Discrimination of gluten-free oats from contaminants using near infrared hyperspectral imaging technique

Abstract

Oat is considered as a good addition to the gluten-free diet, but it is a challenge to keep the oats segregated from other gluten-rich grains, such as wheat, barley, and rye. Therefore, oat-processing industry demands better detection tools for identifying and screening oat grain. The research goal of this study was to investigate the potential of near infrared (NIR) hyperspectral imaging for non-destructive and accurate discrimination of oats from barley, wheat, and rye. A procedure was developed to classify six grains (oat, dehulled oat, barley, dehulled barley, wheat and rye) using NIR hyperspectral imaging in the wavelength range of 900–1700 nm coupled with multivariate data analysis. The reflectance spectra were analyzed using Principal Component Analysis (unsupervised) and Partial Least Squares Discriminant Analysis (supervised) classification models to discriminate single oat kernels. Good results of dehulled oats grain prediction (99%) were achieved using only few selected key wavelengths (1069, 1126, 1189, 1243, and 1413 nm). Our results establish that NIR hyperspectral imaging has potential for application in on-line oat grain quality control and inspection at the different stages of industrial processing.