Skip to Main content Skip to Navigation
Theses

Segmentation des lèvres par un modèle déformable analytique

Abstract : Lip segmentation is an essential stage in many multimedia systems such as videoconferencing, lip reading, or low bit rate coding communication systems. In this paper, we propose an accurate and robust quasi automatic lip segmentation algorithm. First, the upper mouth boundary and several characteristic points are detected in the first frame by using a new kind of active contour : the “jumping snake”. Unlike classic snakes, it can be initialized far from the final edge and the adjustment of its parameters is easy and intuitive. Then, to achieve the segmentation we propose a parametric model composed of several cubic curves. Its high flexibility enables accurate lip contour extraction even in the challenging case of very asymmetric mouth. Compared to existing models, it brings a significant accuracy and realism improvement. The segmentation in the following frames is achieved by using an interframe tracking of the keypoints and the model parameters. However, we show that, with a usual tracking algorithm, the keypoints positions become unreliable after a few frames. We therefore propose an adjustment process that enables an accurate tracking even after hundreds of frames. Finally, we show that the mean keypoints tracking errors of our algorithm are comparable to manual points selection errors.
Complete list of metadatas

Cited literature [122 references]  Display  Hide  Download

https://tel.archives-ouvertes.fr/tel-00007181
Contributor : Nicolas Eveno <>
Submitted on : Friday, October 22, 2004 - 3:05:02 PM
Last modification on : Friday, November 6, 2020 - 4:39:39 AM
Long-term archiving on: : Friday, April 2, 2010 - 9:07:40 PM

Identifiers

  • HAL Id : tel-00007181, version 1

Collections

UGA

Citation

Nicolas Eveno. Segmentation des lèvres par un modèle déformable analytique. Traitement du signal et de l'image [eess.SP]. Institut National Polytechnique de Grenoble - INPG, 2003. Français. ⟨tel-00007181⟩

Share

Metrics

Record views

364

Files downloads

2038