Abstract
Recent advancements in the area of facial recognition and verification introduced thepossibility of facial attendance for various use cases. In this paper we present a system namedas AttendXNet. Our method uses the ResNet and Multi-layer feed forward network to achievethe state of art results. Extensive analysis of various deep learning and machine learningtechniques is described. Face anti-spoofing is a major challenge in facial attendance.Extended-MobileNet is used to resolve the same issue. We also introduced the end to endpipeline to implement an attendance system for various use cases.
Highlights
Attendance is very crucial part in any organization for maintaining the proper workflow.In schools and colleges, lecture attendance normally takes 10 minutes
Facial attendance involves the process of face detection and verification
ML classifiers and distance functions, we found results that were suitable for facial attendance
Summary
Attendance is very crucial part in any organization for maintaining the proper workflow. If we extend our analysis for manual attendance time for a month or year, we found long hours are going into vain. Automatic attendance system is the need of hour where without human intervention attendance can be marked. Facial attendance involves the process of face detection and verification. There are various popular techniques for face detection and verification
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
