Skip to main content
ARS Home » Research » Publications at this Location » Publication #238440

Title: Line-scan imaging for improved high-speed food safety inspection

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

Submitted to: Popular Publication
Publication Type: Popular Publication
Publication Acceptance Date: 3/27/2009
Publication Date: 4/1/2009
Citation: Kim, M.S., Chao, K., Chan, D.E., Lefcourt, A.M. 2009. Line-scan imaging for improved high-speed food safety inspection. SPIE News Room Article, 10.1117/2.1200903.1564.

Interpretive Summary: Chemical/biological food properties can often be assessed by spectroscopic methods. While machine vision is already ubiquitous for sorting for physical attributes, new spectral imaging technologies can deliver high-speed online safety and quality inspection of food and agricultural products on high-throughput processing lines. ARS scientists have developed a new line-scan hyperspectral imaging platform for high-speed inspection on commercial processing lines, capable of simultaneous multiple inspection algorithms for different safety and quality problems. 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. The presented line-scan spectral imaging technologies are useful to food processing scientists, engineers, regulatory government agencies, and food processing industries.

Technical Abstract: New spectral imaging technologies can deliver high-speed online safety and quality inspection of food and agricultural products on high-throughput processing lines. Spectral imaging techniques have been developed to combine the advantages of spectroscopy and machine vision in addressing food quality and safety problems. Hyperspectral imaging methods provide full spectrum data—often hundreds of spectral data points—for every pixel in the image of a food product, enabling spectral and spatial analysis for correlation to composition, contaminants, and physical attributes such as size and shape. Due to speed restrictions, hyperspectral imaging has often been used as a research tool to develop rapid multispectral methods based on only a few spectral data points for online applications. We have developed a new line-scan hyperspectral imaging platform for high-speed inspection on commercial processing lines, capable of simultaneous multiple inspection algorithms to address different safety and quality problems.