Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization
| Affiliation auteurs | !!!! Error affiliation !!!! |
| Titre | Generative vs. Discriminative Deep Belief Netwok for 3D Object Categorization |
| Type de publication | Conference Paper |
| Year of Publication | 2017 |
| Auteurs | Zrira N, Hannat M, Bouyakhf EHoussine, Khan HAhmad |
| Editor | Imai F, Tremeau A, Braz J |
| Conference Name | PROCEEDINGS OF THE 12TH INTERNATIONAL JOINT CONFERENCE ON COMPUTER VISION, IMAGING AND COMPUTER GRAPHICS THEORY AND APPLICATIONS (VISIGRAPP 2017), VOL 5 |
| Publisher | Inst Syst & Technologies Informat, Control & Commun; ACM SIGGRAPH; AFIG; Eurographics |
| Conference Location | AV D MANUELL, 27A 2 ESQ, SETUBAL, 2910-595, PORTUGAL |
| ISBN Number | 978-989-758-226-4 |
| Mots-clés | 3D Object Categorization, Bback-propagation, DDBN, GDBN, Joint Density Model, point clouds, RBM, Viewpoint Feature Histogram (VFH) |
| Résumé | 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. |
| DOI | 10.5220/0006151100980107 |