Speeded-Up Robust Features (SURF)

  title={Speeded-Up Robust Features (SURF)},
  author={Herbert Bay and Andreas Ess and Tinne Tuytelaars and Luc Van Gool},
  journal={Comput. Vis. Image Underst.},

An Analysis of the SURF Method

The SURF method (Speeded Up Robust Features) is a fast and robust algorithm for local, similarity invariant representation and comparison of images, thus enabling real-time applications such as tracking and object recognition.

A new scale invariant feature detector and modified SURF descriptor

A new scale invariant octagonal center-surround detector, named OCT, and a modified SURF descriptor named I-SURF descriptor are introduced, which have better performance than SURF and SIFT.

An Evaluation of Open Source SURF Implementations

Different SURF implementations written in C++ are evaluated and it is found that some implementations produce up to 33% lower repeatability and up to 44% lower maximum recall than the original implementation, while the implementation provided with the software Pan-o-matic produced almost identical results.

Gauge-SURF descriptors

Fast Feature Matching by Coarse-to-Fine Comparison of Rearranged SURF Descriptors

A fast matching method that rearranges the elements of SURF descriptors based on their entropies, divides SURF descriptorors into sub-descriptors, and sequentially and analytically matches them to each other is proposed.

Unbiased evaluation of keypoint detectors with respect to rotation invariance

The most computationally complex detector, i.e. the SIFT performs best under rotation transformation of images, but the FAST and ORB detectors, while being less computationally demanding, perform almost equally well and can be viable choices in image processing tasks for mobile applications.

A fast, robust and low bit-rate representation for SIFT and SURF features

This work investigates low bit-rate representations based on a binarisation of SIFT and SURF features and is able to reduce the descriptor length by a factor of 8–32 and lifts the curse of dimensionality.

KPB-SIFT: a compact local feature descriptor

The produced KPB-SIFT descriptor is more compact as compared to the state-of-the-art, does not require pre-training step needed by PCA based descriptors, and shows superior advantages in terms of distinctiveness, invariance to scale, and tolerance of geometric distortions.

RSD-HoG: A New Image Descriptor

A novel local image descriptor called RSD-HoG is proposed that performs better than many state of the art descriptors such as SIFT, GLOH, DAISY and PCA-SIFT and has rich, discriminative set of local information related to the curvature of the image surface.



Distinctive Image Features from Scale-Invariant Keypoints

  • D. Lowe
  • Computer Science
    International Journal of Computer Vision
  • 2004
This paper presents a method for extracting distinctive invariant features from images that can be used to perform reliable matching between different views of an object or scene and can robustly identify objects among clutter and occlusion while achieving near real-time performance.

PCA-SIFT: a more distinctive representation for local image descriptors

  • Yan KeR. Sukthankar
  • Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
This paper examines (and improves upon) the local image descriptor used by SIFT, and demonstrates that the PCA-based local descriptors are more distinctive, more robust to image deformations, and more compact than the standard SIFT representation.

A performance evaluation of local descriptors

It is observed that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best and Moments and steerable filters show the best performance among the low dimensional descriptors.

Multi-scale phase-based local features

  • G. CarneiroA. Jepson
  • Computer Science
    2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings.
  • 2003
The results show that the phase-based local features lead to better performance than the other two approaches when dealing with common illumination changes, 2D rotation, and sub-pixel translation.

Indexing based on scale invariant interest points

  • K. MikolajczykC. Schmid
  • Mathematics
    Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001
  • 2001
This paper presents a new method for detecting scale invariant interest points. The method is based on two recent results on scale space: (1) Interest points can be adapted to scale and give

Invariant Features from Interest Point Groups

This work introduces a family of features which use groups of interest points to form geometrically invariant descriptors of image regions to ensure robust matching between images in which there are large changes in viewpoint, scale and illumi- nation.

Fast Approximated SIFT

A considerably faster approximation of the well known SIFT method by using efficient data structures for both, the detector and the descriptor and an analysis of the computational costs.

Object recognition from local scale-invariant features

  • D. Lowe
  • Computer Science
    Proceedings of the Seventh IEEE International Conference on Computer Vision
  • 1999
Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.

Rapid object detection using a boosted cascade of simple features

  • Paul A. ViolaMichael J. Jones
  • Computer Science
    Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001
  • 2001
A machine learning approach for visual object detection which is capable of processing images extremely rapidly and achieving high detection rates and the introduction of a new image representation called the "integral image" which allows the features used by the detector to be computed very quickly.

SURF: Speeded-Up Robust Features

In this document, the SURF detector-descriptor scheme used in the OpenSURF library is discussed in detail. First the algorithm is analysed from a theoretical standpoint to provide a detailed overview