Intelligent facial emotion recognition using moth-firefly optimization
作者：
Highlights：
• A descriptor combining LBP, LGBP and LBPV is proposed for feature extraction.
• Moth-firefly optimization is proposed for feature selection.
• It mitigates premature convergence of FA and MFO algorithms.
• Simulated Annealing is also used to further improve the most promising solution.
• It outperforms other optimization and facial expression recognition methods.
摘要
•A descriptor combining LBP, LGBP and LBPV is proposed for feature extraction.•Moth-firefly optimization is proposed for feature selection.•It mitigates premature convergence of FA and MFO algorithms.•Simulated Annealing is also used to further improve the most promising solution.•It outperforms other optimization and facial expression recognition methods.
论文关键词：Facial expression recognition,Feature selection,Evolutionary algorithm,Ensemble classifier
论文评审过程：Received 18 March 2016, Revised 18 August 2016, Accepted 19 August 2016, Available online 22 August 2016, Version of Record 23 September 2016.
论文官网地址：https://doi.org/10.1016/j.knosys.2016.08.018
