Using the Shape Gradient for Active Contour Segmentation: from the Continuous to the Discrete Formulation

Article

Abstract

A variational approach to image or video segmentation consists in defining an energy depending on local or global image characteristics, the minimum of which being reached for objects of interest. This study focuses on energies written as an integral on a domain of a function which can depend on this domain. The derivative of the energy with respect to the domain, the so-called shape derivative, is a function of a velocity field applied to the domain boundary. For a given, non-optimal domain, the velocity should be chosen such that the shape derivative is negative, thus indicating a way to deform the domain in order to decrease its energy. Minimizing the energy through an iterative deformation process is known as the active contour method. In the continuous framework, setting the velocity to the opposite of the gradient associated with the L2 inner product is a common practice. In this paper, it is noted that the negativity of the shape derivative is not preserved, in general, by the discretization of this velocity required by implementation. In order to guarantee that the negativity condition holds in the discrete framework, it is proposed to choose the velocity as a linear combination of pre-defined velocities. This approach also gives more flexibility to the active contour process by allowing to introduce some a priori knowledge about the optimal domain. Some experimental results illustrate the differences between the classical and the proposed approach.

Keywords

Segmentation Shape optimization Shape derivative Active contour Discrete formulation Variational approach 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Arulampalam, M.S., Maskell, S., Gordon, N., Clapp, T.: A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE Trans. Signal Process. 50, 174–188 (2002) CrossRefGoogle Scholar
  2. 2.
    Aubert, G., Barlaud, M., Faugeras, O., Jehan-Besson, S.: Image segmentation using active contours: Calculus of variations or shape gradients? SIAM J. Appl. Math. 63, 2128–2154 (2003) MATHCrossRefMathSciNetGoogle Scholar
  3. 3.
    Brigger, P., Hoeg, J., Unser, M.: B-spline snakes: A flexible tool for parametric contour detection. IEEE Trans. Image Process. 9, 1484–1496 (2000) MATHCrossRefMathSciNetGoogle Scholar
  4. 4.
    Caselles, V., Catté, F., Coll, T., Dibos, F.: A geometric model for active contours. Numer. Math. 66, 1–31 (1993) MATHCrossRefMathSciNetGoogle Scholar
  5. 5.
    Caselles, V., Kimmel, R., Sapiro, G.: Geodesic active contours. Int. J. Comput. Vis. 22, 61–79 (1997) MATHCrossRefGoogle Scholar
  6. 6.
    Chan, T., Vese, L.: Active contours without edges. IEEE Trans. Image Process. 10, 266–277 (2001) MATHCrossRefGoogle Scholar
  7. 7.
    Charpiat, G., Keriven, R., Pons, J.-P., Faugeras, O.: Designing spatially coherent minimizing flows for variational problems based on active contours. In: International Conference on Computer Vision, vol. 2, pp. 1403–1408 (2005) Google Scholar
  8. 8.
    Chesnaud, C., Réfrégier, P., Boulet, V.: Statistical region snake-based segmentation adapted to different physical noise models. IEEE Trans. Pattern Anal. Mach. Intell. 21, 1145–1156 (1999) CrossRefGoogle Scholar
  9. 9.
    Cremers, D., Schnörr, C.: Motion competition: Variational integration of motion segmentation and shape regularization. In: DAGM-Symposium, Lecture Notes in Computer Science, vol. 2449, pp. 472–480 (2002) Google Scholar
  10. 10.
    Cremers, D., Soatto, S.: Variational space-time motion segmentation. In: International Conference on Computer Vision, vol. 2, pp. 886–893 (2003) Google Scholar
  11. 11.
    Debreuve, E., Barlaud, M., Aubert, G., Darcourt, J.: Space time segmentation using level set active contours applied to myocardial gated SPECT. IEEE Trans. Med. Imaging 20, 643–659 (2001) CrossRefGoogle Scholar
  12. 12.
    Debreuve, E., Barlaud, M., Marmorat, J.-P., Aubert, G.: Active contour segmentation with a parametric shape prior: link with the shape gradient. In: International Conference on Image Processing, pp. 1653–1656 (2006) Google Scholar
  13. 13.
    Delfour, M.C., Zolésio, J.-P.: Shapes and Geometries: Analysis, Differential Calculus and Optimization. Advances in Design and Control. SIAM, Philadelphia (2001) MATHGoogle Scholar
  14. 14.
    Delingette, H., Montagnat, J.: Shape and topology constraints on parametric active contours. Comput. Vis. Image Underst. 83, 140–171 (2001) MATHCrossRefGoogle Scholar
  15. 15.
    Doǧan, G., Morin, P., Nochetto, R.H., Verani, M.: Finite element methods for shape optimization and applications. Preprint (2005) Google Scholar
  16. 16.
    Gastaud, M., Barlaud, M., Aubert, G.: Combining shape prior and statistical features for active contour segmentation. IEEE Trans. Circuits Syst. Video Technol. 14, 726–734 (2004) CrossRefGoogle Scholar
  17. 17.
    Germain, O., Réfrégier, P.: Optimal snake-based segmentation of a random luminance target on a spatially disjoint background. Opt. Lett. 21, 1845–1847 (1996) CrossRefGoogle Scholar
  18. 18.
    Haug, E., Choi, K.K.: Methods of Engineering Mathematics. Prentice Hall, Englewood Cliffs (1993) MATHGoogle Scholar
  19. 19.
    Hintermüller, M., Ring, W.: A second order shape optimization approach for image segmentation. SIAM J. Appl. Math. 64, 442–467 (2003) MATHCrossRefMathSciNetGoogle Scholar
  20. 20.
    Isard, M., Blake, A.: CONDENSATION—Conditional density propagation for visual tracking. Int. J. Comput. Vis. 29, 5–28 (1998) CrossRefGoogle Scholar
  21. 21.
    Jacob, M., Blu, T., Unser, M.: A unifying approach and interface for spline-based snakes. In: International Symposium on Medical Imaging: Image Processing. Proc. SPIE, vol. 4322, pp. 340–347 (2001) Google Scholar
  22. 22.
    Jacob, M., Blu, T., Unser, M.: Efficient energies and algorithms for parametric snakes. IEEE Trans. Image Process. 13, 1231–1244 (2004) CrossRefGoogle Scholar
  23. 23.
    Jehan-Besson, S., Barlaud, M., Aubert, G.: DREAM2S: Deformable regions driven by an Eulerian accurate minimization method for image and video segmentation. Int. J. Comput. Vis. 53, 45–70 (2003) CrossRefGoogle Scholar
  24. 24.
    Kass, M., Witkin, A., Terzopoulos, D.: Snakes: Active contour models. Int. J. Comput. Vis. 1, 321–332 (1988) CrossRefGoogle Scholar
  25. 25.
    Li, H., Elmoataz, A., Fadili, J., Ruan, S.: Dual front evolution model and its application in medical imaging. In: Medical Image Computing and Computer-Assisted Intervention. Lecture Notes in Computer Science, vol. 3216, pp. 103–110 (2004) Google Scholar
  26. 26.
    Li, H., Yezzi, A.: Local or global minima: flexible dual front active contours. In: Computer Vision for Biomedical Image Applications. Lecture Notes in Computer Science, vol. 3765, pp. 356–366 (2005) Google Scholar
  27. 27.
    Lobregt, S., Viergever, M.: A discrete dynamic contour model. IEEE Trans. Med. Imaging 14, 12–23 (1995) CrossRefGoogle Scholar
  28. 28.
    Marmorat, J.-P.: Private communication on shape gradient in the context of a parametric active contour (2005) Google Scholar
  29. 29.
    Mumford, D., Shah, J.: Optimal approximations by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42, 577–685 (1989) MATHCrossRefMathSciNetGoogle Scholar
  30. 30.
    Overgaard, N.C., Solem, J.E.: An analysis of variational alignment of curves in images. In: International Conference on Scale Space and PDE methods in Computer Vision. Lecture Notes in Computer Science, vol. 3459, pp. 480–491 (2005) Google Scholar
  31. 31.
    Paragios, N., Deriche, R.: Geodesic active regions for motion estimation and tracking. In: International Conference on Computer Vision, vol. 1, pp. 688–694 (1999) Google Scholar
  32. 32.
    Precioso, F., Barlaud, M., Blu, T., Unser, M.: Robust real-time segmentation of images and videos using a smooth-spline snake-based algorithm. IEEE Trans. Image Process. 14, 910–924 (2005) CrossRefGoogle Scholar
  33. 33.
    Robinson, D., Milanfar, P.: Fast local and global projection-based methods for affine motion estimation. J. Math. Imaging Vis. 18, 35–54 (2003) MATHCrossRefMathSciNetGoogle Scholar
  34. 34.
    Roy, T., Debreuve, E., Barlaud, M., Aubert, G.: Segmentation of a vector field: Dominant parameter and shape optimization. J. Math. Imaging Vis. 24, 259–276 (2006) CrossRefMathSciNetGoogle Scholar
  35. 35.
    Schnörr, C.: Computation of discontinuous optical flow by domain decomposition and shape optimization. Int. J. Comput. Vis. 8, 153–165 (1992) CrossRefGoogle Scholar
  36. 36.
    Sokolowski, J., Zolésio, J.-P.: Introduction to Shape Optimization: Shape Sensitivity Analysis. Springer, Berlin (1992) MATHGoogle Scholar
  37. 37.
    Solem, J.E., Overgaard, N.C.: A geometric formulation of gradient descent for variational problems with moving surfaces. In: International Conference on Scale Space and PDE methods in Computer Vision. Lecture Notes in Computer Science, vol. 3459, pp. 419–430 (2005) Google Scholar
  38. 38.
    Taton, B., Lachaud, J.-O.: Deformable model with non-Euclidean metrics. In: European Conference on Computer Vision. Lecture Notes in Computer Science, vol. 2352, pp. 438–453 (2002) Google Scholar
  39. 39.
    Unal, G., Yezzi, A., Krim, H.: Information-theoretic active polygons for unsupervised texture segmentation. Int. J. Comput. Vis. 62, 199–220 (2005) CrossRefGoogle Scholar
  40. 40.
    Unser, M., Aldroubi, A., Eden, M.: B-spline signal processing: Part I—Theory. IEEE Trans. Signal Process. 41, 821–833 (1993) MATHCrossRefGoogle Scholar
  41. 41.
    Yezzi, A.J., Tsai, A., Willsky, A.: A statistical approach to snakes for bimodal and trimodal imagery. In: International Conference on Computer Vision, vol. 2, pp. 898–903 (1999) Google Scholar
  42. 42.
    Zhu, S., Ma, K.-K.: A new diamond search algorithm for fast block matching motion estimation. IEEE Trans. Image Process. 9, 287–290 (2000) CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC 2007

Authors and Affiliations

  • É. Debreuve
    • 1
  • M. Gastaud
    • 1
  • M. Barlaud
    • 1
  • G. Aubert
    • 2
  1. 1.Laboratoire I3SUMR CNRS 6070Sophia AntipolisFrance
  2. 2.Laboratoire DieudonnéUMR CNRS 6621NiceFrance

Personalised recommendations