A neural-AdaBoost based facial expression recognition system

作者：

Highlights：

• The study improves expression recognition rate and execution time.

• Average recognition rates in JAFFE and Yale databases are 96.83% and 92.22%, respectively.

• The execution time for processing 100 × 100 pixel size is 14.5 ms.

• Best recognitions are happy, surprise, and disgust and the poorest is neutral.

• The general results are very encouraging when compared with others.

摘要

•The study improves expression recognition rate and execution time.•Average recognition rates in JAFFE and Yale databases are 96.83% and 92.22%, respectively.•The execution time for processing 100 × 100 pixel size is 14.5 ms.•Best recognitions are happy, surprise, and disgust and the poorest is neutral.•The general results are very encouraging when compared with others.

论文关键词：Facial expression recognition,Bessel transform,Gabor feature,AdaBoost,MFFNN

论文评审过程：Available online 8 December 2013.

论文官网地址：https://doi.org/10.1016/j.eswa.2013.11.041