13
Abstract
The object of this thesis is computer vision. With the advent of high-‐speed
computers
and
cameras
with
high
resolution
and
definition,
the
research
interest
was
expanded
for
the
development
and
implementation
of
algorithms
in
the
field
of
computer
vision.
Algorithms
for
applications
vary
depending
on
their
field
of
interest.
Applications
can
be
developed
with
computer
vision
for
security,
military
and
intelligence,
for
health
issues,
research
and
production.
Among
these
applications,
one
of
the
most
frequently
performed
task
is
to
determine
the
position
and
the
motion
detection
for
each
subject,
all
of
which
occupied us to develop our application.
Nowadays,
the
external
aesthetics
and
integrity
of
the
products
is
obtained
in
an
equal
degree
with
regard
to
the
product
itself
from
the
general
public,
a
fact
that
preoccupies
manufacturers.
To
ensure
long-‐term
promotion
of
a
product,
the
appearance
and
quality
product
integrity
must
be
visually
inspected
before
dispatch.
This
desired
result
can
be
achieved
if
the
process
inspection
become
automated
and
is
performed
without
human
intervention.
By
using
the
techniques
offered
on
machine
vision
tasks,
we
designed
and
implemented
an
application
for
product
classification
in
a
transmission
line
using
camera,
i.e.
the
use
of
a
sequence
of
images.
This
application
enables
the
holder
to
have
a
complete
picture
regarding
quality
and
quantity
of
the
products
thus avoiding any human errors.
At
this
point
I
would
like
to
thank
my
supervisor
Dr.
Mina
Dasygeni
for
his
valuable
help
during
the
implementation
of
this
thesis
and
for
the
knowledge
I
gained
thanks
to
him.
The
topic
of
the
thesis
was
proposed
by
Dr.
Minas
Dasygenis
and
the
application
was
developed
with
programming
language
C++
using
the
libraries
of
OpenCV.
Keywords:
OpenCV,
C
+
+,
Computer
Vision,
Production
line.
Kozani, June 2014
Loizou Konstantina