Configuring options of classification

Further it is necessary to customize options of classification.

Classifier generalization level defines how much classified regions can differ from a pattern. The more the level of generalization, the less similar to a pattern the regions will be classified.

Window size determines diameter of a round floating window for which the statistical characteristics are calculated. If these characteristics differ from the patterned onto the size depending on the classifier generalization level, then all window is classified as belonging to the class. The admissible deviation level of window characteristics depends on the classifier generalization level.

Average line width is used at the subsequent steps for calculation of a direction vector at the ends of a line. Mode «Use texture» adds use of texture characteristics at classification. In some cases enabling this mode improves quality of recognition, but slows down speed of processing.