SURF: Speeded Up Robust Features
SURF: Speeded Up Robust Features
- New search for: Bay, Herbert
- New search for: Tuytelaars, Tinne
- New search for: Gool, Luc
- New search for: Bay, Herbert
- New search for: Tuytelaars, Tinne
- New search for: Gool, Luc
Abstract In this paper, we present a novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features). It approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster. This is achieved by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (in casu, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by simplifying these methods to the essential. This leads to a combination of novel detection, description, and matching steps. The paper presents experimental results on a standard evaluation set, as well as on imagery obtained in the context of a real-life object recognition application. Both show SURF’s strong performance.
Document information
SURF: Speeded Up Robust Features
Computer Vision – ECCV 2006 ; 3 ; 404-417
Lecture Notes in Computer Science ; 3951 , 3
2006-01-01
14 pages
Article/Chapter (Book)
Electronic Resource
English
Similar titles
SURF: Speeded Up Robust Features
| British Library Conference Proceedings | 2006
Speeded-Up Robust Features (SURF)
| British Library Online Contents | 2008
Underwater pipeline repair speeded
| Tema Archive | 1981
Aircraft production speeded by electricity
| Engineering Index Backfile | 1930
Freight handling speeded by electric cranes
Engineering Index Backfile | 1928