A novel robust facial expression recognition approach

At present, the method of facial expression recognition is put forward in many applications. In these applications, the responsiveness and robustness of the system is very important, especially the robustness is crucial. In this paper, a method of facial expression recognition based on robust minimax probability machine(RMPM) is proposed. By simply modifying the input data to improve the robustness of the estimation error in the mean and covariance matrix, we can ensure that the accuracy of the test set (TSA) is always greater than the low estimation bound of RMPM. Experiments show that the recognition method based on RMPM is better than that based on MPM.