Expression Modelling Of Facial Dataset Using DCGAN For Facial Expression Recognition

Abstract

Facial Expression Recognition is an area of research which involves studying emotions and classifying it. FER is one of the challenging tasks and has a wide range of application. Facial expression recognition involves identifying six basic emotions such as anger, sad fear, smile, surprise, and disgust. Combining Generative Adversarial Networks with deep learning methods and image synthesis using GAN is a recent area of research. Over years various GAN methods have been developed and used in a wide range of applications such as improving resolution, generating animation characters, and various image modeling applications. In this paper, we are going to analyze the performance of DCGAN on the FEI dataset.