OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

A Bayesian nonparametric model for unsupervised joint segmentation of a collection of images

Sodjo, Jessica and Giremus, Audrey and Dobigeon, Nicolas and Caron, François A Bayesian nonparametric model for unsupervised joint segmentation of a collection of images. (2019) IEEE Access, 7. 12017-12018. ISSN 2169-3536

[img]
Preview
(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1MB

Official URL: https://doi.org/10.1109/ACCESS.2019.2936541

Abstract

Jointly segmenting a collection of images with shared classes is expected to yield better results than single-image based methods, due to the use of the shared statistical information across different images. This paper proposes a Bayesian approach for tackling this problem. As a first contribution, the proposed method relies on a new prior distribution for the class labels, which combines a hierarchical Dirichlet process (HDP) with a Potts model. The latter classically favors a spatial dependency, whereas the HDP is a Bayesian nonparametric model that allows the number of classes to be inferred automatically. The HDP also explicitly induces a sharing of classes between the images. The resulting posterior distribution of the labels is not analytically tractable and can be explored using a standard Gibbs sampler. However, such a sampling strategy is known to have poor mixing properties for high-dimensional data. To alleviate this issue, the second contribution reported in this paper consists of an adapted generalized Swendsen-Wang algorithm which is a sampling technique that improves the exploration of the posterior distribution. Finally, since the inferred segmentation depends on the values of the hyperparameters, the third contribution aims at adjusting them while sampling the posterior label distribution by resorting to an original combination of two sequential Monte Carlo samplers. The proposed methods are validated on both simulated and natural images from databases.

Item Type:Article
Additional Information:Thanks to IEEE editor. The definitive version is available at http://ieeexplore.ieee.org The original PDF can be found at IEEE Access (ISSN 2169-3536) website : https://ieeexplore.ieee.org/document/8808928 Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
HAL Id:hal-02397238
Audience (journal):International peer-reviewed journal
Uncontrolled Keywords:
Institution:Other partners > Bordeaux INP - BINP (FRANCE)
French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - INPT (FRANCE)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UPS (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Université de Bordeaux (FRANCE)
Other partners > University of Oxford (UNITED KINGDOM)
Other partners > Université des Antilles et de la Guyane (FRANCE)
Laboratory name:
Funders:
ANR : Agence nationale de la recherche (France)
Statistics:download
Deposited By: IRIT IRIT
Deposited On:29 Nov 2019 10:44

Repository Staff Only: item control page