Accelerated skeletonization algorithm for tubular structures in large datasets by randomized erosion

Gerald Adam Zwettler, Werner Backfrieder, Franz Pfeifer, Roland Swoboda

Publikation: Beitrag in Buch/Bericht/TagungsbandKonferenzbeitragBegutachtung

5 Zitate (Scopus)

Abstract

Skeletonization is an important procedure in morphological analysis of three-dimensional objects. A simplified object geometry allows easy semantic interpretation at the cost of high computational effort. This paper introduces a fast morphological thinning approach for skeletonization of tubular structures and objects of arbitrary shape. With minimized constraints for erosions at the surface, hit-ratio is increased allowing high performance thinning with large datasets. Time consuming neighbourhood checking is solved by use of fast indexing lookup tables. The novel algorithm homogenously erodes the object's surface, resulting in an accurate extraction of the centerline, even when the medial axis is placed between the actual voxel-grid. The thinning algorithm is applied for vessel tree analysis in the field of computer-based medical diagnostics and thus has to meet high robustness and performance requirements.

OriginalspracheEnglisch
TitelVISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
Seiten74-81
Seitenumfang8
PublikationsstatusVeröffentlicht - 2008
Veranstaltung3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008 - Funchal, Madeira, Portugal
Dauer: 22 Jän. 200825 Jän. 2008

Publikationsreihe

NameVISAPP 2008 - 3rd International Conference on Computer Vision Theory and Applications, Proceedings
Band1

Konferenz

Konferenz3rd International Conference on Computer Vision Theory and Applications, VISAPP 2008
Land/GebietPortugal
OrtFunchal, Madeira
Zeitraum22.01.200825.01.2008

Fingerprint

Untersuchen Sie die Forschungsthemen von „Accelerated skeletonization algorithm for tubular structures in large datasets by randomized erosion“. Zusammen bilden sie einen einzigartigen Fingerprint.

Zitieren