Fusarium head blight (FHB) is among the most common fungal diseases affecting wheat, resulting in decreased yield, low-density kernels, and production of the mycotoxin deoxynivalenol, a compound toxic to humans and livestock. Human visual analysis of representative wheat samples has been the traditional method for FHB assessment in both official inspection and plant breeding operations. While not requiring specialized equipment, visual analysis is dependent on a trained and consistent workforce, such that in the absence of these aspects, biases may arise among inspectors and evaluation dates. This research was intended to avoid such pitfalls by using longer wavelength radiation than the visible using hyperspectral imaging (HSI) on individual kernels. Linear discriminant analysis models to differentiate between sound and scab-damaged kernels were developed based on mean of reflectance values of the interior pixels of each kernel at four wavelengths (1100, 1197, 1308, and 1394 nm). Other input variables were examined, including kernel morphological properties and histogram features from the pixel responses of selected wavelengths of each kernel. The results indicate the strong potential of HSI in estimating fusarium damage. However, improvement in aligning this procedure to visual analysis is hampered by the inherent level of subjectivity in visual analysis. •Near-infrared hyperspectral imaging can identify fusarium-damaged wheat kernels.•Spectral features are more useful than morphological ones at finding kernel damage.•Reflectances at as few as 3–4 wavelengths are sufficient to identify fusarium damage.