SPD Siamese Neural Network for Skeleton-based Hand Gesture Recognition

Mohamed Akremi, Rim Slama, Hedi Tabia

2022

Abstract

This article proposes a new learning method for hand gesture recognition from 3D hand skeleton sequences. We introduce a new deep learning method based on a Siamese network of Symmetric Positive Definite (SPD) matrices. We also propose to use the Contrastive Loss to improve the discriminative power of the network. Experimental results are conducted on the challenging Dynamic Hand Gesture (DHG) dataset. We compared our method to other published approaches on this dataset and we obtained the highest performances with up to 95,60% classification accuracy on 14 gestures and 94.05% on 28 gestures.

Download


Paper Citation


in Harvard Style

Akremi M., Slama R. and Tabia H. (2022). SPD Siamese Neural Network for Skeleton-based Hand Gesture Recognition. In Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP, ISBN 978-989-758-555-5, pages 394-402. DOI: 10.5220/0010822500003124


in Bibtex Style

@conference{visapp22,
author={Mohamed Akremi and Rim Slama and Hedi Tabia},
title={SPD Siamese Neural Network for Skeleton-based Hand Gesture Recognition},
booktitle={Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,},
year={2022},
pages={394-402},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010822500003124},
isbn={978-989-758-555-5},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 4: VISAPP,
TI - SPD Siamese Neural Network for Skeleton-based Hand Gesture Recognition
SN - 978-989-758-555-5
AU - Akremi M.
AU - Slama R.
AU - Tabia H.
PY - 2022
SP - 394
EP - 402
DO - 10.5220/0010822500003124