摘要
针对人脸图像的年龄估计方法大多只考虑特定年龄的面部特征且男性与女性的老化差异影响年龄估计的准确性,本文提出了一个统一的年龄估计框架,利用性别和年龄之间的语义关系,并着重考虑不同性别之间的老化差异,将整个性别空间划分为男女性别子空间,在性别子空间中利用男性与女性间的老化差异进行年龄估计。实验结果表明,该方法不仅取得了良好的实验结果,而且在揭示人脸老化差异方面具有良好的可解释性。
Human age estimation has attracted increasing research due to its wide applicability.Although a variety of methods have been proposed,most of them only focus on the age-specific facial appearance and the aging difference between the male and the female inevitably affect the age estimation.A unified framework to perform gender-aware age estimation is proposed.The proposed method considers and utilizes the semantic relationship between the gender and the age,sand the aging discrepancy between the male and the female.Finally,experimental results demonstrate not only the superiority of our method in performance,but also its good interpretability in revealing the aging discrepancy.
作者
马闯
田青
孙赫阳
曹猛
MA Chuang;TIAN Qing;SUN Heyang;CAO Meng(School of Computer and Software,Nanjing University of Information Science&Technology,Nanjing 210044,Jiangsu,China;Collaborative Innovation Center of Atmospheric Environment and Equipment Technology,Nanjing University of Information Science&Technology,Nanjing 210044,Jiangsu,China)
出处
《陕西师范大学学报（自然科学版）》
CAS
CSCD
北大核心
2021年第1期52-60,共9页
Journal of Shaanxi Normal University：Natural Science Edition
基金
国家自然科学基金(61702273)
江苏省自然科学基金(BK20170956)
模式识别国家重点实验室开放课题(202000007)。
关键词
年龄预测
性别意识年龄预测
阈值回归
支持向量回归
age estimation
gender-aware age estimation
threshold-based ordinal regression
support vector ordinal regression
