Tracking Articulators in X-ray Movies of the Vocal Tract

  • Georg Thimm
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1689)


Tongue, lips, palate, and throat are tracked in X-ray films showing the side-view of the vocal tract. Specialized histogram normalization techniques and a new tracking method that is robust against occlusion, noise, and spontaneous, non-linear deformations of objects are used. Although the segmentation procedure is optimized for the X-ray images of the vocal tract, the underlying tracking method can be used in other applications.


contour tracking edge template joined forward-backward tracking 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    J. Barron, S. Beauchemin, and D. Fleet: On optical flow, in Int. Conf. on Artificial Intelligence and Information-Control Systems of Robots, (1994) 3–14.Google Scholar
  2. 2.
    T. Cootes, A. Hill, C. Taylor, and J. Haslam: Use of active shape models for locating structures in medical images, Image and Vision Computing 12 (1994) 355–365.CrossRefGoogle Scholar
  3. 3.
    E.P. Davis, A.S. Douglas, and M. Stone: A continuum mechanics representation of tongue deformation, in Proc. of Int. Conf. on Spoken Language Processing (Bunnell and Idsardi, eds.) 2, New Castle, Delaware, Citation Delaware (1996) 788–792.Google Scholar
  4. 4.
    Y. Laprie and M. Berger: Towards automatic extraction of tongue contours in x-ray images, in Proc. of Int. Conf. on Spoken Language Processing 1, Philadelphia, USA (1996) 268–271.CrossRefGoogle Scholar
  5. 5.
    J. Luettin and N.A. Thacker: Speechreading using probabilistic models, Computer Vision and Image Understanding 65:2 (1997) 163–178.CrossRefGoogle Scholar
  6. 6.
    K. Munhall, E. Vatikiotis-Bateson, and Y. Tokhura: X-ray film database for speech research, J. Acoust. Soc. Am. 98:2 (1995) 1222–1224.CrossRefGoogle Scholar
  7. 7.
    L.H. Staib and J.S. Duncan: Boundary finding with parametrically deformable models, IEEE Trans. on Pattern Analysis and Machine Intelligence 14 (1992) 1061–1075.CrossRefGoogle Scholar
  8. 8.
    M. Stone and E. Davis: A head and transducer support system for making ultrasound images of tongue/jaw movement, J. Acoust. Soc. Am. 98:6 (1995) 3107–3112.CrossRefGoogle Scholar
  9. 9.
    M. Stone and L. Lundberg: Three-dimensional tongue surface shapes of english consonants and vowels, J. Acoust. Soc. Am. 99:6 (1996) 1–10.CrossRefGoogle Scholar
  10. 10.
    G. Thimm: Segmentation of X-ray image sequences showing the vocal tract, IDIAP-RR 1, IDIAP, CP 592, CH-1920 Martigny, Switzerland (1999).Google Scholar
  11. 11.
    G. Thimm and J. Luettin: Illumination-robust pattern matching using distorted color histograms, in Lecture Notes in Computer Science (5th Open German-Russian Workshop on Pattern Recognition and Image Understanding), Springer Verlag (1998). To appear.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Georg Thimm
    • 1
  1. 1.IDIAPMartignySwitzerland

Personalised recommendations