LIP Contour Extraction Using a Deformable Model

The use of visual information from lip movements can improve the accuracy and robustness of a speech recognition system. Accurate extraction of visual features associated with the lips is thus very important. In this paper, we present a deformablemodel-basedtechniquefor lip contour extraction from color lip images. The geometriclip model we proposed is able to fit different lip shapes. Our method starts by generating a probability map of the lip image using spatial fuzzy clustering. Then the optimum set of model parameters that partitions a lip probabilitymap into lip region and non-lip region is found, such that the joint probability of the two regions is maximised.Experimentalresults indicate that accurate and robust lip contour extraction is possible using this approach.

• Type: Conference
• Year: 2000
• Where: ICIP
• Authors: Alan Wee-Chung Liew, Shu Hung Leung, Wing Hong Lau
• Keywords: Deformablemodel-basedtechniquefor Lip Contour, ICIP 2000, Image Processing, Lip Contour Extraction, Robust Lip Contour