Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization

Nabila Zrira, Mohamed Hannat, El Houssine Bouyakhf, Haris Ahmad khan

2017

Abstract

Object categorization has been an important task of computer vision research in recent years. In this paper, we propose a new approach for representing and learning 3D object categories. First, We extract the Viewpoint Feature Histogram (VFH) descriptor from point clouds and then we learn the resulting features using deep learning architectures. We evaluate the performance of both generative and discriminative deep belief network architectures (GDBN/DDBN) for object categorization task. GDBN trains a sequence of Restricted Boltzmann Machines (RBMs) while DDBN uses a new deep architecture based on RBMs and the joint density model. Our results show the power of discriminative model for object categorization and outperform state-of-the-art approaches when tested on the Washington RGBD dataset.

Paper Citation

in Harvard Style

Zrira N., Hannat M., Bouyakhf E. and Ahmad khan H. (2017). Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization . In Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017) ISBN 978-989-758-226-4, pages 98-107. DOI: 10.5220/0006151100980107

in Bibtex Style

@conference{visapp17,
author={Nabila Zrira and Mohamed Hannat and El Houssine Bouyakhf and Haris Ahmad khan},
title={Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization},
booktitle={Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)},
year={2017},
pages={98-107},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006151100980107},
isbn={978-989-758-226-4},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 12th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 5: VISAPP, (VISIGRAPP 2017)
TI - Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization
SN - 978-989-758-226-4
AU - Zrira N.
AU - Hannat M.
AU - Bouyakhf E.
AU - Ahmad khan H.
PY - 2017
SP - 98
EP - 107
DO - 10.5220/0006151100980107