Evaluation of interest point detectors

被引:1195
作者
Schmid, C [1 ]
Mohr, R [1 ]
Bauckhage, C [1 ]
机构
[1] INRIA Rhone Alpes, F-38330 Montbonnot St Martin, France
关键词
interest points; quantitative evaluation; comparison of detectors; repeatability; information content;
D O I
10.1023/A:1008199403446
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Many different low-level feature detectors exist and it is widely agreed that the evaluation of detectors is important. In this paper we introduce two evaluation criteria for interest points: repeatability rate and information content. Repeatability rate evaluates the geometric stability under different transformations. Information content measures the distinctiveness of features. Different interest point detectors are compared using these two criteria. We determine which detector gives the best results and show that it satisfies the criteria well.
引用
收藏
页码:151 / 172
页数:22
相关论文
共 49 条