A new deformable model for 3D image segmentation

  • Zixin Zhang
  • Michael Braun
  • Phillip Abbott
Poster Session A: Color & Texture, Enhancement, Image Analysis & Pattern Recognition, Segmentation
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1310)


A fully 3D active surface model is presented with self-inflation and self-deflation forces. The model makes full use of 3D image information, deforms locally and allowes strong deformation. The self-inflation and self-deflation forces enable the active surface to travel a long distance without the help from any external forces. We introduce a method of adapting model parameters, which enables our model to bypass some noise and irrelevant edge points. The model is tested with synthetic and real images. Accurate segmentation results are obtained in the presence of image noise and imperfect image data. Importantly, the model is capable of converging to the correct boundary even if the initial estimate is not close. Computational efficiency of segmentation with our model is addressed.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Bulpitt A.J. and Efford N.D.: An effective 3d deformable model with a self-optimising mesh. Image Vision Computing Vol.14 pp 573–580, August 1996.Google Scholar
  2. 2.
    Cohen L.D.: On active contour models and balloons. Computer Graphics and Image Processing: Image Understanding Vol.53, No.2, pp 211–218, 1991Google Scholar
  3. 3.
    Cohen L.D. & Cohen I.: Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans. Pattern Analysis and Machine Intelligence Vol.PAMI-15, No.11, pp 1131–1147, 1993Google Scholar
  4. 4.
    Delingette H.: Adaptive and deformable models based on simplex meshes. In IEEE Computer Vision and Pattern Recognition CVPR'94, pp 152–157 1994Google Scholar
  5. 5.
    Hoppe H. et al. Piecewise smooth surface reconstruction. Computer Graphics Proceedings, Annual Conference Series, 1994 SIGGRAPH 94, pp 295–302 1994Google Scholar
  6. 6.
    Huang W.C. & Goldgof D.B.: Left ventricle motion modeling and analysis by adaptive-size physically-based models. SPIE—Biomedical Image Processing and Three-Dimensional Microscopy Vol.1660, pp 299–310 1992Google Scholar
  7. 7.
    Gupta A., O'Donnell T. & Singh A.: A 3-D deformable model for segmentation and tracking of anisotropic cine cardiac MR images. SPIE-Image Processing Vol.2167, pp 77–86, 1994Google Scholar
  8. 8.
    Kass M., Witkin A. & Terzopoulos D.: Snakes: active contour models. International Journal of Computer Vision Vol.1, pp 321–331, 1988Google Scholar
  9. 9.
    Leymarie F. & Levine M.D.: Tracking deformable objects in the plane using an active contour model. IEEE Trans. Pattern Analysis and Machine Intelligence Vol.PAMI-15, No.6, pp 617–634, 1993Google Scholar
  10. 10.
    Rivara M.C.: Algorithms for refining triangular grids suitable for adaptive and multigrid techniques. International Journal for mathematical methods in engineering Vol.20, pp 745–756, 1984Google Scholar
  11. 11.
    Terzopoulos D., Witkin A. & Kass M.: Constraints on deformable models: recovering 3D shape and nonrigid motion. Artificial Intelligence Vol.36, pp 91–123, 1988Google Scholar
  12. 12.
    Terzopoulos D. & Vasilescu M.: Adaptive surface reconstruction. SPIE—Sensor fusion III: 3-D perception and reconstruction Vol.1383, pp 257–264, 1990Google Scholar
  13. 13.
    Whitaker J.M. & Braun M.: Three dimensional image segmentation using active contours with interslice energy. Proc. APRS/CBT Image Segmentation Workshop, Sydney, Australia pp 47–51, December 1996Google Scholar
  14. 14.
    Williams D.J. & Shah M.: A fast algorithm for active contours and curvature estimation. Computer Graphics and Image Processing: Image Understanding Vol.55, No.1, pp 14–26, 1992Google Scholar
  15. 15.
    Zhang Z. & Braun M.: Fully 3D active surface models with self-inflation and self-deflation forces. Proc. IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'97) San Juan, Puerto Rico, June 1997Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Zixin Zhang
    • 1
  • Michael Braun
    • 1
  • Phillip Abbott
    • 1
  1. 1.Department of Applied PhysicsUniversity of Technology, SydneyBroadwayAustralia

Personalised recommendations