The application of the Kohonen neural network in the non-parametric quality-based classification of tomatoes

By using the classification properties of Kohonen-type networks (Tipping 1996), a neural model was built for the quality-based identification of tomatoes. The resulting empirical data in the form of digital images of tomatoes at various stages of storage were subsequently used to draw up a topological SOFM (Self-Organizing Feature Map) which features cluster centers of "comparable" cases (Tadeusiewicz 1997, Boniecki 2008). Radial neurons from the Kohonen topological map were labeled appropriately to allow for the practical quality-based classification of tomatoes (De Grano 2007).