Enhancing Facial Emotion Detection with CNN: Exploring the Impact of Hyperparameters

In recent years, computer vision and machine learning have seen a surge in research on Facial Emotion Recognition (FER). The significance of accurately recognizing and interpreting facial expressions for effective communication and social interaction cannot be overstated, making FER a topic of interest in diverse several disciplines, such as psychology, human-computer interaction, and security. Our research paper focuses on deep learning techniques for facial emotion recognition (FER). We specifically investigate the usefulness of Convolutional Neural Networks (CNN) in FER, due to their excellent performance in image classification challenges and their capacity to automatically identify key characteristics from images. Many datasets are researched and analyzed in this study for training expression recognition algorithms. Many datasets are researched and analyzed in this study for training expression recognition algorithms. Our study enhances the state-of-the-art model's accuracy to 98.85%, outperforming other existing models. This study will provide further information about face emotion detection and recognition. It will also highlight the aspects that influence its efficiency.