Learning Bayesian Network Classifiers for Facial Expression Recognition英文学习资料.pdfVIP

Learning Bayesian Network Classifiers for Facial Expression Recognition using both Labeled and Unlabeled Data Ira Cohen , Nicu Sebe , Fabio G. Cozman , Marcelo C. Cirelo , Thomas S. Huang
   Beckman Institute, University of Illinois at Urbana-Champaign, IL, USA,  iracohen, huang @  Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands, nicu@liacs.nl  Escola Politecnica,´ Universidade de Sao˜ Paulo, Sao˜ Paulo, Brazil  fgcozman, marcelo.cirelo @usp.br Abstract tailed review of many of the research done in recent years). All these methods are similar in that they first extract some Understanding human emotions is one of the necessary features from the images or video, then these features are skills for the computer to interact intelligently with human used as inputs into a classification system, and the outcome users. The most expressive way humans display emotions is one of the preselected emotion categories. They differ is through facial expressions. In this paper, we report on mainly in the features extracted and in the classifiers used to several advances we have made in building a system for distinguish between the different emotions. classification of facial expressions fr om continuous video We have developed a real time facial expression recogni- input. We use Bayesian network classifiers for classifying tion system. The system use