English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Most computer vision application rely on algorithms finding localcorrespondences between different images. These algorithms detect and comparestable local invariant descriptors centered at scale-invariant keypoints.Because of the importance of the problem, new keypoint detectors anddescriptors are constantly being proposed, each one claiming to perform better(or to be complementary) to the preceding ones. This raises the question of afair comparison between very diverse methods. This evaluation has been mainlybased on a repeatability criterion of the keypoints under a series of imageperturbations (blur, illumination, noise, rotations, homotheties, homographies,etc). In this paper, we argue that the classic repeatability criterion isbiased towards algorithms producing redundant overlapped detections. Tocompensate this bias, we propose a variant of the repeatability rate takinginto account the descriptors overlap. We apply this variant to revisit thepopular benchmark by Mikolajczyk et al., on classic and new feature detectors.Experimental evidence shows that the hierarchy of these feature detectors isseverely disrupted by the amended comparator.

Comparing Feature Detectors: A bias in the repeatability criteria, and how to correct it