Facial Expression Recognition Based on Local Feature Bidirectional 2DPCA

In this paper, a method based on local feature bidirectional two-dimensional principal component analysis is proposed for facial expression recognition. First of all, a facial expressional image is divided into three separate sub-blocks, from the horizontal and vertical directions we utilize bidirectional 2DPCA to extract local feature of each sub-block. To different parts of human face containing different expressional information, every local feature is given to corresponding weighted coefficient. Through the experiments on JAFFE facial expression database, the results show that the method is feasible and effective, it also improve the expression recognition rate.