Evaluation of interest point detectors. Schmid, C., Mohr, R., & Bauckhage, C. International Journal of Computer Vision, 37(2):151-172, 2000.
doi  abstract   bibtex   
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.
@article{
 title = {Evaluation of interest point detectors},
 type = {article},
 year = {2000},
 keywords = {comparison of detectors,information content,interest points,quantitative evaluation,repeatability},
 pages = {151-172},
 volume = {37},
 id = {5515efe0-2d3c-3700-8827-2cd6ec46a926},
 created = {2022-09-19T10:49:11.261Z},
 file_attached = {true},
 profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
 group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
 last_modified = {2022-09-19T10:49:41.205Z},
 read = {false},
 starred = {false},
 authored = {false},
 confirmed = {true},
 hidden = {false},
 folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
 private_publication = {false},
 abstract = {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.},
 bibtype = {article},
 author = {Schmid, Cordelia and Mohr, Roger and Bauckhage, Christian},
 doi = {10.1023/A:1008199403446},
 journal = {International Journal of Computer Vision},
 number = {2}
}

Downloads: 0