An approach to the automatic design of multiple classifier systems

Multiple classifier systems (MCSs) based on the combination of outputs of a set of different classifiers have been proposed in the field of pattern re cognition as a method for the development of high performance classificatio n systems. Previous work clearly showed that multiple classifier systems ar e effective only if the classifiers forming them are accurate and make diff erent errors. Therefore, the fundamental need for methods aimed to design " accurate and diverse" classifiers is currently acknowledged. In this paper, an approach to the automatic design of multiple classifier systems is prop osed. Given an initial large set of classifiers, our approach is aimed at s electing the subset made up of the most accurate and diverse classifiers. A proof of the optimality of the proposed design approach is given. Reported results on the classification of multisensor remote sensing images show th at this approach allows the design of effective multiple classifier systems . (C) 2001 Elsevier Science B.V. All rights reserved.