ATTENDANCE MANAGEMENT SYSTEM BASED ON THE CLOUD WEB APPLICATION WITH THE FUNCTION OF FACE RECOGNITION
Abstract : The problem about checking attendant is the main problem of teacher in nowadays. In order to solve this problem, Many systems have been completely changed due to this evolve to achieve more accurate results. However, in my study, these study still lack of the efficiency about correct the face and students cannot verify or pose to edit the data when there is error in class. With this reason, this research aims to develop the facing attendant system to be more effective and the mechanic of the system which students can easily verify. The experiment of this research is to find the way to recognize the face by using the technique of Android Face Recognition with Deep Learning which can correctly recognize up to 97%. The database is connected to Attendance Management System web server by using cloud storage. The result on screen in real time on the application so that students can verify and check data.
The system uses the Tencent cloud server as the shared cloud virtual host, Nginx1.10.2 as the server, MySQL as the database management system. Use Andriod Studio to implement front-end functionality development. Using the PHP language, the Laravel framework, Laravel-admin completes the backend application development. Baidu Echarts Data Visualization Chart Library to complete the rich and diverse background data analysis and statistics
Required almost 100% accuracy: attendance usually affects students directly. Many schools also require attendance as part of the assessment process. See an example of the course syllabus for EBIO 6300 of the University of Colorado in semester fall-2013 .At FPT polytechnic, the minimum attendance required is 80% (over 30 slots of studying). There are several strategies to solve the problem apart from the special technical efforts such as additional policy, system support, etc.
Constrained because of the environment: installed equipment is mainly used for security purposes instead of attendance taking [20]. The cameras are hung at the intersection in the corridor, such as the elevator hall, corridor corner. The AT must not generate any effects on the existing CCTV system.
Performance of the current methods in a real environment: even if the accuracy of ArcFace ,the highest archive algorithm mentioned in is up to 99.83% on MS-Celeb-1M test set. Algorithms almost work well in an ideal environment, which may not be satisfied in the real settings because of the effect of motion, camera resolution ,light conditions. The attendance taking task may not require to respond in runtime; however, the delay should be as short as possible, or it is feasible to do this by increasing the processing capacity of the system. Meanwhile, most of the high accuracy libraries implement the state-of-the-art in FR asked for high processing time. Ability to integrate with existing systems: attendance taking system has a significant influence on the way the performance of attendees is measured. System integration relates to user habits and operating experience. Therefore, they need to be able to leverage the available resources of existing information systems. Besides, these systems also bring other benefits to the attendance system.
The proposed model is based on face recognition mechanism. The basic methodology is presented in figure 1. Whenever a student enters the class and comes across the camera module of the system his image is captured in the system and is recognized and validated if he is a student of the class. If recognized then his attendance is automatically marked via post processing of the system. The system includes mobile clients and servers. Students use mobile terminals to complete the classroom face recognition real-time attendance, request leave and leave the certificate upload process. Teachers to achieve classroom attendance management, review the Leave list, check attendance information.
It seemed promising and showed that we increase the effectiveness of our system. We propose a full system solution powered by state-of-the-art facial recognition model, from hardware to procedures for handling many streaming videos with unknown faces recorded by CCTV. By taking advantage of multi-process and job scheduling, we also leverage the hardware efficiency of face recognition to minimize system cost but still meet the required response time.
It seemed promising and showed that we increase the effectiveness of our system. We propose a full system solution powered by state-of-the-art facial recognition model, from hardware to procedures for handling many streaming videos with unknown faces recorded by CCTV. By taking advantage of multi-process and job scheduling, we also leverage the hardware efficiency of face recognition to minimize system cost but still meet the required response time.
It seemed promising and showed that we increase the effectiveness of our system. We propose a full system solution powered by state-of-the-art facial recognition model, from hardware to procedures for handling many streaming videos with unknown faces recorded by CCTV. By taking advantage of multi-process and job scheduling, we also leverage the hardware efficiency of face recognition to minimize system cost but still meet the required response time.
It seemed promising and showed that we increase the effectiveness of our system. We propose a full system solution powered by state-of-the-art facial recognition model, from hardware to procedures for handling many streaming videos with unknown faces recorded by CCTV. By taking advantage of multi-process and job scheduling, we also leverage the hardware efficiency of face recognition to minimize system cost but still meet the required response time.
|