New radial basis function network based techniques for holistic recognition of facial expressions

Abstract

With a number of emerging new applications, automatic recognition of facial expressions is a research area of current interest. This research focuses on the development of Radial Basis Function (RBF) network based classifiers suitable for the holistic recognition of expressions from static images. In the development, two new types of basis functions, namely, the Differentially Weighted Radial Basis Function (DWRRBF) and the Cloud Basis Function (CBF) are proposed. The new classifiers are carefully crafted to yield best performance by using the specific properties of the problem domain. The proposed classifiers have demonstrated superior performance compared with traditional RBF networks as well as several other types of holistic techniques. The best performance of 96.1% and 92.7% recognition rates were obtained for the proposed CBF network and DWRRBF network classifiers respectively, compared to the best recognition rate of 89.8% obtained among all other classification schemes tested using the same database.