A novel facial emotion recognition method for stress inference of facial nerve paralysis patients
作者：
Highlights：
• We built an emotional face video dataset from facial nerve paralysis patients.
• The emotions of facial nerve paralysis patients are recognizable via face images.
• Transfer learning helps conquer the problem of limited data size in the clinic.
• It is feasible to infer emotional stress state of a facial nerve paralysis patient.
• Emotion recognition and stress inference may help improve emotional well-being.
摘要
•We built an emotional face video dataset from facial nerve paralysis patients.•The emotions of facial nerve paralysis patients are recognizable via face images.•Transfer learning helps conquer the problem of limited data size in the clinic.•It is feasible to infer emotional stress state of a facial nerve paralysis patient.•Emotion recognition and stress inference may help improve emotional well-being.
论文关键词：Facial nerve paralysis,Facial expression recognition,Emotion recognition,Stress,Deep learning
论文评审过程：Received 28 November 2021, Revised 28 January 2022, Accepted 20 February 2022, Available online 23 February 2022, Version of Record 9 March 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.116705
