Advertisement

Expression Intensity Recognition Based on Multilayer Hybrid Classifier

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 194)

Abstract

In this paper, an automatic system for recognizing expression intensity is proposed. Modified Active Appearance Model (MAAM) is utilized to extract facial feature points (FFPs), and then, according to the FFPs’ position, the sequence is preprocessed. Coarse-to-fine pyramid algorithm is employed to track FFPs for extracting 23 optical flow vectors, and eliminating the error caused by rigid movement of head. Expression intensity is recognized by multilayer hybrid classifier. Support Vector Machine (SVM) classifies the expression in the form of optical flow vectors, and KNN classifier recognizes the intensity. We conduct the experiments on Cohn-Kanade expression database and the result shows good effect.

Keywords

Expression intensity recognition MAAM optical flow vector SVM KNN 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Donato, G.: Classifying facial actions. IEEE Transactions on Pattern Analysis and Machine Intelligence 21(10), 974–989 (1999)MathSciNetCrossRefGoogle Scholar
  2. 2.
    Ma, L., Khorasani, K.: Facial expression recognition using constructive feedforward neural networks. IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics 34(3), 1588–1595 (2004)CrossRefGoogle Scholar
  3. 3.
    Wu, Y., Liu, H., Zha, H.: Modeling facial expression space for recognition. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1968–1973 (2005)Google Scholar
  4. 4.
    Jung, S.U., An, K.H., Chung, M.J.: Efficient rectangle feature extraction for real-time facial expression recognition based on AdaBoost. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1941–1946 (2005)Google Scholar
  5. 5.
    Lien, J.J.J.: Subtly different facial expression recognition and expression intensity estimation. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 853–859 (1998)Google Scholar
  6. 6.
    Park, S., Kim, D.: Subtle facial expression recognition using motion magnification. Pattern Recognition Letters 30(7), 708–716 (2009)CrossRefGoogle Scholar
  7. 7.
    Essa, Pentland: Coding, analysis, interpretation, and recognition of facial expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence 19(7), 757–763 (1997)Google Scholar
  8. 8.
    Amin, M.A., Yan, H.: Expression intensity measurement from facial images by self-organizing maps. In: IEEE International Conference on Machine Learning and Cybernetics, vol. 6, pp. 3490–3496 (2008)Google Scholar
  9. 9.
    Cootes, T., Edwards, G.J.F., Taylor, C.J.: Active appearance models. IEEE Transactions on Pattern Analysis and Machine Intelligence 23(6), 681–685 (2001)CrossRefGoogle Scholar
  10. 10.
    Wang, X.K., Mao, X., Caleanu, C.D.: Nonlinear Shape-Texture Manifold Learning. IEICE Transactions on Information and Systems 93(7), 2016–2019 (2010)CrossRefGoogle Scholar
  11. 11.
    Barron, J.L., Fleet, D.J., Beauchemin, S.S.: Performance of optical flow techniques. International Journal of Computer Vision 12(1), 43–77 (1994)CrossRefGoogle Scholar
  12. 12.
    Patrick, E.A., Fischer III, F.P.: A generalized k-nearest neighbor rule. Information and Control 16(2), 128–152 (1970)MathSciNetMATHCrossRefGoogle Scholar
  13. 13.
    Lucey, P., et al.: The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 94–101 (2010)Google Scholar
  14. 14.
    Ertekin, S., Huang, J., Giles, C.L.: Active learning for class imbalance problem. In: Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 823–824 (2007)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  1. 1.School of Electronic and Information EngineeringBeihang UniversityBeijingChina

Personalised recommendations