Research on Facial Emotion Recognition System Based on Exoskeleton Rehabilitation Robot

Abstract

In the existing robot-assisted rehabilitation training process, the interactive control between the patient and the rehabilitation robot is mainly based on sensing the patient's active “movement”, failing to consider the patient's “psychological” level of active participation, which has certain limitations. To solve this problem, we propose a facial emotion recognition system for exoskeleton rehabilitation robot. This system takes the frustration, excitement and boredom of the patient as the target emotion, and combines LNUS feature points with Gabors wavelet for feature extraction. The radial basis kernel SVM target emotion classifier recognizes the facial emotions of patients, and finally uses the recognized emotions to select the appropriate training difficulty. The experimental results showed that the average recognition rate of the patient's emotions reaches 86.3%, which can effectively recognize the three emotions of the patients, providing a basis for selecting the appropriate training difficulty in the later stage.