Unsupervised lip segmentation under natural conditions

  title={Unsupervised lip segmentation under natural conditions},
  author={Marc Li{\'e}vin and Franck Luthon},
An unsupervised algorithm for speaker’s lip segmentation is presented in this paper. A color video sequence of speaker’s face is acquired, under natural lighting conditions and without any particular make-up. First, a logarithmic color transform is performed from RGB to HI (hue, intensity) color space and sequence dependant parameters are evaluated. Second, a statistical approach using Markov random field modeling segment mouth shape using red hue predominant region and motion in a… CONTINUE READING
Highly Cited
This paper has 28 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 18 extracted citations

Adaptive mouth segmentation using chromatic features

Pattern Recognition Letters • 2002
View 4 Excerpts
Highly Influenced

Lip-based Behavioural Biometrics

View 9 Excerpts
Highly Influenced

Automated Lip Contour Detection Using the Level Set Segmentation Method

14th International Conference on Image Analysis and Processing (ICIAP 2007) • 2007
View 1 Excerpt


Publications referenced by this paper.
Showing 1-6 of 6 references

Hennecke.Speechreading by Humans and Machines, volume 150

M. D. Stork

A set of french visemes for visual speech synthesis

C. Benoı̂t, M. T. Lallouache, T. Mohamadi
Elseviers Science Publishers, • 1992
View 1 Excerpt

Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images

IEEE Transactions on Pattern Analysis and Machine Intelligence • 1984
View 1 Excerpt

Similar Papers

Loading similar papers…