View-based object representations using RBF networks

摘要

Radial basis function (RBF) networks have been proposed as suitable representations for 3-D objects, in particular, since they can learn view-based representations from a small set of training views. One of the basic questions that arise in the context of RBF networks concerns their complexity, i.e. the number of basis functions that are necessary for a reliable representation, which should balance the accuracy and the robustness. In this paper, we propose a systematic approach for building object representations in terms of RBF networks. We studied and designed two procedures: the off-line procedure, where the network is constructed after having a complete set of training views of an object, and the on-line procedure, where the network is incrementally built as new views of an object arrive. We tested the procedures both on synthetic and real data.