Local Shape Similarity Retrieval of Mechanical Parts

DOI

10.2991/mmeceb-15.2016.1How to use a DOI?

Keywords

3D model retrieval; 3D shape analysis; design reuse; part database

Abstract

A scale-invariant shape feature is proposed. The shape feature is extracted on gray voxel models by a SIFT-like algorithm to describe the local shape information of 3D models. Shape feature vectors are constructed by a BoF method. A distance function that supports the part-in-whole matching is employed to compute the dissimilarity between 3D models. Experiments demonstrate that the proposed method achieves a satisfactory retrieval performance.

Copyright

© 2016, 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  - Jiale Wang
AU  - Yin Jun
PY  - 2015/12
DA  - 2015/12
TI  - Local Shape Similarity Retrieval of Mechanical Parts
BT  - Proceedings of the 2015 2nd International Conference on Machinery, Materials Engineering, Chemical Engineering and Biotechnology
PB  - Atlantis Press
SP  - 1
EP  - 5
SN  - 2352-5401
UR  - https://doi.org/10.2991/mmeceb-15.2016.1
DO  - 10.2991/mmeceb-15.2016.1
ID  - Wang2015/12
ER  -