Next Article in Journal
Effect of Holes on Dynamic Crack Propagation under Impact Loading
Previous Article in Journal
Feasibility Analysis of a Membrane Desorber Powered by Thermal Solar Energy for Absorption Cooling Systems
 
 
Article

CLEANIR: Controllable Attribute-Preserving Natural Identity Remover

The Department of Electronics and Computer Engineering, Hanyang University, Seoul 04763, Korea
*
Author to whom correspondence should be addressed.
Appl. Sci. 2020, 10(3), 1120; https://doi.org/10.3390/app10031120
Received: 27 December 2019 / Revised: 27 January 2020 / Accepted: 30 January 2020 / Published: 7 February 2020
(This article belongs to the Section Computing and Artificial Intelligence)
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. View Full-Text
Keywords: privacy preserving; face de-identification; generative model; variational auto-encoder privacy preserving; face de-identification; generative model; variational auto-encoder
Show Figures

Figure 1

MDPI and ACS Style

Cho, D.; Lee, J.H.; Suh, I.H. CLEANIR: Controllable Attribute-Preserving Natural Identity Remover. Appl. Sci. 2020, 10, 1120. https://doi.org/10.3390/app10031120

AMA Style

Cho D, Lee JH, Suh IH. CLEANIR: Controllable Attribute-Preserving Natural Identity Remover. Applied Sciences. 2020; 10(3):1120. https://doi.org/10.3390/app10031120

Chicago/Turabian Style

Cho, Durkhyun, Jin Han Lee, and Il Hong Suh. 2020. "CLEANIR: Controllable Attribute-Preserving Natural Identity Remover" Applied Sciences 10, no. 3: 1120. https://doi.org/10.3390/app10031120

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop