Skip to main content

Research Repository

Advanced Search

High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation

Wedowski, Raphael; Farooq, Abdul; Smith, Lyndon; Smith, Melvyn

High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation Thumbnail


Authors

Raphael Wedowski

Abdul Farooq Abdul2.Farooq@uwe.ac.uk
Associate Director (Human-Centric Robotics)

Lyndon Smith Lyndon.Smith@uwe.ac.uk
Professor in Computer Simulation and Machine

Profile Image

Melvyn Smith Melvyn.Smith@uwe.ac.uk
Research Centre Director Vision Lab/Prof



Contributors

W Smari
Editor

Abstract

We propose a new high speed line tracing algorithm based on a well known differential geometric line extraction algorithm. The previously separate steps of line detection and line tracing are performed simultaneously. This allows the exclusion of non-candidates from processing. Exploiting the inherent continuity of lines and using extracted line characteristics in subsequent detection/tracing also solves the problem of multiple, computationally expensive scale space iterations. Consequently, processing time is shown to be reduced by up to a factor of fifty. Furthermore, the extraction is very sensitive as hard to set global thresholds are no longer required. In the context of these proposals, we also review methods to identify the pixel-wise line orientation. The previously used orientation of maximum second derivative proved to suffer from systematic errors, whereas, our two novel methods proved more reliable. Our algorithm is designed for images containing only a single line but can be applied to images with multiple lines, especially if the global image structure is known. © 2010 IEEE.

Citation

Wedowski, R., Farooq, A., Smith, L., & Smith, M. (2010). High speed, multi-scale tracing of curvilinear features with automated scale selection and enhanced orientation computation. In W. Smari (Ed.), International Conference on High Performance Computing and Simulation (HPCS), 2010 (410-417). https://doi.org/10.1109/HPCS.2010.5547105

Conference Name Proceedings of the 2010 International Conference on High Performance Computing and Simulation, HPCS 2010
Publication Date Sep 28, 2010
Deposit Date Nov 18, 2010
Publicly Available Date Apr 12, 2016
Peer Reviewed Not Peer Reviewed
Pages 410-417
Book Title International Conference on High Performance Computing and Simulation (HPCS), 2010
ISBN 9781424468270
DOI https://doi.org/10.1109/HPCS.2010.5547105
Keywords curve tracing, gaussian scale space, high speed, line detection, sub-pixel
Public URL https://uwe-repository.worktribe.com/output/976716
Publisher URL http://dx.doi.org/10.1109/HPCS.2010.5547105
Additional Information Additional Information : Copyright © 2010 IEEE. Reprinted from International Conference on High Performance Computing and Simulation (HPCS), 2010. This material is posted here with permission of the IEEE. Such permission of the IEEE does not in any way imply IEEE endorsement of any of the University of the West of England (UWE's) products or services. Internal or personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution must be obtained from the IEEE by writing to pubs-permissions@ieee.org. By choosing to view this document, you agree to all provisions of the copyright laws protecting it.

Files







You might also like



Downloadable Citations