A robust lip tracking algorithm using localized color active contours and deformable models

Lip tracking is crucial to the success of a lipreading recognition system. This paper presents a robust lip tracking algorithm using localized color active contours and deformable models. The proposed approach utilizes a combined semiellipse as the initial evolving curve and computes the localized energies in color space for evolving such that a separation of the original lip image into lip and non-lip regions can be found. Moreover, the dynamic radius selection of the local region is presented with a 16-point deformable model (Wang et al. 2004) to achieve the lip tracking. The proposed approach is adaptive to the movement of the lips from frame to frame, and robust against the appearance of the teeth and tongue. Experiments have shown the promising results.