CVOct 12, 2018

DeepScores and Deep Watershed Detection: current state and open issues

arXiv:1810.05423v15 citations
Originality Synthesis-oriented
AI Analysis

This work addresses challenges in Optical Music Recognition for researchers and practitioners, but it is incremental as it summarizes existing efforts without presenting new results.

The paper provides an overview of current Optical Music Recognition research, including the release of the DeepScores dataset and Deep Watershed Detector method, with ongoing efforts to improve their usefulness for real-world tasks and address extreme class imbalance.

This paper gives an overview of our current Optical Music Recognition (OMR) research. We recently released the OMR dataset \emph{DeepScores} as well as the object detection method \emph{Deep Watershed Detector}. We are currently taking some additional steps to improve both of them. Here we summarize current and future efforts, aimed at improving usefulness on real-world task and tackling extreme class imbalance.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes