No abstract

Short wave infrared hyperspectral imaging (SWIR) (1000-2500 nm) was used to detect aflatoxin B 1 (AFB 1) in single maize kernels. One hundred and twenty kernels of four varieties artificially inoculated with a toxigenic strain of Aspergillus flavus in the field were examined. Normalisation and principal component analysis (PCA) were applied on average spectra of each kernel to reduce dimensionality and noise. Combining with support vector machine (SVM) classification methods, the first five principal components (PCs) were used to qualitatively classify the AFB 1 contamination levels (<20 ppb, 20-100 ppb, ≥100 ppb) in single kernels without effect of maize variety. Classification accuracies were 83.75% and 82.50% for calibration and validation set, respectively. It was also noted that a general correlation exists between categorical AFB 1 content and the first three PCs. Coefficients of determination (R 2) of the support vector machine regression model were 0.77 and 0.70 for calibration and validation set separately. A possible distribution map of AFB 1 was also made by applying the regression model on every pixel of the hyperspectral image. Moreover, using loading plots of the mutual first three PCs, five wavelengths (1317, 1459, 1865, 1934 and 2274 nm) were selected as characteristic wavelengths. Results indicated that hyperspectral imaging could be used to classify AFB 1 level qualitatively in individual maize kernels, however

No abstract

No abstract

The feasibility of using a visible/near-infrared hyperspectral imaging system with a wavelength range between 400 and 1000 nm to detect and differentiate different levels of aflatoxin B1 (AFB1 ) artificially titrated on maize kernel surface was examined. To reduce the color effects of maize kernels, image analysis was limited to a subset of original spectra (600 to 1000 nm). Residual staining from the AFB1 on the kernels surface was selected as regions of interest for analysis. Principal components analysis (PCA) was applied to reduce the dimensionality of hyperspectral image data, and then a stepwise factorial discriminant analysis (FDA) was performed on latent PCA variables. The results indicated that discriminant factors F2 can be used to separate control samples from all of the other groups of kernels with AFB1 inoculated, whereas the discriminant factors F1 can be used to identify maize kernels with levels of AFB1 as low as 10 ppb. An overall classification accuracy of 98% was achieved. Finally, the peaks of β coefficients of the discrimination factors F1 and F2 were analyzed and several key wavelengths identified for differentiating maize kernels with and without AFB1 , as well as those with differing levels of AFB1 inoculation. Results indicated that Vis/NIR hyperspectral imaging technology combined with the PCA-FDA was a practical method to detect and differentiate different levels of AFB1 artificially inoculated on the maize kernels surface. However, indicated the potential to detect and differentiate naturally occurring toxins in maize kernel.