Proposed method for Cheating Detection in Examination using Digital Image Processing
in Public Sector Universities in Pakistan: Review
Farooq Faisal, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Saleem Zahid, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Lala Rukh, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Said Ul Abrar, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Gohar Rehman Khalil, Institute of Computer Sciences and Information Technology (ICS/IT), The University of Agriculture Peshawar, Pakistan.
Corresponding Author:
Farooq Faisal (farooqfaisal83@gmail.com)
Abstract:
One of the main issues associated with the modern education system and to evaluate the students through written exams is cheating using Unfair means. This problem of cheating in exams is a growing concern in academic institutions worldwide. Conventional and traditional systems fail or found incomplete to overcome this issue, Digital image processing (DIP) could be the possible and timely solution. DIP techniques can be used to detect images of students cheating in exam halls and distinguish them from images of normal students attempting the paper. This paper presents a comprehensive approach for detecting images of students cheating in exam halls, using digital image processing techniques such as image acquisition, image preprocessing, feature extraction, and image classification. We propose a feature extraction method that captures the unique visual patterns associated with cheating behavior, and we train a classifier using labeled data to distinguish between images of students cheating and those of normal students attempting the paper. We will implement the proposed approach using MATLAB, and will evaluate its performance using a dataset of images of students in exam halls. The results will demonstrate the effectiveness of the proposed approach in detecting images of students cheating in exam halls and expect for achieving high classification accuracy. The proposed approach has the potential to be used as a tool to prevent and deter cheating in academic institutions.
Keywords:
Digital Image Processing; Preprocessing; Feature Extraction; Classification; Accuracy