• 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 - Request a copy

Scale space versus topographic map for natural images

Caselles, Vincent; Coll, Bartomeu; Morel, Jean-Michel (1997), Scale space versus topographic map for natural images, in Haar Romeny, Bart ter; Florack, Luc; Koenderink, Jan; Viergever, Max, Scale-Space Theory in Computer Vision First International Conference, Scale-Space'97 Utrecht, The Netherlands, July 2–4, 1997 Proceedings, Springer : Berlin, p. 29-49. http://dx.doi.org/10.1007/3-540-63167-4_38

Type
Communication / Conférence
Date
1997
Conference title
First International Conference on Scale-Space Theory in Computer Vision (Scale-Space'97)
Conference date
1997-07
Conference city
Utrecht
Conference country
Pays-Bas
Book title
Scale-Space Theory in Computer Vision First International Conference, Scale-Space'97 Utrecht, The Netherlands, July 2–4, 1997 Proceedings
Book author
Haar Romeny, Bart ter; Florack, Luc; Koenderink, Jan; Viergever, Max
Publisher
Springer
Series title
Lecture Notes in Computer Science
Series number
1252
Published in
Berlin
ISBN
978-3-540-63167-5
Number of pages
365
Pages
29-49
Publication identifier
http://dx.doi.org/10.1007/3-540-63167-4_38
Metadata
Show full item record
Author(s)
Caselles, Vincent
Coll, Bartomeu
Morel, Jean-Michel
Abstract (EN)
We call "natural" image any photograph of an outdoor or indoor scene taken by a standard camera. In such images, most observed objects undergo occlusions and the illumination condition and contrast response of the camera are unknown. Actual Scale Space theories do not incorporate obvious restrictions imposed by the physics of image generation. The heat equation (linear scale space) is not contrast invariant and destroys T-junctions. The same is true for the recently proposed curvature equations (mean curvature motion and affine shortening): They break the symmetry of junctions. To apply directly these models to natural world images, with occlusions, is irrevelant. Returning to the edge detection problem, in which scale space theory originates, we show how level lines can be found in an image without smoothing. As an alternative to edge detection/scale space, we propose to define the line structure in a natural image by its topographic map (set of all level lines). We also show that a modification of morphological scale space can help to the visualization of the topographic map.
Subjects / Keywords
Scale Space theories; images

Related items

Showing items related by title and author.

  • Thumbnail
    An axiomatic approach to image interpolation 
    Caselles, Vincent; Morel, Jean-Michel; Sbert, Catalina (1998) Article accepté pour publication ou publié
  • Thumbnail
    A Kanizsa Programme 
    Coll, Bartomeu; Caselles, Vincent; Morel, Jean-Michel (1996) Communication / Conférence
  • Thumbnail
    Shape preserving local histogram modification 
    Caselles, Vincent; Lisani, Jose-Luis; Morel, Jean-Michel; Sapiro, Guillermo (1999) Article accepté pour publication ou publié
  • Thumbnail
    Axioms and fundamental equations of image processing 
    Alvarez, Luis; Guichard, Frédéric; Lions, Pierre-Louis; Morel, Jean-Michel (1993) Article accepté pour publication ou publié
  • Thumbnail
    A variational method in image segmentation: Existence and approximation results 
    Del Maso, G.; Morel, Jean-Michel; Solimini, S. (1992) 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