基于多任务学习的跨年龄人脸识别  

Cross-age face recognition based on multi-task learning

作　　者：闫鹏飞 张忠民[1] YAN Peng-fei;ZHANG Zhong-min(School of Information and Communication Engineering,Harbin Engineering University,Harbin 150001,China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,哈尔滨150001

出　　处：《哈尔滨商业大学学报（自然科学版）》2023年第1期53-59,共7页Journal of Harbin University of Commerce：Natural Sciences Edition

基　　金：国家自然科学基金资助项目(70971088);教育部博士点基金资助项目(9800462)。

摘　　要：为了解决年龄因素影响下的人脸识别问题,设计了一种多任务学习模型,用以进行年龄干扰下的人脸识别.通过卷积神经网络对人脸图像进行全面的特征提取,作为多任务学习的主干部分;使用特征分解模块提取出具有年龄相关信息的掩码层,从而从混杂的人脸特征中分离出年龄信息和身份信息;通过交叉熵损失函数和Arcface函数分别对年龄特征和身份特征进行约束.提出的网络对年龄干扰下的人脸特征具有较好的识别能力.In order to solve the problem of face recognition under the influence of age,a multi-task learning model was designed for face recognition under the influence of age.The convolution neural network was used to extract the features of the face image as the main part of multi-task learning.Then the mask layer with age-related information was extracted by using the feature decomposition module,so as to separate age information and identity information from the mixed face features;the age features and the identity features were constrained by the cross entropy loss function and the Arcface function respectively.The proposed network has good recognition ability for face features under age interference.

关 键 词：人脸识别 年龄 多任务学习 特征分解模块 交叉熵损失函数 Arcface函数 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程]