A full-fledged OMR checking software that can read and evaluate OMR sheets scanned at any angle and having any color. With support for a customizable marking scheme with section-wise marking, bonus questions, etc.
Preferred operating system : Linux
Use --depth=1
if you want only the latest version(less than half download size)
git clone https://github.com/udayraj123/OMRChecker
More details here: https://www.pyimagesearch.com/2018/09/19/pip-install-opencv/
sudo python3 -m pip install --upgrade pip
sudo python3 -m pip install opencv-python
sudo python3 -m pip install opencv-contrib-python
sudo python3 -m pip install -r requirements.txt
If you face an distutils error, use the --ignore-installed
flag
sudo python3 -m pip install --ignore-installed -r requirements.txt
- Make a copy of 'OMR_Files_sample' and rename it to 'OMR_Files' (Do not make changes to the directory structure)
- Run code
python3 main.py
- 😏 😏 😏
- Profit!!
This structure has been created to suit for better organization of OMRs (Citywise, then Group-wise and Language-wise). Making changes to this would require changes in the code.
1. Put your OMR images in `inputs/OMR_Files/CityName/HE` (You can rename CityName)
2. Put marker crop at `inputs/omr_marker.jpg`
3. Put template layout(s) in `inputs/Layouts` (Guide coming soon)
4. Adjust templ_scale_fac in globals.py
5. (optional) More advanced configuration can be done in globals.py
6. Run code - If your images are taken close-up using scanner, remember to run code with `--closeUp` option.
**/ignore
**/gitignore
**/CheckedOMRs
**/OMR_Files
outputs/Results
**/__pycache__