Abstract
We propose a linear-time line segment detector that gives accurate results, a controlled number of false detections, and requires no parameter tuning. This algorithm is tested and compared to state-of-the-art algorithms on a wide set of natural images. © 2010 IEEE.
| Original language | English |
|---|---|
| Article number | 4731268 |
| Pages (from-to) | 722-732 |
| Number of pages | 11 |
| Journal | IEEE Transactions on Pattern Analysis and Machine Intelligence |
| Volume | 32 |
| Issue number | 4 |
| Early online date | 14 Dec 2008 |
| DOIs | |
| Publication status | Published - Apr 2010 |
| Externally published | Yes |
Bibliographical note
Acknowledgments:The authors are indebted to their collaborators for many remarks and corrections, and more particularly to Andre´s Almansa, Gabriele Facciolo, Enric Meinhardt-Llopis, and Pablo Muse´. They wish to thank J. Ross Beveridge for providing the software for the Burns et al. algorithm. The authors also wish to extend thanks to the editor and the anonymous reviewers for their valuable suggestions and comments.
Funding
The research was partially financed by the ALFA project CVFA II-0366-FA, the Centre National d’Etudes Spatiales, and the US Office of Naval Research under grant N00014-97-1-0839.
Keywords
- Line segment detection
- NFA
- Helmholtz principle
- a contrario detection