ANALYSIS OF THE NEURAL-NETWORK RECOGNITION CHARACTERISTICS OF 6 BASICFACIAL EXPRESSIONS

In order to develop ''Active Human Interface, (AHI)'' that realizes em otive communication between intelligent machine and human being, we ha ve been investigating machine recognition of human emotions from facia l expressions. Using a neural network (NN), we have already obtained a high correct recognition ratio of about 90[%] for 6 basic facial expr essions, but we find that, depending on the NN learning information, t here exist certain characteristics in the NN misrecognition and correc t recognition. This paper analyzes these characteristics using action units (AUs) employed in the psychological field for describing the bas ic muscle movements of human face and analyzing the relationship betwe en the NN input and output information. We clarify, in this paper, the reason why misrecognition occurs by using the Jacobian of the NN inpu t-output function and how AUs influence the recognition results throug h sensitivity analysis done by assigning a zero value to each AU used in NN input information.