Comparing decision fusion paradigms using -NN based classifiers, decision trees and logistic regression in a multi-modal identity verification ap plication

The contribution of this paper is threefold: (1) to formulate a decision fusion problem encountered in the design of a multi-modal identity verification system as a particular classification problem, (2) to propose three simple classifiers to solve this problem, (3) to compare the relative performances of the proposed classifiers. The multi-modal identity verification system under consideration is built of d modalities in parallel, each one delivering as output a scalar number, called score, stating how well the claimed identity is verified. A fusion module receiving as input the d scores has to take a binary decision: acceptor reject identity. This fusion problem has been solved using three different classifiers, respectively based on the k-nearestneighbor (k-NN) classifier, decision trees and logistic regression. The performances of these different fusion modules have been evaluated and compared on a multi-modal database, containing both vocal and visual modalities.