Abstract:

Generally the geometrical normalization process is important to the extraction of facial expression features. In commonly used normalization methods,  the unstability of the fiducial features resulted from facial motions always causes normalization errors. Making use of the optical flow method, the pap er analyzes quantitatively the serious influence on feature extraction caused by normalization errors,and proposes a weighted optimal matching algorithm  to solve it. The algorithm is founded on the basis of the template matching theory, and  rees when carrying on the calculation of correlative coefficients. Experimental results show that the algorithm can restrain the disturbance that normal ization error produces,and facial expression features can be extracted more accurately.

Key words: （human facial feature extraction, normalization, error-correction, optical flow）