pmcmfiltering

Performs Mean Curvature Motion filtering on image.

Synopsis

pmcmfiltering iterations [-m mask] [im_in|-] [im_out|-]

Description

pmcmfiltering performs a Mean Curvature Motion filtering on the input image im_in. It is based on the diffusion equation:

  d(im_in/dt) - Curv(im_in).|grad(im_in)|

where Curv(im-in) = div( grad(im_in) / |grad(im_in)| ).

Concretely, the diffusion is made in the orthogonal direction with the gradient and thus it preserves the edges and smoothes the remainder of the image.

The image border (of size 1) is not considered for processing. The output image border is just a copy of the input image border.

Parameters

specifies the number of iterations required to solve the model equation. It is a positive integer. The number of iterations strongly depends on the size of the objects contained in the image.

Inputs

im_in: an image.

Outputs

im_out: an image of the same type as the input image.

Result

Returns SUCCESS or FAILURE.

Examples

Applies the Mean Curvature Motion filter to tangram.pan:

   pmcmfiltering 2 tangram.pan out.pan

C++ prototype

Errc PMcmFiltering( const Img2duc &im_in, Img2duc &im_out, int iterations );

Version française

Lissage d'une image par filtre de courbure moyenne.

Author: Abderrahim Elmoataz