基于自适应多重多元回归的人脸年龄估计  

The Facial Age Estimation Based on Adaptive Multivariate Multiple Regression

作　　者：曾雪强 罗明珠[1] 陈素芬 吴水秀[2] 万中英[2] ZENG Xueqiang;LUO Mingzhu;CHEN Sufen;WU Shuixiu;WAN Zhongying(Information Engineering School,Nanchang University,Nanchang Jiangxi 330031,China;School of Computer and Information Engineering,Jiangxi Normal University,Nanchang Jiangxi 330022,China;School of Information Engineering,Nanchang Institute of Technology,Nanchang Jiangxi 330099,China)

机构地区：[1]南昌大学信息工程学院,江西南昌330031 [2]江西师范大学计算机信息工程学院,江西南昌330022 [3]南昌工程学院信息工程学院,江西南昌330099

出　　处：《江西师范大学学报（自然科学版）》2019年第1期68-75,共8页Journal of Jiangxi Normal University(Natural Science Edition)

基　　金：国家自然科学基金(61463033;61866017);江西省教育厅科学技术研究(GJJ150354);江西省杰出青年人才资助计划(20171BCB23013)资助项目

摘　　要：针对基于标记分布学习的多重多元回归模型不能生成和人脸老化趋势一致标记分布的问题,提出自适应多重多元回归的人脸年龄估计方法.在为不同年龄生成具有适合标准差的离散高斯分布的基础上,采用偏最小二乘模型并有效地利用邻近年龄的人脸老化信息进行年龄估计.在MORPH人脸数据库上的对比实验结果表明,该文的人脸年龄估计模型具有更好的性能.In order to address the problem that traditional multivariate multiple regression based label distribution learning methods cannot generate the label distribution according to the tendency of facial aging,a facial age estimation method based on adaptive multivariate multiple regression has been proposed. The proposed method generates the discrete Gaussian distributions with different standard deviations adapted to different ages,and using partial least square model to effectively utilize adjacent facial ageing information to predict facial age. Our experimental results on the MORPH face database show that the facial age estimation model in the paper has better performance than existing correlation models.

关 键 词：人脸年龄估计 自适应多重多元回归 标记分布学习 偏最小二乘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]