Facial Tracking Using Radial Basis Function

This paper implements facial tracking using Radial basis function neural network (RBF). There is no unique method that claims perfect facial tracking in video transfer. The local features of a frame are segmented. A ratio is found based on a criteria and output of RBF is used for transferring the necessary information of the frame from one system to another system. A decision approach, with a threshold, is used to detect if there is any change in the local object of the successive frames. The accuracy of the result depends upon the number of centers. The performance of the algorithm in reconstructing the tracked object is about 96.5% and similar to the performance of back propagation algorithm (BPA), in terms of reduced time and quality of reconstruction.