The identification of students in exams is currently done by physically checking each and every student if their appearance and identity match the one on their student ID cards. If we wish to shorten the time needed to check students' identities, we need a more efficient way of verification. We solve this problem by developing a plugin for the Moodle learning management software, which is able to record prints of typing styles and images of faces by displaying an input form. Along with the plugin, we develop a backend system, that can distinguish faces using the OpenFace open-source library and typing styles. Finally, we test the system's reliability on volunteers and see that its accuracy is very high when using both comparison techniques.
|
