Passer à la navigation principale Passer à la recherche Passer au contenu principal

Unsupervised segmentation of non stationary images with non Gaussian correlated noise using triplet Markov fields and the pearson system

Résultats de recherche: Le chapitre dans un livre, un rapport, une anthologie ou une collectionContribution à une conférenceRevue par des pairs

Résumé

The hidden Markov field (HMF) model has been used in many model-based solutions for image segmentation, and generally gives satisfying results. However, when the class image is non stationary, the unsupervised segmentation results provided by HMF can be poor. In this paper, we propose a new model based on triplet Markov fields (TMF) and the Pearson system which enables one to deal with non stationary hidden fields and correlated, possibly non Gaussian noise. Moreover, the nature of marginal distributions of the noise can vary with the class. We specify a new general parameter estimation method and apply it to unsupervised Bayesian image segmentation.

langue originaleAnglais
titreImage and Multidimensional Signal Processing Signal Processing Education Bio Imaging and Signal Processing
EditeurInstitute of Electrical and Electronics Engineers Inc.
PagesII701-II704
ISBN (imprimé)142440469X, 9781424404698
Les DOIs
étatPublié - 1 janv. 2006
Evénement2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006 - Toulouse, France
Durée: 14 mai 200619 mai 2006

Série de publications

NomICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2
ISSN (imprimé)1520-6149

Une conférence

Une conférence2006 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2006
Pays/TerritoireFrance
La villeToulouse
période14/05/0619/05/06

Empreinte digitale

Examiner les sujets de recherche de « Unsupervised segmentation of non stationary images with non Gaussian correlated noise using triplet Markov fields and the pearson system ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation