Performance Evaluation of Intelligent Driving Emotion Recognition Model based on Synthetic Dataset in Real Scenes

The paper aims to explore the feasibility of using artificially generated facial expressions with different emotions to enhance the features and increase the data volume for emotion recognition in the context of intelligent cockpit. The paper first introduces the background and significance of the research, which is motivated by the increasing number of private cars in China, the development of intelligent cockpit technology, and the importance of emotion recognition for driving safety. The paper then reviews the existing literature on emotion recognition based on facial recognition, and points out the challenges and limitations of using real datasets, such as ImageNet, which may have high cost, low quality, privacy issues, and inaccurate annotations. The study suggests utilizing synthetic facial expressions that convey a range of emotions, created through advanced deep learning algorithms, as a solution to enhance the precision and reliability of the emotion detection system. The paper further examines the prospective applications and effects of the recommended technique pertaining to the realm of intelligent automotive cockpits and the associated vehicular journey. The paper concludes by summarizing the main contributions and limitations of the research, and suggesting some directions for future work.