A geometrical modification of SVM outputs for pattern recognition

We present a novel way of interpreting and modifying the outputs of the support vector machine classifiers. The geometrical interpretation of the SVM outputs, as distance of the patterns from the hyperylane, gives us a way to calculate posterior probability, i.e. construct a rejection threshold for vectors belonging to one of the classes. We illustrate the results by analyzing three classification problems and also by comparation with already published method for modifying SVM outputs.