3.9 Article

Content-based 3D mesh model retrieval from hand-written sketch

Publisher

SPRINGER HEIDELBERG
DOI: 10.1007/s12008-008-0038-4

Keywords

Shape retrieval; Content; based retrieval; Mesh model; Generic Fourier descriptor; Local binary pattern

Funding

  1. Japanese MEXT

Ask authors/readers for more resources

5 Recently, huge numbers of 3D models (solid, surface, and mesh models) have been archived in CA-X systems for industrial design, engineering, manufacturing and e-commerce. Efficient searching methods for 3D models become important for system users. For this purpose, a content-based 3D mesh model retrieval system from handwritten sketch is proposed in this paper. In the system, the user puts a query in the form of a 2D hand-written sketch to a 3D mesh model database, and the system automatically returns a set of mesh models whose 2D views are similar to the input sketch. Generic Fourier Descriptor and Local Binary Pattern which are features invariant to rotation, translation and scaling of 2D images are used to measure dissimilarities between a query sketch and images generated from 3D models. The effectiveness of the retrieval system is evaluated through case studies on industrial design process.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

3.9
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available