Efficient 3D Model Retrieval using Cubic Spline Interpolation-Shape Distribution

DOI

10.2991/ssemse-15.2015.323How to use a DOI?

Keywords

Shape Distribution; cubic spline interpolation; 3D model retrieval.

Abstract

3D model retrieval has been becoming a significant research field of modern information retrieval. To target at obtaining a better retrieval results, a novel Cubic Spline Interpolation-Shape Distribution algorithm (CSI-SD) is proposed. On the basis of traditional Shape Distribution algorithm (SD), The CSI-SD we propose improves the retrieval effect in two aspects: firstly, complete the normalization by gaining the 3D model’s gravity center; secondly, use the cubic spline interpolation curve to characterize shape distribution histogram more accurately. We conduct experiments based on the large-scale comprehensive benchmark, which was compiled in SHREC2014. Experimental results show that our CSI-SD algorithm outperforms initial SD and the 3D Shape Histogram algorithm according to six general evaluation metrics.

Copyright

© 2015, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Jingwei Li
AU  - Qiang Cai
AU  - Haisheng Li
PY  - 2015/11
DA  - 2015/11
TI  - Efficient 3D Model Retrieval using Cubic Spline Interpolation-Shape Distribution
BT  - Proceedings of the 2015 International Conference on Social Science, Education Management and Sports Education
PB  - Atlantis Press
SP  - 1256
EP  - 1259
SN  - 2352-5398
UR  - https://doi.org/10.2991/ssemse-15.2015.323
DO  - 10.2991/ssemse-15.2015.323
ID  - Li2015/11
ER  -