The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Publications Copernicus
Download
Citation
Articles | Volume XLVI-4/W3-2021
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 103–107, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-103-2022
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVI-4/W3-2021, 103–107, 2022
https://doi.org/10.5194/isprs-archives-XLVI-4-W3-2021-103-2022
 
10 Jan 2022
10 Jan 2022

DEEP LEARNING: NEW APPROACH FOR DETECTING SCHOLAR EXAMS FRAUD

S. El Kohli, Y. Jannaj, M. Maanan, and H. Rhinane S. El Kohli et al.
  • Earth Sciences Department, Faculty of Sciences Ain Chock, University Hassan II, Casablanca, Morocco

Keywords: Deep learning, cheating on exams, CNN, 3DCNN, image classification, Object detection, OpenCV

Abstract. Cheating in exams is a worldwide phenomenon that hinders efforts to assess the skills and growth of students. With scientific and technological progress, it has become possible to develop detection systems in particular a system to monitor the movements and gestures of the candidates during the exam. Individually or collectively. Deep learning (DL) concepts are widely used to investigate image processing and machine learning applications. Our system is based on the advances in artificial intelligence, particularly 3D Convolutional Neural Network (3D CNN), object detector methods, OpenCV and especially Google Tensor Flow, to provides a real-time optimized Computer Vision. The proposal approach, we provide a detection system able to predict fraud during exams. Using the 3D CNN to generate a model from 7,638 selected images and objects detector to identify prohibited things. These experimental studies provide a detection performance with 95% accuracy of correlation between the training and validation data set.