pgaussaggregation

Performs pixel aggregation based on gaussian criterion.

Synopsis

pgaussaggregation connexity alpha [-m mask] [rg_in|-] [im_in|-] [rg_out|-]

Description

pgausaggregation builds a new region map from aggregation of pixels to regions of the input region map rg_in. A pixel p is aggregated to a region R if:

p is connected to the region R according to the specified connexity;
[mean(R) - alpha*stdv(R), mean(R) + alpha*stdv(R)] ≤ threshold

where mean(R) is the inner mean of the region R and stdv(R) is the standard deviation of region R.

The mean and the standard deviation of the region are not updated with the new pixel to avoid moving away too much from the initial situation. One prefer iterative executions of the operator to update the mean and the standard deviation. For example, operator can be iterated until pstatus returns 0.

The output region map rg_out has the same number of labels than the input region map.

Parameters

connexity specifies the neighbor relation between pixel and region (4 or 8 for 2D; 6 or 26 for 3D).
alpha specifies the width of the gaussian. It is a real value. A typical value is 3.0.

Inputs

rg_in: a region map.
im_in: a grayscale image.

Outputs

rg_out: a region map.

Result

Returns the number of aggregation or FAILURE.

Examples

Aggregates pixels to tangram pieces:

   pbinarization 96 1e30 tangram.pan a.pan
   plabeling 8 a.pan b.pan
   pgaussaggregation 8 4 b.pan tangram.pan out.pan

C++ prototype

Errc PGaussAggregation(Reg2d &rg_in, Img2duc &im_in, Reg2d &rg_out, int connexity, float alpha);

Version française

Croissance des régions d'une carte selon une distribution gaussienne.

Author: Régis Clouard