Feature Based Decision Fusion

In this paper we present a new architecture for combining classifiers. This approach integrates learning into the voting scheme used to aggregate individual classifiers decisions. This overcomes the drawbacks of having static voting techniques. The focus of this work is to make the decision fusion a more adaptive process. This approach makes use of feature detectors responsible for gathering information about the input to perform adaptive decision aggregation. Test results show improvement in the overall classification rates over any individual classifier, as well as different static classifier-combining schemes.