Non-rigid Shape Registration using Curvature Information

Albane Borocco, Beatriz Marcotegui

2019

Abstract

This paper addresses a registration problem for an industrial control application: it meets the need to registrate a model on an image of a flexible object. We propose a non-rigid shape registration approach that deals with a great disparity of the number of points in the model and in the manufactured object. We have developed a method based on a classical minimization process combining a distance term and a regularization term. We observed that, even if the control points fall on the object boundary, the registration failed on high curvature points. In this paper we add a curvature-based term in order to improve the registration on object extremities. We validate our approach on a real industrial application. The addition of this curvature term reduces by two the error of the inner boundaries location on the previously problematic cases of our database.

Paper Citation

in Harvard Style

Borocco A. and Marcotegui B. (2019). Non-rigid Shape Registration using Curvature Information. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP; ISBN 978-989-758-354-4, SciTePress, pages 334-340. DOI: 10.5220/0007354903340340

in Bibtex Style

@conference{visapp19,
author={Albane Borocco and Beatriz Marcotegui},
title={Non-rigid Shape Registration using Curvature Information},
booktitle={Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP},
year={2019},
pages={334-340},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007354903340340},
isbn={978-989-758-354-4},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2019) - Volume 4: VISAPP
TI - Non-rigid Shape Registration using Curvature Information
SN - 978-989-758-354-4
AU - Borocco A.
AU - Marcotegui B.
PY - 2019
SP - 334
EP - 340
DO - 10.5220/0007354903340340
PB - SciTePress