Generalized Gradients: Priors on Minimization Flows

Guillaume Charpiat 1, 2 Pierre Maurel 3, 2 Jean-Philippe Pons 4, 5, 2 Renaud Keriven 6, 2 Olivier Faugeras 7, 2
1 STARS - Spatio-Temporal Activity Recognition Systems
CRISAM - Inria Sophia Antipolis - Méditerranée
2 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique de l'École normale supérieure, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
3 VisAGeS - Vision, Action et Gestion d'informations en Santé
INSERM - Institut National de la Santé et de la Recherche Médicale : U746, Inria Rennes – Bretagne Atlantique , IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
4 IMAGINE [Marne-la-Vallée]
LIGM - Laboratoire d'Informatique Gaspard-Monge, CSTB - Centre Scientifique et Technique du Bâtiment, ENPC - École des Ponts ParisTech
7 NEUROMATHCOMP - Mathematical and Computational Neuroscience
CRISAM - Inria Sophia Antipolis - Méditerranée , JAD - Laboratoire Jean Alexandre Dieudonné : UMR6621
Abstract : This paper tackles an important aspect of the variational problem underlying active contours: optimization by gradient flows. Classically, the definition of a gradient depends directly on the choice of an inner product structure. This consideration is largely absent from the active contours literature. Most authors, explicitely or implicitely, assume that the space of admissible deformations is ruled by the canonical L 2 inner prod-uct. The classical gradient flows reported in the literature are relative to this particular choice. Here, we investigate the relevance of using (i) other inner products, yielding other gradient descents, and (ii) other minimizing flows not deriving from any inner product. In particular, we show how to induce different de-grees of spatial consistency into the minimizing flow, in order to decrease the probability of getting trapped into irrelevant local minima. We report numerical experiments indicating that the sensitivity of the active contours method to initial conditions, which seriously limits its applicability and efficiency, is alleviated by our application-specific spatially coherent minimizing flows. We show that the choice of the inner product can be seen as a prior on the deformation fields and we present an extension of the definition of the gradient toward more general priors.
Liste complète des métadonnées

Cited literature [35 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01117529
Contributor : Pierre Maurel <>
Submitted on : Tuesday, February 17, 2015 - 11:49:02 AM
Last modification on : Monday, March 4, 2019 - 2:08:05 PM
Document(s) archivé(s) le : Monday, May 18, 2015 - 10:20:51 AM

File

gradients.pdf
Files produced by the author(s)

Identifiers

Citation

Guillaume Charpiat, Pierre Maurel, Jean-Philippe Pons, Renaud Keriven, Olivier Faugeras. Generalized Gradients: Priors on Minimization Flows. International Journal of Computer Vision, Springer Verlag, 2007, 73, pp.325 - 344. ⟨10.1007/s11263-006-9966-2⟩. ⟨hal-01117529⟩

Share

Metrics

Record views

660

Files downloads

299