Facial Expression-Driven Music Recommendation: A Novel Approach for Personalized Listening Experiences

The potential of customized music recommendation systems to boost user happiness and engagement has gained a lot of attention in recent years. The use of non-verbal clues like facial expressions to provide better suggestions that take the user’s situation into account is gaining popularity. In this study, we provide an innovative approach to music recommendation using facial expressions, with a focus on creating unique listening sessions for each individual user. The main goal is to provide a new approach to automate music playing based on the analysis of facial expressions. Most existing techniques either need human intervention, the use of wearable computers, or the categorization of aural features. We suggest instead that music be chosen and played automatically. Convolutional neural networks have been successfully used to the problem of emotion recognition. We use Pygame and T-Kinter to implement music suggestion. By implementing our proposed strategy, we anticipate a decrease in overall system costs and processing time, which will result in enhanced precision. We evaluate the efficacy of the system using the FER dataset, which captures facial expressions using an integrated camera. These facial images are then processed to identify different emotions, such as surprise, joy, anger, sorrow, and neutrality. Based on the user’s current disposition, a music playlist is automatically generated. In terms of computational efficiency, our method outperforms all previously described methods.