Share Email Print
cover

Proceedings Paper

3D discriminative feature selection for mid-level representation
Author(s): Jie Zhang; Junhua Sun
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

Discriminative feature representation is significant for boosting the performance of computer vision tasks covering different levels. Traditional low-level feature representation exhibits good generalization and robustness while lacks of enough discriminant ability. In this paper, we focus on 3D local shape features, proposing a discriminative feature selection method, which is also closely related with mid-level 3D shape representation. We firstly design a histogram-signature hybrid 3D local shape descriptor using 3D geometrical information from the 3D point cloud of a tested object. Then, we propose a discrimination power metric to automatically select a collection of discriminative local shapes from a candidate set, resulting in a mid-level shape feature representation. The proposed algorithm is applied in the task of multi-view 2.5D scan registration. The performance was verified on public and popular instance-level 3D object datasets. Both qualitative and quantitative results demonstrate the effectiveness and robustness of the proposed algorithm on different 3D objects. Compared with low-level 3D object representation, the discriminative feature selection for 3D shape feature representation allows for superior performance with higher precision and recall rate.

Paper Details

Date Published: 24 October 2017
PDF: 8 pages
Proc. SPIE 10462, AOPC 2017: Optical Sensing and Imaging Technology and Applications, 104620X (24 October 2017); doi: 10.1117/12.2282948
Show Author Affiliations
Jie Zhang, BeiHang Univ. (China)
Junhua Sun, BeiHang Univ. (China)


Published in SPIE Proceedings Vol. 10462:
AOPC 2017: Optical Sensing and Imaging Technology and Applications
Yadong Jiang; Haimei Gong; Weibiao Chen; Jin Li, Editor(s)

© SPIE. Terms of Use
Back to Top