Facial expression recognition via transfer learning

INTRODUCTION: With the development of artificial intelligence, facial expression recognition has become a hot topic. Facial expression recognition has been widely applied to every field of our life. How to improve the accuracy of facial emotion recognition is an important research content.

OBJECTIVES: In today's facial expression recognition, there are problems such as weak generalization ability and low recognition accuracy. Aiming to improve the current facial expression recognition problems, we propose a novel facial emotion recognition method.

METHODS: This paper focuses on the deep learning-based static face image expression recognition method, and combines transfer learning and deep residual network ResNet-101 to realize facial expression recognition.

RESULTS: The simulation results show that the overall accuracy of our method is 96.29± 0.78%.

CONCLUSION: The performance of this model is superior to the current mainstream face emotion recognition models. In the future research, we will try other methods based on deep learning.