Page 49 from: March 2016

49March 2016

growing variety in the appearance of an object,
the manual approach becomes ‘less and less
feasible’.
A number of sorting approaches focus exclu-
sively on colour such that broad application
in different industrial settings is ‘questionable’,
Richter stated. An automatic derivation of
object descriptors and classification rules would
therefore ‘clearly be an improvement’.
The suggested approach is based on the ‘bag of
visual words’ (BOW) framework and is driven

by the insight that each existing document car-
ries words, of which some words give more valu-
able information than others.

‘Nearly perfect classification’
‘The key idea is to consider an image to be com-
posed of visual words, in which the data clusters
form a so-called vocabulary,’ Richter explained.
‘Then, images (material readings) can be classi-
fied by finding out which of and how often these
descriptions occur.’
The imaging part of the sorting system con-
sisted of an RGB line camera producing a reso-
lution of 170 µm x 170 µm per pixel. The overall
inspection width was 700 mm while halogen
lamps were used for illumination.
During the first two rounds, two types of stone
were fed through the system separately, accord-
ing to ‘dense sampling’ which considers a key
point to extract the low-level local descriptors,
yielding a total of 5883 images.
The work produced ‘nearly perfect classifi-
cation’, Richter told his audience in Aachen.
Features could be extracted in less than 90 ms
per sample once the vocabulary had been deter-
mined. ‘The bulk of the processing time was

spent in computing every single object pixel,’
said the researcher. ‘Clearly, the results are far
too slow for a real-time application, at least for
the moment. Our system is a prototype that has
not yet been optimised for speed.’
The main objective now is to balance the sup-
ply of discriminative information with a much
more efficient computational load. The Fraun-
hofer team hopes that trial and error will further
boost the results to fit the time slot of 15 ms for
all objects between inspection line and ejection
stage.

In the case of I-SORT3R technology, the material is
displayed on a touchscreen on which ‘intruders’ from
a predominant waste stream can be selected.

TableSort achieved a 97% precision rate in sorting
ABS derived from end-of-life vehicles.

®

by

COMPACT WIRE CHOPPING SYSTEM

CONTAINERIZED, TURNKEY WIRE CHOPPING SOLUTION

• Maximum Efficiency & Robustness
– Proven MTB Process for Optimal Quality
– Proven MTB Equipment for Reliability

• Integrated Electrical Controls & Dust Collection System

• Process wide and difficult material types
– Shredder Wire – Pre-shred escraps – Wire Harnesses
– Shielded cables – URD Cables – Pre-shred Cu/Al radiators

To learn more about MTB’s Compact Wire Chopping System,
contact us or visit us at ISRI (LAS VEGAS) Booth # 1035,
or IFAT (MUNICH) Booth # C2.408

Cables

Copper Aluminum Plastic

ICW

+33 474 928 768 Quartier de la Gare – 38460 Trept – FRANCE [email protected]

NEW2T/h industrial line