A flexible hierarchical approach for facial age estimation based on multiple features
作者：
Highlights：
• A highly discriminative feature representation, which is able to model shape and appearance as well as wrinkles and skin spots.
• A novel hierarchical method consisting of a multi-class SVM and a SVR.
• The errors are compensated in the detailed age estimation by overlapping flexibly the age ranges of each age function.
• Experiments have been carried out on the publicly available FG-NET Aging and MORPH Album 2 datasets.
• An increased robustness to blur, lighting and expression variance through local phase features.
摘要
Highlights•A highly discriminative feature representation, which is able to model shape and appearance as well as wrinkles and skin spots.•A novel hierarchical method consisting of a multi-class SVM and a SVR.•The errors are compensated in the detailed age estimation by overlapping flexibly the age ranges of each age function.•Experiments have been carried out on the publicly available FG-NET Aging and MORPH Album 2 datasets.•An increased robustness to blur, lighting and expression variance through local phase features.
论文关键词：Age estimation,Face recognition,Local phase quantization,Active appearance models,Regression,Classification
论文评审过程：Received 1 August 2015, Revised 1 November 2015, Accepted 2 December 2015, Available online 29 December 2015, Version of Record 27 February 2016.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.12.003
