Attendance System using Machine Learning-based Face Detection for Meeting Room Application

Abstract

In a modern meeting room, a smart system to make attendance quickly is mandatory. Most of the existing systems perform manual attendance, such as registration and fingerprint. Despite the fingerprint method can reject the Unknown person and give the grant access to the Known person, it will take time to register first a person one-by-one. Moreover, it is possible to create long queues for fingerprint checking before entering the meeting room. Machine learning, along with the Internet of Things (IoT) technology is the best solution; it offers many advantages when applied in the meeting rooms. Generally, the method used is to create a presence by detecting faces. In this paper, we present a facial recognition authentication based on machine learning technology for connection to the meeting rooms. Furthermore, specific website to display the detection result and data storage design testing is developed. The method uses 1) the Dlib library for deep learning purposes, 2) OpenCV for video camera processing, and 3) Face Recognition for Dlib processing. The proposed system allows placing the multiple cameras in a meeting room as needed. However, in this work, we only used one camera as the main system. Tests conducted include identification of one Known person, identification of one Unknown person, identification of two people, and three people. The parameter to be focused is the required time in detecting the number of faces recorded by the camera. The results reveal that the face can be recognized or not recognized, then it will be displayed on the website.

Facial Recognition Technology-Based Attendance Management System Application in Smart Classroom

“…When used in real-time to distinguish faces, it almost eliminates FPs, and as shown in Table 1, its accuracy reaches 94%. This accuracy is acceptable in real-time and educational environments compared to other studies that used this method, such as [50], which faces a problem when there are 2 or 3 people in front of one camera and has a minimum distance of 2 meters to detect faces. This method suffers from two problems.…”