PROCEEDING IC-ITECHS 2014
Vol 3 No 1 (2022): IC-ITECHS

Cheating Detection During Exam with YOLO V4

Fani Oktaf Laurisa (STIKI Malang, Indonesia)
Keith Marvin Sajul (Chandigarh University, Punjab, India)
Arif Tirtana (STIKI Malang, Indonesia)



Article Info

Publish Date
23 Dec 2022

Abstract

Computer-based exams have been widely implemented in various agencies in Indonesia, especially in the field of education. But in practice use Computer Based Test(CBT). Does not guarantee that examines do things honestly, if the supervisor is negligent then the opportunity to cheat appears. This can be minimized by using technology Artificial Intelligence(AI), especially in domains of computer vision (CV). Start with observation problems and then collect datasets in the form of human images facing the camera and looking sideways, then do the image annotation, pre-processing data, YOLOv4 architecture design, training data, model testing, and finally deployment of the application on the website. The model test result show accuracy with a precision score of 0.99 (99%), a recall score of 1.00(100%), and an F-1 Score of 0.99(99%).

Copyrights © 2022