https://github.com/aashrafh/mozart

An optical music recognition (OMR) system. Converts sheet music to a machine-readable version.
https://github.com/aashrafh/mozart

mozart music music-sheet music-sheet-reading neural-network omr opencv optical-character-recognition optical-music-recognition reader skimage sklearn

Last synced: 3 days ago
JSON representation

An optical music recognition (OMR) system. Converts sheet music to a machine-readable version.

• Host: GitHub
• URL: https://github.com/aashrafh/mozart
• Owner: aashrafh
• License: apache-2.0
• Created: 2020-12-14T11:49:14.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2022-08-24T18:18:43.000Z (over 2 years ago)
• Last Synced: 2024-12-28T02:17:10.666Z (3 days ago)
• Topics: mozart, music, music-sheet, music-sheet-reading, neural-network, omr, opencv, optical-character-recognition, optical-music-recognition, reader, skimage, sklearn
• Language: Jupyter Notebook
• Homepage:
• Size: 350 MB
• Stars: 627
• Watchers: 17
• Forks: 92
• Open Issues: 4
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml
  • License: LICENSE

Awesome Lists containing this project

README

        


  

 



 :notes: Convert sheet music to a machine-readable version.

    
 





  

        

  

   

        

  

  

        

        

  

        

        

  

        



---

## 📝 Table of Contents

- [About](#about)

- [Methodology](#methodology)

- [Install](#Install)

- [Technology](#tech)

## 🧐 About 

The aim of this project is to develop a sheet music reader. This is called Optical Music Recognition (OMR). Its objective is to convert sheet music to a machine-readable version. We take a simplified version where we convert an image of sheet music to a textual representation that can be further processed to produce midi files or audio files like wav or mp3. 



  

 



## :computer: Methodology 

### 1. Noise Filtering and Binarization



  

 



### 2. Segmentation



  

  
 
 

  
 
 

  



### 3. Staff Line Detection and Removal



  

  
 
 

  
 
 

  



### 4. Construct The New Staff Lines



  

  
 
 

  
 
 

  



### 5. Symbol Detection and Recognition



  

  
 
 

  
 
 

  



## 🏁 Install 

1. You can use the attached notebook for quick testing and visualization.

2. You can setup an environment on your local machine to run the project:

    1. Install [Conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/)

    2. ```conda env create -f requirements.yml```

    3. ```conda activate mozart```

    4. ```python3 main.py  ```

> You can find the dataset on [Google Drive](https://drive.google.com/drive/u/0/folders/1OVGA3CGnEKjyg_k_L8MP2RO5R3oDIbHE).

> Please check the following [issue](https://github.com/aashrafh/Mozart/issues/8) for another ```requirements.yml``` file. 

## ⛏️ Built Using 

- [Python 3.8.3](https://www.python.org/)

- [NumPy](https://numpy.org/doc/stable/index.html)

- [OpenCV](https://opencv.org/)

- [scikit-learn](https://scikit-learn.org/stable/)

- [scikit-image](https://scikit-image.org/)