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.
7
,
No
.
1
,
Feb
r
u
ar
y
201
7
,
p
p
.
2
00
~
2
08
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v7
i
1
.
1
2
7
1
8
200
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
JE
C
E
Identity
Ana
ly
sis
of Eg
g
Ba
sed o
n Digita
l a
nd The
r
m
a
l
I
m
a
g
ing
:
I
m
a
g
e P
ro
cess
ing
a
nd Co
unting
O
bje
ct
Co
ncept
Su
na
rdi
1
,
A
nto
n Yudh
a
na
2
,
Sh
o
f
f
a
n Sa
if
ull
a
h
3
1,
2
De
p
a
rtm
e
n
t
o
f
El
e
c
tri
c
a
l
En
g
in
e
e
rin
g
,
Un
iv
e
rsitas
A
h
m
a
d
Da
h
lan
3
M
a
ste
r
o
f
In
f
o
r
m
a
ti
c
s E
n
g
in
e
e
rin
g
,
Un
iv
e
rsitas
A
h
m
a
d
Da
h
lan
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
2
,
2
0
1
6
R
ev
i
s
ed
No
v
2
8
,
2
0
1
6
A
cc
ep
ted
Dec
1
5
,
2
0
1
6
T
h
is
re
se
a
r
c
h
wa
s
c
o
n
d
u
c
ted
t
o
a
n
a
ly
z
e
t
h
e
id
e
n
ti
f
ica
ti
o
n
o
f
e
g
g
s.
T
h
e
r
e
se
a
rc
h
p
ro
c
e
ss
e
s
u
se
t
w
o
to
o
ls,
n
a
m
e
l
y
th
e
r
m
a
l
i
m
a
g
in
g
c
a
m
e
ra
a
n
d
s
m
a
rtp
h
o
n
e
c
a
m
e
ra
.
T
h
e
id
e
n
ti
f
ica
ti
o
n
p
ro
c
e
ss
w
a
s
d
o
n
e
b
y
u
sin
g
M
a
tl
a
b
p
ro
t
o
ty
p
e
to
o
ls.
T
h
e
i
m
a
g
e
h
a
s
b
e
e
n
a
c
q
u
ired
b
y
m
e
a
n
s
o
f
p
ro
f
ici
e
n
c
y
lev
e
l,
th
e
n
a
n
a
ly
z
e
d
a
n
d
a
p
p
li
e
d
se
v
e
ra
l
m
e
th
o
d
s.
Im
a
g
e
a
c
q
u
isit
io
n
re
su
lt
s
o
f
th
e
rm
a
l
i
m
a
g
in
g
c
a
m
e
ra
a
re
p
ro
c
e
ss
e
d
u
sin
g
m
o
rp
h
o
l
o
g
ica
l
d
il
a
ti
o
n
a
n
d
d
o
th
e
c
o
m
p
le
m
e
n
t
in
b
lac
k
a
n
d
w
h
it
e
(BW
).
W
h
il
e
th
e
d
ig
it
a
l
im
a
g
e
u
se
s
th
e
m
e
rg
e
r
m
e
th
o
d
o
f
m
o
rp
h
o
l
o
g
ica
l
d
il
a
ti
o
n
a
n
d
o
p
e
n
i
n
g
,
a
n
d
it
d
o
e
sn
'
t
n
e
e
d
to
b
e
c
o
m
p
le
m
e
n
ted
.
L
a
b
e
li
n
g
p
ro
c
e
ss
is
d
o
n
e
,
a
n
d
th
e
p
ro
c
e
ss
o
f
d
e
ter
m
in
in
g
c
e
n
tro
id
a
n
d
b
o
u
n
d
i
n
g
b
o
x
.
T
h
e
p
ro
c
e
ss
h
a
s
b
e
e
n
d
o
n
e
a
n
d
it
c
a
n
b
e
a
p
p
li
e
d
f
o
r
id
e
n
ti
f
y
in
g
o
f
c
h
ick
e
n
e
g
g
s
w
it
h
th
e
a
c
c
u
ra
c
y
ra
te
o
f
1
0
0
%
.
T
h
e
re
a
re
d
if
fe
re
n
t
m
e
th
o
d
s
o
f
b
o
th
ima
g
e
s
is
o
b
tain
e
d
a
re
a
(p
ix
e
ls)
w
h
ich
is
e
q
u
iv
a
len
t
t
o
th
e
d
if
f
e
re
n
c
e
is
v
e
r
y
s
m
a
ll
a
s 6
x
1
0
-
3
.
K
ey
w
o
r
d
:
C
en
tr
o
id
an
d
b
o
u
n
d
i
n
g
b
o
x
Dig
ital i
m
a
g
e
Mo
r
p
h
o
lo
g
y
T
h
er
m
al
i
m
a
g
i
n
g
Co
p
y
rig
h
t
©
2
0
1
7
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts
re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sh
o
f
f
a
n
Sai
f
u
lla
h
,
Ma
s
ter
o
f
I
n
f
o
r
m
atic
s
E
n
g
i
n
ee
r
in
g
,
Un
i
v
er
s
ita
s
A
h
m
ad
Dah
lan
,
J
l.
Pro
f
.
So
ep
o
m
o
,
J
an
tu
r
an
-
5
5
1
6
4
,
Yo
g
y
ak
ar
ta
,
I
n
d
o
n
es
ia.
E
m
ail:
s
h
o
f
f
a
n
_
s
@
y
a
h
o
o
.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
m
ag
e
p
r
o
ce
s
s
i
n
g
ca
n
b
e
d
o
n
e
w
it
h
an
o
b
j
ec
t
th
at
h
as
b
ee
n
f
o
r
m
ed
in
to
a
d
ig
ital
i
m
a
g
e.
I
n
th
e
d
ig
ital
i
m
a
g
e
f
o
r
m
atio
n
,
it
ca
n
b
e
p
er
f
o
r
m
ed
b
y
u
s
i
n
g
t
h
e
i
m
a
g
e
ca
p
tu
r
e
to
o
ls
.
I
m
a
g
e
ac
q
u
is
i
tio
n
i
s
d
o
n
e
w
it
h
th
er
m
a
l
i
m
a
g
i
n
g
(
b
ased
o
n
h
e
at)
an
d
o
r
d
in
ar
y
i
m
a
g
e
(
s
u
c
h
as
a
r
ea
l
o
b
j
ec
t)
.
T
h
er
m
al
i
m
a
g
in
g
i
s
a
tech
n
iq
u
e
u
s
i
n
g
i
n
f
r
ar
ed
en
er
g
y
t
h
at
is
n
o
t
v
is
ib
le
to
t
h
e
h
u
m
a
n
e
y
e,
e
m
itted
b
y
t
h
e
o
b
j
ec
t
is
th
e
n
co
n
v
er
ted
i
n
to
h
ea
t
v
is
u
al
i
m
a
g
e
[
1
]
.
B
asicall
y
,
e
v
er
y
o
b
j
ec
t
ab
o
v
e
a
te
m
p
er
atu
r
e
o
f
0
ab
s
o
lu
te
e
m
its
t
h
er
m
al
en
er
g
y
i
n
th
e
f
o
r
m
o
f
in
f
r
ar
ed
.
So
,
ev
er
y
o
b
j
ec
t
ca
n
b
e
id
en
t
if
ied
b
y
u
s
i
n
g
a
t
h
er
m
al
i
m
ag
i
n
g
ca
m
er
a.
T
h
e
d
ig
ital
i
m
a
g
e
i
s
a
n
i
m
a
g
e
ta
k
en
w
it
h
a
s
m
ar
tp
h
o
n
e
ca
m
er
a
th
a
t
p
r
o
d
u
c
es
i
m
a
g
es
e
x
ac
tl
y
i
n
ac
co
r
d
an
ce
w
i
th
t
h
e
s
tate
o
f
th
e
o
b
j
ec
t.
T
h
e
co
n
ce
p
t o
f
d
ig
ita
l
i
m
a
g
e
is
a
r
ef
lectio
n
lik
e
a
m
ir
r
o
r
,
w
h
ic
h
d
escr
ib
es
th
e
r
ea
l o
b
j
ec
t lo
o
k
s
lik
e
t
h
e
o
r
ig
in
al.
T
h
e
co
n
ce
p
t
o
f
th
er
m
al
i
m
ag
i
n
g
e
x
p
lain
s
th
a
t
th
e
o
b
j
ec
ts
ar
e
ab
o
v
e
a
tem
p
er
at
u
r
e
o
f
0
(
ze
r
o
)
m
a
y
b
e
in
an
i
m
a
te
o
b
j
ec
ts
o
r
liv
in
g
t
h
i
n
g
s
,
in
cl
u
d
in
g
ch
ick
e
n
eg
g
s
.
T
h
e
o
b
j
ec
t
-
s
h
elled
eg
g
s
t
h
at
co
n
tai
n
a
liv
e
e
m
b
r
y
o
p
r
o
d
u
ce
d
b
y
p
o
u
ltr
y
(
ch
ick
e
n
s
,
d
u
ck
s
,
b
ir
d
s
,
etc.
)
[
2
]
.
C
h
ick
e
n
e
g
g
s
u
n
d
er
n
o
r
m
a
l
ci
r
cu
m
s
tan
ce
s
(
n
o
t
a
n
en
g
i
n
e
co
o
lin
g
)
o
r
w
h
e
n
i
n
c
u
b
ated
h
av
e
h
o
t
te
m
p
er
at
u
r
es.
Fo
r
th
at
e
n
ab
les
t
h
e
id
en
tific
a
tio
n
o
f
eg
g
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
b
y
u
s
i
n
g
a
t
h
er
m
a
l
i
m
a
g
i
n
g
ca
m
er
a.
T
h
e
u
s
e
o
f
t
h
is
ca
m
er
a
d
o
es
n
o
t
p
r
o
d
u
ce
an
y
r
ad
iatio
n
o
r
n
eg
at
iv
e
e
f
f
ec
ts
o
n
th
e
e
g
g
s
an
d
t
h
e
en
v
ir
o
n
m
e
n
t
b
ec
au
s
e
it
d
o
es
n
o
t
e
m
it
in
f
r
a
r
ed
r
ay
s
o
r
o
th
er
elec
tr
o
m
ag
n
etic
w
a
v
es,
b
u
t a
b
s
o
r
b
s
in
f
r
ar
ed
r
a
y
s
f
r
o
m
t
h
e
h
ea
t r
ad
iatio
n
e
m
itted
b
y
t
h
e
o
b
j
ec
ts
[
3
]
.
T
h
e
eg
g
s
i
m
a
g
e
p
r
o
ce
s
s
in
g
a
n
al
y
s
i
s
p
r
o
ce
s
s
co
n
d
u
cted
b
y
u
s
i
n
g
th
er
m
al
i
m
ag
in
g
tech
n
o
lo
g
y
b
ased
o
n
th
e
id
e
n
ti
f
icatio
n
m
a
n
u
a
l.
E
g
g
s
ar
e
an
a
n
alo
g
i
m
a
g
e
w
h
ic
h
m
u
s
t
b
e
co
n
v
er
ted
in
t
o
d
ig
ital
i
m
ag
e
s
f
o
r
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
(
s
o
-
ca
lled
i
m
a
g
i
n
g
)
.
T
h
e
i
m
ag
i
n
g
p
r
o
ce
s
s
u
s
i
n
g
a
th
er
m
al
i
m
a
g
in
g
ca
m
er
a
a
n
d
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
d
en
tity A
n
a
lysi
s
o
f E
g
g
B
a
s
ed
o
n
Dig
ita
l a
n
d
Th
erma
l I
ma
g
in
g
:
I
ma
g
e
P
r
o
ce
s
s
in
g
a
n
d
....
(
S
u
n
a
r
d
i)
201
s
m
ar
tp
h
o
n
e
ca
m
er
a.
So
,
it
g
ets
t
w
o
d
if
f
er
e
n
t
d
ig
i
tal
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
to
b
e
p
er
f
o
r
m
ed
co
m
p
ar
is
o
n
g
o
o
d
i
m
a
g
e
o
f
th
e
t
h
er
m
al
i
m
a
g
i
n
g
ca
m
er
a
i
m
ag
e
an
d
t
h
e
i
m
a
g
e
o
f
th
e
s
m
ar
tp
h
o
n
e
ca
m
er
a.
W
ith
th
e
d
ig
ital
tech
n
o
lo
g
y
b
ased
o
n
h
ea
t
(
th
er
m
al
i
m
a
g
i
n
g
)
ca
n
b
e
u
s
ed
to
d
etec
t
th
e
ch
ick
e
n
eg
g
s
th
at
e
m
it
h
ea
t.
T
h
is
tech
n
o
lo
g
y
is
u
s
ed
to
as
s
is
t
in
th
e
i
m
a
g
in
g
p
r
o
ce
s
s
p
r
io
r
to
th
e
tes
tin
g
p
r
o
ce
s
s
u
n
til
t
h
e
i
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
an
d
co
n
d
u
cted
co
m
p
ar
in
g
w
i
t
h
o
r
d
in
ar
y
d
ig
ital
i
m
ag
e
s
r
an
g
in
g
f
r
o
m
th
e
p
r
o
ce
s
s
o
f
i
m
a
g
e
an
al
y
s
i
s
,
i
m
a
g
e
ac
q
u
is
itio
n
,
th
e
r
es
u
lti
n
g
h
i
s
to
g
r
a
m
,
a
n
d
i
m
a
g
e
p
r
o
ce
s
s
in
g
m
eth
o
d
s
u
s
ed
an
d
th
e
r
es
u
lts
.
2.
RE
S
E
ARCH
M
E
T
H
O
D
T
h
e
m
et
h
o
d
o
lo
g
y
w
a
s
u
s
ed
is
s
h
o
w
n
in
o
u
r
p
r
ev
io
u
s
r
esear
ch
[
4
]
.
T
h
e
d
ata
co
llectio
n
w
a
s
d
o
n
e
b
y
tak
i
n
g
a
p
ictu
r
e
o
f
c
h
ick
e
n
e
g
g
s
u
s
i
n
g
an
F
L
I
R
th
er
m
al
i
m
ag
in
g
ca
m
er
a
a
n
d
a
s
m
ar
tp
h
o
n
e
ca
m
er
a
at
t
h
e
p
o
s
itio
n
(
o
r
d
er
o
f
d
if
f
er
en
t
e
g
g
s
)
.
T
h
e
an
al
y
s
i
s
w
ill
f
ac
il
itat
e
th
e
d
esi
g
n
o
f
t
h
e
s
y
s
te
m
to
b
e
cr
ea
ted
.
A
s
w
ell
as
t
h
e
m
et
h
o
d
s
u
s
ed
f
o
r
t
h
e
co
m
p
ar
is
o
n
o
f
i
m
ag
e
p
r
o
ce
s
s
i
n
g
o
n
th
e
t
h
er
m
al
i
m
a
g
in
g
ca
m
er
a
an
d
a
s
m
ar
tp
h
o
n
e
ca
m
er
a.
T
h
e
s
y
s
te
m
u
s
e
Ma
tlab
ap
p
licatio
n
to
cr
ea
te
a
p
r
o
to
t
y
p
e
in
p
er
f
o
r
m
in
g
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
s
ta
g
es
ch
ick
e
n
e
g
g
s
.
T
h
e
d
es
ig
n
i
s
d
o
n
e
w
it
h
t
w
o
g
r
o
o
v
es
r
esear
c
h
m
et
h
o
d
s
b
y
a
p
r
o
ce
s
s
f
lo
w
as
i
n
Fi
g
u
r
e
1
.
T
h
e
test
s
y
s
te
m
is
d
o
n
e
b
y
p
r
o
ce
s
s
in
g
i
m
a
g
e
d
ata
u
s
in
g
Ma
tlab
a
s
a
p
r
o
to
ty
p
e
ap
p
licatio
n
.
(
a)
(
b
)
Fig
u
r
e
1
.
Step
s
Desi
g
n
o
f
I
m
a
g
e
P
r
o
ce
s
s
in
g
C
h
ic
k
en
E
g
g
s
(
a)
Or
d
in
ar
y
i
m
a
g
e,
(
b
)
T
h
er
m
al
I
m
ag
er
y
B
ased
o
n
th
e
ab
o
v
e
p
ictu
r
e
c
an
b
e
s
ee
n
t
h
e
d
if
f
er
en
ce
o
f
t
w
o
i
m
ag
e
p
r
o
ce
s
s
i
n
g
.
I
n
o
r
d
in
ar
y
i
m
a
g
e
u
s
i
n
g
m
o
r
p
h
o
lo
g
ical
d
ilatio
n
a
n
d
o
p
en
in
g
(
Fi
g
u
r
e
1
(
a)
)
,
w
h
ile
t
h
e
th
er
m
al
i
m
ag
e
u
s
in
g
d
ilatio
n
o
n
l
y
(
Fig
u
r
e
1
(
b
)
)
.
T
h
e
p
r
o
ce
s
s
o
f
d
eter
m
i
n
i
n
g
ce
n
tr
o
id
a
n
d
b
o
u
n
d
i
n
g
b
o
x
d
ir
ec
tl
y
p
r
o
ce
s
s
e
d
,
w
h
ile
th
e
t
h
er
m
a
l
i
m
a
g
e
o
f
th
e
co
m
p
le
m
en
t
p
r
o
ce
s
s
m
u
s
t
b
e
d
o
n
e
in
ad
v
an
ce
,
th
at
is
,
ch
an
g
e
th
e
v
a
lu
e
to
t
h
e
i
m
a
g
e
o
f
b
lack
an
d
w
h
ite
(
B
W
)
w
h
ich
w
a
s
o
r
ig
i
n
all
y
1
w
a
s
ch
a
n
g
ed
to
0
an
d
v
ice
v
er
s
a.
Qu
alit
y
clas
s
i
f
icatio
n
o
f
e
g
g
s
b
ased
o
n
th
e
clea
n
lin
e
s
s
o
f
th
e
eg
g
s
h
e
ll
u
s
i
n
g
a
s
a
m
p
le
co
n
s
is
ti
n
g
o
f
9
0
eg
g
s
f
r
o
m
ea
ch
o
f
3
0
ch
ic
k
en
e
g
g
s
q
u
alit
y
I
,
I
I
,
an
d
I
I
I
.
T
h
e
alg
o
r
ith
m
u
s
ed
i
s
a
f
ir
s
t
o
r
d
er
s
tatis
tics
a
n
d
th
e
s
ec
o
n
d
o
r
d
er
f
o
r
f
ea
tu
r
e
ex
tr
ac
tio
n
,
an
d
K
-
Nea
r
est
Nei
g
h
b
o
r
(
KNN)
as
a
E
u
clid
ea
n
-
b
ased
class
if
icatio
n
p
r
o
ce
s
s
.
T
h
e
s
u
cc
e
s
s
r
ate
o
f
r
esear
ch
i
s
8
8
.
8
9
%
[
5
].
T
h
e
ap
p
licatio
n
o
f
co
m
p
u
ter
v
is
io
n
a
n
d
s
e
g
m
en
tatio
n
tech
n
iq
u
es
in
clas
s
i
f
y
i
n
g
t
h
e
p
h
y
s
ical
s
ize
o
f
e
g
g
s
b
y
w
ei
g
h
t.
T
h
is
r
esear
c
h
w
a
s
co
n
d
u
ct
ed
b
y
u
s
in
g
a
w
eb
ca
m
er
a
to
o
l
an
d
p
r
o
ce
s
s
es
u
s
i
n
g
i
m
a
g
e
s
eg
m
e
n
tatio
n
m
e
th
o
d
f
o
r
i
m
a
g
e
s
h
ar
in
g
,
ac
co
r
d
in
g
to
th
e
cr
i
ter
ia
o
f
s
i
m
ilar
it
y
a
n
d
co
lo
r
in
te
n
s
it
y
to
ap
p
r
o
ac
h
r
eg
r
ess
io
n
an
al
y
s
is
w
ei
g
h
t
in
g
b
ased
o
n
t
h
e
n
u
m
b
er
o
f
p
ix
el
s
th
e
o
b
j
ec
t.
T
esti
n
g
t
h
e
cla
s
s
i
f
ica
tio
n
o
f
3
6
s
a
m
p
le
s
o
f
ch
ic
k
en
e
g
g
s
s
h
o
w
s
th
e
ac
cu
r
ac
y
r
ate
o
f
1
0
0
%
an
d
ac
cu
r
ac
y
o
f
4
2
%
w
ei
g
h
tin
g
ap
p
r
o
ac
h
[
6
].
T
h
e
d
etec
tio
n
s
y
s
te
m
o
f
t
h
e
e
m
b
r
y
o
i
n
a
n
e
g
g
ca
r
r
ied
b
y
w
eb
ca
m
,
th
e
d
etec
tio
n
p
r
o
ce
s
s
eg
g
e
m
b
r
y
o
s
u
s
in
g
t
h
r
es
h
o
ld
in
g
m
et
h
o
d
to
id
en
ti
f
y
e
g
g
s
b
y
s
ep
ar
atin
g
th
e
eg
g
w
i
th
a
b
ac
k
g
r
o
u
n
d
o
b
j
ec
t
an
d
ca
lcu
lati
n
g
th
e
n
u
m
b
er
o
f
p
ix
els
o
f
t
h
e
o
b
j
ec
t
b
ein
g
f
o
r
m
ed
.
T
h
e
p
r
o
ce
s
s
o
f
d
etec
tio
n
u
s
i
n
g
a
th
r
es
h
o
ld
o
f
5
0
eg
g
s
o
n
e
g
g
e
m
b
r
y
o
s
,
w
h
ich
h
av
e
a
s
u
cc
ess
r
ate
o
f
1
0
0
%.
T
h
e
p
r
o
ce
s
s
o
f
eg
g
d
etec
tio
n
o
n
th
e
co
n
d
itio
n
o
f
b
r
o
k
en
eg
g
s
o
b
tai
n
ed
a
s
u
cc
e
s
s
r
ate
o
f
9
1
.
7
%.
So
f
r
o
m
a
ll
o
f
th
e
d
ata
r
etr
ie
v
al
w
it
h
all
co
n
d
itio
n
s
o
f
eg
g
s
o
b
tain
ed
th
e
er
r
o
r
o
f
1
.
8
%
an
d
a
s
u
cc
es
s
r
ate
o
f
9
8
.
2
%
[
7
].
C
lass
i
f
icatio
n
o
f
ch
ic
k
en
eg
g
s
an
d
q
u
ail
e
g
g
s
u
s
i
n
g
co
n
n
ec
ted
co
m
p
o
n
e
n
t
an
al
y
s
is
m
eth
o
d
,
t
h
is
m
et
h
o
d
w
as
s
u
cc
es
s
f
u
ll
y
ap
p
lied
t
o
th
e
s
e
g
m
en
tatio
n
I
m
a
g
e
A
c
q
u
i
s
i
t
i
o
n
C
o
l
o
r
I
m
a
g
e
(
R
G
B
)
G
r
a
y
s
c
a
l
e
I
m
a
g
e
H
i
s
t
o
g
r
a
m
c
o
n
v
e
r
t
c
o
n
v
e
r
t
C
e
n
t
r
o
i
d
&
B
o
u
n
d
i
n
g
B
o
x
c
o
m
p
a
r
i
s
o
n
L
a
b
e
l
l
i
n
g
T
h
r
e
s
h
o
l
d
O
t
s
u
I
m
a
g
e
A
c
q
u
i
s
i
t
i
o
n
C
o
l
o
r
I
m
a
g
e
(
R
G
B
)
G
r
a
y
s
c
a
l
e
I
m
a
g
e
H
i
s
t
o
g
r
a
m
c
o
n
v
e
r
t
c
o
n
v
e
r
t
C
e
n
t
r
o
i
d
&
B
o
u
n
d
i
n
g
B
o
x
c
o
m
p
a
r
i
s
o
n
L
a
b
e
l
l
i
n
g
T
h
r
e
s
h
o
l
d
O
t
s
u
D
i
l
a
t
i
o
n
&
O
p
e
n
i
n
g
(
M
o
r
p
h
o
l
o
g
y
)
B
l
a
c
k
W
h
i
t
e
I
m
a
g
e
D
I
l
a
t
i
o
n
(
M
o
r
p
h
o
l
o
g
y
I
m
a
g
e
B
l
a
c
k
W
h
i
t
e
c
o
m
p
l
e
m
e
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
7
:
2
00
–
2
0
8
202
p
r
o
ce
s
s
ch
ick
e
n
eg
g
s
an
d
q
u
ai
l
eg
g
s
w
it
h
th
e
b
lack
b
ac
k
g
r
o
u
n
d
.
T
h
e
r
esu
ltin
g
lev
e
l
o
f
ac
cu
r
ac
y
o
f
1
0
0
%
an
d
ab
le
to
g
i
v
e
a
c
lass
if
icatio
n
o
n
s
o
m
e
t
y
p
e
o
f
e
g
g
b
ased
w
ei
g
h
ti
n
g
ap
p
r
o
ac
h
.
I
f
d
etec
ted
n
o
t
a
ch
ick
e
n
o
r
q
u
a
il
eg
g
s
,
th
e
n
t
h
e
p
r
o
g
r
a
m
w
ill
n
o
t p
er
f
o
r
m
t
h
e
ca
lc
u
latio
n
o
f
th
e
n
u
m
b
er
o
f
eg
g
s
[
8
].
T
h
e
in
tr
o
d
u
ctio
n
o
f
th
e
eg
g
s
c
an
b
e
d
o
n
e
b
y
u
s
i
n
g
a
f
ea
t
u
r
e
ex
tr
ac
tio
n
b
ased
o
n
t
h
e
c
h
ar
ac
ter
is
tics
o
f
th
e
co
lo
r
i
m
ag
e.
T
h
e
m
e
th
o
d
u
s
ed
is
t
h
e
ce
n
tr
o
id
class
i
f
ier
an
d
p
r
ep
r
o
ce
s
s
in
g
i
s
d
o
n
e
b
y
ch
an
g
i
n
g
th
e
i
m
a
g
e
o
f
R
GB
in
to
HSV
(
H
u
e,
Sat
u
r
atio
n
,
an
d
Val
u
e)
.
T
h
e
r
esu
lts
o
b
tain
ed
ar
e
d
u
ck
eg
g
s
h
a
v
e
an
a
v
er
ag
e
h
u
e
ch
ar
ac
ter
is
tic
b
et
w
ee
n
0
.
0
8
9
to
0
.
0
9
4
an
d
an
av
er
a
g
e
s
atu
r
a
tio
n
o
f
b
et
w
ee
n
0
.
1
2
to
0
.
3
2
.
Do
m
esti
c
ch
ick
e
n
eg
g
s
h
a
v
e
an
a
v
er
ag
e
h
u
e
c
h
a
r
ac
ter
is
tic
b
et
w
ee
n
0
.
0
3
3
to
0
.
0
5
3
an
d
an
av
er
ag
e
s
at
u
r
atio
n
o
f
b
et
w
ee
n
0
.
5
2
to
0
.
6
2
,
w
h
ile
t
h
e
c
h
ick
e
n
e
g
g
s
h
av
e
a
n
a
v
er
ag
e
h
u
e
ch
ar
ac
ter
is
tic
b
et
w
ee
n
0
.
0
6
1
to
0
.
0
6
8
an
d
an
av
er
a
g
e
s
atu
r
atio
n
o
f
b
et
w
ee
n
0
.
2
1
-
0
.
2
5
[
9
].
T
h
e
in
tr
o
d
u
ctio
n
o
f
t
h
e
u
s
u
a
l
t
y
p
es
o
f
ch
ick
e
n
eg
g
s
an
d
ch
ic
k
e
n
eg
g
s
o
m
e
g
a
-
3
u
s
i
n
g
th
e
m
eth
o
d
o
f
s
tatis
t
ical
an
al
y
s
i
s
th
at
i
s
u
s
in
g
th
e
f
ir
s
t
-
o
r
d
er
d
if
f
er
en
ce
s
i
n
p
h
y
s
ical
s
h
ap
e
an
d
co
lo
r
o
f
th
e
eg
g
s
.
T
h
e
m
e
th
o
d
u
s
ed
in
i
m
a
g
e
p
r
o
ce
s
s
in
g
th
at
is
ch
a
n
g
in
g
th
e
v
al
u
e
o
f
g
r
a
y
,
i
m
a
g
e
co
n
tr
as
t
en
h
a
n
ce
m
en
t,
f
ilter
i
n
g
w
it
h
a
Gau
s
s
ian
f
ilter
,
h
i
s
to
g
r
a
m
eq
u
aliza
tio
n
,
th
r
es
h
o
ld
in
g
s
e
g
m
en
tatio
n
O
ts
u
,
an
d
th
e
f
ir
s
t
-
o
r
d
er
s
tatis
tic
s
in
t
h
e
class
i
f
icatio
n
.
T
h
e
r
esu
lt
is
ab
le
to
d
is
tin
g
u
i
s
h
o
r
d
in
ar
y
ch
ick
e
n
e
g
g
s
an
d
ch
ick
e
n
e
g
g
s
o
m
e
g
a
-
3
w
it
h
t
h
e
d
if
f
er
e
n
ce
in
t
h
e
v
al
u
e
o
f
s
ta
tis
tics
[
10
].
T
h
er
m
al
i
m
a
g
in
g
tech
n
o
lo
g
y
ca
n
b
e
u
s
ed
to
d
etec
t
h
atch
in
g
eg
g
s
in
t
h
e
in
c
u
b
ato
r
f
o
r
1
6
d
ay
s
.
T
h
e
s
tate
o
f
t
h
e
eg
g
s
i
n
th
e
i
n
c
u
b
ato
r
f
o
r
4
-
1
6
d
ay
s
to
d
o
r
esear
c
h
w
it
h
th
er
m
al
i
m
a
g
in
g
tec
h
n
o
lo
g
y
.
T
h
e
an
al
y
s
i
s
w
a
s
co
n
d
u
cted
b
ased
o
n
th
e
cu
r
v
e
o
f
t
h
e
co
ld
,
co
ld
r
eg
io
n
s
,
d
ev
elo
p
m
e
n
t,
o
v
al
s
h
ap
e
an
d
m
o
r
p
h
o
lo
g
y
o
f
t
h
e
eg
g
s
,
a
s
w
ell
as
t
h
e
e
x
tr
ac
tio
n
o
f
e
g
g
s
u
s
i
n
g
R
e
g
io
n
o
f
I
n
ter
est
(
R
OI
)
.
I
n
t
h
i
s
r
esear
c
h
s
h
o
w
s
t
h
at
th
e
e
g
g
i
s
n
o
t f
er
ti
lized
w
it
h
i
n
4
d
a
y
s
w
a
s
8
9
.
6
%,
an
d
th
e
e
m
b
r
y
o
eg
g
s
in
1
6
d
ay
s
w
as 9
6
.
3
% o
f
th
e
t
o
tal
[
1
1
].
Dete
r
m
i
n
atio
n
o
f
f
er
tili
t
y
e
g
g
an
d
ea
r
l
y
e
m
b
r
y
o
u
s
i
n
g
h
y
p
er
s
p
ec
tr
al
i
m
a
g
i
n
g
w
it
h
s
a
m
p
le
d
ata
u
s
ed
ar
e
1
7
0
ch
ick
en
eg
g
s
(
1
5
2
eg
g
s
w
er
e
f
er
tile,
a
n
d
1
8
ar
e
n
o
t
f
er
tile
)
.
T
h
e
m
eth
o
d
u
s
ed
u
s
i
n
g
R
eg
io
n
o
f
I
n
ter
e
s
t
(
R
OI
)
in
t
h
e
ex
tr
ac
tio
n
ch
ar
a
cter
is
tics
a
n
d
K
-
Me
an
s
to
its
class
i
f
icatio
n
.
R
e
s
ea
r
ch
is
s
h
o
w
i
n
g
th
e
r
e
s
u
l
ts
o
f
class
i
f
icatio
n
f
o
r
all
th
e
e
g
g
s
o
n
ea
ch
d
a
y
o
f
in
c
u
b
atio
n
i
s
t
h
e
d
a
y
1
s
t
is
6
5
.
2
9
%,
th
e
2
n
d
d
ay
is
6
1
.
1
8
%,
th
e
3
r
d
d
ay
t
h
at
i
s
7
2
.
9
4
%,
an
d
t
h
e
4
th
d
a
y
is
8
4
.
1
2
%.
L
o
w
er
class
i
f
icatio
n
r
es
u
lt
s
o
n
Da
y
1
an
d
Da
y
2
,
w
h
ich
s
h
o
w
s
th
at
e
m
b
r
y
o
n
ic
d
ev
elo
p
m
e
n
t
is
d
i
f
f
icu
l
t
to
d
etec
t
d
u
r
in
g
t
h
e
f
ir
s
t
2
d
a
y
s
at
t
h
e
t
i
m
e
t
h
e
eg
g
s
w
er
e
in
th
e
i
n
c
u
b
ato
r
[
1
2
].
T
h
e
u
s
e
o
f
t
h
er
m
al
i
m
a
g
i
n
g
i
n
id
e
n
tify
i
n
g
an
d
f
il
ter
in
g
o
n
t
h
e
f
er
tile
e
g
g
s
.
I
m
a
g
e
p
r
o
ce
s
s
in
g
u
s
in
g
t
h
e
So
b
el
o
p
er
ato
r
to
s
ea
r
ch
f
o
r
an
o
u
ts
i
d
e
lin
e
o
n
t
h
e
eg
g
s
a
n
d
f
u
zz
y
th
eo
r
y
is
u
s
ed
to
o
b
tain
t
h
e
b
est
t
h
r
es
h
o
ld
v
al
u
es
o
n
t
h
e
b
r
o
k
en
e
g
g
is
u
s
i
n
g
g
r
a
y
s
ca
le
m
atr
i
x
co
-
o
cc
u
r
r
en
c
e.
T
h
en
t
h
e
s
y
s
te
m
ca
n
m
a
k
e
an
as
s
es
s
m
en
t
o
f
w
h
eth
er
ea
c
h
eg
g
is
g
o
o
d
o
r
b
a
d
.
T
h
e
ac
cu
r
ac
y
o
f
th
e
s
y
s
te
m
ca
n
r
ea
ch
9
6
%,
an
d
th
e
d
etec
tio
n
r
ate
o
f
2
-
3
s
ec
o
n
d
s
[
1
3
].
T
h
e
u
s
e
o
f
a
s
i
m
p
le
m
o
r
p
h
o
lo
g
ical
c
h
ar
ac
ter
is
t
ic
m
ea
s
u
r
e
m
en
t
s
o
f
t
h
e
lea
f
s
h
ap
es
(
u
s
in
g
p
ar
am
eter
2
/ar
ea
)
,
h
ad
ef
f
ec
ti
v
en
e
s
s
b
et
w
ee
n
5
2
%
an
d
7
4
%
in
d
if
f
er
en
tiat
in
g
th
e
t
w
o
t
y
p
es
o
f
p
lan
t
s
d
ep
en
d
in
g
o
n
th
e
s
ize
o
f
th
e
p
lan
t.
A
n
d
t
h
e
n
eu
r
al
n
et
wo
r
k
allo
w
s
t
h
e
s
y
s
te
m
to
lea
r
n
an
d
d
is
ti
n
g
u
is
h
b
et
w
ee
n
s
p
ec
ies
w
it
h
an
ac
cu
r
ac
y
m
o
r
e
th
an
7
5
%
[
1
4
]
.
Seg
m
en
tatio
n
o
f
r
eti
n
al
v
e
s
s
el
s
is
d
o
n
e,
an
d
p
r
o
p
o
s
e
t
w
o
au
to
m
atic
b
lo
o
d
v
ess
el
s
e
g
m
e
n
tat
io
n
m
e
th
o
d
s
.
T
h
e
f
ir
s
t
p
r
o
p
o
s
ed
alg
o
r
ith
m
s
tar
ts
w
i
t
h
th
e
ex
tr
ac
tio
n
o
f
b
lo
o
d
v
ess
el
ce
n
ter
li
n
e
p
ix
e
ls
.
T
h
e
f
in
al
s
eg
m
e
n
tatio
n
is
o
b
tain
ed
u
s
i
n
g
a
n
iter
ati
v
e
r
eg
io
n
g
r
o
w
i
n
g
m
et
h
o
d
(
u
s
e
b
in
ar
y
i
m
a
g
es
o
n
o
n
n
o
r
m
alize
d
r
etin
al
i
m
ag
e
s
)
.
I
n
th
e
s
ec
o
n
d
p
r
o
p
o
s
ed
alg
o
r
ith
m
th
e
b
lo
o
d
v
ess
el
i
s
s
eg
m
e
n
ted
u
s
i
n
g
n
o
r
m
alize
d
m
o
d
i
f
ied
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
an
d
n
e
u
r
o
f
u
zz
y
cla
s
s
i
f
ier
.
No
r
m
alize
d
m
o
r
p
h
o
lo
g
ical
o
p
er
atio
n
s
ar
e
u
s
ed
to
e
n
h
a
n
ce
t
h
e
v
es
s
els a
n
d
n
eu
r
o
f
u
zz
y
cla
s
s
i
f
ier
i
s
u
s
e
d
to
s
eg
m
en
t r
etin
a
l
b
lo
o
d
v
ess
els.
T
h
e
r
esu
lt
s
d
em
o
n
s
tr
ate
th
at
th
e
f
ir
s
t
al
g
o
r
ith
m
s
ar
e
v
er
y
ef
f
ec
ti
v
e
m
et
h
o
d
s
to
d
etec
t
r
etin
al
b
lo
o
d
v
ess
els
[
1
5
]
.
A
n
o
v
el
s
eg
m
e
n
tat
io
n
m
et
h
o
d
b
ased
o
n
co
m
b
in
at
io
n
lo
ca
l
m
ea
n
o
f
g
r
ey
-
s
ca
le
a
n
d
lo
ca
l
v
ar
ian
ce
o
f
g
r
ad
ien
t
m
a
g
n
itu
d
e.
T
h
e
p
r
o
p
o
s
ed
ex
tr
ac
tio
n
b
eg
in
s
w
i
th
n
o
r
m
al
izatio
n
o
f
t
h
e
f
i
n
g
er
p
r
in
t.
T
h
en
,
it
is
f
o
llo
w
ed
b
y
f
o
r
e
g
r
o
u
n
d
r
eg
io
n
s
ep
ar
atio
n
f
r
o
m
t
h
e
b
ac
k
g
r
o
u
n
d
.
Fin
al
l
y
,
t
h
e
g
r
ad
ien
t
co
h
er
en
ce
ap
p
r
o
ac
h
is
u
s
ed
to
d
etec
t
t
h
e
n
o
is
e
r
eg
io
n
s
ex
is
ted
i
n
t
h
e
f
o
r
eg
r
o
u
n
d
.
E
x
p
er
i
m
e
n
tal
r
es
u
lt
s
o
n
NI
ST
-
Data
b
ase1
4
f
i
n
g
er
p
r
in
t i
m
a
g
es i
n
d
icate
t
h
a
t th
e
p
r
o
p
o
s
ed
m
et
h
o
d
g
iv
e
s
t
h
e
i
m
p
r
es
s
i
v
e
r
esu
l
ts
[
1
6
]
.
A
n
e
w
a
lg
o
r
it
h
m
b
ased
o
n
e
m
p
ir
ical
m
o
d
e
d
ec
o
m
p
o
s
it
io
n
alg
o
r
ith
m
f
o
r
t
h
e
h
is
to
g
r
a
m
o
f
th
e
in
p
u
t
i
m
a
g
e
w
ill
g
en
er
ate
t
h
e
n
u
m
b
er
o
f
clu
s
ter
s
a
n
d
in
itia
l
ce
n
tr
o
id
s
r
eq
u
ir
ed
f
o
r
clu
s
ter
i
n
g
.
I
t
o
v
er
co
m
es
t
h
e
s
h
o
r
tag
e
o
f
r
a
n
d
o
m
i
n
itial
izati
o
n
in
tr
ad
itio
n
al
cl
u
s
ter
in
g
a
n
d
ac
h
iev
e
s
h
ig
h
co
m
p
u
tat
io
n
al
s
p
ee
d
b
y
r
ed
u
ci
n
g
th
e
n
u
m
b
e
r
o
f
iter
atio
n
s
.
T
h
e
ex
p
er
i
m
e
n
tal
r
es
u
lts
s
h
o
w
th
a
t
m
u
l
tip
le
f
ea
t
u
r
e
Fu
zz
y
C
m
e
an
s
h
a
s
s
e
g
m
e
n
ted
th
e
m
icr
o
ar
r
ay
i
m
a
g
e
m
o
r
e
ac
cu
r
atel
y
t
h
a
n
o
th
er
alg
o
r
it
h
m
s
[
1
7
]
.
T
h
e
m
et
h
o
d
ai
m
s
at
d
etec
ti
n
g
d
ef
ec
ti
v
e
ar
ea
s
in
a
tile,
b
a
s
ed
o
n
ex
tr
ac
ti
n
g
f
ea
t
u
r
es
o
f
ed
g
e
d
ef
ec
ts
.
I
n
th
e
p
r
o
p
o
s
ed
m
eth
o
d
,
f
ir
s
t,
in
o
r
d
er
to
ex
tr
ac
t
f
r
eq
u
en
c
y
ch
ar
ac
ter
is
tic
s
r
esis
ta
n
t
ag
ain
s
t
tr
a
n
s
f
er
en
ce
,
Un
d
ec
i
m
a
ted
Dis
cr
ete
W
av
el
et
P
ac
k
ets
tr
an
s
f
o
r
m
i
s
ap
p
lie
d
o
n
i
m
a
g
es.
L
ater
,
b
y
co
m
p
u
ti
n
g
lo
ca
l
e
n
tr
o
p
y
v
alu
e
s
o
n
h
ig
h
-
f
r
eq
u
en
c
y
s
u
b
-
b
an
d
s
i
m
a
g
es,
t
h
o
s
e
w
h
ich
ap
p
r
o
p
r
iately
in
cl
u
d
e
i
m
ag
e
s
d
ef
ec
ts
ar
e
ch
o
s
e
n
to
ex
tr
ac
t
s
tatis
t
ical
f
ea
t
u
r
es.
Fi
n
all
y
,
B
ac
k
p
r
o
p
ag
atio
n
n
eu
r
al
n
et
w
o
r
k
m
et
h
o
d
is
u
s
ed
to
d
eter
m
in
e
s
e
g
m
en
te
d
i
m
a
g
es
co
n
tai
n
in
g
d
e
f
ec
ti
v
e
ar
ea
s
.
T
h
e
o
b
tain
ed
r
esu
lt
s
,
b
o
th
v
i
s
u
al
l
y
a
n
d
co
m
p
u
tati
o
n
all
y
in
d
icate
th
e
h
ig
h
er
ef
f
icac
y
o
f
t
h
i
s
m
et
h
o
d
co
m
p
ar
ed
w
ith
t
h
e
r
elate
d
s
ta
te
o
f
th
e
ar
t
m
e
th
o
d
s
[
1
8
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
d
en
tity A
n
a
lysi
s
o
f E
g
g
B
a
s
ed
o
n
Dig
ita
l a
n
d
Th
erma
l I
ma
g
in
g
:
I
ma
g
e
P
r
o
ce
s
s
in
g
a
n
d
....
(
S
u
n
a
r
d
i)
203
B
ased
o
n
th
e
r
esear
ch
co
n
d
u
c
ted
,
r
esear
ch
er
s
w
il
l
m
a
k
e
a
d
if
f
er
e
n
ce
in
i
m
a
g
e
p
r
o
ce
s
s
in
g
f
r
o
m
t
h
e
u
s
e
o
f
m
et
h
o
d
s
,
an
al
y
s
is
,
a
n
d
u
s
e
m
et
h
o
d
s
th
a
t
h
a
v
e
b
ee
n
d
o
n
e
b
u
t
b
y
co
m
b
i
n
i
n
g
t
h
e
m
.
I
n
a
s
tu
d
y
d
o
n
e
b
y
u
s
i
n
g
ce
n
tr
o
id
an
d
th
e
b
o
u
n
d
in
g
b
o
x
i
n
d
eter
m
i
n
in
g
th
e
o
b
j
ec
t
an
d
th
e
ar
ea
o
f
ch
ic
k
en
eg
g
s
,
a
n
d
u
s
ed
co
m
p
ar
is
o
n
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
s
s
,
th
e
m
et
h
o
d
s
u
s
ed
,
an
d
th
e
r
esu
l
ts
o
f
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
b
et
w
ee
n
t
h
e
th
er
m
a
l i
m
a
g
i
n
g
an
d
d
ig
ital i
m
ag
e
o
f
th
e
o
r
d
in
ar
y
.
2
.
1
.
I
m
a
g
e
Acquis
it
io
n
T
h
e
i
m
a
g
e
i
s
a
r
ep
r
ese
n
tatio
n
(
p
ictu
r
e)
,
li
k
en
e
s
s
o
r
i
m
i
tatio
n
o
f
a
n
o
b
j
ec
t
[
1
9
]
.
I
m
ag
e
ac
q
u
is
itio
n
i
s
th
e
i
n
itia
l
s
tag
e
to
g
e
t
a
d
i
g
ita
l
i
m
a
g
e.
T
h
e
p
u
r
p
o
s
e
o
f
i
m
a
g
e
ac
q
u
is
i
tio
n
to
d
eter
m
i
n
e
t
h
e
n
ec
es
s
ar
y
d
ata
an
d
ch
o
o
s
e
th
e
m
et
h
o
d
o
f
d
ig
ital i
m
ag
e
r
ec
o
r
d
in
g
.
T
h
e
h
is
to
g
r
a
m
i
s
d
ef
i
n
ed
as
a
s
tatis
tical
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
f
ea
c
h
le
v
el
o
f
g
r
a
y
(
g
r
a
y
s
ca
le)
i
n
th
e
d
ig
ital
i
m
a
g
e
[
2
0
]
.
B
y
u
s
in
g
th
i
s
m
et
h
o
d
ca
n
b
e
p
er
f
o
r
m
e
d
f
o
r
f
latten
i
n
g
t
h
e
h
i
s
to
g
r
a
m
o
f
th
e
i
m
a
g
e
ex
is
t,
s
o
th
at
th
e
i
m
ag
e
ca
n
b
e
g
r
o
u
p
ed
b
y
le
v
el
o
f
t
h
e
i
n
ten
s
it
y
v
al
u
es
o
f
p
i
x
els
o
f
d
i
f
f
er
e
n
t
co
lo
r
s
.
I
n
th
e
g
r
a
y
i
m
a
g
e
(
Gr
a
y
s
ca
l
e)
8
b
its
,
th
er
e
ar
e
2
5
6
lev
els o
f
i
n
ten
s
it
y
v
a
lu
es d
i
f
f
er
e
n
t i
n
ten
s
it
y
.
2
.
2
.
M
o
rpho
lo
g
y
a
nd
I
m
a
g
e
Seg
m
e
nta
t
io
n
Mo
r
p
h
o
lo
g
y
is
an
i
m
a
g
e
p
r
o
c
ess
i
n
g
tec
h
n
iq
u
e
th
a
t
is
b
ased
o
n
th
e
s
h
ap
e
o
f
a
s
eg
m
e
n
t
o
r
r
eg
io
n
[
2
1
]
.
I
n
m
o
r
p
h
o
lo
g
y
t
h
er
e
ar
e
s
ev
er
al
o
p
er
atio
n
s
o
f
w
h
ich
ar
e
u
s
ed
in
t
h
is
s
tu
d
y
ar
e
d
ilatio
n
o
p
er
atio
n
er
o
s
io
n
o
p
er
atio
n
an
d
o
p
en
in
g
o
p
er
atio
n
.
I
m
ag
e
s
e
g
m
e
n
tat
io
n
i
s
d
o
n
e
t
o
s
ep
ar
ate
th
e
o
b
j
ec
t
w
it
h
t
h
e
b
ac
k
g
r
o
u
n
d
.
T
h
e
s
ep
ar
atio
n
p
r
o
ce
s
s
ai
m
s
to
s
i
m
p
li
f
y
t
h
e
p
r
o
ce
s
s
s
o
th
at
th
e
o
b
j
ec
t
class
if
icatio
n
an
d
co
u
n
tin
g
o
f
eg
g
s
i
n
th
e
i
m
ag
e
ca
n
b
e
g
r
o
u
p
ed
ap
p
r
o
p
r
iately
a
n
d
w
er
e
co
u
n
ted
ac
cu
r
atel
y
.
S
eg
m
e
n
tatio
n
h
as
b
ee
n
d
o
n
e
to
th
e
clu
s
t
er
in
g
p
r
o
ce
s
s
[
2
2
]
.
Op
er
atio
n
b
in
ar
is
m
s
is
th
e
s
e
g
m
e
n
tat
io
n
p
r
o
ce
s
s
o
f
a
g
r
ay
s
ca
le
i
m
a
g
e
to
p
r
o
d
u
ce
a
b
in
ar
y
i
m
a
g
e.
B
in
ar
ies
p
r
o
ce
s
s
r
eq
u
ir
es
a
th
r
es
h
o
ld
v
alu
e
(
T
)
,
th
e
p
r
o
ce
s
s
o
f
f
i
n
d
i
n
g
t
h
e
t
h
r
esh
o
ld
v
a
lu
e
i
s
ca
ll
ed
th
r
esh
o
ld
in
g
t
h
e
i
m
a
g
e.
I
m
a
g
e
th
r
es
h
o
ld
in
g
i
s
a
s
i
m
p
le,
y
e
t
ef
f
ec
ti
v
e,
w
a
y
o
f
p
ar
titi
o
n
in
g
a
n
i
m
a
g
e
i
n
t
o
a
f
o
r
eg
r
o
u
n
d
an
d
b
ac
k
g
r
o
u
n
d
[
2
3
]
.
2
.
3
.
Cent
ro
id a
nd
B
o
un
din
g
B
o
x
T
h
e
ce
n
tr
o
id
is
th
e
m
id
d
le
v
a
lu
e
o
f
an
o
b
j
ec
t
is
d
etec
ted
,
a
n
d
th
e
b
o
u
n
d
in
g
b
o
x
is
a
f
u
n
ctio
n
th
at
s
er
v
es
to
m
a
k
e
t
h
e
ap
p
r
o
p
r
ia
te
b
o
x
th
e
s
ize
o
f
t
h
e
o
b
j
ec
t
id
en
tif
ied
[
2
4
]
.
A
n
d
to
ass
i
s
t
in
th
e
p
r
o
ce
s
s
o
f
d
et
er
m
in
i
n
g
t
h
e
ce
n
tr
o
id
an
d
t
h
e
b
o
u
n
d
in
g
b
o
x
r
eq
u
ir
ed
r
eg
io
n
p
r
o
p
s
p
r
o
ce
s
s
.
R
eg
io
n
p
r
o
p
s
is
a
m
et
h
o
d
u
s
ed
to
m
ea
s
u
r
e
a
s
et
o
f
p
r
o
p
er
ties
f
r
o
m
ev
er
y
r
eg
io
n
th
at
h
a
v
e
b
ee
n
lab
eled
in
th
e
m
atr
i
x
lab
el
[
2
4
]
,
[
2
5
]
.
3.
RE
SU
L
T
S
A
ND
AN
AL
Y
SI
S
R
es
u
lts
o
b
tain
ed
f
r
o
m
t
h
e
s
t
u
d
y
w
it
h
a
p
r
o
to
ty
p
e
u
s
in
g
Ma
tlab
w
ill
b
e
p
r
esen
ted
s
ta
r
tin
g
f
r
o
m
p
r
ep
r
o
ce
s
s
in
g
to
i
m
a
g
e
p
r
o
ce
s
s
in
g
an
d
g
et
th
e
r
es
u
lt.
3
.
1
.
P
re
pro
ce
s
s
ing
(
O
rig
ina
l (
Co
lo
r)
I
m
a
g
e
beco
m
es
G
ra
y
s
ca
le)
T
h
e
p
r
o
ce
s
s
p
r
ep
r
o
ce
s
s
in
g
o
f
th
e
ca
p
tu
r
ed
i
m
ag
e
FL
I
R
th
e
r
m
al
i
m
a
g
er
ca
m
er
a
a
n
d
i
m
a
g
e
ca
p
tu
r
e
r
esu
lt
s
f
r
o
m
a
s
m
ar
tp
h
o
n
e
ca
m
er
a.
T
h
e
in
itial
p
r
o
ce
s
s
is
to
ch
an
g
e
th
e
co
lo
r
im
a
g
e
(
R
G
B
)
in
to
a
g
r
ay
i
m
a
g
e
(
g
r
a
y
s
ca
le)
to
f
latten
t
h
e
i
n
te
n
s
it
y
o
f
co
lo
r
p
o
s
s
e
s
s
ed
b
y
t
h
e
co
lo
r
i
m
a
g
e
(
o
r
ig
i
n
al)
.
T
h
e
i
m
ag
er
y
u
s
ed
i
s
t
h
e
i
m
a
g
e
o
f
a
ch
ic
k
e
n
eg
g
th
a
t
h
ad
b
ee
n
tak
e
n
f
r
o
m
t
w
o
o
f
th
ese
to
o
ls
.
I
m
ag
e
p
r
o
ce
s
s
in
g
o
n
t
h
e
in
i
tial
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
s
s
is
d
o
n
e
b
y
c
h
a
n
g
i
n
g
th
e
i
m
a
g
e
o
f
a
c
h
ick
e
n
e
g
g
i
n
to
a
g
r
a
y
s
ca
le
i
m
ag
e
a
s
ca
n
b
e
s
ee
n
in
Fi
g
u
r
e
1
.
(
a)
(
b
)
(
c)
(
d
)
Fig
u
r
e
2
.
I
m
a
g
e
w
it
h
T
h
er
m
al
I
m
ag
i
n
g
C
a
m
er
a
(
a)
.
C
o
lo
r
I
m
ag
e,
(
b
)
.
Gr
ay
s
ca
le
I
m
ag
e
; a
n
d
S
m
ar
tp
h
o
n
e
C
a
m
er
a
(
c)
.
C
o
lo
r
I
m
a
g
e,
(
d
)
.
Gr
a
y
s
ca
le
I
m
ag
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
7
:
2
00
–
2
0
8
204
Fig
u
r
e
2
s
h
o
w
s
th
e
r
esu
lts
o
f
th
e
co
n
v
er
s
io
n
o
f
a
co
lo
r
i
m
ag
e
i
n
to
a
g
r
a
y
s
ca
le
i
m
ag
e
.
Fo
r
th
e
i
m
a
g
er
y
o
f
t
h
er
m
al
i
m
ag
in
g
s
h
o
w
ed
a
s
i
g
n
if
ica
n
t
d
i
f
f
er
en
ce
b
et
w
ee
n
th
e
co
lo
r
i
m
a
g
e
(
Fig
u
r
e
2
(
a)
)
w
it
h
a
g
r
a
y
s
ca
le
i
m
a
g
e
(
Fi
g
u
r
e
2
(
b
)
)
,
b
u
t
to
th
e
i
m
a
g
e
o
f
t
h
e
s
m
ar
tp
h
o
n
e
ca
m
er
a
s
h
o
w
ed
th
e
s
a
m
e
r
es
u
lts
(
Fig
u
r
e
2
(
c)
an
d
Fi
g
u
r
e
2
(
d
)
)
w
h
e
n
v
ie
w
ed
w
it
h
t
h
e
n
a
k
ed
e
y
e,
b
ec
au
s
e
t
h
e
e
g
g
s
ar
e
ta
k
e
n
s
a
m
p
le
i
s
a
n
e
g
g
th
at
h
a
s
a
w
h
ite
co
lo
r
an
d
th
e
b
ac
k
g
r
o
u
n
d
ap
p
r
o
ac
h
in
g
g
r
a
y
i
s
h
b
lack
s
tr
ip
es.
3
.
2
.
H
is
t
o
g
ra
m
Ana
ly
s
is
o
f
Chic
k
e
n E
g
g
s
I
m
a
g
e
3
.
2
.
1
.
T
her
m
a
l I
m
a
g
e
Or
ig
i
n
al
i
m
ag
e
(
Fi
g
u
r
e
3
(
a)
)
an
d
g
r
a
y
s
ca
le
i
m
ag
e
(
Fi
g
u
r
e
4
(
a)
)
g
iv
e
d
if
f
er
e
n
t
h
is
to
g
r
a
m
.
Or
ig
in
a
l
i
m
a
g
e
s
h
o
w
h
i
s
to
g
r
a
m
w
it
h
all
o
f
i
m
a
g
e
co
m
p
o
n
e
n
t
(
R
ed
,
Gr
ee
n
,
an
d
B
lu
e)
.
B
ase
d
o
n
th
e
co
m
p
ar
is
o
n
o
f
Fig
u
r
e
3
(
b
)
an
d
Fig
u
r
e
4
(
b
)
o
b
tain
ed
th
e
r
esu
lt
t
h
at
th
e
g
r
a
y
s
ca
le
i
m
ag
e
h
is
to
g
r
a
m
,
av
er
ag
e
p
ix
el
in
te
n
s
it
y
o
b
tain
ed
in
a
g
i
v
en
ar
ea
b
et
w
e
en
r
an
g
e
0
-
256.
(
a)
(
b
)
(
c)
Fig
u
r
e
3
.
(
a)
Or
ig
in
al
I
m
a
g
e
(
C
o
lo
r
)
,
(
b
)
His
to
g
r
a
m
C
o
lo
r
I
m
ag
e
(
C
o
m
p
o
s
ite)
,
(
c)
His
to
g
r
a
m
E
ac
h
C
o
lo
r
(
a)
(
b
)
Fig
u
r
e
4
.
(
a)
Gr
ay
s
ca
le
I
m
ag
e,
(
b
)
His
to
g
r
a
m
I
m
a
g
e
Gr
a
y
s
ca
le
3
.
2
.
2
.
Dig
it
a
l I
m
a
g
e
B
ased
o
n
th
e
co
m
p
ar
is
o
n
o
f
F
ig
u
r
e
5
(
b
)
an
d
Fig
u
r
e
6
(
b
)
o
b
t
ain
ed
th
e
r
es
u
lt
t
h
at
t
h
e
g
r
a
y
s
ca
le
i
m
a
g
e
h
is
to
g
r
a
m
,
a
v
er
ag
e
p
i
x
el
i
n
te
n
s
it
y
o
b
tain
ed
as
w
e
ll
as
i
n
t
h
e
th
er
m
al
i
m
a
g
e.
B
u
t
i
n
th
is
ca
s
e,
th
e
h
is
to
g
r
a
m
lo
o
k
s
al
m
o
s
t
t
h
e
s
a
m
e
as
t
h
e
o
r
ig
in
al
i
m
a
g
e
is
s
i
m
ilar
t
o
a
g
r
a
y
s
ca
le
i
m
a
g
e
t
h
at
r
e
s
e
m
b
les
th
e
co
lo
r
co
m
p
o
n
e
n
t
s
o
v
er
a
g
r
a
y
s
ca
le
i
m
a
g
e.
Hi
s
to
g
r
a
m
co
lo
r
i
m
a
g
es
o
f
b
o
t
h
t
h
er
m
a
l
an
d
o
r
d
in
a
r
y
i
m
ag
e
o
b
tain
ed
f
r
o
m
co
m
b
i
n
in
g
ea
ch
co
lo
r
h
i
s
to
g
r
a
m
o
f
ea
ch
co
lo
r
im
a
g
e
b
ased
o
n
R
GB
(
R
ed
,
Gr
ee
n
,
B
lu
e)
in
Fig
u
r
e
3
(
c)
an
d
Fig
u
r
e
5
(
c)
.
E
ac
h
co
lo
r
m
ad
e
its
h
is
to
g
r
a
m
ar
e
t
h
en
co
m
b
in
ed
in
to
o
n
e
(
Fi
g
u
r
e
3
(
b
)
an
d
Fig
u
r
e
5
(
b
)
)
.
(
a)
(
b
)
(
c)
Fig
u
r
e
5
.
(
a)
Or
ig
in
al
I
m
a
g
e
(
C
o
lo
r
)
,
(
b
)
His
to
g
r
an
C
o
lo
r
I
m
ag
e
(
C
o
m
p
o
s
ite)
,
(
c)
His
to
g
r
a
m
E
ac
h
C
o
lo
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
d
en
tity A
n
a
lysi
s
o
f E
g
g
B
a
s
ed
o
n
Dig
ita
l a
n
d
Th
erma
l I
ma
g
in
g
:
I
ma
g
e
P
r
o
ce
s
s
in
g
a
n
d
....
(
S
u
n
a
r
d
i)
205
(
a)
(
b
)
Fig
u
r
e
6
.
(
a)
Gr
ay
s
ca
le
I
m
ag
e,
(
b
)
His
to
g
r
a
m
I
m
a
g
e
Gr
a
y
s
ca
le
T
h
e
s
a
m
p
le
u
s
ed
in
th
e
a
n
al
y
s
is
is
th
e
i
m
a
g
e
e
g
g
s
h
is
to
g
r
a
m
tak
e
n
f
r
o
m
t
h
e
th
er
m
al
i
m
a
g
i
n
g
ca
m
er
a
(
Fig
u
r
e
3
(
a)
an
d
Fig
u
r
e
4
(
a)
)
an
d
s
m
ar
tp
h
o
n
e
ca
m
er
a
(
Fig
u
r
e
5
(
a)
an
d
Fig
u
r
e
6
(
a)
)
.
B
a
s
ed
o
n
co
m
p
ar
ativ
e
an
al
y
s
is
o
f
t
h
e
h
is
to
g
r
a
m
o
f
co
lo
r
an
d
g
r
a
y
s
ca
le,
g
r
a
y
s
ca
l
e
i
m
a
g
es
(
u
s
i
n
g
a
t
h
r
es
h
o
ld
Ots
u
)
o
b
tai
n
ed
th
e
in
te
n
s
it
y
o
f
th
e
co
lo
r
is
f
lat
ter
th
a
n
th
e
co
lo
r
i
m
a
g
e
h
i
s
to
g
r
a
m
i
s
ap
p
ar
en
t
th
a
t
t
h
e
co
lo
r
h
is
to
g
r
a
m
p
r
o
d
u
ce
s
co
lo
r
s
p
r
ea
d
s
(
Fig
u
r
e
5
(
b
)
)
,
a
n
d
g
r
a
y
s
ca
le
i
m
ag
e
s
clo
s
er
s
e
ctio
n
(
Fi
g
u
r
e
6
(
b
)
,
w
h
ic
h
i
s
d
en
s
er
an
d
h
as
a
f
lat
in
te
n
s
it
y
.
3
.
3
.
T
he
P
ro
ce
s
s
o
f
Dila
t
io
n a
t
G
ra
y
s
ca
le
I
m
a
g
e
T
h
e
p
r
o
ce
s
s
o
f
eg
g
p
r
o
d
u
ce
d
d
ilatio
n
i
m
a
g
e
s
h
o
w
n
in
F
ig
u
r
e
7
.
(
a)
(
b
)
Fig
u
r
e
7
.
R
esu
lts
o
f
Op
er
atio
n
s
I
m
a
g
e
P
r
o
ce
s
s
in
g
w
i
th
D
ilati
o
n
to
th
e
m
o
r
p
h
o
lo
g
y
(
a)
T
h
er
m
al
i
m
ag
e,
(
b
)
Or
d
in
ar
y
I
m
a
g
e
Dilatio
n
o
p
er
atio
n
p
er
f
o
r
m
ed
to
en
lar
g
e
t
h
e
s
ize
o
f
t
h
e
s
e
g
m
en
t.
I
n
t
h
is
i
m
a
g
e
(
Fi
g
u
r
e
7
(
a)
)
o
f
th
e
d
ilatio
n
p
r
o
ce
s
s
i
s
ca
r
r
ied
o
u
t
u
s
in
g
Stre
l
'
d
ia
m
o
n
d
'
,
s
o
th
a
t
in
t
h
e
p
ict
u
r
e
th
er
e
ar
e
a
lo
t
o
f
p
ar
allelo
g
r
a
m
s
(
Fig
u
r
e
7
(
b
)
)
.
3
.
4
.
Co
nv
er
t
I
m
a
g
e
I
nto
a
G
ra
y
s
ca
le
I
m
a
g
e
B
la
ck
White
(
B
W)
T
h
e
r
esu
lts
o
f
th
e
p
r
o
ce
s
s
o
f
d
ilatio
n
co
n
v
er
ted
to
im
a
g
es
i
n
b
lack
an
d
w
h
ite
(
Fig
u
r
a
8
(
a)
)
,
an
d
th
e
n
d
o
th
e
co
m
p
le
m
e
n
t
(
Fi
g
u
r
e
8
(
b
)
)
w
il
l
b
e
u
s
ed
f
o
r
ca
lcu
lati
n
g
t
h
e
ce
n
tr
o
id
th
at
e
x
is
t
i
n
t
h
e
i
m
ag
e
t
h
er
m
al,
w
h
ite
co
lo
r
r
ep
r
esen
ts
a
v
a
lu
e
o
f
1
in
d
icatin
g
t
h
at
t
h
er
e
ar
e
o
b
j
ec
ts
an
d
w
ill
lo
o
k
f
o
r
v
alu
e
ce
n
tr
o
id
n
y
a,
a
n
d
b
lack
r
ep
r
esen
ts
a
v
al
u
e
o
f
0
w
h
ic
h
is
b
ac
k
g
r
o
u
n
d
ex
is
t
s
in
th
e
i
m
a
g
e.
A
s
f
o
r
th
e
u
s
u
al
i
m
ag
e
(
Fig
u
r
e
9
(
a)
)
o
f
th
e
o
p
en
i
n
g
p
r
o
ce
s
s
f
o
r
s
ep
ar
atin
g
o
b
j
ec
ts
th
at
m
er
g
e
o
r
eli
m
i
n
ate
s
m
all
o
b
j
ec
ts
(
s
p
r
ea
d
s
n
o
is
e)
s
o
th
at
t
h
e
o
b
j
ec
t d
etec
ted
is
eg
g
alo
n
e
(
F
ig
u
r
e
9
(
b
)
)
.
(
a)
(
b
)
Fig
u
r
e
8
.
T
h
er
m
al
I
m
a
g
e
s
(
a)
R
es
u
lts
o
f
C
o
n
v
er
s
io
n
to
B
W
,
(
b
)
C
o
m
p
le
m
en
t o
f
B
W
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
7
:
2
00
–
2
0
8
206
(
a)
(
b
)
Fig
u
r
e
9
.
Or
d
in
ar
y
I
m
a
g
e
(
a)
R
es
u
lts
o
f
C
o
n
v
er
s
io
n
to
B
W
,
(
b
)
d
ilatio
n
o
f
Gr
ay
s
ca
le
an
d
Op
en
in
g
o
f
B
W
3
.
5
.
Resul
t
s
L
a
belin
g
,
Cent
ro
id
Det
er
m
i
na
t
io
n P
ro
ce
s
s
a
nd
B
o
un
din
g
B
o
x
I
m
ag
e
p
r
o
ce
s
s
in
g
r
e
s
u
l
ts
o
b
t
ain
ed
f
r
o
m
t
h
e
o
b
j
ec
t
r
ec
o
g
n
itio
n
e
g
g
s
i
m
a
g
e
(
Fi
g
u
r
e
1
0
)
.
I
m
a
g
e
p
r
o
ce
s
s
in
g
g
r
o
u
p
(
th
er
e
ar
e
6
eg
g
s
)
s
h
o
w
ed
6
eg
g
o
b
j
ec
t
i
s
o
b
tain
ed
.
T
h
e
r
esu
lt
o
f
lab
ellin
g
,
ce
n
tr
o
id
an
d
b
u
n
d
i
n
g
b
o
x
h
av
e
s
h
o
w
n
i
n
Fig
u
r
e
1
0
(
a)
w
ith
lab
el
1
a
u
n
til
6
a
f
r
o
m
t
h
er
m
al
i
m
a
g
e,
an
d
Fig
u
r
e
1
0
(
b
)
w
it
h
lab
el
1
b
u
n
til 6
b
f
r
o
m
d
ig
ita
l i
m
ag
e.
(
a)
(
b
)
Fig
u
r
e
1
0
.
I
m
a
g
e
P
r
o
ce
s
s
in
g
Gr
o
u
p
E
g
g
s
w
i
th
C
e
n
tr
o
id
an
d
Dete
r
m
i
n
atio
n
o
f
P
lace
s
w
i
th
L
ab
el
(
a)
T
h
er
m
a
l I
m
a
g
e,
(
b
)
Dig
ital
I
m
a
g
e
T
ab
le
1
.
R
esu
lts
o
f
I
m
a
g
e
P
r
o
ce
s
s
i
n
g
R
ated
C
e
n
tr
o
id
(
X,
Y)
an
d
T
o
tal
ar
ea
(
P
ix
el)
C
en
tr
o
id
X
a
n
d
Y
w
it
h
t
h
e
v
alu
e
o
f
r
ea
d
in
g
i
s
s
tar
ted
f
r
o
m
m
a
tr
ices
(
0
.
0
)
,
w
h
er
ein
t
h
e
m
atr
i
x
s
tar
tin
g
at
th
e
to
p
lef
t
co
r
n
er
p
o
in
t.
Fro
m
T
ab
le
1
it
ca
n
b
e
s
ee
n
th
at
b
y
u
s
in
g
a
th
er
m
al
i
m
a
g
e
an
d
o
r
d
in
ar
y
i
m
a
g
e
o
b
tain
ed
d
ata
h
av
e
T
o
t
al
A
r
ea
(
P
ix
el)
E
q
u
iv
ale
n
t
(
≡)
o
r
clo
s
e
t
o
th
e
s
a
m
e.
So
as
to
o
b
tain
th
e
r
atio
o
f
th
e
ar
ea
as T
ab
le
2
.
D
a
t
a
L
a
b
e
l
N
a
me
C
e
n
t
r
o
i
d
T
o
t
a
l
A
r
e
a
(
P
i
x
e
l
)
X
Y
1a
L
a
b
e
l
2
1
5
7
,
4
6
4
4
2
5
2
,
8
4
9
4
1
0
8
9
,
0
0
3
3
2a
L
a
b
e
l
4
3
1
6
,
6
7
3
2
2
4
2
,
5
3
4
8
1
1
0
3
,
0
0
3
3
3a
L
a
b
e
l
6
4
3
9
,
6
4
6
2
2
6
,
9
1
8
9
1
1
1
7
,
0
0
3
3
4a
L
a
b
e
l
1
1
5
0
,
2
8
6
1
1
3
1
,
9
3
7
2
1
0
8
2
,
0
0
3
3
5a
L
a
b
e
l
3
3
1
1
,
1
5
3
9
1
1
4
,
8
1
6
7
1
0
9
6
,
0
0
3
3
6a
L
a
b
e
l
5
4
3
5
,
1
2
0
2
8
0
,
8
7
5
3
1
1
1
0
,
0
0
3
3
1b
L
a
b
e
l
1
2
9
2
,
8
8
3
5
5
6
8
,
9
4
2
5
1
0
8
2
,
0
0
2
7
2b
L
a
b
e
l
4
7
4
5
,
0
3
0
5
5
9
0
,
7
5
1
3
1
1
0
3
,
0
0
2
7
3b
L
a
b
e
l
6
1
0
6
2
,
4
5
5
6
3
5
,
1
6
6
1
1
1
7
,
0
0
2
7
4b
L
a
b
e
l
2
3
5
5
,
0
2
1
3
2
2
0
,
1
7
3
8
1
0
8
9
,
0
0
2
7
5b
L
a
b
e
l
3
7
1
0
,
2
6
4
7
2
3
9
,
8
8
3
6
1
0
9
6
,
0
0
2
7
6b
L
a
b
e
l
5
1
0
4
9
,
4
9
9
2
8
5
,
3
8
2
5
1
1
1
0
,
0
0
2
7
1a
2
a
3
a
1b
2b
3b
4
a
5
a
6
a
4b
5b
6b
Evaluation Warning : The document was created with Spire.PDF for Python.
I
J
E
C
E
I
SS
N:
2
0
8
8
-
8708
I
d
en
tity A
n
a
lysi
s
o
f E
g
g
B
a
s
ed
o
n
Dig
ita
l a
n
d
Th
erma
l I
ma
g
in
g
:
I
ma
g
e
P
r
o
ce
s
s
in
g
a
n
d
....
(
S
u
n
a
r
d
i)
207
T
ab
le
2
.
C
o
m
p
ar
is
o
n
o
f
T
o
tal
A
r
ea
(
P
ix
el)
B
ased
o
n
T
ab
le
2
an
d
Fig
u
r
e
1
0
(
a)
an
d
(
b
)
D
a
t
a
(
a
)
D
a
t
a
(
b
)
F
i
g
u
r
e
T
o
t
a
l
A
r
e
a
Eq
u
i
v
a
l
e
n
t
(
a
)
(
b
)
(
a
)
P
i
x
e
l
(
b
)
P
i
x
e
l
1a
4b
L
a
b
e
l
2
L
a
b
e
l
2
1
0
8
9
,
0
0
3
3
1
0
8
9
,
0
0
2
7
2a
2b
L
a
b
e
l
4
L
a
b
e
l
4
1
1
0
3
,
0
0
3
3
1
1
0
3
,
0
0
2
7
3a
3b
L
a
b
e
l
6
L
a
b
e
l
6
1
1
1
7
,
0
0
3
3
1
1
1
7
,
0
0
2
7
4a
1b
L
a
b
e
l
1
L
a
b
e
l
1
1
0
8
2
,
0
0
3
3
1
0
8
2
,
0
0
2
7
5a
5b
L
a
b
e
l
3
L
a
b
e
l
5
1
0
9
6
,
0
0
3
3
1
0
9
6
,
0
0
2
7
6a
6b
L
a
b
e
l
5
L
a
b
e
l
6
1
1
1
0
,
0
0
3
3
1
1
1
0
,
0
0
2
7
B
ased
o
n
an
e
g
g
-
b
ased
i
m
a
g
e
p
r
o
ce
s
s
in
g
o
f
th
er
m
al
i
m
a
g
i
n
g
an
d
o
u
ts
ta
n
d
in
g
i
m
a
g
e
t
h
a
t
h
as
b
ee
n
d
o
n
e,
it c
a
n
b
e
co
n
cl
u
d
ed
t
h
at
th
e
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
ca
n
b
e
d
o
n
e
an
d
g
et
th
e
r
es
u
lts
ca
n
d
et
er
m
in
e
t
h
e
n
u
m
b
er
o
f
eg
g
s
i
n
th
e
ca
p
t
u
r
e
w
ith
t
h
e
FL
I
R
t
h
er
m
al
i
m
ag
i
n
g
ca
m
e
r
a
an
d
a
s
m
ar
tp
h
o
n
e
ca
m
er
a.
T
h
e
u
s
e
o
f
m
e
th
o
d
s
th
at
d
is
ti
n
g
u
is
h
f
o
r
i
m
a
g
e
p
r
o
ce
s
s
i
n
g
.
T
h
e
co
m
p
ar
is
o
n
i
s
s
h
o
w
n
i
n
T
ab
le
3
.
T
ab
le
3
.
C
o
m
p
ar
is
o
n
o
f
I
m
a
g
e
P
r
o
ce
s
s
in
g
an
d
R
es
u
lts
No
T
h
e
r
mal
I
mag
e
I
mag
e
D
i
g
i
t
a
l
N
o
t
e
1.
M
o
r
p
h
o
l
o
g
i
c
a
l
D
i
l
a
t
i
o
n
M
o
r
p
h
o
l
o
g
i
c
a
l
D
i
l
a
t
i
o
n
a
n
d
O
p
e
n
i
n
g
D
i
f
f
e
r
e
n
c
e
s i
n
mo
r
p
h
o
l
o
g
i
c
a
l
i
mag
e
p
r
o
c
e
ssi
n
g
t
h
a
t
i
s
u
se
d
i
s
t
h
e
u
s
u
a
l
i
mag
e
n
e
e
d
s t
o
b
e
d
o
n
e
t
o
se
p
a
r
a
t
e
t
h
e
p
r
o
c
e
ss o
f
o
p
e
n
i
n
g
a
n
d
o
b
j
e
c
t
s
t
h
a
t
c
o
mb
i
n
e
o
r
e
l
i
mi
n
a
t
e
n
o
i
se
.
2.
C
o
mp
l
e
me
n
t
No
T
h
e
t
h
e
r
mal
i
mag
e
p
r
o
c
e
ss m
u
s
t
b
e
d
o
n
e
c
o
mp
l
e
me
n
t
o
f
B
W
i
m
a
g
e
t
h
a
t
h
a
s
b
e
e
n
p
r
o
c
e
sse
d
t
o
b
e
a
r
e
c
o
g
n
i
z
a
b
l
e
o
b
j
e
c
t
t
o
b
e
d
e
t
e
r
mi
n
e
d
v
a
l
u
e
o
f
t
h
e
c
e
n
t
r
o
i
d
a
n
d
t
h
e
b
o
u
n
d
i
n
g
b
o
x
.
3.
I
n
d
e
t
i
f
i
e
d
I
n
d
e
t
i
f
i
e
d
A
l
l
t
h
e
i
mag
e
s c
a
n
b
e
i
d
e
n
t
i
f
i
e
d
f
o
r
a
l
l
o
b
j
e
c
t
s e
g
g
s t
h
a
t
h
a
v
e
b
e
e
n
c
a
p
t
u
r
e
d
.
4.
T
o
t
a
l
A
r
e
a
(
P
i
x
e
l
)
i
s
k
n
o
w
n
T
o
t
a
l
A
r
e
a
(
P
i
x
e
l
)
i
s
k
n
o
w
n
O
f
t
h
e
t
w
o
i
mag
e
s o
b
t
a
i
n
e
d
T
o
t
a
l
A
r
e
a
e
q
u
i
v
a
l
e
n
t
.
4.
CO
NCLU
SI
O
N
T
h
e
R
es
u
lt
s
h
o
w
s
t
h
at
t
h
e
id
en
ti
f
icatio
n
p
r
o
ce
s
s
c
h
ic
k
en
eg
g
s
u
s
in
g
a
th
er
m
al
i
m
ag
i
n
g
ca
m
er
a
a
n
d
a
s
m
ar
tp
h
o
n
e
ca
m
er
a
ca
n
w
o
r
k
1
0
0
%
w
it
h
t
h
e
o
b
tain
ed
d
if
f
er
en
ce
m
o
r
p
h
o
lo
g
ical
p
r
o
ce
s
s
es
an
d
an
al
y
s
i
s
o
f
o
b
j
ec
ts
b
y
ch
a
n
g
in
g
to
co
m
p
l
e
m
en
t.
So
f
r
o
m
t
h
e
i
m
ag
e
p
r
o
ce
s
s
in
g
ce
n
tr
o
id
an
d
t
h
e
b
o
u
n
d
i
n
g
b
o
x
ca
n
b
e
s
ee
n
an
d
co
u
n
t
o
f
o
b
j
ec
t
.
A
lth
o
u
g
h
th
er
e
ar
e
d
if
f
er
en
ce
s
,
t
h
e
r
esu
lts
o
f
t
h
e
co
u
n
ti
n
g
ar
ea
(
p
ix
els)
o
f
b
o
th
ar
e
eq
u
iv
ale
n
t to
th
e
d
i
f
f
er
en
ce
is
v
er
y
s
m
all
a
s
6
x
1
0
-
3
.
RE
F
E
R
E
NC
E
S
[1
]
T
RIDIN
E
W
S
,
“
P
e
n
jela
sa
n
F
u
n
g
si
d
a
n
Ke
g
u
n
a
a
n
d
a
ri
T
h
e
rm
o
g
ra
p
h
y
,
”
T
riDiNe
ws
Up
d
a
te
In
f
o
r
m
a
t
io
n
&
S
h
a
ri
n
g
Kn
o
w
led
g
e
,
2
0
1
4
.
[
Ci
ted
:
S
e
p
tem
b
e
r
1
,
2
0
1
6
]
h
t
tp
:/
/www
.
n
e
w
s.tr
id
in
a
m
ik
a
.
c
o
m
/
[2
]
E.
S
e
ti
a
w
a
n
,
“
Ka
m
u
s
Be
sa
r
Ba
h
a
sa
In
d
o
n
e
sia
(KBBI)
,”
T
e
lu
r.
[
On
li
n
e
]
Ba
d
a
n
P
e
n
g
e
m
b
a
n
g
a
n
d
a
n
P
e
m
b
in
a
a
n
Ba
h
a
sa
,
Ke
m
d
ik
b
u
d
(
P
u
sa
t
Ba
h
a
sa
),
2
0
1
2
.
[
Cit
e
d
:
S
e
p
tem
b
e
r
1
,
2
0
1
6
]
.
h
tt
p
:/
/k
b
b
i.
w
e
b
.
id
/
.
[3
]
In
f
ra
ta
m
a
In
d
o
n
e
sia
,
In
f
ra
re
d
S
u
rv
e
y
o
r
,
“
A
b
o
u
t
In
f
ra
re
d
T
h
e
rm
o
g
ra
p
h
y
,”
P
T
In
f
re
a
ta
m
In
d
o
n
e
si
a
2
0
0
2
.
[
Cit
e
d
:
S
e
p
term
b
e
r
1
,
2
0
1
6
]
h
t
tp
:/
/www
.
i
n
f
r
a
ta
m
a
.
c
o
.
id
/
[4
]
S
u
n
a
r
d
i,
e
t
a
l.
,
“
T
h
e
rm
a
l
I
m
a
g
in
g
Un
tu
k
Id
e
n
ti
f
ik
a
si
T
e
lu
r,
”
Pro
sid
i
n
g
K
o
n
fer
e
n
si
N
a
sio
n
a
l
Ke
-
4
,
Aso
sia
si
Pro
g
ra
m
Pa
sc
a
sa
rj
a
n
a
Per
g
u
ru
a
n
T
i
n
g
g
i
M
u
h
a
mm
a
d
iya
h
(
AP
PP
T
M
)
,
p
p
.
1
5
2
-
1
5
7
.
[5
]
T
.
P
.
R
.
M
a
im
u
n
a
h
,
“
Kla
sif
ik
a
si
M
u
t
u
T
e
lu
r
Be
rd
a
sa
rk
a
n
Ke
b
e
rsih
a
n
Ke
ra
b
a
n
g
T
e
lu
r
M
e
n
g
g
u
n
a
k
a
n
K
-
Ne
a
re
st
Ne
ig
h
b
o
r
,
”
Ko
n
fer
e
n
si Na
si
o
n
a
l
I
n
fo
rm
a
t
ika
(
KNIF)
,
2
0
1
5
.
[6
]
W
ij
a
y
a
T
.
A
.
a
n
d
Yu
d
i
P.
,
“
Im
p
le
m
e
n
tas
i
V
isi
Ko
m
p
u
ter
Da
n
S
e
g
m
e
n
tas
i
Cit
ra
Un
tu
k
Kla
sif
i
k
a
si
Bo
b
o
t
T
e
lu
r
Ay
a
m
Ra
s
,
”
S
e
min
a
r Na
si
o
n
a
l
A
p
li
k
a
si
T
e
k
n
o
l
o
g
i
In
f
o
rm
a
si
,
Y
o
g
y
a
k
a
rta
,
p
p
.
G1
-
G5
,
2
0
1
0
.
[7
]
Kh
a
b
ib
u
ll
o
h
M
.
A
.
,
e
t
a
l
.
,
“
Ra
n
c
a
n
g
Ba
n
g
u
n
S
iste
m
D
e
tek
si
E
m
b
rio
p
a
d
a
T
e
lu
r
M
e
n
g
g
u
n
a
k
a
n
W
e
b
c
a
m
e
,
”
J
u
rn
a
l
T
e
k
n
ik P
o
mits
,
v
o
l/
issu
e
:
1
(
1
)
,
pp.
1
-
6
,
2
0
1
2
.
[8
]
Ru
slian
to
I
.
,
“
Kla
sif
ik
a
si
T
e
lu
r
Ay
a
m
Da
n
Telu
r
Bu
ru
n
g
P
u
y
u
h
M
e
n
g
g
u
n
a
k
a
n
M
e
to
d
e
Co
n
n
e
c
ted
Co
m
p
o
n
e
n
t
A
n
a
l
y
si
s
,”
J
u
rn
a
l
Ilmi
a
h
S
I
S
FOT
ENIKA
,
v
o
l/
issu
e
:
3
(
1
)
,
p
p
.
41
-
50
,
2
0
1
3
.
[9
]
Uta
m
i
Y
.
R
.
A.
,
“
P
e
n
g
e
n
a
lan
T
e
l
u
r
Be
rd
a
sa
rk
a
n
Ka
ra
k
teristik
W
a
rn
a
Cit
ra
,”
J
u
rn
a
l
Ilmi
a
h
S
INUS
,
v
o
l/
issu
e
:
7
(
2
)
,
p
p
.
1
-
14
,
2
0
0
9
.
[1
0
]
Nu
rh
a
y
a
ti
O
.
D
.
,
“
S
istem
A
n
a
li
si
s
T
e
k
stu
r
S
e
c
a
ra
S
tatisti
k
Ord
e
P
e
rta
m
a
Un
tu
k
M
e
n
g
e
n
a
li
Je
n
is
T
e
lu
r
Ay
a
m
Bias
a
d
a
n
T
e
lu
r
Ay
a
m
O
m
e
g
a
-
3
,”
J
u
rn
a
l
S
istem
Ko
mp
u
ter
,
v
o
l/
issu
e
:
5
(
2
)
,
pp.
79
-
82
,
2
0
1
5
.
[1
1
]
L
.
H
.
L
i
n
g
,
e
t
a
l.
,
“
Re
se
a
rc
h
o
n
t
h
e
Disc
rim
in
a
ti
o
n
o
f
Ha
tch
in
g
E
g
g
s
A
c
ti
v
it
y
Ba
se
d
o
n
T
h
e
rm
a
l
Im
a
g
in
g
:
A
F
o
o
d
No
n
d
e
str
u
c
ti
v
e
T
e
stin
g
P
ra
c
ti
c
e
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
S
ma
rt
Ho
me
,
v
o
l/
issu
e
:
10
(
2
)
,
p
p
.
1
7
5
-
1
8
6
,
2
0
1
6
.
[1
2
]
L
.
L
iu
a
n
d
M
.
O.
Ng
a
d
i,
“
D
e
tec
ti
n
g
F
e
rti
li
ty
a
n
d
Earl
y
E
m
b
r
y
o
D
e
v
e
lo
p
m
e
n
t
o
f
Ch
ick
e
n
E
g
g
s
Us
in
g
Ne
a
r
-
In
f
ra
r
e
d
H
y
p
e
r
sp
e
c
tral
I
m
a
g
in
g
,
”
Fo
o
d
Bi
o
p
ro
c
e
ss
T
e
c
h
n
o
l
,
v
o
l.
6
,
p
p
.
2
5
0
3
-
2
5
1
3
,
2
0
1
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
J
E
C
E
Vo
l.
7
,
No
.
1
,
Feb
r
u
ar
y
2
0
1
7
:
2
00
–
2
0
8
208
[1
3
]
C
.
S
.
L
in
,
e
t
a
l
.
,
“
T
h
e
Id
e
n
t
if
ica
ti
o
n
a
n
d
F
il
terin
g
o
f
F
e
rti
li
z
e
d
Eg
g
s
w
it
h
a
T
h
e
r
m
a
l
I
m
a
g
in
g
S
y
ste
m
,”
Co
mp
u
ter
s
a
n
d
El
e
c
tro
n
ics
in
A
g
ric
u
lt
u
re
,
v
o
l/
issu
e
:
91
(
2
0
1
3
)
,
p
p
.
94
–
1
0
5
,
2
0
1
3
.
[1
4
]
A
it
k
e
n
h
e
a
d
M
.
J
.
,
e
t
a
l.
,
“
W
e
e
d
a
n
d
c
ro
p
d
isc
rim
in
a
ti
o
n
u
sin
g
im
a
g
e
a
n
a
l
y
sis
a
n
d
a
rti
f
icia
l
in
telli
g
e
n
c
e
m
e
th
o
d
s
,”
Co
mp
u
ter
s
a
n
d
Ag
ric
u
lt
u
re
,
v
o
l/
i
ss
u
e
:
3
9
(
2
0
0
3
)
,
p
p
.
1
5
7
-
1
7
1
,
2
0
0
3
.
[1
5
]
Ak
h
a
v
a
n
R
.
a
n
d
F
a
e
z
K
.
,
“
Tw
o
No
v
e
l
Re
ti
n
a
l
Blo
o
d
V
e
ss
e
l
S
e
g
m
e
n
tatio
n
A
lg
o
rit
h
m
s
,”
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/
issu
e
:
4
(
3
)
,
p
p
.
398
-
4
1
0
,
2
0
1
4
.
[1
6
]
S
.
G
.
S
a
p
a
ru
d
in
,
“
S
e
g
m
e
n
tatio
n
o
f
F
in
g
e
rp
rin
t
Im
a
g
e
Ba
s
e
d
o
n
G
ra
d
ien
t
M
a
g
n
it
u
d
e
a
n
d
C
o
h
e
re
n
c
e
,”
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
t
e
r E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l/
issu
e
:
5
(5
)
,
p
p
.
1
2
0
2
-
1
2
1
5
,
2
0
1
5
.
[1
7
]
Ha
rik
iran
J
.
,
e
t
a
l.
,
“
M
u
lt
i
p
le
F
e
a
tu
re
F
u
z
z
y
c
-
m
e
a
n
s
Clu
ste
rin
g
A
lg
o
rit
h
m
f
o
r
S
e
g
m
e
n
tatio
n
o
f
M
icro
a
rra
y
Im
a
g
e
s
,”
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
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l/
issu
e
:
5
(5
),
p
p
.
1
0
4
5
-
1
0
5
3
,
2
0
1
5
.
[1
8
]
F
a
th
i1
A
.
a
n
d
Esk
a
n
d
a
ri
A
.
R.
,
“
D
e
f
e
c
t
D
e
tec
ti
o
n
o
f
T
il
e
s
Ba
s
e
d
o
n
Hig
h
F
re
q
u
e
n
c
y
Disto
rti
o
n
,”
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
t
e
r E
n
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l/
issu
e
:
3
(4
)
,
p
p
.
4
8
3
-
4
9
1
,
2
0
1
3
.
[1
9
]
P
.
N.
A
n
d
o
n
o
,
“
Ko
n
se
p
P
e
n
g
o
la
h
a
n
Cit
ra
Dig
it
a
l
,
”
Ed
.
1
.
Yo
g
y
a
k
a
rta
,
A
n
d
i,
2
0
1
5
.
[2
0
]
M
e
to
d
e
-
a
lg
o
rit
m
a
.
c
o
m
,
“
P
e
ra
taa
n
Ek
u
a
li
sa
si
Histo
g
ra
m
Cit
ra
Dig
ial
,”
h
tt
p
:/
/www
.
m
e
to
d
e
-
a
lg
o
rit
m
a
.
c
o
m
/2
0
1
5
/0
7
/m
e
to
d
e
-
p
e
n
y
e
tara
a
n
-
h
isto
g
ra
m
.
h
tm
l
[
CIted
:
S
e
p
tem
b
e
r
3
,
2
0
1
6
]
[2
1
]
U.
A
h
m
a
d
,
“
P
e
n
g
o
la
h
a
n
Cit
ra
Di
g
it
a
l
&
T
e
k
n
ik
P
e
m
ro
g
ra
m
a
n
n
y
a
,
”
e
d
.
1
,
Yo
g
y
a
k
a
rta
,
G
ra
h
a
Il
m
u
,
2
0
0
5
.
[2
2
]
T
.
Ka
n
u
n
g
o
,
e
t
a
l.
,
“
A
n
Eff
icie
n
t
k
-
M
e
a
n
s
Clu
ste
rin
g
A
lg
o
rit
h
m
:
A
n
a
l
y
sis
a
n
d
Im
p
le
m
e
n
tatio
n
,
”
IEE
E
T
ra
n
sa
c
ti
o
n
s O
n
P
a
tt
e
rn
An
a
lys
is
An
d
M
a
c
h
i
n
e
In
telli
g
e
n
c
e
,
v
o
l/
is
su
e
:
24
(
7
)
,
p
p
.
8
8
1
-
8
9
2
,
2
0
0
2
.
[2
3
]
M
a
th
w
o
rk
s
,
“
I
m
a
g
e
T
h
re
sh
o
ld
in
g
.
A
n
a
l
y
z
in
g
I
m
a
g
e
s
Us
in
g
I
m
a
g
e
T
h
re
sh
o
ld
in
g
T
e
c
h
n
iq
u
e
s
,”
M
a
th
w
o
rk
s,
1
9
9
4
.
[
Cit
e
d
:
S
e
p
tem
b
e
r
3
,
2
0
1
6
]
h
tt
p
:/
/
ww
w
.
m
a
th
w
o
rk
s.co
m
/d
isc
o
v
e
r
y
/i
m
a
g
e
-
th
re
sh
o
ld
in
g
.
h
tm
l
[2
4
]
P
ra
m
a
n
a
C
.
J.,
“
I
m
p
le
m
e
n
tas
i
M
e
to
d
e
T
h
re
sh
o
ld
in
g
d
a
n
M
e
to
d
e
Re
g
io
n
p
ro
p
s
u
n
t
u
k
M
e
n
d
e
tek
si
M
a
rk
a
J
a
lan
S
e
c
a
ra
L
i
v
e
V
id
e
o
,
”
J
u
r
n
a
l
Un
ive
rs
it
a
s Dia
n
Nu
swa
n
t
o
ro
S
e
ma
ra
n
g
,
2
0
1
4
.
[2
5
]
M
a
th
w
o
rk
s,
Re
g
io
p
ro
p
s,
“
M
e
a
s
u
re
P
ro
p
e
rti
e
s
o
f
I
m
a
g
e
R
e
g
io
n
s,”
M
a
th
w
o
rk
s,
1
9
9
4
.
[
Cit
e
d
:
S
e
p
te
m
b
e
r
3
,
2
0
1
6
]
h
tt
p
:
//
ww
w
.
m
a
th
w
o
rk
s.co
m
/
h
e
l
p
/
im
a
g
e
s/r
e
f
/reg
io
n
p
ro
p
s.h
tm
l
Evaluation Warning : The document was created with Spire.PDF for Python.