Near-infrared hyperspectral imaging for identification of aflatoxin contamination on corn kernels

Authors: TAO, FEIFEI - Mississippi State University; YAO, HAIBO - Mississippi State University; HRUSKA, ZUZANA - Mississippi State University; KINCAID, RUSSEL - Mississippi State University; Rajasekaran, Kanniah - Rajah

Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 12/18/2020
Publication Date: 4/12/2021
Citation: Tao, F., Yao, H., Hruska, Z., Kincaid, R., Rajasekaran, K. 2021. Near-infrared hyperspectral imaging for identification of aflatoxin contamination on corn kernels. Proceedings of SPIE Vol. 11754, Sensing for Agriculture and Food Quality and Safety XIII, 1175408. https://doi.org/10.1117/12.2591078.
DOI: https://doi.org/10.1117/12.2591078

Interpretive Summary:

Technical Abstract: The potential for identification of aflatoxin contamination on corn kernels through near-infrared hyperspectral imaging over the spectral range of 900 - 2500 nm was investigated. Six hundred kernels were used for 3 treatments at 200 kernels each: 1) inoculated with the AF13 fungus (aflatoxigenic); 2) inoculated with the AF36 fungus (non-aflatoxigenic); and 3) inoculated with sterile distilled water as control. One hundred kernels from each treatment were subjected to incubation at 30 °C for 5 and 8 days, separately, and then the kernels were dried and surface wiped to remove exterior signs of mold prior to imaging. The mean spectra including mean reflectance and absorbance, and the textural features consisting of contrast, correlation, energy and homogeneity, were extracted separately from the endosperm regions of single kernels. The partial least-squares discriminant analysis (PLS-DA) models were established using extracted mean spectra or textural features as individual inputs. The full spectral PLS-DA modeling results indicate that the mean spectra including both reflectance and absorbance spectra performed significantly better than using the textural features in identifying aflatoxin contamination on corn kernels. Using the mean reflectance and absorbance spectra between 925 and 2484 nm, the full spectral PLS-DA models achieved mean overall prediction accuracies of 88.3% and 86.3% when taking 20 ppb as the classification threshold. The corresponding means of overall prediction accuracies were 85.5% and 85.6% when the classification threshold of 100 ppb was applied. The extracted textural features of contrast, correlation, energy and homogeneity were not found to be useful in identifying aflatoxin contamination.