Skip to content

OMR based auto grader tool for paper based MCQ questions.

License

Notifications You must be signed in to change notification settings

GayashanNA/MCQAutoGrader

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

28 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

OMR based MCQ Autograder

MCQAutoGrader implements an Optical Mark Recognition based autograding tool for paper based MCQ questions. The project is mainly designed to be used for CS1033 Programming Fundamentals course offered by the Dept. of Computer Science and Engineering at University of Moratuwa, Sri Lanka.

MCQAutoGrader is designed to take a list of scanned answer scripts (bubble sheets) as inputs along with the marking scheme and the template of the bubble sheet. The template of the bubble sheet is available here.

The project uses poetry for dependency management and packaging. To set up the dependencies run the following command after cloning/downloading the repository.

poetry install

Using the autograder tool

To find more information about the tool execute the following command after you have set up the project:

python3 mcqautograder/autograder.py --help

Typical use of the tool require the template, marking scheme, directory containing scanned answer scripts, a list of students as a csv file to be provided as follows. Refer the samples directory.

python3 mcqautograder/autograder.py --template samples/template.jpg --markingscheme samples/marking_scheme.jpg --answers samples/answers/ --studentslist samples/students_list.csv

Using the multiversion_autograder tool

MCQAutoGrader also contains a multiversion_autograder tool to grade exam papers with multiple versions. Typical use of this tool would require templates and marking schemes for each version, directory containing scanned answer scripts, and a list of students and the corresponding exam paper version given to the student as a csv file to be provided as follows. Refer the samples directory.

python3 mcqautograder/multiversion_autograder.py --templates samples/templates/ --markingschemes samples/marking_schemes/ --answers samples/answers/ --studentslist samples/students_list.csv --numversions 2

Please note that here the templates and corresponding marking schemes should be renamed to just the version number (eg: 1.jpg, 2.jpg, ...).

Contact

If you have any questions, please contact: [email protected]

Acknowledgements

This project is inspired and based on the following work. Special thanks should go to these authors for their contributions:

[1] Chidrewar, Vaibhav, Junwei Yang, and Donguk Moon. "Mobile based auto grading of answersheets." (2014).

[2] Jain, Salay and Sharma, Harsh, "OMR-Auto-Grading-System", https://github.com/salay-jain/OMR-Auto-Grading-System

About

OMR based auto grader tool for paper based MCQ questions.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%