Gradient flows and geometric active contour models
- 31 May 1995
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 810-815
- https://doi.org/10.1109/iccv.1995.466855
Abstract
In this paper, we analyze the geometric active contour models discussed previously from a curve evolution point of view and propose some modifications based on gradient flows relative to certain new feature-based Riemannian metrics. This leads to a novel snake paradigm in which the feature of interest may be considered to lie at the bottom of a potential well. Thus the snake is attracted very naturally and efficiently to the desired feature. Moreover, we consider some 3-D active surface models based on these ideas.Keywords
This publication has 18 references indexed in Scilit:
- Shape modeling with front propagation: a level set approachIeee Transactions On Pattern Analysis and Machine Intelligence, 1995
- A theory of multiscale, curvature-based shape representation for planar curvesIeee Transactions On Pattern Analysis and Machine Intelligence, 1992
- On the evolution of curves via a function of curvature. I. The classical caseJournal of Mathematical Analysis and Applications, 1992
- Toward a computational theory of shape: An overviewLecture Notes in Computer Science, 1990
- A short note on the evolution of a surface by its mean curvatureDuke Mathematical Journal, 1989
- Fronts propagating with curvature-dependent speed: Algorithms based on Hamilton-Jacobi formulationsJournal of Computational Physics, 1988
- Constraints on deformable models:Recovering 3D shape and nonrigid motionArtificial Intelligence, 1988
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- Curvature and the evolution of frontsCommunications in Mathematical Physics, 1985
- Riemann Solvers, the Entropy Condition, and DifferenceSIAM Journal on Numerical Analysis, 1984