Abstract
In this paper a novel 3D model retrieval method that employs multi-level spherical moment analysis and relies on voxelization and spherical mapping of the 3D models is proposed. For a given polygon-soup 3D model, first a pose normalization step is done to align the model into a canonical coordinate frame so as to define the shape representation with respect to this orientation. Afterward we rasterize its exterior surface into cubical voxel grids, then a series of homocentric spheres with their center superposing the center of the voxel grids cut the voxel grids into several spherical images. Finally moments belonging to each sphere are computed and the moments of all spheres constitute the descriptor of the model. Experiments showed that Euclidean distance based on this kind of feature vector can distinguish different 3D models well and that the 3D model retrieval system based on this arithmetic yields satisfactory performance.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ankerst, M., Kastenmller, G., Peter, K.H., 1999. 3D Shape Histograms for Similarity Search and Classification in Spatial Database. Proceeding of the 6th International Symposium on Large Spatial Database, Hong Kong, China, p.207–226.
Chen, S.C., Chen, T., 2002. Retrieval of 3D Protein Structure. Proceedings of International Conference on Information Processing (ICIP 2002), Rochester, NY, p.34–43.
Chen, D., Ouhyoung, M., 2002a. A 3D Object Retrieval System Based on Multi-Resolution Reeb Graph. Proceedings of Computer Graphics Workshop, Taiwan, China, p.16–20.
Chen, D., Ouhyoung, M., 2002b. A 3D Model Alignment and Retrieval System. Proceedings of International Computer Symposium, Workshop on Multimedia Technologies, Hualien, Taiwan, p.1436–1443.
Chen, D., Tian, X., Shen, Y., 2003. On visual similarity based 3D model retrieval. Computer Graphics Forum, 22(3): 223–232. [doi:10.1111/1467-8659.00669]
Garland, M., Shaffer, E., 2002. A Multiphase Approach to Efficient Surface Simplification. Proceedings of IEEE Visualization, Boston, MA, p.117–124.
Hilaga, M., Shinagawa, Y., Kohmura, T., 2001. Topology Matching for Fully Automatic Similarity Estimation of 3D Shapes. Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH, Los Angeles, CA, p.203–212.
Horn, B., 1984. Extended Gaussian images. Proceedings of the IEEE, 72(12): 1671–1686.
Jobst, L., 2000. Content-Based Retrieval of 3D Models in Distributed Web Databases by Visual Shape Information. IEEE International Conference on Information Visualization, London, UK, p.82–87.
Min, P.K., Chen, J., Funkhouser, T., 2002. A 2D Sketch Interface for a 3D Model Search Engine. Computer Graphics Proceedings, Annual Conference Series, ACM SIGGRAPH 2002 Technical Sketch, San Autonio, Texas, p.334–341.
Osada, R., Funkhouser, T., Chazelle, B., 2001. Matching 3D Models with Shape Distributions. Proceedings International Conference on Shape Modeling and Applications SMA-01, Genoa, Italy, p.154–166. [doi:10.1109/SMA.2001.923386]
Osada, R., Funkhouser, T., Chazelle, B., 2002. Shape distributions. ACM Trans. on Graphics, 21(4):807–832. [doi:10.1145/571647.571648]
Patrick, M., 2004. A 3D Model Search Engine. Ph.D. Thesis, Princeton University.
Paquet, E., Rioux, M., 1997. A Query by Content Software for Three Dimensions Database Management. Proceedings International Conference on Recent Advances in 3-D Digital Imaging and Modeling (Cat No 97TB100134) IM-97, Ottawa, Canada, p.345–352. [doi:10.1109/IM.1997.603886]
Paquet, E., Rioux, M., 1998. A Content-based Search for VRML Database. Proceedings 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat No 98CB36231) CVPR-98, Santa Barbara, CA, p.541–546. [doi:10.1109/CVPR.1998.698658]
Shilane, P., Min, P., Kazhdan, M., Funkhouser, T., 2004. The Princeton Shape Benchmark. Shape Modelling International, Genova, Italy, p.373–385.
Suzuki, M.T., Kato, T., Otsu, N., 2000. A Similarity Retrieval of 3D Polygonal Model Using Rotation Invariant Shape Descriptors. Proceeding of IEEE International on Systems, Man, and Cybernetics, Nashville, Tennessee, p.2946–2952.
Tangelder, J.W., Veltkamp, R.C., 2003. Polyhedral model retrieval using weighted point sets. International Journal of Image and Graphics, 3(1):209–229. [doi:10.1142/S021946780300097X]
Vranic, D.V., Saupe, D., 2001a. 3D Shape Descriptor Based on 3D Fourier Transform. Proceeding of the EURASIP Conference on Digital Signal Processing of Multimedia Communications and Services, Budapest, Hungary, p.271–274.
Vranic, D.V., Saupe, D., 2001b. Tools for 3D Object Retrieval: Karhunen-Loeve Transform and Spherical Harmonics. IEEE Workshop on Multimedia Signal Processing (MMSP’2001), Cannes, p.293–298.
Vranic, D.V., Saupe, D., 2002. Description of 3D Shape Using a Complex Function on Sphere. Proceedings IEEE International Conference on Multimedia and Expo ICME-02, Lausanne, Switzerland, p.177–180. [doi:10.1109/ICME.2002.1035747]
Zhang, C., Chen, T., 2001. Efficient Feature Extraction for 2D/3D Objects in Mesh Representation. ICIP 2001.
Author information
Authors and Affiliations
Additional information
Project (No. 60573146) supported by the National Natural Science Foundation of China
Rights and permissions
About this article
Cite this article
Liu, W., He, Yj. Multi-level spherical moments based 3D model retrieval. J. Zhejiang Univ. - Sci. A 7, 1500–1507 (2006). https://doi.org/10.1631/jzus.2006.A1500
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1631/jzus.2006.A1500