In this paper, a novel scale- and rotation-invariant interest point detector and descr iptor, coined SURF (Speeded Up Robust

Features) is presented. 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 descr iptors (in casu, using a Hessian matrix-based measure for the detector, and a

distribution-based descr iptor) and by simplifying these methods to the

essential. This leads to a combination of novel detection, descr iption, 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.-In this paper, a novel scale- and rotation-invariant interest point detector and descr iptor, coined SURF (Speeded Up Robust

Features) is presented. 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 descr iptors (in casu, using a Hessian matrix-based measure for the detector, and a

distribution-based descr iptor)　and by simplifying these methods to the

essential. This leads to a combination of novel detection, descr iption, 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.