Potential of near-infrared hyperspectral reflectance imaging for screening of farm feed contamination

Wenbo Wang; Jitendra Paliwal

doi:10.1117/12.628232

13 October 2005 Potential of near-infrared hyperspectral reflectance imaging for screening of farm feed contamination

Wenbo Wang, Jitendra Paliwal

Proceedings Volume 5969, Photonic Applications in Biosensing and Imaging; 59692T (2005) https://doi.org/10.1117/12.628232
Event: Photonics North, 2005, Toronto, Canada

Abstract

With the outbreak of Bovine Spongiform Encephalopathy (BSE) (commonly known as mad cow disease) in 1987 in the United Kingdom and a recent case discovered in Alberta, more and more emphasis is placed on food and farm feed quality and safety issues internationally. The disease is believed to be spread through farm feed contamination by animal byproducts in the form of meat-and-bone-meal (MBM). The paper reviewed the available techniques necessary to the enforcement of legislation concerning the feed safety issues. The standard microscopy method, although highly sensitive, is laborious and costly. A method to routinely screen farm feed contamination certainly helps to reduce the complexity of safety inspection. A hyperspectral imaging system working in the near-infrared wavelength region of 1100-1600 nm was used to study the possibility of detection of ground broiler feed contamination by ground pork. Hyperspectral images of raw broiler feed, ground broiler feed, ground pork, and contaminated feed samples were acquired. Raw broiler feed samples were found to possess comparatively large spectral variations due to light scattering effect. Ground feed adulterated with 1%, 3%, 5%, and 10% of ground pork was tested to identify feed contamination. Discriminant analysis using Mahalanobis distance showed that the model trained using pure ground feed samples and pure ground pork samples resulted in 100% false negative errors for all test replicates of contaminated samples. A discriminant model trained with pure ground feed samples and 10% contamination level samples resulted in 12.5% false positive error and 0% false negative error.

Citation Download Citation

Wenbo Wang and Jitendra Paliwal "Potential of near-infrared hyperspectral reflectance imaging for screening of farm feed contamination", Proc. SPIE 5969, Photonic Applications in Biosensing and Imaging, 59692T (13 October 2005); https://doi.org/10.1117/12.628232

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available