I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
,
p
p
.
852
~
860
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
1
.
p
p
8
5
2
-
8
6
0
852
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Efficien
t
Y
O
L
O
-
ba
sed mo
dels for
real
-
time
cer
a
mic
crack
detec
tion
B
encha
la
k
M
a
un
g
m
ee
s
ri
1
,
S
a
s
it
ho
rn
K
ho
ntho
n
2
,
Dec
hrit
M
a
neet
ha
m
3
,
P
a
dm
a
Ny
o
ma
n Cr
is
na
pa
t
i
3
1
D
e
p
a
r
t
me
n
t
o
f
E
n
g
i
n
e
e
r
i
n
g
M
a
n
a
g
e
men
t
,
S
u
a
n
S
u
n
a
n
d
h
a
R
a
j
a
b
h
a
t
U
n
i
v
e
r
si
t
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
2
D
e
p
a
r
t
me
n
t
o
f
I
n
d
u
s
t
r
i
a
l
P
r
o
d
u
c
t
D
e
si
g
n
,
P
h
r
a
n
a
k
h
o
n
R
a
j
a
b
h
a
t
U
n
i
v
e
r
si
t
y
,
B
a
n
g
k
o
k
,
T
h
a
i
l
a
n
d
3
D
e
p
a
r
t
me
n
t
o
f
M
e
c
h
a
t
r
o
n
i
c
s E
n
g
i
n
e
e
r
i
n
g
,
R
a
j
a
m
a
n
g
a
l
a
U
n
i
v
e
r
si
t
y
o
f
Te
c
h
n
o
l
o
g
y
T
h
a
n
y
a
b
u
r
i
,
K
h
l
o
n
g
L
u
a
n
g
,
T
h
a
i
l
a
n
d
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ap
r
1
1
,
2
0
2
5
R
ev
is
ed
Dec
2
9
,
2
0
2
5
Acc
ep
ted
J
an
2
2
,
2
0
2
6
Th
e
fo
ll
o
win
g
re
se
a
rc
h
wo
rk
s
y
ste
m
a
ti
c
a
ll
y
c
o
m
p
a
re
s
fo
u
r
v
a
rian
ts
o
f
y
o
u
o
n
l
y
l
o
o
k
o
n
c
e
(
YO
LO
)
,
n
a
m
e
ly
,
YO
LO
v
8
,
YO
LOv
9
,
YO
LO
v
1
0
,
a
n
d
YO
LOv
1
1
p
ro
p
o
se
d
re
c
e
n
tl
y
,
c
o
n
sid
e
ri
n
g
th
e
k
e
y
p
r
o
p
e
rti
e
s
r
e
q
u
ired
t
o
p
e
rfo
rm
c
e
ra
m
ic
su
rfa
c
e
c
ra
c
k
d
e
tec
ti
o
n
tas
k
s
wit
h
h
i
g
h
c
o
m
p
u
tatio
n
a
l
e
fficie
n
c
y
,
re
a
l
-
ti
m
e
in
fe
re
n
c
e
s
p
e
e
d
,
a
n
d
l
o
w
m
e
m
o
ry
u
sa
g
e
.
A
t
o
tal
o
f
3
0
0
ima
g
e
s
o
f
c
e
ra
m
ic
su
rfa
c
e
s
we
re
c
o
ll
e
c
ted
wit
h
m
a
n
u
a
ll
y
lab
e
led
c
ra
c
k
s
a
n
d
d
iv
i
d
e
d
in
t
o
trai
n
in
g
,
v
a
li
d
a
ti
o
n
,
a
n
d
tes
ti
n
g
se
ts
i
n
p
o
rt
io
n
s
o
f
2
6
3
,
2
2
,
a
n
d
1
5
ima
g
e
s,
re
sp
e
c
ti
v
e
l
y
.
Eac
h
o
f
th
e
f
o
u
r
YO
LO
v
a
rian
ts
wa
s
trai
n
e
d
f
o
r
5
0
a
n
d
1
0
0
e
p
o
c
h
s,
a
n
d
e
a
c
h
wa
s
e
v
a
lu
a
ted
re
g
a
rd
i
n
g
m
e
a
n
a
v
e
ra
g
e
p
re
c
isio
n
(m
AP)
,
in
fe
re
n
c
e
ti
m
e
,
m
o
d
e
l
si
z
e
,
a
n
d
c
o
m
p
u
tatio
n
a
l
c
o
m
p
lex
it
y
in
g
i
g
a
flo
a
ti
n
g
p
o
i
n
t
o
p
e
ra
ti
o
n
s
p
e
r
se
c
o
n
d
(
G
F
LOP
s
)
.
YO
LOv
9
p
ro
d
u
c
e
d
t
h
e
h
ig
h
e
st
a
c
c
u
ra
c
y
with
m
AP
v
a
lu
e
s
a
s
h
ig
h
a
s
0
.
7
5
2
-
0
.
7
9
b
u
t
th
e
h
i
g
h
e
st
c
o
st
in
term
s
o
f
in
c
re
a
se
d
c
o
m
p
u
tat
io
n
a
l
c
o
m
p
lex
it
y
.
Ho
we
v
e
r,
a
m
o
n
g
t
h
e
se
m
e
th
o
d
s,
YO
LOv
8
c
a
n
p
ro
d
u
c
e
th
e
fa
ste
st
in
fe
re
n
c
e
(~
2
-
2
.
3
m
s)
with
a
sm
a
ll
m
e
m
o
ry
fo
o
tp
ri
n
t
(~
6
M
B)
with
a
n
a
c
c
e
p
tab
le
a
c
c
u
ra
c
y
o
f
~
0
.
6
5
-
0
.
6
7
.
Th
e
re
su
lt
s
s
h
o
we
d
th
a
t
YO
LOv
8
is
t
h
e
m
o
st
fe
a
sib
le
t
o
d
e
p
lo
y
i
n
re
so
u
rc
e
-
c
o
n
stra
in
e
d
i
n
d
u
strial
a
u
t
o
m
a
ti
o
n
e
n
v
ir
o
n
m
e
n
ts.
B
y
o
ffe
r
in
g
t
h
is
c
o
m
p
a
ra
ti
v
e
stu
d
y
,
th
e
re
se
a
rc
h
a
tt
e
m
p
ts
to
p
ro
v
i
d
e
h
i
n
ts
fo
r
th
e
se
lec
ti
o
n
o
f
a
p
p
ro
p
riate
YO
LO
-
b
a
se
d
m
o
d
e
ls
b
y
p
ra
c
ti
ti
o
n
e
rs
in
q
u
a
li
t
y
c
o
n
tro
l
a
p
p
li
c
a
ti
o
n
s rela
ted
t
o
c
e
ra
m
ic m
a
n
u
fa
c
tu
rin
g
.
K
ey
w
o
r
d
s
:
C
er
am
ic
cr
ac
k
d
etec
tio
n
L
o
w
-
m
em
o
r
y
d
e
v
ices
Ob
ject
d
etec
tio
n
R
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
Yo
u
o
n
ly
lo
o
k
o
n
ce
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Sas
ith
o
r
n
Kh
o
n
th
o
n
Dep
ar
tm
en
t o
f
I
n
d
u
s
tr
ial
Pro
d
u
ct
Desig
n
,
Ph
r
an
ak
h
o
n
R
ajab
h
at
Un
iv
er
s
ity
9
C
h
ae
n
g
W
atth
an
a
R
d
,
An
u
s
awa
r
i,
B
an
g
Kh
en
,
B
an
g
k
o
k
1
0
2
2
0
,
T
h
ailan
d
E
m
ail:
s
asit
h
o
r
n
@
p
n
r
u
.
ac
.
th
1.
I
NT
RO
D
UCT
I
O
N
C
er
am
ic
m
ater
ials
ar
e
w
id
ely
u
tili
ze
d
,
in
clu
d
in
g
ap
p
licatio
n
s
in
v
o
lv
in
g
elec
tr
o
n
ics
to
ae
r
o
s
p
ac
e,
o
win
g
to
th
eir
r
esis
tan
ce
to
h
ig
h
tem
p
er
atu
r
es,
s
tab
ilit
y
,
an
d
s
tr
en
g
th
[
1
]
.
Desp
ite
th
e
m
en
tio
n
e
d
m
er
its
,
ce
r
am
ic
m
ater
ials
ten
d
to
ex
p
er
ien
ce
m
icr
o
-
cr
ac
k
in
g
th
at
ca
u
s
es
ca
tast
r
o
p
h
ic
f
ailu
r
e
[
2
]
.
I
t
is
ess
en
tial
to
d
etec
t
th
e
m
icr
o
-
cr
ac
k
s
im
m
ed
iately
to
en
s
u
r
e
th
at
th
e
p
r
o
d
u
cts
ar
e
s
af
e
an
d
f
u
n
ctio
n
ef
f
ec
tiv
ely
[
3
]
.
A
co
n
v
en
tio
n
al
tech
n
iq
u
e
to
i
n
s
p
ec
t
m
icr
o
-
cr
ac
k
i
n
g
m
ig
h
t
ty
p
ically
in
v
o
lv
e
h
u
m
a
n
o
b
s
er
v
atio
n
an
d
th
e
u
s
e
o
f
c
o
n
v
e
n
tio
n
al
im
a
g
e
p
r
o
ce
s
s
in
g
,
wh
ich
te
n
d
s
to
b
e
ti
m
e
-
co
n
s
u
m
in
g
a
n
d
r
eq
u
ir
es
p
r
ec
is
e
illu
m
in
atio
n
co
n
d
itio
n
s
[
4
]
.
Ho
wev
er
,
th
e
em
er
g
en
ce
o
f
d
ee
p
lear
n
in
g
m
eth
o
d
s
h
as
b
r
o
u
g
h
t
a
r
ev
o
lu
tio
n
ar
y
ap
p
r
o
ac
h
to
au
to
m
ated
d
ef
ec
t d
etec
tio
n
,
an
d
co
n
v
o
lu
tio
n
al
n
e
u
r
al
n
etwo
r
k
s
(
C
NNs
)
h
av
e
p
r
o
v
ed
r
em
a
r
k
ab
ly
s
u
cc
ess
f
u
l in
im
ag
e
class
if
icatio
n
an
d
o
b
ject
d
etec
tio
n
p
r
o
b
lem
s
[
5
]
–
[
7
]
.
On
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
tech
n
iq
u
es
in
th
e
d
o
m
ai
n
o
f
o
b
ject
d
etec
tio
n
is
th
e
y
o
u
o
n
ly
lo
o
k
o
n
ce
(
YOL
O)
f
am
ily
o
f
alg
o
r
ith
m
s
[
8
]
.
YOL
O
is
a
s
in
g
le
-
en
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
fficien
t YOLO
-
b
a
s
ed
mo
d
els fo
r
r
ea
l
-
time
ce
r
a
mic
cra
ck
d
etec
tio
n
(
B
en
ch
a
la
k
Ma
u
n
g
mee
s
r
i
)
853
n
etwo
r
k
u
s
ed
f
o
r
b
o
t
h
th
e
cla
s
s
if
icatio
n
an
d
lo
ca
lizatio
n
o
f
o
b
jects;
its
s
u
b
s
eq
u
en
t
v
er
s
i
o
n
s
h
av
e
a
d
ap
ted
a
co
m
p
r
o
m
is
e
b
etwe
en
th
e
ac
c
u
r
ac
y
o
f
d
ef
ec
t
d
etec
tio
n
an
d
r
ea
l
-
tim
e
p
r
o
ce
s
s
in
g
,
m
ak
i
n
g
it
an
id
ea
l
a
p
p
r
o
ac
h
f
o
r
au
t
o
m
atio
n
in
th
e
in
d
u
s
tr
y
[
9
]
,
[
1
0
]
.
R
ec
en
tly
,
im
p
r
o
v
e
m
en
ts
in
th
e
YOL
O
m
eth
o
d
,
r
a
n
g
in
g
f
r
o
m
YOL
Ov
8
to
YOL
Ov
1
1
,
h
av
e
led
to
h
ig
h
ly
o
p
tim
ized
d
esig
n
s
th
at
d
eliv
er
h
ig
h
v
alu
es
f
o
r
th
e
a
v
er
ag
e
p
r
ec
is
io
n
m
etr
ic
[
1
1
]
–
[
1
4
]
.
Ho
wev
er
,
th
ese
d
esig
n
s
ca
n
b
e
c
o
m
p
u
tatio
n
-
i
n
ten
s
iv
e,
wh
ich
ca
n
p
o
s
e
ch
al
len
g
es
f
o
r
th
eir
u
s
e
o
n
r
eso
u
r
ce
-
lim
ited
p
latf
o
r
m
s
lik
e
th
o
s
e
o
n
an
in
d
u
s
tr
y
f
lo
o
r
[
1
5
]
.
I
n
an
in
d
u
s
tr
ial
in
s
p
ec
tio
n
s
y
s
tem
,
ap
ar
t
f
r
o
m
th
e
a
cc
u
r
ac
y
lev
el,
lo
w
laten
cy
r
ates a
n
d
m
e
m
o
r
y
u
s
a
g
e
ar
e
im
p
o
r
tan
t f
o
r
th
e
s
y
s
te
m
to
f
u
n
ctio
n
in
a
n
o
n
lin
e
p
r
o
ce
s
s
[
1
6
]
,
[
1
7
]
.
T
h
er
e
h
as
b
ee
n
an
in
c
r
ea
s
in
g
am
o
u
n
t
o
f
s
tu
d
ies
co
n
ce
n
tr
at
in
g
o
n
t
h
e
ap
p
licatio
n
o
f
d
ee
p
lear
n
in
g
tech
n
iq
u
es
f
o
r
th
e
d
etec
tio
n
o
f
ce
r
am
ic
d
ef
ec
ts
.
Fo
r
in
s
tan
ce
,
Yu
et
a
l.
[
1
8
]
p
r
esen
ted
an
ad
v
an
ce
d
YOL
Ov
5
s
y
s
tem
f
o
r
au
to
m
atic
s
u
r
f
ac
e
d
ef
ec
t
d
etec
tio
n
in
ce
r
am
i
c
tiles
th
r
o
u
g
h
th
e
o
p
tim
iza
tio
n
o
f
th
e
m
o
d
el
co
m
p
o
n
en
ts
an
d
th
e
ap
p
licatio
n
o
f
th
e
atten
tio
n
m
ec
h
an
is
m
,
lead
in
g
to
h
i
g
h
er
d
etec
tio
n
ac
cu
r
ac
y
an
d
f
aster
co
m
p
u
tin
g
s
p
ee
d
.
An
o
t
h
er
ex
am
p
le
,
Alex
an
d
r
u
et
a
l.
[
1
9
]
p
r
esen
ted
an
in
n
o
v
ativ
e
m
et
h
o
d
f
o
r
t
h
e
d
etec
tio
n
o
f
ce
r
am
ic
p
late
d
ef
ec
ts
u
tili
zin
g
YOL
O
-
R
,
d
ea
lin
g
with
th
e
d
if
f
icu
lties
in
th
e
p
r
esen
ce
o
f
d
if
f
er
en
t
ty
p
es
o
f
ce
r
am
ic
d
ef
ec
ts
an
d
o
b
tain
in
g
co
m
p
etitiv
e
d
etec
tio
n
s
p
ee
d
.
R
elativ
ely
m
o
r
e
r
ec
en
tly
,
th
er
e
h
av
e
b
ee
n
s
tu
d
ies
u
tili
zin
g
th
e
m
o
r
e
ad
v
a
n
ce
d
YOL
O
m
o
d
els
f
o
r
f
u
r
th
er
im
p
r
o
v
e
d
p
e
r
f
o
r
m
an
ce
in
th
e
d
etec
tio
n
o
f
ce
r
am
ic
d
ef
ec
ts
.
Fo
r
ex
am
p
le,
Z
h
u
a
n
d
So
n
g
[
2
0
]
p
r
esen
ted
an
ad
v
an
ce
d
YOL
Ov
8
m
o
d
el
s
p
ec
if
ically
f
o
r
th
e
d
etec
tio
n
o
f
s
m
all
ce
r
am
ic
s
u
r
f
ac
e
d
ef
ec
ts
u
tili
zin
g
s
u
p
p
le
m
en
tar
y
d
etec
tio
n
h
ea
d
s
a
n
d
a
s
elec
tiv
e
atten
tio
n
m
o
d
u
le.
At
th
e
s
am
e
tim
e,
Hu
an
g
et
a
l.
[
2
1
]
u
tili
ze
d
d
ee
p
le
ar
n
in
g
tech
n
iq
u
es
f
o
r
t
h
e
estab
lis
h
m
en
t
o
f
d
ef
ec
t
d
etec
tio
n
s
y
s
tem
s
f
o
r
ce
r
a
m
ic
s
u
b
s
tr
ates
b
ased
o
n
YOL
Ov
3
m
o
d
els
an
d
o
b
tain
ed
co
n
s
id
er
ab
le
im
p
r
o
v
em
e
n
ts
in
b
o
th
d
etec
tio
n
ac
cu
r
ac
y
a
n
d
co
m
p
u
tin
g
s
p
ee
d
.
Oth
er
r
esear
ch
ef
f
o
r
ts
h
av
e
b
ee
n
d
ev
o
te
d
to
f
u
r
th
er
c
r
af
ti
n
g
th
e
d
etec
tio
n
o
f
d
ef
ec
ts
in
ce
r
am
ics
u
s
in
g
m
o
b
ile
-
f
r
ien
d
ly
v
is
io
n
t
r
an
s
f
o
r
m
er
s
,
s
u
p
er
io
r
f
ea
t
u
r
e
f
u
s
io
n
m
o
d
els,
a
n
d
c
u
s
to
m
lo
s
s
f
u
n
ctio
n
s
.
T
h
ese
in
clu
d
e,
f
o
r
ex
am
p
le,
MCAW
-
YOL
O
[
2
2
]
wh
ich
in
teg
r
ated
a
v
is
io
n
tr
an
s
f
o
r
m
er
in
to
its
b
ac
k
b
o
n
e
ar
ch
itectu
r
e
f
o
r
g
lo
b
al
an
d
lo
c
al
co
n
tex
t
u
n
d
er
s
tan
d
in
g
,
a
n
d
an
o
th
er
[
2
3
]
t
h
at
f
u
r
th
er
b
o
o
s
ted
th
e
p
er
f
o
r
m
a
n
ce
o
f
YOL
Ov
5
s
v
ia
an
ch
o
r
s
tr
u
ctu
r
e
o
p
tim
izatio
n
an
d
th
e
ap
p
licatio
n
o
f
t
h
e
atten
tio
n
m
ec
h
an
is
m
.
Oth
er
r
esear
ch
ef
f
o
r
ts
in
[
2
4
]
,
[
2
5
]
h
av
e
b
ee
n
d
ir
ec
ted
at
c
r
af
tin
g
d
en
s
e
d
etec
tio
n
alg
o
r
ith
m
s
an
d
u
n
iq
u
e
co
n
v
o
l
u
tio
n
al
m
o
d
els
f
o
r
tack
lin
g
m
u
lti
-
s
ca
le
an
d
s
m
all
-
tar
g
et
d
ef
ec
t
d
etec
tio
n
.
T
h
e
b
o
d
y
o
f
r
esear
ch
wo
r
k
alr
ea
d
y
p
r
esen
ted
h
as
p
r
im
a
r
ily
tar
g
eted
th
e
im
p
r
o
v
em
e
n
t
o
f
th
e
d
etec
tio
n
p
er
f
o
r
m
a
n
ce
u
s
in
g
s
u
p
er
io
r
ar
ch
itectu
r
al
r
ef
in
em
en
t,
in
c
lu
d
in
g
im
p
r
o
v
ed
f
ea
t
u
r
e
f
u
s
io
n
,
atten
tio
n
m
ec
h
an
is
m
s
,
an
d
co
m
p
lex
lo
s
s
f
u
n
ctio
n
s
.
W
h
ile
th
ese
h
av
e
a
lr
ea
d
y
d
em
o
n
s
tr
ated
s
u
cc
ess
in
d
ef
ec
t
d
etec
tio
n
,
th
er
e
r
em
a
in
ch
allen
g
es
with
m
o
d
els
ch
ar
a
cter
ized
b
y
h
ig
h
er
co
m
p
u
tin
g
co
m
p
lex
ity
,
lar
g
er
m
o
d
els,
a
n
d
lo
n
g
e
r
in
f
er
en
ce
tim
es,
wh
ic
h
r
em
ain
a
co
n
ce
r
n
f
o
r
i
n
d
u
s
tr
y
im
p
lem
en
tatio
n
.
T
h
e
o
r
ig
in
ality
o
f
t
h
is
cu
r
r
e
n
t
r
esear
ch
wo
r
k
is
in
ca
r
r
y
in
g
o
u
t
a
co
m
p
a
r
ativ
e
an
aly
s
is
o
f
th
e
p
er
f
o
r
m
an
ce
o
f
f
o
u
r
YOL
O
m
o
d
els:
YOL
Ov
8
,
YOL
Ov
9
,
YOL
Ov
1
0
,
a
n
d
YOL
Ov
1
1
f
o
r
th
e
d
etec
tio
n
o
f
ce
r
am
ic
cr
ac
k
s
p
er
f
o
r
m
e
d
i
n
a
cu
s
to
m
ized
d
ataset
o
f
th
e
c
er
am
ic
m
ater
ial.
T
h
e
r
esear
c
h
wo
r
k
f
o
cu
s
es
o
n
ad
d
r
ess
in
g
th
e
lo
w
m
em
o
r
y
a
n
d
r
ea
l
-
tim
e
is
s
u
es
co
u
p
led
in
th
e
ce
r
am
ic
m
an
u
f
ac
tu
r
in
g
p
r
o
ce
s
s
b
y
tak
in
g
in
t
o
co
n
s
id
er
atio
n
th
e
tr
ad
e
-
o
f
f
s
b
etwe
en
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
m
o
d
els
in
ter
m
s
o
f
p
r
e
cisi
o
n
,
r
ec
all,
m
ea
n
av
er
ag
e
p
r
ec
is
io
n
(
m
AP)
-
5
0
,
m
AP5
0
–
9
5
,
an
d
th
ei
r
ab
ilit
y
to
wo
r
k
with
in
th
e
c
o
m
p
u
tatio
n
al
co
s
ts
o
f
b
o
th
ex
ec
u
tio
n
tim
e
m
ea
s
u
r
ed
in
m
icr
o
s
ec
o
n
d
s
,
s
ize
o
f
th
e
m
o
d
el
in
m
eg
ab
y
tes,
an
d
g
ig
a
f
lo
ati
n
g
p
o
in
t
o
p
e
r
atio
n
s
p
er
s
ec
o
n
d
(
GFLO
Ps
)
.
I
n
th
is
r
esear
ch
,
b
o
th
5
0
an
d
1
0
0
ep
o
ch
m
o
d
els
ar
e
u
s
ed
f
o
r
an
aly
s
is
o
f
p
e
r
f
o
r
m
an
ce
.
T
h
e
two
m
o
d
els
ar
e
u
s
ed
f
o
r
an
aly
s
is
o
f
p
er
f
o
r
m
an
ce
to
d
e
ter
m
in
e
th
e
ef
f
e
cts
o
f
ad
d
itio
n
al
tr
ain
in
g
in
ter
m
s
o
f
p
er
f
o
r
m
an
ce
an
d
u
tili
za
tio
n
o
f
c
o
m
p
u
tatio
n
al
r
eso
u
r
c
es.
T
h
e
a
n
aly
s
is
o
f
th
is
r
es
ea
r
ch
p
r
o
v
i
d
es
a
s
ig
n
if
ican
t
m
iles
to
n
e
in
d
eter
m
in
in
g
th
e
YOL
O
m
o
d
el
th
at
s
h
o
u
ld
b
e
u
s
ed
in
in
d
u
s
tr
ial
au
to
m
atio
n
s
y
s
tem
s
f
o
r
th
eir
ac
cu
r
ac
y
an
d
f
ea
s
ib
il
ity
in
r
ea
l
-
tim
e
a
u
to
m
atio
n
s
y
s
tem
s
.
T
h
e
r
esear
ch
wo
r
k
h
as
co
n
tr
ib
u
ted
to
b
o
th
th
e
ac
cu
r
ac
y
a
n
d
c
o
m
p
u
tatio
n
al
co
s
t a
r
ea
s
in
d
etec
tin
g
d
e
f
ec
tiv
e
ce
r
am
ic
p
r
o
d
u
cts.
2.
M
E
T
H
O
D
T
h
e
to
tal
ex
p
er
im
en
t
p
r
o
ce
d
u
r
e
f
o
r
th
e
d
etec
tio
n
o
f
ce
r
am
ic
b
r
ea
k
ag
e
is
s
h
o
wn
in
Fig
u
r
e
1
.
A
d
ataset
o
f
3
0
0
im
ag
es
is
ass
em
b
led
an
d
s
p
lit
in
to
s
ets
f
o
r
tr
ain
in
g
,
v
alid
atio
n
,
an
d
test
in
g
.
I
m
ag
e
p
r
ep
r
o
ce
s
s
in
g
task
s
lik
e
ca
ch
in
g
an
d
s
ca
lin
g
a
r
e
u
s
ed
f
o
r
im
ag
e
p
r
ep
a
r
atio
n
s
b
ef
o
r
e
tr
ain
i
n
g
.
T
h
e
n
,
th
e
m
o
d
el
tr
ain
s
f
o
r
5
0
o
r
1
0
0
ep
o
ch
s
o
n
all
f
o
u
r
v
er
s
io
n
s
o
f
th
e
YOL
O
m
o
d
el
(
YOL
O
-
v
8
,
YOL
O
-
v
9
,
YOL
O
-
v
1
0
,
an
d
YOL
O
-
v
1
1
)
.
Dete
ctio
n
p
er
f
o
r
m
an
ce
an
d
r
eso
u
r
ce
-
r
elate
d
cr
iter
ia
ar
e
in
v
esti
g
ated
o
n
co
m
p
u
tatio
n
ally
in
ten
s
iv
e
p
ar
am
eter
s
lik
e
in
f
er
en
ce
tim
in
g
s
,
m
o
d
el
s
ize,
an
d
GFLO
Ps
alo
n
g
with
cr
u
cial
d
e
tectio
n
p
ar
am
eter
s
lik
e
p
r
ec
is
io
n
,
r
ec
all,
m
AP5
0
,
m
AP5
0
-
9
5
,
an
d
f
itn
ess
s
co
r
es.
2
.
1
.
Da
t
a
c
o
llect
io
n a
nd
prepro
ce
s
s
ing
I
n
to
tal,
3
0
0
im
ag
es
wer
e
co
l
lecte
d
f
r
o
m
ce
r
a
m
ic
p
ar
ts
with
d
if
f
er
e
n
t
cr
ac
k
s
ev
er
ities
.
E
ac
h
im
ag
e
was m
an
u
ally
lab
eled
with
b
o
u
n
d
in
g
b
o
x
es f
o
r
all
th
e
v
is
ib
le
cr
ac
k
s
.
T
h
e
d
ataset
was d
iv
i
d
ed
r
an
d
o
m
ly
in
to
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J
Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
852
-
8
6
0
854
tr
ain
in
g
s
et
co
n
s
is
tin
g
o
f
2
6
3
im
ag
es,
a
v
alid
atio
n
s
et
o
f
2
2
im
ag
es,
an
d
a
f
in
al
test
s
et
o
f
1
5
im
ag
es.
All
im
ag
es
wer
e
r
esized
to
6
4
0
×6
4
0
p
ix
els
to
u
n
if
y
in
p
u
t
d
im
en
s
io
n
s
.
Fo
r
tr
ai
n
in
g
,
d
ata
au
g
m
e
n
tatio
n
was
ca
r
r
ied
o
u
t
t
o
in
cr
ea
s
e
m
o
d
el
r
o
b
u
s
tn
ess
an
d
to
a
v
o
id
o
v
er
f
itti
n
g
.
E
m
p
lo
y
i
n
g
au
g
m
en
tati
o
n
tech
n
iq
u
es
s
u
ch
as
b
lu
r
an
d
m
e
d
ian
b
l
u
r
s
im
u
lates
m
in
o
r
d
is
to
r
tio
n
s
in
im
a
g
es.
Gr
ay
s
ca
le
co
n
v
er
s
io
n
e
n
f
o
r
ce
s
th
e
m
o
d
el
to
r
ely
o
n
lu
m
i
n
an
ce
r
ath
e
r
th
an
co
lo
r
alo
n
e.
C
o
n
t
r
ast
lim
ited
ad
ap
tiv
e
h
is
to
g
r
am
e
q
u
aliza
tio
n
(
C
L
AHE
)
is
u
s
ed
to
h
ig
h
lig
h
t su
b
tle
cr
ac
k
s
in
lo
w
-
co
n
tr
ast r
eg
io
n
s
.
Fig
u
r
e
1
.
R
esear
ch
o
v
er
v
iew
2
.
2
.
YO
L
O
m
o
del v
a
ria
nts
Fo
u
r
v
ar
iatio
n
s
o
f
YOL
O
wer
e
test
ed
in
th
is
p
ap
er
:
YOL
Ov
8
,
YOL
Ov
9
,
YOL
Ov
1
0
,
YOL
Ov
1
1
.
I
n
YOL
O,
th
er
e
ar
e
th
r
ee
o
v
er
ar
ch
in
g
task
s
in
th
e
d
etec
tio
n
s
tep
:
b
o
u
n
d
i
n
g
b
o
x
r
e
g
r
ess
io
n
,
o
b
jectn
ess
(
co
n
f
id
e
n
ce
)
p
r
e
d
ictio
n
,
c
lass
p
r
ed
ictio
n
.
Fo
r
th
e
p
r
ed
ictio
n
(
̂
,
̂
,
̂
,
̂
obj
,
̂
cls
)
g
iv
en
th
e
co
r
r
esp
o
n
d
in
g
g
r
o
u
n
d
tr
u
t
h
v
alu
es (
x
,
y
,
w,
h
,
p
o
b
j,
p
cls),
YOL
O
lo
s
s
ℒ
u
s
u
ally
co
m
p
u
tes as sh
o
wn
in
(
1
)
[
2
6
]
.
ℒ
=
λ
×
ℒ
+
λ
×
ℒ
+
λ
×
ℒ
(
1
)
W
h
er
e
ℒ
is
th
e
b
o
u
n
d
in
g
b
o
x
r
eg
r
ess
io
n
lo
s
s
,
o
f
ten
ca
lcu
late
d
as
a
c
o
m
b
in
atio
n
o
f
m
ea
n
s
q
u
ar
ed
er
r
o
r
o
r
g
en
er
alize
d
in
ter
s
ec
tio
n
o
v
e
r
u
n
io
n
(
GI
o
U
)
/
co
m
p
lete
in
ter
s
ec
tio
n
o
v
er
u
n
i
o
n
(
C
I
o
U
)
-
b
as
ed
ter
m
s
;
ℒ
is
th
e
o
b
jectn
ess
(
co
n
f
id
en
ce
)
lo
s
s
,
p
en
alizin
g
i
n
co
r
r
ec
t
p
r
ed
ictio
n
s
o
f
b
ac
k
g
r
o
u
n
d
as
o
b
jects
a
n
d
v
ice
v
e
r
s
a;
ℒ
is
th
e
class
if
icatio
n
lo
s
s
,
h
er
e
m
in
im
ized
o
v
er
a
s
in
g
le
class
“d
am
ag
e”
in
t
h
e
ca
s
e
o
f
c
r
ac
k
d
etec
tio
n
;
a
n
d
λ
,
λ
,
λ
ar
e
h
y
p
e
r
p
ar
am
eter
s
th
at
b
alan
ce
th
e
r
elativ
e
im
p
o
r
tan
ce
o
f
ea
ch
c
o
m
p
o
n
en
t.
2
.
3
.
T
ra
ini
ng
a
nd
t
esting
co
nfig
ura
t
io
n
A
l
l
t
h
e
m
o
d
e
l
s
w
e
r
e
t
r
a
in
e
d
w
i
t
h
P
y
th
o
n
3
.
1
1
.
1
1
an
d
P
y
T
o
r
ch
2
.
5
.
1
,
a
s
s
i
s
t
e
d
b
y
an
N
VI
D
I
A
T
e
s
l
a
T
4
G
P
U
(
1
5
G
B
V
R
A
M
)
.
T
h
e
b
a
t
c
h
s
i
ze
w
a
s
f
i
x
ed
t
o
1
6
,
a
n
d
th
e
m
o
d
e
l
w
a
s
tr
a
i
n
ed
f
o
r
5
0
o
r
1
0
0
e
p
o
c
h
s
t
o
d
e
t
e
r
m
i
n
e
t
h
e
r
e
s
u
l
t
s
a
f
ter
i
n
te
n
s
e
tr
a
i
n
in
g
.
T
h
e
o
p
t
im
i
z
e
r
u
s
e
d
w
a
s
th
e
Ad
a
m
W
o
p
t
i
m
i
ze
r
,
i
n
i
t
ia
l
l
e
a
r
n
in
g
r
a
t
e
a
d
ju
s
t
e
d
au
t
o
m
at
i
c
a
l
l
y
.
Pr
e
c
i
s
i
o
n
an
d
r
e
c
a
l
l
as
i
n
(
2
)
an
d
(
3
)
,
m
A
P
a
s
i
n
(
4
)
,
i
n
te
r
s
e
c
t
io
n
o
v
er
u
n
i
o
n
(
I
o
U
)
a
s
i
n
(
5
)
,
in
f
er
e
n
c
e
t
im
e
,
m
o
d
e
l
s
i
z
e
(
i
n
M
B
)
,
an
d
G
FL
O
P
s
w
e
r
e
t
h
e
m
e
tr
i
c
s
u
s
ed
f
o
r
e
v
a
l
u
a
t
i
o
n
[
2
7
]
.
=
+
′
(
2
)
=
+
(
3
)
=
1
∑
=
1
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
fficien
t YOLO
-
b
a
s
ed
mo
d
els fo
r
r
ea
l
-
time
ce
r
a
mic
cra
ck
d
etec
tio
n
(
B
en
ch
a
la
k
Ma
u
n
g
mee
s
r
i
)
855
=
(
∩
)
(
∪
)
(
5
)
Af
ter
h
y
p
er
p
ar
am
eter
t
u
n
in
g
o
n
th
e
v
alid
atio
n
s
et,
ea
ch
m
o
d
el
was
test
ed
o
n
th
e
h
eld
o
u
t
s
et
o
f
1
5
im
ag
es.
T
h
is
f
in
al
ev
alu
atio
n
m
ea
s
u
r
ed
h
o
w
well
th
e
m
o
d
el
s
g
en
er
alize
d
to
u
n
s
ee
n
d
ata
.
T
h
e
r
esu
lts
r
ef
lecte
d
th
eir
r
ea
l
-
wo
r
ld
p
er
f
o
r
m
an
ce
in
ce
r
am
ic
cr
ac
k
d
etec
tio
n
task
s
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
M
o
del
perf
o
rma
nce
o
v
e
rv
iew
T
ab
les
1
an
d
2
p
r
esen
ts
a
h
i
g
h
-
lev
el
s
u
m
m
ar
y
o
f
th
e
r
esu
lts
f
o
r
ea
ch
YOL
O
v
ar
ian
t
at
5
0
an
d
1
0
0
ep
o
ch
s
,
f
o
c
u
s
in
g
o
n
m
AP@
0
.
5
,
m
AP@
0
.
5
–
0
.
9
5
,
i
n
f
er
en
ce
tim
e,
a
n
d
m
o
d
el
s
ize.
YOL
Ov
9
an
d
YOL
Ov
1
1
co
n
s
is
ten
tly
ac
h
iev
in
g
h
ig
h
e
r
m
AP
(
u
p
to
0
.
7
9
)
b
u
t
at
th
e
co
s
t
o
f
lar
g
er
m
o
d
el
s
izes
(
1
5
–
1
9
MB)
a
n
d
s
lo
wer
i
n
f
er
en
ce
tim
es
(
~5
–
6
m
s
)
.
YOL
Ov
8
m
ain
tain
in
g
th
e
f
astes
t
in
f
er
en
ce
s
p
ee
d
(
~2
–
2
.
3
m
s
)
a
n
d
s
m
allest
m
o
d
el
f
o
o
tp
r
in
t
(
~6
MB),
wit
h
s
lig
h
tly
lo
wer
m
AP
(
0
.
6
5
–
0
.
6
7
)
.
YOL
Ov
1
0
p
r
o
v
id
i
n
g
a
m
id
d
le
-
g
r
o
u
n
d
s
o
lu
tio
n
in
ter
m
s
o
f
ac
cu
r
a
cy
an
d
s
p
ee
d
,
b
u
t
n
o
t
s
ig
n
if
ica
n
tly
o
u
tp
e
r
f
o
r
m
in
g
YOL
Ov
8
in
r
eso
u
r
ce
ef
f
icien
c
y
.
T
ab
le
1
.
T
h
e
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
5
0
ep
o
c
h
s
M
o
d
e
l
mA
P
5
0
mA
P
5
0
-
95
I
n
f
e
r
e
n
c
e
t
i
me
(
ms)
G
F
LO
P
s
M
o
d
e
l
s
i
z
e
(
M
B
)
I
n
si
g
h
t
Y
O
LO
v
8
0
.
6
6
9
0
.
4
7
2
~
2
.
3
8
.
2
~
6
.
2
F
a
st
e
s
t
a
n
d
sm
a
l
l
e
s
t
;
a
c
c
e
p
t
a
b
l
e
a
c
c
u
r
a
c
y
Y
O
LO
v
9
0
.
7
5
2
0
.
5
6
4
~
6
.
0
2
6
.
7
~
1
5
.
2
H
i
g
h
e
r
a
c
c
u
r
a
c
y
b
u
t
sl
o
w
e
r
a
n
d
l
a
r
g
e
r
Y
O
LO
v
1
0
0
.
6
5
5
0
.
3
8
9
~
6
.
0
2
4
.
4
~
1
6
.
5
Lo
w
e
r
a
c
c
u
r
a
c
y
c
o
m
p
a
r
e
d
t
o
o
t
h
e
r
s
Y
O
LO
v
1
1
0
.
7
0
4
0
.
4
7
7
~
5
.
1
2
1
.
3
~
1
9
.
2
M
o
d
e
r
a
t
e
a
c
c
u
r
a
c
y
a
n
d
s
p
e
e
d
T
ab
le
2
.
T
h
e
p
er
f
o
r
m
a
n
ce
co
m
p
ar
is
o
n
o
f
1
0
0
ep
o
ch
s
M
o
d
e
l
mA
P
5
0
mA
P
5
0
-
95
I
n
f
e
r
e
n
c
e
t
i
me
(
ms)
G
F
LO
P
s
M
o
d
e
l
s
i
z
e
(
M
B
)
C
o
mm
e
n
t
s
Y
O
LO
v
8
0
.
6
5
2
0
.
4
2
5
~
2
.
0
8
.
1
~
6
.
3
F
a
st
e
s
t
a
n
d
sm
a
l
l
e
s
t
;
sl
i
g
h
t
d
r
o
p
i
n
a
c
c
u
r
a
c
y
Y
O
LO
v
9
0
.
7
9
2
0
.
5
1
3
~
6
.
0
2
6
.
7
~
1
5
.
2
H
i
g
h
e
s
t
a
c
c
u
r
a
c
y
;
h
e
a
v
i
e
r
a
n
d
s
l
o
w
e
r
Y
O
LO
v
1
0
0
.
7
4
1
0
.
4
0
1
~
6
.
3
2
4
.
4
~
1
6
.
5
G
o
o
d
a
c
c
u
r
a
c
y
b
u
t
l
a
r
g
e
r
t
h
a
n
Y
O
LO
v
8
Y
O
LO
v
1
1
0
.
7
3
2
0
.
4
8
3
~
5
.
0
2
1
.
3
~
1
9
.
2
M
o
d
e
r
a
t
e
a
c
c
u
r
a
c
y
;
sl
o
w
e
r
t
h
a
n
Y
O
L
O
v
8
3
.
2
.
I
nfluence
o
f
t
ra
ini
ng
ep
o
chs
W
h
ile
in
cr
ea
s
in
g
ep
o
c
h
s
f
r
o
m
5
0
to
1
0
0
ty
p
ically
y
ield
s
an
im
p
r
o
v
em
e
n
t
in
m
AP,
th
e
m
a
g
n
itu
d
e
o
f
th
is
g
ain
v
ar
ies
am
o
n
g
m
o
d
els.
YOL
Ov
9
b
en
ef
its
th
e
m
o
s
t,
with
an
in
c
r
ea
s
e
o
f
a
b
o
u
t
4
–
5
p
o
in
ts
i
n
m
AP@
0
.
5
.
YOL
Ov
8
’
s
im
p
r
o
v
em
en
t
is
m
o
r
e
m
o
d
est
(
a
b
o
u
t
2
–
3
p
o
in
ts
)
.
Giv
e
n
th
e
tim
e
an
d
r
eso
u
r
ce
co
n
s
tr
ain
ts
in
in
d
u
s
tr
ial
s
ettin
g
s
,
th
e
d
ec
is
io
n
to
tr
ain
f
o
r
ad
d
itio
n
al
ep
o
ch
s
d
ep
e
n
d
s
o
n
wh
eth
er
m
ar
g
in
al
ac
cu
r
ac
y
g
ai
n
s
ju
s
tify
lo
n
g
e
r
t
r
ain
in
g
d
u
r
atio
n
s
.
T
h
e
eig
h
t
p
r
ec
is
io
n
-
r
ec
all
(
P
R
)
cu
r
v
es
in
Fig
u
r
e
2
lik
el
y
r
ep
r
esen
t
f
o
u
r
YOL
O
v
ar
ian
t
s
tr
ain
ed
at
5
0
an
d
1
0
0
ep
o
ch
:
YOL
Ov
8
a
s
in
Fig
u
r
es
2
(
a)
an
d
2
(
b
)
,
YOL
Ov
9
as
in
Fig
u
r
es
2
(
c)
an
d
2
(
d
)
,
YOL
Ov
1
0
as
in
Fig
u
r
es
2
(
e)
an
d
2
(
f
)
,
an
d
YOL
Ov
1
1
as
in
Fig
u
r
es
2
(
g
)
an
d
2
(
h
)
.
E
ac
h
cu
r
v
e
p
lo
ts
p
r
e
cisi
o
n
o
n
th
e
y
-
ax
is
ag
ain
s
t
r
ec
all
o
n
th
e
x
-
ax
is
,
illu
s
tr
atin
g
h
o
w
well
a
m
o
d
el
b
alan
ce
s
th
ese
two
m
etr
ics
ac
r
o
s
s
v
ar
y
in
g
co
n
f
id
en
ce
th
r
esh
o
ld
s
.
As
th
e
th
r
esh
o
ld
f
o
r
p
r
ed
ictin
g
a
“d
a
m
ag
e”
d
etec
tio
n
ch
a
n
g
e,
p
r
ec
i
s
io
n
an
d
r
ec
all
s
h
if
t
ac
co
r
d
in
g
l
y
lo
wer
th
r
esh
o
ld
s
ty
p
ically
b
o
o
s
t
r
ec
all
b
u
t
r
e
d
u
ce
p
r
ec
is
io
n
,
wh
ile
h
ig
h
er
th
r
esh
o
ld
s
im
p
r
o
v
e
p
r
ec
is
io
n
b
u
t
o
f
ten
lo
we
r
r
ec
al
l.
I
n
g
en
er
al,
a
m
o
r
e
“
b
o
wed
”
PR
cu
r
v
e
th
at
s
tay
s
to
war
d
th
e
to
p
-
r
ig
h
t
co
r
n
er
in
d
ic
ates
b
etter
p
er
f
o
r
m
an
ce
,
m
ea
n
in
g
th
e
m
o
d
el
m
ain
tain
s
h
ig
h
p
r
ec
is
io
n
at
h
ig
h
er
r
ec
all
lev
els.
T
h
e
l
ab
el
m
AP@
0
.
5
o
n
ea
ch
p
lo
t
r
ef
e
r
s
to
t
h
e
m
AP
at
a
0
.
5
I
o
U
t
h
r
esh
o
ld
,
wh
ich
is
a
s
in
g
le
-
v
alu
e
s
u
m
m
ar
y
r
e
f
lec
tin
g
th
e
ar
ea
u
n
d
e
r
th
e
PR
cu
r
v
e.
T
h
e
h
ig
h
er
t
h
e
m
AP@
0
.
5
,
th
e
b
etter
th
e
ab
ilit
y
to
h
an
d
le
a
wid
e
r
an
g
e
o
f
r
ec
all
lev
els,
wh
ich
m
ain
tain
s
a
h
ig
h
p
r
ec
is
io
n
wh
i
le
g
ettin
g
m
o
s
t o
f
th
e
cr
ac
k
s
.
W
h
en
co
m
p
ar
in
g
th
e
v
a
r
io
u
s
v
er
s
io
n
s
o
f
th
e
YOL
O,
th
e
PR
cu
r
v
es
o
f
th
e
YOL
Ov
9
,
o
r
th
e
YOL
Ov
1
1
,
ar
e
g
e
n
er
ally
h
ig
h
er
,
in
d
icatin
g
im
p
r
o
v
ed
d
etec
to
r
p
er
f
o
r
m
a
n
ce
.
Ho
we
v
er
,
th
e
m
em
o
r
y
r
eq
u
ir
em
e
n
ts
as
well
as
th
e
i
n
f
er
en
ce
tim
e
a
r
e
r
elativ
ely
l
ar
g
er
.
On
t
h
e
o
th
e
r
h
an
d
,
th
e
YOL
Ov
8
aim
s
f
o
r
im
p
r
o
v
e
d
s
p
ee
d
,
wh
ich
m
ig
h
t
tr
an
s
late
to
a
s
lig
h
tly
d
ec
r
ea
s
ed
m
AP
b
u
t
ca
n
s
til
l
b
e
ef
f
ec
tiv
e
in
a
r
ea
l
-
tim
e
s
ettin
g
.
As
f
o
r
t
h
e
YOL
Ov
1
0
,
it
g
en
e
r
ally
lies
in
b
etwe
en
,
p
r
o
m
is
in
g
im
p
r
o
v
em
e
n
ts
o
v
e
r
th
e
YOL
Ov
8
b
u
t
n
o
t e
n
tire
ly
o
n
th
e
le
v
el
o
f
t
h
e
YOL
Ov
9
.
T
o
co
m
p
a
r
e
5
0
v
er
s
u
s
1
0
0
ep
o
ch
s
,
lo
n
g
er
tr
ain
i
n
g
(
1
0
0
ep
o
ch
s
)
te
n
d
s
to
h
elp
s
ta
b
ilize
an
d
m
ar
g
in
ally
ad
v
an
ce
th
e
c
u
r
v
e
in
ter
m
s
o
f
p
r
ec
is
io
n
v
er
s
u
s
r
ec
all,
im
p
ly
in
g
m
o
r
e
m
o
d
el
co
n
v
er
g
en
ce
an
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J
Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
852
-
8
6
0
856
o
p
tim
izatio
n
.
Ho
wev
er
,
i
n
cr
e
m
en
tal
g
ain
s
d
if
f
er
f
o
r
d
if
f
e
r
e
n
t
v
er
s
io
n
s
o
f
th
e
YOL
O
m
o
d
el:
ce
r
tain
v
er
s
io
n
s
r
ep
o
r
t
la
r
g
e
b
en
ef
its
f
o
r
lo
n
g
er
tr
ain
in
g
tim
es,
alth
o
u
g
h
d
i
m
in
is
h
in
g
r
etu
r
n
s
also
ten
d
to
b
e
ass
o
ciate
d
with
ex
ten
d
ed
tr
ain
in
g
f
o
r
ce
r
tain
v
er
s
io
n
s
.
Gen
e
r
ally
,
wh
ic
h
m
o
d
el
to
b
e
u
s
ed
f
o
r
ce
r
am
ic
cr
ac
k
d
etec
tio
n
,
co
n
d
itio
n
al
u
p
o
n
a
p
p
licatio
n
n
ee
d
s
,
is
as
f
o
llo
ws:
f
o
r
r
ea
l
-
tim
e
n
ee
d
s
co
m
b
in
e
d
with
lim
ited
g
r
ap
h
ics
p
r
o
ce
s
s
in
g
u
n
it
(
GPU
)
r
eso
u
r
ce
s
,
th
e
r
elativ
e
wea
k
n
ess
in
p
r
ec
is
io
n
f
o
r
YOL
Ov
8
ap
p
ea
r
s
in
co
n
s
eq
u
e
n
tial.
Fo
r
ap
p
licatio
n
s
s
tr
ess
in
g
o
v
er
all
p
r
ec
is
io
n
f
o
r
task
s
r
eq
u
ir
in
g
lar
g
e
c
o
m
p
u
tatio
n
r
eso
u
r
ce
s
,
YOL
Ov
9
o
r
YOL
Ov
1
1
f
o
r
1
0
0
ep
o
ch
s
m
ig
h
t b
e
p
r
e
f
er
ab
le.
(
a)
(
b
)
(
c)
(
d
)
(
e)
(f)
(
g
)
(
h
)
Fig
u
r
e
2
.
T
h
e
PR
cu
r
v
e
co
m
p
a
r
is
o
n
f
o
r
:
(
a)
YOL
Ov
8
–
5
0
e
p
o
ch
,
(
b
)
YOL
Ov
8
–
1
0
0
e
p
o
ch
s
,
(
c)
YOL
Ov
9
–
5
0
ep
o
ch
,
(
d
)
Y
OL
Ov
9
–
1
0
0
ep
o
ch
s
,
(
e)
YOL
Ov
1
0
–
5
0
ep
o
ch
,
(
f
)
YOL
Ov
1
0
–
1
0
0
ep
o
c
h
s
,
(
g
)
YOL
Ov
1
1
–
5
0
ep
o
c
h
,
an
d
(
h
)
YOL
Ov
1
1
–
1
0
0
ep
o
ch
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
fficien
t YOLO
-
b
a
s
ed
mo
d
els fo
r
r
ea
l
-
time
ce
r
a
mic
cra
ck
d
etec
tio
n
(
B
en
ch
a
la
k
Ma
u
n
g
mee
s
r
i
)
857
Fig
u
r
e
3
s
h
o
ws
1
5
d
etec
tio
n
r
esu
lts
with
d
if
f
er
en
t
b
o
u
n
d
in
g
b
o
x
es
lab
ele
d
"d
am
a
g
e"
o
n
t
h
e
v
ar
io
u
s
s
u
r
f
ac
es
o
f
ce
r
am
ics;
ea
ch
o
f
th
ese
h
as
a
co
n
f
id
en
ce
s
co
r
e
r
an
g
in
g
a
p
p
r
o
x
im
ately
f
r
o
m
0
.
4
5
to
0
.
8
4
.
T
h
e
s
co
r
es
ar
e
a
p
r
o
b
ab
ilit
y
-
l
ik
e
m
ea
s
u
r
e
o
f
th
e
m
o
d
el'
s
co
n
f
id
en
ce
t
h
at
a
ce
r
tain
r
e
g
io
n
co
n
tain
s
a
cr
ac
k
.
I
n
g
en
er
al,
th
e
h
ig
h
e
r
t
h
e
s
co
r
e,
s
u
ch
as
0
.
8
4
o
r
0
.
7
7
,
th
e
s
tr
o
n
g
er
th
e
b
elief
in
a
ctu
al
d
am
ag
e,
wh
ile
a
lo
we
r
s
co
r
e,
s
u
ch
as
0
.
4
5
o
r
0
.
5
2
,
i
n
d
icate
s
m
o
r
e
u
n
ce
r
tain
ty
.
On
s
o
m
e
im
ag
es,
th
e
m
o
d
el
m
ig
h
t
p
r
o
d
u
ce
m
u
ltip
le
b
o
u
n
d
in
g
b
o
x
es
if
it
d
etec
ts
s
ev
er
al
r
eg
io
n
s
wh
ich
ar
e
d
is
tin
ct
f
r
o
m
a
c
r
ac
k
o
r
wh
en
s
u
b
t
le
v
is
u
al
cu
es
ca
u
s
e
a
s
in
g
le
cr
ac
k
to
b
e
s
eg
m
en
ted
in
to
p
ar
ts
.
Fig
u
r
e
3
.
YOL
Ov
8
ce
r
am
ic
cr
ac
k
d
etec
tio
n
r
esu
lts
T
h
e
b
o
u
n
d
i
n
g
b
o
x
f
i
t
s
w
e
l
l
w
i
t
h
v
i
s
i
b
l
y
c
l
e
a
r
c
r
a
c
k
s
a
t
r
e
l
a
t
i
v
e
l
y
h
i
g
h
c
o
n
f
i
d
e
n
c
e
s
a
b
o
v
e
0
.
7
0
,
r
e
f
l
e
c
t
i
n
g
t
h
e
a
b
i
l
i
t
y
o
f
t
h
e
m
o
d
e
l
t
o
i
d
e
n
t
i
f
y
w
e
l
l
-
d
e
f
i
n
e
d
c
r
a
c
k
f
e
a
t
u
r
e
s
.
C
o
n
v
e
r
s
e
l
y
,
f
o
r
m
a
n
y
c
a
s
e
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J
Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
852
-
8
6
0
858
w
i
t
h
a
m
o
d
e
r
a
t
e
o
r
l
o
w
e
r
c
o
n
f
i
d
e
n
c
e
s
c
o
r
e
,
t
h
e
c
r
a
c
k
i
s
q
u
i
t
e
l
i
g
h
t
,
t
h
i
n
,
o
r
p
a
r
t
i
a
l
l
y
o
b
s
c
u
r
e
d
b
y
l
i
g
h
t
i
n
g
c
o
n
d
i
t
i
o
n
s
a
n
d
b
a
c
k
g
r
o
u
n
d
t
e
x
t
u
r
e
s
.
P
o
o
r
c
o
n
t
r
a
s
t
o
r
u
n
e
v
e
n
p
a
t
t
e
r
n
s
i
n
c
e
r
a
m
i
c
s
,
a
m
o
n
g
o
t
h
e
r
e
n
v
i
r
o
n
m
e
n
t
a
l
f
a
c
t
o
r
s
,
m
a
k
e
i
t
d
i
f
f
i
c
u
l
t
f
o
r
t
h
e
m
o
d
e
l
t
o
d
e
t
e
c
t
c
r
a
c
k
s
w
i
t
h
r
e
l
i
a
b
i
l
i
t
y
,
h
e
n
c
e
t
h
e
f
a
l
l
i
n
c
o
n
f
i
d
e
n
c
e
.
T
h
e
s
e
d
if
f
er
e
n
ce
s
in
c
o
n
f
i
d
e
n
c
e
h
i
g
h
l
i
g
h
t
h
o
w
im
p
o
r
t
an
t
co
n
t
ex
t
i
s
w
h
e
n
g
a
u
g
i
n
g
th
e
p
r
e
d
i
c
t
io
n
s
o
f
t
h
e
m
o
d
e
l.
A
d
ju
s
t
i
n
g
t
h
e
d
e
t
e
c
t
io
n
t
h
r
e
s
h
o
l
d
c
an
h
e
l
p
i
n
t
a
i
lo
r
in
g
p
e
r
f
o
r
m
a
n
c
e
to
s
u
i
t
th
e
n
e
ed
s
o
f
a
p
a
r
t
i
cu
l
a
r
a
p
p
l
i
c
a
t
io
n
.
A
h
i
g
h
e
r
th
r
e
s
h
o
ld
d
o
e
s
r
e
d
u
c
e
f
a
l
s
e
p
o
s
i
t
iv
e
s
,
en
s
u
r
in
g
o
n
l
y
t
h
e
m
o
s
t
s
u
r
e
f
ir
e
d
e
t
e
c
t
io
n
s
r
e
m
a
i
n
u
n
d
er
c
o
n
s
i
d
e
r
a
t
io
n
,
b
y
r
em
o
v
i
n
g
b
o
x
e
s
w
i
t
h
l
o
w
er
c
o
n
f
id
e
n
c
e
.
A
s
m
a
l
l
er
th
r
e
s
h
o
ld
r
i
s
k
s
a
d
m
i
t
t
i
n
g
m
o
r
e
f
a
l
s
e
a
la
r
m
s
b
u
t
m
a
y
b
e
ab
l
e
to
d
e
te
c
t
m
i
n
o
r
o
r
b
o
r
d
e
r
l
in
e
b
r
e
ac
h
e
s
.
T
h
e
o
p
t
im
a
l
t
h
r
e
s
h
o
l
d
th
u
s
d
e
p
e
n
d
s
o
n
wh
e
t
h
er
,
f
o
r
a
p
ar
t
i
cu
l
a
r
m
a
n
u
f
a
c
t
u
r
i
n
g
o
r
q
u
a
l
i
t
y
-
c
o
n
t
r
o
l
s
i
t
u
a
t
i
o
n
,
i
t
i
s
m
o
r
e
c
r
i
t
i
c
a
l
to
m
i
s
s
a
c
r
a
c
k
(
f
a
l
s
e
n
e
g
a
t
iv
e
)
o
r
to
f
a
l
s
e
ly
s
i
g
n
a
l
a
n
in
t
a
c
t
ar
e
a
(
f
a
l
s
e
p
o
s
i
t
i
v
e)
.
4.
CO
NCLU
SI
O
N
T
h
is
s
tu
d
y
co
m
p
ar
e
d
f
o
u
r
v
ar
ian
ts
o
f
YOL
O
f
o
r
r
ea
l
-
ti
m
e
ce
r
am
ic
c
r
ac
k
d
etec
tio
n
,
in
clu
d
in
g
YOL
Ov
8
,
YOL
Ov
9
,
YOL
Ov
1
0
,
an
d
YOL
Ov
1
1
,
with
a
f
o
cu
s
o
n
f
ast
in
f
e
r
en
ce
an
d
l
o
w
m
em
o
r
y
u
s
ag
e.
YOL
Ov
9
an
d
YOL
Ov
1
1
r
esu
lt
in
a
h
ig
h
er
d
etec
tio
n
ac
cu
r
ac
y
wh
ile
s
u
b
s
tan
tial
ly
in
cr
ea
s
in
g
th
e
co
m
p
u
tatio
n
al
co
s
t.
T
h
u
s
,
th
e
y
ar
e
n
o
t
s
u
itab
le
f
o
r
r
eso
u
r
ce
-
co
n
s
tr
ain
ed
en
v
ir
o
n
m
e
n
ts
.
E
v
en
tu
ally
,
YOL
Ov
8
tu
r
n
s
o
u
t
to
b
e
o
p
tim
al
in
an
in
d
u
s
tr
ial
co
n
tex
t,
o
f
f
er
in
g
an
ex
ce
llen
t
c
o
m
p
r
o
m
is
e
b
etwe
en
d
etec
tio
n
p
er
f
o
r
m
an
ce
,
in
f
er
en
ce
s
p
ee
d
,
an
d
m
o
d
el
co
m
p
ac
tn
ess
.
T
h
ese
f
in
d
in
g
s
u
n
d
e
r
lin
e
th
e
p
o
ten
tial
o
f
YOL
Ov
8
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
in
au
to
m
ated
ce
r
am
ic
d
ef
ec
t
in
s
p
ec
tio
n
an
d
th
u
s
im
p
r
o
v
e
q
u
ali
ty
co
n
tr
o
l
ef
f
icien
cy
in
an
in
d
u
s
tr
ial
en
v
ir
o
n
m
en
t.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
wo
u
l
d
lik
e
t
o
ex
p
r
ess
th
eir
s
in
ce
r
e
g
r
atitu
d
e
to
Su
an
Su
n
an
d
h
a
R
ajab
h
at
Un
i
v
er
s
ity
an
d
R
ajam
an
g
ala
Un
iv
er
s
ity
o
f
T
e
ch
n
o
lo
g
y
T
h
an
y
ab
u
r
i
f
o
r
t
h
eir
v
alu
ab
le
s
u
p
p
o
r
t
an
d
en
c
o
u
r
a
g
em
en
t
th
r
o
u
g
h
o
u
t
th
is
r
esear
ch
p
r
o
ject.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
th
er
e
is
n
o
f
u
n
d
i
n
g
in
v
o
lv
ed
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
B
en
ch
alak
Ma
u
n
g
m
ee
s
r
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Sas
ith
o
r
n
Kh
o
n
th
o
n
✓
✓
✓
✓
✓
✓
✓
Dec
h
r
it M
an
ee
th
am
✓
✓
✓
✓
✓
✓
✓
✓
Pad
m
a
Ny
o
m
an
C
r
is
n
ap
ati
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
W
e
h
av
e
o
b
tain
ed
in
f
o
r
m
ed
c
o
n
s
en
t f
r
o
m
all
in
d
iv
id
u
als in
c
lu
d
ed
in
t
h
is
s
tu
d
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
E
fficien
t YOLO
-
b
a
s
ed
mo
d
els fo
r
r
ea
l
-
time
ce
r
a
mic
cra
ck
d
etec
tio
n
(
B
en
ch
a
la
k
Ma
u
n
g
mee
s
r
i
)
859
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
av
ailab
l
e
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
t
h
o
r
,
[
SK]
,
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
S
.
D
h
a
n
a
s
e
k
a
r
e
t
a
l
.
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
s
t
u
d
y
o
f
c
e
r
a
m
i
c
m
a
t
r
i
x
c
o
m
p
o
s
i
t
e
s
f
o
r
s
p
a
c
e
a
p
p
l
i
c
a
t
i
o
n
s
,
”
A
d
v
a
n
c
e
s
i
n
M
a
t
e
r
i
a
l
s
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
2
0
2
2
,
p
p
.
1
–
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
6
1
6
0
5
9
1
.
[
2
]
Ş
.
S
.
F
i
d
a
n
a
n
d
R
.
Ü
n
a
l
,
“
A
s
u
r
v
e
y
o
n
c
e
r
a
m
i
c
r
a
d
o
m
e
f
a
i
l
u
r
e
t
y
p
e
s
a
n
d
t
h
e
i
m
p
o
r
t
a
n
c
e
o
f
d
e
f
e
c
t
d
e
t
e
r
m
i
n
a
t
i
o
n
,
”
E
n
g
i
n
e
e
r
i
n
g
F
a
i
l
u
r
e
A
n
a
l
y
s
i
s
,
v
o
l
.
1
4
9
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
f
a
i
l
a
n
a
l
.
2
0
2
3
.
1
0
7
2
3
4
.
[
3
]
H
.
S
.
M
u
n
a
w
a
r
,
A
.
W
.
A
.
H
a
m
m
a
d
,
A
.
H
a
d
d
a
d
,
C
.
A
.
P
.
S
o
a
r
e
s
,
a
n
d
S
.
T
.
W
a
l
l
e
r
,
“
I
m
a
g
e
-
b
a
s
e
d
c
r
a
c
k
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
:
a
r
e
v
i
e
w
,
”
I
n
f
r
a
s
t
r
u
c
t
u
r
e
s
,
v
o
l
.
6
,
n
o
.
8
,
2
0
2
1
,
d
o
i
:
1
0
.
3
3
9
0
/
i
n
f
r
a
s
t
r
u
c
t
u
r
e
s
6
0
8
0
1
1
5
.
[
4
]
A
.
K
u
m
a
r
a
n
d
S
.
P
.
H
a
r
s
h
a
,
“
A
s
y
s
t
e
m
a
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
o
f
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
i
n
r
a
i
l
w
a
y
s
u
s
i
n
g
m
a
c
h
i
n
e
v
i
s
i
o
n
-
b
a
s
e
d
i
n
s
p
e
c
t
i
o
n
m
e
t
h
o
d
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
T
r
a
n
s
p
o
r
t
a
t
i
o
n
S
c
i
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
8
,
p
p
.
2
0
7
–
2
2
6
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
j
t
s
t
.
2
0
2
4
.
0
6
.
0
0
6
.
[
5
]
S
.
B
.
J
h
a
a
n
d
R
.
F
.
B
a
b
i
c
e
a
n
u
,
“
D
e
e
p
C
N
N
-
b
a
s
e
d
v
i
s
u
a
l
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
:
s
u
r
v
e
y
o
f
c
u
r
r
e
n
t
l
i
t
e
r
a
t
u
r
e
,
”
C
o
m
p
u
t
e
r
s
i
n
I
n
d
u
s
t
r
y
,
v
o
l
.
1
4
8
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
o
m
p
i
n
d
.
2
0
2
3
.
1
0
3
9
1
1
.
[
6
]
A
.
S
a
b
e
r
i
r
o
n
a
g
h
i
,
J
.
R
e
n
,
a
n
d
M
.
E
l
-
G
i
n
d
y
,
“
D
e
f
e
c
t
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
f
o
r
i
n
d
u
s
t
r
i
a
l
p
r
o
d
u
c
t
s
u
s
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
:
a
r
e
v
i
e
w
,
”
A
l
g
o
r
i
t
h
m
s
,
v
o
l
.
1
6
,
n
o
.
2
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
1
6
0
2
0
0
9
5
.
[
7
]
R
.
K
h
a
n
a
m
,
M
.
H
u
s
s
a
i
n
,
R
.
H
i
l
l
,
a
n
d
P
.
A
l
l
e
n
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
c
o
n
v
o
l
u
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
s
f
o
r
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
i
n
i
n
d
u
s
t
r
i
a
l
a
p
p
l
i
c
a
t
i
o
n
s
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
1
2
,
n
o
.
1
,
p
p
.
9
4
2
5
0
–
9
4
2
9
5
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
4
.
3
4
2
5
1
6
6
.
[
8
]
M
.
L
.
A
l
i
a
n
d
Z
.
Z
h
a
n
g
,
“
T
h
e
Y
O
L
O
f
r
a
m
e
w
o
r
k
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
e
v
o
l
u
t
i
o
n
,
a
p
p
l
i
c
a
t
i
o
n
s
,
a
n
d
b
e
n
c
h
m
a
r
k
s
i
n
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
,
”
C
o
m
p
u
t
e
r
s
,
v
o
l
.
1
3
,
n
o
.
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
c
o
m
p
u
t
e
r
s
1
3
1
2
0
3
3
6
.
[
9
]
H
.
M
.
A
h
m
a
d
a
n
d
A
.
R
a
h
i
m
i
,
“
D
e
e
p
l
e
a
r
n
i
n
g
m
e
t
h
o
d
s
f
o
r
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
i
n
s
m
a
r
t
m
a
n
u
f
a
c
t
u
r
i
n
g
:
A
s
u
r
v
e
y
,
”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
r
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
6
4
,
p
p
.
1
8
1
–
1
9
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
m
s
y
.
2
0
2
2
.
0
6
.
0
1
1
.
[
1
0
]
M
.
T
.
H
o
s
a
i
n
,
A
.
Z
a
m
a
n
,
M
.
R
.
A
b
i
r
,
S
.
A
k
t
e
r
,
S
.
M
u
r
s
a
l
i
n
,
a
n
d
S
.
S
.
K
h
a
n
,
“
S
y
n
c
h
r
o
n
i
z
i
n
g
o
b
j
e
c
t
d
e
t
e
c
t
i
o
n
:
a
p
p
l
i
c
a
t
i
o
n
s
,
a
d
v
a
n
c
e
m
e
n
t
s
a
n
d
e
x
i
s
t
i
n
g
c
h
a
l
l
e
n
g
e
s
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
1
2
,
p
p
.
5
4
1
2
9
–
5
4
1
6
7
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
4
.
3
3
8
8
8
8
9
.
[
1
1
]
R
.
S
a
p
k
o
t
a
,
Z
.
M
e
n
g
,
M
.
C
h
u
r
u
v
i
j
a
,
X
.
D
u
,
Z
.
M
a
,
a
n
d
M
.
K
a
r
k
e
e
,
“
C
o
m
p
r
e
h
e
n
s
i
v
e
p
e
r
f
o
r
m
a
n
c
e
e
v
a
l
u
a
t
i
o
n
o
f
Y
O
L
O
v
1
2
,
Y
O
L
O
1
1
,
Y
O
L
O
v
1
0
,
Y
O
L
O
v
9
a
n
d
Y
O
L
O
v
8
o
n
d
e
t
e
c
t
i
n
g
a
n
d
c
o
u
n
t
i
n
g
f
r
u
i
t
l
e
t
i
n
c
o
m
p
l
e
x
o
r
c
h
a
r
d
e
n
v
i
r
o
n
m
e
n
t
s
,
”
A
g
r
i
c
u
l
t
u
r
e
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
2
0
2
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
g
r
c
o
m
.
2
0
2
6
.
1
0
0
1
2
5
.
[
1
2
]
G
.
W
a
n
g
,
Y
.
C
h
e
n
,
P
.
A
n
,
H
.
H
o
n
g
,
J
.
H
u
,
a
n
d
T
.
H
u
a
n
g
,
“
U
A
V
-
Y
O
L
O
v
8
:
a
s
m
a
l
l
-
o
b
j
e
c
t
-
d
e
t
e
c
t
i
o
n
m
o
d
e
l
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
Y
O
L
O
v
8
f
o
r
U
A
V
a
e
r
i
a
l
p
h
o
t
o
g
r
a
p
h
y
s
c
e
n
a
r
i
o
s
,
”
S
e
n
s
o
r
s
,
v
o
l
.
2
3
,
n
o
.
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
s
2
3
1
6
7
1
9
0
.
[
1
3
]
B
.
X
i
a
o
,
M
.
N
g
u
y
e
n
,
a
n
d
W
.
Q
.
Y
a
n
,
“
F
r
u
i
t
r
i
p
e
n
e
s
s
i
d
e
n
t
i
f
i
c
a
t
i
o
n
u
s
i
n
g
Y
O
L
O
v
8
m
o
d
e
l
,
”
M
u
l
t
i
m
e
d
i
a
T
o
o
l
s
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
8
3
,
n
o
.
9
,
p
p
.
2
8
0
3
9
–
2
8
0
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
1
0
4
2
-
023
-
16570
-
9.
[
1
4
]
M
.
S
a
f
a
l
d
i
n
,
N
.
Z
a
g
h
d
e
n
,
a
n
d
M
.
M
e
j
d
o
u
b
,
“
A
n
i
m
p
r
o
v
e
d
Y
O
L
O
v
8
t
o
d
e
t
e
c
t
m
o
v
i
n
g
o
b
j
e
c
t
s
,
”
I
E
E
E
A
c
c
e
s
s
,
v
o
l
.
1
2
,
p
p
.
5
9
7
8
2
–
5
9
8
0
6
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
E
S
S
.
2
0
2
4
.
3
3
9
3
8
3
5
.
[
1
5
]
G
.
N
a
i
n
,
K
.
K
.
P
a
t
t
a
n
a
i
k
,
a
n
d
G
.
K
.
S
h
a
r
m
a
,
“
T
o
w
a
r
d
s
e
d
g
e
c
o
m
p
u
t
i
n
g
i
n
i
n
t
e
l
l
i
g
e
n
t
m
a
n
u
f
a
c
t
u
r
i
n
g
:
p
a
s
t
,
p
r
e
s
e
n
t
a
n
d
f
u
t
u
r
e
,
”
J
o
u
r
n
a
l
o
f
M
a
n
u
f
a
c
t
u
r
i
n
g
S
y
s
t
e
m
s
,
v
o
l
.
6
2
,
p
p
.
5
8
8
–
6
1
1
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
m
s
y
.
2
0
2
2
.
0
1
.
0
1
0
.
[
1
6
]
C
.
X
u
a
n
d
G
.
Z
h
u
,
“
I
n
t
e
l
l
i
g
e
n
t
m
a
n
u
f
a
c
t
u
r
i
n
g
l
i
e
g
r
o
u
p
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
:
r
e
a
l
-
t
i
m
e
a
n
d
e
f
f
i
c
i
e
n
t
i
n
s
p
e
c
t
i
o
n
s
y
s
t
e
m
b
a
s
e
d
o
n
f
o
g
c
o
m
p
u
t
i
n
g
,
”
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
M
a
n
u
f
a
c
t
u
r
i
n
g
,
v
o
l
.
3
2
,
n
o
.
1
,
p
p
.
2
3
7
–
2
4
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
8
4
5
-
020
-
01570
-
5.
[
1
7
]
Y
.
L
i
u
,
Y
.
D
e
n
g
,
A
.
N
a
l
l
a
n
a
t
h
a
n
,
a
n
d
J
.
Y
u
a
n
,
“
M
a
c
h
i
n
e
l
e
a
r
n
i
n
g
f
o
r
6
G
e
n
h
a
n
c
e
d
u
l
t
r
a
-
r
e
l
i
a
b
l
e
a
n
d
l
o
w
-
l
a
t
e
n
c
y
s
e
r
v
i
c
e
s
,
”
I
E
E
E
W
i
r
e
l
e
s
s
C
o
m
m
u
n
i
c
a
t
i
o
n
s
,
v
o
l
.
3
0
,
n
o
.
2
,
p
p
.
4
8
–
5
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
M
W
C
.
0
0
6
.
2
2
0
0
4
0
7
.
[
1
8
]
S
.
Y
u
,
C
.
Z
h
a
n
g
,
a
n
d
H
.
Y
a
n
g
,
“
S
u
r
f
a
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
f
o
r
c
e
r
a
m
i
c
t
i
l
e
s
b
a
s
e
d
o
n
m
u
l
t
i
-
a
n
c
h
o
r
m
e
c
h
a
n
i
s
m
,
”
i
n
2
0
2
4
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
V
i
s
i
o
n
,
I
m
a
g
e
a
n
d
D
e
e
p
L
e
a
r
n
i
n
g
(
C
V
I
D
L
)
,
2
0
2
4
,
p
p
.
1
2
8
1
–
1286
,
doi
:
1
0
.
1
1
0
9
/
C
V
I
D
L
6
2
1
4
7
.
2
0
2
4
.
1
0
6
0
3
5
0
8
.
[
1
9
]
T
.
A
.
-
A
l
e
x
a
n
d
r
u
,
C
.
C
o
s
m
i
n
,
S
.
I
o
a
n
,
T
.
A
d
r
i
a
n
-
A
l
e
x
a
n
d
r
u
,
a
n
d
D
.
E
.
H
e
n
r
i
e
t
t
a
,
“
N
o
v
e
l
c
e
r
a
m
i
c
p
l
a
t
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
u
s
i
n
g
Y
O
L
O
-
R
,
”
i
n
2
0
2
2
1
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
E
l
e
c
t
r
o
n
i
c
s
,
C
o
m
p
u
t
e
r
s
a
n
d
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
(
E
C
A
I
)
,
2
0
2
2
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
E
C
A
I
5
4
8
7
4
.
2
0
2
2
.
9
8
4
7
4
3
1
.
[
2
0
]
Y
.
Z
h
u
a
n
d
H
.
S
o
n
g
,
“
I
m
p
r
o
v
e
d
s
m
a
l
l
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
o
n
c
e
r
a
m
i
c
s
u
r
f
a
c
e
s
w
i
t
h
Y
O
L
O
v
8
,
”
i
n
2
0
2
4
3
9
t
h
Y
o
u
t
h
A
c
a
d
e
m
i
c
A
n
n
u
a
l
C
o
n
f
e
r
e
n
c
e
o
f
C
h
i
n
e
s
e
A
s
s
o
c
i
a
t
i
o
n
o
f
A
u
t
o
m
a
t
i
o
n
(
Y
A
C
)
,
2
0
2
4
,
p
p
.
1
8
7
9
–
1884
,
d
o
i
:
1
0
.
1
1
0
9
/
Y
A
C
6
3
4
0
5
.
2
0
2
4
.
1
0
5
9
8
7
2
1
.
[
2
1
]
C.
-
Y
.
H
u
a
n
g
,
I
.
-
C
.
L
i
n
,
a
n
d
Y
.
-
L
.
L
i
u
,
“
A
p
p
l
y
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
t
o
c
o
n
s
t
r
u
c
t
a
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
s
y
s
t
e
m
f
o
r
c
e
r
a
m
i
c
s
u
b
s
t
r
a
t
e
s
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
2
,
n
o
.
5
,
2
0
2
2
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
2
0
5
2
2
6
9
.
[
2
2
]
X
.
Y
u
,
Q
.
Y
u
,
Q
.
M
u
,
Z
.
H
u
,
a
n
d
J
.
X
i
e
,
“
M
C
A
W
-
Y
O
L
O
:
a
n
e
f
f
i
c
i
e
n
t
d
e
t
e
c
t
i
o
n
m
o
d
e
l
f
o
r
c
e
r
a
m
i
c
t
i
l
e
s
u
r
f
a
c
e
d
e
f
e
c
t
s
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
3
,
n
o
.
2
1
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
3
2
1
1
2
0
5
7
.
[
2
3
]
H
.
P
a
n
,
G
.
L
i
,
H
.
F
e
n
g
,
Q
.
L
i
,
P
.
S
u
n
,
a
n
d
S
.
Y
e
,
“
S
u
r
f
a
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
o
f
c
e
r
a
m
i
c
d
i
s
c
b
a
s
e
d
o
n
i
m
p
r
o
v
e
d
Y
O
L
O
v
5
s
,
”
H
e
l
i
y
o
n
,
v
o
l
.
1
0
,
n
o
.
1
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
h
e
l
i
y
o
n
.
2
0
2
4
.
e
3
3
0
1
6
.
[
2
4
]
P
.
S
u
n
,
C
.
H
u
a
,
W
.
D
i
n
g
,
C
.
H
u
a
,
P
.
L
i
u
,
a
n
d
Z
.
L
e
i
,
“
C
e
r
a
m
i
c
t
a
b
l
e
w
a
r
e
s
u
r
f
a
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
b
a
s
e
d
o
n
d
e
e
p
l
e
a
r
n
i
n
g
,
”
E
n
g
i
n
e
e
r
i
n
g
A
p
p
l
i
c
a
t
i
o
n
s
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
4
1
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
n
g
a
p
p
a
i
.
2
0
2
4
.
1
0
9
7
2
3
.
[
2
5
]
X
.
J
i
a
e
t
a
l
.
,
“
H
i
g
h
-
p
e
r
f
o
r
m
a
n
c
e
d
e
f
e
c
t
d
e
t
e
c
t
i
o
n
m
e
t
h
o
d
s
f
o
r
r
e
a
l
-
t
i
m
e
m
o
n
i
t
o
r
i
n
g
o
f
c
e
r
a
m
i
c
a
d
d
i
t
i
v
e
m
a
n
u
f
a
c
t
u
r
i
n
g
p
r
o
c
e
s
s
b
a
s
e
d
o
n
s
m
a
l
l
-
s
c
a
l
e
d
a
t
a
s
e
t
s
,
”
P
r
o
c
e
s
s
e
s
,
v
o
l
.
1
2
,
n
o
.
4
,
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
p
r
1
2
0
4
0
6
3
3
.
[
2
6
]
J
.
T
e
r
v
e
n
,
D
.
-
M
.
C
ó
r
d
o
v
a
-
E
s
p
a
r
z
a
,
a
n
d
J
.
-
A
.
R
o
m
e
r
o
-
G
o
n
z
á
l
e
z
,
“
A
c
o
m
p
r
e
h
e
n
s
i
v
e
r
e
v
i
e
w
o
f
Y
O
L
O
a
r
c
h
i
t
e
c
t
u
r
e
s
i
n
c
o
m
p
u
t
e
r
v
i
s
i
o
n
:
f
r
o
m
Y
O
L
O
v
1
t
o
Y
O
L
O
v
8
a
n
d
Y
O
L
O
-
N
A
S
,
”
M
a
c
h
i
n
e
L
e
a
r
n
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
E
x
t
r
a
c
t
i
o
n
,
v
o
l
.
5
,
n
o
.
4
,
p
p
.
1
6
8
0
–
1
7
1
6
,
2
0
2
3
,
d
o
i
:
1
0
.
3
3
9
0
/
m
a
k
e
5
0
4
0
0
8
3
.
[
2
7
]
E
.
C
a
s
a
s
,
L
.
R
a
m
o
s
,
C
.
R
o
m
e
r
o
,
a
n
d
F
.
R
i
v
a
s
-
E
c
h
e
v
e
r
r
í
a
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
Y
O
L
O
v
5
a
n
d
Y
O
L
O
v
8
f
o
r
c
o
r
r
o
s
i
o
n
s
e
g
m
e
n
t
a
t
i
o
n
t
a
s
k
s
i
n
m
e
t
a
l
s
u
r
f
a
c
e
s
,
”
A
r
r
a
y
,
v
o
l
.
2
2
,
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
a
r
r
a
y
.
2
0
2
4
.
1
0
0
3
5
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J
Ar
tif
I
n
tell
,
Vo
l.
15
,
No
.
1
,
Feb
r
u
ar
y
2
0
2
6
:
852
-
8
6
0
860
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Be
n
c
h
a
la
k
M
a
u
n
g
m
e
e
sr
i
i
s
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
o
f
M
a
teria
ls
Tec
h
n
o
l
o
g
y
(Ce
ra
m
ic
Tec
h
n
o
lo
g
y
)
a
t
S
u
a
n
S
u
n
a
n
d
h
a
Ra
ja
b
h
a
t
U
n
iv
e
rsit
y
,
Th
a
il
a
n
d
.
S
h
e
re
c
e
iv
e
d
h
e
r
b
a
c
h
e
lo
r’s
d
e
g
re
e
i
n
Ce
ra
m
ic
Tec
h
n
o
l
o
g
y
fro
m
P
h
ra
n
a
k
h
o
n
Te
a
c
h
e
rs
Co
ll
e
g
e
in
1
9
9
0
a
n
d
m
a
ste
r’
s
d
e
g
re
e
in
In
d
u
strial
E
d
u
c
a
ti
o
n
fr
o
m
S
ri
n
a
k
h
a
ri
n
wiro
t
Un
iv
e
rsity
in
1
9
9
5
a
n
d
h
e
r
P
h
.
D.
i
n
M
a
n
a
g
e
m
e
n
t
Tec
h
n
o
lo
g
y
fr
o
m
P
h
ra
n
a
k
h
o
n
Ra
jab
h
a
t
Un
iv
e
rsity
,
a
n
d
h
e
r
P
h
.
D.
in
Bu
sin
e
ss
Ad
m
in
istrati
o
n
a
n
d
Dig
it
a
l
In
n
o
v
a
ti
o
n
fr
o
m
M
a
h
a
sa
ra
k
h
a
m
Un
iv
e
rsity
in
2
0
2
3
.
S
h
e
is
a
lec
tu
re
r
a
t
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
a
n
d
I
n
d
u
strial
Tec
h
n
o
lo
g
y
,
S
u
a
n
S
u
n
a
n
d
h
a
Ra
jab
h
a
t
Un
iv
e
rsity
,
Th
a
il
a
n
d
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
in
d
u
strial
c
e
ra
m
ics
,
m
a
teri
a
l
e
n
g
in
e
e
rin
g
,
a
n
d
tec
h
n
o
l
o
g
y
m
a
n
a
g
e
m
e
n
t
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
e
n
c
h
a
lak
.
m
u
@s
sru
.
a
c
.
th
.
S
a
sith
o
r
n
K
h
o
n
th
o
n
c
u
rre
n
tl
y
se
rv
in
g
a
s
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
in
In
d
u
strial
P
ro
d
u
c
t
De
sig
n
a
t
P
h
ra
n
a
k
h
o
n
R
a
jab
h
a
t
Un
iv
e
rsit
y
,
T
h
a
il
a
n
d
.
S
h
e
h
a
s
d
e
d
ica
ted
h
e
r
c
a
re
e
r
to
th
e
a
d
v
a
n
c
e
m
e
n
t
o
f
c
e
ra
m
ic
tec
h
n
o
lo
g
y
.
He
r
a
c
a
d
e
m
ic
jo
u
rn
e
y
b
e
g
a
n
with
a
Ba
c
h
e
lo
r
o
f
S
c
ien
c
e
(B.
S
c
.
)
in
Ce
ra
m
ic
Tec
h
n
o
l
o
g
y
fro
m
P
h
ra
n
a
k
h
o
n
Ra
jab
h
a
t
In
stit
u
te
in
1
9
9
2
,
fo
l
lo
we
d
b
y
a
M
a
ste
r
o
f
S
c
ien
c
e
(M
.
S
c
.
)
in
In
d
u
strial
Tec
h
n
o
l
o
g
y
fro
m
P
h
ra
n
a
k
h
o
n
Ra
jab
h
a
t
Un
i
v
e
rsity
in
2
0
0
0
.
S
h
e
late
r
e
a
rn
e
d
a
Do
c
to
r
o
f
E
n
g
i
n
e
e
rin
g
(D
.
En
g
.
)
i
n
Ce
ra
m
ic
En
g
in
e
e
rin
g
fro
m
S
u
ra
n
a
re
e
Un
iv
e
rsity
o
f
Tec
h
n
o
l
o
g
y
in
2
0
0
9
.
Wi
th
o
v
e
r
3
0
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
in
c
e
ra
m
ic
s,
sh
e
h
a
s
c
o
n
ti
n
u
o
u
sl
y
c
o
n
tri
b
u
ted
t
o
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
c
e
ra
m
ic
te
c
h
n
o
l
o
g
y
.
He
r
a
c
a
d
e
m
ic
wo
rk
in
c
lu
d
e
s
re
se
a
rc
h
p
u
b
li
c
a
ti
o
n
s,
s
h
o
rt
-
term
train
in
g
p
ro
g
ra
m
s,
a
n
d
p
u
b
li
c
e
x
h
ib
it
io
n
s
a
t
v
a
rio
u
s
a
c
a
d
e
m
ic
c
o
n
fe
re
n
c
e
s.
Ad
d
it
i
o
n
a
ll
y
,
sh
e
h
a
s
p
lay
e
d
a
k
e
y
r
o
le
in
in
teg
ra
ti
n
g
c
e
ra
m
ic
tec
h
n
o
l
o
g
y
with
3
D
p
ri
n
ti
n
g
fo
r
a
p
p
li
c
a
ti
o
n
s
i
n
th
e
c
e
ra
m
ic
i
n
d
u
stry
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
at
e
m
a
il
:
sa
s
it
h
o
r
n
@p
n
ru
.
a
c
.
th
.
De
c
h
r
it
Ma
n
e
e
th
a
m
c
u
rre
n
tl
y
se
rv
e
s
a
s
a
p
ro
fe
ss
o
r
i
n
M
e
c
h
a
tro
n
ics
En
g
in
e
e
rin
g
a
t
Ra
jam
a
n
g
a
la
Un
iv
e
rsity
o
f
T
e
c
h
n
o
l
o
g
y
in
T
h
a
n
y
a
b
u
ri,
Th
a
il
a
n
d
.
His
a
c
a
d
e
m
ic
jo
u
rn
e
y
in
c
lu
d
e
s
e
a
rn
in
g
B.
I
n
d
.
Tec
h
.
i
n
M
a
teria
l
Ha
n
d
l
in
g
Tec
h
n
o
l
o
g
y
a
n
d
M
.
S
.
i
n
M
e
c
h
a
n
ica
l
En
g
i
n
e
e
rin
g
fr
o
m
Kin
g
M
o
n
g
k
u
t
’s
Un
iv
e
rsit
y
o
f
Tec
h
n
o
lo
g
y
in
No
rth
Ba
n
g
k
o
k
.
In
2
0
1
0
,
h
e
a
c
h
iev
e
d
a
D.E
n
g
.
in
M
e
c
h
a
tr
o
n
ics
fro
m
t
h
e
As
ian
In
st
it
u
te
o
f
Tec
h
n
o
l
o
g
y
,
fo
ll
o
we
d
b
y
a
P
h
.
D.
in
El
e
c
tri
c
a
l
a
n
d
C
o
m
p
u
ter E
n
g
i
n
e
e
rin
g
fro
m
M
a
h
a
sa
ra
k
h
a
m
Un
iv
e
rsit
y
i
n
2
0
1
8
.
Wi
th
a
we
a
lt
h
o
f
e
x
p
e
rien
c
e
e
x
c
e
e
d
in
g
1
5
y
e
a
rs
i
n
tea
c
h
in
g
e
n
g
in
e
e
rin
g
,
h
e
h
a
s
sig
n
i
fica
n
t
ly
c
o
n
tri
b
u
ted
t
o
th
e
fiel
d
.
His c
o
n
tri
b
u
ti
o
n
s e
x
te
n
d
t
o
th
e
p
u
b
li
c
a
ti
o
n
o
f
o
v
e
r
9
0
tec
h
n
ica
l
p
a
p
e
rs.
Be
y
o
n
d
a
c
a
d
e
m
ia,
h
e
h
a
s
sh
a
re
d
h
is
k
n
o
wle
d
g
e
t
h
ro
u
g
h
ro
b
o
ti
c
s
sh
o
rt
c
o
u
rse
s
a
t
v
a
ri
o
u
s
c
o
n
fe
re
n
c
e
s
a
n
d
a
u
t
h
o
re
d
se
v
e
n
b
o
o
k
s.
Th
e
se
p
u
b
li
c
a
ti
o
n
s
c
o
v
e
r
a
ra
n
g
e
o
f
t
o
p
ics
,
i
n
c
lu
d
in
g
p
n
e
u
m
a
ti
c
s
sy
ste
m
,
h
y
d
ra
u
l
ics
sy
ste
m
,
M
CS
-
5
1
m
icro
c
o
n
tr
o
ll
e
r,
P
IC
m
icro
c
o
n
tro
ll
e
r,
Ard
u
in
o
m
icro
c
o
n
tro
ll
e
r,
P
LC
Be
c
k
h
o
ff
,
a
n
d
r
o
b
o
t.
Th
e
se
wo
r
k
s
sh
o
wc
a
se
h
is
e
x
p
e
rti
se
in
th
e
re
a
lms
o
f
r
o
b
o
ti
c
s,
a
u
to
m
a
ti
o
n
,
m
e
c
h
a
tro
n
ics
,
a
n
d
b
i
o
m
e
d
ica
l
a
p
p
li
c
a
ti
o
n
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
e
c
h
rit
_
m
@rm
u
tt
.
a
c
.
t
h
.
Pa
d
m
a
N
y
o
m
a
n
Cr
isn
a
p
a
ti
o
b
tain
e
d
h
is
b
a
c
h
e
lo
r'
s
d
e
g
r
e
e
in
2
0
0
9
fro
m
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s
En
g
i
n
e
e
rin
g
o
f
I
n
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r
.
He
o
b
tain
e
d
h
is
first
m
a
ste
r'
s
d
e
g
re
e
in
Lea
rn
in
g
Tec
h
n
o
l
o
g
y
in
2
0
1
1
a
n
d
a
n
o
th
e
r
m
a
ste
r'
s
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
i
n
2
0
1
8
fr
o
m
G
a
n
e
sh
a
Ed
u
c
a
ti
o
n
U
n
iv
e
rsi
ty
.
Th
e
n
,
h
e
su
c
c
e
ss
fu
ll
y
a
c
h
iev
e
d
a
D.E
n
g
.
in
t
h
e
De
p
a
rt
m
e
n
t
o
f
M
e
c
h
a
tro
n
ics
E
n
g
in
e
e
rin
g
o
f
Ra
jam
a
n
g
a
la
U
n
iv
e
rsit
y
o
f
Tec
h
n
o
lo
g
y
T
h
a
n
y
a
b
u
ri
(RM
UTT)
.
His
a
re
a
s
o
f
in
tere
st
a
re
v
e
ry
e
x
ten
siv
e
.
S
o
m
e
o
f
th
o
se
a
re
a
s
in
c
lu
d
e
m
e
c
h
a
tro
n
ics
,
r
o
b
o
ti
c
s,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
Io
T
,
a
u
g
m
e
n
ted
re
a
li
ty
/
v
irt
u
a
l
re
a
li
ty
,
3
D CAD
.
He
c
a
n
b
e
c
o
n
ta
c
ted
at
e
m
a
il
:
c
risn
a
p
a
ti
@rm
u
tt
.
a
c
.
th
.
Evaluation Warning : The document was created with Spire.PDF for Python.