[IPOL announce] new article: Matching of Weakly-Localized Features under Different Geometric Models
announcements about the IPOL journal
announce at list.ipol.im
Sat Feb 22 09:42:45 CET 2020
A new article is available in IPOL: http://www.ipol.im/pub/art/2020/247/
Erez Farhan,
Matching of Weakly-Localized Features under Different Geometric Models,
Image Processing On Line, 10 (2020), pp. 1–23.
https://doi.org/10.5201/ipol.2020.247
Abstract
Matching corresponding local patches between images is a fundamental
building block in many computer-vision algorithms, reducing the
high-dimensional challenge of recovering geometric relations between
images to a series of relatively simple and independent tasks. This
approach is geometrically very flexible and has clear computational
advantages over more convoluted global solutions. But it also has two
major practical shortcomings: 1) Sparsity: the need to rely on
high-quality repeatable features for matching drives current local
methods to discard low-textured image locations and leave them
unanalysed; 2) Reliability: the limited spatial context in which those
methods work often does not contain enough information for achieving
reliable matches. In this work, we target a major blind spot of local
feature matching: ill-textured locations. We observe that while classic
methods avoided using poorly localized features (e.g. edges) as matching
candidates, due to their low reliability, these features contain highly
valuable information for image registration. We show how, given the
appropriate geometric context, reliable matches can be produced from
these features, contributing to a better coverage of the scene. We
present a statistically attractive framework for encoding the
uncertainty that stems from using weakly localized matches into a
coupled geometric estimation and match extraction process. We examine
the practical application of the proposed framework to the problems of
guided matching and affine region expansion and show significant
improvement over preceding methods.
More information about the announce
mailing list