E-Eye Solution for the Discrimination of Common and Niche Celery Ecotypes

Celery (Apium graveolens L.) is a well- known plant and at the basis of culinary tradition different populations. In Italy, several celery ecotypes, presenting unique peculiarities, are grown by small local producers, they need to be characterized, in order protected safeguarded. The present work aims developing fast non-destructive method for discrimination common (the "Elne" celery) from typical Abruzzo (Central Italy). proposed strategy based on use an e-eye tool which allows collection images used infer colorgrams. Initially, principal component analysis model was investigate trends outliers data. Then, classification between (Elne class) Torricella Peligna (Torricella achieved discriminant analysis, conducted sequential preprocessing through orthogonalization (SPORT) orthogonalized covariance selection (SO-CovSel) class-modelling called soft independent modelling class analogies (SIMCAs). Among these, highest accuracy provided strategies, classifiers, both total 82% external validation.