musique contemporaine

Ircam - articles scientifiques notice originale

Unsupervised Segmentation of Randomly Switching Data Hidden With Non-Gaussian Correlated Noise : Hidden Markov chains, Triplet Markov Chains, Copulas, non-Gaussian correlated noise

Type

text
 

Genre(s)

article
 

Forme(s)

document imprimé
 

Cette ressource est disponible chez l'organisme suivant : Ircam - Centre Pompidou

Identification

Titre

Unsupervised Segmentation of Randomly Switching Data Hidden With Non-Gaussian Correlated Noise
 

Sous-Titre

Hidden Markov chains, Triplet Markov Chains, Copulas, non-Gaussian correlated noise
 

Nom(s)

Lanchantin, Pierre (auteur)
 
Lapuyade-Lahorgue, Jérôme (auteur)
 
Pieczynski, Wojciech (auteur)
 

Publication

2011
 

Description

Résumé

Hidden Markov chains (HMC) are a very powerful tool in hidden data restoration and are currently used to solve a wide range of problems. However, when these data are not stationary, estimating the parameters, which are required for unsupervised processing, poses a problem. Moreover, taking into account correlated non-Gaussian noise is difficult without model approximations. The aim of this paper is to propose a simultaneous solution to both of these problems using triplet Markov chains (TMC) and copulas. The interest of the proposed models and related processing is validated by different experiments some of which are related to semi-supervised and unsupervised image segmentation.
 

Note(s)

Article paru dans : Signal Processing vol. 91 n°2
 

Localisation

Envoyer la notice

Bookmark and Share 
 

Identifiant OAI

 

Date de la notice

2010-11-04 01:00:00
 

Identifiant portail

 

Contact