Date
1997
Collection title
Lecture Notes in Computer Science
Collection Id
1252
Dewey
Probabilités et mathématiques appliquées
Sujet
Scale Space theories; images
Conference name
First International Conference on Scale-Space Theory in Computer Vision (Scale-Space'97)
Conference date
07-1997
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
Author
Haar Romeny, Bart ter; Florack, Luc; Koenderink, Jan; Viergever, Max
Publisher
Springer
Publisher city
Berlin
Year
1997
Pages number
365
ISBN
978-3-540-63167-5
Author
Caselles, Vincent
Coll, Bartomeu
Morel, Jean-Michel
Type
Communication / Conférence
Item number of pages
29-49
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.