A two-tiered retrieval method of CAD model based on spectral theory and face code

Li Hao; Rong Mo; Weilong Niu; Zhoupeng Han

doi:10.1117/12.2524208

6 May 2019 A two-tiered retrieval method of CAD model based on spectral theory and face code

Li Hao, Rong Mo, Weilong Niu, Zhoupeng Han

Proceedings Volume 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018); 1106924 (2019) https://doi.org/10.1117/12.2524208
Event: Tenth International Conference on Graphic and Image Processing (ICGIP 2018), 2018, Chengdu, China

Abstract

This paper proposes a novel two-tiered retrieval method for CAD models based on the graph spectral theory and face code to match three dimension (3D) CAD models with undirected graphs. This approach applies a hierarchical feature descriptor, a two-tiered retrieval mechanism to represent and retrieval CAD models. The first tier is rapid rough matching, which is a similarity metric by weighted bipartite graph matching between library models and retrieval models. Second tier is exact matching through comparing face code. Experimental results show the proposed method could improve the efficiency of retrieval performance, and achieve the reuse of CAD model.

Citation Download Citation

Li Hao, Rong Mo, Weilong Niu, and Zhoupeng Han "A two-tiered retrieval method of CAD model based on spectral theory and face code", Proc. SPIE 11069, Tenth International Conference on Graphics and Image Processing (ICGIP 2018), 1106924 (6 May 2019); https://doi.org/10.1117/12.2524208

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available