Direct Content-Based Retrieval from Music Score Images

The digitization of musical scores plays a crucial role in their preservation and accessibility, yet information retrieval still depends mainly on metadata searches, such as by title or composer. Content-based search in music score images remains underexplored compared to text documents despite its potential value for musicians, musicologists, and educators. This work contributes to the field by proposing a methodological framework that discusses and motivates the relevance of different score characteristics for general content-based music score retrieval and then defining a systematic method for constructing query datasets from any corpus annotated for OMR. We also consider diverse methods for content-based search on music score images, including transcription-based approaches relying on optical music recognition (OMR), a transcription-free Transformer model trained to recognize queries directly from score images, and a text-prompted large language model. Our experiments evaluate these models on four corpora exhibiting diverse characteristics in terms of dataset size, image quality, and typesetting mechanisms. Overall, each method excels under different conditions: OMR-based pipelines achieve higher in-domain retrieval, whereas transcription-free models remain more robust in the tested domain shifts.