A dynamic framework based on local Zernike moment and motion history image for facial expression recognition

作者：

Highlights：

• Proposes a facial expression recognition framework that uses dynamic information.

• Introduces QLZM_MCF to capture dynamic information in temporal domain.

• Introduces enMHI_OF to utlise motion speed and spatial information.

• Proposes a weighting strategy on a grid for high recognition rate.

摘要

Highlights•Proposes a facial expression recognition framework that uses dynamic information.•Introduces QLZM_MCF to capture dynamic information in temporal domain.•Introduces enMHI_OF to utlise motion speed and spatial information.•Proposes a weighting strategy on a grid for high recognition rate.

论文关键词：Zernike moment,Facial expression,Motion history image,Entropy,Feature extraction

论文评审过程：Received 29 February 2016, Revised 1 December 2016, Accepted 2 December 2016, Available online 5 December 2016, Version of Record 13 December 2016.

论文官网地址：https://doi.org/10.1016/j.patcog.2016.12.002