bioModelGenerate
    ----------------

Learn multi variate gaussian models using segmented images.
For each segmented pixel measure vectors are loaded with the features
previously computed.
Then, clusters are determined to approximate multi variate gaussian model.
(cf. bioVision algorithm)

Options :

-i <list of string>
    Input features image(s)

-g <list of string>
    ROI Graph(s). ROI are used to determine the class of each segmented voxel

-bv <string>
    Output bioVision classes file

[ -t <DOUBLE> ]
    Clustering threshold [default : 1.0]

[ -s <DOUBLE> ]
    Clustering minimal temperature [default : 2]

[ -r <DOUBLE> ]
    Clustering sigma ratio used to divide sigma [default : 2]

[ -n <S32> ]
    Clustering maximum number of clusters [default : 12]

[ -ms <DOUBLE> ]
    Cluster minimum size (percent of class voxel size) [default : 0.0]

[ -cp <S32> ]
    Cluster creation policy (1 : histogram maxima, 2 : median) [default : 1]

[ -p <list of DOUBLE> ]
    Probability prior for each class [default : 1 / number of classes]

[ --output_4d_volumes <S32> ]
    Write 4D images as several 3D files (0 = series of 3D volumes, 1 = one 4D
    volume, no value = use .aimsrc configuration files)

[ --debugLevel <S32> ]
    Set debug information level (default = 0)

[ --verbose | -v [ <S32> ] ]
    Set verbosity level (default = 0, without value = 1)

[ -h | --help <boolean> ]
    show help message

[ --version <boolean> ]
    show Cartograph version

[ --info <boolean> ]
    show libraries information (install, plugins, paths, etc.)

[ --optionsfile <string> ]
    Read additional commandline options from the specified file (one switch or
    value per line)