Deep dual domain joint discriminant feature framework for emotion based music player

Emotion based music player is an interdisciplinary study of computer vision and psychology. As music enhances the positive vibes it plays a significant role in soothing people’s emotion. Emotions can be predicted through facial expression analysis using vision-based methods. However, challenges like environment and expression complexity have become hindrance to attain a good recognition rate. Therefore, we put forward a deep dual domain joint feature framework based on linear discriminant analysis for facial emotion recognition. First, we detect the human face and learn the emotion pattern using the popular complementary deep domain networks called EfficientNet and ResNet50. The learned deep dual domain space is projected onto linear discriminant space to achieve a joint discriminant feature space. The recognition rate of the proposed joint discriminant feature framework is analyzed using support vector machine. To prove the efficacy of the proposed framework, we validated it on two Benchmarks namely FER2013 and CK48+ datasets. The proposed framework achieved a good recognition rate of 99% and 98.6% on FER2013 and CK48+ respectively. Experimental analysis on our EmDe dataset showed an accuracy of 99% and proves that the deep dual domain joint discriminant framework as a promising pipeline for emotion-based music player system.