Normalized Gradient Vector Diffusion and Image Segmentation

  • Zeyun Yu
  • Chandrajit Bajaj
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2352)


In this paper, we present an approach for image segmentation, based on the existing Active Snake Model and Watershed-based Region Merging. Our algorithm includes initial segmentation using Normalized Gradient Vector Diffusion (NGVD) and region merging based on Region Adjacency Graph (RAG). We use a set of heat diffusion equations to generate a vector field over the image domain, which provides us with a natural way to define seeds as well as an external force to attract the active snakes. Then an initial segmentation of the original image can be obtained by a similar idea as seen in active snake model. Finally an RAG-based region merging technique is used to find the true segmentation as desired. The experimental results show that our NGVD-based region merging algorithm overcomes some problems as seen in classic active snake model. We will also see that our NGVD has several advantages over the traditional gradient vector diffusion.


Image segmentation Gradient vector diffusion Heat diffusion equation Active snake model Watershed method Region merging 


  1. 1.
    Kass, M., Witkin, A., Terzopoulos, D.: Snake: active contour model. Int. J. Computer Vision. 1(1987) 321–331CrossRefGoogle Scholar
  2. 2.
    Xu, C., Prince, J.L.: Snakes, shapes, and gradient vector flow. IEEE Trans. Image Processing. 7(3) (1998) 359–369zbMATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Xu, C., Prince, J.L.: Generalized gradient vector flow external force for active contour. Signal Processing-An International Journal. 71(2) (1998) 131–139zbMATHCrossRefGoogle Scholar
  4. 4.
    Xu, C., Prince, J.L.: Gradient Vector Flow Deformable Models. Handbook of Medical Imaging, edited by Isaac Bankman, Academic Press. September, 2000Google Scholar
  5. 5.
    Cohen, L.D., Cohen, I.: Finite-element method for active contour models and balloons for 2D and 3D images. IEEE Trans. on Pattern Analysis and Machine Intelligence. 15(11) (1993) 1131–1147CrossRefGoogle Scholar
  6. 6.
    Terzopoulos, D., Witkin, A., Kass, M.: Constraints on deformable models: recovering 3D shape and non-rigid motion. Artificial Intelligence. 36(1) (1988) 91–123zbMATHCrossRefGoogle Scholar
  7. 7.
    Malladi, R., Sethian, J.A., Vemuri, B.C.: Shape modeling with front propagation: A level set approach. IEEE Trans. on Pattern Analysis and Machine Intelligence. 17 (1995) 158–175CrossRefGoogle Scholar
  8. 8.
    Leroy B., Herliin, I., Cohen, L.D.: Multi-resolution algorithm for active contour models. In 12th Int. Conf. Analysis and Optimization of System. (1996) 58–65Google Scholar
  9. 9.
    Cohen, L.D.: On active contour models and balloons. CVGIP: Image Understanding. 53 (1991) 211–218zbMATHCrossRefGoogle Scholar
  10. 10.
    Davatzikos, C., Prince, J.L.: An active contour model for mapping the cortex. IEEE Trans. Medical Image. 14 (1995) 65–80CrossRefGoogle Scholar
  11. 11.
    Abrantes, A.J., Marques, J.S.: A class of constrained clustering algorithm for object boundary extraction. IEEE Trans. Image Processing. 5 (1996) 1507–1521CrossRefGoogle Scholar
  12. 12.
    Prince, J.L., Xu, C.: A new external force model for snakes. Proc. 1996 Image and Multidimensional Signal Processing Workshop. (1996) 30–31Google Scholar
  13. 13.
    Perona, P., Malik, J.: Scale-space and edge detection using anisotropic diffusion. IEEE Trans. on Pattern Analysis and Machine Intelligence. 12(7) (1990) 629–639CrossRefGoogle Scholar
  14. 14.
    McInerney, T., Terzopoulos, D.: A dynamic finite element surface model for segmentation and tracking in multidimensional medical images with application to cardiac 4D image analysis. Comput. Med. Imag. Graph.. 19 (1995) 69–83CrossRefGoogle Scholar
  15. 15.
    Leymarie, F., Levine, M.D.: Tracking deformable objects in the plane using an active contour model. IEEE Trans. on Pattern Analysis and Machine Intelligence. 15 (1993) 617–634CrossRefGoogle Scholar
  16. 16.
    Terzopoulos, D., Szeliski, R.: Tracking with Kalman snakes. in Active Vision, A. Blake and A. Yuille, Eds. Cambridge, MA: MIT Press, (1992) 3–20Google Scholar
  17. 17.
    Malladi, R., Sethian, J.A.: A real-time algorithm for medical shape recovery. in Proceedings of International Conference on Computer Vision. Mumbai, India. (1998) 304–310Google Scholar
  18. 18.
    Shah, J.: A common framework for curve evolution, segmentation and anisotropic diffusion. in Proceedings of International Conference on Computer Vision and Pattern Recognition: CVPR’96. June (1996) 136–142Google Scholar
  19. 19.
    Weickert, J.: Fast segmentation methods based on partial differential equations and the watershed transformation. P. Levi, R.-J. Ahlers, F. May, M. Schanz (Eds.), Mustererkennung 1998, Springer, Berlin. (1998) 93–100Google Scholar
  20. 20.
    Haris, K., Efstratiadis, S.N., Maglaveras, N., Katsaggelos, A.K.: Hybrid image segmentation using watersheds and fast region merging. IEEE Trans. on Image Processing. 7(12) (1998) 1684–1699CrossRefGoogle Scholar
  21. 21.
    Moscheni, F., Bhattacharjee, S., Kunt, M.: Spatiotemporal segmentation based on region merging. IEEE Trans. on Pattern Analysis and Machine Intelligence. 20(9) (1998) 897–915CrossRefGoogle Scholar
  22. 22.
    Vincent, L., Soille, P.: Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans. on Pattern Analysis and Machine Intelligence. 13(6) (1991) 583–598CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Zeyun Yu
    • 1
  • Chandrajit Bajaj
    • 1
  1. 1.Department of Computer ScienceUniversity of Texas at AustinAustinUSA

Personalised recommendations