loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Xupeng Wang 1 ; Ferdous Sohel 2 ; Mohammed Bennamoun 3 ; Yulan Guo 4 and Hang Lei 5

Affiliations: 1 University of Electronic Science and Technology of China and University of Western Australia, China ; 2 Murdoch University, Australia ; 3 University of Western Australia, Australia ; 4 National University of Defense Technology and University of Western Australia, China ; 5 The University of Electronic Science and Technology of China, China

Keyword(s): 3D Deformable Shapes, Interest Point Detection, Persistent Homology, Diffusion Geometry, Heat Kernel Signature Function.

Related Ontology Subjects/Areas/Topics: Computer Vision, Visualization and Computer Graphics ; Geometric Computing ; Geometry and Modeling

Abstract: Several approaches for interest point detection on rigid shapes have been proposed, but few are available for non-rigid shapes. It is a very challenging task due to the presence of the large degrees of local deformations. This paper presents a novel method called persistence-based heat kernel signature (pHKS). It consists of two steps: scalar field construction and interest point detection. We propose to use the heat kernel signature function at a moderately small time scale to construct the scalar field. It has the advantage of being stable under various transformations. Based on the predefined scalar field, a 0-dimensional persistence diagram is computed, and the local geometric and global structural information of the shape are captured at the same time. Points with local maxima and high persistence are selected as interest points. We perform a comprehensive evaluation on two popular datasets (i.e., PHOTOMESH and Interest Points Dataset) to show the effectiveness of our method. Co mpared with existing techniques, our interest point detector achieves a superior performance in terms of repeatability and distinctiveness. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.119.137.175

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Wang, X.; Sohel, F.; Bennamoun, M.; Guo, Y. and Lei, H. (2017). Persistence-based Interest Point Detection for 3D Deformable Surface. In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - GRAPP; ISBN 978-989-758-224-0; ISSN 2184-4321, SciTePress, pages 58-69. DOI: 10.5220/0006093800580069

@conference{grapp17,
author={Xupeng Wang. and Ferdous Sohel. and Mohammed Bennamoun. and Yulan Guo. and Hang Lei.},
title={Persistence-based Interest Point Detection for 3D Deformable Surface},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - GRAPP},
year={2017},
pages={58-69},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006093800580069},
isbn={978-989-758-224-0},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2017) - GRAPP
TI - Persistence-based Interest Point Detection for 3D Deformable Surface
SN - 978-989-758-224-0
IS - 2184-4321
AU - Wang, X.
AU - Sohel, F.
AU - Bennamoun, M.
AU - Guo, Y.
AU - Lei, H.
PY - 2017
SP - 58
EP - 69
DO - 10.5220/0006093800580069
PB - SciTePress