Page 31 - Kutnar, Andreja, et al., eds., 2015. Proceedings of the 1st COST Action FP1307 International Conference - Life Cycle Assessment, EPDs, and modified wood. University of Primorska Press, Koper.

ntify
a
log
by
means
of
two
images,
is
part
of
ongoing
scientific
research.
The
shape

characteristic
of
annual
rings
(Figure
1),
location
of
pith,
and
log
shape
are
considered
as
unique

biometric
features
(similar
to
ridges
in
human
fingerprints)
which
are
assumed
to
distinguish

between
logs.

Figure
1:

Sectional
RGB
image
of
log
end
face
(left),
binary
image
displaying
segmented

annual
rings
(right).

RGB
images
were
used
because
cameras
like
GoPro
cameras
can
easily
be
mounted
on
the

harvester.
With
technical
modifications
these
cameras
can
be
triggered
via
remote
control
and

can
be
placed
in
shock
absorbent
plastic
housings.

A
previous
study
used
the
annual
ring
pattern
on
rough
log
end
faces
for
recognition
purposes.

This
study
showed
that
logs
can
be
distinguished
by
means
of
a
gabor
filter
databank
using

distinct
block
processing.
Computing
statistical
index
numbers
of
each
block
with
a
gabor
filter

forms
the
basis
for
feature
vectors,
allowing
logs
to
be
identified
using
RGB
images
of
log
end

faces.
The
study
showed
that
logs
can
even
be
reliably
identified
by
images
made
several

centimetres
behind
the
original
slice.

References

Lins
da
Silva
D.,
Corrêa
P.L.P.,
Najim
L.H.
2010.
Requirements
analysis
for
a
traceability
system
for

management
wood
supply
chain
on
Amazon
Forest.
In:
Proceedings
of
IEEE
5th
International

Conference
on
Digital
Information
Management
(ICDIM)
2010;
1(1):
87–94.

European
Timber
regulation
2010.
Regulation
(EU)
No
995/2010
of
the
European
Parliament
and
of
the

council
of
20th
October
2010
laying
down
the
obligations
of
operators
who
place
timber
and
timber

products
on
the
market.
Official
Journal
of
the
European
Union.
Brussels,
2010.

Tzoulis
I,
Andreopoulou
Z.,
2013.
Emerging
traceability
technologies
as
a
tool
for
quality
wood
trade.
In:
6th

International
Conference
on
Information
and
Communication
Technologies
in
Agriculture,
Food
and

Environment
(HAICTA
2013).
Procedia
Technology
2013;
8:606-­‐611.

Schraml
R,
Charwat-­‐Pessler
J,
Uhl
A.
2014.
Temporal
and
longitudinal
variances
in
wood
log
cross-­‐section

image
analysis.
In:
Proceedings
of
the
IEEE
International
Conference
on
Image
Processing
(ICIP).
Paris,

2014.

Acknowledgments

The
authors
would
like
to
thank
the
FWF
Austrian
Science
Fund
for
financing
the
research

project
TRP
254-­‐N13.

19