Temporal face feature progression with cycle GAN

Abstract

The aging process creates significant changes in the appearances of people’s faces. When compared to other causes of variation in face imaging, aging-related variation has specific distinct properties. Facial Aging variations, for example, is unique for each person; it occurs gradually and is significantly influenced by other characteristics including health, gender, and life-style. As a result, the proposed effort will use Generative Adversarial Networks to address these critical concerns (GANs). Generative Adversarial Networks (GAN’s) is made up of a generator and a discriminator network. The generator model generates images that a discriminator model analyses to determine if they are real or fake. This paper provides a Temporal Face Feature Progressive framework with Cycle GAN, which maintains the initial appearance and identity in the elderly aspect of their facial structure. To address aging concerns, our goal is to transform an initial age category image into a targeted age with age progression. We show that our temporal face features progressive cycle GAN learns and transfers facial traits from the source group to the targeted group by training various images. The IMDB-WIKI Face dataset has been used to obtain the results for the same.