Advertisement

Automatic Combination of Feature Descriptors for Effective 3D Shape Retrieval

  • Biao Leng
  • Zheng Qin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4418)

Abstract

We focus on improving the effectiveness of content-based 3D shape retrieval. Motivated by retrieval performance of several individual 3D model feature vectors, we propose a novel method, called prior knowledge based automatic weighted combination, to improve the retrieval effectiveness. The method dynamically determines the weighting scheme for different feature vectors based on the prior knowledge. The experimental results show that the proposed method provides significant improvements on retrieval effectiveness of 3D shape search with several measures on a standard 3D database. Compared with two existing combination methods, the prior knowledge weighted combination technique has gained better retrieval effectiveness.

Keywords

Feature Vector Average Precision Retrieval Performance Weighted Combination Query Model 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bustos, B., et al.: Automatic selection and combination of descriptors for effective 3d similarity search. In: Proceedings of IEEE Sixth International Symposium on Multimedia Software Engineering (SME2004), Miami, USA, December 2004, pp. 514–521. IEEE Computer Society Press, Los Alamitos (2004)CrossRefGoogle Scholar
  2. 2.
    Bustos, B., et al.: Using entropy impurity for improved 3d object similarity search. In: Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Taipeh, Taiwan, June 2004, pp. 1303–1306. IEEE, Los Alamitos (2004)CrossRefGoogle Scholar
  3. 3.
    Bustos, B., et al.: Feature-based similarity search in 3d object databases. ACM Computing Surveys 37(4), 345–387 (2005)CrossRefGoogle Scholar
  4. 4.
    Ricardo, B.Y., Berthier, R.N.: Modern Information Retrieval. Addison-Wesley, Cambridge (1999)Google Scholar
  5. 5.
    Vranic, D.V.: 3D Model Retrieval. PhD thesis, University of Leipzig, Leipzig, Germany (2004)Google Scholar
  6. 6.
    Vranic, D.V.: Desire: a composite 3d-shape descriptor. In: Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Amsterdam, Holand, July 2005, pp. 962–965. IEEE, Los Alamitos (2005)CrossRefGoogle Scholar
  7. 7.
    Vranic, D.V., Saupe, D.: Description of 3d-shape using a complex function on the sphere. In: Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Lausanne, Switzerland, August 2002, pp. 177–180. IEEE, Los Alamitos (2002)CrossRefGoogle Scholar
  8. 8.
    Chen, D.Y., et al.: On visual similarity based 3d model retrieval. Computer Graphics Forum 22(3), 223–232 (2003)CrossRefGoogle Scholar
  9. 9.
    Paquet, E., Rioux, M.: Nefertiti: a query by content software for three-dimensional models databases management. Image and Vision Computing 17(2), 157–166 (1999)CrossRefGoogle Scholar
  10. 10.
    Leifman, G., Meir, R., Tal, A.: Semantic-oriented 3d shape retrieval using relevance feedback. The Visual Computer 21(8-10), 865–875 (2005)CrossRefGoogle Scholar
  11. 11.
    Yeh, J.S., et al.: A web-based three-dimensional protein retrieval system by matching visual similarity. Bioinformatics 21, 3056–3057 (2005)CrossRefGoogle Scholar
  12. 12.
    Pu, J.T., Ramani, K.: On visual similarity based 2d drawing retrieval. Computer-Aided Design 38(3), 249–259 (2006)CrossRefGoogle Scholar
  13. 13.
    Kazhdan, M., et al.: A reflective symmetry descriptor for 3d models. Algorithmica 38(1), 201–225 (2003)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Rotation invariant spherical harmonic representation of 3d shape descriptors. In: Proceedings of the 2003 Eurographics symposium on Geometry processing, Aachen, Germany, June 2003, pp. 156–164 (2003)Google Scholar
  15. 15.
    Kazhdan, M., Funkhouser, T., Rusinkiewicz, S.: Shape matching and anisotropy. ACM Transactions on Graphics 23(3), 623–629 (2004)CrossRefGoogle Scholar
  16. 16.
    Iyer, N., et al.: Three-dimensional shape searching: state-of-the-art review and future trends. Computer-Aided Design 37(5), 509–530 (2005)CrossRefGoogle Scholar
  17. 17.
    Min, P., Kazhdan, M., Funkhouser, T.: A comparison of text and shape matching for retrieval of online 3d models. In: Heery, R., Lyon, L. (eds.) ECDL 2004. LNCS, vol. 3232, pp. 209–220. Springer, Heidelberg (2004)Google Scholar
  18. 18.
    Shilane, P., et al.: The princeton shape benchmark. In: Proceedings of Shape Modeling and Applications (SMI), Palazzo Ducale, Genova, Italy, June 2004, pp. 167–178 (2004)Google Scholar
  19. 19.
    Ohbuchi, R., Nakazawa, M., Takei, T.: Retrieving 3d shapes based on their appearance. In: Proceedings of the 5th ACM SIGMM international workshop on Multimedia information retrieval, Berkeley, California, USA, November 2003, pp. 39–45. ACM Press, New York (2003)CrossRefGoogle Scholar
  20. 20.
    Osada, R., et al.: Shape distributions. ACM Transactions on Grgphics 21(4), 807–832 (2002)CrossRefGoogle Scholar
  21. 21.
    Hou, S.Y., Lou, K.Y., Ramani, K.: Svm-based semantic clustering and retrieval of a 3d model dababase. Journal of Computer Aided Design and Application 2, 155–164 (2005)Google Scholar
  22. 22.
    Funkhouser, T., et al.: Shape-based retrieval and analysis of 3d models. Communications of the ACM 48(6), 58–64 (2005)CrossRefGoogle Scholar
  23. 23.
    Regli, W.C., Cicirello, V.A.: Managing digital libraries for computer-aided design. Computer-Aided Design 32(2), 119–132 (2000)CrossRefGoogle Scholar

Copyright information

© Springer Berlin Heidelberg 2007

Authors and Affiliations

  • Biao Leng
    • 1
  • Zheng Qin
    • 1
  1. 1.Department of Computer Science & Technology, Tsinghua University, 100084, Beijing, China, School of Software, Tsinghua University, 100084, BeijingChina

Personalised recommendations