Age estimation with dynamic age range

作者：Lai, Dehe; Chen, Yewang^*; Luo, Xiangyu^*; Du, Jixiang^*; Wang, Tian

来源：Multimedia Tools and Applications, 2017, 76(5): 6551-6573.

DOI：10.1007/s11042-015-3230-0

• Age estimation
• Density peak
• Local binary pattern(LBP)
• Confidence interval/confidence level

Age estimation has been widely used and became more and more important, for its usefulness in various applications. However, accurately predict the age for an unlabeled image is difficult, because there are many factors that have impact on the appearance of a person. Some people look younger than his/her true age, while the others look much older. Therefore, predict an age group or a specific age for a facial image is not good enough. In this paper, we propose a new method to estimate the age of facial image into a dynamic range or a discrete age set rather than a single age or age group. Furthermore, we introduce a new measurement, i. e. Confidence Interval/Confidence Level to evaluate the performance of proposed method. Our experimental results show that the proposed method is promising.

• 出版日期2017-3
• 单位华侨大学