Machine vision system for online inspection of freshly slaughtered chickens

Authors: Yang, Chun Chieh; Chao, Kuanglin - Kevin Chao; Kim, Moon

Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 12/5/2008
Publication Date: 1/30/2009
Citation: Yang, C., Chao, K., Kim, M.S. 2009. Machine vision system for online inspection of freshly slaughtered chickens. Sensing and Instrumentation for Food Quality and Safety. 3(1):70-80.

Interpretive Summary: American chicken plants process over 8.8 billion birds annually, and FSIS/USDA requires that any chickens with infectious condition such as septicemia and toxemia be removed from the processing line. This poses significant pressure on the performance of human inspectors. Poultry processing plants are seeking ways to maintain high food safety standards while increasing their processing speeds and production output in order to satisfy increasing consumer demand for poultry products. For fast, accurate, and efficient online inspection of poultry carcasses, a line-scan automatic machine vision system was successfully developed for online differentiation of systemically diseased chickens from wholesome chickens on a high speed commercial processing line operating at 140 birds per minute. During continuous multispectral inspection for one eight-hour processing shift in a commercial processing plant, the machine vision system identified 0.11% of chicken carcasses as systemically diseased, the same percentage identified by the human inspectors working during the same shift. The fast imaging speed and effective image processing and differentiation algorithm that produced the high accuracy inspection results demonstrated that the line-scan machine vision system was successfully developed and can be effectively used in a commercial processing environment. Use of the system could produce significant benefits for increasing production efficiency and reducing human error for the poultry processing industry. This system demonstrates developments that can be helpful to food scientists and food process engineers in advancing automated inspection technologies for food products in general.

Technical Abstract: A machine vision system was developed and evaluated for the automation of online inspection to differentiate freshly slaughtered wholesome chickens from systemically diseased chickens. The system consisted of an electron-multiplying charge-coupled-device camera used with an imaging spectrograph and controlled by a computer to obtain line-scan images quickly on a chicken processing line of a commercial poultry plant. The system scanned chicken carcasses on an eviscerating line operating at a speed of 140 chickens per minute. An algorithm was implemented in the system to automatically recognize individual carcasses entering and exiting the field of view, to locate the region of interest (ROI) of each chicken, to extract useful spectra from the ROI as inputs to the differentiation method, and to determine the condition for each carcass as being wholesome or systemically diseased. The system can acquire either hyperspectral or multispectral images without any cross-system calibration. The essential spectral features were selected from hyperspectral images of chicken samples. The differentiation of chickens on the processing line was then carried out using multispectral imaging. The high accuracy obtained from the evaluation results showed that the machine vision system can be applied successfully to automatic online inspection for chicken processing.