Humans have traditionally had an easy time detecting emotions from facial expression, but performing the same feat with a computer programme is rather difficult. It is now possible to discern emotions from photos because to recent advances in computer vision and machine learning. This study provides an overview of the current phases, methodologies, and datasets for Facial Emotion Recognition (FER). For decades, FER has been identified, and it is a critical topic in the disciplines of computer vision and machine learning. Automatic FER is beneficial in a wide range of applications, including healthcare, safety, education, criminal investigation, and the Human Robot Interface, among others. This study provides a review of the most effective strategies offered in recent years, as well as a brief introduction to the system and database that were employed. For the identical problem mentioned in this document, several writers have utilised alternative algorithms. Various approaches of emotion recognition are reviewed and contrasted in this review paper. The goal of this paper is to review recent research on automatic facial emotion recognition (FER) using a convolutional neural network