|Chao, Kuanglin - Kevin Chao|
|Yang, Chun Chieh|
|Delwiche, Stephen - Steve|
Submitted to: Symposium Proceedings
Publication Type: Proceedings
Publication Acceptance Date: 7/20/2010
Publication Date: 7/20/2010
Citation: Kim, M.S., Chao, K., Chan, D.E., Yang, C., Lefcourt, A.M., Delwiche, S.R. 2010. Hyperspectral Imaging Technologies for Nondestructive Agro-Food Evaluation. International Symposium on New Sensing Technology for Measuring Agro-Food Quality Proceedings. p. 57-71.
Interpretive Summary: During the last decade, researchers of the United States Department of Agriculture, Agricultural Research Service, have developed line-scan-based hyperspectral imaging systems for visible/near-infrared reflectance and visible fluorescence imaging for agrofood samples. The hyperspectral imaging techniques used have served both as laboratory research tools to develop imaging inspection methods for food products and as platforms for implementing and performing rapid online multispectral imaging inspection of food products. Keeping in mind rising public awareness of foodborne illnesses and food safety risks associated with widely-distributed fresh food products, the development of image-based sensing methodologies and technologies targets food safety risk reduction in the form of practical methods suitable for producers/processors to use in addressing food safety and quality concerns in commercial processing operations. This paper presents the recent developments for (1) online line-scan hyperspectral imaging systems to inspect fresh chicken carcasses for wholesomeness, and (2) multitask line-scan hyperspectral imaging methodologies to simultaneously detect fecal contamination and defects on apples. Information presented in this paper is useful to food processing scientists, engineers, regulatory government agencies, and food processing industries.
Technical Abstract: Over the past decade, researchers at the Agricultural Research Service (ARS), United States Department of Agriculture (USDA), 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 agro-foods. 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 in recent years have included the development of automated online poultry inspection systems for detecting pathophysiological abnormalities in poultry, with the goal of commercial implementation as part of existing or new poultry processing systems; and image-based, rapid online inspection techniques for simultaneous detection of fecal contamination and defects on fruits and vegetables. Here we present recent development of line-scan hyperspectral imaging technologies for online apple and poultry inspection