An Android-based Face Recognition System for Class Attendance and Malpractice Control

Abstract

Over time, examination malpractice in form of students indulging in impersonation has been a serious setback to academic growth in several Educational institutions. Conventional methods of keeping student’s attendance records has proved inefficient as there are so many cases of data loss and mismanagement. Several systems developed to solve this problem are either immobile or costly to implement. In order to solve this problem of cost and rigidity as well as remove the problem of examination impersonation, a mobile system running on the Android Operating System was developed using the Viola-Jones object detection framework and Eigen faces to carry out Facial Recognition of students and take record of attendance in classes in a user-friendly and secure manner. The facial recognition ability of the system was tested with 95% accuracy while that of Facial Detection ability gave an accuracy of 78%. The optimum security performance achieved by the system was based on its strong backend and its distinct modular structure.