Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos

作者：

Highlights：

• We propose a facial expression recognition method in practical videos.

• We propose a method for selecting the peak expression face from a video.

• We propose a robust subject-independent feature extraction.

• The feature extraction normalizes facial identity of peak expression face.

• The proposed method is feasible for spontaneous facial expression.

摘要

•We propose a facial expression recognition method in practical videos.•We propose a method for selecting the peak expression face from a video.•We propose a robust subject-independent feature extraction.•The feature extraction normalizes facial identity of peak expression face.•The proposed method is feasible for spontaneous facial expression.

论文关键词：Facial expression recognition (FER),Collaborative expression representation,Subject-independent FER,Peak expression face,Intra class variation (ICV) face

论文评审过程：Received 19 May 2015, Revised 14 December 2015, Accepted 25 December 2015, Available online 19 January 2016, Version of Record 27 February 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2015.12.016