Generalized Data Field and its Application for Facial Expression Recognition
Shuliang Wang, Ying Li, Yuan Xie, Hanning Yuan · International Conference on Machine Learning and Applications · 2010
Data field is a method to understand and depict the characteristics of the data in the context of physics. And face recognition is one difficulty in pattern recognition. In this paper, a generalized data field is proposed to better estimate the potential function in view of the inadequacy of the already existent potential function in multi-dimensional data field, along with an experiment on face recognition. First, the state of the art is overviewed. Then, the methodology is given. Third, facial expression is recognized with the generalized data field, the overall Recognizable Rate of which is as high as 94.3%. It indicates that the generalized data field is not only validity for this application but also more accurate than the other similar methods.