Skip to main content
ARS Home » Research » Publications at this Location » Publication #258909
Title: Vis/NIR line-scan hyperspectral imaging techniques for food safety and quality inspection

Author
item Kim, Moon
item Chao, Kuanglin - Kevin Chao
item Yang, Chun Chieh
item Lefcourt, Alan
item Chan, Diane

Submitted to: Meeting Abstract
Publication Type: Abstract Only
Publication Acceptance Date: 11/18/2010
Publication Date: 11/18/2010
Citation: Kim, M.S., Chao, K., Yang, C., Lefcourt, A.M., Chan, D.E. 2010. Vis/NIR line-scan hyperspectral imaging techniques for food safety and quality inspection. Meeting Abstract.

Interpretive Summary:

Technical Abstract: The great utility of spectral line-scan hyperspectral imaging platforms for visible to near-infrared reflectance and fluorescence has been demonstrated for development and implementation of methods and techniques for a broad range of food safety and quality issues, and including the use of multispectral platforms for automated inspection of agro-foods on high-throughput commercial processing lines. Major areas of research focus have included the development of automated inspection techniques for both fresh poultry and for fruits and vegetables. Automated online poultry inspection systems have been developed for detecting unwholesome poultry carcasses, with the goal of commercial implementation as part of existing or new poultry processing systems. An online line-scan imaging system capable of both hyperspectral and multispectral reflectance imaging was developed to inspect freshly slaughtered chickens for wholesomeness on high-speed processing lines operating at 140 birds per minute, and is now undergoing commercialization for use as part of existing or new poultry processing systems in the industry. For the fresh produce industry, inspection systems must be able to effectively address multiple inspection tasks to be considered truly practical for commercial use. A line-scan spectral imaging system was specifically developed to simultaneously capture fluorescence and NIR and reflectance images and has been tested for apple imaging applied to a combination of safety and quality inspection tasks on a commercial apple sorter operating at speeds just over 3 apples per second. The development of image-based, rapid online imaging technologies for multitask inspection, such as for simultaneous detection fecal contamination and quality defects on fresh produce, will be of great benefit to the industry which has become extremely sensitive to consumer awareness and fear of safety and quality issues. We envision that the line-scan hyperspectral imaging technologies can deliver concurrent safety and quality inspection for a variety of agricultural products on high-throughput processing lines. The ARS line-scan hyperspectral imaging technologies and their applications for online agro-food inspection are presented.