A Sobolev-type metric for polar active contours

Baust, Maximillian and Yezzi, Anthony J. and Ünal, Gözde and Navab, Nassir (2011) A Sobolev-type metric for polar active contours. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011), Colorado Springs, USA

[img]PDF (CVPR 2011) - Registered users only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://dx.doi.org/10.1109/CVPR.2011.5995310


Polar object representations have proven to be a power- ful shape model for many medical as well as other com- puter vision applications, such as interactive image seg- mentation or tracking. Inspired by recent work on Sobolev active contours we derive a Sobolev-type function space for polar curves. This so-called polar space is endowed with a metric that allows us to favor origin translations and scale changes over smooth deformations of the curve. Moreover, the resulting curve flow inherits the coarse-to-fine behavior of Sobolev active contours and is thus very robust to local minima. These properties make the resulting polar active contours a powerful segmentation tool for many medical applications, such as cross-sectional vessel segmentation, aneurysm analysis, or cell tracking.

Item Type:Papers in Conference Proceedings
Uncontrolled Keywords:Sobolev active contours , Sobolev type metric , computer vision , polar active contours , polar object representations , segmentation tool
Subjects:Q Science > QA Mathematics > QA075 Electronic computers. Computer science
ID Code:17595
Deposited By:Gözde Ünal
Deposited On:05 Jan 2012 21:12
Last Modified:30 Jul 2019 14:58

Repository Staff Only: item control page