A hierarchical model and a Bayesian strategy for unsupervised deconvolution-segmentation of textured image

The proposed talk deals with the problem of deconvolution-segmentation of textured images. It is specifically devoted to the case of oriented textures and focused on unsupervised solutions. The images are composed of patches of textures that belong to a set of K possible classes described by a Gaussian random field. The labels that define the patches are modelled by a Potts field. The method relies on a hierarchical model and a Bayesian strategy to jointly estimate the labels, the textured images as well as the hyperparameters including texture and the Potts parameters. The estimators are computed based on a convergent procedure, from samples of the posterior obtained through an MCMC algorithm (Gibbs sampler including Perturbation-Optimization and Fisher-oriented Metropolis-Hastings). A first numerical evaluation is proposed. 
 

Jean-François GIOVANNELLI was born in Béziers, France, in 1966. He graduated from the Ecole Nationale Supérieure de l'Electronique et de ses Applications in 1990. He received the Ph. D. degree and the Habilitation à Diriger des Recherches in physics (signal-image processing) from the Université Paris-Sud, in 1995 and 2005 respectively. From 1997 to 2008, he has been Assistant Professor with the Université Paris-Sud, and a Researcher with the Laboratoire des Signaux et Systèmes, Groupe Problèmes Inverses. He is presently Professor with the Université de Bordeaux and a Researcher with the Laboratoire d'Intégration du Matériau au Système, Groupe Signal-Image. He is interested in regularization and Bayesian methods for inverse problems in signal and image processing, mainly unsupervised and myopic (self-calibrated) problems. His application fields essentially concern astronomical, medical, proteomics and geophysical imaging. For more information: http://giovannelli.free.fr