Classification of Facial Expressions with Domain Gaussian RBF Networks
J. M. Hogan, Michael W. Norris, Joachim Diederich · Studies in fuzziness and soft computing · 2001
This chapter examines the problem of categorization of facial expressions through the use of a receptive field neural network model, based upon novel domain Gaussian network units trained through error back-propagation. Such networks are trained upon images derived from the Ekman and Friesen “Pictures of Facial Affect” database, and they are subsequently able to successfully generalize to images of unseen subjects, and provide qualitative replication of the perceptual confusions common to previous studies. By using digital morphing techniques to produce intermediate frames between the existing stills, we are able to study the space of transitions between endpoint expressions. Our results suggest that expressions unrelated to the endpoint images may be perceived during certain transitions, a path far more complex than direct translation through a neutral expression. These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.