Combining edge detection and region segmentation for lip contour extraction

Saeed, Usman; Dugelay, Jean-Luc
AMDO 2010, 6th Conference on Articulated Motion and Deformable Objects, July 7-9, 2010, Andratx, Mallorca, Spain / Also published in LNCS, Volume 6169/2010

 

 

 

 

 

 

The automatic detection of the lip contour is relatively a difficult problem in computer vision due to the variation amongst humans and environmental conditions. In this paper we improve upon the classical methods by introducing fusion. Two separate methods are first applied, one based on edge detection and the other on region segmentation to detect the outer lip contour, the results from them are then combined. Empirical evaluation of the detection process is also presented on an image subset of the Valid database, which contains lighting, pose and speech variation with promising results.


DOI
Type:
Conference
City:
Andratx
Date:
2010-07-07
Department:
Digital Security
Eurecom Ref:
3142
Copyright:
© Springer. Personal use of this material is permitted. The definitive version of this paper was published in AMDO 2010, 6th Conference on Articulated Motion and Deformable Objects, July 7-9, 2010, Andratx, Mallorca, Spain / Also published in LNCS, Volume 6169/2010 and is available at : http://dx.doi.org/10.1007/978-3-642-14061-7_2

PERMALINK : https://www.eurecom.fr/publication/3142