Utilisation of visible/near-infrared hyperspectral images to classify aflatoxin B1 contaminated maize kernels

A visible/near-infrared (VNIR) hyperspectral imaging (HSI) system (400-1000 nm) was used to assess the feasibility of detecting aflatoxin B-1 (AFB(1)) on surfaces of 600 kernels of four maize varieties from different regions of the U.S.A. i.e. Georgia, Illinois, Indiana and Nebraska. For each variety, four AFB(1) solutions (10, 20, 100 and 500 ppb) were artificially applied on kernel surfaces. Similarly, a control group was generated from 30 kernels of each variety treated with a solution of methanol. Principal component analysis (PCA) was used to reduce dimensionality of the HSI data followed by the application of factorial discriminant analysis (FDA) on the principal component variables. PCA results showed a pattern of separation between uncontaminated and contaminated kernels for all varieties except for Indiana and pooled samples. FDA showed the ability to predict AFB(1) contamination of each variety with over 96% validation accuracy while prediction for AFB(1) contamination group membership of pooled samples reached 98% accuracy in validation. Variation in the spectra of AFB(1) contaminated kernels could have caused the variation in the predicted AFB(1) contamination group membership. The PCA and FDA models where influenced by the chemical information from C-H, N-H and O-H bonds of VNIR spectral regions. This study presents the potential of using VNIR hyperspectral imaging in direct AFB(1) contamination classification studies of maize kernels of different varieties. The study further suggests that varietal differences of maize kernels may have no influence on AFB(1) contamination classification. (C) 2017 IAgrE. Published by Elsevier Ltd. All rights reserved.