CLASSIFICATION METHOD BASED ON SUPPORT VECTOR MACHINE

摘要

The present invention relates to a classification method based on a support vector machine, and more particularly to a classification method effective for a small volume of learning data. The classification method based on a support vector machine according to the present invention comprises a step of constructing a first classification model to which a weight according to the geometric distribution of a feature vector is applied; a step of constructing a second classification model by considering the degree of classification likelihood of the feature vector; and a step of performing dual optimization to merge the first and second classification models.