Skip to main content
ARS Home » Research » Publications at this Location » Publication #190423


item Park, Bosoon
item Lawrence, Kurt
item Windham, William
item Snead, Matthew

Submitted to: International Society for Optical Engineering
Publication Type: Proceedings
Publication Acceptance Date: 3/1/2006
Publication Date: 8/8/2006
Citation: Park, B., Lawrence, K.C., Windham, W.R., Snead, M.P. 2006. Real-time multispectral imaging application for poultry safety inspection. International Society for Optical Engineering. 6070-7:1-10.

Interpretive Summary: For science-based poultry inspection system, the ARS imaging research group in Athens, Georgia has developed a real-time multispectral imaging system for fecal and ingesta contaminant detection on broiler carcasses for poultry industry. The industrial-scale system was able to calibrate imaging hardware and acquire and process images in real-time using a common aperture camera with three visible wavelength optical filters. The in-house image processing software was applicable for real-time image processing and analysis at pilot-scale imaging line. The test results of industrial-sacle real-time system demonstrated that the multispectral imaging technique was able to detect fecal contaminants with a commercial processing speed (currently 140 birds per minute). This industrial-scale imaging system can improve the FSIS poultry safety inspection program by incorporating scientific testing and efficacy of fecal detection during poultry processing.

Technical Abstract: Industrial-scale multispectral imaging system with real-time image processing software for on-line detection of poultry fecal and ingesta contaminants was developed. The software using Unified Modeling Language (UML) design approach was effective to develop real-time image processing software for on-line application. The UML models including class, object, activity, sequence, and collaboration diagram were developed. A window based real-time image processing software was consist twelve components, which represented classes and architectures. Based on the test at the pilot-scale poultry processing plant, the run-time of the software was fast enough to inspect carcasses on-line with 140 birds per minute. The imaging system was able to acquire high quality poultry images in real-time. The temperature increase inside enclosure was allowable (only 4 degree above ambient temperature) for long time operation in harsh environments. According to preliminary tests, the accuracy for fecal and ingesta contaminant detection was approximately 96%. Thus, the imaging system was reliable for in-plant trials.