Affective Music Recommendation System Reflecting the Mood of Input Image

摘要

We present an affective music recommendation system using input images without textual information. Music that matches our current mood can create a deep impression. However, we do not know which music best matches our present mood. As it is difficult to select music manually, we need a recommendation system that can operate affectively. In this paper, we assume that there exists a relationship between our mood and images because visual information affects our mood when we listen to music. Our system matches an input image with music using valence-arousal plane which is an emotional plane.