Grade exams fast and accurately using a scanner π¨ or your phone π€³.
TLDR; Jump to Getting Started.
A full-fledged OMR checking software that can read and evaluate OMR sheets scanned at any angle and having any color. Support is also provided for a customisable marking scheme with section-wise marking, bonus questions, etc.
π― Accurate - Currently nearly 100% accurate on good quality document scans; and about 90% accurate on mobile images.
πͺπΏ Robust - Supports low resolution, xeroxed sheets. See Robustness for more.
β© Fast Current processing speed without any optimization is 200 OMRs/minute.
β Extensible - Easily apply to different OMR layouts, surveys, etc.
π Visually Rich Outputs - get insights to configure and debug easily.
π Lightweight - Core code size is less than 500 KB(Samples excluded).
π« Large Scale - Already used on tens of thousands of OMRs at Technothlon.
π©πΏβπ» Dev Friendly - Well documented repository based on python and openCV.
Devs can look at TODOs for live challenges. See more at Project Wiki.
Although windows is supported, Linux is recommended for a bug-free experience.
Note: To get a copy button for below commands, use CodeCopy Chrome | CodeCopy Firefox.
python3 -m pip install --user --upgrade pip
python3 -m pip install --user opencv-python
python3 -m pip install --user opencv-contrib-python
More details on pip install openCV here.
Note: On a fresh computer some of the libraries may get missing in above pip install.
Install them using the following commands: Windows users may skip this step.
sudo apt-get install -y build-essential cmake unzip pkg-config
sudo apt-get install -y libjpeg-dev libpng-dev libtiff-dev
sudo apt-get install -y libavcodec-dev libavformat-dev libswscale-dev libv4l-dev
sudo apt-get install -y libatlas-base-dev gfortran
git clone https://github.com/Udayraj123/OMRChecker
cd OMRChecker/
python3 -m pip install --user -r requirements.txt
Note: If you face a distutils error, use the
--ignore-installed
flag
sudo python3 -m pip install --ignore-installed -r requirements.txt
- Copy sample data:
Note: If you are not running this for the first time, delete previous inputs first
cp -r inputs/samples/sample1/* inputs/
mv inputs/OMR_Files/ ~/.trash # can delete permanently using: rm -rf inputs/OMR_Files/ cp -r inputs/samples/sample1/* inputs/
- Run OMRChecker:
python3 main.py
- ???
- Profit!!
Note: For subsequent runs, if you don't want the outputs to append to previous results-
Make sure the outputs
folder is clean : rm -rf outputs/
.
- Follow the User Guide to create your own Template Layout.
- Open
globals.py
and play with the parameters (although most of them would need no change π) - Run the code with appropriate arguments.
Once you configure the OMR layout, just throw images of the sheets at the software; and you'll get back the graded responses in an excel sheet!
Images can be taken from various angles as shown below-
These images will be processed in the following manner:
*Note: This image is generated by the code itself!*
Finally a CSV file will also be generated containing all the responses and scoring
There are a lot more visuals in the wiki. Check them out!
Our Motto:
Don't reinvent the wheel, use good wheels to make great vehicles!
After seeing it work fabulously at large scale on scanned OMR sheets at Technothlon, we have decided to open source the code and roll out mobile based scanning as well. The feedback from you all will be extremely valuable in making this idea become successful.
OMRChecker is completely open source and published under GPLv3 license which is just to give you a heads up to disclose usage of this software in your code.
OMRChecker can be forked and modified. You are encouraged to play with it and we would love to see your own projects in action!
A Huge thanks to : The creative master Adrian Rosebrock for his blog : https://pyimagesearch.com
The legendary Harrison aka sentdex for his video tutorials.
And the james bond of computer vision Satya Mallic for his blog: https://www.learnopencv.com
And many other rockstars without whom this project would never have completed.
Thank you!
Copyright Β© 2019 Udayraj Deshmukh
OMRChecker : Grade exams fast and accurately using a scanner π¨ or your phone π€³
This is free software, and you are welcome to redistribute it under certain conditions;
Here's a sneak peak of the Android OMR Helper App(WIP):
Help us reach 550 stars β to become #1 (Currently #4) on the "OMR" tag on github
To keep my π‘ brain juices flowing and create more such projects, β Buy Me A Coffee
If this project saved you large costs on OMR Software licenses, or saved efforts to make one, or simply want to give me some credit:
Note: As per non-profit traditions of Technothlon, all of your your donations will go into funding good initiatives in the future.