Skip to main content
ARS Home » Research » Publications at this Location » Publication #253665

Title: Real-time detection of feces on poultry carcasses by A line-scan hyperspectral image camera

item Yoon, Seung-Chul
item Park, Bosoon
item Lawrence, Kurt
item Windham, William
item Heitschmidt, Gerald - Jerry

Submitted to: Near Infrared Spectroscopy International Conference Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 7/28/2010
Publication Date: 4/28/2011
Citation: Yoon, S.C., Park, B., Lawrence, K.C., Windham, W.R., Heitschmidt, G.W. 2011. Real-time detection of feces on poultry carcasses by A line-scan hyperspectral image camera. Near Infrared Spectroscopy International Conference Proceedings. p.1013-1015.

Interpretive Summary: Feces undetected during poultry processing can be a source of pathogens causing foodborne illness. In poultry processing plants, human inspectors examine chicken carcasses to ensure no fecal contaminated birds entering water chillers. In an attempt to develop a science-based fecal detection program, USDA researchers developed an online fecal detection system based on a line-scan hyperspectral imaging platform. The line-scan hyperspectral imaging system was capable of extracting separate wavelength bands defined by the user and running a fecal detection algorithm in real-time (up to 3 birds per second). The fecal detection algorithm was based on dual band ratios of 565nm/517nm and 802nm/517nm followed by thresholding. The application software for the real-time image acquisition and processing was written in C++. Reflectance calibration at each pixel was done on the fly. In this study, twelve chickens were used for testing the speed of the imaging system. Two different processing line speeds (140 birds per minute and 180 birds per minute) were tested in a pilot-scale processing plant. The performance of the fecal detection algorithm was also evaluated. Four types of fecal materials (duodenum, ceca, colon and ingesta) were used for the study. The performance of fecal detection was comparable to what the previous research achieved. The imaging platform showed its potential use in commercial poultry processing lines.

Technical Abstract: N/A