Submitted to: Sensing and Instrumentation for Food Quality and Safety
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 5/7/2011
Publication Date: 5/27/2011
Citation: Delwiche, S.R., Kim, M.S., Dong, Y. 2011. Fusarium damage assessment in wheat kernels by Vis/NIR hyperspectral imaging. Sensing and Instrumentation for Food Quality and Safety. 5:63-71.
Interpretive Summary: The most common fungal disease of pre-harvest wheat is Fusarium Head Blight. Affecting kernels during development, the disease results in wheat that is poor in milling and baking quality. The fungus also produces a mycotoxin called deoxynivalenol (DON) that is toxic to humans and livestock and consequently under regulation worldwide. Chemical assay procedures exist for DON, but these are time consuming and expensive. As an alternative, a nonchemical system was developed that can rapidly evaluate kernels for evidence of mold damage. It is based on a combination of near-infrared spectroscopy and digital imaging. When applied to a limited set of hard wheat, this system successfully identified Fusarium-damaged kernels at accuracies exceeding 95 percent. The technology has immediate application to quality grading in inspection operations and, with scale up, application to commercial storage and milling operations.
Technical Abstract: Fusarium head blight is a fungal disease that affects the world's small grains, such as wheat and barley. Attacking the spikelets during development, the fungus causes a reduction of yield and grain of poorer processing quality. Secondary metabolites that often accompany the fungus, such as deoxynivalenol (DON), are health concerns to humans and livestock. Conventional grain inspection procedures for Fusarium damage are heavily reliant on human visual analysis. As an inspection alternative, a near-infrared (NIR) hyperspectral image system (1000-1700 nm) was fabricated and applied to Fusarium-damaged kernel recognition. An existing extended visible (400-1000 nm) system was similarly used. Exhaustive searches were performed on the 144 and 125 wavelength pair images that respectively comprised the NIR and visible systems to determine accuracy of classification using a linear discriminant analysis classifier. On a limited set of wheat samples the best wavelength pairs, either with visible or NIR wavelengths, were able to discriminate Fusarium-damaged kernels from sound kernels, both based on visual assessment, at an average accuracy of approximately 95%. Accuracy dropped off substantially when the visual contrast between the two kernel conditions became imperceptible. The NIR region was slightly better than the visible region in its broader array of acceptable wavelength pairs. Further, the region of interest (ROI) defined as the whole kernel was slightly better than ROIs limited to either a portion of the endosperm or the germ tip. For the NIR region, the spectral absorption near 1200 nm, attributed to ergosterol (a primary constituent in fungi cell membranes), was shown to be useful in spectral recognition of Fusarium damage.