Exploring the Role of Computer Vision in Human Emotion Recognition: A Systematic Review and Meta-Analysis

Human emotion recognition is an important area of research with numerous applications in various fields. In recent years, computer vision techniques have emerged as a promising approach for automated human emotion recognition. This systematic review and meta-analysis provide an overview of the role of computer vision in human emotion recognition research. The review found that computer vision techniques have been utilized for a range of tasks related to human emotion recognition, including facial expression recognition, body posture analysis, and speech and voice analysis. The most used computer vision techniques include deep learning, support vector machines, and principal component analysis. The accuracy of computer vision-based emotion recognition approaches varied widely across studies, with reported accuracies ranging from 60% to 99%. The review identified several factors that may influence the accuracy of these approaches, including the quality of the data used for training and testing, the complexity of the emotions being recognized, and the choice of features and algorithms used for analysis. Additionally, ethical considerations related to privacy and bias were discussed as important considerations in the development and deployment of computer vision-based emotion recognition systems. In conclusion, this systematic review and meta-analysis provides a comprehensive overview of the role of computer vision in human emotion recognition research. The findings suggest that computer vision techniques have the potential to contribute significantly to the field, but further research is needed to address the identified limitations and challenges. The results of this review could be used as a basis for future research and development of computer vision-based emotion recognition systems.