Comparing and evaluating interest points

TLDR

Computer vision tasks rely on feature extraction, for which interest points serve as key features. The study aims to quantitatively assess interest points’ repeatability and information content. The authors introduce repeatability rate and information content as evaluation criteria and compare several detectors using these metrics. Interest points are geometrically stable, highly distinctive, and effective for image matching, with detector choice influencing performance and a best‑performing detector identified.

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.