Postprint version. Published in Proceedings from the International Conference on Image Processing: Vancouver, B.C., September 10, 2000.
Copyright © 2000 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The definitive version is available at http://dx.doi.org/10.1109/ICIP.2000.899336 .
NOTE: At the time of publication, the author Xiaozheng Zhang was not yet affiliated with Cal Poly.
The use of color information can significantly improve efficiency and robustness of lip feature extraction capability over purely grayscale-based methods. Edge information provides another useful tool in characterizing lip boundaries. In this paper we present a method of integrating both types of information to address the problem of lip feature extraction for the purpose of speechreading. We first examine various color models and view hue as an effective descriptor to characterize the lips due to its invariance to luminance and human skin color, and its discriminative properties. We use prominent red hue as an indicator to locate the position of the lips. Based on the identified lip area, we further refine the interior and exterior lip boundary using both color and spatial edge information, where those two are combined within a Markov random field (MRF) framework. Experimental results are presented to show the effectiveness of this method.
Electrical and Computer Engineering