Lauda Manuscript Dataset with Active and Sequential Learning Codebase for Optical Music Recognition (OMR)

This archive contains the full dataset and Python codebase used in our MLSP 2025 paper: **“Experimenting Active and Sequential Learning in a Medieval Music Manuscript”** It supports **Optical Music Recognition (OMR)** and **Active Learning and Sequential Learning experiments** on historical document images. --- ### 📦 Contents:- `images/`: 340 high-resolution digitized medieval manuscript pages - `annotations/`: COCO-format JSON with bounding boxes and class labels - `data_split.py`: Creates train/val splits - `Sequential_learning.py`: Trains the baseline object detection model - `Uncertainty_AL.py`: Performs uncertainty-based active learning - `README.md` and `LICENSE` --- ### 📄 License:Creative Commons Attribution 4.0 International (CC BY 4.0) --- ### 📚 Citation:If you use this dataset or code, please cite: > Sharma, S., Simonetta, F., & Flammini, M. (2025). *Experimenting Active and Sequential Learning in a Medieval Music Manuscript*. IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Gran Sasso Science Institute, Italy. --- ### 🏛️ Acknowledgment This work has been funded by the European Union (Horizon Programme for Research and Innovation 2021–2027, ERC Advanced Grant **“The Italian Lauda: Disseminating Poetry and Concepts Through Melody (12th–16th century)”**, acronym **LAUDARE**, project no. **101054750**). The views and opinions expressed are, however, only those of the authors and do not necessarily reflect those of the European Union or the European Research Council. Neither the European Union nor the awarding authority can be held responsible for such matters.