A Facial Expression Recognition Approach Based on Novel Support Vector Machine Tree
Automatic facial expression recognition is the kernel part of emotional information processing. This paper dedicates to develop an automatic facial expression recognition approach based on a novel support vector machine tree, which performs feature selection at each internal node, to improve recognition accuracy and robustness. After the Pseudo-Zernike moment features were extracted, they were used to train a support vector machine tree for automatic recognition. The structure of a support vector machine enables the model to divide the facial recognition problem into sub-problems according to the teacher signals, so that it can solve the sub-problems in decreased complexity in different tree levels. In the training phase, those sub-samples assigned to two internal sibling nodes perform decreasing confusion cross, thus, the generalization ability for recognition of facial expression is enhanced. The compared results on Cohn-Kanade facial expression database also show that the proposed approach appeared higher recognition accuracy and robustness than other approaches.
KeywordsSupport Vector Machine Feature Selection Facial Expression Recognition Accuracy Internal Node
Unable to display preview. Download preview PDF.
- 2.Ekman, P., Friesen, W.V.: Facial Action Coding System: A technique for the Measurement of Facial Movement. Consulting Psychologists Press, Palo Alto (1978)Google Scholar
- 4.Xu, Q.Z., Song, A.G., Pei, W.J., Yang, L.X., He, Z.Y.: Tree-Structured Support Vector Machine with Confusion Cross for Complex Pattern Recognition Problems. In: Proceedings of 2005 IEEE International Workshop on VLSI Design and Video Technology, pp. 195–198 (2005)Google Scholar
- 13.Kanade, T., Cohn, J.F., Tian, Y.I.: Comprehensive Database for Facial Expression Analysis. In: Proc. of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition, pp. 46–53 (2000)Google Scholar
- 15.Littlewort, G., Bartlett, M., Fasel, I., Susskind, J., Movellan, J.R.: Dynamics of Facial Expression Extracted Automatically from Eideo. In: Proc. Of IEEE Conference on Computer Vision and Pattern Recognition, Workshop on Face Processing in Video, Orlando, FL, vol. 5, p. 80 (2004)Google Scholar