A Multiple-Choice Test Recognition System based on the Gamera Framework

Abstract

This article describes JECT-OMR, a system that analyzes digital images representing scans of multiple-choice tests compiled by students. The system performs a structural analysis of the document in order to get the chosen answer for each question, and it also contains a bar-code decoder, used for the identification of additional information encoded in the document. JECT-OMR was implemented using the Python programming language, and leverages the power of the Gamera framework in order to accomplish its task. The system exhibits an accuracy of over 99% in the recognition of marked and non-marked squares representing answers, thus making it suitable for real world applications