Computer Science Review· 2026Q1· Review
Deep learning for optical music recognition: A review
- 5citations
- Q1SCImago
- 2026year
Short summary
Deep learning has revolutionized Optical Music Recognition (OMR), significantly improving music score digitization for accessibility, preservation, and analysis.
AI-generated from the title and abstract; the full text is not read.
Key points
- Deep learning has revolutionized Optical Music Recognition (OMR), surpassing earlier heuristic methods.
- DL techniques have significantly improved OMR tasks like layout analysis, symbol recognition, and music transcription.
- The review provides an in-depth analysis of datasets, evaluation metrics, methodologies, and results of DL-based OMR approaches.
- Key challenges and future research directions in OMR are identified.
AI-generated from the title and abstract; the full text is not read.
Abstract
This paper presents a comprehensive review of the advancements in Optical Music Recognition (OMR) driven by Deep Learning (DL) techniques. OMR aims to digitize music scores, transforming them into structured formats to enhance accessibility, facilitate preservation, and enable automated analysis. While early methods were based on heuristic approaches, the adoption of DL has revolutionized the field, achieving remarkable improvements in tasks such as layout analysis, symbol recognition, and music transcription. This survey offers a detailed examination of recent DL-based approaches, providing an in-depth analysis of datasets, evaluation metrics, methodologies, and results. Additionally, it explores emerging trends, identifies key challenges, and proposes future directions to advance OMR research. Despite the substantial progress achieved, critical challenges remain, highlighting the need for continued innovation and positioning this review as a valuable reference for both new and experienced researchers in OMR.
The authors' abstract, as published at the source. Computer Science Review, 2026 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionComputer Science