8 June 2012 The application of the Kohonen neural network in the nonparametric-quality-based classification of tomatoes
Author Affiliations +
Proceedings Volume 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012); 833427 (2012) https://doi.org/10.1117/12.954158
Event: Fourth International Conference on Digital Image Processing (ICDIP 2012), 2012, Kuala Lumpur, Malaysia
Abstract
By using the classification properties of Kohonen-type networks (Tipping 1996), a neural model was built for the qualitybased 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).
© (2012) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
P. Boniecki, K. Nowakowski, R. Tomczak, S. Kujawa, H. Piekarska-Boniecka, "The application of the Kohonen neural network in the nonparametric-quality-based classification of tomatoes", Proc. SPIE 8334, Fourth International Conference on Digital Image Processing (ICDIP 2012), 833427 (8 June 2012); doi: 10.1117/12.954158; https://doi.org/10.1117/12.954158
PROCEEDINGS
5 PAGES


SHARE
Back to Top