A performance evaluation of local descriptors
A performance evaluation of local descriptors
复制标题
DOI：
10.1109/tpami.2005.188
复制
发表时间：
2005-10-01
影响因子：
23.6
通讯作者：
Schmid, C
中科院分区：
文献类型：
--
作者：
Mikolajczyk, K;Schmid, C
在本文中，我们比较了针对局部感兴趣区域计算的描述符的性能，例如由哈里斯仿射探测器[32]提取的区域。文献中已经提出了许多不同的描述符。不清楚哪些描述符更合适，以及它们的性能如何取决于感兴趣区域探测器。描述符应该具有独特性，同时对观察条件的变化以及探测器的误差具有鲁棒性。我们的评估使用查准率相关的召回率作为标准，并针对不同的图像变换进行。我们比较了形状上下文[3]、可操纵滤波器[12]、主成分分析 - 尺度不变特征变换（PCA - SIFT）[19]、微分不变量[20]、旋转图像[21]、尺度不变特征变换（SIFT）[26]、复数滤波器[37]、矩不变量[43]以及针对不同类型感兴趣区域的互相关。我们还提出了尺度不变特征变换（SIFT）描述符的一种扩展，并表明它优于原始方法。此外，我们观察到描述符的排名大多与感兴趣区域探测器无关，并且基于尺度不变特征变换（SIFT）的描述符性能最佳。在低维描述符中，矩和可操纵滤波器表现出最佳性能。
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. 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.