Image Generation and Recognition (Emotions)

TL;DR

This paper surveys recent GAN research, focusing on architectures, training methods, and applications in emotion recognition, and presents a new dataset of emotion images along with experiments using StarGAN.

Contribution

It provides a comprehensive review of GAN advancements and introduces a novel emotion image dataset with experimental analysis using StarGAN.

Findings

StarGAN trained on emotion dataset shows promising results

New dataset captures diverse 'in the wild' emotion images

Survey highlights future directions for GAN research in emotion recognition

Abstract

Generative Adversarial Networks (GANs) were proposed in 2014 by Goodfellow et al., and have since been extended into multiple computer vision applications. This report provides a thorough survey of recent GAN research, outlining the various architectures and applications, as well as methods for training GANs and dealing with latent space. This is followed by a discussion of potential areas for future GAN research, including: evaluating GANs, better understanding GANs, and techniques for training GANs. The second part of this report outlines the compilation of a dataset of images `in the wild' representing each of the 7 basic human emotions, and analyses experiments done when training a StarGAN on this dataset combined with the FER2013 dataset.