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

Automatic Inspection Using Machine Vision for Food Safety

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

Citation:  7th World Congress on Computers in Agriculture Conference Proceedings, 22-24 June 2009, Reno, Nevada (electronic only)  711P0409e.(doi:10.13031/2013.29040)
Authors:   Chun-Chieh Yang, Kuanglin Chao, Moon S Kim
Keywords:   machine vision, poultry carcass inspection, food safety.

The proposed research has created a machine vision system for automatic poultry carcass inspection. This system will be very useful for identifying unwholesome chickens for tracking and removal from the processing line for food safety control. The line-scan machine vision system uses an electron-multiplying-charge-coupled-device (EMCCD) camera and a spectrograph to acquire line-scan images to form complete hyperspectral images of whole carcasses spanning many wavebands across a broad spectral range. The system can be switched to acquire multispectral images using a few pre-selected wavebands, which increases imaging speed. The system scans the surfaces of poultry carcasses on a processing line, automatically recognizing each individual carcass as it is scanned, quickly locates the region of interest (ROI) for each carcass, and identifies in real-time those carcasses that are unwholesome. During in-plant tests, the line-scan machine vision system has successfully inspected over 60,000 carcasses on a poultry processing line operating at a speed of 140 carcasses per minute.

(Download PDF)    (Export to EndNotes)