Line-scan spectral imaging systems for online poultry carcass inspection

Authors: Chao, Kuanglin - Kevin Chao; YANG, CHUN-CHIEH - VIS SCI-UNIV OF KY; Kim, Moon

Submitted to: Journal of Food Process Engineering
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 8/28/2008
Publication Date: 10/28/2009
Citation: Chao, K., Yang, C., Kim, M.S. 2009. Line-scan spectral imaging systems for online poultry carcass inspection. Journal of Food Process Engineering. Available at http://dx.doi.org/10.1111/j.1745-4530.2008.00341.x

Interpretive Summary: The Agricultural Research Service of U.S. Department of Agriculture has developed a spectral imaging inspection system for identifying wholesome and unwholesome freshly slaughtered chicken carcasses on high-speed commercial chicken processing lines. The spectral imaging inspection system was developed using an electron-multiplying charge-coupled-device (EMCCD) camera. The EMCCD-based cameras can accommodate low-light imaging environments and both hyperspectral and multispectral imaging of rapidly moving targets. Their high quantum efficiencies, rapid frame-transfer mechanisms, and pre-output signal amplification via electron-multiplication also allow significantly improved signal-to-readout-noise ratios. When utilized for line-scan imaging, software controls for an EMCCD camera eliminate the need for the mechanical operation of a shutter and can operate the same camera for either hyperspectral or multispectral imaging without necessitating hardware adjustments. The imaging system inspected over 100,000 chickens on a commercial 140 bpm kill line during continuous operation and achieved over 99% accuracy in identifying wholesome chickens and over 96% accuracy in identifying unwholesome diseased chickens. Use of the line-scan imaging system will help poultry processing plants to improve food safety and production efficiency and satisfy increasing consumer demand for poultry products.

Technical Abstract: An online line-scan imaging system capable of both hyperspectral and multispectral visible/near-infrared reflectance was developed to inspect freshly slaughtered chickens on a processing line for wholesomeness. Hyperspectral images were acquired using the line-scan imaging system for 5549 wholesome chicken carcasses and 93 unwholesome chicken carcasses on a commercial processing line, for analysis to optimize ROI size and location and to determine the key intensity waveband and ratio wavebands to be used for online inspection. Multispectral imaging algorithms were developed for multispectral inspection of over 100,000 chickens on a 140 bpm processing line during two 8-hour shifts at a commercial poultry plant. In-plant testing results indicated that the imaging inspection system can perform successfully on a commercial poultry processing line.