A Neural Network Strategy for 3D Surface Registration

  • Heng Liu
  • Jingqi Yan
  • David Zhang
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3980)


3D surface registration is commonly used in shape analysis, surface representation, and medical image aided surgery. This technique is extremely computationally expensive and sometimes will lead to bad result configured with unstructured mass data for its’ iterative searching procedure and ill-suited distance function. In this paper, we propose a novel neural network strategy for surface registration. Before that, a typical preprocessing procedure-mesh PCA is used for coordinate direction normalization. The results and comparisons show such neural network method is a promising approach for 3D shape matching.


Neural Network Principal Component Analysis Less Mean Square Registration Result Surface Registration 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Hoffmann, M., Varady, L.: Free-Form Modeling Surfaces for Scattered Data by Neural Networks. Journal of Geometry and Graphics 1, 1–6 (1998)MathSciNetGoogle Scholar
  2. 2.
    Barhark, J., Fishcher, A.: Adaptive Reconstruction of Freeform Objects With 3D SOM Neural Networks Grids. In: Conference proceedings in Pacific Graphics, pp. 97–105 (2001)Google Scholar
  3. 3.
    Peng, L.W., Shamsuddin, S.M.: 3D Object Reconstruction and Representation Using Neural Networks. In: Proceedings GRAPHITE 2004, pp. 139–147 (2004)Google Scholar
  4. 4.
    Nasrabadi, M.N., Choo, Y.C.: Hopfield Network for Stereo Vision Correspondence. IEEE Transactions On eural Networks 3(1), 5–13 (1992)CrossRefGoogle Scholar
  5. 5.
    Tzovaras, D., Ploskas, N., Strintzis, M.G.: Rigid 3-D Motion Estimation Using Neural Networks and Initially Estimated 2-D Motion Data. IEEE Transactions On Circuits and Systems For video Technology 10(1), 158–165 (2000)CrossRefGoogle Scholar
  6. 6.
    Chen, T., Lin, W.-C., Chen, C.-T.: Artificial Neural Networks for 3-D Motion Analysis-Part I: Rigid Motion. IEEE Transactions On Neural Networks 6(6), 1386–1393 (1995)CrossRefGoogle Scholar
  7. 7.
    Besl, P., McKay, N.: A Method for Registration of 3-D Shapes. IEEE Trans. on Pattern Analysis and Machine Intelligence 14 (1992)Google Scholar
  8. 8.
    Feldmar, J., Malandain, G., Declerck, J., Ayache, N.: Extension of the ICP Algorithm to Nonrigid Intensity-Based Registration of 3D Volumes. Computer Vision and Image Understanding 66, 193–206 (1997)CrossRefGoogle Scholar
  9. 9.
    Rusinkiewicz, S., Levoy, M.: Efficient Variants of the ICP Algorithm. In: Proceedings of 3rd International Conference on 3D Digital Imaging and Modeling, pp. 145–152 (2001)Google Scholar
  10. 10.
    Vranic, D.V., Saupe, D., Richter, J.: Tools For 3D Object Retrieval: Karhunen-Loeve Transform and Spherical harmonics. In: Proceedings of IEEE 2001 Workshop Multimedia Signal Processing, pp. 293–298 (2001)Google Scholar
  11. 11.
    Schroder, P.: Subdivision as a Fundamental Building Block of Digital Geometry Processing Algorithms. Journal of Computational and Applied Mathematics 149(1), 207–219Google Scholar
  12. 12.
    Garland, M., Zhou, Y.: Quadric-based Simplification in any Dimension. Transactions on Graphics 24(2), 271–292 (2005)Google Scholar
  13. 13.
    Andrew, R.W.: Statistics Pattern Recognition, 2nd edn. Wiley, Chichester (2002)Google Scholar
  14. 14.
    Sameh Yamany, M., Aly Farag, A.: Surface Signatures: an Orientation Independent Free-Form Surface Representation Scheme for the Purpose of Objects Registration and Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence 24(8), 1105–1120 (2002)CrossRefGoogle Scholar
  15. 15.
    Sun, Y., Paik, J., Koschan, A., Page, D.L., Abidi, M.A.: Point Fingerprint: A New 3-D Object Representation Scheme. IEEE Transactions On System, Man, And Cybernetics-Part B: Cybernetics 33(4), 712–717 (2003)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Heng Liu
    • 1
    • 2
  • Jingqi Yan
    • 1
  • David Zhang
    • 3
  1. 1.Institute of Image Processing and Pattern Recognition, Min Hang DistrictShanghai Jiao Tong UniveristyShanghaiP.R. China
  2. 2.Southwest University of Science and TechnologyMianyangP.R. China
  3. 3.Department of ComputingThe Hong Kong Polytechnic UniversityHong KongP.R. China

Personalised recommendations