Dynamic Linear Combination of Two-Class Classifiers

In two-class problems, the linear combination of the outputs (scores) of an ensemble of classifiers is widely used to attain high performance. In this paper we investigate some techniques aimed at dynamically estimate the coefficients of the linear combination on a pattern per pattern basis. We will show that such a technique allows providing better performance than those of static combination techniques, whose parameters are computed beforehand. The coefficients of the linear combination are dynamically computed according to the Wilcoxon-Mann-Whitney statistic. Reported results on a multi-modal biometric dataset show that the proposed dynamic mechanism allows attaining very low error rates when high level of precision are required.