BriefGPT.xyz
Oct, 2018
GANs重建匿名化面部特征的Refacing技术
Refacing: reconstructing anonymized facial features using GANs
HTML
PDF
David Abramian, Anders Eklund
TL;DR
本研究利用 CycleGAN 无监督图像转换框架，分别对面部有模糊和无脸部的 T1 MR 图像进行匿名化测试。结果表明，进行脸部模糊可能无法提供足够的保护措施，而脸部去除虽然提供更强的匿名化保护，但仍部分可逆。
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
→