University of Twente Student Theses


Gender obfuscation through face morphing

Wang, S. (2020) Gender obfuscation through face morphing.

[img] PDF
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.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Programme:Electrical Engineering MSc (60353)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page