Detection of scab-damaged hard red spring wheat kernels by near-infrared reflectance

Scab (Fusarium head blight) is a fungal disease that has become increasingly prevalent in North American wheat during the past 15 years. It is of concern to growers, processors, and the consumers because of depressed yields, poor flour quality, and the potential for elevated concentrations of the mycotoxin, deoxynivalenol (DON). Both wheat breeder and wheat inspector must currently deal with the assessment of scab in harvested wheat by manual human inspection. The study described herein examined the accuracy of a semi-automated wheat scab inspection system that is based on near-infrared (NIR) reflectance (1,0001,700 nm) of individual kernels. Using statistical classification techniques such as linear discriminant analysis and nonparametric (k-nearest-neighbor) classification, upper limits of accuracy for NIR-based classification schemes of approximate to 88% (cross-validation) and 97% (test) were determined. An exhaustive search of the most suitable wavelength pairs for the spectral difference, [log(1/R)(lambda1) - log(1/R)(lambda2)], revealed that the slope of the low-wavelength side of a broad carbohydrate absorption band (centered at approximate to 1,200 nm) was very effective at discriminating between healthy and scab-damaged kernels with test set accuracies of 95%. The achieved accuracy levels demonstrate the potential for the use of NIR spectroscopy in commercial sorting and inspection operations for wheat scab.