Please use this identifier to cite or link to this item:
http://hdl.handle.net/10071/28764
Author(s): | Proença, P. Gaspar, F. Dias, J. |
Editor: | George Bebis Richard Boyle Bahram Parvin Darko Koracin Baoxin Li Fatih Porikli Victor Zordan David Gotz James Klosowski Sabine Coquillart Xun Luo Min Chen |
Date: | 2013 |
Title: | Good appearance and shape descriptors for object category recognition |
Volume: | 8033 |
Book title/volume: | Advances in visual computing: 9th International Symposium, ISVC 2013, Proceedings |
Pages: | 385 - 394 |
Collection title and number: | Lecture Notes in Artificial Intelligence; |
Reference: | Proença, P., Gaspar, F., & Dias, J. (2013). Good appearance and shape descriptors for object category recognition. Em G. Bebis, R. Boyle, B. Parvin, D. Koracin, B. Li, F. Porikli, V. Zordan, J. Klosowski, S. Coquillart, X. Luo, M. Chen, & D. Gotz (Eds.). Advances in visual computing: 9th International Symposium, ISVC 2013, Proceedings (pp. 385-394). Springer. https://doi.org/10.1007/978-3-642-41914-0_38 |
ISSN: | 0302-9743 |
ISBN: | 978-3-642-41913-3 |
Keywords: | Information Intra class Learning-based approach Naive bayes Nearest neighbors Object category recognition Shape based Shape descriptors |
Abstract: | In the problem of object category recognition, we have studied different families of descriptors exploiting RGB and 3D information. Furthermore, we have proven practically that 3D shape-based descriptors are more suitable for this type of recognition due to low shape intra-class variance, as opposed to image texture-based. In addition, we have also shown how an efficient Naive Bayes Nearest Neighbor (NBNN) classifier can scale to a large hierarchical RGB-D Object Dataset [2] and achieve, with a single descriptor type, an accuracy close to state-of-art learning based approaches using combined descriptors. |
Peerreviewed: | yes |
Access type: | Open Access |
Appears in Collections: | ISTAR-CRI - Comunicações a conferências internacionais |
Files in This Item:
File | Size | Format | |
---|---|---|---|
conferenceObject_24329.pdf | 1,55 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.