A Review on Facial Expression Recognition Models, Datasets, and Future Direction of Research

Facial Expression Recognition (FER) is an emerging area of study and has been an innovative area of research nowadays. It has many real-life uses like recognizing the emotions of individuals for security purposes, as one can know a lot about someone's actions from their expressions. Other areas explored are social media to boost the experience of the user. FER can be implemented using different types of Machine Learning (ML) and Deep Learning (DL) architectures by constructing a model for optimal efficiency. The performance can also be affected by the dataset used to train the model. Multiple aspects of FER use different types of models and datasets. The paper highlights and compares the results of different models and datasets. The concern of the paper is to review previous works to improve the FER field for future researchers.