Towards building new, friendlier human-computer interaction and multimedia interactive services systems, we developed a neural network-based image processing system (called NEU-FACES), which first determines automatically whether or not there are any faces in given images and, if so, returns the location and extent of each face. Next, NEU-FACES uses neural network-based classifiers, which allow the classification of several facial expressions from features that we develop and describe. In the process of building NEU-FACES, we conducted an empirical study in which we specify related design requirements and, study statistically the expression recognition performance of humans. In this paper, we make and evaluation of performance of our NEU-FACES system versus the human's expression recognition performance. © 2008 Springer-Verlag Berlin Heidelberg.
CITATION STYLE
Stathopoulou, I. O., & Tsihrintzis, G. A. (2008). Comparative performance evaluation of artificial neural network-based vs. human facial expression classifiers for facial expression recognition. Studies in Computational Intelligence, 142, 55–65. https://doi.org/10.1007/978-3-540-68127-4_6
Mendeley helps you to discover research relevant for your work.