ASABE Technical Library - Abstract

Click on “Download PDF” for the PDF version or on the title for the HTML version.
If you are not an ASABE member or if your employer has not arranged for access to the full-text, view access and subscription options

Real-Time Detection of Physical Hazards in De-Bonded Poultry Using High-Resolution X-Ray Imaging

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  033084,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.15004) @2003
Authors:   Xin Chen, Hansong Jing, Yang Tao, L. Carr, F. Wheaton
Keywords:   X-ray imaging, bone fragment detection, multithread scheme, rule-based system, pattern recognition, machine vision, real-time system

Thickness variation of chicken fillet is a major challenge to X-ray detection of embedded bone fragments. As a novel solution, combined x-ray and laser range imaging has been developed for thickness compensation effectively. In order for this synergic technology to work successfully for on-line industrial applications, the vision system should have viable real-time capabilities and be able to detect a variety of physical hazards. In this paper, a multithread scheme is developed for real-time image processing, implementation and performance of which are also presented. A rule-based approach is formulated under a unified framework for detection of diversified subjects, and performance of this framework is also discussed.

(Download PDF)    (Export to EndNotes)