BACHELOR Assignment
Morphing detection based on facial marks
Type: Bachelor EE/CS
Period: TBD
Student: (Unassigned)
If you are interested please contact :
Introduction:
Face morphing is a technique to blend facial images of two or more subjects such that the result resembles both subjects. Face morphing attacks pose a serious risk for any face recognition system. Without automated morphing detection, state of the art face recognition systems are extremely vulnerable to morphing attacks. The most common approach to face morphing is by rst detecting landmarks in both contributing faces, then dene triangles in the images, determine an average geometry and map the averages of the textures in the triangles from the contributing faces to the averaged geometry.
Figure 1: From left to right: landmarks on face 1 and 2; triangulated geometry; morphed face.
Assignment:
Because two images are warped and blended together, ne facial structures, like facial marks are less clearly visible in the the resulting morphed face. This means that there is a good chance that morphed images may be detected by analysing the distribution of facial marks in the morphed face and compare that to those of the contributing faces. An approach for face comparison based on facial marks was proposed in:
C. Zeinstra, R. Veldhuis and L. Spreeuwers, "Grid-Based Likelihood Ratio Classiers for the Comparison of Facial Marks," in IEEE Transactions on Information Forensics and Security, vol. 13, no. 1, pp. 253-264, Jan. 2018.
The aim of this assignment is to investigate of these techniques can be used to detect morphed images.