• xmlui.mirage2.page-structure.header.title
    • français
    • English
  • Help
  • Login
  • Language 
    • Français
    • English
View Item 
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
  •   BIRD Home
  • CEREMADE (UMR CNRS 7534)
  • CEREMADE : Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

BIRDResearch centres & CollectionsBy Issue DateAuthorsTitlesTypeThis CollectionBy Issue DateAuthorsTitlesType

My Account

LoginRegister

Statistics

Most Popular ItemsStatistics by CountryMost Popular Authors
Thumbnail

Boundary Extraction in Natural Images Using Ultrametric Contour Maps

Arbelaez, Pablo (2006), Boundary Extraction in Natural Images Using Ultrametric Contour Maps, Conference on Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Proceedings, IEEE, p. 182. http://dx.doi.org/10.1109/CVPRW.2006.48

View/Open
Arbelaez_POCV06.pdf (958.4Kb)
Type
Communication / Conférence
Date
2006
Conference title
Conference on Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06
Conference date
2006-06
Conference city
New York
Conference country
États-Unis
Book title
Conference on Computer Vision and Pattern Recognition Workshop, 2006. CVPRW '06. Proceedings
Publisher
IEEE
ISBN
0-7695-2646-2
Pages
182
Publication identifier
http://dx.doi.org/10.1109/CVPRW.2006.48
Metadata
Show full item record
Author(s)
Arbelaez, Pablo
Abstract (EN)
This paper presents a low-level system for boundary extraction and segmentation of natural images and the evaluation of its performance. We study the problem in the framework of hierarchical classification, where the geometric structure of an image can be represented by an ultrametric contour map, the soft boundary image associated to a family of nested segmentations. We define generic ultrametric distances by integrating local contour cues along the regions boundaries and combining this information with region attributes. Then, we evaluate quantitatively our results with respect to ground-truth segmentation data, proving that our system outperforms significantly two widely used hierarchical segmentation techniques, as well as the state of the art in local edge detection.
Subjects / Keywords
segmentation techniques; Computer vision

Related items

Showing items related by title and author.

  • Thumbnail
    Extraction of Tubular and Tree Structures in Biomedical Images using Minimal Paths and Tubular Models 
    Cohen, Laurent D. (2010) Communication / Conférence
  • Thumbnail
    Scale space versus topographic map for natural images 
    Caselles, Vincent; Coll, Bartomeu; Morel, Jean-Michel (1997) Communication / Conférence
  • Thumbnail
    Interactive Retinal Vessel Centreline Extraction and Boundary Delineation Using Anisotropic Fast Marching and Intensities Consistency 
    Chen, Da; Cohen, Laurent D. (2015) Communication / Conférence
  • Thumbnail
    A geometric model for active contours in image processing 
    Caselles, Vincent; Catté, Francine; Coll, Tomeu; Dibos, Françoise (1993) Article accepté pour publication ou publié
  • Thumbnail
    Fast extraction of minimal paths in 3D images and applications to virtual endoscopy 
    Cohen, Laurent D.; Deschamps, Thomas (2001) Article accepté pour publication ou publié
Dauphine PSL Bibliothèque logo
Place du Maréchal de Lattre de Tassigny 75775 Paris Cedex 16
Phone: 01 44 05 40 94
Contact
Dauphine PSL logoEQUIS logoCreative Commons logo