Comparing and Evaluating Interest Points

Cordelia Schmid 1 Roger Mohr 1 Christian Bauckhage 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : Many computer vision tasks rely on feature extraction. Interest points are such features. This paper shows that interest points are geometrically stable under different transformations and have high information content (distinctiveness). These two properties make interest points very successful in the contest of image matching. To measure these two properties quantitatively, we introduce two evaluation criteria: repeatability rate and information content. The quality of the interest points depends on the detector used. In this paper several detectors are compared according to the criteria specified above. We determine which detector gives the best results and show that it satisfies the criteria well.
Document type :
Conference papers
Complete list of metadatas

https://hal.inria.fr/inria-00548328
Contributor : Thoth Team <>
Submitted on : Wednesday, December 22, 2010 - 12:01:13 PM
Last modification on : Wednesday, April 11, 2018 - 1:53:04 AM
Long-term archiving on: Wednesday, March 23, 2011 - 2:35:31 AM

File

schmid_iccv98.pdf
Files produced by the author(s)

Identifiers

Collections

IMAG | CNRS | INRIA | UGA

Citation

Cordelia Schmid, Roger Mohr, Christian Bauckhage. Comparing and Evaluating Interest Points. 6th International Conference on Computer Vision (ICCV '98), Jan 1998, Bombay, India. pp.230--235, ⟨10.1109/ICCV.1998.710723⟩. ⟨inria-00548328⟩

Share

Metrics

Record views

422

Files downloads

1006