Systems and methods for shaking action recognition based on facial feature points

摘要

The present disclosure relates to systems and methods for action recognition. The systems and methods may obtain a plurality of sequential target image frames associated with facial information of an object. Each of the plurality of sequential target image frames may include a plurality of feature points associated with the facial information. The systems and methods may determine a first area and a second area based on the plurality of feature points in each of the plurality of sequential target image frames. The systems and methods may determine an asymmetry parameter in each of the plurality of sequential target image frames based on the first area and the second area. The systems and methods may identify a shaking action in response to that the asymmetry parameter satisfies a preset condition.