Emotion Recognition from Dance Image Sequences Using Contour Approximation

  • Hanhoon Park
  • Jong-Il Park
  • Un-Mi Kim
  • Woontack Woo
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3138)


We present a novel approach that exploits shape context to recognize emotion from monocular dance image sequences. The method makes use of contour information as well as region-based shape information. The procedure of the method is as follows. First, we compute binary silhouette images and its bounding box from dance images. Next, we extract the quantitative features that represent the quality of the motion of a dance. Then, we find meaningful low-dimensional structures, removing redundant information but retaining essential information possessing high discrimination power, of the features using SVD (Singular Value Decomposition). Finally, we classify the low- dimensional features into predefined emotional categories using TDMLP (Time Delayed Multi-Layer Perceptron). Experimental results demonstrate the validity of the proposed method.


  1. 1.
    Kim, Y.-S.: Shape Descriptor for Content-Based Image Retrieval. Ph.D. dissertation, Hanyang University (2000)Google Scholar
  2. 2.
    Teh, C.-H., Chin, R.T.: On the Detection of Dominant Points on Digital Curves. IEEE Transactions on Pattern Analysis and Machine Intelligence 11(8), 859–872 (1989)CrossRefGoogle Scholar
  3. 3.
    Suzuki, R., Iwadate, Y., Inoue, M., Woo, W.: MIDAS: MIC Interactive Dance System. IEEE Intl Conf. on Systems, Man and Cybernetics 2, 751–756 (2000)Google Scholar
  4. 4.
    Woo, W., Park, J.-I., Iwadate, Y.: Emotion Analysis from Dance Performance Using Time- Delay Neural Netwroks. In: Proc. of CVPRIP, vol. 2, pp. 374–377 (2000)Google Scholar
  5. 5.
    Park, H., Park, J.-I., Kim, U.-M., Woo, W.: A Statistical Approach for Recognizing Emotion from Dance Sequence. In: Proc. of ITC-CSCC 2002, Thailand, vol.2, pp. 1161–1164 (2002)Google Scholar
  6. 6.
    Camurri, A., Ricchetti, M., Trocca, R.: Eyeweb-toward gesture and affect recognition in dance/music interactive system. In: Proc. IEEE Multimedia Systems (1999)Google Scholar
  7. 7.
    Kim, N., Woo, W., Tadenuma, M.: Photo-realistic Interactive Virtual Environment Generation Using Multiview Cameras. In: Proc. of SPIE PW-EI-VCIP 2001, vol. 4310 (2001)Google Scholar
  8. 8.
    Open Source Computer Vision Library,
  9. 9.
    Laban, R.: Modern Educational Dance. Trans-Atlantic Publications (1988)Google Scholar
  10. 10.
    Kojima, K., Otobe, T., Hironaga, M., Nagae, S.: A Human Motion Analysis Using the Rhythm. In: Proc. of IWRHIC 2000, Japan, pp. 190–193 (2000)Google Scholar
  11. 11.
    Wilson, A., Bobick, A., Cassell, J.: Temporal Classification of Natural Gesture and Application to Video Coding. In: Proc. of CVPR 1997, pp. 948–954 (1997)Google Scholar
  12. 12.
    Fuji, R., Matsumoto, K., Mitsuyoshi, S., Gai, L.: Researches on the emotion measurement system. In: Proc. of ICSMC 2002, vol.2, pp. 1666–1672 (2003)Google Scholar
  13. 13.
    Cohen, I., Sebe, N., Cozman, F., Cirelo, M., Huang, T.: Learning Bayesian Network Classifier for Facial Expression Recognition using both Labeled and Unlabeled Data. In: Proc. of CVPR 2003, vol.1, pp. 595–601 (2003)Google Scholar
  14. 14.
    Lee, K., Xu, Y.: Real-time Estimation of Facial Expression Intensity. In: Proc. of ICRA 2003, vol.2, pp. 2567–2572 (2003)Google Scholar
  15. 15.
    Cowie, R., Douglas-Cowie, E., Tsapatsoulis, N., Votsis, G., Kollias, S., Fellenz, W., Taylor, J.G.: Emotion Recognition in Human-Computer Interaction. IEEE Signal Processing Magazine, 32–80 (2001)Google Scholar
  16. 16.
    Picard, R., Vyzas, E., Healey, J.: Toward Machine Emotional Intelligence: Analysis of Affective Physiological State. IEEE Transaction on Pattern Analysis and Machine Intelligence 23(10), 1175–1191 (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2004

Authors and Affiliations

  • Hanhoon Park
    • 1
  • Jong-Il Park
    • 1
  • Un-Mi Kim
    • 2
  • Woontack Woo
    • 3
  1. 1.Department of ECEHanyang UnivSeoulKorea
  2. 2.Department of DanceHanyang UnivSeoulKorea
  3. 3.U-VR LabK-JISTKwangjuKorea

Personalised recommendations