MF-tree: Extracting and Clustering the Structural Features from Music Object in MusicXML

In the music information retrieval field, the most important topic is to extract the feature which represents the content from the music objects. The content feature is useful for music analysis, music retrieval, and other services. In this paper, our data form is MusicXML. We extract the structural feature from the classical music object and it is based on music theory and music form. According to the hierarchical rule of music form, we construct a tree which is called MF-tree, it is also to be provided with music theory feature and structure in the MF-tree. We also propose the dissimilarity function of MF-tree to calculate the dissimilarity of music objects. Finally, we adapt the hierarchical clustering and system implementation to show the clustering.