A robust level-set algorithm for centerline extraction

A.C. Telea, A. Vilanova

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

3 Downloads (Pure)


We present a robust method for extracting 3D centerlines from volumetric datasets. We start from a 2D skeletonization method to locate voxels centered with respect to three orthogonal slicing directions. Next, we introduce a new detection criterion to extract the centerline voxels from the above skeletons, followed by a thinning, reconnection, and a ranking step. Overall, the proposed method produces centerlines that are object-centered, connected, one voxel thick, robust with respect to object noisiness, handles arbitrary object topologies, comes with a simple pruning threshold, and is fast to compute. We compare our results with two other methods on a variety of real-world datasets.
Original languageEnglish
Title of host publicationVisSym 2003, Symposium on Visualization (Grenoble, France, May 26-28, 2003)
Place of PublicationAire-la-Ville, Switzerland
PublisherEurographics Association
ISBN (Print)1-58113-698-6
Publication statusPublished - 2003


Dive into the research topics of 'A robust level-set algorithm for centerline extraction'. Together they form a unique fingerprint.

Cite this