Adaptive 3D facial action intensity estimation and emotion recognition

作者：

Highlights：

• We estimate AU intensity based on mRMR-based feature selection.

• Adaptive ensemble classifiers are proposed for robust expression classification.

• The ensemble models show superior ability for novel emotion class detection.

• Both database images and real human subjects are used to evaluate the system.

• It outperforms related work reported in the literature for the Bosphorus database.

摘要

•We estimate AU intensity based on mRMR-based feature selection.•Adaptive ensemble classifiers are proposed for robust expression classification.•The ensemble models show superior ability for novel emotion class detection.•Both database images and real human subjects are used to evaluate the system.•It outperforms related work reported in the literature for the Bosphorus database.

论文关键词：Facial emotion recognition,Action unit intensity estimation,Adaptive ensemble classifiers,Complementary Neural Networks,Support Vector Regression,Support vector classification

论文评审过程：Available online 16 September 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.08.042