Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold

Ryoma Yataka, Kazuhiro Fukui

2017

Abstract

In this paper, we propose a method for recognizing three-dimensional (3D) objects using multi-view depth images. To derive the essential 3D shape information extracted from these images for stable and accurate 3D object recognition, we need to consider how to integrate partial shapes of a 3D object. To address this issue, we introduce two ideas. The first idea is to represent a partial shape of the 3D object by a three-dimensional subspace in a high-dimensional vector space. The second idea is to represent a set of the shape subspaces as a subspace on a Grassmann manifold, which reflects the 3D shape of the object more completely. Further, we measure the similarity between two subspaces on the Grassmann manifold by using the canonical angles between them. This measurement enables us to construct a more stable and accurate method based on richer information about the 3D shape. We refer to this method based on subspaces on a Grassmann manifold as the Grassmann mutual subspace method (GMSM). To further enhance the performance of the GMSM, we equip it with powerful feature-extraction capabilities. The validity of the proposed method is demonstrated through experimental comparisons with several conventional methods on a hand-depth image dataset.

Paper Citation

in Harvard Style

Yataka R. and Fukui K. (2017). Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold . In Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-222-6, pages 208-216. DOI: 10.5220/0006204702080216

in Bibtex Style

@conference{icpram17,
author={Ryoma Yataka and Kazuhiro Fukui},
title={Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold},
booktitle={Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2017},
pages={208-216},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006204702080216},
isbn={978-989-758-222-6},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Three-dimensional Object Recognition via Subspace Representation on a Grassmann Manifold
SN - 978-989-758-222-6
AU - Yataka R.
AU - Fukui K.
PY - 2017
SP - 208
EP - 216
DO - 10.5220/0006204702080216