Pose Invariant Shape Prior Segmentation Using Continuous Cuts and Gradient Descent on Lie Groups

DSpace Repository

Pose Invariant Shape Prior Segmentation Using Continuous Cuts and Gradient Descent on Lie Groups

Show full item record

Files for download

Find Full text There are no files associated with this item..

Facebook

Simple item record

Publication Conference Paper, peer reviewed
Title Pose Invariant Shape Prior Segmentation Using Continuous Cuts and Gradient Descent on Lie Groups
Author(s) Overgaard, Niels Chr. ; Fundana, Ketut ; Heyden, Anders
Date 2009
English abstract
This paper proposes a novel formulation of the Chan-Vese model for pose invariant shape prior segmentation as a continuous cut problem. The model is based on the classic L 2 shape dissimilarity measure and with pose invariance under the full (Lie-) group of similarity transforms in the plane. To overcome the common numerical problems associated with step size control for translation, rotation and scaling in the discretization of the pose model, a new gradient descent procedure for the pose estimation is introduced. This procedure is based on the construction of a Riemannian structure on the group of transformations and a derivation of the corresponding pose energy gradient. Numerically, this amounts to an adaptive step size selection in the discretization of the gradient descent equations. Together with efficient numerics for TV-minimization we get a fast and reliable implementation of the model. Moreover, the theory introduced is generic and reliable enough for application to more general segmentation- and shape-models.
DOI http://dx.doi.org/10.1007/978-3-642-02256-2_57 (link to publisher's fulltext.)
Host/Issue Scale Space and Variational Methods in Computer Vision;5567
Series/Issue Lecture Notes in Computer Science
ISSN 0302-9743
ISBN 978-3-642-02255-5
Pages 684-695
Language eng (iso)
Subject(s) Technology
Research Subject Categories::TECHNOLOGY
Note Second International Conference, SSVM - Scale Space and Variational Methods in Computer Vision, Voss, Norway, June 1-5, 2009
Handle http://hdl.handle.net/2043/10055 (link to this page)
Link http://www.math.uio.no/conference/ssvm2009/index.html (external link to related web page)

This item appears in the following Collection(s)

Show full item record

Search


Browse

My Account

Statistics