DMCA
A PERFORMANCE EVALUATION OF LOCAL DESCRIPTORS (2005)
Cached
Download Links
| Citations: | 1783 - 51 self |
BibTeX
@MISC{Mikolajczyk05aperformance,
author = {Krystian Mikolajczyk and Cordelia Schmid},
title = { A PERFORMANCE EVALUATION OF LOCAL DESCRIPTORS },
year = {2005}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
In this paper we compare the performance of descriptors computed for local interest regions, as for example extracted by the Harris-Affine detector [32]. Many different descriptors have been proposed in the literature. However, 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 [3], steerable filters [12], PCA-SIFT [19], differential invariants [20], spin images [21], SIFT [26], complex filters [37], moment invariants [43], 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.
Keyphrases
performance evaluation local descriptor steerable filter interest region detector criterion recall differential invariant time robust sift descriptor different type local interest region complex filter spin image low dimensional descriptor many different descriptor interest region moment invariant different image transformation original method shape context harris-affine detector
