Automated assessment of pen and paper tests using computer vision

Abstract

Computer vision is one of the artificial intelligence’s most challenging fields, enabling computers to interpret, analyse and derive meaningful information from the visual world. There are various utilizations of computer vision algorithms, and most of them, from simpler to more complicated, have an object and shape recognition in common. Traditional pen and paper tests are designed in a pre-established format and consist of numerous basic shapes, which designate the important parts of the test itself. With that in mind, many computer vision applications regarding pen and paper tests arise as an opportunity. Massive courses and large schooling organizations mostly conduct their exams in paper format and assess them manually, which imposes a significant burden on the teaching staff. Any kind of automatization that will facilitate the grading process is highly desirable. Hence, an automated answer recognition system in assessment was developed to mitigate the problems above. The system uses images of scanned test pages obtained from the test scanning process and performs the necessary image manipulation steps to increase target recognition accuracy. Further, it manages to identify regions of interest containing multiple-choice questions and contours. Finally, the system verifies obtained results using the knowledge of the whereabouts of the test template regions of interest.

Software System for Automatic Grading of Paper Tests

“…These question classes are presented in ascending order of complexity, considering the technologies required to effectively address them. Initially, the implemented system focused solely on automating the evaluation of multiple-choice questions [7], and a comprehensive account of this capability can be found in previous research [8]. However, subsequent developments have facilitated the expansion of the system to encompass the automated assessment of matching questions, where correct answers are underlined, as well as short answer questions involving numerical responses.…”

“…The chosen systems satisfying the previously given criteria were developed at the School of Electrical Engineering, University of Belgrade (SEE-UB) [8], School of Engineering, Edith Cowan University (SE-ECU) [9], Department of Telematic Engineering, University Carlos III of Madrid (DTE-UCM) [10], School of Electronic and Information Engineering, Foshan University (SEIE-FU) [11], Prince Mohammad bin Fahd University (PMFU) [12], Artificial intelligence Department, Faculty of Computers and Artificial Intelligence, Benha University (FCAI-BU) [13], Information Technologies Division, Adana Alparslan Turkes Science and Technology University (ITD-AATSU) [14], School of Software South China, University of Technology Guangzhou and College of Medical Information Engineering, Guangzhou University of Chinese Medicine (SSSC-UTG/CMIE-GUCM) [15].…”