An images-based 3d model retrieval approach

Authors:
Yuehong Wang;Rujie Liu;Takayuki Baba;Yusuke Uehara;Daiki Masumoto;Shigemi Nagata
Affiliations:
Fujitsu Research and Development Center LTD., Beijing, China;Fujitsu Research and Development Center LTD., Beijing, China;Fujitsu Laboratories LTD., Kawasaki, Japan;Fujitsu Laboratories LTD., Kawasaki, Japan;Fujitsu Laboratories LTD., Kawasaki, Japan;Fujitsu Laboratories LTD., Kawasaki, Japan
Venue:
MMM'08 Proceedings of the 14th international conference on Advances in multimedia modeling
Year:
2008

Citing 5
Cited 2

Topology matching for fully automatic similarity estimation of 3D shapes

Proceedings of the 28th annual conference on Computer graphics and interactive techniques
Shape distributions

ACM Transactions on Graphics (TOG)
A Survey of Content Based 3D Shape Retrieval Methods

SMI '04 Proceedings of the Shape Modeling International 2004
The Princeton Shape Benchmark

SMI '04 Proceedings of the Shape Modeling International 2004
Thickness Histogram and Statistical Harmonic Representation for 3D Model Retrieval

3DPVT '04 Proceedings of the 3D Data Processing, Visualization, and Transmission, 2nd International Symposium

3D object classification using salient point patterns with application to craniofacial research

Pattern Recognition
Recognising 3D products and sourcing part documentation with scanned data

Computers in Industry

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an images based 3D model retrieval method in which each model is described by six 2D images. The images are generated by three steps: 1) the model is normalized based on the distribution of the surface normal directions; 2) then, the normalized model is uniformly sampled to generate a number of random points; 3) finally, the random points are projected along six directions to create six images, each of which is described by Zernike moment feature. In the comparison of two models, six images of each model are naturally divided into three pairs, and the similarity between two models is calculated by summing up the distances of all corresponding pairs. The effectiveness of our method is verified by comparative experiments. Meanwhile, high matching speed is achieved, e.g., it takes about 3e-5 seconds to compare two models using a computer with Pentium IV 3.00GHz CPU.