Classification of oat and groat kernels using NIR hyperspectral imaging

An innovative procedure to classify oat and groat kernels based on coupling hyperspectral imaging (HSI) in the near infrared (NIR) range (1006–1650 nm) and chemometrics was designed, developed and validated. According to market requirements, the amount of groat, that is the hull-less oat kernels, is one of the most important quality characteristics of oats. Hyperspectral images of oat and groat samples have been acquired by using a NIR spectral camera (Specim, Finland) and the resulting data hypercubes were analyzed applying Principal Component Analysis (PCA) for exploratory purposes and Partial Least Squares-Discriminant Analysis (PLS-DA) to build the classification models to discriminate the two kernel typologies. Results showed that it is possible to accurately recognize oat and groat single kernels by HSI (prediction accuracy was almost 100%). The study demonstrated also that good classification results could be obtained using only three wavelengths (1132, 1195 and 1608 nm), selected by means of a bootstrap-VIP procedure, allowing to speed up the classification processing for industrial applications. The developed objective and non-destructive method based on HSI can be utilized for quality control purposes and/or for the definition of innovative sorting logics of oat grains.

► A new method for identification of oat and groat kernels by NIR-HSI was developed.
► The study was applied to improve quality of oat products.
► Different chemometric strategies were applied to the oats spectral data.
► Oat and groat kernels were correctly classified also selecting only 3 wavelengths.
► HSI is a powerful non-destructive technique to extract features from sample surface.