Title :
Feature based similarity search in simplified surface 3D model using interpolation method
Author :
Kim, Ami ; Gwun, Oubong ; Song, Juwhan
Author_Institution :
Div. of Electron. & Inf. Eng., Chonbuk Nat. Univ., Jeonju, South Korea
Abstract :
This paper proposes the feature descriptor for 3D model similarity search using the distribution of normal directions on the simplified surface. Feature descriptor of 3D model should be invariant to translation, rotation and scale for its model. So this paper normalizes all the model using PCA and preprocesses surface mesh simplification to robust against noise. The normal is sampled in proportion to each polygon´s area and then it is calculated by weight average method via angles and interpolated. We implemented the 3D model retrieval system and performed the similarity search test with the shape bench mark data provided by the Princeton University. Experimental results show the performance improvement of proposed algorithm from 24.7% to 32.2% in comparison with conventional methods by ANMRR.
Keywords :
content-based retrieval; feature extraction; image retrieval; interpolation; mesh generation; principal component analysis; solid modelling; 3D model retrieval system; PCA; feature based similarity search; feature descriptor; interpolation method; normal direction distribution; simplified surface 3D model; surface mesh simplification; weight average method; Gaussian distribution; Interpolation; Sampling methods;
Conference_Titel :
Digital Information Management, 2009. ICDIM 2009. Fourth International Conference on
Conference_Location :
Ann Arbor, MI
Print_ISBN :
978-1-4244-4253-9
Electronic_ISBN :
978-1-4244-4254-6
DOI :
10.1109/ICDIM.2009.5356790