|
Published Articles >> Table of Contents >> Abstract
Fifth International Conference on Computer Vision (ICCV'95)
p. 810
Gradient flows and geometric active contour models
S. Kichenassamy, Dept. of Math., Minnesota Univ., Minneapolis, MN, USA
A. Kumar, Dept. of Math., Minnesota Univ., Minneapolis, MN, USA
P. Olver, Dept. of Math., Minnesota Univ., Minneapolis, MN, USA
A. Tannenbaum, Dept. of Math., Minnesota Univ., Minneapolis, MN, USA
A. Yezzi, Dept. of Math., Minnesota Univ., Minneapolis, MN, USA
Full Article Text:
  
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICCV.1995.466855
Send link to a friend
| 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.
|
 Additional Information
|
Index Terms- computer vision; computational geometry; gradient flows; geometric active contour models; curve evolution; feature-based Riemannian metrics; snake paradigm; 3-D active surface models
Citation:
S. Kichenassamy, A. Kumar, P. Olver, A. Tannenbaum, A. Yezzi,
"Gradient flows and geometric active contour models,"
iccv,
p. 810,
Fifth International Conference on Computer Vision (ICCV'95),
1995
|
|
