Synthesising Security Camera Images for Face Recognition

The field of face recognition sees a lot of development, but its use in forensic settings has lagged behind. One of the reasons for this is the lack of face image sets of sufficient size for training neural networks. This paper looks at the creation of a system to generate such a set of face images in a simulated forensic setting, since none exist for this purpose. The viability of using those images is tested with the FaceNet face recognition network.