Deep Watershed Detector for Music Object Recognition
This addresses the challenge of accurately recognizing music symbols in digital images for music information retrieval, with incremental improvements in detection methods.
The paper tackles the problem of detecting music symbols in high-resolution images for Optical Music Recognition by introducing the Deep Watershed Detector, achieving state-of-the-art results on common music symbols and demonstrating effectiveness on both synthetic and handwritten scores.
Optical Music Recognition (OMR) is an important and challenging area within music information retrieval, the accurate detection of music symbols in digital images is a core functionality of any OMR pipeline. In this paper, we introduce a novel object detection method, based on synthetic energy maps and the watershed transform, called Deep Watershed Detector (DWD). Our method is specifically tailored to deal with high resolution images that contain a large number of very small objects and is therefore able to process full pages of written music. We present state-of-the-art detection results of common music symbols and show DWD's ability to work with synthetic scores equally well as on handwritten music.