Submitted to: Handbook of Poultry Science and Technology
Publication Type: Book / Chapter
Publication Acceptance Date: September 7, 2008
Publication Date: August 1, 2009
Citation: Chao, K. 2009. Online inspection. In: Guerrero-Legarreta, I., Hui, Y.H., editors. Handbook of Poultry Science and Technology, Vol. 1, Primary Processing. Hoboken, NJ: Wiley-Blackwell. p 683-701. Interpretive Summary: With over 8.8 billion broilers processed yearly, the U.S. poultry industry faces the challenge of satisfying an ever-increasing demand for poultry products while maintaining operations to provide safe and wholesome products. The ARS Food Safety Laboratory in Beltsville has developed an automated online chicken inspection system for high-speed spectral imaging on chicken processing lines. Using an electron-multiplying charge-coupled device detector and line-scan spectrograph with multispectral algorithms developed for real-time imaging, the system successfully demonstrated identification of wholesome and unwholesome (systemically diseased) freshly slaughtered chicken carcasses on high-speed commercial chicken processing lines operating at a speed of 140 birds per minute. The imaging system inspected over 100,000 chickens during continuous operation and achieved over 99% accuracy in identifying wholesome chickens and over 96% accuracy in identifying unwholesome chickens. A system of this type can perform food safety inspection tasks accurately and with less variation in performance at high speeds, and help poultry plants to improve 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 imaging was developed to inspect freshly slaughtered chickens on a processing line for wholesomeness. In-plant testing results indicated that the imaging inspection system achieved over 99% accuracy in identifying wholesome chickens and over 96% accuracy in identifying unwholesome diseased chickens. With appropriate methods of hyperspectral analysis and algorithms for online image processing, a machine vision system utilizing an EMCCD camera for multispectral inspection can satisfy both the food safety performance standards and the high-speed production requirements (i.e., at least 140 bpm) of commercial chicken processing. Use of the imaging system may also help to improve product safety by preventing most unwholesome birds from entering the evisceration line, thus lowering the risk of cross-contamination. In addition, use of the system can help reduce the routine workload imposed upon FSIS inspectors working in HIMP processing plants, allowing them opportunities to perform more meaningful tasks for ensuring the safety of poultry products and addressing related public health concerns.