Facial Biometrics in the Social Media Era: An In-Depth Analysis of the Challenge Posed by Beautification Filters

Automatic beautification through social media filters has gained popularity in recent years. Users apply face filters to adhere to beauty standards, posing challenges to the reliability of facial images and complicating tasks like automatic face recognition. In this work, the impact of digital beautification is assessed, focusing on the most popular social media filters from three different platforms, on a range of AI-based face analysis technologies: face recognition, gender classification, apparent age estimation, weight estimation, and heart rate assessment. Tests are performed on our extended Facial Features Modification Filters dataset, containing a total of 24312 images and 260 videos. An extensive set of experiments is carried out to show through quantitative metrics the impact of beautification filters on the performance of the different face analysis tasks. The results reveal that employing filters significantly disrupts soft biometric estimation, resulting in a pronounced impact on the performance of weight and heart rate networks. Nevertheless, we observe that certain less aggressive filters do not adversely affect face recognition and gender estimation networks, in some instances enhancing their performances. Scripts and more information are available at https://github.com/nmirabeth/filters_biometrics.