Skip to main content
ARS Home » Research » Publications at this Location » Publication #201027
Title: Real-time multispectral imaging system for online poultry fecal inspection using UML

Author
item Park, Bosoon
item Kise, Michio
item Lawrence, Kurt
item Windham, William
item Smith, Douglas
item THAI, CHI - UGA

Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 10/3/2006
Publication Date: 11/10/2006
Citation: Park, B., Kise, M., Lawrence, K.C., Windham, W.R., Smith, D.P., Thai, C.N. 2006. Real-time multispectral imaging system for online poultry fecal inspection using UML. Proceedings of SPIE. 6381-33

Interpretive Summary: Fecal contaminations are a food safety risk because of correlation between feces and pathogenic bacteria. FSIS is pursuing a broad and long-term science-based strategy to improve the safety of poultry and poultry products to better protect public health. The ARS has developed an imaging system for fecal and ingesta contaminant detection on broiler carcasses. In order to implement real-time imaging system in a harsh environmental poultry processing plant, system design factors for both hardware and software were investigated. Particularly, real-time image processing software was developed for increasing detection accuracy and decreasing errors. The test results of industrial-scale 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: A prototype real-time multispectral imaging system for fecal and ingesta contaminant detection on broiler carcasses was developed and tested. The prototype system includes a common aperture camera with three optical trim filters (517, 565 and 802-nm wavelength), which were selected and validated by a decision tree algorithm. The on-line testing results demonstrated the multispectral imaging technique was effective for detecting feces from various digestive tracts on the surface of broiler carcasses. This study demonstrated performance of both multispectral imaging hardware and software. For the software development, the Unified Modeling Language (UML) design approach was used for on-line application. User interface model included seventeen input parameters and six outputs. A window based real-time image processing software composed of eleven components, which represented class, architecture, and activity. The run-time of the software including online calibration was fast enough to inspect carcasses on-line with an industry requirement. Based on the preliminary test results at the pilot-scale processing plant, the imaging system is reliable for the harsh environments and UML based image processing software was flexible and easy to be updated when additional parameters were needed for in-plant trials.