Page Banner

United States Department of Agriculture

Agricultural Research Service

Title: Comparison of Visible and Near Infrared Reflectance Spectroscopy for the Detection of Faeces/ingesta Contaminants for Sanitation Verification at Slaughter Plants

Authors
item Liu, Yongliang - VISITING SCI., UNIV KY
item Chao, Kuanglin
item Chen, Yud
item Kim, Moon
item Nou, Xiangwu
item Chan, Diane
item Yang, Chun-Chieh - VISITING SCI., UNIV KY

Submitted to: Near Infrared Spectroscopy Journal
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: August 29, 2006
Publication Date: November 20, 2006
Citation: Liu, Y.D., Chao, K., Chen, Y.R., Kim, M.S., Nou, X., Chan, D.E., Yang, C. 2006. Comparison of visible and near infrared reflectance spectroscopy for the detection of faeces/ingesta contaminants for sanitation verification at slaughter plants. Near Infrared Spectroscopy Journal. 14:325-331.

Interpretive Summary: To be assured of wholesome and safe meat supply to the consumers, the USDA’s Food Safety Inspection Service (FSIS) has also adopted the Pathogen Reduction, Hazard Analysis and Critical Control Points (HACCP) systems, which require all meat and poultry plants to develop written sanitation standard operating procedures to show how they will meet daily sanitation requirements. This is important in reducing pathogens on poultry, because unsanitary practices in plants increase the likelihood of product cross contamination. Currently, FSIS inspectors use the established guidelines to identify fecal remains, the most likely source of pathogenic contamination, at surfaces of equipment, utensils, and walls at slaughter plants. Certainly, the verification is both labor intensive and prone to both human error and inspector-to-inspector variation. Therefore, researchers at the USDA Agricultural Research Service have been developing hyper- and multi- spectral reflectance and fluorescence imaging techniques for the use in real-time on-line detection of fecal spots on chicken carcasses. Hopefully, these imaging systems can evolve into low-cost, reliable, and portable sensing devices, such as head-wear goggles and binoculars. One key factor in the successful applications is to have a few essential spectral bands, which not only reflect the chemical / physical information in the samples, but also maintain the successive discrimination and classification efficiency. Here, we first determined the characteristic bands in the visible and NIR regions for a set of chicken feces and ingesta samples as well as control ones (rubber belt and stainless steel), then we developed a number of algorithms to classify chicken feces / ingesta (“F/I”), as objectives, from rubber belt / stainless steel (“RB/SS”), as backgrounds. Meanwhile, both principal component analysis (PCA) and 2-class SIMCA (soft independent modeling of class analogy) models were used to examine the effectiveness of separation and classification. Results indicated that using ratio algorithms in the visible or NIR region could separate “F/I” objectives from “RB/SS” backgrounds with a success of over 97%. This result provides agricultural engineers and researchers a new sight in applying both visible/NIR and imaging spectroscopy for sanitation verification and poultry safety at processing plant.

Technical Abstract: Visible and NIR spectra were acquired to explore the potential for the discrimination of feces/ingesta (“F/I”) objectives from rubber belt and stainless steel (“RB/SS”) backgrounds by using several wavelengths. Spectral features of “F/I” objectives and “RB/SS” backgrounds showed large differences in both visible and NIR regions, due to the diversity of their chemical compositions. These spectral distinctions formed the basis on which to develop simple three-band ratio algorithms for the classification analysis. Meanwhile, score-score plots from principal component analysis (PCA) indicated the obvious cluster separation between “F/I” objectives and “RB/SS” backgrounds, but the corresponding loadings did not show any specific wavelengths for developing effective algorithms. Furthermore, 2-class soft independent modeling of class analogy (SIMCA) models were developed to compare the correct classifications with those from the ratio algorithms. Results indicated that using ratio algorithms in the visible or NIR region could separate “F/I” objectives from “RB/SS” backgrounds with a success rate of over 97%.

Last Modified: 8/29/2014
Footer Content Back to Top of Page