Learning bayesian network classifiers for facial expression recognition using both labeled and unlabeled data

  • Authors:

  • Ira Cohen;Nicu Sebe;Fabio G. Cozman;Marcelo C. Cirelo;Thomas S. Huang

  • Affiliations:

  • Beckman Institute, University of Illinois at Urbana-Champaign, IL;Leiden Institute of Advanced Computer Science, Leiden University, The Netherlands;Escola Politécnica, Universidade de São Paulo, São Paulo, Brazil;Escola Politécnica, Universidade de São Paulo, São Paulo, Brazil;Beckman Institute, University of Illinois at Urbana-Champaign, IL

  • Venue:
  • CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
  • Year:
  • 2003

Quantified Score

Hi-index 0.00

Visualization

Abstract

Understanding human emotions is one of the necessary skills for the computer to interact intelligently with human users. The most expressive way humans display emotions is through facial expressions. In this paper, we report on several advances we have made in building a system for classification of facial expressions from continuous video input. We use Bayesian network classifiers for classifying expressions from video. One of the motivating factor in using the Bayesian network classifiers is their ability to handle missing data, both during inference and training. In particular, we are interested in the problem of learning with both labeled and unlabeled data. We show that when using unlabeled data to learn classifiers, using correct modeling assumptions is critical for achieving improved classification performance. Motivated by this, we introduce a classification driven stochastic structure search algorithm for learning the structure of Bayesian network classifiers. We show that with moderate size labeled training sets and large amount of unlabeled data, our method can utilize unlabeled data to improve classification performance. We also provide results using the Naive Bayes (NB) and the Tree-Augmented Naive Bayes (TAN) classifiers, showing that the two can achieve good performance with labeled training sets, but perform poorly when unlabeled data are added to the training set.