E-Eye-Based Approach for Traceability and Annuality Compliance of Lentils

In recent years, thanks to their numerous nutritional benefits, legumes have been rediscovered and attracted interest from many consumers. However, these products, the most valuable ones traditionally produced in smaller communities particular, can be objects of fraud; this is case Italian lentils, which, being a dry product, fairly long shelf life, but, due minimal visual changes that affect them, it possible expired lentils may sold alongside edible ones. The present work aims at creating non-destructive method for classifying according harvest year origin, discriminating between order achieve goal, Red-Green-Blue (RGB) imaging, which could considered as sort e-eye represents cutting-edge, rapid, effective analytical method, was used combination with discriminant classifier (Sequential Preprocessing through ORThogonalization-Linear Discriminant Analysis, SPORT-LDA) create novel testing models. SPORT-LDA models built discriminate different geographical origins provided an average correct classification rate on test set about 88%, whereas overall 90% accuracy obtained (on samples) by model recognize whether sample still within its expiry date or not.