Abstract
We set out in this review article to construct a generalized theory of classi er combination for classi ers that, at least in the theory's initial form, act within noncoincident feature-spaces. Doing so involves the postulation of an equivalence between the various strategies for classi er combination and the tomographic reconstruction of the joint pattern-space probability density function, where the classi ers themselves are interpreted as extremely bandwidth limited Radon transform data. This analogue will immediately suggest techniques for improving the process, as well as de ning the optimal performance to be gained by such combinatorial approaches with respect to arbitrary joint pattern-space PDF morphologies. Furthermore, this methodology of optimality naturally will also encompass the feature selection process to present a uni ed perspective on the various di ering aspects of classi er combination. A practical implementation of the methodology is also given, along with a series of tests to establish its performance in relation to both model and real-word classi cation scenarios.