Skip to main content
ARS Home » Research » Publications at this Location » Publication #195958


item Chen, Yud
item Kim, Moon

Submitted to: Computers and Electronics in Agriculture
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/9/2007
Publication Date: 8/1/2007
Citation: Cho, B., Chen, Y.R., Kim, M.S. 2007. Multispectral detection of organic residues on poultry processing plant equipment based on hyperspectral reflectance imaging technique. Computers and Electronics in Agriculture. 57(2):177-189.

Interpretive Summary: The importance of safe and secure production of foods has been increasingly recognized in the current mass production environment of the meat industry. Food-related illnesses are mainly caused by bacteria, which are often transmitted through fecal matter and ingesta on meat and poultry. During poultry processing operations, eviscerated chicken carcasses and processing equipment can be contaminated with ingesta from the stomach (proventriculus/gizzard), and with feces from the intestines, through incidental ruptures of the digestive tract of poultry carcasses. These contaminants may contain human pathogens and can cause cross-contamination of subsequent carcasses on the processing line. Sanitation monitoring for equipment surfaces during and after processing is also needed to reduce cross-contamination to comply with zero tolerance of contaminant-free production. In this paper, multispectral reflectance imaging techniques are shown to be able to accurately detect diluted poultry residues, specifically feces and ingesta, and other product residues, such as blood, skin, meat, fat, and smeared fluids from poultry skin, on poultry processing equipment surfaces. The optimal wavebands and classification algorithms to detect and discriminate between diluted residues in wet and dry conditions on the surface of poultry processing equipment are reported. These findings can be used for developing low-cost and wearable/portable multispectral imaging devices for sanitation monitoring of processing equipment in poultry processing plants. This information is very useful for researchers, engineers, regulatory agencies, and processors that are interested in inspection devices or systems for effectively monitoring poultry processing plant sanitation.

Technical Abstract: Diluted organic residues, such as feces, ingesta and other biological substances on poultry processing plant equipment surfaces, not easily discernible by human eye, are potential contamination sources for poultry carcasses. Development of sensitive detection methods for diluted organic residues is essential to ensure safe production of poultry carcasses. Hyperspectral imaging techniques have shown good potential for detecting the presence of fecal and other biological contaminants on food and processing equipment surfaces. In this study, the use of high spatial resolution hyperspectral reflectance is presented as a tool for selecting a few multispectral bands to detect diluted organic residues on the surface of materials used for manufacturing processing equipment. Reflectance imaging methods were explored for use in the detection of a range of diluted organic residues for both wet and dry conditions. Results showed that low concentrations of wet and dry residues, diluted up to 1:100 by weight with double distilled water, could be detected with accuracies of 94.0% and 99.7%, respectively. Spectral bands determined in this study could be used for developing a multispectral inspection system for sanitation monitoring of poultry processing plants.