Enhancing music information retrieval by incorporating image-based local features

This paper presents a novel approach to Music Information Retrieval. Having represented the music tracks in the form of two dimensional images, we apply the "bag of visual words" method from visual IR in order to classify the songs into 19 genres. By switching to visual domain we can abstract from musical concepts such as melody, timbre and rhythm. We obtained classification accuracy of 46% (with 5% theoretical baseline for random classification) which is comparable with existing state-of-the-art approaches. Moreover, the novel features characterize different properties of the signal than standard methods. Therefore, the combination of them should further improve the performance of existing techniques