Unsupervised lip segmentation under natural conditions

Marc Liévin (1) , Franck Luthon (1)

1 LIS - Laboratoire des images et des signaux

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 spatiotemporal neighborhood. Simultaneously, a Region Of Interest (ROI) is automatically extracted. Third, the speaker's lip shape is extracted from the final hue field with good quality results in this challenging situation.

Domaines: Traitement du signal et de l'image [eess.SP]; Traitement du signal et de l'image [eess.SP]

Marc Liévin, Franck Luthon. Unsupervised lip segmentation under natural conditions. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP'99), Mar 1999, Phoenix, Arizona, United States. pp.3065-3068. ⟨hal-00961012⟩