Stochastic Processes in Vision: From Langevin to Beltrami

Diffusion processes which are widely used in low level vision are presented as a result of an underlying stochastic process. The short-time non-linear diffusion is interpreted as a Fokker-Planck equation which governs the evolution in time of a probability distribution for a Brownian motion on a Riemannian surface. The non linearity of the diffusion has a direct relation to the geometry of the surface. A short time kernel to the diffusion as well as generalizations are found.

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

[2]  Mark A. Pinsky,et al.  Geometry of Random Motion , 1988 .

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

[4]  J. Zinn-Justin Quantum Field Theory and Critical Phenomena , 2002 .

[5]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  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).

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

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