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

With the aim to improve the performance of feature matching, we present anunsupervised approach to fuse various local descriptors in the space ofhomographies. Inspired by the observation that the homographies of correctfeature correspondences vary smoothly along the spatial domain, our approachstands on the unsupervised nature of feature matching, and can select a gooddescriptor for matching each feature point. Specifically, the homography spaceserves as the common domain, in which a correspondence obtained by anydescriptor is considered as a point, for integrating various heterogeneousdescriptors. Both geometric coherence and spatial continuity amongcorrespondences are considered via computing their geodesic distances in thespace. In this way, mutual verification across different descriptors isallowed, and correct correspondences will be highlighted with a high degree ofconsistency (i.e., short geodesic distances here). It follows that one-classSVM can be applied to identifying these correct correspondences, and boosts theperformance of feature matching. The proposed approach is comprehensivelycompared with the state-of-the-art approaches, and evaluated on four benchmarksof image matching. The promising results manifest its effectiveness.

Descriptor Ensemble: An Unsupervised Approach to Descriptor Fusion in the Homography Space