Combination of Decisions by Multiple Classifiers

A technique for combining the results of classifier decisions in a multiclassifier recognition system is presented. Each classifier produces a ranking of a set of classes. The combination t echnique uses these rankings to determine a small subset of the set of classes that contains the correct class. A group consensus function is then applied to re-rank the elements in the subset. This methodology is especially suited for recognition systems with large numbers of classes where it is valuable to reduce the decision problem to a manageable size before making a final determination about the identity of the image. Experimentation is discussed in which the proposed method is used with a word recognition problem where 40 classifiers are applied to degraded machine-printed word images and where a typical lexicon contains 235 words. A 96.6% correct rate is achieved within the 10 best decisions for 817 test images.