A Method of Feature Extraction and Compression of 3D Model

DOI

10.2991/icadme-15.2015.101How to use a DOI?

Keywords

Pre-processing; Perspective projection; Fourier transform; Compression

Abstract

Feature extraction is a major concern in 3D retrieval, which decides its performance and efficiency. Therefore, feature extraction and compression become the keys to guarantee the retrieval’s performance and speed. The process is as follows: firstly, transform the standard 3D model to 2D images by perspective projection; secondly, transform these images to frequency domain by Fourier Transformation to get the vectors feature; lastly, compress the vectors to six dimensions. This algorithm solves the contradictions between large information and low speed, low information and low performance. Proved by the experiment: the solution is more effective and more rapidly.

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  - Zuojun Liu
AU  - Lihong Li
AU  - Mi Yu
PY  - 2015/10
DA  - 2015/10
TI  - A Method of Feature Extraction and Compression of 3D Model
BT  - Proceedings of the 5th International Conference on Advanced Design and Manufacturing Engineering
PB  - Atlantis Press
SP  - 505
EP  - 509
SN  - 2352-5401
UR  - https://doi.org/10.2991/icadme-15.2015.101
DO  - 10.2991/icadme-15.2015.101
ID  - Liu2015/10
ER  -