## On active contour models and balloons

Venue: | CVGIP: Image |

Citations: | 477 - 37 self |

### BibTeX

@INPROCEEDINGS{Cohen_onactive,

author = {D. Cohen},

title = {On active contour models and balloons},

booktitle = {CVGIP: Image},

year = {}

}

### Years of Citing Articles

### OpenURL

### Abstract

The use.of energy-minimizing curves, known as “snakes, ” to extract features of interest in images has been introduced by Kass, Witkhr & Terzopoulos (Znt. J. Comput. Vision 1, 1987,321-331). We present a model of deformation which solves some of the problems encountered with the original method. The external forces that push the curve to the edges are modified to give more stable results. The original snake, when it is not close enough to contours, is not attracted by them and straightens to a line. Our model makes the curve behave like a balloon which is inflated by an additional force. The initial curve need no longer be close to the solution to converge. The curve passes over weak edges and is stopped only if the edge is strong. We give examples of extracting a ventricle in medical images. We have also made a first step toward 3D object reconstruction, by tracking the extracted contour on a series of successive cross sections. 0 1991 Academic press, 1~. I.

### Citations

3261 | A Computational Approach to Edge Detection - Canny - 1986 |

3185 | Snakes: active contour models - Kass, Witkin, et al. - 1987 |

750 | Visual Reconstruction - Blake, Zisserman - 1987 |

596 | Feature extraction from faces using deformable templates - Yuille, Hallinan, et al. - 1992 |

241 | Using Canny’s criteria to derive a recursively implemented optimal edge detector. Int J Comput Vision 1:167–187 - Deriche - 1987 |

241 | Constraints on deformable models: recovering 3D shape and nonrigid motion - Terzopoulos, Witkin, et al. - 1988 |

146 | The computation of visible-surface representations - Terzopoulos - 1988 |

74 | Model driven edge detection - Fua, Leclerc - 1988 |

25 |
M.: 3D Edge Detection Using Recursive Filtering: Application to Scanner Images. CVGIP: Image Understanding 53(1
- Monga, Deriche, et al.
- 1991
(Show Context)
Citation Context ...ted recursively by Deriche [6] to compute the image gradient. The other image is a slice from a 3D NMR image in the heart area. We want to extract the left ventricle. We use here the 30 edge detector =-=[7]-=- obtained by generalization of the 2D Canny-Deriche filter. We give in comparison examples of what happens when we do not normalize the image force (Fig. 5). If the time step is too large, the force ~... |

19 | On matching deformable models to images - Terzopoulos - 1987 |

9 |
Building highly structured volume representations
- Ayache, Boissonnat, et al.
- 1989
(Show Context)
Citation Context ...e result obtained in the previously processed connected section (as was done for motion tracking in [I]). We made a first approach to 3D reconstruction by extracting the contour slice by slice (as in =-=[9]-=- where the curves were extracted by hand, on each slice, using an image of edges). Figures 12 and 13 show the reconstruction of the left and right ventricles. This reconstruction is almost automatic. ... |

1 | Snakes: to follow the deformation of a ventricle during a cycle), Active contour models - Witkin, Terzopoulos - 1987 |

1 |
Visual Reconstruction, matching of extracted features to an atlas, which is reMIT
- Blake, Zisserman
- 1987
(Show Context)
Citation Context ...achieve a solution of the static problem.CONTOUR MODELS AND BALLOONS 213 The evolution problem becomes after finite differences in time (step 7) and space (step h): (Id -I- 7A)uf = (uf-’ + TF(u’-I)) =-=(3)-=- where Id denotes the identity matrix. Thus, we obtain a linear system and we have to solve a pentadiagonal banded symmetric positive system. We compute the solution using a LU decomposition of (Zd + ... |

1 | The computation of visible-surface represenwith simple geometric shapes as templates which are de- tations - Terzopoulos - 1988 |

1 | Rachid Deriche, Using Canny’s criteria to derive a recursively implemented optimal edge detector - CONCLUSION - 1987 |