Optical Mark Recognition: Advances, Difficulties, and Limitations

Abstract

Performing mass assessment corrections is a tedious and costly task, especially when allocating teachers or instructors to do these corrections. Such task can be facilitated and accelerated by Optical Mark Recognition (OMR) technology, bringing educational institutions to look for this solution. OMR initially appeared as a dedicated hardware solution, but software solutions have emerged with the evolution of technology, gradually replacing dedicated equipment. However, most solutions lack flexibility, mainly for the end-users. The literature proposes several methods, often highlighting the issue of cost and accessibility. The present work reviews 35 papers around OMR subject and lists the reviewed methods' main characteristics, datasets, restrictions, technological challenges, techniques used, processing time, and accuracy. We map and categorize the restrictions to help the reader improve the current software OMR technology state. We also call the community's attention to the lack of a standard dataset that could be used to compare OMR solutions.

Automated Paper-based Multiple Choice Scoring Framework using Fast Object Detection Algorithm

“…OMR is now widely used for exams or surveys with multiple choice answers [1]. According to Zhang et al [2], this is the most common type of exercise used in education.…”