Enhanced age estimation by considering the areas of non-skin and the non-uniform illumination of visible light camera sensor

作者：

Highlights：

• We propose an age estimation method using a weighted MLBP based on fuzzy system.

• With two inputs, optimal weights are obtained by fuzzy system without training.

• Optimal weight is assigned to histogram features by MLBP method in each sub-block.

• Age is estimated by SVR based on the fusion of weighted MLBP and Gabor features.

摘要

•We propose an age estimation method using a weighted MLBP based on fuzzy system.•With two inputs, optimal weights are obtained by fuzzy system without training.•Optimal weight is assigned to histogram features by MLBP method in each sub-block.•Age is estimated by SVR based on the fusion of weighted MLBP and Gabor features.

论文关键词：Human age estimation,Non-AAM-based methods,Face box,Noise areas of hair, backgrounds, and non-uniform illumination of visible light camera sensor

论文评审过程：Received 18 March 2016, Revised 13 September 2016, Accepted 14 September 2016, Available online 14 September 2016, Version of Record 22 September 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.09.024