CLEANIR: Controllable Attribute-Preserving Natural Identity Remover

Author:

Cho DurkhyunORCID,Lee Jin HanORCID,Suh Il Hong

Abstract

We live in an era of privacy concerns. As smart devices such as smartphones, service robots and surveillance cameras spread, preservation of our privacy becomes one of the major concerns in our daily life. Traditionally, the problem was resolved by simple approaches such as image masking or blurring. While these provide effective ways to remove identities from images, there are certain limitations when it comes to a matter of recognition from the processed images. For example, one may want to get ambient information from scenes even when privacy-related information such as facial appearance is removed or changed. To address the issue, our goal in this paper is not only to modify identity from faces but also keeps facial attributes such as color, pose and facial expression for further applications. We propose a novel face de-identification method based on a deep generative model in which we design the output vector from an encoder to be disentangled into two parts: identity-related part and the rest representing facial attributes. We show that by solely modifying the identity-related part from the latent vector, our method effectively modifies the facial identity to a completely new one while the other attributes that are loosely related to personal identity are preserved. To validate the proposed method, we provide results from experiments that measure two different aspects: effectiveness of personal identity modification and facial attribute preservation.

Funder

Korea Evaluation Institute of Industrial Technology

Publisher

MDPI AG

Subject

Fluid Flow and Transfer Processes,Computer Science Applications,Process Chemistry and Technology,General Engineering,Instrumentation,General Materials Science

Reference61 articles.

1. The Privacy-Utility Tradeoff for Remotely Teleoperated Robots

2. Learning to Anonymize Faces for Privacy Preserving Action Detection;Ren;arXiv,2018

Cited by 18 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Anonymizing medical case-based explanations through disentanglement;Medical Image Analysis;2024-07

2. Toward a Privacy-Preserving Face Recognition System: A Survey of Leakages and Solutions;ACM Computing Surveys;2024-06-17

3. Overview of Face De-identification Techniques;Face De-identification: Safeguarding Identities in the Digital Era;2024

4. FaceWard: Face Anonymization in Group Photos;Proceedings of the 25th International Conference on Mobile Human-Computer Interaction;2023-09-26

5. De-identifying Face Image Datasets While Retaining Facial Expressions;2023 IEEE International Joint Conference on Biometrics (IJCB);2023-09-25

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3