Pri-EMO:A universal perturbation method for privacy preserving facial emotion recognition

作     者：Yong Zeng Zhenyu Zhang Jiale Liu Jianfeng Ma Zhihong Liu 

作者机构：School of Cyber EngineeringXidian UniversityXi'an 710071China 

出 版 物：《Journal of Information and Intelligence》 (信息与智能学报（英文）)

年 卷 期：2023年第1卷第4期

页      面：330-340页

学科分类：11[军事学] 0810[工学-信息与通信工程] 1105[军事学-军队指挥学] 08[工学] 081002[工学-信号与信息处理] 110503[军事学-军事通信学] 

基　　金：supported by the Foundation for Innovative Research Groups of the National Natural Science Foundation of China(62121001) 

主　　题：Facial emotion recognition Privacy preserving Perturbation Universal algorithm Feature space 

摘      要：Facial emotion have great significance in human-computer interaction,virtual reality and people s *** methods for facial emotion privacy mainly concentrate on the perturbation of facial emotion ***,cryptography-based perturbation algorithms are highly computationally expensive,and transformation-based perturbation algorithms only target specific recognition *** this paper,we propose a universal feature vector-based privacy-preserving perturbation algorithm for facial *** method implements privacy-preserving facial emotion images on the feature space by computing tiny perturbations and adding them to the original *** addition,the proposed algorithm can also enable expression images to be recognized as specific *** show that the protection success rate of our method is above 95%and the image quality evaluation degrades no more than *** quantitative and qualitative results show that our proposed method has a balance between privacy and usability.