A MACHINE LEARING BASED MUSIC PLAYER BY DETECTING EMOTIONS

We propose a novel method for automatically playing music based on facial emotion.The majority of existing approaches involve manually playing music, using wearable computing devices, or classifying based on audio features.Instead, we propose that the manual sorting and playing be changed.For emotion detection, we used a Convolutional Neural Net.TensorFlow used to make music recommendations.Our developed scheme tends to reduce the computational time required to obtain the results as well as the overall cost of the proposed framework, thereby increasing the overall accuracy of the system.The system is tested using the FER2013 dataset.Using an embedded camera, facial expressions are managed to capture.Feature extraction is performed on detected face images to detect emotions such as happy, angry, heartbreaking, surprise, and neutral.The user's current emotion is used to develop a fully automated music playlist.When compared to the algorithm in the relevant research, it performs better in terms of computational time.