A performance evaluation of local descriptors

Abstract

In this paper, we compare the performance of descriptors computed for local interest regions, as, for example, extracted by the Harris-Affine detector [Mikolajczyk, K and Schmid, C, 2004]. Many different descriptors have been proposed in the literature. It is unclear which descriptors are more appropriate and how their performance depends on the interest region detector. The descriptors should be distinctive and at the same time robust to changes in viewing conditions as well as to errors of the detector. Our evaluation uses as criterion recall with respect to precision and is carried out for different image transformations. We compare shape context [Belongie, S, et al., April 2002], steerable filters [Freeman, W and Adelson, E, Setp. 1991], PCA-SIFT [Ke, Y and Sukthankar, R, 2004], differential invariants [Koenderink, J and van Doorn, A, 1987], spin images [Lazebnik, S, et al., 2003], SIFT [Lowe, D. G., 1999], complex filters [Schaffalitzky, F and Zisserman, A, 2002], moment invariants [Van Gool, L, et al., 1996], and cross-correlation for different types of interest regions. We also propose an extension of the SIFT descriptor and show that it outperforms the original method. Furthermore, we observe that the ranking of the descriptors is mostly independent of the interest region detector and that the SIFT-based descriptors perform best. Moments and steerable filters show the best performance among the low dimensional descriptors.

DOI: 10.1109/CVPR.2003.1211478

Extracted Key Phrases

15 Figures and Tables

Showing 1-10 of 42 references

DRAFT inria-00548529, version 1 -20 Dec

  • 2005

An affine invariant method for selecting salient regions in images

  • T Kadir, M Brady, A Zisserman
  • 2004
1 Excerpt
Showing 1-10 of 3,275 extracted citations

Gauge-SURF Descriptors

  • Pablo F. Alcantarillaa, Luis M. Bergasab, Andrew J. Davisonc
  • 2012
Highly Influenced
8 Excerpts
0200400600'03'05'07'09'11'13'15'17
Citations per Year

6,604 Citations

Semantic Scholar estimates that this publication has received between 6,193 and 7,041 citations based on the available data.

See our FAQ for additional information.