Facial expression recognition system based on variational mode decomposition and whale optimized KELM

作者：

Highlights：

• A novel approach for Facial Expression Recognition (FER) is presented.

• Variational Mode Decomposition (VMD) is harnessed to decompose expression images.

• Kernel Extreme Learning Machine (KELM) is adopted for expression recognition.

• Whale Optimization (WO) algorithm is utilized to fine-tune RBF KELM parameters.

• Achieves classification accuracies of 98.81% and 99.30% on CK + and JAFFE datasets.

摘要

•A novel approach for Facial Expression Recognition (FER) is presented.•Variational Mode Decomposition (VMD) is harnessed to decompose expression images.•Kernel Extreme Learning Machine (KELM) is adopted for expression recognition.•Whale Optimization (WO) algorithm is utilized to fine-tune RBF KELM parameters.•Achieves classification accuracies of 98.81% and 99.30% on CK + and JAFFE datasets.

论文关键词：Facial expression recognition,Kernel extreme learning machine,Variational mode decomposition,Whale optimization

论文评审过程：Received 1 December 2021, Revised 18 February 2022, Accepted 31 March 2022, Available online 8 April 2022, Version of Record 26 May 2022.

论文官网地址：https://doi.org/10.1016/j.imavis.2022.104445