Advertisement

3D Freeform Surfaces from Planar Sketches Using Neural Networks

  • Usman Khan
  • Abdelaziz Terchi
  • Sungwoo Lim
  • David Wright
  • Sheng-Feng Qin
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4233)

Abstract

A novel intelligent approach into 3D freeform surface reconstruction from planar sketches is proposed. A multilayer perceptron (MLP) neural network is employed to induce 3D freeform surfaces from planar freehand curves. Planar curves were used to represent the boundaries of a freeform surface patch. The curves were varied iteratively and sampled to produce training data to train and test the neural network. The obtained results demonstrate that the network successfully learned the inverse-projection map and correctly inferred the respective surfaces from fresh curves.

Keywords

neural networks freeform surfaces sketch-based interfaces 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Lim, S., Lee, B., Duffy, A.: Incremental modelling of ambiguous geometric ideas (I-MAGI): representation and maintenance of vague geometry. Artificial Intelligence in Engineering 15, 93–108 (2001)CrossRefGoogle Scholar
  2. 2.
    Karpenko, O., Hughes, J., Raskar, R.: Free-form Sketching with variational implicit surfaces. Eurographics 21, 585–594 (2002)Google Scholar
  3. 3.
    Igarashi, T., Matsuoka, S., Tanaka, H.: Teddy: A Sketching Interface for 3D Freeform Design. In: 26th International Conference on Computer Graphics and Interactive Techniques, pp. 409–416 (1999)Google Scholar
  4. 4.
    Alexe, A., Gaildrat, V., Barth, L.: Interactive Modelling from Sketches using Spherical Implicit Functions. Computer Graphics, Virtual Reality, Visualisation and Interaction in Africa. In: Proceedings of the 3rd International Conference on Computer Graphics, Virtual Reality, Visualisation and Interaction in Africa, Africa, pp. 25–34 (2004)Google Scholar
  5. 5.
    Clowes, M.: On Seeing Things. Artificial Intelligence 2, 79–116 (1971)CrossRefGoogle Scholar
  6. 6.
    Lipson, H., Shpitalni, M.: Correlation-Based Reconstruction of a 3D Object from a Single Freehand Sketch. In: AAAI Spring Symposium on Sketch Understanding, Palo, Alto, USA, pp. 99–104 (2002)Google Scholar
  7. 7.
    Varley, P., Martin, R.: Estimating Depth from Line Drawings. Symposium on Solid Modelling, pp. 180–191. ACM press, Saarbrucken, Germany (2002)Google Scholar
  8. 8.
    Shpitalni, M., Lipson, H.: 3D conceptual design of sheet metal products by sketching. Journal of Materials Processing Technology 103, 128–134 (2000)CrossRefGoogle Scholar
  9. 9.
    Michalik, P., Kim, D.H., Bruderlin, B.D.: Sketch- and constraint-based design of B-spline surfaces. In: Proceedings of the seventh ACM symposium on Solid modelling and applications, pp. 297–304. ACM Press, Saarbrücken, Germany (2002)CrossRefGoogle Scholar
  10. 10.
    Nezis, K., Vosniakos, G.: Recognizing 2 1/2D shape features using a neural network and heuristics. Computer-Aided Design 29, 523–539 (1997)CrossRefGoogle Scholar
  11. 11.
    Peng, L.W., Shamsuddin, S.M.: 3D Object Reconstruction and Representation Using Neural Networks. In: Computer graphics and interactive techniques in Australia and South East Asia, Singapore, pp. 139–147 (2004)Google Scholar
  12. 12.
    Yuan, C., Niemann, H.: Neural Networks for appearance-based 3-D object recognition. Neurocomputing 51, 249–264 (2003)CrossRefGoogle Scholar
  13. 13.
    Gu, P., Yan, X.: Neural network approach to the reconstruction of freeform surfaces for reverse engineering. Computer Aided Design 27 (1995)Google Scholar
  14. 14.
    Hoffman, M., Varady, L.: Free-form Surfaces for Scattered Data by Neural Networks. Journal for Geometry and Graphics 2, 1–6 (1998)MathSciNetGoogle Scholar
  15. 15.
    Barhak, J., Fischer, A.: Adaptive reconstruction of freeform objects with 3D SOM neural network grids. Computer and Graphics 26, 745–751 (2002)CrossRefGoogle Scholar
  16. 16.
    Hornick, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Networks 2, 359–366 (1989)CrossRefGoogle Scholar
  17. 17.
    Rumelhart, D.E., McClelland, J.L.: Parallel Distributed Processing: Exploration in the Microstructure of Cognition, vol. 1. MIT Press, Massachusetts (1986)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Usman Khan
    • 1
  • Abdelaziz Terchi
    • 1
  • Sungwoo Lim
    • 1
  • David Wright
    • 1
  • Sheng-Feng Qin
    • 1
  1. 1.Brunel UniversityUxbridge, MiddlesexUnited Kingdom

Personalised recommendations