Multi-label segmentation of images with partition trees - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports (Research Report) Year : 2014

Multi-label segmentation of images with partition trees


We propose a new framework for multi-class image segmentation with shape priors using a binary partition tree. In the literature, such trees are used to represent hierarchical partitions of images, and are usually computed in a bottom-up manner based on color similarities, then analyzed to detect objects with a known shape prior. However, not considering shape priors during the construction phase induces mistakes in the later segmentation. This paper proposes a method which uses both color distribution and shape priors to optimize the trees for image segmentation. The method consists in pruning and regrafting tree branches in order to minimize the energy of the best segmentation that can be extracted from the tree. Theoretical guarantees help reducing the search space and make the optimization efficient. Our experiments show that the optimization approach succeeds in incorporating shape information into multi-label segmentation, outperforming the state-of-the-art.
Fichier principal
Vignette du fichier
report.pdf (2.33 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01084166 , version 1 (18-11-2014)


  • HAL Id : hal-01084166 , version 1


Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat. Multi-label segmentation of images with partition trees. [Research Report] Inria Sophia Antipolis. 2014. ⟨hal-01084166⟩


178 View
121 Download


Gmail Facebook X LinkedIn More