Tracking Facial Feature Points with Statistical Models and Gabor Wavelet

A precise face tracking algorithm for image sequence is presented in this paper which integrates Gabor wavelets with statistical models AAM (active appearance models). Facial feature points are characterized using Gabor wavelets and can be individually tracked. However, a disadvantage with this kind of purely feature-based tracking is that errors accumulate and nodes loose lock on their corresponding features. To repair this defect, a face affine transform is used to obtain the initial shape of the AAM model, and then the AAM is used to impose global constraints upon the local feature points and to produce a precise tracking. Experimental results demonstrate the ability of the proposed algorithm to precisely track facial features.