A performance evaluation of local descriptors

Krystian Mikolajczyk 1 Cordelia Schmid 2, *
* Corresponding author
2 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [45 references]  Display  Hide  Download

https://hal.inria.fr/inria-00548529
Contributor : Thoth Team <>
Submitted on : Monday, December 20, 2010 - 9:09:12 AM
Last modification on : Wednesday, April 11, 2018 - 1:57:39 AM
Long-term archiving on: Monday, March 21, 2011 - 3:10:18 AM

File

mikolajczyk_pami05.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Krystian Mikolajczyk, Cordelia Schmid. A performance evaluation of local descriptors. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2005, 27 (10), pp.1615--1630. ⟨10.1109/TPAMI.2005.188⟩. ⟨inria-00548529⟩

Share

Metrics

Record views

4034

Files downloads

11945