Advertisement

Segmentation of Faces in Video Footage Using Controlled Weights on HSV Color

  • Osamu Ikeda
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2749)

Abstract

Accurate and reliable automatic segmentation of faces in video footages is often hard to succeed, leading instead to laborious and tedious interactive manual segmentation. This paper presents a segmentation method that uses a few controlled sets of the weights on HSV components. First, it is shown that HSV has advantages over RGB or YCbCr when segmenting a face in image in such that a binary pattern reflects as many features of the face as possible. Then, a face detection system is constructed, in which each time a significant scene change is detected segmentation is carried out for the beginning frame of a new scene using a few sets of the weights on HSV components, and resulting patterns are correlated with a typical face pattern. Computer experiments show that the successful detection rate is more than 95 out of 100 faces.

Keywords

Face Image Image Retrieval Face Detection Segmented Image Color Component 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

References

  1. [1]
    Yang, M-H., Kriegman, D.J., Ahuja, N.: Detecting Faces in Images: A Survey. IEEE Trans. PAMI 24 (2002) 34–58Google Scholar
  2. [2]
    Rowley, H.A., Baluja, S., Kanade, T.: Neural Network-Based Face Detection. IEEE Trans. PAMI 20 (1998) 23–38Google Scholar
  3. [3]
    Feraud, R., Bernier, O.J., Viallet, J.-E., Collobert, M.: A Fast and Accurate Face Detector Based on Neural Networks. IEEE Trans. PAMI 23 (2001) 42–53Google Scholar
  4. [4]
    Schneiderman, H. Kanade, T.: Probabilistic Modeling of Local Appearance and Spatial Relationships for Object Recognition. Proc. CVPR (1998) 45–51Google Scholar
  5. [5]
    Osuna, E., Freund, R., Girosi, G.: Training Support Vector Machines: An Application to Face Detection. Proc. CVPR (1997) 130–136Google Scholar
  6. [6]
    Turk, M.A., Pentland, A.P.: Eigenfaces for Pattern Recognition. J. Cognitive Neuroscience 3 (1991) 71–96CrossRefGoogle Scholar
  7. [7]
    Fröba, B., Ernst, A., Küblbeck, C.: Real-Time Face Detection. Proc. 4th IASTED International Conf. Signal and Image Processing (2002) 497–502Google Scholar
  8. [8]
    Satoh, S., Nakamura, Y., Kanade, T.: Name-It: Naming and Detecting Faces in News Videos. IEEE Multimedia 6 (1999) 22–35CrossRefGoogle Scholar
  9. [9]
    Wang, D.: Unsupervised Video Segmentation Based on Watersheds and Temporal Tracking. IEEE Trans. Circuits and Systems for Video Technology 8 (1998) 539–545CrossRefGoogle Scholar
  10. [10]
    Toklu, C., Tekalp A.M., Tanjuerdem, A.: Simultaneous Alpha Map Generation and 2D Mesh Tracking for Multimedia Applications. Proc. ICIP 1 (1997) 113–116CrossRefGoogle Scholar
  11. [11]
    Long, F., Feng, D., Peng, H., Siu, W.: Extracting Semantic Video Objects. IEEE Computer Graphics and Applications 21 (2001) 48–55CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Osamu Ikeda
    • 1
  1. 1.Faculty of EngineeringTakushoku UniversityHachioji, TokyoJapan

Personalised recommendations