el 21(21): e4

Research Article

Facial expression recognition via transfer learning

Download87 downloads
  • @ARTICLE{10.4108/eai.8-4-2021.169180,
        author={Bin Li},
        title={Facial expression recognition via transfer learning},
        journal={EAI Endorsed Transactions on e-Learning},
        volume={7},
        number={21},
        publisher={EAI},
        journal_a={EL},
        year={2021},
        month={4},
        keywords={Deep residual network, Facial expression recognition, ResNet-101, Transfer learning},
        doi={10.4108/eai.8-4-2021.169180}
    }
    
  • Bin Li
    Year: 2021
    Facial expression recognition via transfer learning
    EL
    EAI
    DOI: 10.4108/eai.8-4-2021.169180
Bin Li1,*
  • 1: School of Computer Science and Technology, Henan Polytechnic University, Jiaozuo, Henan 454000, P R China
*Contact email: 827843449@qq.com

Abstract

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.