MASTER Assignment
Gender Obfuscation through Face Morphing
Type : Master M-EE
Period: Dec, 2019- Aug, 2020
Student : Wang, S. (Shunxin, Student M-EE)
Date Final project: August 31, 2020
Supervisors:
Abstract:
While facial biometric data has been widely adopted for person recognition, recent developments in machine learning show that soft biometrics such as gender, age and ethnicity can be automatically extracted from the facial photographs without permission, which raises privacy concerns. In this work, face morphing is applied to face images so that facial attributes such as gender, can no longer be deduced correctly by the corresponding attribute classifier. Meanwhile, the face images can still be used for identity verification. Experiments show that soft biometrics obfuscated through face morphing cannot be recovered or retrieved easily. It is concluded that face morphing is a good approach to protect soft biometric privacy in face images.