A machine vision based keg inspection system can allow cost effective keg tracking and preventative maintenance programs to be implemented, leading to substantial savings for breweries with large keg fleets. A robust keg serial number recognition and keg condition assessment process is required to cater for different keg brands and a range of keg ages in the fleet. It has been demonstrated that the proposed image processing methodology, and neural network based number recognition system, successfully located and identified keg serial numbers with a 92% digit accuracy. Furthermore, the vision system allowed the concurrent assessment of the keg condition by assessing deformity of the keg rim, and that of the filler valve. A correlation coefficient, generated using a template matching process, proved to be a suitable metric which adequately indicated rims within and outside acceptable deformity bounds.
Computational Intelligence for Automated Keg Identification and Deformnation Detection
2007-04-01
7151532 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Artificial Intelligence-Aided Automated Detection of Railroad Trespassing
Transportation Research Record | 2019
|Computational Intelligence for Human Detection of a Partner Robot
British Library Conference Proceedings | 2004
|Computational aerodynamics and artificial intelligence
AIAA | 1984
|Fuselage assembly with computational intelligence
Tema Archiv | 2008
|