| Title |
The Cheating Probability Prediction System usingGaze Estimation and Glasses Removal Algorithms |
| Authors |
박상진(Sangjin Park) ; 김대하(Daeha Kim) ; 송병철(Byung Cheol Song) |
| DOI |
https://doi.org/10.5573/ieie.2021.58.8.89 |
| Keywords |
Gaze estimation; Generative networks; Human-computer interaction (HCI) |
| Abstract |
In this paper, we propose a system that predicts the probability to cheating from the subject’s gaze information to improve the efficiency of online class. The gaze estimation technique is an efficient method for estimating the gaze direction of the subject, and accurate gaze information can be extracted through a neural network. In addition, the performance of the gaze estimation algorithm has been further improved by introducing a glasses removal algorithm to accurately obtain eye region information, which is a key element required for gaze estimation, and shows robust estimation performance against various cheating scenarios. |