Reliability parameters to improve combination strategies in multi-expert systems

Recognition systems based on a combination of different experts have been w idely investigated in the recent: past. General criteria for improving the performance of such systems are based on estimating the reliability associa ted with the decision of each expert, so as to suitably weight its response in the combination phase. According to the methods proposed to-date, when the expert assigns a sample to a class, the reliability of such a decision is estimated on the basis of the recognition rate obtained by the expert on the chosen class during the training phase. As a consequence, the same rel iability value is associated with every decision attributing a sample to a same class, even though it seems reasonable ro take into account: its depen dence on the quality of the specific sample. We propose a method for estima ting the reliability of each single recognition act of an expert on the bas is of information directly derived from its output. In this way, the reliab ility value of a decision is more properly estimated, thus allowing a more precise weighting during the combination phase. The definition of the relia bility parameters for widely used classification paradigms is discussed, to gether with the combining rules employing them for weighting the expert opi nions. The results obtained by combining four experts in order to recognise handwritten numerals from a standard character database are presented. Com parison with classical combining rules is also reported, and the advantages of the proposed approach outlined.