Joint segmentation of multiple images with shared classes: a Bayesian nonparametrics approach

Abstract : A combination of the hierarchical Dirichlet process (HDP) and the Potts model is proposed for the joint segmentation/classification of a set of images with shared classes. Images are first divided into homogeneous regions that are assumed to belong to the same class when sharing common characteristics. Simultaneously, the Potts model favors configurations defined by neighboring pixels belonging to the same class. This HDP-Potts model is elected as a prior for the images, which allows the best number of classes to be selected automatically. A Gibbs sampler is then designed to approximate the Bayesian estimators, under a maximum a posteriori (MAP) paradigm. Preliminary experimental results are finally reported using a set of synthetic images.
Liste complète des métadonnées

Cited literature [13 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01500506
Contributor : Open Archive Toulouse Archive Ouverte (oatao) <>
Submitted on : Monday, April 3, 2017 - 1:17:18 PM
Last modification on : Friday, April 12, 2019 - 4:23:01 PM
Document(s) archivé(s) le : Tuesday, July 4, 2017 - 12:58:40 PM

File

sodjo_17065.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01500506, version 1
  • OATAO : 17065

Relations

Citation

Jessica Sodjo, Audrey Giremus, François Caron, Jean-François Giovannelli, Nicolas Dobigeon. Joint segmentation of multiple images with shared classes: a Bayesian nonparametrics approach. IEEE Workshop on statistical signal processing (SSP 2016), Jun 2016, Palma de Mallorca, Spain. pp. 1-5. ⟨hal-01500506⟩

Share

Metrics

Record views

282

Files downloads

125