Conditional random fields for object and background estimation in fluorescence video-microscopy - Compartimentation et dynamique cellulaires Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Conditional random fields for object and background estimation in fluorescence video-microscopy

Résumé

This paper describes an original method to detect XFP-tagged pro- teins in time-lapse microscopy. Non-local measurements able to capture spatial intensity variations are incorporated within a Con- ditional Random Field (CRF) framework to localize the objects of interest. The minimization of the related energy is performed by a min-cut/max-flow algorithm. Furthermore, we estimate the slowly varying background at each time step. The difference between the current image and the estimated background provides new and re- liable measurements for object detection. Experimental results on simulated and real data demonstrate the performance of the proposed method.
Fichier principal
Vignette du fichier
2009_isbi_pecot.pdf (246.56 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00794876 , version 1 (26-02-2013)

Identifiants

  • HAL Id : hal-00794876 , version 1

Citer

Thierry Pecot, Anatole Chessel, Sabine Bardin, Jean Salamero, Patrick Bouthemy, et al.. Conditional random fields for object and background estimation in fluorescence video-microscopy. IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2012, Jun 2009, Boston, MA, United States. pp.734-737. ⟨hal-00794876⟩
721 Consultations
98 Téléchargements

Partager

Gmail Facebook X LinkedIn More