Emotion detection from facial expressions using transfer deep learning methods

This study was conducted to evaluate the emotion recognition capabilities of artificial intelligence and deep learning techniques. The need to understand human emotions and analyze them through facial expressions is increasing with the advancement of technology. In this context, emotion analysis was performed using Residual Network (ResNet) and transfer learning models. The focus of the study is to emphasize the effectiveness of the ResNet50 model in emotion recognition tasks. The ResNet architecture is developed to facilitate the training of deep neural networks and reduce overfitting issues. The models aim to transfer the knowledge learned through transfer deep learning to the emotion recognition task. The study was conducted on the Fer2013 dataset, and the performance of the models was evaluated with various metrics. The results obtained indicate that the ResNet50 model has a higher success rate compared to other models. These findings contribute to our understanding of the future potential of artificial intelligence-based emotion recognition applications and the impact of deep learning models in this field. The findings of the study can guide researchers in the development and improvement of emotion recognition technologies. Artificial intelligence-based emotion analysis can find applications in a wide range of fields, from the healthcare sector to smart living spaces, and enhance human-machine interaction. In this context, the success of the ResNet50 model emphasizes the importance of using deep learning models in the field of emotion recognition.