In this note we will discuss how image segmentation can be handled by using Bayesian learning and inference. In particular variational techniques relying on free energy minimization will be introduced. It will be shown how to embed a spatial diffusion process on segmentation labels within the Variational Bayes learning procedure so to enforce spatial constraints among labels.
A Variational Bayes approach to image segmentation. / G. BOCCIGNONE, M. FERRARO, P. NAPOLETANO - In: Advances in Brain, Vision, and Artificial Intelligence : second international symposium, BVAI 2007, Naples, Italy, October 10-12, 2007 : proceedings / [a cura di] F. Mele, G. Ramella, S. Santillo, F. Ventriglia. - Berlin : Springer, 2007. - ISBN 9783540755548. - pp. 234-243 (( Intervento presentato al 2. convegno Brain Vision and Artificial Intelligence tenutosi a Napoli nel 2007.
Titolo: | A Variational Bayes approach to image segmentation. |
Autori: | BOCCIGNONE, GIUSEPPE (Primo) |
Settore Scientifico Disciplinare: | Settore INF/01 - Informatica Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni |
Data di pubblicazione: | 2007 |
Digital Object Identifier (DOI): | http://dx.doi.org/10.1007/978-3-540-75555-5_22 |
Tipologia: | Book Part (author) |
Appare nelle tipologie: | 03 - Contributo in volume |