ePrints

Sequential graph-based extraction of curvilinear structures

Lookup NU author(s): Dr Chris Willcocks, Phillip Jackson, Professor Boguslaw ObaraORCiD

Downloads

• Accepted version [.pdf]

Licence

This is the authors' accepted manuscript of an article that has been published in its final definitive form by Springer London, 2019.

For re-use rights please refer to the publisher's terms and conditions.

Abstract

© 2019, Springer-Verlag London Ltd., part of Springer Nature. In this paper, a new approach is proposed to extract an ordered sequence of curvilinear structures in images, capturing the largest and most influential paths first and then progressively extracting smaller paths until a prespecified size is reached. The results are demonstrated both quantitatively and qualitatively using synthetic and real-world images. The method is shown to outperform comparator methods for certain cases of noise, object class, and scale, while remaining fundamentally easier to use due to its low parameter requirement.

Publication metadata

Author(s): Alharbi SS, Willcocks CG, Jackson PTG, Alhasson HF, Obara B

Publication type: Article

Publication status: Published

Journal: Signal, Image and Video Processing

Year: 2019

Volume: 13

Issue: 5

Pages: 941-949

Print publication date: 01/07/2019

Online publication date: 20/02/2019

Acceptance date: 24/01/2019

Date deposited: 04/05/2021

ISSN (print): 1863-1703

ISSN (electronic): 1863-1711

Publisher: Springer London

URL: https://doi.org/10.1007/s11760-019-01431-6

DOI: 10.1007/s11760-019-01431-6

Altmetrics

Share