Share Email Print

Proceedings Paper

Contrast independent detection of branching points in network-like structures
Author(s): Boguslaw Obara; Mark Fricker; Vicente Grau
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Many biomedical applications require the detection of branching structures in images. While several algorithms have been proposed for (semi-)automatic extraction of these structures, branching points usually need specific treatment. We propose a vector field-based approach to identify branching points in images. A vector field is calculated using a novel contrast-independent tensor representation based on local phase. Non-curvilinear structures, including junctions and end points, are detected using directional statistics of the principal orientation as defined by the tensor. Results on synthetic and real biomedical images show the robustness of the algorithm against changes in contrast, and its ability to detect junctions in highly complex images.

Paper Details

Date Published: 14 February 2012
PDF: 7 pages
Proc. SPIE 8314, Medical Imaging 2012: Image Processing, 83141L (14 February 2012); doi: 10.1117/12.910575
Show Author Affiliations
Boguslaw Obara, Univ. of Oxford (United Kingdom)
Mark Fricker, Univ. of Oxford (United Kingdom)
Vicente Grau, Univ. of Oxford (United Kingdom)

Published in SPIE Proceedings Vol. 8314:
Medical Imaging 2012: Image Processing
David R. Haynor; Sébastien Ourselin, Editor(s)

© SPIE. Terms of Use
Back to Top