A new real-time lip contour extraction algorithm

Author

Wang, S.L. ; Lau, W.H. ; Leung, S.H.

Author_Institution

Dept. of Comput. Eng. & Inf. Technol., City Univ. of Hong Kong, China

Volume

3

fYear

2003

fDate

6-10 April 2003

Abstract

A new lip contour extraction algorithm that combines the merits of the point-based lip model and the parametric lip model is presented. A 16-point lip model is used to describe the lip contour. With the aid of the FCMS (fuzzy clustering method incorporating shape function), a robust probability map is generated and a region-based cost function can be established. An iterative optimization procedure has been developed to fit the lip model to the probability map. In each iteration, the adjustment of the 16 lip points is governed by three pieces of quadratic curves which constrain the points to form a physical lip shape. Experimental results show that the proposed approach provides satisfactory results for 5,000 lip images of over 20 individuals. A real-time lip contour extraction system has also been implemented.

Keywords

feature extraction; fuzzy systems; iterative methods; object detection; optimisation; pattern clustering; probability; automatic speech recognition visual information; cost function; fuzzy clustering method; iterative optimization; lip model; probability map; real-time lip contour extraction algorithm; shape function; Clustering algorithms; Cost function; Data mining; Deformable models; Information technology; Parametric statistics; Principal component analysis; Robustness; Shape; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03). 2003 IEEE International Conference on

ISSN

1520-6149

Print_ISBN

0-7803-7663-3

Type

conf

DOI

10.1109/ICASSP.2003.1199146

Filename

1199146