PDF version of this document

Extensions

Extensions were applied to the code which deals with MDL-based shape model construction (Chapter cha:MDL Models).

As an example, below lies pseudo-code of what is referred to as adaptive precision. It simply selects a suitable tolerance for the optimiser. It does so in order to avoid excessive computations at early stages of the landmark selection procedure.

OUTPUT: precision_required

INPUTS: iterations_ratio, precision_automation_type

    % iterations_ratio is the ratio between the

    % current iteration and the total number

    % of iterations

switch precision_automation_type,

       case 'default'     

            if (iterations_ratio < 0.1),

               return precision_required = 1e-1;

            elseif (iterations_ratio < 0.2),

               return precision_required = 1e-2;

            elseif (iterations_ratio < 0.3),

               return precision_required = 1e-3;

            ...

            else      

               return precision_required = 1e-12;

            end

       case 'smart'

            % Look at the evaluation curve derivatives to

            % infer precision

end