Formation of an Original Database and Development of Innovative Deep Learning Algorithms for Detecting Face Impersonation in Online Exams
Formation of an Original Database and Development of Innovative Deep Learning Algorithms for Detecting Face Impersonation in Online Exams作者机构：Department of Computer Science and Digital Science Virtual University of Côte d’Ivoire Abidjan Côte d’Ivoire
出 版 物：《Open Journal of Applied Sciences》 (应用科学（英文）)
年 卷 期：2023年第13卷第12期
页 面：2223-2232页
学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）]
主 题：Online Exams Face Recognition Convolutional Neural Networks Data Bias
摘 要：The issue related to the risk of identity impersonation, where one person can be replaced by another in online exam surveillance systems, poses challenges. This study focuses on the effectiveness of detecting attempts of identity impersonation through face substitution during online exams, with the aim of ensuring the integrity of assessments. The goal is to develop facial recognition algorithms capable of precisely detecting these impersonations, training them on a tailored database rather than biased generic data. An original database of student faces has been created. An algorithm leveraging advanced deep learning techniques such as depthwise separable convolution has been developed and evaluated on this database. We achieved very high levels of precision, reaching an accuracy rate of 98% in face detection and recognition.
维普期刊数据库