An Evaluation of Bayes and Large Margin Classifiers for Face Expression Recognition
G-D. Guo and C. R. Dyer, Computer Sciences Department Technical Report 1447, University of Wisconsin - Madison, October 2002.
In this paper we investigate three representative methods for face expression recognition. The first one is the Bayes decision approach, which is the most classical algorithm for general pattern recognition. The second is support vector machine (SVM) classification, and the third is the AdaBoost method. Both SVM and AdaBoost are considered Large Margin Classifiers. We evaluate these three methods for face expression recognition on a common database. To solve the multi-class (7 expressions) recognition problem, we use a voting scheme and a binary tree scheme. For the Bayes and AdaBoost methods, we use a pairwise framework for both feature selection and discrimination in order to simplify the problem, and get good results. In contrast, with SVMs, we use all the features without selection. We compare linear and non-linear SVMs to see if there is any improvement using non-linear mapping. We also find that normalization makes recognition performance worse for SVMs but has no influence for Bayes and AdaBoost methods.