The Beltrami flow over implicit manifolds

In many medical computer vision tasks the relevant data is attached to a specific tissue such as the colon or the cortex. This situation calls for regularization techniques which are defined over surfaces. We introduce in this paper the Beltrami flow over implicit manifolds. This new regularization technique overcomes the over-smoothing of the L/sub 2/ flow and the staircasing effects of the L/sub 1/ flow, that were recently suggested via the harmonic map methods. The key of our approach is first to clarify the link between the intrinsic Polyakov action and the implicit harmonic energy functional and then use the geometrical understanding of the Beltrami flow to generalize it to images on implicitly defined non flat surfaces. It is shown that once again the Beltrami flow interpolates between the L/sub 2/ and L/sub 1/ flows on non flat surfaces. The implementation scheme of this flow is presented and various experimental results obtained on a set of various real images illustrate the performances of the approach as well as the differences with the harmonic map flows. This extension of the Beltrami flow to the case of non flat surfaces opens new perspectives in the regularization of noisy data defined on manifolds.

[1]  Rachid Deriche,et al.  Constrained Flows of Matrix-Valued Functions: Application to Diffusion Tensor Regularization , 2002, ECCV.

[2]  Ron Kimmel,et al.  Images as Embedded Maps and Minimal Surfaces: Movies, Color, Texture, and Volumetric Medical Images , 2000, International Journal of Computer Vision.

[3]  Tony F. Chan,et al.  Variational Restoration of Nonflat Image Features: Models and Algorithms , 2001, SIAM J. Appl. Math..

[4]  L. Rudin,et al.  Nonlinear total variation based noise removal algorithms , 1992 .

[5]  Li-Tien Cheng,et al.  Variational Problems and Partial Differential Equations on Implicit Surfaces: The Framework and Exam , 2000 .

[6]  Rachid Deriche,et al.  Nonlinear operators in image restoration , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[7]  S. Osher,et al.  Solving variational problems and partial differential equations mapping into general target manifolds , 2004 .

[8]  R. Deriche,et al.  Les EDP en traitement des images et vision par ordinateur , 1995 .

[9]  Max A. Viergever,et al.  Nonlinear scale-space , 1995, Image Vis. Comput..

[10]  A. Polyakov.  Quantum Geometry of Bosonic Strings , 1981 .

[11]  Rachid Deriche,et al.  The Beltrami Flow over Manifolds , 2002 .

[12]  Ron Kimmel,et al.  From High Energy Physics to Low Level Vision , 1997, Scale-Space.

[13]  William E. Lorensen,et al.  Marching cubes: A high resolution 3D surface construction algorithm , 1987, SIGGRAPH.

[14]  Ron Kimmel,et al.  Orientation Diffusion or How to Comb a Porcupine , 2002, J. Vis. Commun. Image Represent..

[15]  Yehoshua Y. Zeevi,et al.  Representation of colored images by manifolds embedded in higher dimensional non-Euclidean space , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[16]  Guillermo Sapiro,et al.  Diffusion of General Data on Non-Flat Manifolds via Harmonic Maps Theory: The Direction Diffusion Case , 2000, International Journal of Computer Vision.

[17]  Rachid Deriche,et al.  Orthonormal Vector Sets Regularization with PDE's and Applications , 2002, International Journal of Computer Vision.

[18]  Ron Kimmel.  Intrinsic Scale Space for Images on Surfaces: The Geodesic Curvature Flow , 1997, CVGIP Graph. Model. Image Process..

[19]  Ron Kimmel,et al.  A general framework for low level vision , 1998, IEEE Trans. Image Process..