DMCA
Shape Priors for Level Set Representations (2002)
| Venue: | In ECCV |
| Citations: | 202 - 14 self |
BibTeX
@INPROCEEDINGS{Rousson02shapepriors,
author = {Mikael Rousson and Nikos Paragios},
title = {Shape Priors for Level Set Representations},
booktitle = {In ECCV},
year = {2002},
pages = {78--92},
publisher = {Springer}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Level Set Representations, the pioneering framework introduced by Osher and Sethian [14] is the most common choice for the implementation of variational frameworks in Computer Vision since it is implicit, intrinsic, parameter and topology free. However, many Computer vision applications refer to entities with physical meanings that follow a shape form with a certain degree of variability. In this paper, we propose a novel energetic form to introduce shape constraints to level set representations. This formulation exploits all advantages of these representations resulting on a very elegant approach that can deal with a large number of parametric as well as continuous transformations. Furthermore, it can be combined with existing well known level set-based segmentation approaches leading to paradigms that can deal with noisy, occluded and missing or physically corrupted data. Encouraging experimental results are obtained using synthetic and real images.
Keyphrases
level set representation shape prior real image level set-based segmentation approach certain degree set representation many computer vision application shape constraint shape form variational framework encouraging experimental result computer vision large number common choice pioneering framework novel energetic form physical meaning elegant approach continuous transformation
