Skip to main content
ARS Home » Southeast Area » Athens, Georgia » U.S. National Poultry Research Center » Quality and Safety Assessment Research Unit » Research » Publications at this Location » Publication #377133
Research Project: Develop Rapid Optical Detection Methods for Food Hazards

Location: Quality and Safety Assessment Research Unit

Title: A SWIR hyperspectral imaging method for classifying Aflatoxin B1 contaminated maize kernels

Author
item KIMULI, DANIEL - China Agricultural University
item Lawrence, Kurt
item Yoon, Seung-Chul
item WANG, WEI - China Agricultural University
item Heitschmidt, Gerald - Jerry
item ZHAO, XIN - China Agricultural University

Submitted to: ASABE Annual International Meeting
Publication Type: Proceedings
Publication Acceptance Date: 6/7/2017
Publication Date: 7/27/2017
Citation: Kimuli, D., Lawrence, K.C., Yoon, S.C., Wang, W., Heitschmidt, G.W., Zhao, X. 2017. A SWIR hyperspectral imaging method for classifying Aflatoxin B1 contaminated maize kernels. ASABE Annual International Meeting. Paper No. 1700764.
DOI: https://doi.org/10.13031/aim.201700764

Interpretive Summary: Maize is one of the major agronomically important cereals grown worldwide. However, in the field and during post-harvest storage, maize is susceptible to infection by toxigenic fungi. The fungal infections diminish the qualitative and nutritive value of grains because of contamination with secondary metabolites such as mycotoxins, which are toxic to both livestock and humans. The current study demonstrated the potential of short wave-infrared (SWIR) hyperspectral imaging using principal component analysis and Mahalanobis distance classification. The study found that the model could identify directly coated pure AFB1 concentrations as low as 10 ppb on maize kernels.

Technical Abstract: A short wave-infrared (SWIR) hyperspectral imaging system (1000-2500 nm) was used to assess the feasibility of detecting aflatoxin B1 (AFB1) on surfaces of 150 kernels of yellow dent maize variety from Indiana State of the U.S.A. Four AFB1 solutions i.e. 10, 20, 100 and 500 ppb were artificially applied on kernel surfaces. Similarly, a control group was generated from 30 kernels treated with a solution of methanol. Principal component analysis (PCA) was used to reduce dimensionality of the HSI data followed by the application of Mahalanobis distance classifier on the regions of interest (ROI) classes. It was possible to find clusters representing non-contaminated and contaminated maize kernels by interactively tracing clusters in the score plot of the 11th and 12th principal components and projecting the results on the score image space. Mahalanobis distance classifier could not only identify aflatoxin contaminated from non-contaminated, but also discriminate between the concentrations applied to kernels. Chemical interpretation of the loading line plots showed key spectral bands such as 1146, 1729, 2274 and 2344 nm which contribute the most to the observed differences. The study suggests that hyperspectral imaging technique accompanied by the PCA-Mahalanobis distance classifier can be used to identify directly coated pure AFB1 concentrations as low as 10 ppb on maize kernels.