Multi-target evolutionary latent space search of a generative adversarial network for human face generation
Benjamín Machín, Sergio Nesmachnow, Jamal Toutouh · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2022
This article presents an evolutionary approach for multi-target synthesized human face image generation based on exploring the latent space of generative adversarial networks. The proposed approach seeks to generate different human face images those share similarities to two given target images. The optimization applies generative adversarial networks for face generation, facial recognition for similarity evaluation, and an ad-hoc evolutionary algorithm for exploring the search space. The main results show that realistic images are generated, properly blending the main features of the two given target images, and deceiving a well-known facial recognition system.