Hyperspectral and Multispectral Imaging Technique for Food Quality and Safety Evaluation

Authors: Kim, Moon; Chao, Kuanglin - Kevin Chao; Chan, Diane; Yang, Chun Chieh; Lefcourt, Alan; Delwiche, Stephen - Steve

Submitted to: Emerging Technologies for Food Quality and Food Safety Inspection
Publication Type: Book / Chapter
Publication Acceptance Date: 8/10/2010
Publication Date: 2/15/2011
Citation: Kim, M.S., Chao, K., Chan, D.E., Yang, C., Lefcourt, A.M., Delwiche, S.R. 2011. Hyperspectral and multispectral imaging technique for food quality and safety evaluation. In: Cho, Y., Kang, S. editors. Emerging Technologies for Food Quality and Food Safety Inspection. New York, N.Y.: CRC Press. p. 207-234.

Interpretive Summary: Our research goals have been to develop image-based sensing methodologies and technologies to address food quality issues and safety concerns for food production and to aid in reducing food safety risks in food processing. Major research areas have included the development of automated online poultry inspection systems for detecting unwholesome poultry carcasses, with the goal of commercial implementation as part of existing or new poultry processing systems; and image-based, rapid online techniques for simultaneous detection of fecal contamination and defects on fruits and vegetables. Researchers at ARS have developed several versions of line-scan-based hyperspectral imaging systems capable of both visible to near-infrared reflectance and fluorescence methods. These line-scan hyperspectral imaging techniques have served dual purposes, as both basic laboratory-based research tools and online multispectral platforms to perform rapid inspection of poultry carcasses and apples. During in-plant testing, the system inspected over 100,000 chickens on a 140 bird per minute processing line and accurately identified over 99% of wholesome chickens and over 96% of unwholesome chickens. To be of practical benefit, an effective product screening system must be able to address multiple inspection tasks. An enhanced line-scan spectral imaging system was specifically developed to simultaneously address a combination of safety and quality inspection tasks (multitasking) for apples on a commercial sorter operating at 3-4 apples per second. We envision that the line-scan spectral imaging technologies can deliver concurrent safety and quality inspection for a variety of agricultural products on high-throughput processing lines. Information presented in this paper is useful to food processing scientists, engineers, regulatory government agencies, and food processing industries.

Technical Abstract: In this chapter, recently developed ARS line-scan hyperspectral-based sensing technologies to address agro-food safety concerns are presented including a case study using the laboratory-based hyperspectral imaging platforms. An online line-scan imaging system capable of both hyperspectral and multispectral reflectance imaging was developed to inspect freshly slaughtered chickens on a high-speed processing line for wholesomeness. During continuous in-plant operation in automated multispectral imaging inspection mode, the system inspected over 100,000 chickens on a 140 bird per minute processing line and accurately identified over 99% of wholesome chickens and over 96% of unwholesome chickens. To be of practical benefit, an effective product screening system must be able to address multiple inspection tasks. A line-scan spectral imaging system was specifically developed to simultaneously capture NIR reflectance and fluorescence, and was applied to address a combination of safety and quality inspection tasks (multitasking) for apples on a commercial sorter operating at 3-4 apples per second. We envision that the line-scan spectral imaging technologies can deliver concurrent safety and quality inspection for a variety of agricultural products on high-throughput processing lines. Further research is being conducted to develop inspection systems suitable for commercial processing of other fresh produce such as leafy greens. Effective detection of contamination by fecal matter, for example, is important due to their association with common bacterial causes of foodborne illness. Adaptable to a broad range of problems and commodities, the line-scan hyperspectral imaging platform will be critically useful for both research and commercial food safety and quality inspection applications.