Semisupervised Learning of Classifiers: Theory, Algorithms, and Their Application to Human-Computer Interaction
Issue No. 12 - December (2004 vol. 26)
Ira Cohen , IEEE
Nicu Sebe , IEEE
Thomas S. Huang , IEEE
Automatic classification is one of the basic tasks required in any pattern recognition and human computer interaction application. In this paper, we discuss training probabilistic classifiers with labeled and unlabeled data. We provide a new analysis that shows under what conditions unlabeled data can be used in learning to improve classification performance. We also show that, if the conditions are violated, using unlabeled data can be detrimental to classification performance. We discuss the implications of this analysis to a specific type of probabilistic classifiers, Bayesian networks, and propose a new structure learning algorithm that can utilize unlabeled data to improve classification. Finally, we show how the resulting algorithms are successfully employed in two applications related to human-computer interaction and pattern recognition: facial expression recognition and face detection.
Semisupervised learning, generative models, facial expression recognition, face detection, unlabeled data, Bayesian network classifiers.
F. G. Cozman, I. Cohen, N. Sebe, T. S. Huang and M. C. Cirelo, "Semisupervised Learning of Classifiers: Theory, Algorithms, and Their Application to Human-Computer Interaction," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 26, no. , pp. 1553-1567, 2004.