
e
r
is
d
etec
ted
o
r
th
e
u
s
er
d
id
n
o
t
r
esp
o
n
d
at
a
g
iv
en
tim
e,
th
e
h
o
u
s
e
alar
m
will
b
e
ac
tiv
ated
.
I
t
is
,
th
er
ef
o
r
e,
co
n
clu
d
ed
t
h
at
th
e
f
iv
e
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
es
u
s
ed
b
y
th
e
r
esear
ch
er
s
ar
e
ev
id
e
n
t
i
n
r
ec
o
g
n
izin
g
th
e
im
ag
e
a
n
d
id
en
tify
in
g
wh
eth
e
r
th
e
p
ictu
r
e
ca
p
tu
r
ed
b
y
t
h
e
s
y
s
tem
is
an
in
tr
u
d
er
o
r
n
o
t.
T
h
e
d
if
f
er
en
t
alg
o
r
ith
m
s
h
av
e
u
n
iq
u
e
ch
ar
ac
ter
is
tics
th
at
ca
n
b
e
h
ig
h
lig
h
te
d
in
th
e
p
r
o
ce
s
s
o
f
g
i
v
in
g
d
ec
is
io
n
s
if
th
e
ca
p
tu
r
ed
p
ictu
r
e
ca
n
b
e
id
en
tifie
d
as
an
in
tr
u
d
er
o
r
n
o
t.
I
t
is
also
co
n
c
lu
d
ed
th
at
th
e
d
ee
p
lear
n
in
g
a
lg
o
r
ith
m
is
th
e
b
est
im
ag
e
p
r
o
ce
s
s
in
g
tech
n
iq
u
e
th
at
ca
n
b
e
u
s
ed
in
f
ac
e
r
ec
o
g
n
itio
n
b
ec
au
s
e
it
g
iv
es
a
h
ig
h
e
r
p
e
r
ce
n
ta
g
e
o
f
p
er
f
o
r
m
a
n
ce
r
esu
lts
b
ased
o
n
th
e
cr
iter
ia
ev
alu
atio
n
.
As
m
u
ch
as
th
e
r
e
is
o
n
e
alg
o
r
i
th
m
u
s
ed
i
n
f
ac
e
d
etec
tio
n
an
d
f
iv
e
alg
o
r
ith
m
s
in
f
ac
ial
r
ec
o
g
n
itio
n
,
it
is
r
ec
o
m
m
en
d
e
d
to
s
ea
r
ch
f
o
r
o
th
er
alg
o
r
ith
m
s
th
at
ca
n
b
e
ad
d
ed
t
o
th
e
s
y
s
tem
.
Sin
ce
ea
ch
alg
o
r
it
h
m
h
as
its
u
n
iq
u
e
way
o
f
d
etec
tin
g
an
d
r
ec
o
g
n
izin
g
a
f
ac
e
in
a
n
im
ag
e
,
th
e
r
esear
ch
er
s
also
r
ec
o
m
m
en
d
h
av
in
g
a
s
tr
es
s
test
in
g
o
f
th
e
s
aid
s
y
s
tem
t
o
en
s
u
r
e
th
e
ac
cu
r
ac
y
o
f
e
ac
h
alg
o
r
ith
m
in
a
g
iv
e
n
o
p
tim
al
s
o
lu
tio
n
in
r
ec
o
m
m
en
d
in
g
t
h
e
b
est
alg
o
r
it
h
m
to
b
e
u
s
ed
b
y
th
e
s
y
s
tem
.
Dif
f
er
en
t
cr
iter
ia
ev
alu
atio
n
s
u
s
ed
b
y
th
e
r
esear
ch
er
s
wer
e
ef
f
ec
tiv
e
a
n
d
p
r
o
d
u
ce
d
a
n
o
p
tim
al
s
o
l
u
tio
n
,
it
is
also
r
ec
o
m
m
e
n
d
ed
th
at
th
e
cr
iter
ia
ev
alu
atio
n
ca
n
b
e
en
h
a
n
ce
d
a
n
d
ad
d
m
o
r
e
cr
iter
ia
th
at
f
o
cu
s
o
n
a
lar
g
er
co
m
m
u
n
ity
.
I
t
is
r
ec
o
m
m
en
d
ed
also
to
p
r
esen
t th
e
s
y
s
tem
to
g
o
v
er
n
m
en
t a
g
e
n
cies a
n
d
p
r
iv
ate
co
m
p
an
ies f
o
r
m
ass
p
r
o
d
u
cti
o
n
o
f
th
e
s
y
s
tem
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
r
esear
ch
er
s
wo
u
ld
lik
e
to
th
an
k
th
e
Un
iv
er
s
ity
o
f
th
e
E
ast
Gr
ad
u
ate
Stu
d
ies
I
n
f
o
r
m
atio
n
an
d
C
o
m
m
u
n
icatio
n
Dep
a
r
tm
en
t
h
ea
d
ed
b
y
th
e
C
h
air
,
Dr
.
Den
n
is
Go
n
za
les
wh
o
p
r
o
v
id
ed
in
s
ig
h
t
an
d
ex
p
er
tis
e
th
at
g
r
ea
tly
ass
is
ted
th
e
r
ese
ar
ch
,
f
o
r
s
h
ar
in
g
th
eir
p
ea
r
ls
o
f
wis
d
o
m
with
u
s
d
u
r
i
n
g
th
e
co
u
r
s
e
o
f
th
is
r
esear
ch
.
W
e
also
th
an
k
th
e
p
a
n
elis
ts
wh
o
ar
e
alwa
y
s
willin
g
to
h
elp
in
th
e
im
p
r
o
v
em
e
n
t o
f
th
is
p
ap
er
.
RE
F
E
R
E
NC
E
S
[1
]
V.
P
ra
sh
y
a
n
u
s
o
rn
,
P
.
P
ra
sh
y
a
n
u
so
rn
,
S
.
Ka
v
i
y
a
,
Y.
F
u
ji
i,
a
n
d
P
.
P
.
Yu
p
a
p
i
n
,
“
Th
e
u
se
o
f
se
c
u
rit
y
c
a
m
e
ra
s
wit
h
p
riv
a
c
y
p
ro
tec
ti
n
g
a
b
il
it
y
,
”
Pr
o
c
e
d
ia
En
g
in
e
e
rin
g
,
v
o
l
.
8
,
p
p
.
3
0
1
-
3
0
7
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
ro
e
n
g
.
2
0
1
1
.
0
3
.
0
5
6
.
[2
]
A.
A.
Aly
,
S
.
Bin
De
ris,
a
n
d
N.
Zak
i
,
“
Re
se
a
rc
h
Re
v
iew
fo
r
Dig
it
a
l
Im
a
g
e
S
e
g
m
e
n
tat
io
n
Tec
h
n
iq
u
e
s,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
I
n
fo
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
3
,
n
o
.
5
,
p
p
.
9
9
-
1
0
6
,
2
0
1
1
,
d
o
i:
1
0
.
5
1
2
1
/i
jcs
it
.
2
0
1
1
.
3
5
0
9
.
[3
]
M
.
S
.
Alk
o
ffa
sh
,
S
.
Alq
ra
i
n
y
,
H
.
M
u
a
id
i,
a
n
d
M
.
Wed
y
a
n
,
“
A
n
o
v
e
l
a
p
p
ro
a
c
h
fo
r
fa
c
e
re
c
o
g
n
i
ti
o
n
b
a
se
d
o
n
a
m
u
lt
ip
le
fa
c
e
s
d
a
tab
a
se
,
”
J
o
u
rn
a
l
o
f
S
o
ft
w
a
re
En
g
in
e
e
rin
g
a
n
d
A
p
p
li
c
a
ti
o
n
s
,
v
o
l.
0
5
,
n
o
.
1
2
,
p
p
.
1
0
0
8
-
1
0
1
2
,
2
0
1
2
,
d
o
i:
1
0
.
4
2
3
6
/j
se
a
.
2
0
1
2
.
5
1
2
1
1
6
.
[4
]
P
.
Ka
u
r
a
n
d
K.
Ka
u
r,
"
Re
v
iew
o
f
Diffe
re
n
t
Ex
isti
n
g
Im
a
g
e
M
i
n
in
g
Tec
h
n
iq
u
e
s,"
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
C
o
mp
u
ter
S
c
ien
c
e
a
n
d
S
o
ft
w
a
re
En
g
in
e
e
rin
g
,
p
p
.
5
1
8
-
5
2
4
,
2
0
1
4
,
d
o
i:
1
0
.
1
8
5
1
7
/i
jas
e
it
.
1
0
.
1
.
1
0
2
2
7
.
[5
]
S
.
Bu
d
ij
o
n
o
,
J.
An
d
rian
t
o
a
n
d
M
.
N.
No
o
r,
"
De
sig
n
a
n
d
Im
p
lem
e
n
tatio
n
o
f
M
o
d
u
lar
Ho
m
e
S
e
c
u
ri
ty
S
y
ste
m
with
S
h
o
rt
M
e
ss
a
g
in
g
S
y
ste
m
,
"
in
T
h
e
E
u
ro
p
e
a
n
P
h
y
sic
a
l
J
o
u
rn
a
l
Co
n
fer
e
n
c
e
s
6
8
,
0
0
0
2
5
,
2
0
1
4
,
d
o
i:
1
0
.
1
0
5
1
/ep
jc
o
n
f/
2
0
1
4
6
8
0
0
0
2
5
.
[6
]
R.
S
u
re
tt
e
,
"
T
h
e
Th
in
k
in
g
E
y
e
,
"
Po
li
c
in
g
:
A
n
I
n
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
,
v
o
l.
2
8
,
n
o
.
1
,
p
p
.
p
p
.
1
5
2
-
1
7
3
,
2
0
0
5
,
d
o
i:
1
0
.
1
1
0
8
/1
3
6
3
9
5
1
0
5
1
0
5
8
1
0
3
9
.
[7
]
H.
Walk
e
r
a
n
d
A.
To
u
g
h
,
"
F
a
c
ia
l
Co
m
p
a
riso
n
fr
o
m
CCTV
fo
o
tag
e
:
Th
e
c
o
m
p
e
ten
c
e
a
n
d
c
o
n
fi
d
e
n
c
e
o
f
th
e
ju
ry
,
"
S
c
ien
c
e
a
n
d
J
u
stice
5
5
,
p
p
.
4
8
7
-
4
9
8
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
sc
ij
u
s.2
0
1
5
.
0
4
.
0
1
0
.
[8
]
C.
S
a
n
d
e
rso
n
,
A.
Big
d
e
li
,
T.
S
h
a
n
,
S
.
Ch
e
n
,
E.
Be
rg
l
u
n
d
,
a
n
d
B.
C.
Lo
v
e
ll
,
“
In
telli
g
e
n
t
CCTV
fo
r
M
a
ss
Tran
sp
o
rt
S
e
c
u
rit
y
:
Ch
a
ll
e
n
g
e
s
a
n
d
o
p
p
o
r
tu
n
it
ies
f
o
r
v
id
e
o
a
n
d
fa
c
e
p
ro
c
e
ss
in
g
,
”
S
e
rie
s
in
M
a
c
h
i
n
e
Per
c
e
p
ti
o
n
a
n
d
Arti
fi
c
ia
l
In
telli
g
e
n
c
e
,
p
p
.
5
5
7
-
5
7
3
,
2
0
0
9
,
d
o
i:
1
0
.
1
1
4
2
/
9
7
8
9
8
1
2
8
3
4
4
6
1
_
0
0
3
0
.
[9
]
B.
M
o
sh
iri
,
A.
M
.
Kh
a
l
k
h
a
li
,
a
n
d
H.
R.
M
o
m
e
n
i
,
“
De
sig
n
i
n
g
a
h
o
m
e
se
c
u
rit
y
sy
ste
m
u
sin
g
se
n
s
o
r
d
a
ta
fu
sio
n
with
DST
a
n
d
DSM
T
m
e
th
o
d
s,”
2
0
0
7
1
0
th
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
In
fo
rm
a
t
io
n
Fu
sio
n
,
2
0
0
7
,
d
o
i:
1
0
.
1
1
0
9
/i
c
if.
2
0
0
7
.
4
4
0
8
1
9
2
.
[1
0
]
J.
Yu
,
F
.
K
o
n
g
,
X.
Ch
e
n
g
,
R
.
Ha
o
,
a
n
d
J.
F
a
n
,
“
I
n
tru
si
o
n
-
re
sili
e
n
t
id
e
n
ti
t
y
-
b
a
se
d
si
g
n
a
tu
re
:
S
e
c
u
rit
y
d
e
fin
it
io
n
a
n
d
c
o
n
stru
c
ti
o
n
,
”
J
o
u
rn
a
l
o
f
S
y
ste
ms
a
n
d
S
o
ft
w
a
re
,
v
o
l.
8
5
,
n
o
.
2
,
p
p
.
3
8
2
-
3
9
1
,
2
0
1
2
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jss.2
0
1
1
.
0
8
.
0
3
4
.
[1
1
]
J.
R.
Ag
u
st
in
a
a
n
d
G
.
Clav
e
ll
,
"
T
h
e
Im
p
a
c
t
o
f
CC
TV
o
n
F
u
n
d
a
m
e
n
tal
Ri
g
h
ts
a
n
d
Crime
P
re
v
e
n
t
io
n
S
trate
g
ies
:
Th
e
Ca
se
o
f
th
e
Ca
tala
n
C
o
n
tr
o
l
C
o
m
m
issio
n
o
f
Vid
e
o
S
u
rv
e
il
lan
c
e
De
v
ice
s,"
C
o
mp
u
ter
L
a
w
a
n
d
S
e
c
u
rity
Rev
iew,
p
p
.
1
6
8
-
1
7
4
,
2
0
1
1
,
d
o
i:
1
0
.
1
0
1
6
/
j
.
c
lsr.
2
0
1
1
.
0
1
.
0
0
6
.
[1
2
]
A.
El
fa
sa
k
h
a
n
y
,
J.
He
rn
á
n
d
e
z
,
J.
C.
G
a
rc
ía,
M
.
Re
y
e
s,
a
n
d
F
.
M
a
rt
e
ll
,
“
De
sig
n
a
n
d
d
e
v
e
l
o
p
m
e
n
t
o
f
a
h
o
u
se
-
m
o
b
il
e
se
c
u
rit
y
sy
ste
m
,
”
En
g
i
n
e
e
rin
g
,
v
o
l.
0
3
,
n
o
.
1
2
,
p
p
.
1
2
1
3
-
1
2
2
4
,
2
0
1
1
,
d
o
i:
1
0
.
4
2
3
6
/e
n
g
.
2
0
1
1
.
3
1
2
1
5
1
.
[1
3
]
S
.
Re
z
a
Kh
a
n
a
n
d
F
.
S
u
lt
a
n
a
Dri
sty
,
“
An
d
r
o
i
d
b
a
se
d
se
c
u
rit
y
a
n
d
Ho
m
e
Au
to
m
a
ti
o
n
S
y
ste
m
,
”
T
h
e
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Amb
ie
n
t
S
y
ste
ms
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
3
,
n
o
.
1
,
p
p
.
1
5
-
2
4
,
2
0
1
5
,
d
o
i:
1
0
.
5
1
2
1
/i
jas
a
.
2
0
1
4
.
3
1
0
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
5
2
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci,
Vo
l.
2
4
,
No
.
2
,
No
v
em
b
er
20
21
:
84
3
-
8
52
852
[1
4
]
S
.
Ba
n
u
c
h
i
tra
a
n
d
K.
Ku
n
g
u
m
a
ra
j
,
“
A
c
o
m
p
re
h
e
n
siv
e
su
rv
e
y
o
f
c
o
n
ten
t
-
b
a
se
d
ima
g
e
re
tri
e
v
a
l
tec
h
n
iq
u
e
s,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
,
v
o
l
.
5
,
n
o
.
8
,
p
p
.
1
7
5
7
7
-
1
7
5
8
4
,
2
0
1
6
,
d
o
i:
1
0
.
1
8
5
3
5
/
ij
e
c
s/v
5
i
8
.
2
6
.
[1
5
]
M
.
Ya
n
g
,
F
.
Li
,
L.
Z
h
a
n
g
,
a
n
d
Z.
Zh
a
n
g
,
“
De
e
p
lea
rn
in
g
a
lg
o
rit
h
m
with
v
is
u
a
l
imp
re
ss
io
n
,
”
In
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
L
e
tt
e
rs
,
v
o
l.
1
3
6
,
p
p
.
1
-
4
,
2
0
1
8
,
d
o
i
:
1
0
.
1
0
1
6
/j
.
ip
l.
2
0
1
8
.
0
3
.
0
0
4
.
[1
6
]
R.
C.
Rich
e
y
a
n
d
J.
D.
Kle
i
n
,
“
De
v
e
lo
p
m
e
n
tal
re
se
a
rc
h
m
e
th
o
d
s:
C
re
a
ti
n
g
k
n
o
wle
d
g
e
fro
m
in
str
u
c
ti
o
n
a
l
d
e
sig
n
a
n
d
d
e
v
e
lo
p
m
e
n
t
p
ra
c
ti
c
e
,
”
J
o
u
rn
a
l
o
f
Co
mp
u
ti
n
g
i
n
Hig
h
e
r
Ed
u
c
a
ti
o
n
,
v
o
l
.
1
6
,
n
o
.
2
,
p
p
.
2
3
-
3
8
,
2
0
0
5
,
d
o
i:
1
0
.
1
0
0
7
/b
f
0
2
9
6
1
4
7
3
.
[1
7
]
S
.
Li
,
“
T
h
e
a
p
p
li
c
a
ti
o
n
o
f
fa
c
e
re
c
o
g
n
it
io
n
b
a
se
d
o
n
o
p
e
n
c
v
,
”
Ad
v
a
n
c
e
d
M
a
ter
ia
ls
Res
e
a
rc
h
,
v
o
l
.
4
0
3
-
4
0
8
,
p
p
.
2
3
5
0
-
2
3
5
3
,
2
0
1
1
,
d
o
i:
1
0
.
4
0
2
8
/www
.
sc
ien
ti
fic.n
e
t/
a
m
r.
4
0
3
-
4
0
8
.
2
3
5
0
.
[1
8
]
Y.
-
Q.
Wan
g
,
“
An
a
n
a
ly
sis
o
f
t
h
e
v
io
la
-
jo
n
e
s
fa
c
e
d
e
tec
ti
o
n
a
l
g
o
rit
h
m
,
”
Ima
g
e
Pr
o
c
e
ss
in
g
On
L
in
e
,
v
o
l
.
4
,
p
p
.
1
2
8
-
1
4
8
,
2
0
1
4
,
d
o
i:
1
0
.
5
2
0
1
/
i
p
o
l.
2
0
1
4
.
1
0
4
.
[1
9
]
P
.
Vi
o
la
a
n
d
M
.
J.
Jo
n
e
s,
“
Ro
b
u
st
re
a
l
-
ti
m
e
fa
c
e
d
e
tec
ti
o
n
,
”
In
te
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
mp
u
ter
Vi
sio
n
,
v
o
l.
5
7
,
n
o
.
2
,
p
p
.
1
3
7
-
1
5
4
,
2
0
0
4
,
d
o
i:
1
0
.
1
0
2
3
/
b
:v
isi
.
0
0
0
0
0
1
3
0
8
7
.
4
9
2
6
0
.
fb
.
[2
0
]
F
.
F
a
u
x
a
n
d
F
.
L
u
th
o
n
,
“
Th
e
o
r
y
o
f
e
v
id
e
n
c
e
fo
r
fa
c
e
d
e
tec
ti
o
n
a
n
d
trac
k
in
g
,
”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Ap
p
ro
x
ima
te
Rea
so
n
i
n
g
,
v
o
l.
5
3
,
n
o
.
5
,
p
p
.
7
2
8
-
7
4
6
,
2
0
1
2
,
d
o
i:
1
0
.
1
0
1
6
/
j.
ij
a
r.
2
0
1
2
.
0
2
.
0
0
2
.
[2
1
]
J.
Ni
a
n
d
R.
Ch
e
ll
a
p
p
a
,
“
Ev
a
l
u
a
ti
o
n
o
f
sta
te
-
of
-
t
h
e
-
a
rt
a
lg
o
rit
h
m
s
fo
r
re
m
o
te
fa
c
e
re
c
o
g
n
it
i
o
n
,
”
2
0
1
0
IE
EE
In
ter
n
a
t
io
n
a
l
C
o
n
fer
e
n
c
e
o
n
Im
a
g
e
Pro
c
e
ss
in
g
,
2
0
1
0
,
d
o
i:
1
0
.
1
1
0
9
/i
c
ip
.
2
0
1
0
.
5
6
5
2
6
0
8
.
[2
2
]
M
.
Ça
rık
ç
ı
a
n
d
F
.
Öz
e
n
,
“
A
fa
c
e
re
c
o
g
n
it
i
o
n
s
y
ste
m
b
a
se
d
o
n
e
i
g
e
n
fa
c
e
s
m
e
th
o
d
,
”
Pro
c
e
d
ia
T
e
c
h
n
o
l
o
g
y
,
v
o
l.
1
,
p
p
.
1
1
8
-
1
2
3
,
2
0
1
2
,
d
o
i:
1
0
.
1
0
1
6
/
j
.
p
ro
tc
y
.
2
0
1
2
.
0
2
.
0
2
3
.
[2
3
]
A.
De
,
A.
S
a
h
a
,
a
n
d
M
.
C.
P
a
l,
“
A
h
u
m
a
n
fa
c
ial
e
x
p
re
ss
io
n
re
c
o
g
n
it
i
o
n
m
o
d
e
l
b
a
se
d
o
n
E
ig
e
n
F
a
c
e
Ap
p
ro
a
c
h
,
”
Pro
c
e
d
ia
C
o
mp
u
ter
S
c
ien
c
e
,
v
o
l.
4
5
,
p
p
.
2
8
2
-
2
8
9
,
2
0
1
5
,
d
o
i:
1
0
.
1
0
1
6
/j
.
p
r
o
c
s.2
0
1
5
.
0
3
.
1
4
2
.
[2
4
]
R.
Nk
a
,
“
F
a
c
e
re
c
o
g
n
it
i
o
n
b
a
se
d
o
n
p
rin
c
i
p
a
l
c
o
m
p
o
n
e
n
t
a
n
a
l
y
sis
a
n
d
li
n
e
a
r
d
isc
rimin
a
n
t
a
n
a
l
y
sis,
”
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
trica
l
,
El
e
c
tro
n
ics
a
n
d
In
str
u
me
n
ta
t
io
n
E
n
g
in
e
e
rin
g
,
v
o
l.
4
,
n
o
.
8
,
p
p
.
7
2
6
6
-
7
2
7
4
,
2
0
1
5
,
d
o
i:
1
0
.
1
5
6
6
2
/i
jare
e
ie.2
0
1
5
.
0
4
0
8
0
4
6
.
[2
5
]
L.
Li
,
X.
F
e
n
g
,
Z.
Xia
,
X.
Jia
n
g
,
a
n
d
A.
Ha
d
i
d
,
“
F
a
c
e
sp
o
o
fi
n
g
d
e
tec
ti
o
n
wit
h
lo
c
a
l
b
in
a
ry
p
a
tt
e
rn
n
e
two
r
k
,
”
J
o
u
rn
a
l
o
f
Vi
su
a
l
C
o
mm
u
n
ica
ti
o
n
a
n
d
Ima
g
e
Rep
re
se
n
ta
ti
o
n
,
v
o
l.
5
4
,
p
p
.
1
82
-
1
9
2
,
2
0
1
8
,
d
o
i:
1
0
.
1
0
1
6
/j
.
jv
c
ir.
2
0
1
8
.
0
5
.
0
0
9
.
[2
6
]
K.
Th
a
k
a
r,
D.
Ka
p
a
d
ia,
F
.
Na
tali,
a
n
d
J.
S
a
r
v
a
iy
a
,
“
Im
p
lem
e
n
tati
o
n
a
n
d
a
n
a
ly
sis
o
f
tem
p
late
m
a
tch
in
g
f
o
r
ima
g
e
re
g
istratio
n
o
n
d
e
v
k
it
-
8
5
0
0
d
,
”
Op
ti
k
,
v
o
l.
1
3
0
,
p
p
.
9
3
5
-
9
4
4
,
2
0
1
7
,
d
o
i:
j.
ij
leo
.
2
0
1
6
.
1
1
.
0
5
7
.
[2
7
]
G
.
Bra
d
sk
i,
“
Lea
rn
i
n
g
-
b
a
se
d
c
o
m
p
u
ter
v
isi
o
n
wit
h
I
n
tel’s
O
p
e
n
-
S
o
u
rc
e
Co
m
p
u
ter
Visi
o
n
Li
b
ra
ry
,
”
Un
d
e
rs
ta
n
d
in
g
th
e
Pl
a
tf
o
rm
Re
q
u
ire
me
n
ts o
f
Em
e
rg
in
g
En
ter
p
rise
S
o
l
u
ti
o
n
s
,
v
o
l
.
9
,
n
o
.
2
,
2
0
0
5
,
d
o
i:
1
0
.
1
5
3
5
/i
tj
.
0
9
0
2
.
0
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
.
Ne
lso
n
C.
Ro
d
e
la
s
is
o
n
e
o
f
t
h
e
p
ro
u
d
fa
c
u
lt
y
m
e
m
b
e
r
o
f
th
e
Co
ll
e
g
e
o
f
E
n
g
i
n
e
e
rin
g
u
n
d
e
r
th
e
C
o
m
p
u
ter
E
n
g
in
e
e
rin
g
De
p
a
rtme
n
t
o
f
Un
iv
e
rsit
y
o
f
th
e
Eas
t
Ca
lo
o
c
a
n
a
t
th
e
sa
m
e
ti
m
e
a
fa
c
u
lt
y
m
e
m
b
e
r
o
f
th
e
G
ra
d
u
a
te S
tu
d
ies
in
t
h
e
ICT
De
p
a
rtme
n
t
o
f
Un
i
v
e
rsity
o
f
t
h
e
Eas
t
M
a
n
il
a
.
He
is
a
g
ra
d
u
a
te
o
f
D
o
c
to
r
o
f
I
n
fo
rm
a
ti
o
n
Tec
h
n
o
l
o
g
y
a
t
Un
i
v
e
rsity
o
f
th
e
Eas
t
M
a
n
il
a
,
a
M
a
ste
r
o
f
S
c
ien
c
e
in
En
g
i
n
e
e
rin
g
m
a
jo
r
i
n
Co
m
p
u
ter
En
g
i
n
e
e
rin
g
a
t
P
o
ly
tec
h
n
i
c
Un
iv
e
rsity
o
f
t
h
e
P
h
il
i
p
p
in
e
s
a
n
d
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
i
n
C
o
m
p
u
t
e
r
En
g
in
e
e
rin
g
a
t
Un
i
v
e
rsity
o
f
t
h
e
Eas
t
Ca
lo
o
c
a
n
.
He
is
a
l
so
a
c
e
rti
fied
B
o
a
rd
P
a
ss
e
r
in
Li
c
e
n
su
re
E
x
a
m
in
a
ti
o
n
f
o
r
Tea
c
h
e
rs
(LE
T)
m
a
jo
r
in
M
a
th
e
m
a
ti
c
s.
His
p
u
b
li
c
a
ti
o
n
a
n
d
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
e
n
v
iro
n
m
e
n
tal
re
se
a
rc
h
,
wa
ste
m
a
n
a
g
e
m
e
n
t,
d
a
ta an
a
l
y
ti
c
s a
n
d
d
e
e
p
lea
rn
i
n
g
.
Dr
.
Melv
in
A.
Ba
ll
e
r
a
is
a
g
r
a
d
u
a
te
a
n
d
o
n
e
o
f
t
h
e
p
i
o
n
e
e
r
o
f
Do
c
to
r
o
f
P
h
il
o
s
o
p
h
y
i
n
Co
m
p
u
ter
S
c
ien
c
e
in
t
h
e
P
h
il
i
p
p
i
n
e
s.
He
is
o
n
e
o
f
th
e
Dire
c
to
r
o
f
Re
se
a
rc
h
a
n
d
De
v
e
lo
p
m
e
n
t
a
t
th
e
Tec
h
n
o
lo
g
ica
l
In
sti
tu
te
o
f
th
e
P
h
il
ip
p
i
n
e
s.
His
p
u
b
li
c
a
ti
o
n
a
n
d
re
se
a
rc
h
a
re
a
s
in
c
lu
d
e
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
,
d
e
e
p
lea
rn
in
g
,
a
n
d
d
a
ta an
a
l
y
ti
c
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.