Comparing Bayesian Networks to Classify Facial Expressions

C. Simplício, J. Prado, and J. Dias (Portugal)


Facial Expressions – Bayesian Networks – HRI.


In this paper are presented two distinct Bayesian networks to analyse human beings’ facial expressions. Both clas sifiers are completely defined: structure of the networks, belief variables and respective events, likelihoods, initial priors and procedure to change dynamically priors. The performance (relatively to the convergence) of the two ap proaches is compared. For both networks, the classification is done associating the facial expression to the probabilities of five emotional states: anger, fear, happy, sad and neutral. A justification for the usage of this set is presented: it is based in emotional states presented by human beings dur ing social relationships. Classifiers as these described here can be used in Human Robot Interation. We believe that this interaction shall be done in a similar way of that used by human beings to communicate between them and, after all, facial expressions is one of the main non-verbal means of communication used by human.

Important Links:

Go Back