Example of use of the colorProbabilityMap class.

This example gives a general idea how to use the powerful colorProbabilityMaps
to detect an object (or object) in an image if its color is characteristic.

Usage:
        colorProbability [-t] [-c filename] [-h]

        -c Specify the configuration file.  If the file specified does not
           exist, it will be created with a default set of parameters.

        -t Training mode
           In the training mode a list of images and corresponding masks are
           used for both, object and non-object color model estimation.  The
           list of images to be used is specified in the configuration file.

           The masks have to have the same name as the image, but with a suffix
           appended. (the suffix is also indicated in the configuration file).
           For example, if you want to train some pixels in the image
           lenna.png, then you have to create a file lenna_mask.png (in case
           the sufix specified is '_mask').

           All pixels with value 0 (black) in the mask are considered to be
           part of the background (non-object), and all white pixels are taken
           as part of the object.  Pixels with a gray value in the mask are
           ignored.
          
        -h Show a short usage message.

        