Real Time Segmentation of Lip Pixels for Lip Tracker Initialization
We propose a novel segmentation method for real time lip tracker initialisation which is based on a Gaussian mixture model of the pixel data. The model is built using the Predictive Validation technique advocated in . In order to construct an accurate model in real time, we adopt a quasi-random image sampling technique based on Sobol sequences. We test the proposed method on a database of 145 images and demonstrate that its accuracy, even with a few number of samples, is satisfactory and significantly better than the segmentation obtained by k-means clustering. Moreover, the proposed method does not require the number of segments to be specified a priori.
Keywordsgaussian mixture modelling lip tracking
Unable to display preview. Download preview PDF.
- 2.Dupont, S., Luettin, J.: Audio-visual speech modeling for continuous speech recognition. IEEE Transactions on Multimedia 2(3) (Sep 2000) 141–151Google Scholar
- 3.Galambos, C., Kittler, J., Matas, J.: Sampling techniques for the progressive probabilistic Hough transform. (2001) submitted to Pattern Recognition LettersGoogle Scholar
- 4.Kittler, J., Messer, K. Sadeghi, M.: Model validation for model selection. Second Conference on Advances in Pattern Recognition. Brazil, 11–14 March (2001)Google Scholar
- 6.Messer,Matas, J., Kittler, J., Luettin, J., Maitre, G.: Xm2vtsdb: The extended m2vts database. Second International Conference on Audio and Video-based Bio-metric Person Authentication (Mar 1999)Google Scholar
- 7.Press, W.H., Flanney, B.P., Teukolsky, S.A., Vetterling, W.T.: Numerical Recipes in C: The Art of Scientific Computing. Cambridge University Press (1992)Google Scholar
- 10.Yang, J., Waibel, A.: A real-time face tracker. Third IEEE Workshop on Applications of Computer Vision. Sarasota, Florida, USA (1996) 142–147Google Scholar