Corner Detection in Manifold-valued Images and in Vector Fields

Aleksei Shestov, Mikhail Kumskov

2020

Abstract

This paper is devoted to the problem of corner detection in manifold-valued images and in vector fields on manifolds. Our solution is a generalization of the Harris corner detector (C. Harris, 1988). As in the grayscale case, our algorithm is based on an estimation of a self-similarity of a point neighborhood. We define the self-similarity for the general cases and obtain approximations of it by an action of a bilinear form. This form can be viewed as a generalization of the structure tensor (M. Kass, 1987). The generalized structure tensor is then used as usual in the corner detection procedure. Finally, we describe future experiments: the algorithm will be tested on a task of chemical compounds classification.

Paper Citation

in Harvard Style

Shestov A. and Kumskov M. (2020). Corner Detection in Manifold-valued Images and in Vector Fields. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP; ISBN 978-989-758-402-2, SciTePress, pages 405-411. DOI: 10.5220/0009102304050411

in Bibtex Style

@conference{visapp20,
author={Aleksei Shestov and Mikhail Kumskov},
title={Corner Detection in Manifold-valued Images and in Vector Fields},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP},
year={2020},
pages={405-411},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009102304050411},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 4: VISAPP
TI - Corner Detection in Manifold-valued Images and in Vector Fields
SN - 978-989-758-402-2
AU - Shestov A.
AU - Kumskov M.
PY - 2020
SP - 405
EP - 411
DO - 10.5220/0009102304050411
PB - SciTePress