CG-GAN: An Interactive Evolutionary GAN-based Approach for Facial Composite Generation)

TL;DR

This paper introduces CG-GAN, a novel interactive system that uses generative adversarial networks and evolutionary algorithms to enable casual users to create and edit high-resolution facial composites without expert knowledge.

Contribution

The paper presents CG-GAN, a new approach combining GANs and evolutionary computation for intuitive, high-quality facial composite generation from user interactions.

Findings

Enables casual users to generate realistic facial composites.

Allows combining multiple eyewitness representations.

Improves efficiency over traditional expert-dependent systems.

Abstract

Facial composites are graphical representations of an eyewitness's memory of a face. Many digital systems are available for the creation of such composites but are either unable to reproduce features unless previously designed or do not allow holistic changes to the image. In this paper, we improve the efficiency of composite creation by removing the reliance on expert knowledge and letting the system learn to represent faces from examples. The novel approach, Composite Generating GAN (CG-GAN), applies generative and evolutionary computation to allow casual users to easily create facial composites. Specifically, CG-GAN utilizes the generator network of a pg-GAN to create high-resolution human faces. Users are provided with several functions to interactively breed and edit faces. CG-GAN offers a novel way of generating and handling static and animated photo-realistic facial composites, with the possibility of combining multiple representations of the same perpetrator, generated by different eyewitnesses.