NEW GENERAL FEATURES BASED ON SUPERPIXELS FOR IMAGE SEGMENTATION LEARNING

Abstract : Segmenting an image is usually one of the major and most challenging steps in the pipeline of biomedical image analysis. One classical and promising approach is to consider seg-mentation as a classification task, where the aim is to assign to each pixel the label of the objects it belongs to. Pixels are therefore described by a vector of features, where each feature is calculated on the pixel itself or, more frequently, on a sliding window centered on the pixel. In this work, we propose to replace the sliding window by superpixels, i.e. regions which adapt to the image content. We call the resulting features SAF (Superpixel Adaptive Feature). Their contribution is highlighted on a biomedical database of melanocytes images. Qualitative and quantitative analyses show that they are better suited for segmentation purposes than the sliding window approach.
Type de document :
Communication dans un congrès
International Symposium on Biomedical Imaging, Apr 2016, Prague, Czech Republic
Liste complète des métadonnées


https://hal.archives-ouvertes.fr/hal-01276132
Contributeur : Vaïa Machairas <>
Soumis le : jeudi 18 février 2016 - 18:19:10
Dernière modification le : mardi 12 septembre 2017 - 11:40:35
Document(s) archivé(s) le : jeudi 19 mai 2016 - 11:16:56

Fichier

Machairas_HAL_ISBI.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01276132, version 1

Collections

Citation

V Machairas, T Baldeweck, T Walter, Etienne Decencière. NEW GENERAL FEATURES BASED ON SUPERPIXELS FOR IMAGE SEGMENTATION LEARNING. International Symposium on Biomedical Imaging, Apr 2016, Prague, Czech Republic. <hal-01276132>

Partager

Métriques

Consultations de
la notice

387

Téléchargements du document

299