papers AI Learner
The Github is limit! Click to go to the new site.

Refacing: reconstructing anonymized facial features using GANs

2019-01-21
David Abramian, Anders Eklund

Abstract

Anonymization of medical images is necessary for protecting the identity of the test subjects, and is therefore an essential step in data sharing. However, recent developments in deep learning may raise the bar on the amount of distortion that needs to be applied to guarantee anonymity. To test such possibilities, we have applied the novel CycleGAN unsupervised image-to-image translation framework on sagittal slices of T1 MR images, in order to reconstruct facial features from anonymized data. We applied the CycleGAN framework on both face-blurred and face-removed images. Our results show that face blurring may not provide adequate protection against malicious attempts at identifying the subjects, while face removal provides more robust anonymization, but is still partially reversible.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1810.06455

PDF

https://arxiv.org/pdf/1810.06455


Similar Posts

Comments