Makeup Induced Face Spoofing (MIFS)

Available for download here.

A face image dataset collected from YouTube videos of makeup impersonations. Some YouTube users upload videos of themselves applying makeup to look like certain celebrities. We collected 4 images from each video, 2 before-makeup images and 2 after-makeup images. We also collect 2 target images (genuine images of the person a YouTube user is attempting to impersonate). However, it is important to note that the target images are not necessarily those used by the YouTube user as a reference during the makeup transformation process. There are 107 makeup transformations with 6 images each.

C. Chen, A. Dantcheva, T. Swearingen, A. Ross, "Spoofing Faces Using Makeup: An Investigative Study," Proc. of 3rd IEEE International Conference on Identity, Security and Behavior Analysis (ISBA 2017), (New Delhi, India), February 2017.

Makeup Induced Face Spoofing (MIFS)

Publications