Arabica coffee beans have twice the value, or more, compared to Robusta beans, and consequently are susceptible to substitution. In this study, MSI was applied to discriminate roasted Arabica and Robusta coffee beans and perform a quantitative prediction of Arabica coffee bean adulteration with Robusta. Using selected spectral and morphological features from individual coffee beans, and applying an OPLS-DA (orthogonal partial least squares discriminant analysis) model, a 100% correct classification of the two coffee species in the test dataset was achieved. In addition, the OPLS regression model was able to successfully predict the level of adulteration of Arabica with Robusta.
Read the full open access paper